DEB htdig: Added to repository.

Signed-off-by: Slávek Banko <[email protected]>

35 files changed, 16288 insertions, 0 deletions

diff --git a/debian/htdig/htdig-3.2.0b6/htcommon/.cvsignore b/debian/htdig/htdig-3.2.0b6/htcommon/.cvsignore
new file mode 100644
index 00000000..09dc8ef2
--- /dev/null
+++ b/debian/htdig/htdig-3.2.0b6/htcommon/.cvsignore
@@ -0,0 +1,7 @@
+Makefile
+*.lo
+*.la
+.purify
+.pure
+.deps
+.libs
diff --git a/debian/htdig/htdig-3.2.0b6/htcommon/DocumentDB.cc b/debian/htdig/htdig-3.2.0b6/htcommon/DocumentDB.cc
new file mode 100644
index 00000000..0ccbf3cb
--- /dev/null
+++ b/debian/htdig/htdig-3.2.0b6/htcommon/DocumentDB.cc
@@ -0,0 +1,655 @@
+//
+// DocumentDB.cc
+//
+// DocumentDB: This class is the interface to the database of document
+//             references. This database is only used while digging.  
+//             An extract of this database is used for searching.  
+//             This is because digging requires a different index
+//             than searching.
+//
+// Part of the ht://Dig package   <http://www.htdig.org/>
+// Copyright (c) 1995-2004 The ht://Dig Group
+// For copyright details, see the file COPYING in your distribution
+// or the GNU Library General Public License (LGPL) version 2 or later
+// <http://www.gnu.org/copyleft/lgpl.html>
+//
+// $Id: DocumentDB.cc,v 1.34 2004/05/28 13:15:12 lha Exp $
+//
+
+#ifdef HAVE_CONFIG_H
+#include "htconfig.h"
+#endif /* HAVE_CONFIG_H */
+
+#include "DocumentDB.h"
+#include "Database.h"
+#include "HtURLCodec.h"
+#include "IntObject.h"
+#include "HtZlibCodec.h"
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <ctype.h>
+
+#ifndef _MSC_VER /* _WIN32 */
+#include <unistd.h>
+#endif
+
+#ifdef HAVE_STD
+#include <iostream>
+#include <fstream>
+#ifdef HAVE_NAMESPACES
+using namespace std;
+#endif
+#else
+#include <iostream.h>
+#include <fstream.h>
+#endif /* HAVE_STD */
+
+#include <errno.h>
+
+//*****************************************************************************
+// DocumentDB::DocumentDB()
+//
+DocumentDB::DocumentDB()
+{
+    isopen = 0;
+    isread = 0;
+
+    // The first document number (NEXT_DOC_ID_RECORD) is used to
+    // store the nextDocID number itself into.  We avoid using
+    // an all-0 key for this, mostly for being superstitious
+    // about letting in bugs.
+    nextDocID = NEXT_DOC_ID_RECORD + 1;
+}
+
+
+//*****************************************************************************
+// DocumentDB::~DocumentDB()
+//
+DocumentDB::~DocumentDB()
+{
+  Close();
+}
+
+
+//*****************************************************************************
+// int DocumentDB::Open(char *filename, char *indexname, char *headname)
+//   We will attempt to open up an existing document database.  If it
+//   doesn't exist, we'll create a new one.  If we are succesful in
+//   opening the database, we need to look for our special record
+//   which contains the next document ID to use.
+//    There may also be an URL -> DocID index database to take
+//   care of, as well as a DocID -> DocHead excerpt database.
+//
+int DocumentDB::Open(const String& filename, const String& indexfilename, const String& headname)
+{
+  // If the database is already open, we'll close it
+  // We might be opening this object with a new filename, so we'll be safe
+  Close();
+
+  dbf = 0;
+  i_dbf = 0;
+  h_dbf = 0;
+
+  i_dbf = Database::getDatabaseInstance(DB_HASH);
+
+  if (i_dbf->OpenReadWrite(indexfilename, 0666) != OK) {
+    cerr << "DocumentDB::Open: " << indexfilename << " " << strerror(errno) << "\n";
+    return NOTOK;
+  }
+
+  h_dbf = Database::getDatabaseInstance(DB_HASH);
+
+  if (h_dbf->OpenReadWrite(headname, 0666) != OK) {
+    cerr << "DocumentDB::Open: " << headname << " " << strerror(errno) << "\n";
+    return NOTOK;
+  }
+
+  dbf = Database::getDatabaseInstance(DB_HASH);
+	
+  if (dbf->OpenReadWrite(filename, 0666) == OK)
+    {
+      String		data;
+      int             specialRecordNumber = NEXT_DOC_ID_RECORD;
+      String          key((char *) &specialRecordNumber,
+			  sizeof specialRecordNumber);
+      if (dbf->Get(key, data) == OK)
+	{
+	  memcpy(&nextDocID, data.get(), sizeof nextDocID);
+	}
+
+      isopen = 1;
+      return OK;
+    }
+  else {
+    cerr << "DocumentDB::Open: " << filename << " " << strerror(errno) << "\n";
+    return NOTOK;
+  }
+}
+
+
+//*****************************************************************************
+// int DocumentDB::Read(char *filename, char *indexname, char *headname)
+//   We will attempt to open up an existing document database,
+//   and accompanying index database and excerpt database
+//
+int DocumentDB::Read(const String& filename, const String& indexfilename , const String& headfilename )
+{
+    // If the database is already open, we'll close it
+    // We might be opening this object with a new filename, so we'll be safe
+    Close();
+
+    dbf = 0;
+    i_dbf = 0;
+    h_dbf = 0;
+
+    if (!indexfilename.empty())
+    {
+	i_dbf = Database::getDatabaseInstance(DB_HASH);
+
+	if (i_dbf->OpenRead(indexfilename) != OK)
+	    return NOTOK;
+    }
+
+    if (!headfilename.empty())
+      {
+	h_dbf = Database::getDatabaseInstance(DB_HASH);
+	
+	if (h_dbf->OpenRead(headfilename) != OK)
+	  return NOTOK;
+      }
+
+    dbf = Database::getDatabaseInstance(DB_HASH);
+	
+    if (dbf->OpenRead(filename) == OK)
+    {
+	isopen = 1;
+	isread = 1;
+	return OK;
+    }
+    else
+	return NOTOK;
+}
+
+
+//*****************************************************************************
+// int DocumentDB::Close()
+//   Close the database.  Before we close it, we first need to update
+//   the special record which keeps track our nextDocID variable.
+//
+int DocumentDB::Close()
+{
+    if (!isopen) return OK;
+
+    if (!isread)
+    {
+	int specialRecordNumber = NEXT_DOC_ID_RECORD;
+	String key((char *) &specialRecordNumber,
+		   sizeof specialRecordNumber);
+	String data((char *) &nextDocID, sizeof nextDocID);
+
+	dbf->Put(key, data);
+    }
+
+    if (i_dbf)
+    {
+	i_dbf->Close();
+	delete i_dbf;
+	i_dbf = 0;
+    }
+    if (h_dbf)
+      {
+	h_dbf->Close();
+	delete h_dbf;
+	h_dbf = 0;
+      }
+
+    dbf->Close();
+    delete dbf;
+    dbf = 0;
+    isopen = 0;
+    isread = 0;
+    return OK;
+}
+
+
+//*****************************************************************************
+// int DocumentDB::Add(DocumentRef &doc)
+//
+int DocumentDB::Add(DocumentRef &doc)
+{
+    int docID = doc.DocID();
+
+    String temp = 0;
+
+    doc.Serialize(temp);
+
+    String key((char *) &docID, sizeof docID);
+    dbf->Put(key, temp);
+
+    if (h_dbf)
+      {
+	if (doc.DocHeadIsSet())
+	  {
+	    temp = HtZlibCodec::instance()->encode(doc.DocHead());
+	    h_dbf->Put(key, temp);
+	  }
+      }
+    else
+      // If there was no excerpt index when we write, something is wrong.
+      return NOTOK;
+
+    if (i_dbf)
+    {
+	temp = doc.DocURL();
+	i_dbf->Put(HtURLCodec::instance()->encode(temp), key);
+	return OK;
+    }
+    else
+      // If there was no index when we write, something is wrong.
+      return NOTOK;
+}
+
+
+//*****************************************************************************
+// int DocumentDB::ReadExcerpt(DocumentRef &ref)
+// We will attempt to access the excerpt for this ref
+//
+int DocumentDB::ReadExcerpt(DocumentRef &ref)
+{
+    String	data;
+    int		docID = ref.DocID();
+    String	key((char *) &docID, sizeof docID);
+
+    if (!h_dbf)
+      return NOTOK;
+    if (h_dbf->Get(key, data) == NOTOK)
+      return NOTOK;
+
+    ref.DocHead((char*)HtZlibCodec::instance()->decode(data));
+
+    return OK;
+}
+
+//*****************************************************************************
+// DocumentRef *DocumentDB::operator [] (int docID)
+//
+DocumentRef *DocumentDB::operator [] (int docID)
+{
+    String			data;
+    String			key((char *) &docID, sizeof docID);
+
+    if (dbf->Get(key, data) == NOTOK)
+      return 0;
+
+    DocumentRef		*ref = new DocumentRef;
+    ref->Deserialize(data);
+    return ref;
+}
+
+
+//*****************************************************************************
+// DocumentRef *DocumentDB::operator [] (const String& u)
+//
+DocumentRef *DocumentDB::operator [] (const String& u)
+{
+    String			data;
+    String			docIDstr;
+
+    // If there is no index db, then just give up 
+    // (do *not* construct a list and traverse it).
+    if (i_dbf == 0)
+      return 0;
+    else
+    {
+	String url(u);
+  
+	if (i_dbf->Get(HtURLCodec::instance()->encode(url), docIDstr) == NOTOK)
+	  return 0;
+    }
+
+    if (dbf->Get(docIDstr, data) == NOTOK)
+      return 0;
+
+    DocumentRef		*ref = new DocumentRef;
+    ref->Deserialize(data);
+    return ref;
+}
+
+//*****************************************************************************
+// int DocumentDB::Exists(int docID)
+//
+int DocumentDB::Exists(int docID)
+{
+    String key((char *) &docID, sizeof docID);
+    return dbf->Exists(key);
+}
+
+//*****************************************************************************
+// int DocumentDB::Delete(int docID)
+//
+int DocumentDB::Delete(int docID)
+{
+    String key((char*) &docID, sizeof docID);
+    String data;
+  
+    if (i_dbf == 0 || dbf->Get(key, data) == NOTOK)
+      return NOTOK;
+  
+    DocumentRef		*ref = new DocumentRef;
+    ref->Deserialize(data);
+    String url = ref->DocURL();
+    delete ref;
+  
+    // We have to be really careful about deleting by URL, we might
+    // have a newer "edition" with the same URL and different DocID
+    String		docIDstr;
+    String		encodedURL = HtURLCodec::instance()->encode(url);
+    if (i_dbf->Get(encodedURL, docIDstr) == NOTOK)
+      return NOTOK;
+
+    // Only delete if we have a match between what we want to delete
+    // and what's in the database
+    if (key == docIDstr && i_dbf->Delete(encodedURL) == NOTOK)
+	return NOTOK;
+  
+    if (h_dbf == 0 || h_dbf->Delete(key) == NOTOK)
+      return NOTOK;
+
+    return dbf->Delete(key);
+}
+
+//*****************************************************************************
+// int DocumentDB::DumpDB(char *filename, int verbose)
+//   Create an extract from our database which can be used by an
+//   external application. The extract will consist of lines with fields
+//   separated by tabs. 
+//
+//   The extract will likely not be sorted by anything in particular
+//
+int DocumentDB::DumpDB(const String& filename, int verbose)
+{
+    DocumentRef	        *ref;
+    List		*descriptions, *anchors;
+    char		*strkey;
+    String		data;
+    FILE		*fl;
+    String		docKey(sizeof(int));
+
+    if((fl = fopen(filename, "w")) == 0) {
+      perror(form("DocumentDB::DumpDB: opening %s for writing",
+		  (const char*)filename));
+      return NOTOK;
+    }
+
+    dbf->Start_Get();
+    while ((strkey = dbf->Get_Next()))
+    {
+	int docID;
+	memcpy(&docID, strkey, sizeof docID);
+
+	docKey = 0;
+	docKey.append((char *) &docID, sizeof docID);
+
+	dbf->Get(docKey, data);
+
+	if (docID != NEXT_DOC_ID_RECORD)
+	{
+	    ref = new DocumentRef;
+	    ref->Deserialize(data);
+	    if (h_dbf)
+	      {
+		h_dbf->Get(docKey,data);
+		ref->DocHead((char*)HtZlibCodec::instance()->decode(data));
+	      }
+	    fprintf(fl, "%d", ref->DocID());
+	    fprintf(fl, "\tu:%s", ref->DocURL());
+	    fprintf(fl, "\tt:%s", ref->DocTitle());
+	    fprintf(fl, "\ta:%d", ref->DocState());
+	    fprintf(fl, "\tm:%d", (int) ref->DocTime());
+	    fprintf(fl, "\ts:%d", ref->DocSize());
+	    fprintf(fl, "\tH:%s", ref->DocHead());
+	    fprintf(fl, "\th:%s", ref->DocMetaDsc());
+	    fprintf(fl, "\tl:%d", (int) ref->DocAccessed());
+	    fprintf(fl, "\tL:%d", ref->DocLinks());
+	    fprintf(fl, "\tb:%d", ref->DocBackLinks());
+	    fprintf(fl, "\tc:%d", ref->DocHopCount());
+	    fprintf(fl, "\tg:%d", ref->DocSig());
+	    fprintf(fl, "\te:%s", ref->DocEmail());
+	    fprintf(fl, "\tn:%s", ref->DocNotification());
+	    fprintf(fl, "\tS:%s", ref->DocSubject());
+	    fprintf(fl, "\td:");
+	    descriptions = ref->Descriptions();
+	    String	*description;
+	    descriptions->Start_Get();
+	    int		first = 1;
+	    while ((description = (String *) descriptions->Get_Next()))
+	    {
+		if (!first)
+		    fprintf(fl, "\001");
+		first = 0;
+		fprintf(fl, "%s", description->get());
+	    }
+	    fprintf(fl, "\tA:");
+	    anchors = ref->DocAnchors();
+	    String	*anchor;
+	    anchors->Start_Get();
+	    first = 1;
+	    while ((anchor = (String *) anchors->Get_Next()))
+	    {
+		if (!first)
+		    fprintf(fl, "\001");
+		first = 0;
+		fprintf(fl, "%s", anchor->get());
+	    }
+	    fprintf(fl, "\n");
+    	    delete ref;
+	}
+    }
+
+    fclose(fl);
+
+    return OK;
+}
+
+//*****************************************************************************
+// int DocumentDB::LoadDB(const String &filename, int verbose)
+//   Load an extract to our database from an ASCII file
+//   The extract will consist of lines with fields separated by tabs. 
+//   The lines need not be sorted in any fashion.
+//
+int DocumentDB::LoadDB(const String& filename, int verbose)
+{
+    FILE	*input;
+    String	docKey(sizeof(int));
+    DocumentRef ref;
+    StringList	descriptions, anchors;
+    char	*token, field;
+    String	data;
+
+    if((input = fopen(filename, "r")) == 0) {
+      perror(form("DocumentDB::LoadDB: opening %s for reading", 
+		  (const char*)filename));
+      return NOTOK;
+    }
+
+    while (data.readLine(input))
+    {
+	token = strtok(data, "\t");
+	if (token == NULL)
+	  continue;
+
+	ref.DocID(atoi(token));
+	
+	if (verbose)
+	  cout << "\t loading document ID: " << ref.DocID() << endl;
+
+	while ( (token = strtok(0, "\t")) )
+	  {
+	    field = *token;
+	    token += 2;
+
+	    if (verbose > 2)
+		cout << "\t field: " << field;
+
+	    switch(field)
+	      {
+	        case 'u': // URL
+		  ref.DocURL(token);
+		  break;
+	        case 't': // Title
+		  ref.DocTitle(token);
+		  break;
+	        case 'a': // State
+		  ref.DocState(atoi(token));
+		  break;
+	        case 'm': // Modified
+		  ref.DocTime(atoi(token));
+		  break;
+	        case 's': // Size
+		  ref.DocSize(atoi(token));
+		  break;
+	        case 'H': // Head
+		  ref.DocHead(token);
+		  break;
+	        case 'h': // Meta Description
+		  ref.DocMetaDsc(token);
+		  break;
+	        case 'l': // Accessed
+		  ref.DocAccessed(atoi(token));
+		  break;
+	        case 'L': // Links
+		  ref.DocLinks(atoi(token));
+		  break;
+	        case 'b': // BackLinks
+		  ref.DocBackLinks(atoi(token));
+		  break;
+	        case 'c': // HopCount
+		  ref.DocHopCount(atoi(token));
+		  break;
+	        case 'g': // Signature
+		  ref.DocSig(atoi(token));
+		  break;
+	        case 'e': // E-mail
+		  ref.DocEmail(token);
+		  break;
+	        case 'n': // Notification
+		  ref.DocNotification(token);
+		  break;
+	        case 'S': // Subject
+		  ref.DocSubject(token);
+		  break;
+	        case 'd': // Descriptions
+		  descriptions.Create(token, '\001');
+		  ref.Descriptions(descriptions);
+		  break;
+	        case 'A': // Anchors
+		  anchors.Create(token, '\001');
+		  ref.DocAnchors(anchors);
+		  break;
+	        default:
+		  break;
+	      }
+
+	  }
+	
+
+	// We must be careful if the document already exists
+	// So we'll delete the old document and add the new one
+	if (Exists(ref.DocID()))
+	  {
+	    Delete(ref.DocID());
+	  }
+	Add(ref);
+
+	// If we add a record with an ID past nextDocID, update it
+	if (ref.DocID() > nextDocID)
+	  nextDocID = ref.DocID() + 1;
+
+	descriptions.Destroy();
+	anchors.Destroy();
+    }
+
+    fclose(input);
+    return OK;
+}
+
+//*****************************************************************************
+// List *DocumentDB::URLs()
+//   Return a list of all the URLs in the database
+//   Only available when there's an URL -> DocID index db handy.
+//
+List *DocumentDB::URLs()
+{
+    List	*list = new List;
+    char	*coded_key;
+
+    if (i_dbf == 0)
+	return 0;
+
+    i_dbf->Start_Get();
+    while ((coded_key = i_dbf->Get_Next()))
+    {
+	String *key = new String(HtURLCodec::instance()->decode(coded_key));
+	list->Add(key);
+    }
+    return list;
+}
+
+
+//*****************************************************************************
+// List *DocumentDB::DocIDs()
+//   Return a list of all the DocIDs in the database
+//
+List *DocumentDB::DocIDs()
+{
+    List	*list = new List;
+    char	*key;
+
+    dbf->Start_Get();
+    while ((key = dbf->Get_Next()))
+    {
+	int	    docID;
+	memcpy (&docID, key, sizeof docID);
+
+	if (docID != NEXT_DOC_ID_RECORD)
+	    list->Add(new IntObject(docID));
+    }
+    return list;
+}
+
+//*****************************************************************************
+// private
+// int readLine(FILE *in, String &line)
+//
+int readLine(FILE *in, String &line)
+{
+    char	buffer[2048];
+    int		length;
+    
+    line = 0;
+    while (fgets(buffer, sizeof(buffer), in))
+    {
+	length = strlen(buffer);
+	if (buffer[length - 1] == '\n')
+	{
+	    //
+	    // A full line has been read.  Return it.
+	    //
+	    line << buffer;
+	    line.chop('\n');
+	    return 1;
+	}
+	else
+	{
+	    //
+	    // Only a partial line was read.  Append it to the line
+	    // and read some more.
+	    //
+	    line << buffer;
+	}
+    }
+    return line.length() > 0;
+}
+
+// End of DocumentDB.cc
diff --git a/debian/htdig/htdig-3.2.0b6/htcommon/DocumentDB.h b/debian/htdig/htdig-3.2.0b6/htcommon/DocumentDB.h
new file mode 100644
index 00000000..51ade173
--- /dev/null
+++ b/debian/htdig/htdig-3.2.0b6/htcommon/DocumentDB.h
@@ -0,0 +1,96 @@
+//
+// DocumentDB.h
+//
+// DocumentDB: This class is the interface to the database of document
+//             references. This database is only used while digging.  
+//             An extract of this database is used for searching.  
+//             This is because digging requires a different index
+//             than searching.
+//
+// Part of the ht://Dig package   <http://www.htdig.org/>
+// Copyright (c) 1995-2004 The ht://Dig Group
+// For copyright details, see the file COPYING in your distribution
+// or the GNU Library General Public License (LGPL) version 2 or later
+// <http://www.gnu.org/copyleft/lgpl.html>
+//
+// $Id: DocumentDB.h,v 1.14 2004/05/28 13:15:12 lha Exp $
+//
+
+#ifndef _DocumentDB_h_
+#define _DocumentDB_h_
+
+#include "DocumentRef.h"
+#include "List.h"
+#include "Database.h"
+#include "IntObject.h"
+
+/* This is where the running document counter is stored.
+   The first real document number is the next. */
+#define NEXT_DOC_ID_RECORD 1
+
+
+class DocumentDB
+{
+public:
+    //
+    // Construction/Destruction
+    //
+    DocumentDB();
+    ~DocumentDB();
+
+
+    //
+    // Standard database operations
+    //
+    int			Open(const String& filename, const String& indexfilename, const String& headname);
+    int			Read(const String& filename, const String& indexfilename = 0, const String& headfilename = 0);
+    int			Close();
+
+    int			Add(DocumentRef &);
+    // These do not read in the excerpt
+    DocumentRef		*operator [] (int DocID);
+    DocumentRef		*operator [] (const String& url);
+    // You must call this to read the excerpt
+    int			ReadExcerpt(DocumentRef &);
+    int			Exists(int DocID);
+    int			Delete(int DocID);
+
+    //
+    // The database keeps track of document ids.  Here is a way to get
+    // the next document id.
+    //
+    int			NextDocID()		{return nextDocID++;}
+
+    // And here's a way to increment NextDocID after adding lots of records
+    // (for example when merging databases!)
+    void                IncNextDocID (int next)     {nextDocID += next;}
+
+    //
+    // We will need to be able to iterate over the complete database.
+    //
+
+    // This returns a list of all the URLs, as String *
+    List		*URLs();
+
+    // This returns a list of all the DocIDs, as IntObject *
+    List		*DocIDs();
+
+    // Dump the database out to an ASCII text file
+    int			DumpDB(const String& filename, int verbose = 0);
+
+    // Read in the database from an ASCII text file
+    // (created by DumpDB)
+    int			LoadDB(const String& filename, int verbose = 0);
+
+private:
+    Database		*dbf;
+    Database		*i_dbf;
+    Database		*h_dbf;
+    int			isopen;
+    int			isread;
+    int			nextDocID;
+};
+
+#endif
+
+
diff --git a/debian/htdig/htdig-3.2.0b6/htcommon/DocumentRef.cc b/debian/htdig/htdig-3.2.0b6/htcommon/DocumentRef.cc
new file mode 100644
index 00000000..97900cd3
--- /dev/null
+++ b/debian/htdig/htdig-3.2.0b6/htcommon/DocumentRef.cc
@@ -0,0 +1,547 @@
+//
+// DocumentRef.cc
+//
+// DocumentRef: Reference to an indexed document. Keeps track of all
+//              information stored on the document, either by the dig 
+//              or temporary search information.
+//
+// Part of the ht://Dig package   <http://www.htdig.org/>
+// Copyright (c) 1995-2004 The ht://Dig Group
+// For copyright details, see the file COPYING in your distribution
+// or the GNU Library General Public License (LGPL) version 2 or later
+// <http://www.gnu.org/copyleft/lgpl.html>
+//
+// $Id: DocumentRef.cc,v 1.53 2004/05/28 13:15:12 lha Exp $
+//
+
+#ifdef HAVE_CONFIG_H
+#include "htconfig.h"
+#endif /* HAVE_CONFIG_H */
+
+#include "DocumentRef.h"
+#include "good_strtok.h"
+#include "WordRecord.h"
+#include "HtConfiguration.h"
+#include "HtURLCodec.h"
+#include "WordType.h"
+#include "HtWordReference.h"
+#include <stdlib.h>
+#include <ctype.h>
+
+#ifdef HAVE_STD
+#include <fstream>
+#ifdef HAVE_NAMESPACES
+using namespace std;
+#endif
+#else
+#include <fstream.h>
+#endif /* HAVE_STD */
+
+// extern HtConfiguration config;
+
+//*****************************************************************************
+// DocumentRef::DocumentRef()
+//
+DocumentRef::DocumentRef()
+{
+    Clear();
+}
+
+
+//*****************************************************************************
+// DocumentRef::~DocumentRef()
+//
+DocumentRef::~DocumentRef()
+{
+}
+
+
+//*****************************************************************************
+// void DocumentRef::Clear()
+//
+void DocumentRef::Clear()
+{
+  docID = 0;
+  docURL = 0;
+  docTime = 0;
+  docAccessed = 0;
+  docHead = 0;
+  docHeadIsSet = 0;
+  docMetaDsc = 0;
+  docTitle = 0;
+  descriptions.Destroy();
+  docState = Reference_normal;
+  docSize = 0;
+  docLinks = 0;
+  docBackLinks = 0;
+  docAnchors.Destroy();
+  docHopCount = 0;
+  docSig = 0;
+  docEmail = 0;
+  docNotification = 0;
+  docSubject = 0;
+  docScore = 0;
+  docAnchor = 0;
+}
+
+//*****************************************************************************
+// void DocumentRef::DocState(int s)
+//
+void DocumentRef::DocState(int s)
+{
+  // You can't easily do this with a cast, so we'll use a switch
+  switch(s)
+    {
+      case 0:
+	docState = Reference_normal;
+	break;
+      case 1:
+	docState = Reference_not_found;
+	break;
+      case 2:
+	docState = Reference_noindex;
+	break;
+      case 3:
+	docState = Reference_obsolete;
+	break;
+    }
+}
+
+
+enum
+{
+    DOC_ID,				// 0
+    DOC_TIME,				// 1
+    DOC_ACCESSED,			// 2
+    DOC_STATE,				// 3
+    DOC_SIZE,				// 4
+    DOC_LINKS,				// 5
+    DOC_IMAGESIZE,			// 6 -- No longer used
+    DOC_HOPCOUNT,			// 7
+    DOC_URL,				// 8
+    DOC_HEAD,				// 9
+    DOC_TITLE,				// 10
+    DOC_DESCRIPTIONS,	        	// 11
+    DOC_ANCHORS,			// 12
+    DOC_EMAIL,				// 13
+    DOC_NOTIFICATION,		        // 14
+    DOC_SUBJECT,			// 15
+    DOC_STRING,                         // 16
+    DOC_METADSC,                        // 17
+    DOC_BACKLINKS,                      // 18
+    DOC_SIG                             // 19
+};
+
+// Must be powers of two never reached by the DOC_... enums.
+#define CHARSIZE_MARKER_BIT 64
+#define SHORTSIZE_MARKER_BIT 128
+
+//*****************************************************************************
+// void DocumentRef::Serialize(String &s)
+//   Convert all the data in the object to a string. 
+//   The data is in the string is tagged with 
+//
+void DocumentRef::Serialize(String &s)
+{
+    int		length;
+    String	*str;
+
+//
+// The following macros make the serialization process a little easier
+// to follow.  Note that if an object to be serialized has the default
+// value for this class, it it NOT serialized.  This means that
+// storage will be saved...
+//
+#define addnum(id, out, var) \
+ if (var != 0)                                                        \
+ {                                                                    \
+   if (var <= (unsigned char) ~1)                                     \
+   {                                                                  \
+     unsigned char _tmp = var;                                        \
+     out << (char) (id | CHARSIZE_MARKER_BIT);                        \
+     out.append((char *) &_tmp, sizeof(_tmp));                        \
+   }                                                                  \
+   else if (var <= (unsigned short int) ~1)                           \
+   {                                                                  \
+     unsigned short int _tmp = var;                                   \
+     out << (char) (id | SHORTSIZE_MARKER_BIT);                       \
+     out.append((char *) &_tmp, sizeof(_tmp));                        \
+   }                                                                  \
+   else                                                               \
+   {                                                                  \
+     out << (char) id;                                                \
+     out.append((char *) &var, sizeof(var));                          \
+   }                                                                  \
+ }
+
+#define	addstring(id, out, str)	\
+ if (str.length())                                                    \
+ {                                                                    \
+   length = str.length();                                             \
+   if (length <= (unsigned char) ~1)                                  \
+   {                                                                  \
+     unsigned char _tmp = length;                                     \
+     out << (char) (id | CHARSIZE_MARKER_BIT);                        \
+     out.append((char *) &_tmp, sizeof(_tmp));                        \
+   }                                                                  \
+   else if (length <= (unsigned short int) ~1)                        \
+   {                                                                  \
+     unsigned short int _tmp = length;                                \
+     out << (char) (id | SHORTSIZE_MARKER_BIT);                       \
+     out.append((char *) &_tmp, sizeof(_tmp));                        \
+   }                                                                  \
+   else                                                               \
+   {                                                                  \
+     out << (char) id;                                                \
+     out.append((char *) &length, sizeof(length));                    \
+   }                                                                  \
+   out.append(str);                                                   \
+ }
+
+// To keep compatibility with old databases, don't bother
+// with long lists at all.  Bloat the size for long strings with
+// one char to just keep a ~1 marker since we don't know the
+// endianness; we don't know where to put a endian-safe
+// size-marker, and we probably rather want the full char to
+// keep the length.  Only strings shorter than (unsigned char) ~1 
+// will be "optimized"; trying to optimize strings that fit in
+// (unsigned short) does not seem to give anything substantial.
+#define	addlist(id, out, list) \
+ if (list.Count())                                                    \
+ {                                                                    \
+   length = list.Count();                                             \
+   if (length <= (unsigned short int) ~1)                             \
+   {                                                                  \
+     if (length <= (unsigned char) ~1)                                \
+     {                                                                \
+       unsigned char _tmp = length;                                   \
+       out << (char) (id | CHARSIZE_MARKER_BIT);                      \
+       out.append((char *) &_tmp, sizeof(_tmp));                      \
+     }                                                                \
+     else                                                             \
+     {                                                                \
+       unsigned short int _tmp = length;                              \
+       out << (char) (id | SHORTSIZE_MARKER_BIT);                     \
+       out.append((char *) &_tmp, sizeof(_tmp));                      \
+     }                                                                \
+     list.Start_Get();                                                \
+     while ((str = (String *) list.Get_Next()))		              \
+     {                                                                \
+       length = str->length();                                        \
+       if (length < (unsigned char) ~1)                               \
+       {                                                              \
+         unsigned char _tmp = length;                                 \
+         out.append((char*) &_tmp, sizeof(_tmp));                     \
+       }                                                              \
+       else                                                           \
+       {                                                              \
+         unsigned char _tmp = ~1;                                     \
+         out.append((char*) &_tmp, sizeof(_tmp));                     \
+         out.append((char*) &length, sizeof(length));                 \
+       }                                                              \
+       out.append(*str);                                              \
+     }                                                                \
+   }                                                                  \
+   else                                                               \
+   {                                                                  \
+     out << (char) id;                                                \
+     out.append((char *) &length, sizeof(length));                    \
+     list.Start_Get();                                                \
+     while ((str = (String *) list.Get_Next()))                       \
+     {                                                                \
+       length = str->length();                                        \
+       out.append((char*) &length, sizeof(length));                   \
+       out.append(*str);                                              \
+     }                                                                \
+   }                                                                  \
+ }
+
+    addnum(DOC_ID, s, docID);
+    addnum(DOC_TIME, s, docTime);
+    addnum(DOC_ACCESSED, s, docAccessed);
+    addnum(DOC_STATE, s, docState);
+    addnum(DOC_SIZE, s, docSize);
+    addnum(DOC_LINKS, s, docLinks);
+    addnum(DOC_BACKLINKS, s, docBackLinks);
+    addnum(DOC_HOPCOUNT, s, docHopCount);
+    addnum(DOC_SIG, s, docSig);
+
+    // Use a temporary since the addstring macro will evaluate
+    // this multiple times.
+    String tmps = HtURLCodec::instance()->encode(docURL);
+    addstring(DOC_URL, s, tmps);
+    // This is done in the DocumentDB code through the excerpt database
+    //    addstring(DOC_HEAD, s, docHead);
+    addstring(DOC_METADSC, s, docMetaDsc);
+    addstring(DOC_TITLE, s, docTitle);
+
+    addlist(DOC_DESCRIPTIONS, s, descriptions);
+    addlist(DOC_ANCHORS, s, docAnchors);
+
+    addstring(DOC_EMAIL, s, docEmail);
+    addstring(DOC_NOTIFICATION, s, docNotification);
+    addstring(DOC_SUBJECT, s, docSubject);
+}
+
+
+//*****************************************************************************
+// void DocumentRef::Deserialize(String &stream)
+//   Extract the contents of our private variables from the given
+//   character string.  The character string is expected to have been
+//   created using the Serialize member.
+//
+void DocumentRef::Deserialize(String &stream)
+{
+    Clear();
+    char	*s = stream.get();
+    char	*end = s + stream.length();
+    int		length;
+    int		count;
+    int		i;
+    int		x;
+    int		throwaway; // As the name sounds--used for old fields
+    String	*str;
+
+// There is a problem with getting a numeric value into a
+// numeric unknown type that may be an enum (the other way
+// around is simply by casting (int)).
+//  Supposedly the enum incarnates as a simple type, so we can
+// just check the size and copy the bits.
+#define MEMCPY_ASSIGN(to, from, type) \
+ do {                                                                 \
+   type _tmp = (type) (from);                                         \
+   memcpy((char *) &(to), (char *) &_tmp, sizeof(to));                \
+ } while (0)
+
+#define NUM_ASSIGN(to, from) \
+ do {                                                                 \
+   if (sizeof(to) == sizeof(unsigned long int))                       \
+     MEMCPY_ASSIGN(to, from, unsigned long int);                      \
+   else if (sizeof(to) == sizeof(unsigned int))                       \
+     MEMCPY_ASSIGN(to, from, unsigned int);                           \
+   else if (sizeof(to) == sizeof(unsigned short int))                 \
+     MEMCPY_ASSIGN(to, from, unsigned short int);                     \
+   else if (sizeof(to) == sizeof(unsigned char))                      \
+     MEMCPY_ASSIGN(to, from, unsigned char);                          \
+   /* else fatal error here? */                                       \
+ } while (0)
+
+#define	getnum(type, in, var) \
+ if (type & CHARSIZE_MARKER_BIT)                                      \
+ {                                                                    \
+   NUM_ASSIGN(var, *(unsigned char *) in);                            \
+   in += sizeof(unsigned char);                                       \
+ }                                                                    \
+ else if (type & SHORTSIZE_MARKER_BIT)                                \
+ {                                                                    \
+   unsigned short int _tmp0;                                          \
+   memcpy((char *) &_tmp0, (char *) (in), sizeof(unsigned short));    \
+   NUM_ASSIGN(var, _tmp0);                                            \
+   in += sizeof(unsigned short int);                                  \
+ }                                                                    \
+ else                                                                 \
+ {                                                                    \
+   memcpy((char *) &var, in, sizeof(var));                            \
+   in += sizeof(var);                                                 \
+ }
+
+#define	getstring(type, in, str) \
+ getnum(type, in, length);                                            \
+ str = 0;                                                             \
+ str.append(in, length);                                              \
+ in += length
+
+#define	getlist(type, in, list) \
+ getnum(type, in, count);                                             \
+ if (type & (CHARSIZE_MARKER_BIT | SHORTSIZE_MARKER_BIT))             \
+ {                                                                    \
+   for (i = 0; i < count; i++)                                        \
+   {                                                                  \
+     unsigned char _tmp = *(unsigned char *) in;                      \
+     in += sizeof(_tmp);                                              \
+     if (_tmp < (unsigned char) ~1)                                   \
+       length = _tmp;                                                 \
+     else                                                             \
+       getnum(~(CHARSIZE_MARKER_BIT | SHORTSIZE_MARKER_BIT), in,      \
+              length);                                                \
+     str = new String;                                                \
+     str->append(in, length);                                         \
+     list.Add(str);                                                   \
+     in += length;                                                    \
+   }                                                                  \
+ }                                                                    \
+ else                                                                 \
+ {                                                                    \
+   for (i = 0; i < count; i++)                                        \
+   {                                                                  \
+     getnum(~(CHARSIZE_MARKER_BIT | SHORTSIZE_MARKER_BIT), in,        \
+            length);                                                  \
+     str = new String;                                                \
+     str->append(in, length);                                         \
+     list.Add(str);                                                   \
+     in += length;                                                    \
+   }                                                                  \
+ }
+
+    while (s < end)
+    {
+        x = (unsigned char) *s++;
+        switch (x & ~(CHARSIZE_MARKER_BIT | SHORTSIZE_MARKER_BIT))
+        {
+        case DOC_ID:
+            getnum(x, s, docID);
+            break;
+        case DOC_TIME:
+            getnum(x, s, docTime);
+            break;
+        case DOC_ACCESSED:
+            getnum(x, s, docAccessed);
+            break;
+        case DOC_STATE:
+            getnum(x, s, docState);
+            break;
+        case DOC_SIZE:
+            getnum(x, s, docSize);
+            break;
+        case DOC_IMAGESIZE: // No longer used
+	    getnum(x, s, throwaway);
+	    break;
+        case DOC_LINKS:
+            getnum(x, s, docLinks);
+            break;
+        case DOC_HOPCOUNT:
+            getnum(x, s, docHopCount);
+            break;
+	case DOC_BACKLINKS:
+	    getnum(x, s, docBackLinks);
+	    break;
+	case DOC_SIG:
+	    getnum(x, s, docSig);
+	    break;
+        case DOC_URL:
+	    {
+	      // Use a temporary since the addstring macro will evaluate
+	      // this multiple times.
+	      String tmps;
+	      getstring(x, s, tmps);
+
+	      docURL = HtURLCodec::instance()->decode(tmps);
+	    }
+	    break;
+        case DOC_HEAD:
+            getstring(x, s, docHead); docHeadIsSet = 1;
+            break;
+	case DOC_METADSC:
+	    getstring(x, s, docMetaDsc);
+	    break;
+        case DOC_TITLE:
+            getstring(x, s, docTitle);
+            break;
+        case DOC_DESCRIPTIONS:
+            getlist(x, s, descriptions);
+            break;
+        case DOC_ANCHORS:
+            getlist(x, s, docAnchors);
+            break;
+        case DOC_EMAIL:
+            getstring(x, s, docEmail);
+            break;
+        case DOC_NOTIFICATION:
+            getstring(x, s, docNotification);
+            break;
+        case DOC_SUBJECT:
+            getstring(x, s, docSubject);
+            break;
+	case DOC_STRING:
+	  // This is just a debugging string. Ignore it.
+	    break;
+        default:
+            cerr << "BAD TAG IN SERIALIZED DATA: " << x << endl;
+            return;
+        }
+    }
+}
+
+
+//*****************************************************************************
+// void DocumentRef::AddDescription(char *d, HtWordList &words)
+//
+void DocumentRef::AddDescription(const char *d, HtWordList &words)
+{
+    if (!d || !*d)
+        return;
+
+    while (isspace(*d))
+        d++;
+   
+   if (!d || !*d)
+     return;
+
+    String	desc = d;
+    desc.chop(" \t");
+
+    // Add the description text to the word database with proper factor
+    // Do this first because we may have reached the max_description limit
+    // This also ensures we keep the proper weight on descriptions 
+    // that occur many times
+
+    // Parse words.
+    char         *p                   = desc;
+    HtConfiguration* config= HtConfiguration::config();
+    static int    minimum_word_length = config->Value("minimum_word_length", 3);
+    static int    max_descriptions    = config->Value("max_descriptions", 5);
+
+    String word;
+    HtWordReference wordRef;
+    wordRef.Flags(FLAG_LINK_TEXT);
+    wordRef.DocID(docID);
+
+    while (*p)
+    {
+      // Reset contents before adding chars each round.
+      word = 0;
+
+      while (*p && HtIsWordChar(*p))
+        word << *p++;
+
+      HtStripPunctuation(word);
+
+      if (word.length() >= minimum_word_length) {
+        // The wordlist takes care of lowercasing; just add it.
+	wordRef.Location((p - (char*)desc) - word.length());
+	wordRef.Word(word);
+        words.Replace(wordRef);
+      }
+
+      while (*p && !HtIsStrictWordChar(*p))
+        p++;
+    }
+
+    // And let's flush the words! (nice comment hu :-)
+    words.Flush();
+    
+    // Now are we at the max_description limit?
+    if (descriptions.Count() >= max_descriptions)
+  	return;
+  	
+    descriptions.Start_Get();
+    String	*description;
+    while ((description = (String *) descriptions.Get_Next()))
+    {
+        if (mystrcasecmp(description->get(), (char*)desc) == 0)
+            return;
+    }
+    descriptions.Add(new String(desc));
+}
+
+
+//*****************************************************************************
+// void DocumentRef::AddAnchor(char *a)
+//
+void DocumentRef::AddAnchor(const char *a)
+{
+    if (a)
+    	docAnchors.Add(new String(a));
+}
+
+
diff --git a/debian/htdig/htdig-3.2.0b6/htcommon/DocumentRef.h b/debian/htdig/htdig-3.2.0b6/htcommon/DocumentRef.h
new file mode 100644
index 00000000..446ff6f7
--- /dev/null
+++ b/debian/htdig/htdig-3.2.0b6/htcommon/DocumentRef.h
@@ -0,0 +1,171 @@
+//
+// DocumentRef.h
+//
+// DocumentRef: Reference to an indexed document. Keeps track of all
+//              information stored on the document, either by the dig 
+//              or temporary search information.
+//
+// Part of the ht://Dig package   <http://www.htdig.org/>
+// Copyright (c) 1995-2004 The ht://Dig Group
+// For copyright details, see the file COPYING in your distribution
+// or the GNU Library General Public License (LGPL) version 2 or later
+// <http://www.gnu.org/copyleft/lgpl.html>
+//
+// $Id: DocumentRef.h,v 1.29 2004/05/28 13:15:12 lha Exp $
+//
+
+#ifndef _DocumentRef_h_
+#define _DocumentRef_h_
+
+#include "htString.h"
+#include "List.h"
+#include "HtWordList.h"
+
+#include <time.h>
+
+enum ReferenceState
+{
+    Reference_normal,
+    Reference_not_found,
+    Reference_noindex,
+    Reference_obsolete
+};
+
+class DocumentRef : public Object
+{
+    public:
+    //
+    // Construction/Destruction
+    //
+    DocumentRef();
+    ~DocumentRef();
+
+    //
+    // A DocumentRef can read itself from a character string and
+    // convert itself into a character string
+    //
+    void		Serialize(String &s);
+    void		Deserialize(String &s);
+
+    //
+    // Access to the members
+    //
+    int			DocID()				{return docID;}
+    char		*DocURL()			{return docURL;}
+    time_t		DocTime()			{return docTime;}
+    char		*DocTitle()			{return docTitle;}
+    char		*DocAuthor()			{return docAuthor;}
+    char		*DocHead()			{return docHead;}
+    int			DocHeadIsSet()			{return docHeadIsSet;}
+    char                *DocMetaDsc()                   {return docMetaDsc;}
+    time_t		DocAccessed()			{return docAccessed;}
+    int			DocLinks()			{return docLinks;}
+    int                 DocBackLinks()                  {return docBackLinks;}
+    List		*Descriptions()			{return &descriptions;}
+    ReferenceState	DocState()			{return docState;}
+    int			DocSize()			{return docSize;}
+    List		*DocAnchors()			{return &docAnchors;}
+    double     		DocScore()			{return docScore;}
+    int                 DocSig()                        {return docSig;}
+    int			DocAnchor()			{return docAnchor;}
+    int			DocHopCount()			{return docHopCount;}
+    char		*DocEmail()			{return docEmail;}
+    char		*DocNotification()		{return docNotification;}
+    char		*DocSubject()			{return docSubject;}
+	
+    void		DocID(int d)			{docID = d;}
+    void		DocURL(const char *u)		{docURL = u;}
+    void		DocTime(time_t t)		{docTime = t;}
+    void		DocTitle(const char *t)		{docTitle = t;}
+    void		DocAuthor(const char *a)	{docAuthor = a;}
+    void		DocHead(const char *h)		{docHeadIsSet = 1; docHead = h;}
+    void                DocMetaDsc(const char *md)      {docMetaDsc = md;}
+    void		DocAccessed(time_t t)		{docAccessed = t;}
+    void		DocLinks(int l)			{docLinks = l;}
+    void                DocBackLinks(int l)             {docBackLinks = l;}
+    void		Descriptions(List &l)		{descriptions = l;}
+    void		AddDescription(const char *d, HtWordList &words);
+    void		DocState(ReferenceState s)	{docState = s;}
+    void		DocState(int s);
+    void		DocSize(int s)			{docSize = s;}
+    void                DocSig(int s)                   {docSig = s;}
+    void		DocAnchors(List &l)		{docAnchors = l;}
+    void		AddAnchor(const char *a);
+    void		DocScore(double s)		{docScore = s;}
+    void		DocAnchor(int a)		{docAnchor = a;}
+    void		DocHopCount(int h)		{docHopCount = h;}
+    void		DocEmail(const char *e)		{docEmail = e;}
+    void		DocNotification(const char *n)	{docNotification = n;}
+    void		DocSubject(const char *s)	{docSubject = s;}
+	
+    void		Clear();			// Reset everything
+
+    protected:
+    //
+    // These values will be stored when serializing
+    //
+
+    // This is the index number of the document in the database.
+    int			docID;
+    // This is the URL of the document.
+    String		docURL;
+    // This is the time specified in the document's header
+    // Usually that's the last modified time, for servers that return it.
+    time_t		docTime;
+    // This is the time that the last retrieval occurred.
+    time_t		docAccessed;
+    // This is the stored excerpt of the document, just text.
+    String		docHead;
+    // This indicates if the stored excerpt of the document has been set.
+    int			docHeadIsSet;
+    // This is the document-specified description.
+    // For HTML, that's the META description tag.
+    String              docMetaDsc;
+    // This is the title of the document.
+    String		docTitle;
+    // This is the author of the document, as specified in meta information
+    String		docAuthor;
+    // This is a list of Strings, the text of links pointing to this document.
+    // (e.g. <a href="docURL">description</a>
+    List		descriptions;
+    // This is the state of the document--modified, normal, etc.
+    ReferenceState	docState;
+    // This is the size of the original document.
+    int			docSize;
+    // This is a count of the links in the document (outgoing links).
+    int			docLinks;
+    // This is a count of the links to the document (incoming links).
+    int                 docBackLinks;
+    // This is a list of the anchors in the document (i.e. <A NAME=...)
+    List		docAnchors;
+    // This is a count of the number of hops from start_urls to here.
+    int			docHopCount;
+    // This is a signature of the document. (e.g. md5sum, checksum...)
+    // This is currently unused.
+    long int		docSig;
+	
+    //
+    // The following values are for the email notification of expiration
+    //
+
+    // This is the email destination for htnotify.
+    String		docEmail;
+    // This is the date that htnotify should use as comparison.
+    String		docNotification;
+    // This is the subject of the email sent out by htnotify.
+    String		docSubject;
+
+    //
+    // This is used for searching and is not stored in the database
+    //
+    
+    // This is the current score of this document.
+    double			docScore;
+    // This is the nearest anchor for the search word.
+    int			docAnchor;
+
+};
+
+#endif
+
+
diff --git a/debian/htdig/htdig-3.2.0b6/htcommon/HtConfiguration.cc b/debian/htdig/htdig-3.2.0b6/htcommon/HtConfiguration.cc
new file mode 100644
index 00000000..ad3ce4f6
--- /dev/null
+++ b/debian/htdig/htdig-3.2.0b6/htcommon/HtConfiguration.cc
@@ -0,0 +1,271 @@
+//
+// HtConfiguration.cc
+//
+//             HtConfiguration: extends Configuration class
+//             to implement Apache-style config. Uses parser
+//             generated by Bison from conf_parser.yxx
+//
+// Part of the ht://Dig package   <http://www.htdig.org/>
+// Copyright (c) 1995-2004 The ht://Dig Group
+// For copyright details, see the file COPYING in your distribution
+// or the GNU Library General Public License (LGPL) version 2 or later
+// <http://www.gnu.org/copyleft/lgpl.html>
+//
+// $Id: HtConfiguration.cc,v 1.10 2004/05/28 13:15:12 lha Exp $
+//
+
+#ifdef HAVE_CONFIG_H
+#include "htconfig.h"
+#endif /* HAVE_CONFIG_H */
+
+#include <stdio.h>
+#include "HtConfiguration.h"
+#include <stdlib.h>
+
+#ifdef HAVE_STD
+#include <fstream>
+#ifdef HAVE_NAMESPACES
+using namespace std;
+#endif
+#else
+#include <fstream.h>
+#endif /* HAVE_STD */
+
+#include <stdlib.h>
+#include <ctype.h>
+#include <locale.h>
+
+
+//********************************************************************
+//  Add complex entry to the configuration
+//
+void
+HtConfiguration::Add(const char *name, const char *value, Configuration *aList) {
+
+  if (strcmp("url",name)==0) {  //add URL entry
+    URL tmpUrl(strdup(value));
+	Dictionary *paths= NULL;
+    if ( (paths=(Dictionary *)dcUrls[tmpUrl.host()]) ) {
+      paths->Add(tmpUrl.path(),aList);
+    } else {
+      paths=new Dictionary();
+      paths->Add(tmpUrl.path(),aList);
+      dcUrls.Add(tmpUrl.host(),paths);
+    }
+    } else {
+
+      Object *treeEntry=dcBlocks[name];
+      if (treeEntry!=NULL) {
+	((Dictionary *)treeEntry)->Add(value,aList);
+      } else {
+	treeEntry=new Dictionary(16);
+	((Dictionary *)treeEntry)->Add(value,aList);
+	dcBlocks.Add(name, treeEntry);
+      }
+    }
+}
+
+//*********************************************************************
+const String HtConfiguration::Find(const char *blockName,const char *name,const char *value) const
+{
+  if (!(blockName && name && value) )
+    return String();
+  union {
+    void      *ptr;
+    Object *obj;
+    Dictionary *dict;
+    HtConfiguration *conf;
+  } tmpPtr;
+  String chr;
+  
+  if (strcmp("url",blockName)==0) { // URL needs special compare
+    URL paramUrl(name);     // split URL to compare separatly host and path
+    chr=Find(&paramUrl,value);
+    if (chr[0]!=0) {
+      return chr;
+    }
+    }
+    else { // end "server"
+      tmpPtr.obj=dcBlocks.Find(blockName);
+      if (tmpPtr.ptr) {
+	tmpPtr.obj = tmpPtr.dict->Find(name);
+	if (tmpPtr.ptr) {
+	  chr = tmpPtr.conf->Find(value);
+	  if (chr[0] != 0)
+		return chr;
+	}
+      }
+    }
+ 
+  // If this parameter is defined in global then return it
+  chr=Find(value);
+  if (chr[0]!=0) {
+    return chr;
+  }
+#ifdef DEBUG
+  cerr << "Could not find configuration option " << blockName<<":"
+       <<name<<":"<<value<< "\n";
+#endif
+  return String();
+}
+
+//*********************************************************************
+//
+const String HtConfiguration::Find(URL *aUrl, const char *value) const
+{
+ if (!aUrl)
+    return String();
+  Dictionary *tmpPtr=(Dictionary *)dcUrls.Find( aUrl->host() );
+  if (tmpPtr) {       // We've got such host in config
+    tmpPtr->Start_Get();
+    // Try to find best matched URL
+    //
+    struct candidate {
+      Object		*obj;
+      unsigned int	len;
+      String		value;
+    } candidate;
+    candidate.len=0; 
+    String returnValue;
+    // Begin competition: which URL is better?
+    //
+    // TODO: move this loop into Dictionary
+    // (or create Dictionary::FindBest ?)
+    // or make url list sorted ?
+    // or implement abstract Dictionary::Compare?
+    const char *strParamUrl=(const char *)aUrl->path();
+    char* confUrl= NULL;
+    bool found(false);
+    while ((confUrl=tmpPtr->Get_Next()) ) {   
+      if (strncmp(confUrl,strParamUrl,strlen(confUrl))==0 
+	  && (strlen(confUrl)>=candidate.len))  {
+	// it seems this URL match better
+	candidate.obj=tmpPtr->Find(confUrl);
+
+        // Let's see if it exists
+        if (((HtConfiguration *)candidate.obj)->Exists(value))
+        {
+          // yes, it has! We've got new candidate.
+          candidate.value=((HtConfiguration *)candidate.obj)->Find(value);
+          returnValue=candidate.value;
+          candidate.len=candidate.value.length();
+          found = true;
+        }
+      }
+    }
+
+    if (found)
+      return ParsedString(returnValue).get(dcGlobalVars);
+       
+  }
+  return Find(value);
+}
+
+
+//*********************************************************************
+int HtConfiguration::Value(const char *blockName, const char *name,
+   const char *value, int default_value ) {
+int retValue=default_value;
+String tmpStr=Find(blockName,name,value);
+ if (tmpStr[0]!=0) {
+   retValue=atoi(tmpStr.get());
+ }
+return retValue;
+}
+
+//*********************************************************************
+double HtConfiguration::Double(const char *blockName, const char *name,
+   const char *value, double default_value ) {
+double retValue=default_value;
+String tmpStr=Find(blockName,name,value);
+ if (tmpStr[0]!=0) {
+   retValue=atof(tmpStr.get());
+ }
+return retValue;
+}
+
+//*********************************************************************
+int HtConfiguration::Boolean(const char *blockName, const char *name,
+   const char *value, int default_value ) {
+int retValue=default_value;
+String tmpStr=Find(blockName,name,value);
+ if (tmpStr[0]!=0) {
+        if (mystrcasecmp((char*)tmpStr, "true") == 0 ||
+            mystrcasecmp((char*)tmpStr, "yes") == 0 ||
+            mystrcasecmp((char*)tmpStr, "1") == 0)
+            retValue = 1;
+        else if (mystrcasecmp((char*)tmpStr, "false") == 0 ||
+                 mystrcasecmp((char*)tmpStr, "no") == 0 ||
+                 mystrcasecmp((char*)tmpStr, "0") == 0)
+            retValue = 0;
+
+ }
+return retValue;
+}
+
+//*********************************************************************
+//*********************************************************************
+int HtConfiguration::Value(URL *aUrl, const char *value,
+			 int default_value ) {
+int retValue=default_value;
+String tmpStr=Find(aUrl,value);
+ if (tmpStr[0]!=0) {
+   retValue=atoi(tmpStr.get());
+ }
+return retValue;
+}
+
+//*********************************************************************
+double HtConfiguration::Double(URL *aUrl,const char *value,
+				double default_value ) {
+double retValue=default_value;
+String tmpStr=Find(aUrl,value);
+ if (tmpStr[0]!=0) {
+   retValue=atof(tmpStr.get());
+ }
+return retValue;
+}
+
+//*********************************************************************
+int HtConfiguration::Boolean(URL *aUrl,const char *value,
+				 int default_value ) {
+int retValue=default_value;
+String tmpStr=Find(aUrl,value);
+ if (tmpStr[0]!=0) {
+        if (mystrcasecmp((char*)tmpStr, "true") == 0 ||
+            mystrcasecmp((char*)tmpStr, "yes") == 0 ||
+            mystrcasecmp((char*)tmpStr, "1") == 0)
+            retValue = 1;
+        else if (mystrcasecmp((char*)tmpStr, "false") == 0 ||
+                 mystrcasecmp((char*)tmpStr, "no") == 0 ||
+                 mystrcasecmp((char*)tmpStr, "0") == 0)
+            retValue = 0;
+
+ }
+return retValue;
+}
+
+//*********************************************************************
+//
+int 
+HtConfiguration::Read(const String& filename)
+{
+extern FILE* yyin;
+extern int yyparse(void*);
+if ((yyin=fopen(filename,"r"))==NULL) 
+	return NOTOK;
+
+FileName=filename; // need to be before yyparse() because is used in it
+yyparse(this);
+fclose(yyin);
+return OK;
+}
+
+HtConfiguration* HtConfiguration::_config= NULL;
+
+HtConfiguration* const HtConfiguration::config() {
+	if(_config == NULL) {
+		_config= new HtConfiguration();
+	}
+	return _config;
+}
diff --git a/debian/htdig/htdig-3.2.0b6/htcommon/HtConfiguration.h b/debian/htdig/htdig-3.2.0b6/htcommon/HtConfiguration.h
new file mode 100644
index 00000000..accb379a
--- /dev/null
+++ b/debian/htdig/htdig-3.2.0b6/htcommon/HtConfiguration.h
@@ -0,0 +1,95 @@
+//
+// HtConfiguration.h
+//
+//             HtConfiguration: extends Configuration class
+//             to implement Apache-style config. Uses parser
+//             generated by Bison from conf_parser.yxx
+//
+// Part of the ht://Dig package   <http://www.htdig.org/>
+// Copyright (c) 1995-2004 The ht://Dig Group
+// For copyright details, see the file COPYING in your distribution
+// or the GNU Library General Public License (LGPL) version 2 or later
+// <http://www.gnu.org/copyleft/lgpl.html>
+//
+// $Id: HtConfiguration.h,v 1.5 2004/05/28 13:15:12 lha Exp $
+//
+
+
+#ifndef	_HtConfiguration_h_
+#define	_HtConfiguration_h_
+
+#include"Configuration.h"
+#include "ParsedString.h"
+#include "URL.h"
+
+class HtConfiguration : public Configuration
+{
+ public:
+    const String	Find(const String& name) const {return(Configuration::Find(name));}
+    int			Value(const String& name, int default_value = 0) const
+      {return(Configuration::Value  (name,default_value));}
+    double	Double(const String& name, double default_value = 0) const 
+      {return(Configuration::Double (name,default_value));}
+    int		Boolean(const String& name, int default_value = 0) const   
+      {return(Configuration::Boolean(name,default_value));}
+    void		Add(const String& str){Configuration::Add(str);}
+    void		Add(const String& name, const String& value)
+      {Configuration::Add(name,value);}
+    void		AddParsed(const String& name, const String& value)
+      {Configuration::AddParsed(name,value);}
+
+    void		Add(const char *name, const char *value,
+                           Configuration *aList);
+    const String	Find(URL *aUrl, const char *value) const;
+    const String	Find(const char *blockName, const char *name, const char *value) const;
+    int		Value(const char *blockName, const char *name, const char *value,
+                  int default_value = 0);
+    double	Double(const char *blockName, const char *name, const char *value,
+                  double default_value = 0);
+    int		Boolean(const char *blockName, const char *name, const char *value,
+                  int default_value = 0);
+    int		Value(URL *aUrl,const char *value,int default_value = 0);
+    double	Double(URL *aUrl,const char *value,double default_value = 0);
+    int		Boolean(URL *aUrl,const char *value,int default_value = 0);
+    inline
+    String	ParseString(const char*) const;   // parse ${var} string
+    String	getFileName() const { return FileName; }
+
+    //
+    // We need some way of reading in the database from a configuration file
+    // ... this uses the parser
+    virtual int         Read(const String& filename);
+
+ protected:
+    Dictionary          dcBlocks;
+    Dictionary          dcUrls;
+    String		FileName;	// config's file name
+
+ public:
+    HtConfiguration():Configuration()
+	{;}
+
+    HtConfiguration(const HtConfiguration& config) :
+	Configuration(config),
+	dcBlocks(config.dcBlocks),
+	dcUrls(config.dcUrls)
+	{
+	    ;
+	}
+
+	static HtConfiguration* const config();
+
+  private:
+  	static HtConfiguration* _config;
+};
+
+//********************************************************************
+//
+inline
+String HtConfiguration::ParseString(const char *str) const {
+ return ParsedString(str).get(dcGlobalVars);
+}
+
+#endif
+
+
diff --git a/debian/htdig/htdig-3.2.0b6/htcommon/HtSGMLCodec.cc b/debian/htdig/htdig-3.2.0b6/htcommon/HtSGMLCodec.cc
new file mode 100644
index 00000000..23518119
--- /dev/null
+++ b/debian/htdig/htdig-3.2.0b6/htcommon/HtSGMLCodec.cc
@@ -0,0 +1,124 @@
+//
+// HtSGMLCodec.cc
+//
+// HtSGMLCodec: A Specialized HtWordCodec class to convert between SGML 
+//              ISO 8859-1 entities and high-bit characters.
+//
+// Part of the ht://Dig package   <http://www.htdig.org/>
+// Copyright (c) 1995-2004 The ht://Dig Group
+// For copyright details, see the file COPYING in your distribution
+// or the GNU Library General Public License (LGPL) version 2 or later 
+// <http://www.gnu.org/copyleft/lgpl.html>
+//
+// $Id: HtSGMLCodec.cc,v 1.6 2004/06/01 18:25:01 angusgb Exp $
+//
+
+#ifdef HAVE_CONFIG_H
+#include "htconfig.h"
+#endif /* HAVE_CONFIG_H */
+
+#include "HtSGMLCodec.h"
+#include "HtConfiguration.h"
+
+// Constructor: parses the appropriate parameters using the
+// encapsulated HtWordCodec class.
+// Only used in privacy.
+HtSGMLCodec::HtSGMLCodec()
+{
+  HtConfiguration* config= HtConfiguration::config();
+  int translate_latin1 = config->Boolean("translate_latin1", 1);
+  StringList *myTextFromList = new StringList(); // For &foo;
+  StringList *myNumFromList = new StringList(); // For &#nnn;
+  StringList *myToList = new StringList();
+  String myTextFromString(770); // Full text list
+  
+  // Is this really the best way to do this?
+ if (!translate_latin1 )
+ {
+  myTextFromString = "&nbsp;";
+ }
+ else
+ {
+  // this set has been slightly modified in order to manage the &euro; entity
+  // the resulting charset is therefore a ISO-8859-1 partially moved to ISO-8859-15
+  myTextFromString = "&nbsp;|&iexcl;|&cent;|&pound;|&euro;|&yen;|&brvbar;|&sect;|";
+  myTextFromString << "&uml;|&copy;|&ordf;|&laquo;|&not;|&shy;|&reg;|&macr;|&deg;|";
+  myTextFromString << "&plusmn;|&sup2;|&sup3;|&acute;|&micro;|&para;|&middot;|&cedil;|";
+  myTextFromString << "&sup1;|&ordm;|&raquo;|&frac14;|&frac12;|&frac34;|&iquest;|&Agrave;|";
+  myTextFromString << "&Aacute;|&Acirc;|&Atilde;|&Auml;|&Aring;|&AElig;|&Ccedil;|&Egrave;|";
+  myTextFromString << "&Eacute;|&Ecirc;|&Euml;|&Igrave;|&Iacute;|&Icirc;|&Iuml;|&ETH;|";
+  myTextFromString << "&Ntilde;|&Ograve;|&Oacute;|&Ocirc;|&Otilde;|&Ouml;|&times;|&Oslash;|";
+  myTextFromString << "&Ugrave;|&Uacute;|&Ucirc;|&Uuml;|&Yacute;|&THORN;|&szlig;|&agrave;|";
+  myTextFromString << "&aacute;|&acirc;|&atilde;|&auml;|&aring;|&aelig;|&ccedil;|&egrave;|";
+  myTextFromString << "&eacute;|&ecirc;|&euml;|&igrave;|&iacute;|&icirc;|&iuml;|&eth;|";
+  myTextFromString << "&ntilde;|&ograve;|&oacute;|&ocirc;|&otilde;|&ouml;|&divide;|&oslash;|";
+  myTextFromString << "&ugrave;|&uacute;|&ucirc;|&uuml;|&yacute;|&thorn;|&yuml;";
+ }
+
+  myTextFromList->Create(myTextFromString, '|');
+
+  for (int i = 160; i <= 255; i++)
+    {
+      String temp = 0;
+      temp << (char) i;
+      myToList->Add(temp);
+
+      temp = 0;
+      temp << "&#" << i << ";";
+      myNumFromList->Add(temp);
+      if (!translate_latin1 )
+	break;
+    }
+
+  // Now let's take care of the low-bit characters with encodings.
+  myTextFromList->Add("&quot;");
+  myToList->Add("\"");
+  myNumFromList->Add("&#34;");
+
+  myTextFromList->Add("&amp;");
+  myToList->Add("&");
+  myNumFromList->Add("&#38;");
+
+  myTextFromList->Add("&lt;");
+  myToList->Add("<");
+  myNumFromList->Add("&#60;");
+
+  myTextFromList->Add("&gt;");
+  myToList->Add(">");
+  myNumFromList->Add("&#62;");
+
+  myTextWordCodec = new HtWordCodec(myTextFromList, myToList, '|');
+  myNumWordCodec = new HtWordCodec(myNumFromList, myToList, '|');
+}
+
+
+HtSGMLCodec::~HtSGMLCodec()
+{
+  delete myTextWordCodec;
+  delete myNumWordCodec;
+}
+
+
+// Supposedly used as HtSGMLCodec::instance()->ErrMsg()
+// to check if HtWordCodec liked what was fed.
+String& HtSGMLCodec::ErrMsg()
+{
+  return myErrMsg;
+}
+
+
+// Canonical singleton interface.
+HtSGMLCodec *
+HtSGMLCodec::instance()
+{
+  static HtSGMLCodec *_instance = 0;
+
+  if (_instance == 0)
+  {
+    _instance = new HtSGMLCodec();
+  }
+
+  return _instance;
+}
+
+// End of HtSGMLCodec.cc
diff --git a/debian/htdig/htdig-3.2.0b6/htcommon/HtSGMLCodec.h b/debian/htdig/htdig-3.2.0b6/htcommon/HtSGMLCodec.h
new file mode 100644
index 00000000..2fef9f90
--- /dev/null
+++ b/debian/htdig/htdig-3.2.0b6/htcommon/HtSGMLCodec.h
@@ -0,0 +1,63 @@
+//
+// HtSGMLCodec.h
+//
+// HtSGMLCodec: A Specialized HtWordCodec class to convert between SGML 
+//              ISO 8859-1 entities and high-bit characters.
+//
+// Part of the ht://Dig package   <http://www.htdig.org/>
+// Copyright (c) 1995-2004 The ht://Dig Group
+// For copyright details, see the file COPYING in your distribution
+// or the GNU Library General Public License (LGPL) version 2 or later 
+// <http://www.gnu.org/copyleft/lgpl.html>
+//
+// $Id: HtSGMLCodec.h,v 1.4 2004/05/28 13:15:12 lha Exp $
+//
+#ifndef __HtSGMLCodec_h
+#define __HtSGMLCodec_h
+
+#include "HtWordCodec.h"
+
+// Container for a HtWordCodec (not subclassed from it due to
+// portability-problems using initializers).
+// Not for subclassing.
+class HtSGMLCodec
+{
+public:
+  static HtSGMLCodec *instance();
+  virtual ~HtSGMLCodec();
+
+  // Similar to the HtWordCodec class.  Each string may contain
+  // zero or more of words from the lists. Here we need to run
+  // it through two codecs because we might have two different forms
+  inline String encode(const String &uncoded) const
+  { return myTextWordCodec->encode(myNumWordCodec->encode(uncoded)); }
+
+  // But we only want to decode into one form i.e. &foo; NOT &#nnn;
+  String decode(const String &coded) const
+  { return myTextWordCodec->decode(coded); }
+
+  // If an error was discovered during the parsing of
+  // entities, this returns an error message
+  String& ErrMsg();
+
+  // egcs-1.1 (and some earlier versions) always erroneously
+  // warns (even without warning flags) about classic singleton
+  // constructs ("only defines private constructors and has no
+  // friends").  Rather than adding autoconf tests to shut these
+  // versions up with -Wno-ctor-dtor-privacy, we fake normal
+  // conformism for it here (the minimal effort).
+  friend void my_friend_Harvey__a_faked_friend_function();
+
+private:
+  // Hide default-constructor, copy-constructor and assignment
+  // operator, making this a singleton.
+  HtSGMLCodec();
+  HtSGMLCodec(const HtSGMLCodec &);
+  void operator= (const HtSGMLCodec &);
+
+  HtWordCodec *myTextWordCodec; // For &foo;
+  HtWordCodec *myNumWordCodec; // For &#foo;
+  String myErrMsg;
+};
+
+#endif /* __HtSGMLCodec_h */
diff --git a/debian/htdig/htdig-3.2.0b6/htcommon/HtURLCodec.cc b/debian/htdig/htdig-3.2.0b6/htcommon/HtURLCodec.cc
new file mode 100644
index 00000000..16a68c8e
--- /dev/null
+++ b/debian/htdig/htdig-3.2.0b6/htcommon/HtURLCodec.cc
@@ -0,0 +1,66 @@
+//
+// HtURLCodec.cc
+//
+// HtURLCodec:  Specialized HtWordCodec which just caters to the
+//              needs of "url_part_aliases" and "common_url_parts".
+//              Used for coding URLs when they are on disk; the key and the
+//              href field in db.docdb.
+//
+// Part of the ht://Dig package   <http://www.htdig.org/>
+// Copyright (c) 1995-2004 The ht://Dig Group
+// For copyright details, see the file COPYING in your distribution
+// or the GNU Library General Public License (LGPL) version 2 or later 
+// <http://www.gnu.org/copyleft/lgpl.html>
+//
+// $Id: HtURLCodec.cc,v 1.4 2004/05/28 13:15:12 lha Exp $
+//
+
+#ifdef HAVE_CONFIG_H
+#include "htconfig.h"
+#endif /* HAVE_CONFIG_H */
+
+#include "HtURLCodec.h"
+#include "defaults.h" // For "config"
+
+// Constructor: parses the appropriate parameters using the
+// encapsulated HtWordCodec class.
+// Only used in privacy.
+HtURLCodec::HtURLCodec()
+{
+  HtConfiguration* config= HtConfiguration::config();
+  StringList l1(config->Find("url_part_aliases"), " \t");
+  StringList l2(config->Find("common_url_parts"), " \t");
+
+  myWordCodec = new HtWordCodec(l1, l2, myErrMsg);
+}
+
+
+HtURLCodec::~HtURLCodec()
+{
+  delete myWordCodec;
+}
+
+
+// Supposedly used as HtURLCodec::instance()->ErrMsg()
+// to check if HtWordCodec liked what was fed.
+String& HtURLCodec::ErrMsg()
+{
+  return myErrMsg;
+}
+
+
+// Canonical singleton interface.
+HtURLCodec *
+HtURLCodec::instance()
+{
+  static HtURLCodec *_instance = 0;
+
+  if (_instance == 0)
+  {
+    _instance = new HtURLCodec();
+  }
+
+  return _instance;
+}
+
+// End of HtURLCodec.cc
diff --git a/debian/htdig/htdig-3.2.0b6/htcommon/HtURLCodec.h b/debian/htdig/htdig-3.2.0b6/htcommon/HtURLCodec.h
new file mode 100644
index 00000000..a6aa2804
--- /dev/null
+++ b/debian/htdig/htdig-3.2.0b6/htcommon/HtURLCodec.h
@@ -0,0 +1,64 @@
+//
+// HtURLCodec.h
+//
+// HtURLCodec:  Specialized HtWordCodec which just caters to the
+//              needs of "url_part_aliases" and "common_url_parts".
+//              Used for coding URLs when they are on disk; the key and the
+//              href field in db.docdb.
+//
+// Part of the ht://Dig package   <http://www.htdig.org/>
+// Copyright (c) 1995-2004 The ht://Dig Group
+// For copyright details, see the file COPYING in your distribution
+// or the GNU Library General Public License (LGPL) version 2 or later 
+// <http://www.gnu.org/copyleft/lgpl.html>
+//
+// $Id: HtURLCodec.h,v 1.4 2004/05/28 13:15:12 lha Exp $
+//
+
+#ifndef __HtURLCodec_h
+#define __HtURLCodec_h
+
+#include "HtWordCodec.h"
+
+// Container for a HtWordCodec (not subclassed from it due to
+// portability-problems using initializers).
+// Not for subclassing.
+class HtURLCodec
+{
+public:
+  static HtURLCodec *instance();
+  virtual ~HtURLCodec();
+
+  // Same as in the HtWordCodec class.  Each string may contain
+  // zero  or more of words from the lists.
+  inline String encode(const String &uncoded) const
+  { return myWordCodec->encode(uncoded); }
+
+  String decode(const String &coded) const
+  { return myWordCodec->decode(coded); }
+
+  // If an error was discovered during the parsing of
+  // url_part_aliases or common_url_parts, this member gives a
+  // nonempty String with an error message.
+  String& ErrMsg();
+
+  // egcs-1.1 (and some earlier versions) always erroneously
+  // warns (even without warning flags) about classic singleton
+  // constructs ("only defines private constructors and has no
+  // friends").  Rather than adding autoconf tests to shut these
+  // versions up with -Wno-ctor-dtor-privacy, we fake normal
+  // conformism for it here (the minimal effort).
+  friend void my_friend_Harvey__a_faked_friend_function();
+
+private:
+  // Hide default-constructor, copy-constructor and assignment
+  // operator, making this a singleton.
+  HtURLCodec();
+  HtURLCodec(const HtURLCodec &);
+  void operator= (const HtURLCodec &);
+
+  HtWordCodec *myWordCodec;
+  String myErrMsg;
+};
+
+#endif /* __HtURLCodec_h */
diff --git a/debian/htdig/htdig-3.2.0b6/htcommon/HtURLRewriter.cc b/debian/htdig/htdig-3.2.0b6/htcommon/HtURLRewriter.cc
new file mode 100644
index 00000000..76c9faa1
--- /dev/null
+++ b/debian/htdig/htdig-3.2.0b6/htcommon/HtURLRewriter.cc
@@ -0,0 +1,59 @@
+//
+// HtURLRewriter.cc
+//
+// HtURLRewriter:  Container for a HtRegexReplaceList (not subclassed from it due to
+//                 portability-problems using initializers).
+//                 Not for subclassing.
+//
+// Part of the ht://Dig package   <http://www.htdig.org/>
+// Copyright (c) 2000-2004 The ht://Dig Group
+// For copyright details, see the file COPYING in your distribution
+// or the GNU Library General Public License (LGPL) version 2 or later 
+// <http://www.gnu.org/copyleft/lgpl.html>
+//
+// $Id: HtURLRewriter.cc,v 1.4 2004/05/28 13:15:12 lha Exp $
+//
+
+#include "HtURLRewriter.h"
+#include "defaults.h" // For "config"
+
+// Constructor: parses the appropriate parameters using the
+// encapsulated RegexReplaceList class.
+// Only used in privacy.
+HtURLRewriter::HtURLRewriter()
+{
+	HtConfiguration* config= HtConfiguration::config();
+	StringList list(config->Find("url_rewrite_rules"), " \t");
+
+	myRegexReplace = new HtRegexReplaceList(list);
+}
+
+
+HtURLRewriter::~HtURLRewriter()
+{
+	delete myRegexReplace;
+}
+
+// Supposedly used as HtURLRewriter::instance()->ErrMsg()
+// to check if RegexReplaceList liked what was fed.
+const String& HtURLRewriter::ErrMsg()
+{
+	return myRegexReplace->lastError();
+}
+
+
+// Canonical singleton interface.
+HtURLRewriter *
+HtURLRewriter::instance()
+{
+	static HtURLRewriter *_instance = 0;
+
+	if (_instance == 0)
+	{
+		_instance = new HtURLRewriter();
+	}
+
+	return _instance;
+}
+
+// End of HtURLRewriter.cc
diff --git a/debian/htdig/htdig-3.2.0b6/htcommon/HtURLRewriter.h b/debian/htdig/htdig-3.2.0b6/htcommon/HtURLRewriter.h
new file mode 100644
index 00000000..d0197c07
--- /dev/null
+++ b/debian/htdig/htdig-3.2.0b6/htcommon/HtURLRewriter.h
@@ -0,0 +1,52 @@
+//
+// HtURLRewriter.h
+//
+// HtURLRewriter:  Container for a HtRegexReplaceList (not subclassed from it due to
+//                 portability-problems using initializers).
+//                 Not for subclassing.
+//
+// Part of the ht://Dig package   <http://www.htdig.org/>
+// Copyright (c) 2000-2004 The ht://Dig Group
+// For copyright details, see the file COPYING in your distribution
+// or the GNU Library General Public License (LGPL) version 2 or later 
+// <http://www.gnu.org/copyleft/lgpl.html>
+//
+// $Id: HtURLRewriter.h,v 1.4 2004/05/28 13:15:12 lha Exp $
+//
+#ifndef __HtURLRewriter_h
+#define __HtURLRewriter_h
+
+#include "HtRegexReplaceList.h"
+
+class HtURLRewriter
+{
+public:
+	static HtURLRewriter *instance();
+	virtual ~HtURLRewriter();
+
+	inline int replace(String &src) { return myRegexReplace->replace(src); }
+
+	// If an error was discovered during the parsing of
+	// config directives, this member gives a
+	// nonempty String with an error message.
+	const String& ErrMsg();
+
+	// egcs-1.1 (and some earlier versions) always erroneously
+	// warns (even without warning flags) about classic singleton
+	// constructs ("only defines private constructors and has no
+	// friends").  Rather than adding autoconf tests to shut these
+	// versions up with -Wno-ctor-dtor-privacy, we fake normal
+	// conformism for it here (the minimal effort).
+	friend void my_friend_Harvey__a_faked_friend_function();
+
+private:
+	// Hide default-constructor, copy-constructor and assignment
+	// operator, making this a singleton.
+	HtURLRewriter();
+	HtURLRewriter(const HtURLRewriter &);
+	void operator= (const HtURLRewriter &);
+
+	HtRegexReplaceList *myRegexReplace;
+};
+
+#endif /* __HtURLRewriter_h */
diff --git a/debian/htdig/htdig-3.2.0b6/htcommon/HtWordList.cc b/debian/htdig/htdig-3.2.0b6/htcommon/HtWordList.cc
new file mode 100644
index 00000000..566898c1
--- /dev/null
+++ b/debian/htdig/htdig-3.2.0b6/htcommon/HtWordList.cc
@@ -0,0 +1,209 @@
+//
+// HtWordList.cc
+//
+// HtWordList: Specialized WordList class that can hold a list 
+//	       of words waiting to be inserted in the database.
+//
+// Part of the ht://Dig package   <http://www.htdig.org/>
+// Copyright (c) 1995-2004 The ht://Dig Group
+// For copyright details, see the file COPYING in your distribution
+// or the GNU Library General Public License (LGPL) version 2 or later
+// <http://www.gnu.org/copyleft/lgpl.html>
+//
+// $Id: HtWordList.cc,v 1.7 2004/05/28 13:15:12 lha Exp $
+//
+
+#ifdef HAVE_CONFIG_H
+#include "htconfig.h"
+#endif /* HAVE_CONFIG_H */
+
+#include "HtWordList.h"
+#include "HtWordReference.h"
+#include "WordRecord.h"
+#include "WordType.h"
+#include "HtConfiguration.h"
+#include "htString.h"
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <ctype.h>
+
+#ifdef HAVE_STD
+#include <iostream>
+#include <fstream>
+#ifdef HAVE_NAMESPACES
+using namespace std;
+#endif
+#else
+#include <iostream.h>
+#include <fstream.h>
+#endif /* HAVE_STD */
+
+#include <errno.h>
+
+//*****************************************************************************
+// HtWordList::~HtWordList()
+//
+HtWordList::~HtWordList()
+{
+    delete words;
+}
+
+//*****************************************************************************
+//
+HtWordList::HtWordList(const HtConfiguration& config_arg) :
+  WordList(config_arg)
+{
+    words = new List;
+}
+
+//*****************************************************************************
+//
+void HtWordList::Replace(const WordReference& arg)
+{
+  //
+  // New word.  Create a new reference for it and cache it in the object.
+  //
+  words->Add(new WordReference(arg));
+}
+
+//*****************************************************************************
+// void HtWordList::Flush()
+//   Dump the current list of words to the database.  After
+//   the words have been dumped, the list will be destroyed to make
+//   room for the words of the next document.
+//   
+void HtWordList::Flush()
+{
+  HtWordReference	*wordRef;
+
+    // Provided for backwards compatibility
+  if (!isopen)
+    Open(config["word_db"], O_RDWR);
+
+  words->Start_Get();
+  while ((wordRef = (HtWordReference *) words->Get_Next()))
+    {
+      if (wordRef->Word().length() == 0) {
+	cerr << "HtWordList::Flush: unexpected empty word\n";
+	continue;
+      }
+
+      Override(*wordRef);
+    }	
+    
+  // Cleanup
+  words->Destroy();
+}
+
+//*****************************************************************************
+// void HtWordList::Skip()
+//   The current document has disappeared or been modified. 
+//   We do not need to store these words.
+//
+void HtWordList::Skip()
+{
+  words->Destroy();
+}
+
+//
+// Callback data dedicated to Dump and dump_word communication
+//
+class DumpWordData : public Object
+{
+public:
+  DumpWordData(FILE* fl_arg) { fl = fl_arg; }
+
+  FILE* fl;
+};
+
+//*****************************************************************************
+//
+// Write the ascii representation of a word occurence. Helper
+// of WordList::Dump
+//
+static int dump_word(WordList *, WordDBCursor &, const WordReference *word, Object &data)
+{
+  const HtWordReference *word_tmp = (const HtWordReference *)word;
+
+  DumpWordData &info = (DumpWordData &)data;
+
+  word_tmp->Dump(info.fl);
+
+  return OK;
+}
+
+//*****************************************************************************
+// int HtWordList::Dump(char* filename)
+//
+// Write an ascii version of the word database in <filename>
+//
+int HtWordList::Dump(const String& filename)
+{
+  FILE		*fl;
+
+  if (!isopen) {
+    cerr << "WordList::Dump: database must be opened first\n";
+    return NOTOK;
+  }
+
+  if((fl = fopen(filename, "w")) == 0) {
+    perror(form("WordList::Dump: opening %s for writing", (const char*)filename));
+    return NOTOK;
+  }
+
+  HtWordReference::DumpHeader(fl);
+  DumpWordData data(fl);
+  WordCursor* search = Cursor(dump_word, &data);
+  search->Walk();
+  delete search;
+  
+  fclose(fl);
+
+  return OK;
+}
+
+//*****************************************************************************
+// int HtWordList::Load(char* filename)
+//
+// Read in an ascii version of the word database in <filename>
+//
+int HtWordList::Load(const String& filename)
+{
+  FILE		*fl;
+  String	data;
+  HtWordReference *next;
+
+  if (!isopen) {
+    cerr << "WordList::Load: database must be opened first\n";
+    return NOTOK;
+  }
+
+  if((fl = fopen(filename, "r")) == 0) {
+    perror(form("WordList::Load: opening %s for reading", (const char*)filename));
+    return NOTOK;
+  }
+
+  if (HtWordReference::LoadHeader(fl) != OK)
+    {
+      cerr << "WordList::Load: header is not correct\n";
+      return NOTOK;
+    }
+
+  while (data.readLine(fl))
+    {
+      next = new HtWordReference;
+      if (next->Load(data) != OK)
+	{
+	  delete next;
+	  continue;
+	}
+  
+      words->Add(next);
+    }
+
+  Flush();
+  fclose(fl);
+
+  return OK;
+}
diff --git a/debian/htdig/htdig-3.2.0b6/htcommon/HtWordList.h b/debian/htdig/htdig-3.2.0b6/htcommon/HtWordList.h
new file mode 100644
index 00000000..1fd60789
--- /dev/null
+++ b/debian/htdig/htdig-3.2.0b6/htcommon/HtWordList.h
@@ -0,0 +1,69 @@
+//
+// HtWordList.h
+//
+// HtWordList: Specialized WordList class that can hold a list 
+//	       of words waiting to be inserted in the database.
+//
+// Part of the ht://Dig package   <http://www.htdig.org/>
+// Copyright (c) 1995-2004 The ht://Dig Group
+// For copyright details, see the file COPYING in your distribution
+// or the GNU Library General Public License (LGPL) version 2 or later
+// <http://www.gnu.org/copyleft/lgpl.html>
+//
+// $Id: HtWordList.h,v 1.6 2004/05/28 13:15:12 lha Exp $
+//
+
+#ifndef _HtWordList_h_
+#define _HtWordList_h_
+
+#include <fcntl.h>
+#include <stdlib.h>
+
+#include"HtConfiguration.h"
+#include "WordList.h"
+
+class HtWordList : public WordList
+{
+public:
+    //
+    // Construction/Destruction
+    //
+    HtWordList(const Configuration  & config_arg) : WordList(config_arg) 
+	{
+	    cerr << "HtWordList::HtWordList(Configuration) is not valid" << endl; 
+	    abort();
+	}
+    HtWordList(const HtConfiguration& config_arg);
+    virtual ~HtWordList();
+    
+    //
+    // Update/add a word, perform sanity checking and
+    // fill information.
+    //
+    void		Replace(const WordReference& wordRef);
+
+    //
+    // Skip this document -- ignore all words stored in the object
+    //  from this document
+    //
+    void		Skip();
+
+    //
+    // Flush the words stored in the object to the database
+    //
+    void		Flush();
+
+    // Write an ascii version of the word database in <filename>
+    int			Dump(const String& filename);
+
+    // Read in an ascii version of the word database in <filename>
+    int			Load(const String& filename);
+
+private:
+
+    List			*words;
+};
+
+#endif
+
+
diff --git a/debian/htdig/htdig-3.2.0b6/htcommon/HtWordReference.cc b/debian/htdig/htdig-3.2.0b6/htcommon/HtWordReference.cc
new file mode 100644
index 00000000..3b603855
--- /dev/null
+++ b/debian/htdig/htdig-3.2.0b6/htcommon/HtWordReference.cc
@@ -0,0 +1,94 @@
+//
+// HtWordReference.cc
+//
+// Part of the ht://Dig package   <http://www.htdig.org/>
+// Copyright (c) 1999-2004 The ht://Dig Group
+// For copyright details, see the file COPYING in your distribution
+// or the GNU Library General Public License (LGPL) version 2 or later
+// <http://www.gnu.org/copyleft/lgpl.html>
+//
+// $Id: HtWordReference.cc,v 1.5 2004/05/28 13:15:12 lha Exp $
+//
+
+#ifdef HAVE_CONFIG_H
+#include "htconfig.h"
+#endif /* HAVE_CONFIG_H */
+
+#include "HtWordReference.h"
+#include <stdio.h>
+#include <stdlib.h>
+
+//
+// Explain the format of data output of the Dump function
+//
+int HtWordReference::DumpHeader(FILE *fl)
+{
+  fprintf(fl, "#word\tdocument id\tflags\tlocation\tanchor\n");
+  return OK;
+}
+
+//
+// Ascii representation of a word occurence.
+//
+int HtWordReference::Dump(FILE *fl) const
+{
+  fprintf(fl, "%s\t%d\t%d\t%d\t%d\n",
+	  (char*)Word(),
+	  DocID(),
+	  Flags(),
+	  Location(),
+	  Anchor());
+  return OK;
+}
+
+//
+// Check the header of the file
+//
+int HtWordReference::LoadHeader(FILE *fl)
+{
+  String header;
+  header.readLine(fl);
+  if (mystrcasecmp("#word\tdocument id\tflags\tlocation\tanchor", header.get()) == 0)
+    return OK;
+  else
+    return NOTOK;
+}
+
+//
+// Ascii representation of a word occurence.
+//
+int HtWordReference::Load(const String& s)
+{
+  String data(s);
+  char *token;
+
+  // Format is "%s\t%d\t%d\t%d\t%d
+
+  token = strtok(data, "\t");
+  if (!token)
+    return NOTOK;
+  Word(token);
+
+  token = strtok(0, "\t");
+  if (!token)
+    return NOTOK;
+  DocID(atoi(token));
+
+  token = strtok(0, "\t");
+  if (!token)
+    return NOTOK;
+  Flags(atoi(token));
+
+  token = strtok(0, "\t");
+  if (!token)
+    return NOTOK;
+  Location(atoi(token));
+
+  token = strtok(0, "\t");
+  if (!token)
+    return NOTOK;
+  Anchor(atoi(token));
+
+  return OK;
+}
+
diff --git a/debian/htdig/htdig-3.2.0b6/htcommon/HtWordReference.h b/debian/htdig/htdig-3.2.0b6/htcommon/HtWordReference.h
new file mode 100644
index 00000000..2b7a6db4
--- /dev/null
+++ b/debian/htdig/htdig-3.2.0b6/htcommon/HtWordReference.h
@@ -0,0 +1,93 @@
+//
+// HtWordReference.h
+//
+// HtWordReference: Reference to a word, derived from WordReference and
+//		    implementing explicit accessors.
+//
+// Part of the ht://Dig package   <http://www.htdig.org/>
+// Copyright (c) 1995-2004 The ht://Dig Group
+// For copyright details, see the file COPYING in your distribution
+// or the GNU Library General Public License (LGPL) version 2 or later
+// <http://www.gnu.org/copyleft/lgpl.html>
+//
+// $Id: HtWordReference.h,v 1.6 2004/05/28 13:15:12 lha Exp $
+//
+#ifndef _HtWordReference_h_
+#define _HtWordReference_h_
+
+#include "WordReference.h"
+#include <stdio.h>
+
+//
+// Flags
+// (If extra flags added, also update  htsearch.cc:colonPrefix
+// 
+#define FLAG_TEXT 0
+#define FLAG_CAPITAL 1
+#define FLAG_TITLE 2
+#define FLAG_HEADING 4
+#define FLAG_KEYWORDS 8
+#define FLAG_DESCRIPTION 16
+#define FLAG_AUTHOR 32
+#define FLAG_LINK_TEXT 64
+#define FLAG_URL 128
+
+// For field-restricted search, at least one of these flags must be set
+// in document.  (255 = OR of the above...)
+#define FLAGS_MATCH_ONE (255 | FLAG_PLAIN)
+
+// The following are not stored in the database, but are used by WeightWord
+#define FLAG_PLAIN 4096
+#define FLAG_EXACT 8192
+#define FLAG_HIDDEN 16384
+#define FLAG_IGNORE 32768
+// The remainder are undefined
+
+class HtWordReference : public WordReference
+{
+public:
+	//
+	// Construction/Destruction
+	//
+        HtWordReference()	{}
+        HtWordReference(const String& key, const String& record) :
+	  WordReference(key, record) { }
+        HtWordReference(const String& word) :
+	  WordReference(word) {	}
+        HtWordReference(String word, unsigned int docid, unsigned int flags, unsigned int location, unsigned int anchor) {
+	  Word(word);
+	  DocID(docid);
+	  Location(location);
+	  Anchor(anchor);
+	  Flags(flags);
+	}
+
+	~HtWordReference()	{}
+
+	//
+	// Accessors
+	//
+	String			Word() const { return key.GetWord(); }
+	void			Word(const String& arg) { key.SetWord(arg); }
+	unsigned int		DocID() const { return key.Get( 1 ); }
+	void			DocID(const unsigned int arg) { key.Set( 1, arg); }
+	unsigned int		Flags() const { return key.Get( 2 ); }
+	void			Flags(const unsigned int arg) { key.Set( 2, arg); }
+	unsigned int		Location() const { return key.Get( 3 ); }
+	void			Location(const unsigned int arg) { key.Set( 3, arg); }
+	unsigned int		Anchor() const { return record.info.data; }
+	void			Anchor(const unsigned int arg) { record.info.data = arg; }
+
+	//
+	// Dumping/Loading
+	//
+	int			Dump(FILE *fl) const;
+	static int		DumpHeader(FILE *fl);
+	int			Load(const String& s);
+	static int		LoadHeader(FILE *fl);
+};
+
+
+#endif
+
+
diff --git a/debian/htdig/htdig-3.2.0b6/htcommon/HtZlibCodec.cc b/debian/htdig/htdig-3.2.0b6/htcommon/HtZlibCodec.cc
new file mode 100644
index 00000000..ac48877f
--- /dev/null
+++ b/debian/htdig/htdig-3.2.0b6/htcommon/HtZlibCodec.cc
@@ -0,0 +1,136 @@
+//
+// HtZlibCodec.cc
+//
+// HtZlibCodec: Provide a generic access to the zlib compression routines.
+//              If zlib is not present, encode and decode are simply 
+//              assignment functions.
+//
+// Part of the ht://Dig package   <http://www.htdig.org/>
+// Copyright (c) 1995-2004 The ht://Dig Group
+// For copyright details, see the file COPYING in your distribution
+// or the GNU Library General Public License (LGPL) version 2 or later
+// <http://www.gnu.org/copyleft/lgpl.html>
+//
+// $Id: HtZlibCodec.cc,v 1.4 2004/05/28 13:15:12 lha Exp $
+//
+
+#ifdef HAVE_CONFIG_H
+#include "htconfig.h"
+#endif /* HAVE_CONFIG_H */
+
+#include "HtZlibCodec.h"
+#include "defaults.h" // For "config"
+
+#if defined(HAVE_LIBZ) && defined(HAVE_ZLIB_H)
+#include <zlib.h>
+#endif
+
+
+HtZlibCodec::HtZlibCodec()
+{
+}
+
+HtZlibCodec::~HtZlibCodec()
+{
+}
+
+String HtZlibCodec::encode(const String &str) const
+{
+  String s = str;
+#if defined(HAVE_LIBZ) && defined(HAVE_ZLIB_H)
+  HtConfiguration* config= HtConfiguration::config();
+  static int cf=config->Value("compression_level",0);    
+  if (cf) {
+    //
+    // Now compress s into c_s
+    //
+    unsigned char c_buffer[16384];
+    String c_s;
+    z_stream c_stream; /* compression stream */
+    c_stream.zalloc=(alloc_func)0;
+    c_stream.zfree=(free_func)0;
+    c_stream.opaque=(voidpf)0;
+    // Get compression factor, default to best
+    if (cf<-1) cf=-1; else if (cf>9) cf=9;
+    int err=deflateInit(&c_stream,cf);
+    if (err!=Z_OK) return 0;
+    int len=s.length();
+    c_stream.next_in=(Bytef*)(char *)s;
+    c_stream.avail_in=len;
+    while (err==Z_OK && c_stream.total_in!=(uLong)len) {
+      c_stream.next_out=c_buffer;
+      c_stream.avail_out=sizeof(c_buffer);
+      err=deflate(&c_stream,Z_NO_FLUSH);
+      c_s.append((char *)c_buffer,c_stream.next_out-c_buffer);
+    }
+    // Finish the stream
+    for (;;) {
+      c_stream.next_out=c_buffer;
+      c_stream.avail_out=sizeof(c_buffer);
+      err=deflate(&c_stream,Z_FINISH);
+      c_s.append((char *)c_buffer,c_stream.next_out-c_buffer);
+      if (err==Z_STREAM_END) break;
+      //CHECK_ERR(err, "deflate");
+    }
+    err=deflateEnd(&c_stream); 
+    s=c_s;
+  }
+#endif // HAVE_LIBZ && HAVE_ZLIB_H
+  return s;
+}
+
+
+String HtZlibCodec::decode(const String &str) const
+{
+  String s = str;
+#if defined(HAVE_LIBZ) && defined(HAVE_ZLIB_H)
+  HtConfiguration* config= HtConfiguration::config();
+  static int cf=config->Value("compression_level",0);    
+  if (cf) {
+    String c_s;
+    // Decompress stream
+    unsigned char c_buffer[16384];
+    z_stream d_stream;
+    d_stream.zalloc=(alloc_func)0;
+    d_stream.zfree=(free_func)0;
+    d_stream.opaque=(voidpf)0;
+    
+    unsigned int len=s.length();
+    d_stream.next_in=(Bytef*)(char *)s;
+    d_stream.avail_in=len;
+    
+    int err=inflateInit(&d_stream);
+    if (err!=Z_OK) return 1;
+    
+    while (err==Z_OK && d_stream.total_in<len) {
+      d_stream.next_out=c_buffer;
+      d_stream.avail_out=sizeof(c_buffer);
+      err=inflate(&d_stream,Z_NO_FLUSH);
+      c_s.append((char *)c_buffer,d_stream.next_out-c_buffer);
+      if (err==Z_STREAM_END) break;
+    }
+    
+    err=inflateEnd(&d_stream);
+    s=c_s;
+  }
+#endif // HAVE_LIBZ && HAVE_ZLIB_H
+  return s;
+}
+
+
+// Canonical singleton interface.
+HtZlibCodec *
+HtZlibCodec::instance()
+{
+  static HtZlibCodec *_instance = 0;
+
+  if (_instance == 0)
+  {
+    _instance = new HtZlibCodec();
+  }
+
+  return _instance;
+}
+
+
+// End of HtZlibCodec.cc
diff --git a/debian/htdig/htdig-3.2.0b6/htcommon/HtZlibCodec.h b/debian/htdig/htdig-3.2.0b6/htcommon/HtZlibCodec.h
new file mode 100644
index 00000000..c4355c97
--- /dev/null
+++ b/debian/htdig/htdig-3.2.0b6/htcommon/HtZlibCodec.h
@@ -0,0 +1,51 @@
+//
+// HtZlibCodec.h
+//
+// HtZlibCodec: Provide a generic access to the zlib compression routines.
+//              If zlib is not present, encode and decode are simply 
+//              assignment functions.
+//
+// Part of the ht://Dig package   <http://www.htdig.org/>
+// Copyright (c) 1995-2004 The ht://Dig Group
+// For copyright details, see the file COPYING in your distribution
+// or the GNU Library General Public License (LGPL) version 2 or later 
+// <http://www.gnu.org/copyleft/lgpl.html>
+//
+// $Id: HtZlibCodec.h,v 1.4 2004/05/28 13:15:12 lha Exp $
+//
+//
+#ifndef __HtZlibCodec_h
+#define __HtZlibCodec_h
+
+#include "htString.h"
+#include "HtCodec.h"
+
+class HtZlibCodec : public HtCodec
+{
+public:
+  static HtZlibCodec *instance();
+  ~HtZlibCodec();
+
+  // Code what's in this string.
+  String encode(const String &) const;
+
+  // Decode what's in this string.
+  String decode(const String &) const;
+
+  // egcs-1.1 (and some earlier versions) always erroneously
+  // warns (even without warning flags) about classic singleton
+  // constructs ("only defines private constructors and has no
+  // friends").  Rather than adding autoconf tests to shut these
+  // versions up with -Wno-ctor-dtor-privacy, we fake normal
+  // conformism for it here (the minimal effort).
+  friend void my_friend_Harvey__a_faked_friend_function();
+
+private:
+  // Hide default-constructor, copy-constructor and assignment
+  // operator, making this a singleton.
+  HtZlibCodec();
+  HtZlibCodec(const HtZlibCodec &);
+  void operator= (const HtZlibCodec &);
+};
+
+#endif /* __HtZlibCodec_h */
diff --git a/debian/htdig/htdig-3.2.0b6/htcommon/Makefile.am b/debian/htdig/htdig-3.2.0b6/htcommon/Makefile.am
new file mode 100644
index 00000000..0a487c94
--- /dev/null
+++ b/debian/htdig/htdig-3.2.0b6/htcommon/Makefile.am
@@ -0,0 +1,44 @@
+
+include $(top_srcdir)/Makefile.config
+
+#
+# Do not output #line because it confuses the dependencies
+# generator of GCC if configure run out of source tree. 
+# Comment these to ease debugging.
+#
+AM_LFLAGS = -L
+AM_YFLAGS = -l -d
+
+EXTRA_DIST=conf_lexer.cxx conf_parser.cxx
+
+pkglib_LTLIBRARIES = libcommon.la
+
+libcommon_la_SOURCES = DocumentDB.cc DocumentRef.cc \
+	HtWordReference.cc HtWordList.cc defaults.cc \
+	HtURLCodec.cc URL.cc URLTrans.cc \
+	HtZlibCodec.cc cgi.cc HtSGMLCodec.cc \
+	HtConfiguration.cc HtURLRewriter.cc \
+	conf_lexer.lxx conf_parser.yxx 
+
+libcommon_la_LDFLAGS = -release $(HTDIG_MAJOR_VERSION).$(HTDIG_MINOR_VERSION).$(HTDIG_MICRO_VERSION) ${extra_ldflags}
+
+noinst_HEADERS = DocumentDB.h \
+	DocumentRef.h \
+	HtWordReference.h \
+	HtWordList.h \
+	HtURLCodec.h \
+	HtSGMLCodec.h \
+	URL.h \
+	cgi.h \
+	HtZlibCodec.h \
+	defaults.h \
+	HtConfiguration.h \
+	HtURLRewriter.h \
+	conf_parser.h
+
+LOCAL_DEFINES=	-DBIN_DIR=\"$(bindir)\" \
+		-DCOMMON_DIR=\"$(COMMON_DIR)\" \
+		-DCONFIG_DIR=\"$(CONFIG_DIR)\" \
+		-DDATABASE_DIR=\"$(DATABASE_DIR)\" \
+		-DIMAGE_URL_PREFIX=\"$(IMAGE_URL_PREFIX)\" 
+
diff --git a/debian/htdig/htdig-3.2.0b6/htcommon/Makefile.in b/debian/htdig/htdig-3.2.0b6/htcommon/Makefile.in
new file mode 100644
index 00000000..6ff19250
--- /dev/null
+++ b/debian/htdig/htdig-3.2.0b6/htcommon/Makefile.in
@@ -0,0 +1,570 @@
+# Makefile.in generated by automake 1.7.9 from Makefile.am.
+# @configure_input@
+
+# Copyright 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003
+# Free Software Foundation, Inc.
+# This Makefile.in is free software; the Free Software Foundation
+# gives unlimited permission to copy and/or distribute it,
+# with or without modifications, as long as this notice is preserved.
+
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY, to the extent permitted by law; without
+# even the implied warranty of MERCHANTABILITY or FITNESS FOR A
+# PARTICULAR PURPOSE.
+
+@SET_MAKE@
+
+#
+# To compile with profiling do the following:
+#
+# make CFLAGS=-g CXXFLAGS=-g PROFILING=-p all
+#
+
+srcdir = @srcdir@
+top_srcdir = @top_srcdir@
+VPATH = @srcdir@
+pkgdatadir = $(datadir)/@PACKAGE@
+pkglibdir = $(libdir)/@PACKAGE@
+pkgincludedir = $(includedir)/@PACKAGE@
+top_builddir = ..
+
+am__cd = CDPATH="$${ZSH_VERSION+.}$(PATH_SEPARATOR)" && cd
+INSTALL = @INSTALL@
+install_sh_DATA = $(install_sh) -c -m 644
+install_sh_PROGRAM = $(install_sh) -c
+install_sh_SCRIPT = $(install_sh) -c
+INSTALL_HEADER = $(INSTALL_DATA)
+transform = $(program_transform_name)
+NORMAL_INSTALL = :
+PRE_INSTALL = :
+POST_INSTALL = :
+NORMAL_UNINSTALL = :
+PRE_UNINSTALL = :
+POST_UNINSTALL = :
+host_triplet = @host@
+ACLOCAL = @ACLOCAL@
+ALLOCA = @ALLOCA@
+AMDEP_FALSE = @AMDEP_FALSE@
+AMDEP_TRUE = @AMDEP_TRUE@
+AMTAR = @AMTAR@
+APACHE = @APACHE@
+APACHE_MODULES = @APACHE_MODULES@
+AR = @AR@
+AUTOCONF = @AUTOCONF@
+AUTOHEADER = @AUTOHEADER@
+AUTOMAKE = @AUTOMAKE@
+AWK = @AWK@
+CC = @CC@
+CCDEPMODE = @CCDEPMODE@
+CFLAGS = @CFLAGS@
+CGIBIN_DIR = @CGIBIN_DIR@
+COMMON_DIR = @COMMON_DIR@
+CONFIG_DIR = @CONFIG_DIR@
+CPP = @CPP@
+CPPFLAGS = @CPPFLAGS@
+CXX = @CXX@
+CXXCPP = @CXXCPP@
+CXXDEPMODE = @CXXDEPMODE@
+CXXFLAGS = @CXXFLAGS@
+CYGPATH_W = @CYGPATH_W@
+DATABASE_DIR = @DATABASE_DIR@
+DEFAULT_CONFIG_FILE = @DEFAULT_CONFIG_FILE@
+DEFS = @DEFS@
+DEPDIR = @DEPDIR@
+ECHO = @ECHO@
+ECHO_C = @ECHO_C@
+ECHO_N = @ECHO_N@
+ECHO_T = @ECHO_T@
+EGREP = @EGREP@
+EXEEXT = @EXEEXT@
+F77 = @F77@
+FFLAGS = @FFLAGS@
+FIND = @FIND@
+GUNZIP = @GUNZIP@
+HAVE_SSL = @HAVE_SSL@
+HTDIG_MAJOR_VERSION = @HTDIG_MAJOR_VERSION@
+HTDIG_MICRO_VERSION = @HTDIG_MICRO_VERSION@
+HTDIG_MINOR_VERSION = @HTDIG_MINOR_VERSION@
+IMAGE_DIR = @IMAGE_DIR@
+IMAGE_URL_PREFIX = @IMAGE_URL_PREFIX@
+INSTALL_DATA = @INSTALL_DATA@
+INSTALL_PROGRAM = @INSTALL_PROGRAM@
+INSTALL_SCRIPT = @INSTALL_SCRIPT@
+INSTALL_STRIP_PROGRAM = @INSTALL_STRIP_PROGRAM@
+LDFLAGS = @LDFLAGS@
+LEX = @LEX@
+LEXLIB = @LEXLIB@
+LEX_OUTPUT_ROOT = @LEX_OUTPUT_ROOT@
+LIBOBJS = @LIBOBJS@
+LIBS = @LIBS@
+LIBTOOL = @LIBTOOL@
+LN_S = @LN_S@
+LTLIBOBJS = @LTLIBOBJS@
+MAINT = @MAINT@
+MAINTAINER_MODE_FALSE = @MAINTAINER_MODE_FALSE@
+MAINTAINER_MODE_TRUE = @MAINTAINER_MODE_TRUE@
+MAKEINFO = @MAKEINFO@
+MV = @MV@
+OBJEXT = @OBJEXT@
+PACKAGE = @PACKAGE@
+PACKAGE_BUGREPORT = @PACKAGE_BUGREPORT@
+PACKAGE_NAME = @PACKAGE_NAME@
+PACKAGE_STRING = @PACKAGE_STRING@
+PACKAGE_TARNAME = @PACKAGE_TARNAME@
+PACKAGE_VERSION = @PACKAGE_VERSION@
+PATH_SEPARATOR = @PATH_SEPARATOR@
+PERL = @PERL@
+RANLIB = @RANLIB@
+RRDTOOL = @RRDTOOL@
+SEARCH_DIR = @SEARCH_DIR@
+SEARCH_FORM = @SEARCH_FORM@
+SED = @SED@
+SENDMAIL = @SENDMAIL@
+SET_MAKE = @SET_MAKE@
+SHELL = @SHELL@
+STRIP = @STRIP@
+TAR = @TAR@
+TESTS_FALSE = @TESTS_FALSE@
+TESTS_TRUE = @TESTS_TRUE@
+TIME = @TIME@
+TIMEV = @TIMEV@
+USER = @USER@
+VERSION = @VERSION@
+YACC = @YACC@
+ac_ct_AR = @ac_ct_AR@
+ac_ct_CC = @ac_ct_CC@
+ac_ct_CXX = @ac_ct_CXX@
+ac_ct_F77 = @ac_ct_F77@
+ac_ct_RANLIB = @ac_ct_RANLIB@
+ac_ct_STRIP = @ac_ct_STRIP@
+am__fastdepCC_FALSE = @am__fastdepCC_FALSE@
+am__fastdepCC_TRUE = @am__fastdepCC_TRUE@
+am__fastdepCXX_FALSE = @am__fastdepCXX_FALSE@
+am__fastdepCXX_TRUE = @am__fastdepCXX_TRUE@
+am__include = @am__include@
+am__leading_dot = @am__leading_dot@
+am__quote = @am__quote@
+bindir = @bindir@
+build = @build@
+build_alias = @build_alias@
+build_cpu = @build_cpu@
+build_os = @build_os@
+build_vendor = @build_vendor@
+datadir = @datadir@
+exec_prefix = @exec_prefix@
+extra_ldflags = @extra_ldflags@
+host = @host@
+host_alias = @host_alias@
+host_cpu = @host_cpu@
+host_os = @host_os@
+host_vendor = @host_vendor@
+includedir = @includedir@
+infodir = @infodir@
+install_sh = @install_sh@
+libdir = @libdir@
+libexecdir = @libexecdir@
+localstatedir = @localstatedir@
+mandir = @mandir@
+oldincludedir = @oldincludedir@
+prefix = @prefix@
+program_transform_name = @program_transform_name@
+sbindir = @sbindir@
+sharedstatedir = @sharedstatedir@
+subdirs = @subdirs@
+sysconfdir = @sysconfdir@
+target_alias = @target_alias@
+
+AUTOMAKE_OPTIONS = foreign no-dependencies
+
+INCLUDES = -DDEFAULT_CONFIG_FILE=\"$(DEFAULT_CONFIG_FILE)\" \
+		-I$(top_srcdir)/include -I$(top_srcdir)/htlib \
+		-I$(top_srcdir)/htnet -I$(top_srcdir)/htcommon \
+		-I$(top_srcdir)/htword \
+		-I$(top_srcdir)/db -I$(top_builddir)/db \
+		$(LOCAL_DEFINES) $(PROFILING)
+
+
+HTLIBS = $(top_builddir)/htnet/libhtnet.la \
+		$(top_builddir)/htcommon/libcommon.la \
+		$(top_builddir)/htword/libhtword.la \
+		$(top_builddir)/htlib/libht.la \
+		$(top_builddir)/htcommon/libcommon.la \
+		$(top_builddir)/htword/libhtword.la \
+		$(top_builddir)/db/libhtdb.la \
+		$(top_builddir)/htlib/libht.la
+
+
+#
+# Do not output #line because it confuses the dependencies
+# generator of GCC if configure run out of source tree. 
+# Comment these to ease debugging.
+#
+AM_LFLAGS = -L
+AM_YFLAGS = -l -d
+
+EXTRA_DIST = conf_lexer.cxx conf_parser.cxx
+
+pkglib_LTLIBRARIES = libcommon.la
+
+libcommon_la_SOURCES = DocumentDB.cc DocumentRef.cc \
+	HtWordReference.cc HtWordList.cc defaults.cc \
+	HtURLCodec.cc URL.cc URLTrans.cc \
+	HtZlibCodec.cc cgi.cc HtSGMLCodec.cc \
+	HtConfiguration.cc HtURLRewriter.cc \
+	conf_lexer.lxx conf_parser.yxx 
+
+
+libcommon_la_LDFLAGS = -release $(HTDIG_MAJOR_VERSION).$(HTDIG_MINOR_VERSION).$(HTDIG_MICRO_VERSION) ${extra_ldflags}
+
+noinst_HEADERS = DocumentDB.h \
+	DocumentRef.h \
+	HtWordReference.h \
+	HtWordList.h \
+	HtURLCodec.h \
+	HtSGMLCodec.h \
+	URL.h \
+	cgi.h \
+	HtZlibCodec.h \
+	defaults.h \
+	HtConfiguration.h \
+	HtURLRewriter.h \
+	conf_parser.h
+
+
+LOCAL_DEFINES = -DBIN_DIR=\"$(bindir)\" \
+		-DCOMMON_DIR=\"$(COMMON_DIR)\" \
+		-DCONFIG_DIR=\"$(CONFIG_DIR)\" \
+		-DDATABASE_DIR=\"$(DATABASE_DIR)\" \
+		-DIMAGE_URL_PREFIX=\"$(IMAGE_URL_PREFIX)\" 
+
+subdir = htcommon
+ACLOCAL_M4 = $(top_srcdir)/aclocal.m4
+mkinstalldirs = $(SHELL) $(top_srcdir)/mkinstalldirs
+CONFIG_HEADER = $(top_builddir)/include/config.h
+CONFIG_CLEAN_FILES =
+LTLIBRARIES = $(pkglib_LTLIBRARIES)
+
+libcommon_la_LIBADD =
+am_libcommon_la_OBJECTS = DocumentDB.lo DocumentRef.lo \
+	HtWordReference.lo HtWordList.lo defaults.lo HtURLCodec.lo \
+	URL.lo URLTrans.lo HtZlibCodec.lo cgi.lo HtSGMLCodec.lo \
+	HtConfiguration.lo HtURLRewriter.lo conf_lexer.lo \
+	conf_parser.lo
+libcommon_la_OBJECTS = $(am_libcommon_la_OBJECTS)
+
+DEFAULT_INCLUDES =  -I. -I$(srcdir) -I$(top_builddir)/include
+depcomp =
+am__depfiles_maybe =
+CXXCOMPILE = $(CXX) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) \
+	$(AM_CPPFLAGS) $(CPPFLAGS) $(AM_CXXFLAGS) $(CXXFLAGS)
+LTCXXCOMPILE = $(LIBTOOL) --mode=compile $(CXX) $(DEFS) \
+	$(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) \
+	$(AM_CXXFLAGS) $(CXXFLAGS)
+CXXLD = $(CXX)
+CXXLINK = $(LIBTOOL) --mode=link $(CXXLD) $(AM_CXXFLAGS) $(CXXFLAGS) \
+	$(AM_LDFLAGS) $(LDFLAGS) -o $@
+LEXCOMPILE = $(LEX) $(LFLAGS) $(AM_LFLAGS)
+LTLEXCOMPILE = $(LIBTOOL) --mode=compile $(LEX) $(LFLAGS) $(AM_LFLAGS)
+YACCCOMPILE = $(YACC) $(YFLAGS) $(AM_YFLAGS)
+LTYACCCOMPILE = $(LIBTOOL) --mode=compile $(YACC) $(YFLAGS) $(AM_YFLAGS)
+COMPILE = $(CC) $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) $(AM_CPPFLAGS) \
+	$(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS)
+LTCOMPILE = $(LIBTOOL) --mode=compile $(CC) $(DEFS) $(DEFAULT_INCLUDES) \
+	$(INCLUDES) $(AM_CPPFLAGS) $(CPPFLAGS) $(AM_CFLAGS) $(CFLAGS)
+CCLD = $(CC)
+LINK = $(LIBTOOL) --mode=link $(CCLD) $(AM_CFLAGS) $(CFLAGS) \
+	$(AM_LDFLAGS) $(LDFLAGS) -o $@
+DIST_SOURCES = $(libcommon_la_SOURCES)
+HEADERS = $(noinst_HEADERS)
+
+DIST_COMMON = $(noinst_HEADERS) $(srcdir)/Makefile.in \
+	$(top_srcdir)/Makefile.config Makefile.am conf_lexer.cxx \
+	conf_parser.cxx conf_parser.h
+SOURCES = $(libcommon_la_SOURCES)
+
+all: all-am
+
+.SUFFIXES:
+.SUFFIXES: .cc .cxx .lo .lxx .o .obj .yxx
+$(srcdir)/Makefile.in: @MAINTAINER_MODE_TRUE@ Makefile.am $(top_srcdir)/Makefile.config $(top_srcdir)/configure.in $(ACLOCAL_M4)
+	cd $(top_srcdir) && \
+	  $(AUTOMAKE) --foreign  htcommon/Makefile
+Makefile: @MAINTAINER_MODE_TRUE@ $(srcdir)/Makefile.in  $(top_builddir)/config.status
+	cd $(top_builddir) && $(SHELL) ./config.status $(subdir)/$@ $(am__depfiles_maybe)
+pkglibLTLIBRARIES_INSTALL = $(INSTALL)
+install-pkglibLTLIBRARIES: $(pkglib_LTLIBRARIES)
+	@$(NORMAL_INSTALL)
+	$(mkinstalldirs) $(DESTDIR)$(pkglibdir)
+	@list='$(pkglib_LTLIBRARIES)'; for p in $$list; do \
+	  if test -f $$p; then \
+	    f="`echo $$p | sed -e 's|^.*/||'`"; \
+	    echo " $(LIBTOOL) --mode=install $(pkglibLTLIBRARIES_INSTALL) $(INSTALL_STRIP_FLAG) $$p $(DESTDIR)$(pkglibdir)/$$f"; \
+	    $(LIBTOOL) --mode=install $(pkglibLTLIBRARIES_INSTALL) $(INSTALL_STRIP_FLAG) $$p $(DESTDIR)$(pkglibdir)/$$f; \
+	  else :; fi; \
+	done
+
+uninstall-pkglibLTLIBRARIES:
+	@$(NORMAL_UNINSTALL)
+	@list='$(pkglib_LTLIBRARIES)'; for p in $$list; do \
+	    p="`echo $$p | sed -e 's|^.*/||'`"; \
+	  echo " $(LIBTOOL) --mode=uninstall rm -f $(DESTDIR)$(pkglibdir)/$$p"; \
+	  $(LIBTOOL) --mode=uninstall rm -f $(DESTDIR)$(pkglibdir)/$$p; \
+	done
+
+clean-pkglibLTLIBRARIES:
+	-test -z "$(pkglib_LTLIBRARIES)" || rm -f $(pkglib_LTLIBRARIES)
+	@list='$(pkglib_LTLIBRARIES)'; for p in $$list; do \
+	  dir="`echo $$p | sed -e 's|/[^/]*$$||'`"; \
+	  test "$$dir" = "$$p" && dir=.; \
+	  echo "rm -f \"$${dir}/so_locations\""; \
+	  rm -f "$${dir}/so_locations"; \
+	done
+conf_parser.h: conf_parser.cxx
+	@if test ! -f $@; then \
+	  rm -f conf_parser.cxx; \
+	  $(MAKE) conf_parser.cxx; \
+	else :; fi
+libcommon.la: $(libcommon_la_OBJECTS) $(libcommon_la_DEPENDENCIES) 
+	$(CXXLINK) -rpath $(pkglibdir) $(libcommon_la_LDFLAGS) $(libcommon_la_OBJECTS) $(libcommon_la_LIBADD) $(LIBS)
+
+mostlyclean-compile:
+	-rm -f *.$(OBJEXT) core *.core
+
+distclean-compile:
+	-rm -f *.tab.c
+
+.cc.o:
+	$(CXXCOMPILE) -c -o $@ `test -f '$<' || echo '$(srcdir)/'`$<
+
+.cc.obj:
+	$(CXXCOMPILE) -c -o $@ `if test -f '$<'; then $(CYGPATH_W) '$<'; else $(CYGPATH_W) '$(srcdir)/$<'; fi`
+
+.cc.lo:
+	$(LTCXXCOMPILE) -c -o $@ `test -f '$<' || echo '$(srcdir)/'`$<
+
+.cxx.o:
+	$(CXXCOMPILE) -c -o $@ `test -f '$<' || echo '$(srcdir)/'`$<
+
+.cxx.obj:
+	$(CXXCOMPILE) -c -o $@ `if test -f '$<'; then $(CYGPATH_W) '$<'; else $(CYGPATH_W) '$(srcdir)/$<'; fi`
+
+.cxx.lo:
+	$(LTCXXCOMPILE) -c -o $@ `test -f '$<' || echo '$(srcdir)/'`$<
+
+.lxx.cxx:
+	$(LEXCOMPILE) `test -f $< || echo '$(srcdir)/'`$<
+	sed '/^#/ s|$(LEX_OUTPUT_ROOT)\.c|$@|' $(LEX_OUTPUT_ROOT).c >$@
+	rm -f $(LEX_OUTPUT_ROOT).c
+
+.yxx.cxx:
+	$(YACCCOMPILE) `test -f '$<' || echo '$(srcdir)/'`$<
+	if test -f y.tab.h; then \
+	  to=`echo "$*_H" | sed \
+                -e 'y/abcdefghijklmnopqrstuvwxyz/ABCDEFGHIJKLMNOPQRSTUVWXYZ/' \
+                -e 's/[^ABCDEFGHIJKLMNOPQRSTUVWXYZ]/_/g'`; \
+	  sed "/^#/ s/Y_TAB_H/$$to/g" y.tab.h >$*.ht; \
+	  rm -f y.tab.h; \
+	  if cmp -s $*.ht $*.h; then \
+	    rm -f $*.ht ;\
+	  else \
+	    mv $*.ht $*.h; \
+	  fi; \
+	fi
+	if test -f y.output; then \
+	  mv y.output $*.output; \
+	fi
+	sed '/^#/ s|y\.tab\.c|$@|' y.tab.c >$@t && mv $@t $@
+	rm -f y.tab.c
+
+mostlyclean-libtool:
+	-rm -f *.lo
+
+clean-libtool:
+	-rm -rf .libs _libs
+
+distclean-libtool:
+	-rm -f libtool
+uninstall-info-am:
+
+ETAGS = etags
+ETAGSFLAGS =
+
+CTAGS = ctags
+CTAGSFLAGS =
+
+tags: TAGS
+
+ID: $(HEADERS) $(SOURCES) $(LISP) $(TAGS_FILES)
+	list='$(SOURCES) $(HEADERS) $(LISP) $(TAGS_FILES)'; \
+	unique=`for i in $$list; do \
+	    if test -f "$$i"; then echo $$i; else echo $(srcdir)/$$i; fi; \
+	  done | \
+	  $(AWK) '    { files[$$0] = 1; } \
+	       END { for (i in files) print i; }'`; \
+	mkid -fID $$unique
+
+TAGS:  $(HEADERS) $(SOURCES)  $(TAGS_DEPENDENCIES) \
+		$(TAGS_FILES) $(LISP)
+	tags=; \
+	here=`pwd`; \
+	list='$(SOURCES) $(HEADERS)  $(LISP) $(TAGS_FILES)'; \
+	unique=`for i in $$list; do \
+	    if test -f "$$i"; then echo $$i; else echo $(srcdir)/$$i; fi; \
+	  done | \
+	  $(AWK) '    { files[$$0] = 1; } \
+	       END { for (i in files) print i; }'`; \
+	test -z "$(ETAGS_ARGS)$$tags$$unique" \
+	  || $(ETAGS) $(ETAGSFLAGS) $(AM_ETAGSFLAGS) $(ETAGS_ARGS) \
+	     $$tags $$unique
+
+ctags: CTAGS
+CTAGS:  $(HEADERS) $(SOURCES)  $(TAGS_DEPENDENCIES) \
+		$(TAGS_FILES) $(LISP)
+	tags=; \
+	here=`pwd`; \
+	list='$(SOURCES) $(HEADERS)  $(LISP) $(TAGS_FILES)'; \
+	unique=`for i in $$list; do \
+	    if test -f "$$i"; then echo $$i; else echo $(srcdir)/$$i; fi; \
+	  done | \
+	  $(AWK) '    { files[$$0] = 1; } \
+	       END { for (i in files) print i; }'`; \
+	test -z "$(CTAGS_ARGS)$$tags$$unique" \
+	  || $(CTAGS) $(CTAGSFLAGS) $(AM_CTAGSFLAGS) $(CTAGS_ARGS) \
+	     $$tags $$unique
+
+GTAGS:
+	here=`$(am__cd) $(top_builddir) && pwd` \
+	  && cd $(top_srcdir) \
+	  && gtags -i $(GTAGS_ARGS) $$here
+
+distclean-tags:
+	-rm -f TAGS ID GTAGS GRTAGS GSYMS GPATH tags
+DISTFILES = $(DIST_COMMON) $(DIST_SOURCES) $(TEXINFOS) $(EXTRA_DIST)
+
+top_distdir = ..
+distdir = $(top_distdir)/$(PACKAGE)-$(VERSION)
+
+distdir: $(DISTFILES)
+	$(mkinstalldirs) $(distdir)/..
+	@srcdirstrip=`echo "$(srcdir)" | sed 's|.|.|g'`; \
+	topsrcdirstrip=`echo "$(top_srcdir)" | sed 's|.|.|g'`; \
+	list='$(DISTFILES)'; for file in $$list; do \
+	  case $$file in \
+	    $(srcdir)/*) file=`echo "$$file" | sed "s|^$$srcdirstrip/||"`;; \
+	    $(top_srcdir)/*) file=`echo "$$file" | sed "s|^$$topsrcdirstrip/|$(top_builddir)/|"`;; \
+	  esac; \
+	  if test -f $$file || test -d $$file; then d=.; else d=$(srcdir); fi; \
+	  dir=`echo "$$file" | sed -e 's,/[^/]*$$,,'`; \
+	  if test "$$dir" != "$$file" && test "$$dir" != "."; then \
+	    dir="/$$dir"; \
+	    $(mkinstalldirs) "$(distdir)$$dir"; \
+	  else \
+	    dir=''; \
+	  fi; \
+	  if test -d $$d/$$file; then \
+	    if test -d $(srcdir)/$$file && test $$d != $(srcdir); then \
+	      cp -pR $(srcdir)/$$file $(distdir)$$dir || exit 1; \
+	    fi; \
+	    cp -pR $$d/$$file $(distdir)$$dir || exit 1; \
+	  else \
+	    test -f $(distdir)/$$file \
+	    || cp -p $$d/$$file $(distdir)/$$file \
+	    || exit 1; \
+	  fi; \
+	done
+check-am: all-am
+check: check-am
+all-am: Makefile $(LTLIBRARIES) $(HEADERS)
+
+installdirs:
+	$(mkinstalldirs) $(DESTDIR)$(pkglibdir)
+install: install-am
+install-exec: install-exec-am
+install-data: install-data-am
+uninstall: uninstall-am
+
+install-am: all-am
+	@$(MAKE) $(AM_MAKEFLAGS) install-exec-am install-data-am
+
+installcheck: installcheck-am
+install-strip:
+	$(MAKE) $(AM_MAKEFLAGS) INSTALL_PROGRAM="$(INSTALL_STRIP_PROGRAM)" \
+	  install_sh_PROGRAM="$(INSTALL_STRIP_PROGRAM)" INSTALL_STRIP_FLAG=-s \
+	  `test -z '$(STRIP)' || \
+	    echo "INSTALL_PROGRAM_ENV=STRIPPROG='$(STRIP)'"` install
+mostlyclean-generic:
+
+clean-generic:
+
+distclean-generic:
+	-rm -f $(CONFIG_CLEAN_FILES)
+
+maintainer-clean-generic:
+	@echo "This command is intended for maintainers to use"
+	@echo "it deletes files that may require special tools to rebuild."
+	-rm -f conf_lexer.cxx
+	-rm -f conf_parser.cxx
+	-rm -f conf_parser.h
+clean: clean-am
+
+clean-am: clean-generic clean-libtool clean-pkglibLTLIBRARIES \
+	mostlyclean-am
+
+distclean: distclean-am
+	-rm -f Makefile
+distclean-am: clean-am distclean-compile distclean-generic \
+	distclean-libtool distclean-tags
+
+dvi: dvi-am
+
+dvi-am:
+
+info: info-am
+
+info-am:
+
+install-data-am:
+
+install-exec-am: install-pkglibLTLIBRARIES
+
+install-info: install-info-am
+
+install-man:
+
+installcheck-am:
+
+maintainer-clean: maintainer-clean-am
+	-rm -f Makefile
+maintainer-clean-am: distclean-am maintainer-clean-generic
+
+mostlyclean: mostlyclean-am
+
+mostlyclean-am: mostlyclean-compile mostlyclean-generic \
+	mostlyclean-libtool
+
+pdf: pdf-am
+
+pdf-am:
+
+ps: ps-am
+
+ps-am:
+
+uninstall-am: uninstall-info-am uninstall-pkglibLTLIBRARIES
+
+.PHONY: CTAGS GTAGS all all-am check check-am clean clean-generic \
+	clean-libtool clean-pkglibLTLIBRARIES ctags distclean \
+	distclean-compile distclean-generic distclean-libtool \
+	distclean-tags distdir dvi dvi-am info info-am install \
+	install-am install-data install-data-am install-exec \
+	install-exec-am install-info install-info-am install-man \
+	install-pkglibLTLIBRARIES install-strip installcheck \
+	installcheck-am installdirs maintainer-clean \
+	maintainer-clean-generic mostlyclean mostlyclean-compile \
+	mostlyclean-generic mostlyclean-libtool pdf pdf-am ps ps-am \
+	tags uninstall uninstall-am uninstall-info-am \
+	uninstall-pkglibLTLIBRARIES
+
+# Tell versions [3.59,3.63) of GNU make to not export all variables.
+# Otherwise a system limit (for SysV at least) may be exceeded.
+.NOEXPORT:
diff --git a/debian/htdig/htdig-3.2.0b6/htcommon/Makefile.win32 b/debian/htdig/htdig-3.2.0b6/htcommon/Makefile.win32
new file mode 100644
index 00000000..62aef30c
--- /dev/null
+++ b/debian/htdig/htdig-3.2.0b6/htcommon/Makefile.win32
@@ -0,0 +1,25 @@
+
+TARGET = $(LIBDIR)/libcommon$(LIBSFX)
+
+# ----------------------------------------------------------------------------
+# add new library members to this list
+
+# ----------------------------------------------------------------------------
+
+include ../Makedefs.win32
+
+CXXSRC = DocumentDB.cc DocumentRef.cc HtWordReference.cc \
+    HtWordList.cc defaults.cc HtURLCodec.cc URL.cc URLTrans.cc \
+	HtZlibCodec.cc cgi.cc HtSGMLCodec.cc HtConfiguration.cc \
+    HtURLRewriter.cc 
+
+LXXSRC = conf_lexer.lxx
+YXXSRC = conf_parser.yxx
+
+CPPFLAGS += -DYY_NEVER_INTERACTIVE -DHAVE_CONFIG_H -I../db -I../htlib -I../htword
+
+$(TARGET): $(OBJDIRDEP) $(LIBDIRDEP) $(OBJS)
+	$(AR) $(ARFLAGS) $(OBJS)
+
+include ../Makerules.win32
+
diff --git a/debian/htdig/htdig-3.2.0b6/htcommon/URL.cc b/debian/htdig/htdig-3.2.0b6/htcommon/URL.cc
new file mode 100644
index 00000000..9ccbe5d5
--- /dev/null
+++ b/debian/htdig/htdig-3.2.0b6/htcommon/URL.cc
@@ -0,0 +1,936 @@
+//
+// URL.cc
+//
+// URL: A URL parsing class, implementing as closely as possible the standard
+//      laid out in RFC2396 (e.g. http://www.faqs.org/rfcs/rfc2396.html)
+//      including support for multiple services. (schemes in the RFC)
+//
+// Part of the ht://Dig package   <http://www.htdig.org/>
+// Copyright (c) 1995-2004 The ht://Dig Group
+// For copyright details, see the file COPYING in your distribution
+// or the GNU Library General Public License (LGPL) version 2 or later 
+// <http://www.gnu.org/copyleft/lgpl.html>
+//
+// $Id: URL.cc,v 1.16 2004/06/04 08:51:01 angusgb Exp $
+//
+
+#ifdef HAVE_CONFIG_H
+#include "htconfig.h"
+#endif /* HAVE_CONFIG_H */
+
+#include "URL.h"
+#include "QuotedStringList.h"
+#include "Dictionary.h"
+#include "HtConfiguration.h"
+#include "StringMatch.h"
+#include "StringList.h"
+#include "HtURLRewriter.h"
+
+#include <string.h>
+#include <stdlib.h>
+#include <stdio.h>
+
+#ifdef HAVE_STD
+#include <fstream>
+#ifdef HAVE_NAMESPACES
+using namespace std;
+#endif
+#else
+#include <fstream.h>
+#endif /* HAVE_STD */
+
+#include <sys/types.h>
+#include <ctype.h>
+
+#ifndef _MSC_VER /* _WIN32 */
+#include <sys/socket.h>
+#include <netdb.h>
+#include <arpa/inet.h>
+#endif
+
+#define NNTP_DEFAULT_PORT 119
+
+static Dictionary	*slashCount = 0;
+
+//*****************************************************************************
+// URL::URL()
+// Default Constructor
+//
+URL::URL()
+: _url(0),
+    _path(0),
+    _service(0),
+    _host(0),
+    _port(0),
+    _normal(0),
+    _hopcount(0),
+    _signature(0),
+    _user(0)
+{
+}
+
+
+//*****************************************************************************
+// URL::URL(const URL& rhs)
+// Copy constructor
+//
+URL::URL(const URL& rhs)
+: _url(rhs._url),
+    _path(rhs._path),
+    _service(rhs._service),
+    _host(rhs._host),
+    _port(rhs._port),
+    _normal(rhs._normal),
+    _hopcount(rhs._hopcount),
+    _signature(rhs._signature),
+    _user(rhs._user)
+{
+}
+
+
+//*****************************************************************************
+// URL::URL(const String &nurl)
+// Construct a URL from a String (obviously parses the string passed in)
+// 
+URL::URL(const String &nurl)
+: _url(0),
+    _path(0),
+    _service(0),
+    _host(0),
+    _port(0),
+    _normal(0),
+    _hopcount(0),
+    _signature(0),
+    _user(0)
+{
+    parse(nurl);
+}
+
+
+//*****************************************************************************
+// Assignment operator
+const URL &URL::operator = (const URL &rhs)
+{
+	if (this == &rhs)
+		return *this;
+
+	// Copy the attributes
+	_url = rhs._url;
+	_path = rhs._path;
+	_service = rhs._service;
+	_host = rhs._host;
+	_port = rhs._port;
+	_normal = rhs._normal;
+	_hopcount = rhs._hopcount;
+	_signature = rhs._signature;
+	_user = rhs._user;
+
+	return *this;
+}
+
+//*****************************************************************************
+// URL::URL(const String &url, const URL &parent)
+//   Parse a reference given a parent url.  This is needed to resolve relative
+//   references which do NOT have a full url.
+//
+URL::URL(const String &url, const URL &parent)
+: _url(0),
+    _path(0),
+    _service(parent._service),
+    _host(parent._host),
+    _port(parent._port),
+    _normal(parent._normal),
+    _hopcount(parent._hopcount + 1), // Since this is one hop *after* the parent, we should account for this
+    _signature(parent._signature),
+    _user(parent._user)
+{
+	HtConfiguration* config= HtConfiguration::config();
+    int  allowspace = config->Boolean("allow_space_in_url", 0);
+    String      temp;
+    const char *urp = url.get();
+    while (*urp)
+    {
+	if (*urp == ' ' && temp.length() > 0 && allowspace)
+	{
+	    // Replace space character with %20 if there's more non-space
+	    // characters to come...
+	    const char *s = urp+1;
+	    while (*s && isspace(*s))
+		s++;
+	    if (*s)
+		temp << "%20";
+	}
+	else if (!isspace(*urp))
+	    temp << *urp;
+	urp++;
+    }
+    char* ref = temp;
+
+    //
+    // Strip any optional anchor from the reference.  If, however, the
+    // reference contains CGI parameters after the anchor, the parameters
+    // will be moved left to replace the anchor.  The overall effect is that
+    // the anchor is removed.
+    // Thanks goes to David Filiatrault <[email protected]> for suggesting
+    // this removal process.
+    //
+    char	*anchor = strchr(ref, '#');
+    char	*params = strchr(ref, '?');
+    if (anchor)
+    {
+	*anchor = '\0';
+	if (params)
+	{
+	    if (anchor < params)
+	    {
+		while (*params)
+		{
+		    *anchor++ = *params++;
+		}
+		*anchor = '\0';
+	    }
+	}
+    }
+
+    //
+    // If, after the removal of a possible '#' we have nothing left,
+    // we just want to use the base URL (we're on the same page but
+    // different anchors)
+    //
+    if (!*ref)
+    {
+        // We've already copied much of the info
+	_url = parent._url;
+	_path = parent._path;
+	// Since this is on the same page, we want the same hopcount
+	_hopcount = parent._hopcount;
+	return;
+    }
+
+    // OK, now we need to work out what type of child URL this is
+    char	*p = ref;
+    while (isalpha(*p))  // Skip through the service portion
+	p++;
+    int	hasService = (*p == ':');
+    	// Why single out http?  Shouldn't others be the same?
+	// Child URL of the form  https:/child  or  ftp:child  called "full"
+	// How about using slashes()?
+    if (hasService && ((strncmp(ref, "http://", 7) == 0) ||
+		       (strncmp(ref, "http:", 5) != 0)))
+    {
+	//
+	// No need to look at the parent url since this is a complete url...
+	//
+	parse(ref);
+    }
+    else if (strncmp(ref, "//", 2) == 0)
+    {
+	// look at the parent url's _service, to make this is a complete url...
+	String	fullref(parent._service);
+	fullref << ':' << ref;
+	parse((char*)fullref);
+    }
+    else
+    {
+	if (hasService)
+	    ref = p + 1;	// Relative URL, skip "http:"
+
+	if (*ref == '/')
+	{
+	    //
+	    // The reference is on the same server as the parent, but
+	    // an absolute path was given...
+	    //
+	    _path = ref;
+
+            //
+            // Get rid of loop-causing constructs in the path
+            //
+            normalizePath();
+	}
+	else
+	{
+	    //
+	    // The reference is relative to the parent
+	    //
+
+	    _path = parent._path;
+	    int i = _path.indexOf('?');
+	    if (i >= 0)
+	    {
+		_path.chop(_path.length() - i);
+	    }
+
+	    //
+	    // Remove any leading "./" sequences which could get us into
+	    // recursive loops.
+	    //
+	    while (strncmp(ref, "./", 2) == 0)
+		ref += 2;
+
+	    if (_path.last() == '/')
+	    {
+		//
+		// Parent was a directory.  Easy enough: just append
+		// the current ref to it
+		//
+		_path << ref;
+	    }
+	    else
+	    {
+		//
+		// Parent was a file.  We need to strip the last part
+		// of the path before we add the reference to it.
+		//
+		String	temp = _path;
+		p = strrchr((char*)temp, '/');
+		if (p)
+		{
+		    p[1] = '\0';
+		    _path = temp.get();
+		    _path << ref;
+		}
+		else
+		{
+		    //
+		    // Something must be wrong since there were no '/'
+		    // found in the parent url.
+		    //
+		    // We do nothing here.  The new url is the parent.
+		    //
+		}
+	    }
+
+            //
+            // Get rid of loop-causing constructs in the path
+            //
+            normalizePath();
+	}
+
+	//
+	// Build the url.  (Note, the host name has NOT been normalized!)
+	// No need for this if we have called URL::parse.
+	//
+	constructURL();
+    }
+}
+
+
+//*****************************************************************************
+// void URL::rewrite()
+//
+void URL::rewrite()
+{
+	if (HtURLRewriter::instance()->replace(_url) > 0)
+		parse(_url.get());
+}
+
+
+//*****************************************************************************
+// void URL::parse(const String &u)
+//   Given a URL string, extract the service, host, port, and path from it.
+//
+void URL::parse(const String &u)
+{
+	HtConfiguration* config= HtConfiguration::config();
+    int  allowspace = config->Boolean("allow_space_in_url", 0);
+    String	temp;
+    const char *urp = u.get();
+    while (*urp)
+    {
+	if (*urp == ' ' && temp.length() > 0 && allowspace)
+	{
+	    // Replace space character with %20 if there's more non-space
+	    // characters to come...
+	    const char *s = urp+1;
+	    while (*s && isspace(*s))
+		s++;
+	    if (*s)
+		temp << "%20";
+	}
+	else if (!isspace(*urp))
+	    temp << *urp;
+	urp++;
+    }
+    char	*nurl = temp;
+
+    //
+    // Ignore any part of the URL that follows the '#' since this is just
+    // an index into a document.
+    //
+    char	*p = strchr(nurl, '#');
+    if (p)
+	*p = '\0';
+
+    // Some members need to be reset.  If not, the caller would
+    // have used URL::URL(char *ref, URL &parent)
+    // (which may call us, if the URL is found to be absolute).
+    _normal = 0;
+    _signature = 0;
+    _user = 0;
+
+    //
+    // Extract the service
+    //
+    p = strchr(nurl, ':');
+    if (p)
+    {
+	_service = strtok(nurl, ":");
+	p = strtok(0, "\n");
+    }
+    else
+    {
+	_service = "http";
+	p = strtok(nurl, "\n");
+    }
+    _service.lowercase();
+
+    //
+    // Extract the host
+    //
+    if (!p || strncmp(p, "//", 2) != 0)
+    {
+	// No host specified, it's all a path.
+	_host = 0;
+	_port = 0;
+	_url = 0;
+	if (p)		// if non-NULL, skip (some) leading slashes in path
+	{
+	    int i;
+	    for (i = slashes (_service); i > 0 && *p == '/'; i--)
+		p++;
+	    if (i)	// if fewer slashes than specified for protocol don't
+			// delete any. -> Backwards compatible (necessary??)
+		p -= slashes (_service) - i;
+	}
+	_path = p;
+	if (strcmp((char*)_service, "file") == 0 || slashes (_service) < 2)
+	  _host = "localhost";
+    }
+    else
+    {
+	p += 2;
+
+	//
+	// p now points to the host
+	//
+	char	*q = strchr(p, ':');
+	char	*slash = strchr(p, '/');
+    
+	_path = "/";
+	if (strcmp((char*)_service, "file") == 0)
+	  {
+	    // These should be of the form file:/// (i.e. no host)
+	    // if there is a file://host/path then strip the host
+	    if (strncmp(p, "/", 1) != 0)
+	      {
+		p = strtok(p, "/");
+		_path << strtok(0, "\n");
+	      }
+	    else
+	      _path << strtok(p+1, "\n");	// _path is "/" - don't double
+	    _host = "localhost";
+	    _port = 0;
+	  }
+	else if (q && ((slash && slash > q) || !slash))
+	{
+	    _host = strtok(p, ":");
+	    p = strtok(0, "/");
+	    if (p)
+	      _port = atoi(p);
+	    if (!p || _port <= 0)
+               _port = DefaultPort();
+	    //
+	    // The rest of the input string is the path.
+	    //
+	    _path << strtok(0, "\n");
+
+	}
+	else
+	{
+	    _host = strtok(p, "/");
+	    _host.chop(" \t");
+            _port = DefaultPort();
+
+	    //
+	    // The rest of the input string is the path.
+	    //
+	    _path << strtok(0, "\n");
+
+	}
+
+	// Check to see if host contains a user@ portion
+	int atMark = _host.indexOf('@');
+	if (atMark != -1)
+	  {
+	    _user = _host.sub(0, atMark);
+	    _host = _host.sub(atMark + 1);
+	  }
+    }
+
+    //
+    // Get rid of loop-causing constructs in the path
+    //
+    normalizePath();
+
+    //
+    // Build the url.  (Note, the host name has NOT been normalized!)
+    //
+    constructURL();
+}
+
+
+//*****************************************************************************
+// void URL::normalizePath()
+// Called from: URL(const String &url, const URL &parent)
+//
+void URL::normalizePath()
+{
+    //
+    // Rewrite the path to be the minimal.
+    // Remove "//", "/../" and "/./" components
+    //
+	HtConfiguration* config= HtConfiguration::config();
+
+    int	i, limit;
+    int	leadingdotdot = 0;
+    String	newPath;
+    int	pathend = _path.indexOf('?');	// Don't mess up query strings.
+    if (pathend < 0)
+        pathend = _path.length();
+
+    //
+    // get rid of "//" first, or "/foo//../" will become "/foo/" not "/"
+    // Some database lookups interpret empty paths (// != /), so give
+    // the use the option to turn this off.
+    //
+    if (!config->Boolean ("allow_double_slash"))
+	while ((i = _path.indexOf("//")) >= 0 && i < pathend)
+	{
+	    newPath = _path.sub(0, i).get();
+	    newPath << _path.sub(i + 1).get();
+	    _path = newPath;
+	    pathend = _path.indexOf('?');
+	    if (pathend < 0)
+		pathend = _path.length();
+	}
+
+    //
+    // Next get rid of redundant "/./".  This could cause infinite
+    // loops.  Moreover, "/foo/./../" should become "/", not "/foo/"
+    //
+    while ((i = _path.indexOf("/./")) >= 0 && i < pathend)
+    {
+        newPath = _path.sub(0, i).get();
+        newPath << _path.sub(i + 2).get();
+        _path = newPath;
+        pathend = _path.indexOf('?');
+        if (pathend < 0)
+            pathend = _path.length();
+    }
+    if ((i = _path.indexOf("/.")) >= 0 && i == pathend-2)
+    {
+        newPath = _path.sub(0, i+1).get();		// keep trailing slash
+        newPath << _path.sub(i + 2).get();
+        _path = newPath;
+        pathend--;
+    }
+
+    //
+    // Now that "empty" path components are gone, remove ("/../").
+    //
+    while ((i = _path.indexOf("/../")) >= 0 && i < pathend)
+    {
+        if ((limit = _path.lastIndexOf('/', i - 1)) >= 0)
+        {
+            newPath = _path.sub(0, limit).get();
+            newPath << _path.sub(i + 3).get();
+            _path = newPath;
+        }
+        else
+        {
+            _path = _path.sub(i + 3).get();
+            leadingdotdot++;
+        }
+        pathend = _path.indexOf('?');
+        if (pathend < 0)
+            pathend = _path.length();
+    }
+    if ((i = _path.indexOf("/..")) >= 0 && i == pathend-3)
+    {
+        if ((limit = _path.lastIndexOf('/', i - 1)) >= 0)
+            newPath = _path.sub(0, limit+1).get();	// keep trailing slash
+        else
+        {
+            newPath = '/';
+            leadingdotdot++;
+        }
+        newPath << _path.sub(i + 3).get();
+        _path = newPath;
+        pathend = _path.indexOf('?');
+        if (pathend < 0)
+            pathend = _path.length();
+    }
+    // The RFC gives us a choice of what to do when we have .. left and
+    // we're at the top level. By principle of least surprise, we'll just
+    // toss any "leftovers" Otherwise, we'd have a loop here to add them.
+
+    // Finally change all "%7E" to "~" for sanity
+    while ((i = _path.indexOf("%7E")) >= 0 && i < pathend)
+      {
+        newPath = _path.sub(0, i).get();
+	newPath << "~";
+        newPath << _path.sub(i + 3).get();
+        _path = newPath;
+        pathend = _path.indexOf('?');
+        if (pathend < 0)
+            pathend = _path.length();
+      }
+
+    // If the server *isn't* case sensitive, we want to lowercase the path
+    if (!config->Boolean("case_sensitive", 1))
+      _path.lowercase();
+
+    // And don't forget to remove index.html or similar file.
+//    if (strcmp((char*)_service, "file") != 0)  (check is now internal)
+	removeIndex(_path, _service);
+}
+
+//*****************************************************************************
+// void URL::dump()
+//
+void URL::dump()
+{
+    cout << "service = " << _service.get() << endl;
+    cout << "user = " << _user.get() << endl;
+    cout << "host = " << _host.get() << endl;
+    cout << "port = " << _port << endl;
+    cout << "path = " << _path << endl;
+    cout << "url = " << _url << endl;
+}
+
+
+//*****************************************************************************
+// void URL::path(const String &newpath)
+//
+void URL::path(const String &newpath)
+{
+	HtConfiguration* config= HtConfiguration::config();
+    _path = newpath;
+    if (!config->Boolean("case_sensitive",1))
+      _path.lowercase();
+    constructURL();
+}
+
+
+//*****************************************************************************
+// void URL::removeIndex(String &path, String &service)
+//   Attempt to remove the remove_default_doc from the end of a URL path if
+//   the service allows that.  (File, ftp don't.  Do others?)
+//   This needs to be done to normalize the paths and make .../ the
+//   same as .../index.html
+// Called from: URL::normalize() from URL::signature()  [redundant?]
+// 		URL::normalizePath()
+//
+void URL::removeIndex(String &path, String &service)
+{
+	HtConfiguration* config= HtConfiguration::config();
+    static StringMatch *defaultdoc = 0;
+
+    if (strcmp((char*)_service, "file") == 0 ||
+        strcmp((char*)_service, "ftp")  == 0)
+	return;
+
+    if (path.length() == 0 || strchr((char*)path, '?'))
+	return;
+
+    int filename = path.lastIndexOf('/') + 1;
+    if (filename == 0)
+        return;
+
+    if (! defaultdoc)
+    {
+      StringList  l(config->Find("remove_default_doc"), " \t");
+      defaultdoc = new StringMatch();
+      defaultdoc->IgnoreCase();
+      defaultdoc->Pattern(l.Join('|'));
+    }
+    int which, length;
+    if (defaultdoc->hasPattern() &&
+	    defaultdoc->CompareWord((char*)path.sub(filename), which, length) &&
+	    filename+length == path.length())
+	path.chop(path.length() - filename);
+}
+
+
+//*****************************************************************************
+// void URL::normalize()
+//   Make sure that URLs are always in the same format.
+//
+void URL::normalize()
+{
+	HtConfiguration* config= HtConfiguration::config();
+    static int	hits = 0, misses = 0;
+
+    if (_service.length() == 0 || _normal)
+	return;
+
+    
+//  if (strcmp((char*)_service, "http") != 0)
+    // if service specifies "doesn't specify an IP host", don't normalize it
+    if (slashes (_service) != 2)
+	return;
+
+//    if (strcmp ((char*)_service, "http") == 0)  (check is now internal)
+	removeIndex(_path, _service);
+
+    //
+    // Convert a hostname to an IP address
+    //
+    _host.lowercase();
+
+    if (!config->Boolean("allow_virtual_hosts", 1))
+    {
+	static Dictionary	hostbyname;
+	unsigned long		addr;
+	struct hostent		*hp;
+
+	String	*ip = (String *) hostbyname[_host];
+	if (ip)
+	{
+	    memcpy((char *) &addr, ip->get(), ip->length());
+	    hits++;
+	}
+	else
+	{
+	    addr = inet_addr(_host.get());
+	    if (addr == 0xffffffff)
+	    {
+		hp = gethostbyname(_host.get());
+		if (hp == NULL)
+		{
+		    return;
+		}
+		memcpy((char *)&addr, (char *)hp->h_addr, hp->h_length);
+		ip = new String((char *) &addr, hp->h_length);
+		hostbyname.Add(_host, ip);
+		misses++;
+	    }
+	}
+
+	static Dictionary	machines;
+	String			key;
+	key << int(addr);
+	String			*realname = (String *) machines[key];
+	if (realname)
+	    _host = realname->get();
+	else
+	    machines.Add(key, new String(_host));
+    }
+    ServerAlias();
+    
+    //
+    // Reconstruct the url
+    //
+    constructURL();
+    _normal = 1;
+    _signature = 0;
+}
+
+
+//*****************************************************************************
+// const String &URL::signature()
+//   Return a string which uniquely identifies the server the current
+//   URL is refering to.
+//   This is the first portion of a url: service://user@host:port/
+//   (in short this is the URL pointing to the root of this server)
+//
+const String &URL::signature()
+{
+    if (_signature.length())
+	return _signature;
+
+    if (!_normal)
+	normalize();
+    _signature = _service;
+    _signature << "://";
+    if (_user.length())
+      _signature << _user << '@';
+    _signature << _host;
+    _signature << ':' << _port << '/';
+    return _signature;
+}
+
+//*****************************************************************************
+// void URL::ServerAlias()
+// Takes care of the server aliases, which attempt to simplify virtual
+// host problems
+//
+void URL::ServerAlias()
+{
+  HtConfiguration* config= HtConfiguration::config();
+  static Dictionary *serveraliases= 0;
+
+  if (! serveraliases)
+    {
+      String l= config->Find("server_aliases");
+      String from, *to;
+      serveraliases = new Dictionary();
+      char *p = strtok(l, " \t");
+      char *salias= NULL;
+      while (p)
+	{
+	  salias = strchr(p, '=');
+	  if (! salias)
+	    {
+	      p = strtok(0, " \t");
+	      continue;
+	    }
+	  *salias++= '\0';
+	  from = p;
+	  from.lowercase();
+	  if (from.indexOf(':') == -1)
+	    from.append(":80");
+	  to= new String(salias);
+	  to->lowercase();
+	  if (to->indexOf(':') == -1)
+	    to->append(":80");
+	  serveraliases->Add(from.get(), to);
+	  // fprintf (stderr, "Alias: %s->%s\n", from.get(), to->get());
+	  p = strtok(0, " \t");
+	}
+    }
+
+  String *al= 0;
+  int newport;
+  int delim;
+  String serversig = _host;
+  serversig << ':' << _port;
+  if ((al= (String *) serveraliases->Find(serversig)))
+    {
+      delim= al->indexOf(':');
+      // fprintf(stderr, "\nOld URL: %s->%s\n", (char *) serversig, (char *) *al);
+      _host= al->sub(0,delim).get();
+      sscanf((char*)al->sub(delim+1), "%d", &newport);
+      _port= newport;
+      // fprintf(stderr, "New URL: %s:%d\n", (char *) _host, _port);
+    }
+}
+
+//*****************************************************************************
+// int URL::slash(const String &protocol)
+// Returns number of slashes folowing the service name for protocol
+//
+int
+URL::slashes(const String &protocol)
+{
+    if (!slashCount)
+    {
+	HtConfiguration* config= HtConfiguration::config();
+	slashCount = new Dictionary();
+
+	slashCount->Add (String("mailto"), new String("0"));
+	slashCount->Add (String("news"),   new String("0"));
+	slashCount->Add (String("http"),   new String("2"));
+	slashCount->Add (String("ftp"),    new String("2"));
+	// file:///  has three, but the last counts as part of the path...
+	slashCount->Add (String("file"),   new String("2"));
+	
+	QuotedStringList	qsl(config->Find("external_protocols"), " \t");
+	String			from;
+	int			i;
+	int			sep,colon;
+
+	for (i = 0; qsl[i]; i += 2)
+	{
+	    from = qsl[i];
+	    sep = from.indexOf("->");
+	    if (sep != -1)
+		from = from.sub(0, sep).get();  // "get" aids portability...
+
+	    colon = from.indexOf(":");
+	    // if service specified as "help:/" or "man:", note trailing slashes
+	    // Default is 2.
+	    if (colon != -1)
+	    {
+		int i;
+		char count [2];
+		for (i = colon+1; from[i] == '/'; i++)
+		    ;
+		count [0] = i - colon + '0' - 1;
+		count [1] = '\0';
+		from = from.sub(0,colon).get();
+		slashCount->Add (from, new String (count));
+	    } else
+		slashCount->Add (from, new String ("2"));
+	}
+    }
+    
+    // Default to two slashes for unknown protocols
+    String *count = (String *)slashCount->Find(protocol);
+    return count ? (count->get()[0] - '0') : 2;
+}
+
+//*****************************************************************************
+// void URL::constructURL()
+// Constructs the _url member from everything else
+// Also ensures the port number is correct for the service
+// Called from  URL::URL(const String &url, const URL &parent)
+//		URL::parse(const String &u)
+//		URL::path(const String &newpath)
+//		URL::normalize()
+//
+void URL::constructURL()
+{
+    if (strcmp((char*)_service, "file") != 0 && _host.length() == 0) {
+	_url = "";
+	return;
+    }
+
+    _url = _service;
+    _url << ":";
+
+    // Add correct number of slashes after service name
+    int i;
+    for (i = slashes (_service); i > 0; i--)
+    {
+	_url << "/";
+    }
+
+    if (slashes (_service) == 2)	// services specifying a particular
+    {					// IP host must begin "service://"
+	if (strcmp((char*)_service, "file") != 0)
+	  {
+	    if (_user.length())
+	      _url << _user << '@';
+	    _url << _host;
+	  }
+
+       if (_port != DefaultPort() && _port != 0)  // Different than the default port
+	  _url << ':' << _port;
+    }
+
+    _url << _path;
+}
+
+
+///////
+   //    Get the default port for the recognised service
+///////
+
+int URL::DefaultPort()
+{
+   if (strcmp((char*)_service, "http") == 0)
+      return 80;
+   else if (strcmp((char*)_service, "https") == 0)
+      return 443;
+   else if (strcmp((char*)_service, "ftp") == 0)
+      return 21;
+   else if (strcmp((char*)_service, "gopher") == 0)
+      return 70;
+   else if (strcmp((char*)_service, "file") == 0)
+      return 0;
+   else if (strcmp((char*)_service, "news") == 0)
+      return NNTP_DEFAULT_PORT;
+   else return 80;
+}
diff --git a/debian/htdig/htdig-3.2.0b6/htcommon/URL.h b/debian/htdig/htdig-3.2.0b6/htcommon/URL.h
new file mode 100644
index 00000000..4cea16ee
--- /dev/null
+++ b/debian/htdig/htdig-3.2.0b6/htcommon/URL.h
@@ -0,0 +1,100 @@
+//
+// URL.h
+//
+// URL: A URL parsing class, implementing as closely as possible the standard
+//      laid out in RFC2396 (e.g. http://www.faqs.org/rfcs/rfc2396.html)
+//      including support for multiple schemes.
+//
+// Part of the ht://Dig package   <http://www.htdig.org/>
+// Copyright (c) 1995-2004 The ht://Dig Group
+// For copyright details, see the file COPYING in your distribution
+// or the GNU Library General Public License (LGPL) version 2 or later 
+// <http://www.gnu.org/copyleft/lgpl.html>
+//
+// $Id: URL.h,v 1.8 2004/05/28 13:15:12 lha Exp $
+//
+
+#ifndef _URL_h_
+#define _URL_h_
+
+#include "htString.h"
+
+class URL
+{
+public:
+    URL();
+    URL(const String &url);
+    URL(const URL& rhs);
+    URL(const String &ref, const URL &parent);
+
+    void parse(const String &url);
+
+    const String &host() const      {return _host;}
+    void host(const String &h)      {_host = h;}
+    
+    int port() const                {return _port;}
+    void port(const int p)          {_port = p;}
+    int DefaultPort();
+    
+    const String &service() const   {return _service;}
+    void service(const String &s)   {_service = s;}
+
+    const String &path() const      {return _path;}
+    void path(const String &p);
+    
+    int hopcount() const            {return _hopcount;}
+    void hopcount(int h)            {_hopcount = h;}
+    
+    const String &user() const      {return _user;}
+    void user(const String &u)      {_user = u;}
+
+    const String &get() const {return _url;}
+    void		dump();
+    void		normalize();
+    void		rewrite();
+    const String &signature();
+
+    const URL &operator = (const URL &rhs);
+
+private:
+    String		_url;
+    String		_path;
+    String		_service;
+    String		_host;
+    int			_port;
+    int			_normal;
+    int			_hopcount;
+    String		_signature;
+    String		_user;
+
+    void		removeIndex(String &, String &);
+    void                normalizePath();
+    void		ServerAlias();
+    void		constructURL();
+    // Number of slashes following service specifier.  eg service("http")=2
+    static int		slashes(const String &);
+};
+
+
+// Unreserved punctuation allowed unencoded in URLs.  We use a more restricted
+// list of unreserved characters than allowed by RFC 2396 (which revises and
+// replaces RFC 1738), because it can't hurt to encode any of these
+// characters, and they can pose problems in some contexts.  RFC 2396 says
+// that only alphanumerics, the unreserved characters "-_.!~*'(),", and
+// reserved characters used for their reserved purposes may be used
+// unencoded within a URL.  We encode reserved characters because we now
+// encode URL parameter values individually before piecing together the whole
+// query string using reserved characters.
+
+#define UNRESERVED	"-_.!~*"
+
+//String &encodeURL(String &, char *valid = "?_@.=&/:");
+//String &encodeURL(String &, char *reserved = ";/?:@&=+$,");
+//	       	              char *unreserved = "-_.!~*'()");
+String &encodeURL(String &, char *valid = (char *)UNRESERVED);
+
+String &decodeURL(String &);
+
+#endif
+
+
diff --git a/debian/htdig/htdig-3.2.0b6/htcommon/URLTrans.cc b/debian/htdig/htdig-3.2.0b6/htcommon/URLTrans.cc
new file mode 100644
index 00000000..82515177
--- /dev/null
+++ b/debian/htdig/htdig-3.2.0b6/htcommon/URLTrans.cc
@@ -0,0 +1,93 @@
+//
+// URLTrans.cc
+//
+// URLTrans: Helper functions for the implementation of the URL class.
+//
+// Part of the ht://Dig package   <http://www.htdig.org/>
+// Copyright (c) 1995-2004 The ht://Dig Group
+// For copyright details, see the file COPYING in your distribution
+// or the GNU Library General Public License (LGPL) version 2 or later 
+// <http://www.gnu.org/copyleft/lgpl.html>
+//
+// $Id: URLTrans.cc,v 1.5 2004/05/28 13:15:12 lha Exp $
+//
+
+#ifdef HAVE_CONFIG_H
+#include "htconfig.h"
+#endif /* HAVE_CONFIG_H */
+
+#include "URL.h"
+#include "htString.h"
+#include "lib.h"
+
+#include <ctype.h>
+
+
+//*****************************************************************************
+// String &decodeURL(String &str)
+//   Convert the given URL string to a normal string.  This means that
+//   all escaped characters are converted to their normal values.  The
+//   escape character is '%' and is followed by 2 hex digits
+//   representing the octet.
+//
+String &decodeURL(String &str)
+{
+    String	temp;
+    char	*p;
+
+    for (p = str; p && *p; p++)
+    {
+	if (*p == '%')
+	{
+	    //
+	    // 2 hex digits follow...
+	    //
+	    int		value = 0;
+	    for (int i = 0; p[1] && i < 2; i++)
+	    {
+		p++;
+		value <<= 4;
+		if (isdigit(*p))
+		    value += *p - '0';
+		else
+		    value += toupper(*p) - 'A' + 10;
+	    }
+	    temp << char(value);
+	}
+	else
+	    temp << *p;
+    }
+    str = temp;
+    return (str);
+}
+
+
+//*****************************************************************************
+// String &encodeURL(String &str, char *valid)
+//   Convert a normal string to a URL 'safe' string.  This means that
+//   all characters not explicitly mentioned in the URL BNF will be
+//   escaped.  The escape character is '%' and is followed by 2 hex
+//   digits representing the octet.
+//
+String &encodeURL(String &str, char *valid)
+{
+    String	temp;
+    static char	*digits = "0123456789ABCDEF";
+    char	*p;
+
+    for (p = str; p && *p; p++)
+    {
+	if (isascii(*p) && (isdigit(*p) || isalpha(*p) || strchr(valid, *p)))
+	    temp << *p;
+	else
+	{
+	    temp << '%';
+	    temp << digits[(*p >> 4) & 0x0f];
+	    temp << digits[*p & 0x0f];
+	}
+    }
+    str = temp;
+    return (str);
+}
+
+
diff --git a/debian/htdig/htdig-3.2.0b6/htcommon/cgi.cc b/debian/htdig/htdig-3.2.0b6/htcommon/cgi.cc
new file mode 100644
index 00000000..557d90ee
--- /dev/null
+++ b/debian/htdig/htdig-3.2.0b6/htcommon/cgi.cc
@@ -0,0 +1,213 @@
+//
+// cgi.cc
+//
+// cgi: Parse cgi arguments and put them in a dictionary.
+//
+// Part of the ht://Dig package   <http://www.htdig.org/>
+// Copyright (c) 1995-2004 The ht://Dig Group
+// For copyright details, see the file COPYING in your distribution
+// or the GNU Library General Public License (LGPL) version 2 or later 
+// <http://www.gnu.org/copyleft/lgpl.html>
+//
+// $Id: cgi.cc,v 1.9 2004/05/28 13:15:12 lha Exp $
+//
+
+#ifdef HAVE_CONFIG_H
+#include "htconfig.h"
+#endif /* HAVE_CONFIG_H */
+
+#ifdef _MSC_VER /* _WIN32 */
+#include <io.h>
+#endif
+
+#include "cgi.h"
+#include "htString.h"
+#include "Dictionary.h"
+#include "good_strtok.h"
+#include "StringList.h"
+#include "URL.h"
+
+#include <stdlib.h>
+
+#ifndef _MSC_VER /* _WIN32 */
+#include <unistd.h>
+#endif
+
+#ifdef HAVE_STD
+#include <fstream>
+#ifdef HAVE_NAMESPACES
+using namespace std;
+#endif
+#else
+#include <fstream.h>
+#endif /* HAVE_STD */
+
+//*****************************************************************************
+// cgi::cgi()
+//
+cgi::cgi()
+{
+	init("");
+}
+
+
+//*****************************************************************************
+// cgi::cgi(char *s)
+//
+cgi::cgi(char *s)
+{
+	init(s);
+}
+
+
+//*****************************************************************************
+// void cgi::init(char *s)
+//
+void
+cgi::init(char *s)
+{
+	pairs = new Dictionary;
+
+	int i;
+	String	method(getenv("REQUEST_METHOD"));
+
+	if ((!s || !*s) && method.length() == 0)
+	{
+		//
+		// Interactive mode
+		//
+		query = 1;
+		return;
+	}
+	query = 0;
+	String	results;
+
+	if (s && *s && method.length() == 0)
+	{
+		results = s;
+	}
+	else if (strcmp((char*)method, "GET") == 0)
+	{
+		results = getenv("QUERY_STRING");
+	}
+	else
+	{
+		int		n;
+		char	*buf;
+		
+		buf = getenv("CONTENT_LENGTH");
+		if (!buf || !*buf || (n = atoi(buf)) <= 0)
+			return;		// null query
+		buf = new char[n + 1];
+		int	r, i = 0;
+		while (i < n && (r = read(0, buf+i, n-i)) > 0)
+			i += r;
+		buf[i] = '\0';
+		results = buf;
+		delete [] buf;
+	}
+
+	//
+	// Now we need to split the line up into name/value pairs
+	//
+	StringList	list(results, "&;");
+	
+	//
+	// Each name/value pair now needs to be added to the dictionary
+	//
+	for (i = 0; i < list.Count(); i++)
+	{
+		char	*name = good_strtok(list[i], '=');
+		String	value(good_strtok(NULL, '\n'));
+		value.replace('+', ' ');
+		decodeURL(value);
+		String	*str = (String *) pairs->Find(name);
+		if (str)
+		{
+			//
+			// Entry was already there.  Append it to the string.
+			//
+			str->append('\001');
+			str->append(value);
+		}
+		else
+		{
+			//
+			// New entry.  Add a new string
+			//
+			pairs->Add(name, new String(value));
+		}
+	}
+}
+
+
+//*****************************************************************************
+// cgi::~cgi()
+//
+cgi::~cgi()
+{
+	delete pairs;
+}
+
+
+//*****************************************************************************
+// char *cgi::operator [] (char *name)
+//
+char *cgi::operator [] (char *name)
+{
+	return get(name);
+}
+
+
+//*****************************************************************************
+// char *cgi::get(char *name)
+//
+char *cgi::get(char *name)
+{
+	String	*str = (String *) (*pairs)[name];
+	if (str)
+		return str->get();
+	else
+	{
+		if (query)
+		{
+			char	buffer[1000];
+			cerr << "Enter value for " << name << ": ";
+			cin.getline(buffer, sizeof(buffer));
+			pairs->Add(name, new String(buffer));
+			str = (String *) (*pairs)[name];
+			return str->get();
+		}
+		return 0;
+	}
+}
+
+
+//*****************************************************************************
+// int cgi::exists(char *name)
+//
+int
+cgi::exists(char *name)
+{
+	return pairs->Exists(name);
+}
+
+//*****************************************************************************
+// char *cgi::path()
+//
+char *cgi::path()
+{
+	static char	buffer[1000] = "";
+
+	if (query)
+	{
+		if (*buffer)
+			return buffer;
+		cerr << "Enter PATH_INFO: ";
+		cin.getline(buffer, sizeof(buffer));
+		return buffer;
+	}
+	return getenv("PATH_INFO");
+}
+
+
diff --git a/debian/htdig/htdig-3.2.0b6/htcommon/cgi.h b/debian/htdig/htdig-3.2.0b6/htcommon/cgi.h
new file mode 100644
index 00000000..c1232f05
--- /dev/null
+++ b/debian/htdig/htdig-3.2.0b6/htcommon/cgi.h
@@ -0,0 +1,40 @@
+//
+// cgi.h
+//
+// cgi: Parse cgi arguments and put them in a dictionary.
+//
+// Part of the ht://Dig package   <http://www.htdig.org/>
+// Copyright (c) 1995-2004 The ht://Dig Group
+// For copyright details, see the file COPYING in your distribution
+// or the GNU Library General Public License (LGPL) version 2 or later 
+// <http://www.gnu.org/copyleft/lgpl.html>
+//
+// $Id: cgi.h,v 1.4 2004/05/28 13:15:12 lha Exp $
+//
+
+#ifndef _cgi_h_
+#define _cgi_h_
+
+class Dictionary;
+
+class cgi
+{
+public:
+	cgi();
+	cgi(char *s);
+	~cgi();
+
+	char			*operator [] (char *);
+	char			*get(char *);
+	int			exists(char *);
+	char			*path();
+
+private:
+	Dictionary		*pairs;
+	int			query;
+	void			init(char *s);
+};
+
+#endif
+
+
diff --git a/debian/htdig/htdig-3.2.0b6/htcommon/conf_lexer.cxx b/debian/htdig/htdig-3.2.0b6/htcommon/conf_lexer.cxx
new file mode 100644
index 00000000..5ac1ceaf
--- /dev/null
+++ b/debian/htdig/htdig-3.2.0b6/htcommon/conf_lexer.cxx
@@ -0,0 +1,2006 @@
+#line 2 "conf_lexer.cxx"
+
+#line 4 "conf_lexer.cxx"
+
+#define  YY_INT_ALIGNED short int
+
+/* A lexical scanner generated by flex */
+
+#define FLEX_SCANNER
+#define YY_FLEX_MAJOR_VERSION 2
+#define YY_FLEX_MINOR_VERSION 5
+#define YY_FLEX_SUBMINOR_VERSION 31
+#if YY_FLEX_SUBMINOR_VERSION > 0
+#define FLEX_BETA
+#endif
+
+/* First, we deal with  platform-specific or compiler-specific issues. */
+
+/* begin standard C headers. */
+#include <stdio.h>
+#include <string.h>
+#include <errno.h>
+#include <stdlib.h>
+
+/* end standard C headers. */
+
+/* flex integer type definitions */
+
+#ifndef FLEXINT_H
+#define FLEXINT_H
+
+/* C99 systems have <inttypes.h>. Non-C99 systems may or may not. */
+
+#if defined __STDC_VERSION__ && __STDC_VERSION__ >= 199901L
+#include <inttypes.h>
+typedef int8_t flex_int8_t;
+typedef uint8_t flex_uint8_t;
+typedef int16_t flex_int16_t;
+typedef uint16_t flex_uint16_t;
+typedef int32_t flex_int32_t;
+typedef uint32_t flex_uint32_t;
+#else
+typedef signed char flex_int8_t;
+typedef short int flex_int16_t;
+typedef int flex_int32_t;
+typedef unsigned char flex_uint8_t; 
+typedef unsigned short int flex_uint16_t;
+typedef unsigned int flex_uint32_t;
+#endif /* ! C99 */
+
+/* Limits of integral types. */
+#ifndef INT8_MIN
+#define INT8_MIN               (-128)
+#endif
+#ifndef INT16_MIN
+#define INT16_MIN              (-32767-1)
+#endif
+#ifndef INT32_MIN
+#define INT32_MIN              (-2147483647-1)
+#endif
+#ifndef INT8_MAX
+#define INT8_MAX               (127)
+#endif
+#ifndef INT16_MAX
+#define INT16_MAX              (32767)
+#endif
+#ifndef INT32_MAX
+#define INT32_MAX              (2147483647)
+#endif
+#ifndef UINT8_MAX
+#define UINT8_MAX              (255U)
+#endif
+#ifndef UINT16_MAX
+#define UINT16_MAX             (65535U)
+#endif
+#ifndef UINT32_MAX
+#define UINT32_MAX             (4294967295U)
+#endif
+
+#endif /* ! FLEXINT_H */
+
+#ifdef __cplusplus
+
+/* The "const" storage-class-modifier is valid. */
+#define YY_USE_CONST
+
+#else	/* ! __cplusplus */
+
+#if __STDC__
+
+#define YY_USE_CONST
+
+#endif	/* __STDC__ */
+#endif	/* ! __cplusplus */
+
+#ifdef YY_USE_CONST
+#define yyconst const
+#else
+#define yyconst
+#endif
+
+/* Returned upon end-of-file. */
+#define YY_NULL 0
+
+/* Promotes a possibly negative, possibly signed char to an unsigned
+ * integer for use as an array index.  If the signed char is negative,
+ * we want to instead treat it as an 8-bit unsigned char, hence the
+ * double cast.
+ */
+#define YY_SC_TO_UI(c) ((unsigned int) (unsigned char) c)
+
+/* Enter a start condition.  This macro really ought to take a parameter,
+ * but we do it the disgusting crufty way forced on us by the ()-less
+ * definition of BEGIN.
+ */
+#define BEGIN (yy_start) = 1 + 2 *
+
+/* Translate the current start state into a value that can be later handed
+ * to BEGIN to return to the state.  The YYSTATE alias is for lex
+ * compatibility.
+ */
+#define YY_START (((yy_start) - 1) / 2)
+#define YYSTATE YY_START
+
+/* Action number for EOF rule of a given start state. */
+#define YY_STATE_EOF(state) (YY_END_OF_BUFFER + state + 1)
+
+/* Special action meaning "start processing a new file". */
+#define YY_NEW_FILE yyrestart(yyin  )
+
+#define YY_END_OF_BUFFER_CHAR 0
+
+/* Size of default input buffer. */
+#ifndef YY_BUF_SIZE
+#define YY_BUF_SIZE 16384
+#endif
+
+#ifndef YY_TYPEDEF_YY_BUFFER_STATE
+#define YY_TYPEDEF_YY_BUFFER_STATE
+typedef struct yy_buffer_state *YY_BUFFER_STATE;
+#endif
+
+extern int yyleng;
+
+extern FILE *yyin, *yyout;
+
+#define EOB_ACT_CONTINUE_SCAN 0
+#define EOB_ACT_END_OF_FILE 1
+#define EOB_ACT_LAST_MATCH 2
+
+    /* Note: We specifically omit the test for yy_rule_can_match_eol because it requires
+     *       access to the local variable yy_act. Since yyless() is a macro, it would break
+     *       existing scanners that call yyless() from OUTSIDE yylex. 
+     *       One obvious solution it to make yy_act a global. I tried that, and saw
+     *       a 5% performance hit in a non-yylineno scanner, because yy_act is
+     *       normally declared as a register variable-- so it is not worth it.
+     */
+    #define  YY_LESS_LINENO(n) \
+            do { \
+                int yyl;\
+                for ( yyl = n; yyl < yyleng; ++yyl )\
+                    if ( yytext[yyl] == '\n' )\
+                        --yylineno;\
+            }while(0)
+    
+/* Return all but the first "n" matched characters back to the input stream. */
+#define yyless(n) \
+	do \
+		{ \
+		/* Undo effects of setting up yytext. */ \
+        int yyless_macro_arg = (n); \
+        YY_LESS_LINENO(yyless_macro_arg);\
+		*yy_cp = (yy_hold_char); \
+		YY_RESTORE_YY_MORE_OFFSET \
+		(yy_c_buf_p) = yy_cp = yy_bp + yyless_macro_arg - YY_MORE_ADJ; \
+		YY_DO_BEFORE_ACTION; /* set up yytext again */ \
+		} \
+	while ( 0 )
+
+#define unput(c) yyunput( c, (yytext_ptr)  )
+
+/* The following is because we cannot portably get our hands on size_t
+ * (without autoconf's help, which isn't available because we want
+ * flex-generated scanners to compile on their own).
+ */
+
+#ifndef YY_TYPEDEF_YY_SIZE_T
+#define YY_TYPEDEF_YY_SIZE_T
+typedef unsigned int yy_size_t;
+#endif
+
+#ifndef YY_STRUCT_YY_BUFFER_STATE
+#define YY_STRUCT_YY_BUFFER_STATE
+struct yy_buffer_state
+	{
+	FILE *yy_input_file;
+
+	char *yy_ch_buf;		/* input buffer */
+	char *yy_buf_pos;		/* current position in input buffer */
+
+	/* Size of input buffer in bytes, not including room for EOB
+	 * characters.
+	 */
+	yy_size_t yy_buf_size;
+
+	/* Number of characters read into yy_ch_buf, not including EOB
+	 * characters.
+	 */
+	int yy_n_chars;
+
+	/* Whether we "own" the buffer - i.e., we know we created it,
+	 * and can realloc() it to grow it, and should free() it to
+	 * delete it.
+	 */
+	int yy_is_our_buffer;
+
+	/* Whether this is an "interactive" input source; if so, and
+	 * if we're using stdio for input, then we want to use getc()
+	 * instead of fread(), to make sure we stop fetching input after
+	 * each newline.
+	 */
+	int yy_is_interactive;
+
+	/* Whether we're considered to be at the beginning of a line.
+	 * If so, '^' rules will be active on the next match, otherwise
+	 * not.
+	 */
+	int yy_at_bol;
+
+    int yy_bs_lineno; /**< The line count. */
+    int yy_bs_column; /**< The column count. */
+    
+	/* Whether to try to fill the input buffer when we reach the
+	 * end of it.
+	 */
+	int yy_fill_buffer;
+
+	int yy_buffer_status;
+
+#define YY_BUFFER_NEW 0
+#define YY_BUFFER_NORMAL 1
+	/* When an EOF's been seen but there's still some text to process
+	 * then we mark the buffer as YY_EOF_PENDING, to indicate that we
+	 * shouldn't try reading from the input source any more.  We might
+	 * still have a bunch of tokens to match, though, because of
+	 * possible backing-up.
+	 *
+	 * When we actually see the EOF, we change the status to "new"
+	 * (via yyrestart()), so that the user can continue scanning by
+	 * just pointing yyin at a new input file.
+	 */
+#define YY_BUFFER_EOF_PENDING 2
+
+	};
+#endif /* !YY_STRUCT_YY_BUFFER_STATE */
+
+/* Stack of input buffers. */
+static size_t yy_buffer_stack_top = 0; /**< index of top of stack. */
+static size_t yy_buffer_stack_max = 0; /**< capacity of stack. */
+static YY_BUFFER_STATE * yy_buffer_stack = 0; /**< Stack as an array. */
+
+/* We provide macros for accessing buffer states in case in the
+ * future we want to put the buffer states in a more general
+ * "scanner state".
+ *
+ * Returns the top of the stack, or NULL.
+ */
+#define YY_CURRENT_BUFFER ( (yy_buffer_stack) \
+                          ? (yy_buffer_stack)[(yy_buffer_stack_top)] \
+                          : NULL)
+
+/* Same as previous macro, but useful when we know that the buffer stack is not
+ * NULL or when we need an lvalue. For internal use only.
+ */
+#define YY_CURRENT_BUFFER_LVALUE (yy_buffer_stack)[(yy_buffer_stack_top)]
+
+/* yy_hold_char holds the character lost when yytext is formed. */
+static char yy_hold_char;
+static int yy_n_chars;		/* number of characters read into yy_ch_buf */
+int yyleng;
+
+/* Points to current character in buffer. */
+static char *yy_c_buf_p = (char *) 0;
+static int yy_init = 1;		/* whether we need to initialize */
+static int yy_start = 0;	/* start state number */
+
+/* Flag which is used to allow yywrap()'s to do buffer switches
+ * instead of setting up a fresh yyin.  A bit of a hack ...
+ */
+static int yy_did_buffer_switch_on_eof;
+
+void yyrestart (FILE *input_file  );
+void yy_switch_to_buffer (YY_BUFFER_STATE new_buffer  );
+YY_BUFFER_STATE yy_create_buffer (FILE *file,int size  );
+void yy_delete_buffer (YY_BUFFER_STATE b  );
+void yy_flush_buffer (YY_BUFFER_STATE b  );
+void yypush_buffer_state (YY_BUFFER_STATE new_buffer  );
+void yypop_buffer_state (void );
+
+static void yyensure_buffer_stack (void );
+static void yy_load_buffer_state (void );
+static void yy_init_buffer (YY_BUFFER_STATE b,FILE *file  );
+
+#define YY_FLUSH_BUFFER yy_flush_buffer(YY_CURRENT_BUFFER )
+
+YY_BUFFER_STATE yy_scan_buffer (char *base,yy_size_t size  );
+YY_BUFFER_STATE yy_scan_string (yyconst char *yy_str  );
+YY_BUFFER_STATE yy_scan_bytes (yyconst char *bytes,int len  );
+
+void *yyalloc (yy_size_t  );
+void *yyrealloc (void *,yy_size_t  );
+void yyfree (void *  );
+
+#define yy_new_buffer yy_create_buffer
+
+#define yy_set_interactive(is_interactive) \
+	{ \
+	if ( ! YY_CURRENT_BUFFER ){ \
+        yyensure_buffer_stack (); \
+		YY_CURRENT_BUFFER_LVALUE =    \
+            yy_create_buffer(yyin,YY_BUF_SIZE ); \
+	} \
+	YY_CURRENT_BUFFER_LVALUE->yy_is_interactive = is_interactive; \
+	}
+
+#define yy_set_bol(at_bol) \
+	{ \
+	if ( ! YY_CURRENT_BUFFER ){\
+        yyensure_buffer_stack (); \
+		YY_CURRENT_BUFFER_LVALUE =    \
+            yy_create_buffer(yyin,YY_BUF_SIZE ); \
+	} \
+	YY_CURRENT_BUFFER_LVALUE->yy_at_bol = at_bol; \
+	}
+
+#define YY_AT_BOL() (YY_CURRENT_BUFFER_LVALUE->yy_at_bol)
+
+/* Begin user sect3 */
+
+#define yywrap(n) 1
+#define YY_SKIP_YYWRAP
+
+typedef unsigned char YY_CHAR;
+
+FILE *yyin = (FILE *) 0, *yyout = (FILE *) 0;
+
+typedef int yy_state_type;
+
+extern int yylineno;
+
+int yylineno = 1;
+
+extern char *yytext;
+#define yytext_ptr yytext
+
+static yy_state_type yy_get_previous_state (void );
+static yy_state_type yy_try_NUL_trans (yy_state_type current_state  );
+static int yy_get_next_buffer (void );
+static void yy_fatal_error (yyconst char msg[]  );
+
+/* Done after the current pattern has been matched and before the
+ * corresponding action - sets up yytext.
+ */
+#define YY_DO_BEFORE_ACTION \
+	(yytext_ptr) = yy_bp; \
+	yyleng = (size_t) (yy_cp - yy_bp); \
+	(yy_hold_char) = *yy_cp; \
+	*yy_cp = '\0'; \
+	(yy_c_buf_p) = yy_cp;
+
+#define YY_NUM_RULES 22
+#define YY_END_OF_BUFFER 23
+/* This struct is not used in this scanner,
+   but its presence is necessary. */
+struct yy_trans_info
+	{
+	flex_int32_t yy_verify;
+	flex_int32_t yy_nxt;
+	};
+static yyconst flex_int16_t yy_accept[63] =
+    {   0,
+        0,    0,   16,   16,    0,    0,    0,    0,    0,    0,
+       23,   21,    3,   20,   11,    5,    8,    8,    3,    2,
+       19,   21,    3,   18,   14,   14,   10,   14,   17,    6,
+        7,    9,    3,    8,    8,    3,    2,   19,    0,    0,
+        1,    3,   14,   14,    0,   14,   14,   10,   15,   17,
+        9,    8,   12,   13,   13,    8,    8,    8,    8,    0,
+        4,    0
+    } ;
+
+static yyconst flex_int32_t yy_ec[256] =
+    {   0,
+        1,    1,    1,    1,    1,    1,    1,    1,    2,    3,
+        4,    4,    4,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    2,    5,    6,    7,    5,    5,    5,    5,    5,
+        5,    5,    5,    5,    5,    5,    8,    9,    9,    9,
+        9,    9,    9,    9,    9,    9,    9,   10,    5,   11,
+        5,   12,    5,    5,   13,   13,   13,   13,   13,   13,
+       13,   13,   13,   13,   13,   13,   13,   13,   13,   13,
+       13,   13,   13,   13,   13,   13,   13,   13,   13,   13,
+        5,   14,    5,    5,   13,    5,   13,   13,   15,   16,
+
+       17,   13,   13,   13,   18,   13,   13,   19,   13,   20,
+       13,   13,   13,   13,   13,   13,   21,   13,   13,   13,
+       13,   13,    5,    5,    5,    5,    5,    5,    5,    5,
+        5,    5,    5,    5,    5,    5,    5,    5,    5,    5,
+        5,    5,    5,    5,    5,    5,    5,    5,    5,    5,
+        5,    5,    5,    5,    5,    5,    5,    5,    5,    5,
+        5,    5,    5,    5,    5,    5,    5,    5,    5,    5,
+        5,    5,    5,    5,    5,    5,    5,    5,    5,    5,
+        5,    5,    5,    5,    5,    5,    5,    5,    5,    5,
+        5,    5,    5,    5,    5,    5,    5,    5,    5,    5,
+
+        5,    5,    5,    5,    5,    5,    5,    5,    5,    5,
+        5,    5,    5,    5,    5,    5,    5,    5,    5,    5,
+        5,    5,    5,    5,    5,    5,    5,    5,    5,    5,
+        5,    5,    5,    5,    5,    5,    5,    5,    5,    5,
+        5,    5,    5,    5,    5,    5,    5,    5,    5,    5,
+        5,    5,    5,    5,    5
+    } ;
+
+static yyconst flex_int32_t yy_meta[22] =
+    {   0,
+        1,    2,    3,    1,    4,    4,    4,    5,    5,    4,
+        6,    6,    5,    4,    5,    5,    5,    5,    5,    5,
+        5
+    } ;
+
+static yyconst flex_int16_t yy_base[73] =
+    {   0,
+        0,   20,   27,   41,   55,   59,   61,    0,   78,   89,
+       87,  183,   84,  183,  183,  183,    0,   65,  100,   82,
+        0,   80,   80,  183,   64,  107,   23,   32,    0,  183,
+      183,    0,   75,    0,   61,    0,    0,    0,   72,   68,
+      183,   68,   54,   35,   61,  121,   62,   25,  183,    0,
+        0,   35,  183,   47,    0,   31,   35,    9,   38,   64,
+      183,  183,  135,  141,  147,   20,  153,  156,  162,  165,
+      171,  176
+    } ;
+
+static yyconst flex_int16_t yy_def[73] =
+    {   0,
+       62,    1,   63,   63,   64,   64,    1,    7,   65,   65,
+       62,   62,   62,   62,   62,   62,   66,   66,   62,   19,
+       20,   67,   62,   62,   68,   69,   68,   68,   70,   62,
+       62,   71,   62,   66,   66,   19,   20,   20,   67,   67,
+       62,   62,   68,   68,   72,   69,   46,   68,   62,   70,
+       71,   66,   62,   72,   46,   66,   66,   66,   66,   62,
+       62,    0,   62,   62,   62,   62,   62,   62,   62,   62,
+       62,   62
+    } ;
+
+static yyconst flex_int16_t yy_nxt[205] =
+    {   0,
+       12,   13,   14,   12,   12,   12,   12,   12,   12,   15,
+       16,   12,   17,   12,   17,   17,   17,   18,   17,   17,
+       17,   19,   20,   21,   34,   59,   22,   12,   23,   24,
+       12,   48,   26,   48,   49,   27,   44,   53,   44,   60,
+       28,   12,   23,   24,   12,   44,   26,   61,   44,   27,
+       58,   57,   54,   56,   28,   12,   13,   12,   12,   12,
+       13,   12,   12,   24,   53,   60,   54,   44,   30,   42,
+       41,   12,   31,   61,   41,   52,   33,   44,   17,   13,
+       12,   42,   41,   38,   35,   33,   62,   62,   12,   12,
+       13,   12,   62,   62,   62,   62,   62,   62,   62,   12,
+
+       12,   36,   37,   38,   62,   62,   39,   45,   45,   62,
+       45,   62,   62,   62,   62,   62,   62,   62,   62,   62,
+       47,   45,   45,   62,   45,   62,   55,   62,   62,   62,
+       62,   62,   62,   62,   47,   25,   25,   25,   25,   25,
+       25,   29,   29,   29,   29,   29,   29,   32,   32,   32,
+       32,   32,   32,   40,   40,   40,   40,   40,   40,   43,
+       43,   43,   46,   46,   62,   46,   46,   46,   50,   50,
+       50,   51,   62,   62,   51,   51,   45,   45,   62,   45,
+       45,   45,   11,   62,   62,   62,   62,   62,   62,   62,
+       62,   62,   62,   62,   62,   62,   62,   62,   62,   62,
+
+       62,   62,   62,   62
+    } ;
+
+static yyconst flex_int16_t yy_chk[205] =
+    {   0,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    1,    1,    1,    1,    1,    1,    1,    1,    1,
+        1,    2,    2,    2,   66,   58,    2,    3,    3,    3,
+        3,   27,    3,   48,   28,    3,   27,   44,   48,   59,
+        3,    4,    4,    4,    4,   28,    4,   59,   44,    4,
+       57,   56,   54,   52,    4,    5,    5,    5,    5,    6,
+        6,    6,    6,    7,   47,   60,   45,   43,    7,   42,
+       40,    7,    7,   60,   39,   35,   33,   25,    7,    9,
+        9,   23,   22,   20,   18,   13,   11,    0,    9,    9,
+       10,   10,    0,    0,    0,    0,    0,    0,    0,   10,
+
+       10,   19,   19,   19,    0,    0,   19,   26,   26,    0,
+       26,    0,    0,    0,    0,    0,    0,    0,    0,    0,
+       26,   46,   46,    0,   46,    0,   46,    0,    0,    0,
+        0,    0,    0,    0,   46,   63,   63,   63,   63,   63,
+       63,   64,   64,   64,   64,   64,   64,   65,   65,   65,
+       65,   65,   65,   67,   67,   67,   67,   67,   67,   68,
+       68,   68,   69,   69,    0,   69,   69,   69,   70,   70,
+       70,   71,    0,    0,   71,   71,   72,   72,    0,   72,
+       72,   72,   62,   62,   62,   62,   62,   62,   62,   62,
+       62,   62,   62,   62,   62,   62,   62,   62,   62,   62,
+
+       62,   62,   62,   62
+    } ;
+
+/* Table of booleans, true if rule could match eol. */
+static yyconst flex_int32_t yy_rule_can_match_eol[23] =
+    {   0,
+1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 1, 1, 
+    1, 1, 0,     };
+
+static yy_state_type yy_last_accepting_state;
+static char *yy_last_accepting_cpos;
+
+extern int yy_flex_debug;
+int yy_flex_debug = 0;
+
+/* The intent behind this definition is that it'll catch
+ * any uses of REJECT which flex missed.
+ */
+#define REJECT reject_used_but_not_detected
+#define yymore() yymore_used_but_not_detected
+#define YY_MORE_ADJ 0
+#define YY_RESTORE_YY_MORE_OFFSET
+char *yytext;
+#line 1 "conf_lexer.lxx"
+/*
+//
+// conf_lexer.lxx
+//
+//             This lexical parser is used to parse ht://Dig config
+//             files.  
+//
+//       Note:  The resulting .cxx file produces warnings of unused
+//		labels.  As at 2003-06-02, these have been manually
+//		removed, but they will reappear when  (f)lex  is re-run.
+//
+// Part of the ht://Dig package   <http://www.htdig.org/>
+// Copyright (c) 1999-2004 The ht://Dig Group
+// For copyright details, see the file COPYING in your distribution
+// or the GNU Library General Public License (LGPL) version 2 or later
+// <http://www.gnu.org/copyleft/lgpl.html>
+//
+// $Id: conf_lexer.cxx,v 1.11 2004/06/10 14:48:38 angusgb Exp $
+//
+*/
+#line 22 "conf_lexer.lxx"
+#ifdef HAVE_CONFIG_H
+#include "htconfig.h"
+#endif /* HAVE_CONFIG_H */
+
+
+
+
+#line 34 "conf_lexer.lxx"
+#ifdef HAVE_STRINGS_H
+#include <strings.h>
+#endif
+
+#include "HtConfiguration.h"
+//#include "Dictionary.h"
+#include "conf_parser.h"
+#define MAX_INCLUDE_DEPTH 10
+YY_BUFFER_STATE include_stack[MAX_INCLUDE_DEPTH];
+String *name_stack[MAX_INCLUDE_DEPTH];
+int lineno_stack[MAX_INCLUDE_DEPTH];
+int include_stack_ptr = 0;
+#line 571 "conf_lexer.cxx"
+
+#define INITIAL 0
+#define t_right 1
+#define incl 2
+#define bracket 3
+#define br_string 4
+
+#ifndef YY_NO_UNISTD_H
+/* Special case for "unistd.h", since it is non-ANSI. We include it way
+ * down here because we want the user's section 1 to have been scanned first.
+ * The user has a chance to override it with an option.
+ */
+#include <unistd.h>
+#endif
+
+#ifndef YY_EXTRA_TYPE
+#define YY_EXTRA_TYPE void *
+#endif
+
+/* Macros after this point can all be overridden by user definitions in
+ * section 1.
+ */
+
+#ifndef YY_SKIP_YYWRAP
+#ifdef __cplusplus
+extern "C" int yywrap (void );
+#else
+extern int yywrap (void );
+#endif
+#endif
+
+#ifndef yytext_ptr
+static void yy_flex_strncpy (char *,yyconst char *,int );
+#endif
+
+#ifdef YY_NEED_STRLEN
+static int yy_flex_strlen (yyconst char * );
+#endif
+
+#ifndef YY_NO_INPUT
+
+#ifdef __cplusplus
+static int yyinput (void );
+#else
+static int input (void );
+#endif
+
+#endif
+
+/* Amount of stuff to slurp up with each read. */
+#ifndef YY_READ_BUF_SIZE
+#define YY_READ_BUF_SIZE 8192
+#endif
+
+/* Copy whatever the last rule matched to the standard output. */
+#ifndef ECHO
+/* This used to be an fputs(), but since the string might contain NUL's,
+ * we now use fwrite().
+ */
+#define ECHO (void) fwrite( yytext, yyleng, 1, yyout )
+#endif
+
+/* Gets input and stuffs it into "buf".  number of characters read, or YY_NULL,
+ * is returned in "result".
+ */
+#ifndef YY_INPUT
+#define YY_INPUT(buf,result,max_size) \
+	if ( YY_CURRENT_BUFFER_LVALUE->yy_is_interactive ) \
+		{ \
+		int c = '*'; \
+		size_t n; \
+		for ( n = 0; n < max_size && \
+			     (c = getc( yyin )) != EOF && c != '\n'; ++n ) \
+			buf[n] = (char) c; \
+		if ( c == '\n' ) \
+			buf[n++] = (char) c; \
+		if ( c == EOF && ferror( yyin ) ) \
+			YY_FATAL_ERROR( "input in flex scanner failed" ); \
+		result = n; \
+		} \
+	else \
+		{ \
+		errno=0; \
+		while ( (result = fread(buf, 1, max_size, yyin))==0 && ferror(yyin)) \
+			{ \
+			if( errno != EINTR) \
+				{ \
+				YY_FATAL_ERROR( "input in flex scanner failed" ); \
+				break; \
+				} \
+			errno=0; \
+			clearerr(yyin); \
+			} \
+		}\
+\
+
+#endif
+
+/* No semi-colon after return; correct usage is to write "yyterminate();" -
+ * we don't want an extra ';' after the "return" because that will cause
+ * some compilers to complain about unreachable statements.
+ */
+#ifndef yyterminate
+#define yyterminate() return YY_NULL
+#endif
+
+/* Number of entries by which start-condition stack grows. */
+#ifndef YY_START_STACK_INCR
+#define YY_START_STACK_INCR 25
+#endif
+
+/* Report a fatal error. */
+#ifndef YY_FATAL_ERROR
+#define YY_FATAL_ERROR(msg) yy_fatal_error( msg )
+#endif
+
+/* end tables serialization structures and prototypes */
+
+/* Default declaration of generated scanner - a define so the user can
+ * easily add parameters.
+ */
+#ifndef YY_DECL
+#define YY_DECL_IS_OURS 1
+
+extern int yylex (void);
+
+#define YY_DECL int yylex (void)
+#endif /* !YY_DECL */
+
+/* Code executed at the beginning of each rule, after yytext and yyleng
+ * have been set up.
+ */
+#ifndef YY_USER_ACTION
+#define YY_USER_ACTION
+#endif
+
+/* Code executed at the end of each rule. */
+#ifndef YY_BREAK
+#define YY_BREAK break;
+#endif
+
+#define YY_RULE_SETUP \
+	if ( yyleng > 0 ) \
+		YY_CURRENT_BUFFER_LVALUE->yy_at_bol = \
+				(yytext[yyleng - 1] == '\n'); \
+	YY_USER_ACTION
+
+/** The main scanner function which does all the work.
+ */
+YY_DECL
+{
+	register yy_state_type yy_current_state;
+	register char *yy_cp, *yy_bp;
+	register int yy_act;
+    
+#line 52 "conf_lexer.lxx"
+
+
+#line 730 "conf_lexer.cxx"
+
+	if ( (yy_init) )
+		{
+		(yy_init) = 0;
+
+#ifdef YY_USER_INIT
+		YY_USER_INIT;
+#endif
+
+		if ( ! (yy_start) )
+			(yy_start) = 1;	/* first start state */
+
+		if ( ! yyin )
+			yyin = stdin;
+
+		if ( ! yyout )
+			yyout = stdout;
+
+		if ( ! YY_CURRENT_BUFFER ) {
+			yyensure_buffer_stack ();
+			YY_CURRENT_BUFFER_LVALUE =
+				yy_create_buffer(yyin,YY_BUF_SIZE );
+		}
+
+		yy_load_buffer_state( );
+		}
+
+	while ( 1 )		/* loops until end-of-file is reached */
+		{
+		yy_cp = (yy_c_buf_p);
+
+		/* Support of yytext. */
+		*yy_cp = (yy_hold_char);
+
+		/* yy_bp points to the position in yy_ch_buf of the start of
+		 * the current run.
+		 */
+		yy_bp = yy_cp;
+
+		yy_current_state = (yy_start);
+		yy_current_state += YY_AT_BOL();
+yy_match:
+		do
+			{
+			register YY_CHAR yy_c = yy_ec[YY_SC_TO_UI(*yy_cp)];
+			if ( yy_accept[yy_current_state] )
+				{
+				(yy_last_accepting_state) = yy_current_state;
+				(yy_last_accepting_cpos) = yy_cp;
+				}
+			while ( yy_chk[yy_base[yy_current_state] + yy_c] != yy_current_state )
+				{
+				yy_current_state = (int) yy_def[yy_current_state];
+				if ( yy_current_state >= 63 )
+					yy_c = yy_meta[(unsigned int) yy_c];
+				}
+			yy_current_state = yy_nxt[yy_base[yy_current_state] + (unsigned int) yy_c];
+			++yy_cp;
+			}
+		while ( yy_base[yy_current_state] != 183 );
+
+yy_find_action:
+		yy_act = yy_accept[yy_current_state];
+		if ( yy_act == 0 )
+			{ /* have to back up */
+			yy_cp = (yy_last_accepting_cpos);
+			yy_current_state = (yy_last_accepting_state);
+			yy_act = yy_accept[yy_current_state];
+			}
+
+		YY_DO_BEFORE_ACTION;
+
+		if ( yy_act != YY_END_OF_BUFFER && yy_rule_can_match_eol[yy_act] )
+			{
+			int yyl;
+			for ( yyl = 0; yyl < yyleng; ++yyl )
+				if ( yytext[yyl] == '\n' )
+					   
+    yylineno++;
+;
+			}
+
+do_action:	/* This label is used only to access EOF actions. */
+
+		switch ( yy_act )
+	{ /* beginning of action switch */
+			case 0: /* must back up */
+			/* undo the effects of YY_DO_BEFORE_ACTION */
+			*yy_cp = (yy_hold_char);
+			yy_cp = (yy_last_accepting_cpos);
+			yy_current_state = (yy_last_accepting_state);
+			goto yy_find_action;
+
+case 1:
+/* rule 1 can match eol */
+YY_RULE_SETUP
+#line 54 "conf_lexer.lxx"
+/*   Ignore comments     */
+	YY_BREAK
+case 2:
+/* rule 2 can match eol */
+YY_RULE_SETUP
+#line 55 "conf_lexer.lxx"
+/*   Ignore empty lines   */
+	YY_BREAK
+case 3:
+YY_RULE_SETUP
+#line 56 "conf_lexer.lxx"
+/*   Ignore spaces       */
+	YY_BREAK
+case 4:
+YY_RULE_SETUP
+#line 57 "conf_lexer.lxx"
+BEGIN(incl);
+	YY_BREAK
+case 5:
+YY_RULE_SETUP
+#line 58 "conf_lexer.lxx"
+{ BEGIN(bracket); return(T_LEFT_BR); }
+	YY_BREAK
+case 6:
+YY_RULE_SETUP
+#line 59 "conf_lexer.lxx"
+return(T_SLASH);
+	YY_BREAK
+case 7:
+YY_RULE_SETUP
+#line 60 "conf_lexer.lxx"
+return(T_RIGHT_BR);
+	YY_BREAK
+case 8:
+YY_RULE_SETUP
+#line 61 "conf_lexer.lxx"
+{
+			//yylval.str = (char *)malloc(yyleng+1);
+                        yylval.str = new char[yyleng+1];
+                        strcpy(yylval.str,yytext);
+			return(T_KEYWORD);
+			}
+	YY_BREAK
+case 9:
+YY_RULE_SETUP
+#line 67 "conf_lexer.lxx"
+{
+			BEGIN(bracket);
+			yylval.str = new char[yyleng+1];
+			strcpy(yylval.str,yytext);
+			return(T_STRING);
+			}
+	YY_BREAK
+case 10:
+YY_RULE_SETUP
+#line 74 "conf_lexer.lxx"
+{
+                        //yylval.str = (char*)malloc(yyleng+1);
+                        yylval.str = new char[yyleng+1];
+                        strcpy(yylval.str,yytext);
+			return(T_NUMBER);
+			}
+	YY_BREAK
+case 11:
+YY_RULE_SETUP
+#line 81 "conf_lexer.lxx"
+{
+			if (YY_START==bracket)
+			    BEGIN(br_string);
+			else
+			BEGIN(t_right);
+                        return(T_DELIMITER);
+                        }
+	YY_BREAK
+case 12:
+/* rule 12 can match eol */
+YY_RULE_SETUP
+#line 89 "conf_lexer.lxx"
+{
+			//yylval.str = (char *)malloc(yyleng+1-2);
+                        yylval.str = new char[yyleng+1-2];
+                        //strcpy(yylval.str,yytext);
+                        memcpy(yylval.str,yytext,yyleng-2);
+                        yylval.str[yyleng-2]='\0';
+			return(T_STRING);  
+			}
+	YY_BREAK
+case 13:
+YY_RULE_SETUP
+#line 98 "conf_lexer.lxx"
+{
+			yylval.str = new char[yyleng+1];
+			strcpy(yylval.str,yytext);
+                        return(T_STRING);
+                        }
+	YY_BREAK
+case 14:
+YY_RULE_SETUP
+#line 104 "conf_lexer.lxx"
+{
+			//yylval.str = (char *)malloc(yyleng+1);
+                        yylval.str = new char[yyleng+1];
+                        strcpy(yylval.str,yytext);
+			return(T_STRING);
+			}
+	YY_BREAK
+case 15:
+/* rule 15 can match eol */
+YY_RULE_SETUP
+#line 110 "conf_lexer.lxx"
+
+	YY_BREAK
+
+/*   Ignore newline after "\"    */
+
+case 16:
+YY_RULE_SETUP
+#line 114 "conf_lexer.lxx"
+
+	YY_BREAK
+
+/*   Ignore spaces               */
+
+case 17:
+YY_RULE_SETUP
+#line 118 "conf_lexer.lxx"
+{ /* got the include file name */
+			if ( include_stack_ptr >= MAX_INCLUDE_DEPTH )
+			    {
+			    fprintf(stderr,"Includes nested too deeply\n");
+			    // exit(1);	// Seems too harsh!
+			    return(T_NEWLINE);
+			    }
+			include_stack[include_stack_ptr++] =
+			    YY_CURRENT_BUFFER;
+
+			HtConfiguration* config= HtConfiguration::config();
+			// handle ${var} in file name
+			String ParsedFilename =
+				config->ParseString(yytext);
+
+			if (ParsedFilename[0] != '/')
+			    {	// Given file name not fully qualified
+				// so strip dir. name from current one
+			    String str;
+			    if (include_stack_ptr > 1)
+				str = *name_stack[include_stack_ptr-2];
+			    else	// still at top level config
+				str = config->getFileName();
+			    int len = str.lastIndexOf('/') + 1;
+			    if (len > 0)
+				{	// Current name has directory path
+					// component, so use it for new name
+				str.chop(str.length() - len);
+				str << ParsedFilename;
+				ParsedFilename = str;
+				}
+			    }
+
+			yyin = fopen( ParsedFilename.get(), "r" );
+
+			if ( ! yyin ) {
+			    fprintf(stderr,"can't find file: %s\n",yytext);
+			    // exit(1);	// Seems too harsh!
+		            include_stack_ptr--;
+			    return(T_NEWLINE);
+			}
+			name_stack[include_stack_ptr-1] =
+					new String(ParsedFilename.get());
+			lineno_stack[include_stack_ptr-1] = yylineno;
+			yylineno = 1;
+		        yy_switch_to_buffer(yy_create_buffer(yyin,YY_BUF_SIZE ) );
+
+		        BEGIN(INITIAL);
+		        }
+	YY_BREAK
+case YY_STATE_EOF(INITIAL):
+case YY_STATE_EOF(t_right):
+case YY_STATE_EOF(incl):
+case YY_STATE_EOF(bracket):
+case YY_STATE_EOF(br_string):
+#line 168 "conf_lexer.lxx"
+{
+		        if ( include_stack_ptr <= 0 )
+			    {
+			    static int termnext = 0;
+			    // fix to allow unterminated final line
+			    if (++termnext <= 1)
+				return(T_NEWLINE);
+			    termnext = 0;	// in case we're called again
+		            yyterminate();
+			    }
+		        else
+		            {
+			    delete name_stack[include_stack_ptr-1];
+			    yylineno = lineno_stack[include_stack_ptr-1];
+		            yy_delete_buffer(YY_CURRENT_BUFFER );
+		            yy_switch_to_buffer(include_stack[--include_stack_ptr] );
+		            }
+		        }
+	YY_BREAK
+case 18:
+/* rule 18 can match eol */
+YY_RULE_SETUP
+#line 189 "conf_lexer.lxx"
+{
+			BEGIN(INITIAL);
+			return(T_NEWLINE);
+			}
+	YY_BREAK
+case 19:
+/* rule 19 can match eol */
+YY_RULE_SETUP
+#line 193 "conf_lexer.lxx"
+
+	YY_BREAK
+case 20:
+/* rule 20 can match eol */
+YY_RULE_SETUP
+#line 195 "conf_lexer.lxx"
+
+	YY_BREAK
+case 21:
+/* rule 21 can match eol */
+YY_RULE_SETUP
+#line 196 "conf_lexer.lxx"
+{ 
+	HtConfiguration* config= HtConfiguration::config();
+	String str;
+	if (include_stack_ptr > 0)
+	    str = *name_stack[include_stack_ptr-1];
+	else	// still at top level config
+	    str = config->getFileName();
+	fprintf(stderr,"Unknown char in file %s line %d: %s\n",str.get(),yylineno,yytext);
+	// exit(1); // Seems too harsh!
+	}
+	YY_BREAK
+case 22:
+YY_RULE_SETUP
+#line 206 "conf_lexer.lxx"
+ECHO;
+	YY_BREAK
+#line 1070 "conf_lexer.cxx"
+
+	case YY_END_OF_BUFFER:
+		{
+		/* Amount of text matched not including the EOB char. */
+		int yy_amount_of_matched_text = (int) (yy_cp - (yytext_ptr)) - 1;
+
+		/* Undo the effects of YY_DO_BEFORE_ACTION. */
+		*yy_cp = (yy_hold_char);
+		YY_RESTORE_YY_MORE_OFFSET
+
+		if ( YY_CURRENT_BUFFER_LVALUE->yy_buffer_status == YY_BUFFER_NEW )
+			{
+			/* We're scanning a new file or input source.  It's
+			 * possible that this happened because the user
+			 * just pointed yyin at a new source and called
+			 * yylex().  If so, then we have to assure
+			 * consistency between YY_CURRENT_BUFFER and our
+			 * globals.  Here is the right place to do so, because
+			 * this is the first action (other than possibly a
+			 * back-up) that will match for the new input source.
+			 */
+			(yy_n_chars) = YY_CURRENT_BUFFER_LVALUE->yy_n_chars;
+			YY_CURRENT_BUFFER_LVALUE->yy_input_file = yyin;
+			YY_CURRENT_BUFFER_LVALUE->yy_buffer_status = YY_BUFFER_NORMAL;
+			}
+
+		/* Note that here we test for yy_c_buf_p "<=" to the position
+		 * of the first EOB in the buffer, since yy_c_buf_p will
+		 * already have been incremented past the NUL character
+		 * (since all states make transitions on EOB to the
+		 * end-of-buffer state).  Contrast this with the test
+		 * in input().
+		 */
+		if ( (yy_c_buf_p) <= &YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[(yy_n_chars)] )
+			{ /* This was really a NUL. */
+			yy_state_type yy_next_state;
+
+			(yy_c_buf_p) = (yytext_ptr) + yy_amount_of_matched_text;
+
+			yy_current_state = yy_get_previous_state(  );
+
+			/* Okay, we're now positioned to make the NUL
+			 * transition.  We couldn't have
+			 * yy_get_previous_state() go ahead and do it
+			 * for us because it doesn't know how to deal
+			 * with the possibility of jamming (and we don't
+			 * want to build jamming into it because then it
+			 * will run more slowly).
+			 */
+
+			yy_next_state = yy_try_NUL_trans( yy_current_state );
+
+			yy_bp = (yytext_ptr) + YY_MORE_ADJ;
+
+			if ( yy_next_state )
+				{
+				/* Consume the NUL. */
+				yy_cp = ++(yy_c_buf_p);
+				yy_current_state = yy_next_state;
+				goto yy_match;
+				}
+
+			else
+				{
+				yy_cp = (yy_c_buf_p);
+				goto yy_find_action;
+				}
+			}
+
+		else switch ( yy_get_next_buffer(  ) )
+			{
+			case EOB_ACT_END_OF_FILE:
+				{
+				(yy_did_buffer_switch_on_eof) = 0;
+
+				if ( yywrap( ) )
+					{
+					/* Note: because we've taken care in
+					 * yy_get_next_buffer() to have set up
+					 * yytext, we can now set up
+					 * yy_c_buf_p so that if some total
+					 * hoser (like flex itself) wants to
+					 * call the scanner after we return the
+					 * YY_NULL, it'll still work - another
+					 * YY_NULL will get returned.
+					 */
+					(yy_c_buf_p) = (yytext_ptr) + YY_MORE_ADJ;
+
+					yy_act = YY_STATE_EOF(YY_START);
+					goto do_action;
+					}
+
+				else
+					{
+					if ( ! (yy_did_buffer_switch_on_eof) )
+						YY_NEW_FILE;
+					}
+				break;
+				}
+
+			case EOB_ACT_CONTINUE_SCAN:
+				(yy_c_buf_p) =
+					(yytext_ptr) + yy_amount_of_matched_text;
+
+				yy_current_state = yy_get_previous_state(  );
+
+				yy_cp = (yy_c_buf_p);
+				yy_bp = (yytext_ptr) + YY_MORE_ADJ;
+				goto yy_match;
+
+			case EOB_ACT_LAST_MATCH:
+				(yy_c_buf_p) =
+				&YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[(yy_n_chars)];
+
+				yy_current_state = yy_get_previous_state(  );
+
+				yy_cp = (yy_c_buf_p);
+				yy_bp = (yytext_ptr) + YY_MORE_ADJ;
+				goto yy_find_action;
+			}
+		break;
+		}
+
+	default:
+		YY_FATAL_ERROR(
+			"fatal flex scanner internal error--no action found" );
+	} /* end of action switch */
+		} /* end of scanning one token */
+} /* end of yylex */
+
+/* yy_get_next_buffer - try to read in a new buffer
+ *
+ * Returns a code representing an action:
+ *	EOB_ACT_LAST_MATCH -
+ *	EOB_ACT_CONTINUE_SCAN - continue scanning from current position
+ *	EOB_ACT_END_OF_FILE - end of file
+ */
+static int yy_get_next_buffer (void)
+{
+    	register char *dest = YY_CURRENT_BUFFER_LVALUE->yy_ch_buf;
+	register char *source = (yytext_ptr);
+	register int number_to_move, i;
+	int ret_val;
+
+	if ( (yy_c_buf_p) > &YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[(yy_n_chars) + 1] )
+		YY_FATAL_ERROR(
+		"fatal flex scanner internal error--end of buffer missed" );
+
+	if ( YY_CURRENT_BUFFER_LVALUE->yy_fill_buffer == 0 )
+		{ /* Don't try to fill the buffer, so this is an EOF. */
+		if ( (yy_c_buf_p) - (yytext_ptr) - YY_MORE_ADJ == 1 )
+			{
+			/* We matched a single character, the EOB, so
+			 * treat this as a final EOF.
+			 */
+			return EOB_ACT_END_OF_FILE;
+			}
+
+		else
+			{
+			/* We matched some text prior to the EOB, first
+			 * process it.
+			 */
+			return EOB_ACT_LAST_MATCH;
+			}
+		}
+
+	/* Try to read more data. */
+
+	/* First move last chars to start of buffer. */
+	number_to_move = (int) ((yy_c_buf_p) - (yytext_ptr)) - 1;
+
+	for ( i = 0; i < number_to_move; ++i )
+		*(dest++) = *(source++);
+
+	if ( YY_CURRENT_BUFFER_LVALUE->yy_buffer_status == YY_BUFFER_EOF_PENDING )
+		/* don't do the read, it's not guaranteed to return an EOF,
+		 * just force an EOF
+		 */
+		YY_CURRENT_BUFFER_LVALUE->yy_n_chars = (yy_n_chars) = 0;
+
+	else
+		{
+			size_t num_to_read =
+			YY_CURRENT_BUFFER_LVALUE->yy_buf_size - number_to_move - 1;
+
+		while ( num_to_read <= 0 )
+			{ /* Not enough room in the buffer - grow it. */
+
+			/* just a shorter name for the current buffer */
+			YY_BUFFER_STATE b = YY_CURRENT_BUFFER;
+
+			int yy_c_buf_p_offset =
+				(int) ((yy_c_buf_p) - b->yy_ch_buf);
+
+			if ( b->yy_is_our_buffer )
+				{
+				int new_size = b->yy_buf_size * 2;
+
+				if ( new_size <= 0 )
+					b->yy_buf_size += b->yy_buf_size / 8;
+				else
+					b->yy_buf_size *= 2;
+
+				b->yy_ch_buf = (char *)
+					/* Include room in for 2 EOB chars. */
+					yyrealloc((void *) b->yy_ch_buf,b->yy_buf_size + 2  );
+				}
+			else
+				/* Can't grow it, we don't own it. */
+				b->yy_ch_buf = 0;
+
+			if ( ! b->yy_ch_buf )
+				YY_FATAL_ERROR(
+				"fatal error - scanner input buffer overflow" );
+
+			(yy_c_buf_p) = &b->yy_ch_buf[yy_c_buf_p_offset];
+
+			num_to_read = YY_CURRENT_BUFFER_LVALUE->yy_buf_size -
+						number_to_move - 1;
+
+			}
+
+		if ( num_to_read > YY_READ_BUF_SIZE )
+			num_to_read = YY_READ_BUF_SIZE;
+
+		/* Read in more data. */
+		YY_INPUT( (&YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[number_to_move]),
+			(yy_n_chars), num_to_read );
+
+		YY_CURRENT_BUFFER_LVALUE->yy_n_chars = (yy_n_chars);
+		}
+
+	if ( (yy_n_chars) == 0 )
+		{
+		if ( number_to_move == YY_MORE_ADJ )
+			{
+			ret_val = EOB_ACT_END_OF_FILE;
+			yyrestart(yyin  );
+			}
+
+		else
+			{
+			ret_val = EOB_ACT_LAST_MATCH;
+			YY_CURRENT_BUFFER_LVALUE->yy_buffer_status =
+				YY_BUFFER_EOF_PENDING;
+			}
+		}
+
+	else
+		ret_val = EOB_ACT_CONTINUE_SCAN;
+
+	(yy_n_chars) += number_to_move;
+	YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[(yy_n_chars)] = YY_END_OF_BUFFER_CHAR;
+	YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[(yy_n_chars) + 1] = YY_END_OF_BUFFER_CHAR;
+
+	(yytext_ptr) = &YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[0];
+
+	return ret_val;
+}
+
+/* yy_get_previous_state - get the state just before the EOB char was reached */
+
+    static yy_state_type yy_get_previous_state (void)
+{
+	register yy_state_type yy_current_state;
+	register char *yy_cp;
+    
+	yy_current_state = (yy_start);
+	yy_current_state += YY_AT_BOL();
+
+	for ( yy_cp = (yytext_ptr) + YY_MORE_ADJ; yy_cp < (yy_c_buf_p); ++yy_cp )
+		{
+		register YY_CHAR yy_c = (*yy_cp ? yy_ec[YY_SC_TO_UI(*yy_cp)] : 1);
+		if ( yy_accept[yy_current_state] )
+			{
+			(yy_last_accepting_state) = yy_current_state;
+			(yy_last_accepting_cpos) = yy_cp;
+			}
+		while ( yy_chk[yy_base[yy_current_state] + yy_c] != yy_current_state )
+			{
+			yy_current_state = (int) yy_def[yy_current_state];
+			if ( yy_current_state >= 63 )
+				yy_c = yy_meta[(unsigned int) yy_c];
+			}
+		yy_current_state = yy_nxt[yy_base[yy_current_state] + (unsigned int) yy_c];
+		}
+
+	return yy_current_state;
+}
+
+/* yy_try_NUL_trans - try to make a transition on the NUL character
+ *
+ * synopsis
+ *	next_state = yy_try_NUL_trans( current_state );
+ */
+    static yy_state_type yy_try_NUL_trans  (yy_state_type yy_current_state )
+{
+	register int yy_is_jam;
+    	register char *yy_cp = (yy_c_buf_p);
+
+	register YY_CHAR yy_c = 1;
+	if ( yy_accept[yy_current_state] )
+		{
+		(yy_last_accepting_state) = yy_current_state;
+		(yy_last_accepting_cpos) = yy_cp;
+		}
+	while ( yy_chk[yy_base[yy_current_state] + yy_c] != yy_current_state )
+		{
+		yy_current_state = (int) yy_def[yy_current_state];
+		if ( yy_current_state >= 63 )
+			yy_c = yy_meta[(unsigned int) yy_c];
+		}
+	yy_current_state = yy_nxt[yy_base[yy_current_state] + (unsigned int) yy_c];
+	yy_is_jam = (yy_current_state == 62);
+
+	return yy_is_jam ? 0 : yy_current_state;
+}
+
+#ifndef YY_NO_INPUT
+#ifdef __cplusplus
+    static int yyinput (void)
+#else
+    static int input  (void)
+#endif
+
+{
+	int c;
+    
+	*(yy_c_buf_p) = (yy_hold_char);
+
+	if ( *(yy_c_buf_p) == YY_END_OF_BUFFER_CHAR )
+		{
+		/* yy_c_buf_p now points to the character we want to return.
+		 * If this occurs *before* the EOB characters, then it's a
+		 * valid NUL; if not, then we've hit the end of the buffer.
+		 */
+		if ( (yy_c_buf_p) < &YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[(yy_n_chars)] )
+			/* This was really a NUL. */
+			*(yy_c_buf_p) = '\0';
+
+		else
+			{ /* need more input */
+			int offset = (yy_c_buf_p) - (yytext_ptr);
+			++(yy_c_buf_p);
+
+			switch ( yy_get_next_buffer(  ) )
+				{
+				case EOB_ACT_LAST_MATCH:
+					/* This happens because yy_g_n_b()
+					 * sees that we've accumulated a
+					 * token and flags that we need to
+					 * try matching the token before
+					 * proceeding.  But for input(),
+					 * there's no matching to consider.
+					 * So convert the EOB_ACT_LAST_MATCH
+					 * to EOB_ACT_END_OF_FILE.
+					 */
+
+					/* Reset buffer status. */
+					yyrestart(yyin );
+
+					/*FALLTHROUGH*/
+
+				case EOB_ACT_END_OF_FILE:
+					{
+					if ( yywrap( ) )
+						return EOF;
+
+					if ( ! (yy_did_buffer_switch_on_eof) )
+						YY_NEW_FILE;
+#ifdef __cplusplus
+					return yyinput();
+#else
+					return input();
+#endif
+					}
+
+				case EOB_ACT_CONTINUE_SCAN:
+					(yy_c_buf_p) = (yytext_ptr) + offset;
+					break;
+				}
+			}
+		}
+
+	c = *(unsigned char *) (yy_c_buf_p);	/* cast for 8-bit char's */
+	*(yy_c_buf_p) = '\0';	/* preserve yytext */
+	(yy_hold_char) = *++(yy_c_buf_p);
+
+	YY_CURRENT_BUFFER_LVALUE->yy_at_bol = (c == '\n');
+	if ( YY_CURRENT_BUFFER_LVALUE->yy_at_bol )
+		   
+    yylineno++;
+;
+
+	return c;
+}
+#endif	/* ifndef YY_NO_INPUT */
+
+/** Immediately switch to a different input stream.
+ * @param input_file A readable stream.
+ * 
+ * @note This function does not reset the start condition to @c INITIAL .
+ */
+    void yyrestart  (FILE * input_file )
+{
+    
+	if ( ! YY_CURRENT_BUFFER ){
+        yyensure_buffer_stack ();
+		YY_CURRENT_BUFFER_LVALUE =
+            yy_create_buffer(yyin,YY_BUF_SIZE );
+	}
+
+	yy_init_buffer(YY_CURRENT_BUFFER,input_file );
+	yy_load_buffer_state( );
+}
+
+/** Switch to a different input buffer.
+ * @param new_buffer The new input buffer.
+ * 
+ */
+    void yy_switch_to_buffer  (YY_BUFFER_STATE  new_buffer )
+{
+    
+	/* TODO. We should be able to replace this entire function body
+	 * with
+	 *		yypop_buffer_state();
+	 *		yypush_buffer_state(new_buffer);
+     */
+	yyensure_buffer_stack ();
+	if ( YY_CURRENT_BUFFER == new_buffer )
+		return;
+
+	if ( YY_CURRENT_BUFFER )
+		{
+		/* Flush out information for old buffer. */
+		*(yy_c_buf_p) = (yy_hold_char);
+		YY_CURRENT_BUFFER_LVALUE->yy_buf_pos = (yy_c_buf_p);
+		YY_CURRENT_BUFFER_LVALUE->yy_n_chars = (yy_n_chars);
+		}
+
+	YY_CURRENT_BUFFER_LVALUE = new_buffer;
+	yy_load_buffer_state( );
+
+	/* We don't actually know whether we did this switch during
+	 * EOF (yywrap()) processing, but the only time this flag
+	 * is looked at is after yywrap() is called, so it's safe
+	 * to go ahead and always set it.
+	 */
+	(yy_did_buffer_switch_on_eof) = 1;
+}
+
+static void yy_load_buffer_state  (void)
+{
+    	(yy_n_chars) = YY_CURRENT_BUFFER_LVALUE->yy_n_chars;
+	(yytext_ptr) = (yy_c_buf_p) = YY_CURRENT_BUFFER_LVALUE->yy_buf_pos;
+	yyin = YY_CURRENT_BUFFER_LVALUE->yy_input_file;
+	(yy_hold_char) = *(yy_c_buf_p);
+}
+
+/** Allocate and initialize an input buffer state.
+ * @param file A readable stream.
+ * @param size The character buffer size in bytes. When in doubt, use @c YY_BUF_SIZE.
+ * 
+ * @return the allocated buffer state.
+ */
+    YY_BUFFER_STATE yy_create_buffer  (FILE * file, int  size )
+{
+	YY_BUFFER_STATE b;
+    
+	b = (YY_BUFFER_STATE) yyalloc(sizeof( struct yy_buffer_state )  );
+	if ( ! b )
+		YY_FATAL_ERROR( "out of dynamic memory in yy_create_buffer()" );
+
+	b->yy_buf_size = size;
+
+	/* yy_ch_buf has to be 2 characters longer than the size given because
+	 * we need to put in 2 end-of-buffer characters.
+	 */
+	b->yy_ch_buf = (char *) yyalloc(b->yy_buf_size + 2  );
+	if ( ! b->yy_ch_buf )
+		YY_FATAL_ERROR( "out of dynamic memory in yy_create_buffer()" );
+
+	b->yy_is_our_buffer = 1;
+
+	yy_init_buffer(b,file );
+
+	return b;
+}
+
+/** Destroy the buffer.
+ * @param b a buffer created with yy_create_buffer()
+ * 
+ */
+    void yy_delete_buffer (YY_BUFFER_STATE  b )
+{
+    
+	if ( ! b )
+		return;
+
+	if ( b == YY_CURRENT_BUFFER ) /* Not sure if we should pop here. */
+		YY_CURRENT_BUFFER_LVALUE = (YY_BUFFER_STATE) 0;
+
+	if ( b->yy_is_our_buffer )
+		yyfree((void *) b->yy_ch_buf  );
+
+	yyfree((void *) b  );
+}
+
+#ifndef __cplusplus
+extern int isatty (int );
+#endif /* __cplusplus */
+    
+/* Initializes or reinitializes a buffer.
+ * This function is sometimes called more than once on the same buffer,
+ * such as during a yyrestart() or at EOF.
+ */
+    static void yy_init_buffer  (YY_BUFFER_STATE  b, FILE * file )
+
+{
+	int oerrno = errno;
+    
+	yy_flush_buffer(b );
+
+	b->yy_input_file = file;
+	b->yy_fill_buffer = 1;
+
+    /* If b is the current buffer, then yy_init_buffer was _probably_
+     * called from yyrestart() or through yy_get_next_buffer.
+     * In that case, we don't want to reset the lineno or column.
+     */
+    if (b != YY_CURRENT_BUFFER){
+        b->yy_bs_lineno = 1;
+        b->yy_bs_column = 0;
+    }
+
+        b->yy_is_interactive = file ? (isatty( fileno(file) ) > 0) : 0;
+    
+	errno = oerrno;
+}
+
+/** Discard all buffered characters. On the next scan, YY_INPUT will be called.
+ * @param b the buffer state to be flushed, usually @c YY_CURRENT_BUFFER.
+ * 
+ */
+    void yy_flush_buffer (YY_BUFFER_STATE  b )
+{
+    	if ( ! b )
+		return;
+
+	b->yy_n_chars = 0;
+
+	/* We always need two end-of-buffer characters.  The first causes
+	 * a transition to the end-of-buffer state.  The second causes
+	 * a jam in that state.
+	 */
+	b->yy_ch_buf[0] = YY_END_OF_BUFFER_CHAR;
+	b->yy_ch_buf[1] = YY_END_OF_BUFFER_CHAR;
+
+	b->yy_buf_pos = &b->yy_ch_buf[0];
+
+	b->yy_at_bol = 1;
+	b->yy_buffer_status = YY_BUFFER_NEW;
+
+	if ( b == YY_CURRENT_BUFFER )
+		yy_load_buffer_state( );
+}
+
+/** Pushes the new state onto the stack. The new state becomes
+ *  the current state. This function will allocate the stack
+ *  if necessary.
+ *  @param new_buffer The new state.
+ *  
+ */
+void yypush_buffer_state (YY_BUFFER_STATE new_buffer )
+{
+    	if (new_buffer == NULL)
+		return;
+
+	yyensure_buffer_stack();
+
+	/* This block is copied from yy_switch_to_buffer. */
+	if ( YY_CURRENT_BUFFER )
+		{
+		/* Flush out information for old buffer. */
+		*(yy_c_buf_p) = (yy_hold_char);
+		YY_CURRENT_BUFFER_LVALUE->yy_buf_pos = (yy_c_buf_p);
+		YY_CURRENT_BUFFER_LVALUE->yy_n_chars = (yy_n_chars);
+		}
+
+	/* Only push if top exists. Otherwise, replace top. */
+	if (YY_CURRENT_BUFFER)
+		(yy_buffer_stack_top)++;
+	YY_CURRENT_BUFFER_LVALUE = new_buffer;
+
+	/* copied from yy_switch_to_buffer. */
+	yy_load_buffer_state( );
+	(yy_did_buffer_switch_on_eof) = 1;
+}
+
+/** Removes and deletes the top of the stack, if present.
+ *  The next element becomes the new top.
+ *  
+ */
+void yypop_buffer_state (void)
+{
+    	if (!YY_CURRENT_BUFFER)
+		return;
+
+	yy_delete_buffer(YY_CURRENT_BUFFER );
+	YY_CURRENT_BUFFER_LVALUE = NULL;
+	if ((yy_buffer_stack_top) > 0)
+		--(yy_buffer_stack_top);
+
+	if (YY_CURRENT_BUFFER) {
+		yy_load_buffer_state( );
+		(yy_did_buffer_switch_on_eof) = 1;
+	}
+}
+
+/* Allocates the stack if it does not exist.
+ *  Guarantees space for at least one push.
+ */
+static void yyensure_buffer_stack (void)
+{
+	int num_to_alloc;
+    
+	if (!(yy_buffer_stack)) {
+
+		/* First allocation is just for 2 elements, since we don't know if this
+		 * scanner will even need a stack. We use 2 instead of 1 to avoid an
+		 * immediate realloc on the next call.
+         */
+		num_to_alloc = 1;
+		(yy_buffer_stack) = (struct yy_buffer_state**)yyalloc
+								(num_to_alloc * sizeof(struct yy_buffer_state*)
+								);
+		
+		memset((yy_buffer_stack), 0, num_to_alloc * sizeof(struct yy_buffer_state*));
+				
+		(yy_buffer_stack_max) = num_to_alloc;
+		(yy_buffer_stack_top) = 0;
+		return;
+	}
+
+	if ((yy_buffer_stack_top) >= ((yy_buffer_stack_max)) - 1){
+
+		/* Increase the buffer to prepare for a possible push. */
+		int grow_size = 8 /* arbitrary grow size */;
+
+		num_to_alloc = (yy_buffer_stack_max) + grow_size;
+		(yy_buffer_stack) = (struct yy_buffer_state**)yyrealloc
+								((yy_buffer_stack),
+								num_to_alloc * sizeof(struct yy_buffer_state*)
+								);
+
+		/* zero only the new slots.*/
+		memset((yy_buffer_stack) + (yy_buffer_stack_max), 0, grow_size * sizeof(struct yy_buffer_state*));
+		(yy_buffer_stack_max) = num_to_alloc;
+	}
+}
+
+/** Setup the input buffer state to scan directly from a user-specified character buffer.
+ * @param base the character buffer
+ * @param size the size in bytes of the character buffer
+ * 
+ * @return the newly allocated buffer state object. 
+ */
+YY_BUFFER_STATE yy_scan_buffer  (char * base, yy_size_t  size )
+{
+	YY_BUFFER_STATE b;
+    
+	if ( size < 2 ||
+	     base[size-2] != YY_END_OF_BUFFER_CHAR ||
+	     base[size-1] != YY_END_OF_BUFFER_CHAR )
+		/* They forgot to leave room for the EOB's. */
+		return 0;
+
+	b = (YY_BUFFER_STATE) yyalloc(sizeof( struct yy_buffer_state )  );
+	if ( ! b )
+		YY_FATAL_ERROR( "out of dynamic memory in yy_scan_buffer()" );
+
+	b->yy_buf_size = size - 2;	/* "- 2" to take care of EOB's */
+	b->yy_buf_pos = b->yy_ch_buf = base;
+	b->yy_is_our_buffer = 0;
+	b->yy_input_file = 0;
+	b->yy_n_chars = b->yy_buf_size;
+	b->yy_is_interactive = 0;
+	b->yy_at_bol = 1;
+	b->yy_fill_buffer = 0;
+	b->yy_buffer_status = YY_BUFFER_NEW;
+
+	yy_switch_to_buffer(b  );
+
+	return b;
+}
+
+/** Setup the input buffer state to scan a string. The next call to yylex() will
+ * scan from a @e copy of @a str.
+ * @param str a NUL-terminated string to scan
+ * 
+ * @return the newly allocated buffer state object.
+ * @note If you want to scan bytes that may contain NUL values, then use
+ *       yy_scan_bytes() instead.
+ */
+YY_BUFFER_STATE yy_scan_string (yyconst char * yy_str )
+{
+    
+	return yy_scan_bytes(yy_str,strlen(yy_str) );
+}
+
+/** Setup the input buffer state to scan the given bytes. The next call to yylex() will
+ * scan from a @e copy of @a bytes.
+ * @param bytes the byte buffer to scan
+ * @param len the number of bytes in the buffer pointed to by @a bytes.
+ * 
+ * @return the newly allocated buffer state object.
+ */
+YY_BUFFER_STATE yy_scan_bytes  (yyconst char * bytes, int  len )
+{
+	YY_BUFFER_STATE b;
+	char *buf;
+	yy_size_t n;
+	int i;
+    
+	/* Get memory for full buffer, including space for trailing EOB's. */
+	n = len + 2;
+	buf = (char *) yyalloc(n  );
+	if ( ! buf )
+		YY_FATAL_ERROR( "out of dynamic memory in yy_scan_bytes()" );
+
+	for ( i = 0; i < len; ++i )
+		buf[i] = bytes[i];
+
+	buf[len] = buf[len+1] = YY_END_OF_BUFFER_CHAR;
+
+	b = yy_scan_buffer(buf,n );
+	if ( ! b )
+		YY_FATAL_ERROR( "bad buffer in yy_scan_bytes()" );
+
+	/* It's okay to grow etc. this buffer, and we should throw it
+	 * away when we're done.
+	 */
+	b->yy_is_our_buffer = 1;
+
+	return b;
+}
+
+#ifndef YY_EXIT_FAILURE
+#define YY_EXIT_FAILURE 2
+#endif
+
+static void yy_fatal_error (yyconst char* msg )
+{
+    	(void) fprintf( stderr, "%s\n", msg );
+	exit( YY_EXIT_FAILURE );
+}
+
+/* Redefine yyless() so it works in section 3 code. */
+
+#undef yyless
+#define yyless(n) \
+	do \
+		{ \
+		/* Undo effects of setting up yytext. */ \
+        int yyless_macro_arg = (n); \
+        YY_LESS_LINENO(yyless_macro_arg);\
+		yytext[yyleng] = (yy_hold_char); \
+		(yy_c_buf_p) = yytext + yyless_macro_arg; \
+		(yy_hold_char) = *(yy_c_buf_p); \
+		*(yy_c_buf_p) = '\0'; \
+		yyleng = yyless_macro_arg; \
+		} \
+	while ( 0 )
+
+/* Accessor  methods (get/set functions) to struct members. */
+
+/** Get the current line number.
+ * 
+ */
+int yyget_lineno  (void)
+{
+        
+    return yylineno;
+}
+
+/** Get the input stream.
+ * 
+ */
+FILE *yyget_in  (void)
+{
+        return yyin;
+}
+
+/** Get the output stream.
+ * 
+ */
+FILE *yyget_out  (void)
+{
+        return yyout;
+}
+
+/** Get the length of the current token.
+ * 
+ */
+int yyget_leng  (void)
+{
+        return yyleng;
+}
+
+/** Get the current token.
+ * 
+ */
+
+char *yyget_text  (void)
+{
+        return yytext;
+}
+
+/** Set the current line number.
+ * @param line_number
+ * 
+ */
+void yyset_lineno (int  line_number )
+{
+    
+    yylineno = line_number;
+}
+
+/** Set the input stream. This does not discard the current
+ * input buffer.
+ * @param in_str A readable stream.
+ * 
+ * @see yy_switch_to_buffer
+ */
+void yyset_in (FILE *  in_str )
+{
+        yyin = in_str ;
+}
+
+void yyset_out (FILE *  out_str )
+{
+        yyout = out_str ;
+}
+
+int yyget_debug  (void)
+{
+        return yy_flex_debug;
+}
+
+void yyset_debug (int  bdebug )
+{
+        yy_flex_debug = bdebug ;
+}
+
+/* yylex_destroy is for both reentrant and non-reentrant scanners. */
+int yylex_destroy  (void)
+{
+    
+    /* Pop the buffer stack, destroying each element. */
+	while(YY_CURRENT_BUFFER){
+		yy_delete_buffer(YY_CURRENT_BUFFER  );
+		YY_CURRENT_BUFFER_LVALUE = NULL;
+		yypop_buffer_state();
+	}
+
+	/* Destroy the stack itself. */
+	yyfree((yy_buffer_stack) );
+	(yy_buffer_stack) = NULL;
+
+    return 0;
+}
+
+/*
+ * Internal utility routines.
+ */
+
+#ifndef yytext_ptr
+static void yy_flex_strncpy (char* s1, yyconst char * s2, int n )
+{
+	register int i;
+    	for ( i = 0; i < n; ++i )
+		s1[i] = s2[i];
+}
+#endif
+
+#ifdef YY_NEED_STRLEN
+static int yy_flex_strlen (yyconst char * s )
+{
+	register int n;
+    	for ( n = 0; s[n]; ++n )
+		;
+
+	return n;
+}
+#endif
+
+void *yyalloc (yy_size_t  size )
+{
+	return (void *) malloc( size );
+}
+
+void *yyrealloc  (void * ptr, yy_size_t  size )
+{
+	/* The cast to (char *) in the following accommodates both
+	 * implementations that use char* generic pointers, and those
+	 * that use void* generic pointers.  It works with the latter
+	 * because both ANSI C and C++ allow castless assignment from
+	 * any pointer type to void*, and deal with argument conversions
+	 * as though doing an assignment.
+	 */
+	return (void *) realloc( (char *) ptr, size );
+}
+
+void yyfree (void * ptr )
+{
+	free( (char *) ptr );	/* see yyrealloc() for (char *) cast */
+}
+
+#define YYTABLES_NAME "yytables"
+
+#undef YY_NEW_FILE
+#undef YY_FLUSH_BUFFER
+#undef yy_set_bol
+#undef yy_new_buffer
+#undef yy_set_interactive
+#undef yytext_ptr
+#undef YY_DO_BEFORE_ACTION
+
+#ifdef YY_DECL_IS_OURS
+#undef YY_DECL_IS_OURS
+#undef YY_DECL
+#endif
+#line 206 "conf_lexer.lxx"
+
+
+
diff --git a/debian/htdig/htdig-3.2.0b6/htcommon/conf_lexer.lxx b/debian/htdig/htdig-3.2.0b6/htcommon/conf_lexer.lxx
new file mode 100644
index 00000000..d17f7e50
--- /dev/null
+++ b/debian/htdig/htdig-3.2.0b6/htcommon/conf_lexer.lxx
@@ -0,0 +1,206 @@
+/*
+//
+// conf_lexer.lxx
+//
+//             This lexical parser is used to parse ht://Dig config
+//             files.  
+//
+//       Note:  The resulting .cxx file produces warnings of unused
+//		labels.  As at 2003-06-02, these have been manually
+//		removed, but they will reappear when  (f)lex  is re-run.
+//
+// Part of the ht://Dig package   <http://www.htdig.org/>
+// Copyright (c) 1999-2004 The ht://Dig Group
+// For copyright details, see the file COPYING in your distribution
+// or the GNU Library General Public License (LGPL) version 2 or later
+// <http://www.gnu.org/copyleft/lgpl.html>
+//
+// $Id: conf_lexer.lxx,v 1.12 2004/06/10 14:48:38 angusgb Exp $
+//
+*/
+%{
+#ifdef HAVE_CONFIG_H
+#include "htconfig.h"
+#endif /* HAVE_CONFIG_H */
+%}
+
+%option yylineno noyywrap nounput
+%x t_right
+%x incl
+%x bracket
+%x br_string
+
+%{
+#ifdef HAVE_STRINGS_H
+#include <strings.h>
+#endif
+
+#include "HtConfiguration.h"
+//#include "Dictionary.h"
+#include "conf_parser.h"
+#define MAX_INCLUDE_DEPTH 10
+YY_BUFFER_STATE include_stack[MAX_INCLUDE_DEPTH];
+String *name_stack[MAX_INCLUDE_DEPTH];
+int lineno_stack[MAX_INCLUDE_DEPTH];
+int include_stack_ptr = 0;
+%}
+
+KEYWORD			[a-zA-Z_][a-zA-Z_0-9/]*
+NUMBER			[0-9]+
+STRING			[\x21-\xff]+
+BR_STRING		[^ \n\t<>]+
+%%
+
+^[[:space:]]*#.*\n	/*   Ignore comments     */
+^[[:space:]]*\n		/*   Ignore empty lines   */
+<*>[ \t]+		/*   Ignore spaces       */
+include[ \t]*:		BEGIN(incl);
+"<"                     { BEGIN(bracket); return(T_LEFT_BR); }
+<bracket>"/"                       return(T_SLASH);
+<bracket>">"            return(T_RIGHT_BR);
+<INITIAL,bracket>{KEYWORD}		{
+			//yylval.str = (char *)malloc(yyleng+1);
+                        yylval.str = new char[yyleng+1];
+                        strcpy(yylval.str,yytext);
+			return(T_KEYWORD);
+			}
+<br_string>{BR_STRING}	{
+			BEGIN(bracket);
+			yylval.str = new char[yyleng+1];
+			strcpy(yylval.str,yytext);
+			return(T_STRING);
+			}
+
+<t_right>{NUMBER}		{
+                        //yylval.str = (char*)malloc(yyleng+1);
+                        yylval.str = new char[yyleng+1];
+                        strcpy(yylval.str,yytext);
+			return(T_NUMBER);
+			}
+
+<INITIAL,bracket>:			{
+			if (YY_START==bracket)
+			    BEGIN(br_string);
+			else
+			BEGIN(t_right);
+                        return(T_DELIMITER);
+                        }
+
+<t_right>{STRING}\\\n	{
+			//yylval.str = (char *)malloc(yyleng+1-2);
+                        yylval.str = new char[yyleng+1-2];
+                        //strcpy(yylval.str,yytext);
+                        memcpy(yylval.str,yytext,yyleng-2);
+                        yylval.str[yyleng-2]='\0';
+			return(T_STRING);  
+			}
+
+<t_right>"\""[^\n]+"\"" {
+			yylval.str = new char[yyleng+1];
+			strcpy(yylval.str,yytext);
+                        return(T_STRING);
+                        }
+
+<t_right>{STRING}		{
+			//yylval.str = (char *)malloc(yyleng+1);
+                        yylval.str = new char[yyleng+1];
+                        strcpy(yylval.str,yytext);
+			return(T_STRING);
+			}
+<t_right>\\\n		
+			{
+			/*   Ignore newline after "\"    */
+			}
+<t_right>[ \t]*		
+			{
+			/*   Ignore spaces               */
+			}
+<incl>{STRING}		{ /* got the include file name */
+			if ( include_stack_ptr >= MAX_INCLUDE_DEPTH )
+			    {
+			    fprintf(stderr,"Includes nested too deeply\n");
+			    // exit(1);	// Seems too harsh!
+			    return(T_NEWLINE);
+			    }
+			include_stack[include_stack_ptr++] =
+			    YY_CURRENT_BUFFER;
+
+			HtConfiguration* config= HtConfiguration::config();
+			// handle ${var} in file name
+			String ParsedFilename =
+				config->ParseString(yytext);
+
+			if (ParsedFilename[0] != '/')
+			    {	// Given file name not fully qualified
+				// so strip dir. name from current one
+			    String str;
+			    if (include_stack_ptr > 1)
+				str = *name_stack[include_stack_ptr-2];
+			    else	// still at top level config
+				str = config->getFileName();
+			    int len = str.lastIndexOf('/') + 1;
+			    if (len > 0)
+				{	// Current name has directory path
+					// component, so use it for new name
+				str.chop(str.length() - len);
+				str << ParsedFilename;
+				ParsedFilename = str;
+				}
+			    }
+
+			yyin = fopen( ParsedFilename.get(), "r" );
+
+			if ( ! yyin ) {
+			    fprintf(stderr,"can't find file: %s\n",yytext);
+			    // exit(1);	// Seems too harsh!
+		            include_stack_ptr--;
+			    return(T_NEWLINE);
+			}
+			name_stack[include_stack_ptr-1] =
+					new String(ParsedFilename.get());
+			lineno_stack[include_stack_ptr-1] = yylineno;
+			yylineno = 1;
+		        yy_switch_to_buffer( yy_create_buffer( yyin, YY_BUF_SIZE ) );
+
+		        BEGIN(INITIAL);
+		        }
+
+<<EOF>> 		{
+		        if ( include_stack_ptr <= 0 )
+			    {
+			    static int termnext = 0;
+			    // fix to allow unterminated final line
+			    if (++termnext <= 1)
+				return(T_NEWLINE);
+			    termnext = 0;	// in case we're called again
+		            yyterminate();
+			    }
+		        else
+		            {
+			    delete name_stack[include_stack_ptr-1];
+			    yylineno = lineno_stack[include_stack_ptr-1];
+		            yy_delete_buffer( YY_CURRENT_BUFFER );
+		            yy_switch_to_buffer(
+		                 include_stack[--include_stack_ptr] );
+		            }
+		        }
+
+
+<bracket,t_right>\n			{
+			BEGIN(INITIAL);
+			return(T_NEWLINE);
+			}
+^[[:space:]]+
+
+\n			
+<*>.|\n		{ 
+	HtConfiguration* config= HtConfiguration::config();
+	String str;
+	if (include_stack_ptr > 0)
+	    str = *name_stack[include_stack_ptr-1];
+	else	// still at top level config
+	    str = config->getFileName();
+	fprintf(stderr,"Unknown char in file %s line %d: %s\n",str.get(),yylineno,yytext);
+	// exit(1); // Seems too harsh!
+	}
+%%
diff --git a/debian/htdig/htdig-3.2.0b6/htcommon/conf_parser.cxx b/debian/htdig/htdig-3.2.0b6/htcommon/conf_parser.cxx
new file mode 100644
index 00000000..13b77ef8
--- /dev/null
+++ b/debian/htdig/htdig-3.2.0b6/htcommon/conf_parser.cxx
@@ -0,0 +1,1553 @@
+/* A Bison parser, made by GNU Bison 1.875c.  */
+
+/* Skeleton parser for Yacc-like parsing with Bison,
+   Copyright (C) 1984, 1989, 1990, 2000, 2001, 2002, 2003 Free Software Foundation, Inc.
+
+   This program is free software; you can redistribute it and/or modify
+   it under the terms of the GNU General Public License as published by
+   the Free Software Foundation; either version 2, or (at your option)
+   any later version.
+
+   This program is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+   GNU General Public License for more details.
+
+   You should have received a copy of the GNU General Public License
+   along with this program; if not, write to the Free Software
+   Foundation, Inc., 59 Temple Place - Suite 330,
+   Boston, MA 02111-1307, USA.  */
+
+/* As a special exception, when this file is copied by Bison into a
+   Bison output file, you may use that output file without restriction.
+   This special exception was added by the Free Software Foundation
+   in version 1.24 of Bison.  */
+
+/* Written by Richard Stallman by simplifying the original so called
+   ``semantic'' parser.  */
+
+/* All symbols defined below should begin with yy or YY, to avoid
+   infringing on user name space.  This should be done even for local
+   variables, as they might otherwise be expanded by user macros.
+   There are some unavoidable exceptions within include files to
+   define necessary library symbols; they are noted "INFRINGES ON
+   USER NAME SPACE" below.  */
+
+/* Identify Bison output.  */
+#define YYBISON 1
+
+/* Skeleton name.  */
+#define YYSKELETON_NAME "yacc.c"
+
+/* Pure parsers.  */
+#define YYPURE 0
+
+/* Using locations.  */
+#define YYLSP_NEEDED 0
+
+
+
+/* Tokens.  */
+#ifndef YYTOKENTYPE
+# define YYTOKENTYPE
+   /* Put the tokens into the symbol table, so that GDB and other debuggers
+      know about them.  */
+   enum yytokentype {
+     NUM = 258,
+     T_DELIMITER = 259,
+     T_NEWLINE = 260,
+     T_RIGHT_BR = 261,
+     T_LEFT_BR = 262,
+     T_SLASH = 263,
+     T_STRING = 264,
+     T_KEYWORD = 265,
+     T_NUMBER = 266
+   };
+#endif
+#define NUM 258
+#define T_DELIMITER 259
+#define T_NEWLINE 260
+#define T_RIGHT_BR 261
+#define T_LEFT_BR 262
+#define T_SLASH 263
+#define T_STRING 264
+#define T_KEYWORD 265
+#define T_NUMBER 266
+
+
+
+
+/* Copy the first part of user declarations.  */
+#line 1 "conf_parser.yxx"
+
+//
+// conf_parser.yxx
+//
+//             This syntax analyzer is used to parse ht://Dig config
+//             files.
+//
+// Part of the ht://Dig package   <http://www.htdig.org/>
+// Copyright (c) 1999-2004 The ht://Dig Group
+// For copyright details, see the file COPYING in your distribution
+// or the GNU Library General Public License (LGPL) version 2 or later
+// <http://www.gnu.org/copyleft/lgpl.html>
+//
+// $Id: conf_parser.cxx,v 1.7 2004/06/10 14:48:38 angusgb Exp $
+//
+
+#ifdef HAVE_CONFIG_H
+#include "htconfig.h"
+#endif /* HAVE_CONFIG_H */
+
+/* Bison version > 1.25 needed */
+/* TODO: 
+1. Better error handling
+2. ?
+*/
+#include <stdio.h> /* for debug */
+#include <stdlib.h>
+
+#ifdef HAVE_STD
+#include <iostream>
+#ifdef HAVE_NAMESPACES
+using namespace std;
+#endif
+#else
+#include <iostream.h>
+#endif /* HAVE_STD */
+
+#include "HtConfiguration.h"
+#include "htString.h"
+/*#define YYDEBUG 1*/
+#define YYPARSE_PARAM aConf
+int yyerror(char *s);
+int yylex(void);  
+#undef DEBUG
+#ifdef DEBUG
+int sn_debug=3;
+#endif
+
+
+/* Enabling traces.  */
+#ifndef YYDEBUG
+# define YYDEBUG 0
+#endif
+
+/* Enabling verbose error messages.  */
+#ifdef YYERROR_VERBOSE
+# undef YYERROR_VERBOSE
+# define YYERROR_VERBOSE 1
+#else
+# define YYERROR_VERBOSE 0
+#endif
+
+#if ! defined (YYSTYPE) && ! defined (YYSTYPE_IS_DECLARED)
+#line 50 "conf_parser.yxx"
+typedef union YYSTYPE {
+	char *str;
+	ConfigDefaults	*ConfLine;
+	HtConfiguration	*ConfLines;
+} YYSTYPE;
+/* Line 191 of yacc.c.  */
+#line 153 "conf_parser.cxx"
+# define yystype YYSTYPE /* obsolescent; will be withdrawn */
+# define YYSTYPE_IS_DECLARED 1
+# define YYSTYPE_IS_TRIVIAL 1
+#endif
+
+
+
+/* Copy the second part of user declarations.  */
+
+
+/* Line 214 of yacc.c.  */
+#line 165 "conf_parser.cxx"
+
+#if ! defined (yyoverflow) || YYERROR_VERBOSE
+
+# ifndef YYFREE
+#  define YYFREE free
+# endif
+# ifndef YYMALLOC
+#  define YYMALLOC malloc
+# endif
+
+/* The parser invokes alloca or malloc; define the necessary symbols.  */
+
+# ifdef YYSTACK_USE_ALLOCA
+#  if YYSTACK_USE_ALLOCA
+#   define YYSTACK_ALLOC alloca
+#  endif
+# else
+#  if defined (alloca) || defined (_ALLOCA_H)
+#   define YYSTACK_ALLOC alloca
+#  else
+#   ifdef __GNUC__
+#    define YYSTACK_ALLOC __builtin_alloca
+#   endif
+#  endif
+# endif
+
+# ifdef YYSTACK_ALLOC
+   /* Pacify GCC's `empty if-body' warning. */
+#  define YYSTACK_FREE(Ptr) do { /* empty */; } while (0)
+# else
+#  if defined (__STDC__) || defined (__cplusplus)
+#   include <stdlib.h> /* INFRINGES ON USER NAME SPACE */
+#   define YYSIZE_T size_t
+#  endif
+#  define YYSTACK_ALLOC YYMALLOC
+#  define YYSTACK_FREE YYFREE
+# endif
+#endif /* ! defined (yyoverflow) || YYERROR_VERBOSE */
+
+
+#if (! defined (yyoverflow) \
+     && (! defined (__cplusplus) \
+	 || (defined (YYSTYPE_IS_TRIVIAL) && YYSTYPE_IS_TRIVIAL)))
+
+/* A type that is properly aligned for any stack member.  */
+union yyalloc
+{
+  short yyss;
+  YYSTYPE yyvs;
+  };
+
+/* The size of the maximum gap between one aligned stack and the next.  */
+# define YYSTACK_GAP_MAXIMUM (sizeof (union yyalloc) - 1)
+
+/* The size of an array large to enough to hold all stacks, each with
+   N elements.  */
+# define YYSTACK_BYTES(N) \
+     ((N) * (sizeof (short) + sizeof (YYSTYPE))				\
+      + YYSTACK_GAP_MAXIMUM)
+
+/* Copy COUNT objects from FROM to TO.  The source and destination do
+   not overlap.  */
+# ifndef YYCOPY
+#  if defined (__GNUC__) && 1 < __GNUC__
+#   define YYCOPY(To, From, Count) \
+      __builtin_memcpy (To, From, (Count) * sizeof (*(From)))
+#  else
+#   define YYCOPY(To, From, Count)		\
+      do					\
+	{					\
+	  register YYSIZE_T yyi;		\
+	  for (yyi = 0; yyi < (Count); yyi++)	\
+	    (To)[yyi] = (From)[yyi];		\
+	}					\
+      while (0)
+#  endif
+# endif
+
+/* Relocate STACK from its old location to the new one.  The
+   local variables YYSIZE and YYSTACKSIZE give the old and new number of
+   elements in the stack, and YYPTR gives the new location of the
+   stack.  Advance YYPTR to a properly aligned location for the next
+   stack.  */
+# define YYSTACK_RELOCATE(Stack)					\
+    do									\
+      {									\
+	YYSIZE_T yynewbytes;						\
+	YYCOPY (&yyptr->Stack, Stack, yysize);				\
+	Stack = &yyptr->Stack;						\
+	yynewbytes = yystacksize * sizeof (*Stack) + YYSTACK_GAP_MAXIMUM; \
+	yyptr += yynewbytes / sizeof (*yyptr);				\
+      }									\
+    while (0)
+
+#endif
+
+#if defined (__STDC__) || defined (__cplusplus)
+   typedef signed char yysigned_char;
+#else
+   typedef short yysigned_char;
+#endif
+
+/* YYFINAL -- State number of the termination state. */
+#define YYFINAL  2
+/* YYLAST -- Last index in YYTABLE.  */
+#define YYLAST   31
+
+/* YYNTOKENS -- Number of terminals. */
+#define YYNTOKENS  12
+/* YYNNTS -- Number of nonterminals. */
+#define YYNNTS  7
+/* YYNRULES -- Number of rules. */
+#define YYNRULES  20
+/* YYNRULES -- Number of states. */
+#define YYNSTATES  37
+
+/* YYTRANSLATE(YYLEX) -- Bison symbol number corresponding to YYLEX.  */
+#define YYUNDEFTOK  2
+#define YYMAXUTOK   266
+
+#define YYTRANSLATE(YYX) 						\
+  ((unsigned int) (YYX) <= YYMAXUTOK ? yytranslate[YYX] : YYUNDEFTOK)
+
+/* YYTRANSLATE[YYLEX] -- Bison symbol number corresponding to YYLEX.  */
+static const unsigned char yytranslate[] =
+{
+       0,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     2,     2,     2,     2,
+       2,     2,     2,     2,     2,     2,     1,     2,     3,     4,
+       5,     6,     7,     8,     9,    10,    11
+};
+
+#if YYDEBUG
+/* YYPRHS[YYN] -- Index of the first RHS symbol of rule number YYN in
+   YYRHS.  */
+static const unsigned char yyprhs[] =
+{
+       0,     0,     3,     4,     7,     9,    11,    13,    18,    23,
+      28,    32,    45,    47,    50,    52,    55,    58,    61,    64,
+      67
+};
+
+/* YYRHS -- A `-1'-separated list of the rules' RHS. */
+static const yysigned_char yyrhs[] =
+{
+      13,     0,    -1,    -1,    13,    14,    -1,    15,    -1,    16,
+      -1,     5,    -1,    10,     4,     9,     5,    -1,    10,     4,
+      11,     5,    -1,    10,     4,    18,     5,    -1,    10,     4,
+       5,    -1,     7,    10,     4,     9,     6,     5,    17,     7,
+       8,    10,     6,     5,    -1,    15,    -1,    17,    15,    -1,
+       5,    -1,     9,     9,    -1,    11,     9,    -1,     9,    11,
+      -1,    11,    11,    -1,    18,     9,    -1,    18,    11,    -1
+};
+
+/* YYRLINE[YYN] -- source line where rule number YYN was defined.  */
+static const unsigned char yyrline[] =
+{
+       0,    65,    65,    66,    69,    81,    87,    90,   100,   106,
+     112,   122,   143,   161,   173,   176,   189,   202,   215,   228,
+     240
+};
+#endif
+
+#if YYDEBUG || YYERROR_VERBOSE
+/* YYTNME[SYMBOL-NUM] -- String name of the symbol SYMBOL-NUM.
+   First, the terminals, then, starting at YYNTOKENS, nonterminals. */
+static const char *const yytname[] =
+{
+  "$end", "error", "$undefined", "NUM", "T_DELIMITER", "T_NEWLINE",
+  "T_RIGHT_BR", "T_LEFT_BR", "T_SLASH", "T_STRING", "T_KEYWORD",
+  "T_NUMBER", "$accept", "input", "block", "simple_expression",
+  "complex_expression", "simple_expression_list", "list", 0
+};
+#endif
+
+# ifdef YYPRINT
+/* YYTOKNUM[YYLEX-NUM] -- Internal token number corresponding to
+   token YYLEX-NUM.  */
+static const unsigned short yytoknum[] =
+{
+       0,   256,   257,   258,   259,   260,   261,   262,   263,   264,
+     265,   266
+};
+# endif
+
+/* YYR1[YYN] -- Symbol number of symbol that rule YYN derives.  */
+static const unsigned char yyr1[] =
+{
+       0,    12,    13,    13,    14,    14,    14,    15,    15,    15,
+      15,    16,    17,    17,    17,    18,    18,    18,    18,    18,
+      18
+};
+
+/* YYR2[YYN] -- Number of symbols composing right hand side of rule YYN.  */
+static const unsigned char yyr2[] =
+{
+       0,     2,     0,     2,     1,     1,     1,     4,     4,     4,
+       3,    12,     1,     2,     1,     2,     2,     2,     2,     2,
+       2
+};
+
+/* YYDEFACT[STATE-NAME] -- Default rule to reduce with in state
+   STATE-NUM when YYTABLE doesn't specify something else to do.  Zero
+   means the default is an error.  */
+static const unsigned char yydefact[] =
+{
+       2,     0,     1,     6,     0,     0,     3,     4,     5,     0,
+       0,     0,    10,     0,     0,     0,     0,     7,    15,    17,
+       8,    16,    18,     9,    19,    20,     0,     0,    14,    12,
+       0,     0,    13,     0,     0,     0,    11
+};
+
+/* YYDEFGOTO[NTERM-NUM]. */
+static const yysigned_char yydefgoto[] =
+{
+      -1,     1,     6,     7,     8,    30,    15
+};
+
+/* YYPACT[STATE-NUM] -- Index in YYTABLE of the portion describing
+   STATE-NUM.  */
+#define YYPACT_NINF -8
+static const yysigned_char yypact[] =
+{
+      -8,     0,    -8,    -8,    -7,    16,    -8,    -8,    -8,    20,
+      -3,     2,    -8,     4,     7,    12,    21,    -8,    -8,    -8,
+      -8,    -8,    -8,    -8,    -8,    -8,    23,     9,    -8,    -8,
+      -6,    18,    -8,    19,    24,    26,    -8
+};
+
+/* YYPGOTO[NTERM-NUM].  */
+static const yysigned_char yypgoto[] =
+{
+      -8,    -8,    -8,    -5,    -8,    -8,    -8
+};
+
+/* YYTABLE[YYPACT[STATE-NUM]].  What to do in state STATE-NUM.  If
+   positive, shift that token.  If negative, reduce the rule which
+   number is the opposite.  If zero, do what YYDEFACT says.
+   If YYTABLE_NINF, syntax error.  */
+#define YYTABLE_NINF -1
+static const unsigned char yytable[] =
+{
+       2,    31,    12,     9,     5,     3,    13,     4,    14,    17,
+       5,    16,    20,    18,    28,    19,    21,    23,    22,     5,
+      10,    24,    29,    25,    11,    32,    33,    26,    27,    34,
+      35,    36
+};
+
+static const unsigned char yycheck[] =
+{
+       0,     7,     5,    10,    10,     5,     9,     7,    11,     5,
+      10,     9,     5,     9,     5,    11,     9,     5,    11,    10,
+       4,     9,    27,    11,     4,    30,     8,     6,     5,    10,
+       6,     5
+};
+
+/* YYSTOS[STATE-NUM] -- The (internal number of the) accessing
+   symbol of state STATE-NUM.  */
+static const unsigned char yystos[] =
+{
+       0,    13,     0,     5,     7,    10,    14,    15,    16,    10,
+       4,     4,     5,     9,    11,    18,     9,     5,     9,    11,
+       5,     9,    11,     5,     9,    11,     6,     5,     5,    15,
+      17,     7,    15,     8,    10,     6,     5
+};
+
+#if ! defined (YYSIZE_T) && defined (__SIZE_TYPE__)
+# define YYSIZE_T __SIZE_TYPE__
+#endif
+#if ! defined (YYSIZE_T) && defined (size_t)
+# define YYSIZE_T size_t
+#endif
+#if ! defined (YYSIZE_T)
+# if defined (__STDC__) || defined (__cplusplus)
+#  include <stddef.h> /* INFRINGES ON USER NAME SPACE */
+#  define YYSIZE_T size_t
+# endif
+#endif
+#if ! defined (YYSIZE_T)
+# define YYSIZE_T unsigned int
+#endif
+
+#define yyerrok		(yyerrstatus = 0)
+#define yyclearin	(yychar = YYEMPTY)
+#define YYEMPTY		(-2)
+#define YYEOF		0
+
+#define YYACCEPT	goto yyacceptlab
+#define YYABORT		goto yyabortlab
+#define YYERROR		goto yyerrorlab
+
+
+/* Like YYERROR except do call yyerror.  This remains here temporarily
+   to ease the transition to the new meaning of YYERROR, for GCC.
+   Once GCC version 2 has supplanted version 1, this can go.  */
+
+#define YYFAIL		goto yyerrlab
+
+#define YYRECOVERING()  (!!yyerrstatus)
+
+#define YYBACKUP(Token, Value)					\
+do								\
+  if (yychar == YYEMPTY && yylen == 1)				\
+    {								\
+      yychar = (Token);						\
+      yylval = (Value);						\
+      yytoken = YYTRANSLATE (yychar);				\
+      YYPOPSTACK;						\
+      goto yybackup;						\
+    }								\
+  else								\
+    { 								\
+      yyerror ("syntax error: cannot back up");\
+      YYERROR;							\
+    }								\
+while (0)
+
+#define YYTERROR	1
+#define YYERRCODE	256
+
+/* YYLLOC_DEFAULT -- Compute the default location (before the actions
+   are run).  */
+
+#ifndef YYLLOC_DEFAULT
+# define YYLLOC_DEFAULT(Current, Rhs, N)		\
+   ((Current).first_line   = (Rhs)[1].first_line,	\
+    (Current).first_column = (Rhs)[1].first_column,	\
+    (Current).last_line    = (Rhs)[N].last_line,	\
+    (Current).last_column  = (Rhs)[N].last_column)
+#endif
+
+/* YYLEX -- calling `yylex' with the right arguments.  */
+
+#ifdef YYLEX_PARAM
+# define YYLEX yylex (YYLEX_PARAM)
+#else
+# define YYLEX yylex ()
+#endif
+
+/* Enable debugging if requested.  */
+#if YYDEBUG
+
+# ifndef YYFPRINTF
+#  include <stdio.h> /* INFRINGES ON USER NAME SPACE */
+#  define YYFPRINTF fprintf
+# endif
+
+# define YYDPRINTF(Args)			\
+do {						\
+  if (yydebug)					\
+    YYFPRINTF Args;				\
+} while (0)
+
+# define YYDSYMPRINT(Args)			\
+do {						\
+  if (yydebug)					\
+    yysymprint Args;				\
+} while (0)
+
+# define YYDSYMPRINTF(Title, Token, Value, Location)		\
+do {								\
+  if (yydebug)							\
+    {								\
+      YYFPRINTF (stderr, "%s ", Title);				\
+      yysymprint (stderr, 					\
+                  Token, Value);	\
+      YYFPRINTF (stderr, "\n");					\
+    }								\
+} while (0)
+
+/*------------------------------------------------------------------.
+| yy_stack_print -- Print the state stack from its BOTTOM up to its |
+| TOP (included).                                                   |
+`------------------------------------------------------------------*/
+
+#if defined (__STDC__) || defined (__cplusplus)
+static void
+yy_stack_print (short *bottom, short *top)
+#else
+static void
+yy_stack_print (bottom, top)
+    short *bottom;
+    short *top;
+#endif
+{
+  YYFPRINTF (stderr, "Stack now");
+  for (/* Nothing. */; bottom <= top; ++bottom)
+    YYFPRINTF (stderr, " %d", *bottom);
+  YYFPRINTF (stderr, "\n");
+}
+
+# define YY_STACK_PRINT(Bottom, Top)				\
+do {								\
+  if (yydebug)							\
+    yy_stack_print ((Bottom), (Top));				\
+} while (0)
+
+
+/*------------------------------------------------.
+| Report that the YYRULE is going to be reduced.  |
+`------------------------------------------------*/
+
+#if defined (__STDC__) || defined (__cplusplus)
+static void
+yy_reduce_print (int yyrule)
+#else
+static void
+yy_reduce_print (yyrule)
+    int yyrule;
+#endif
+{
+  int yyi;
+  unsigned int yylno = yyrline[yyrule];
+  YYFPRINTF (stderr, "Reducing stack by rule %d (line %u), ",
+             yyrule - 1, yylno);
+  /* Print the symbols being reduced, and their result.  */
+  for (yyi = yyprhs[yyrule]; 0 <= yyrhs[yyi]; yyi++)
+    YYFPRINTF (stderr, "%s ", yytname [yyrhs[yyi]]);
+  YYFPRINTF (stderr, "-> %s\n", yytname [yyr1[yyrule]]);
+}
+
+# define YY_REDUCE_PRINT(Rule)		\
+do {					\
+  if (yydebug)				\
+    yy_reduce_print (Rule);		\
+} while (0)
+
+/* Nonzero means print parse trace.  It is left uninitialized so that
+   multiple parsers can coexist.  */
+int yydebug;
+#else /* !YYDEBUG */
+# define YYDPRINTF(Args)
+# define YYDSYMPRINT(Args)
+# define YYDSYMPRINTF(Title, Token, Value, Location)
+# define YY_STACK_PRINT(Bottom, Top)
+# define YY_REDUCE_PRINT(Rule)
+#endif /* !YYDEBUG */
+
+
+/* YYINITDEPTH -- initial size of the parser's stacks.  */
+#ifndef	YYINITDEPTH
+# define YYINITDEPTH 200
+#endif
+
+/* YYMAXDEPTH -- maximum size the stacks can grow to (effective only
+   if the built-in stack extension method is used).
+
+   Do not make this value too large; the results are undefined if
+   SIZE_MAX < YYSTACK_BYTES (YYMAXDEPTH)
+   evaluated with infinite-precision integer arithmetic.  */
+
+#if defined (YYMAXDEPTH) && YYMAXDEPTH == 0
+# undef YYMAXDEPTH
+#endif
+
+#ifndef YYMAXDEPTH
+# define YYMAXDEPTH 10000
+#endif
+
+
+
+#if YYERROR_VERBOSE
+
+# ifndef yystrlen
+#  if defined (__GLIBC__) && defined (_STRING_H)
+#   define yystrlen strlen
+#  else
+/* Return the length of YYSTR.  */
+static YYSIZE_T
+#   if defined (__STDC__) || defined (__cplusplus)
+yystrlen (const char *yystr)
+#   else
+yystrlen (yystr)
+     const char *yystr;
+#   endif
+{
+  register const char *yys = yystr;
+
+  while (*yys++ != '\0')
+    continue;
+
+  return yys - yystr - 1;
+}
+#  endif
+# endif
+
+# ifndef yystpcpy
+#  if defined (__GLIBC__) && defined (_STRING_H) && defined (_GNU_SOURCE)
+#   define yystpcpy stpcpy
+#  else
+/* Copy YYSRC to YYDEST, returning the address of the terminating '\0' in
+   YYDEST.  */
+static char *
+#   if defined (__STDC__) || defined (__cplusplus)
+yystpcpy (char *yydest, const char *yysrc)
+#   else
+yystpcpy (yydest, yysrc)
+     char *yydest;
+     const char *yysrc;
+#   endif
+{
+  register char *yyd = yydest;
+  register const char *yys = yysrc;
+
+  while ((*yyd++ = *yys++) != '\0')
+    continue;
+
+  return yyd - 1;
+}
+#  endif
+# endif
+
+#endif /* !YYERROR_VERBOSE */
+
+
+
+#if YYDEBUG
+/*--------------------------------.
+| Print this symbol on YYOUTPUT.  |
+`--------------------------------*/
+
+#if defined (__STDC__) || defined (__cplusplus)
+static void
+yysymprint (FILE *yyoutput, int yytype, YYSTYPE *yyvaluep)
+#else
+static void
+yysymprint (yyoutput, yytype, yyvaluep)
+    FILE *yyoutput;
+    int yytype;
+    YYSTYPE *yyvaluep;
+#endif
+{
+  /* Pacify ``unused variable'' warnings.  */
+  (void) yyvaluep;
+
+  if (yytype < YYNTOKENS)
+    {
+      YYFPRINTF (yyoutput, "token %s (", yytname[yytype]);
+# ifdef YYPRINT
+      YYPRINT (yyoutput, yytoknum[yytype], *yyvaluep);
+# endif
+    }
+  else
+    YYFPRINTF (yyoutput, "nterm %s (", yytname[yytype]);
+
+  switch (yytype)
+    {
+      default:
+        break;
+    }
+  YYFPRINTF (yyoutput, ")");
+}
+
+#endif /* ! YYDEBUG */
+/*-----------------------------------------------.
+| Release the memory associated to this symbol.  |
+`-----------------------------------------------*/
+
+#if defined (__STDC__) || defined (__cplusplus)
+static void
+yydestruct (int yytype, YYSTYPE *yyvaluep)
+#else
+static void
+yydestruct (yytype, yyvaluep)
+    int yytype;
+    YYSTYPE *yyvaluep;
+#endif
+{
+  /* Pacify ``unused variable'' warnings.  */
+  (void) yyvaluep;
+
+  switch (yytype)
+    {
+
+      default:
+        break;
+    }
+}
+
+
+/* Prevent warnings from -Wmissing-prototypes.  */
+
+#ifdef YYPARSE_PARAM
+# if defined (__STDC__) || defined (__cplusplus)
+int yyparse (void *YYPARSE_PARAM);
+# else
+int yyparse ();
+# endif
+#else /* ! YYPARSE_PARAM */
+#if defined (__STDC__) || defined (__cplusplus)
+int yyparse (void);
+#else
+int yyparse ();
+#endif
+#endif /* ! YYPARSE_PARAM */
+
+
+
+/* The lookahead symbol.  */
+int yychar;
+
+/* The semantic value of the lookahead symbol.  */
+YYSTYPE yylval;
+
+/* Number of syntax errors so far.  */
+int yynerrs;
+
+
+
+/*----------.
+| yyparse.  |
+`----------*/
+
+#ifdef YYPARSE_PARAM
+# if defined (__STDC__) || defined (__cplusplus)
+int yyparse (void *YYPARSE_PARAM)
+# else
+int yyparse (YYPARSE_PARAM)
+  void *YYPARSE_PARAM;
+# endif
+#else /* ! YYPARSE_PARAM */
+#if defined (__STDC__) || defined (__cplusplus)
+int
+yyparse (void)
+#else
+int
+yyparse ()
+
+#endif
+#endif
+{
+  
+  register int yystate;
+  register int yyn;
+  int yyresult;
+  /* Number of tokens to shift before error messages enabled.  */
+  int yyerrstatus;
+  /* Lookahead token as an internal (translated) token number.  */
+  int yytoken = 0;
+
+  /* Three stacks and their tools:
+     `yyss': related to states,
+     `yyvs': related to semantic values,
+     `yyls': related to locations.
+
+     Refer to the stacks thru separate pointers, to allow yyoverflow
+     to reallocate them elsewhere.  */
+
+  /* The state stack.  */
+  short	yyssa[YYINITDEPTH];
+  short *yyss = yyssa;
+  register short *yyssp;
+
+  /* The semantic value stack.  */
+  YYSTYPE yyvsa[YYINITDEPTH];
+  YYSTYPE *yyvs = yyvsa;
+  register YYSTYPE *yyvsp;
+
+
+
+#define YYPOPSTACK   (yyvsp--, yyssp--)
+
+  YYSIZE_T yystacksize = YYINITDEPTH;
+
+  /* The variables used to return semantic value and location from the
+     action routines.  */
+  YYSTYPE yyval;
+
+
+  /* When reducing, the number of symbols on the RHS of the reduced
+     rule.  */
+  int yylen;
+
+  YYDPRINTF ((stderr, "Starting parse\n"));
+
+  yystate = 0;
+  yyerrstatus = 0;
+  yynerrs = 0;
+  yychar = YYEMPTY;		/* Cause a token to be read.  */
+
+  /* Initialize stack pointers.
+     Waste one element of value and location stack
+     so that they stay on the same level as the state stack.
+     The wasted elements are never initialized.  */
+
+  yyssp = yyss;
+  yyvsp = yyvs;
+
+  goto yysetstate;
+
+/*------------------------------------------------------------.
+| yynewstate -- Push a new state, which is found in yystate.  |
+`------------------------------------------------------------*/
+ yynewstate:
+  /* In all cases, when you get here, the value and location stacks
+     have just been pushed. so pushing a state here evens the stacks.
+     */
+  yyssp++;
+
+ yysetstate:
+  *yyssp = yystate;
+
+  if (yyss + yystacksize - 1 <= yyssp)
+    {
+      /* Get the current used size of the three stacks, in elements.  */
+      YYSIZE_T yysize = yyssp - yyss + 1;
+
+#ifdef yyoverflow
+      {
+	/* Give user a chance to reallocate the stack. Use copies of
+	   these so that the &'s don't force the real ones into
+	   memory.  */
+	YYSTYPE *yyvs1 = yyvs;
+	short *yyss1 = yyss;
+
+
+	/* Each stack pointer address is followed by the size of the
+	   data in use in that stack, in bytes.  This used to be a
+	   conditional around just the two extra args, but that might
+	   be undefined if yyoverflow is a macro.  */
+	yyoverflow ("parser stack overflow",
+		    &yyss1, yysize * sizeof (*yyssp),
+		    &yyvs1, yysize * sizeof (*yyvsp),
+
+		    &yystacksize);
+
+	yyss = yyss1;
+	yyvs = yyvs1;
+      }
+#else /* no yyoverflow */
+# ifndef YYSTACK_RELOCATE
+      goto yyoverflowlab;
+# else
+      /* Extend the stack our own way.  */
+      if (YYMAXDEPTH <= yystacksize)
+	goto yyoverflowlab;
+      yystacksize *= 2;
+      if (YYMAXDEPTH < yystacksize)
+	yystacksize = YYMAXDEPTH;
+
+      {
+	short *yyss1 = yyss;
+	union yyalloc *yyptr =
+	  (union yyalloc *) YYSTACK_ALLOC (YYSTACK_BYTES (yystacksize));
+	if (! yyptr)
+	  goto yyoverflowlab;
+	YYSTACK_RELOCATE (yyss);
+	YYSTACK_RELOCATE (yyvs);
+
+#  undef YYSTACK_RELOCATE
+	if (yyss1 != yyssa)
+	  YYSTACK_FREE (yyss1);
+      }
+# endif
+#endif /* no yyoverflow */
+
+      yyssp = yyss + yysize - 1;
+      yyvsp = yyvs + yysize - 1;
+
+
+      YYDPRINTF ((stderr, "Stack size increased to %lu\n",
+		  (unsigned long int) yystacksize));
+
+      if (yyss + yystacksize - 1 <= yyssp)
+	YYABORT;
+    }
+
+  YYDPRINTF ((stderr, "Entering state %d\n", yystate));
+
+  goto yybackup;
+
+/*-----------.
+| yybackup.  |
+`-----------*/
+yybackup:
+
+/* Do appropriate processing given the current state.  */
+/* Read a lookahead token if we need one and don't already have one.  */
+/* yyresume: */
+
+  /* First try to decide what to do without reference to lookahead token.  */
+
+  yyn = yypact[yystate];
+  if (yyn == YYPACT_NINF)
+    goto yydefault;
+
+  /* Not known => get a lookahead token if don't already have one.  */
+
+  /* YYCHAR is either YYEMPTY or YYEOF or a valid lookahead symbol.  */
+  if (yychar == YYEMPTY)
+    {
+      YYDPRINTF ((stderr, "Reading a token: "));
+      yychar = YYLEX;
+    }
+
+  if (yychar <= YYEOF)
+    {
+      yychar = yytoken = YYEOF;
+      YYDPRINTF ((stderr, "Now at end of input.\n"));
+    }
+  else
+    {
+      yytoken = YYTRANSLATE (yychar);
+      YYDSYMPRINTF ("Next token is", yytoken, &yylval, &yylloc);
+    }
+
+  /* If the proper action on seeing token YYTOKEN is to reduce or to
+     detect an error, take that action.  */
+  yyn += yytoken;
+  if (yyn < 0 || YYLAST < yyn || yycheck[yyn] != yytoken)
+    goto yydefault;
+  yyn = yytable[yyn];
+  if (yyn <= 0)
+    {
+      if (yyn == 0 || yyn == YYTABLE_NINF)
+	goto yyerrlab;
+      yyn = -yyn;
+      goto yyreduce;
+    }
+
+  if (yyn == YYFINAL)
+    YYACCEPT;
+
+  /* Shift the lookahead token.  */
+  YYDPRINTF ((stderr, "Shifting token %s, ", yytname[yytoken]));
+
+  /* Discard the token being shifted unless it is eof.  */
+  if (yychar != YYEOF)
+    yychar = YYEMPTY;
+
+  *++yyvsp = yylval;
+
+
+  /* Count tokens shifted since error; after three, turn off error
+     status.  */
+  if (yyerrstatus)
+    yyerrstatus--;
+
+  yystate = yyn;
+  goto yynewstate;
+
+
+/*-----------------------------------------------------------.
+| yydefault -- do the default action for the current state.  |
+`-----------------------------------------------------------*/
+yydefault:
+  yyn = yydefact[yystate];
+  if (yyn == 0)
+    goto yyerrlab;
+  goto yyreduce;
+
+
+/*-----------------------------.
+| yyreduce -- Do a reduction.  |
+`-----------------------------*/
+yyreduce:
+  /* yyn is the number of a rule to reduce with.  */
+  yylen = yyr2[yyn];
+
+  /* If YYLEN is nonzero, implement the default value of the action:
+     `$$ = $1'.
+
+     Otherwise, the following line sets YYVAL to garbage.
+     This behavior is undocumented and Bison
+     users should not rely upon it.  Assigning to YYVAL
+     unconditionally makes the parser a bit smaller, and it avoids a
+     GCC warning that YYVAL may be used uninitialized.  */
+  yyval = yyvsp[1-yylen];
+
+
+  YY_REDUCE_PRINT (yyn);
+  switch (yyn)
+    {
+        case 3:
+#line 66 "conf_parser.yxx"
+    { /* Whole config file */ ;}
+    break;
+
+  case 4:
+#line 69 "conf_parser.yxx"
+    {   
+  // name: value
+               ((HtConfiguration *)aConf)->AddParsed(yyvsp[0].ConfLine->name,yyvsp[0].ConfLine->value);
+	       #ifdef DEBUG
+	       if (sn_debug>=2) {
+		 cout<<"Added to conf: "<<yyvsp[0].ConfLine->name<<":"<<yyvsp[0].ConfLine->value<<endl;
+	       }
+	       #endif
+	       delete [] yyvsp[0].ConfLine->name; 
+	       delete [] yyvsp[0].ConfLine->value;
+	       delete yyvsp[0].ConfLine;
+               ;}
+    break;
+
+  case 5:
+#line 81 "conf_parser.yxx"
+    {
+          // <server www.gc.lviv.ua>
+          //    server_max_docs: 456
+          //    ... : ...
+          // </server>
+	;}
+    break;
+
+  case 6:
+#line 87 "conf_parser.yxx"
+    { /* Ignore empty lines */  ;}
+    break;
+
+  case 7:
+#line 90 "conf_parser.yxx"
+    { 
+  // locale: uk_UA.KOI8-U
+                                        //
+					// We can't do inserting into config
+					// here because we don't know if it's
+                                        // in complex expression or not.
+					yyval.ConfLine=new ConfigDefaults;
+					yyval.ConfLine->name = yyvsp[-3].str; yyval.ConfLine->value=yyvsp[-1].str;
+					;}
+    break;
+
+  case 8:
+#line 100 "conf_parser.yxx"
+    { 
+	  // max_head_length: 300000
+	  //
+	                                yyval.ConfLine=new ConfigDefaults;
+					yyval.ConfLine->name = yyvsp[-3].str; yyval.ConfLine->value=yyvsp[-1].str;
+					;}
+    break;
+
+  case 9:
+#line 106 "conf_parser.yxx"
+    {
+	  // bad_extensions: .XLS .xls .pdf .PDF .doc .DOC 
+	  //
+	  yyval.ConfLine=new ConfigDefaults;
+	  yyval.ConfLine->name = yyvsp[-3].str; yyval.ConfLine->value=yyvsp[-1].str;
+	;}
+    break;
+
+  case 10:
+#line 112 "conf_parser.yxx"
+    {
+	  // excude_urls:
+	  //
+	                            yyval.ConfLine=new ConfigDefaults;
+				    yyval.ConfLine->name = yyvsp[-2].str;
+				    yyval.ConfLine->value=new char[1];
+				    *yyval.ConfLine->value='\0';
+					;}
+    break;
+
+  case 11:
+#line 122 "conf_parser.yxx"
+    {
+		      // check if "<param> ... </param>" are equal
+		      if (strcmp(yyvsp[-10].str,yyvsp[-2].str)!=0) {
+			// todo: setup error string, return with error.
+			// Inform about line number
+			cerr<<"Brackets mismatch: Opened: "<<yyvsp[-10].str<<" Closed: "<<yyvsp[-2].str<<endl;
+			// exit(1);
+		      }
+		      // Oll right. Append set of parameters to object($2)
+		      ((HtConfiguration *)aConf)->Add(yyvsp[-10].str,yyvsp[-8].str,yyvsp[-5].ConfLines);
+		      #ifdef DEBUG
+		      if (sn_debug >= 2) {
+			cout<<"Added to conf: "<<yyvsp[-10].str<<":"<<yyvsp[-8].str<<":"<<yyvsp[-5].ConfLines<<endl;
+		      }
+		      #endif
+		      delete yyvsp[-10].str; 
+		      delete yyvsp[-8].str;
+		      delete [] yyvsp[-2].str;
+		    ;}
+    break;
+
+  case 12:
+#line 143 "conf_parser.yxx"
+    {
+  //aaa: nnn
+  //bbb: ccc
+  // ...
+  //
+  // First entry. We need to create conf to store it.
+  HtConfiguration *expressionList=new HtConfiguration();
+  expressionList->AddParsed(yyvsp[0].ConfLine->name,yyvsp[0].ConfLine->value);
+  yyval.ConfLines=expressionList;
+  #ifdef DEBUG
+  if (sn_debug>=2) {
+    cout<<"Create list of properties: "<<expressionList<<endl;
+  }
+  #endif
+  delete yyvsp[0].ConfLine->name; 
+  delete yyvsp[0].ConfLine->value;
+  delete yyvsp[0].ConfLine;
+;}
+    break;
+
+  case 13:
+#line 161 "conf_parser.yxx"
+    {
+				yyvsp[-1].ConfLines->AddParsed(yyvsp[0].ConfLine->name,yyvsp[0].ConfLine->value);
+				#ifdef DEBUG
+				if (sn_debug>=2) {
+				  cout<<yyvsp[0].ConfLine->name<<":"<<yyvsp[0].ConfLine->value<<" added to "<<yyvsp[-1].ConfLines<<endl;
+				}
+				#endif
+				delete yyvsp[0].ConfLine->name; 
+				delete yyvsp[0].ConfLine->value;
+				delete yyvsp[0].ConfLine;
+				//$$=$1; //I think $$==$1
+			;}
+    break;
+
+  case 14:
+#line 173 "conf_parser.yxx"
+    { /* Ignore empty lines */  ;}
+    break;
+
+  case 15:
+#line 176 "conf_parser.yxx"
+    { 
+	// Paste 2 components. Reallocate memory for 2 components.
+	if ((yyval.str=new char[strlen(yyvsp[-1].str)+strlen(yyvsp[0].str)+1+1])==NULL) {
+		fprintf(stderr,"Can't allocate memory\n");
+		exit(1);
+	}
+	strcpy(yyval.str,yyvsp[-1].str);
+	strcat(yyval.str," ");		// Delimiter in list
+	strcat(yyval.str,yyvsp[0].str);
+	delete [] yyvsp[-1].str; 
+	delete [] yyvsp[0].str;
+	;}
+    break;
+
+  case 16:
+#line 189 "conf_parser.yxx"
+    { 
+	// Paste 2 components. Reallocate memory for 2 components.
+	if ((yyval.str=new char[strlen(yyvsp[-1].str)+strlen(yyvsp[0].str)+1+1])==NULL) {
+		fprintf(stderr,"Can't allocate memory\n");
+		exit(1);
+	}
+	strcpy(yyval.str,yyvsp[-1].str);
+	strcat(yyval.str," ");		// Delimiter in list
+	strcat(yyval.str,yyvsp[0].str);
+	delete [] yyvsp[-1].str; 
+	delete [] yyvsp[0].str;
+	;}
+    break;
+
+  case 17:
+#line 202 "conf_parser.yxx"
+    { 
+	// Paste 2 components. Reallocate memory for 2 components.
+	if ((yyval.str=new char[strlen(yyvsp[-1].str)+strlen(yyvsp[0].str)+1+1])==NULL) {
+		fprintf(stderr,"Can't allocate memory\n");
+		exit(1);
+	}
+	strcpy(yyval.str,yyvsp[-1].str);
+	strcat(yyval.str," ");		// Delimiter in list
+	strcat(yyval.str,yyvsp[0].str);
+	delete [] yyvsp[-1].str; 
+	delete [] yyvsp[0].str;
+	;}
+    break;
+
+  case 18:
+#line 215 "conf_parser.yxx"
+    { 
+	// Paste 2 components. Reallocate memory for 2 components.
+	if ((yyval.str=new char[strlen(yyvsp[-1].str)+strlen(yyvsp[0].str)+1+1])==NULL) {
+		fprintf(stderr,"Can't allocate memory\n");
+		exit(1);
+	}
+	strcpy(yyval.str,yyvsp[-1].str);
+	strcat(yyval.str," ");		// Delimiter in list
+	strcat(yyval.str,yyvsp[0].str);
+	delete [] yyvsp[-1].str; 
+	delete [] yyvsp[0].str;
+	;}
+    break;
+
+  case 19:
+#line 228 "conf_parser.yxx"
+    { 
+		char *old=yyval.str;
+		if ((yyval.str=new char [strlen(yyval.str)+strlen(yyvsp[0].str)+1+1])==NULL) {
+		  fprintf(stderr,"Can't reallocate memory\n");
+		  exit(1);
+		}
+		strcpy(yyval.str,old);
+		delete [] old;
+		strcat(yyval.str," ");
+		strcat(yyval.str,yyvsp[0].str);
+		delete [] yyvsp[0].str;
+	;}
+    break;
+
+  case 20:
+#line 240 "conf_parser.yxx"
+    {
+		char *old=yyval.str;
+		if ((yyval.str=new char [strlen(yyval.str)+strlen(yyvsp[0].str)+1+1])==NULL) {
+		  fprintf(stderr,"Can't reallocate memory\n");
+		  exit(1);
+		}
+		strcpy(yyval.str,old);
+		delete [] old;
+		strcat(yyval.str," ");
+		strcat(yyval.str,yyvsp[0].str);
+		delete [] yyvsp[0].str;
+	;}
+    break;
+
+
+    }
+
+/* Line 1000 of yacc.c.  */
+#line 1309 "conf_parser.cxx"
+
+  yyvsp -= yylen;
+  yyssp -= yylen;
+
+
+  YY_STACK_PRINT (yyss, yyssp);
+
+  *++yyvsp = yyval;
+
+
+  /* Now `shift' the result of the reduction.  Determine what state
+     that goes to, based on the state we popped back to and the rule
+     number reduced by.  */
+
+  yyn = yyr1[yyn];
+
+  yystate = yypgoto[yyn - YYNTOKENS] + *yyssp;
+  if (0 <= yystate && yystate <= YYLAST && yycheck[yystate] == *yyssp)
+    yystate = yytable[yystate];
+  else
+    yystate = yydefgoto[yyn - YYNTOKENS];
+
+  goto yynewstate;
+
+
+/*------------------------------------.
+| yyerrlab -- here on detecting error |
+`------------------------------------*/
+yyerrlab:
+  /* If not already recovering from an error, report this error.  */
+  if (!yyerrstatus)
+    {
+      ++yynerrs;
+#if YYERROR_VERBOSE
+      yyn = yypact[yystate];
+
+      if (YYPACT_NINF < yyn && yyn < YYLAST)
+	{
+	  YYSIZE_T yysize = 0;
+	  int yytype = YYTRANSLATE (yychar);
+	  const char* yyprefix;
+	  char *yymsg;
+	  int yyx;
+
+	  /* Start YYX at -YYN if negative to avoid negative indexes in
+	     YYCHECK.  */
+	  int yyxbegin = yyn < 0 ? -yyn : 0;
+
+	  /* Stay within bounds of both yycheck and yytname.  */
+	  int yychecklim = YYLAST - yyn;
+	  int yyxend = yychecklim < YYNTOKENS ? yychecklim : YYNTOKENS;
+	  int yycount = 0;
+
+	  yyprefix = ", expecting ";
+	  for (yyx = yyxbegin; yyx < yyxend; ++yyx)
+	    if (yycheck[yyx + yyn] == yyx && yyx != YYTERROR)
+	      {
+		yysize += yystrlen (yyprefix) + yystrlen (yytname [yyx]);
+		yycount += 1;
+		if (yycount == 5)
+		  {
+		    yysize = 0;
+		    break;
+		  }
+	      }
+	  yysize += (sizeof ("syntax error, unexpected ")
+		     + yystrlen (yytname[yytype]));
+	  yymsg = (char *) YYSTACK_ALLOC (yysize);
+	  if (yymsg != 0)
+	    {
+	      char *yyp = yystpcpy (yymsg, "syntax error, unexpected ");
+	      yyp = yystpcpy (yyp, yytname[yytype]);
+
+	      if (yycount < 5)
+		{
+		  yyprefix = ", expecting ";
+		  for (yyx = yyxbegin; yyx < yyxend; ++yyx)
+		    if (yycheck[yyx + yyn] == yyx && yyx != YYTERROR)
+		      {
+			yyp = yystpcpy (yyp, yyprefix);
+			yyp = yystpcpy (yyp, yytname[yyx]);
+			yyprefix = " or ";
+		      }
+		}
+	      yyerror (yymsg);
+	      YYSTACK_FREE (yymsg);
+	    }
+	  else
+	    yyerror ("syntax error; also virtual memory exhausted");
+	}
+      else
+#endif /* YYERROR_VERBOSE */
+	yyerror ("syntax error");
+    }
+
+
+
+  if (yyerrstatus == 3)
+    {
+      /* If just tried and failed to reuse lookahead token after an
+	 error, discard it.  */
+
+      if (yychar <= YYEOF)
+        {
+          /* If at end of input, pop the error token,
+	     then the rest of the stack, then return failure.  */
+	  if (yychar == YYEOF)
+	     for (;;)
+	       {
+		 YYPOPSTACK;
+		 if (yyssp == yyss)
+		   YYABORT;
+		 YYDSYMPRINTF ("Error: popping", yystos[*yyssp], yyvsp, yylsp);
+		 yydestruct (yystos[*yyssp], yyvsp);
+	       }
+        }
+      else
+	{
+	  YYDSYMPRINTF ("Error: discarding", yytoken, &yylval, &yylloc);
+	  yydestruct (yytoken, &yylval);
+	  yychar = YYEMPTY;
+
+	}
+    }
+
+  /* Else will try to reuse lookahead token after shifting the error
+     token.  */
+  goto yyerrlab1;
+
+
+/*---------------------------------------------------.
+| yyerrorlab -- error raised explicitly by YYERROR.  |
+`---------------------------------------------------*/
+yyerrorlab:
+
+#ifdef __GNUC__
+  /* Pacify GCC when the user code never invokes YYERROR and the label
+     yyerrorlab therefore never appears in user code.  */
+  if (0)
+     goto yyerrorlab;
+#endif
+
+  yyvsp -= yylen;
+  yyssp -= yylen;
+  yystate = *yyssp;
+  goto yyerrlab1;
+
+
+/*-------------------------------------------------------------.
+| yyerrlab1 -- common code for both syntax error and YYERROR.  |
+`-------------------------------------------------------------*/
+yyerrlab1:
+  yyerrstatus = 3;	/* Each real token shifted decrements this.  */
+
+  for (;;)
+    {
+      yyn = yypact[yystate];
+      if (yyn != YYPACT_NINF)
+	{
+	  yyn += YYTERROR;
+	  if (0 <= yyn && yyn <= YYLAST && yycheck[yyn] == YYTERROR)
+	    {
+	      yyn = yytable[yyn];
+	      if (0 < yyn)
+		break;
+	    }
+	}
+
+      /* Pop the current state because it cannot handle the error token.  */
+      if (yyssp == yyss)
+	YYABORT;
+
+      YYDSYMPRINTF ("Error: popping", yystos[*yyssp], yyvsp, yylsp);
+      yydestruct (yystos[yystate], yyvsp);
+      YYPOPSTACK;
+      yystate = *yyssp;
+      YY_STACK_PRINT (yyss, yyssp);
+    }
+
+  if (yyn == YYFINAL)
+    YYACCEPT;
+
+  YYDPRINTF ((stderr, "Shifting error token, "));
+
+  *++yyvsp = yylval;
+
+
+  yystate = yyn;
+  goto yynewstate;
+
+
+/*-------------------------------------.
+| yyacceptlab -- YYACCEPT comes here.  |
+`-------------------------------------*/
+yyacceptlab:
+  yyresult = 0;
+  goto yyreturn;
+
+/*-----------------------------------.
+| yyabortlab -- YYABORT comes here.  |
+`-----------------------------------*/
+yyabortlab:
+  yyresult = 1;
+  goto yyreturn;
+
+#ifndef yyoverflow
+/*----------------------------------------------.
+| yyoverflowlab -- parser overflow comes here.  |
+`----------------------------------------------*/
+yyoverflowlab:
+  yyerror ("parser stack overflow");
+  yyresult = 2;
+  /* Fall through.  */
+#endif
+
+yyreturn:
+#ifndef yyoverflow
+  if (yyss != yyssa)
+    YYSTACK_FREE (yyss);
+#endif
+  return yyresult;
+}
+
+
+#line 253 "conf_parser.yxx"
+
+int
+yyerror (char *s)  /* Called by yyparse on error */
+{
+   extern int yylineno;
+   extern int include_stack_ptr;
+   extern String *name_stack[];
+   HtConfiguration* config= HtConfiguration::config();
+   String str;
+   if (include_stack_ptr > 0)
+	str = *name_stack[include_stack_ptr-1];
+   else	// still at top level config
+	str = config->getFileName();
+   //fprintf (stderr, "%s\nIn line %d\n",s,yylineno);
+   fprintf(stderr,"Error in file %s line %d: %s\n",str.get(),yylineno,s);
+   // exit(1);
+   return -1;
+}
+
+
diff --git a/debian/htdig/htdig-3.2.0b6/htcommon/conf_parser.h b/debian/htdig/htdig-3.2.0b6/htcommon/conf_parser.h
new file mode 100644
index 00000000..7b0c521d
--- /dev/null
+++ b/debian/htdig/htdig-3.2.0b6/htcommon/conf_parser.h
@@ -0,0 +1,73 @@
+/* A Bison parser, made by GNU Bison 1.875a.  */
+
+/* Skeleton parser for Yacc-like parsing with Bison,
+   Copyright (C) 1984, 1989, 1990, 2000, 2001, 2002, 2003 Free Software Foundation, Inc.
+
+   This program is free software; you can redistribute it and/or modify
+   it under the terms of the GNU General Public License as published by
+   the Free Software Foundation; either version 2, or (at your option)
+   any later version.
+
+   This program is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+   GNU General Public License for more details.
+
+   You should have received a copy of the GNU General Public License
+   along with this program; if not, write to the Free Software
+   Foundation, Inc., 59 Temple Place - Suite 330,
+   Boston, MA 02111-1307, USA.  */
+
+/* As a special exception, when this file is copied by Bison into a
+   Bison output file, you may use that output file without restriction.
+   This special exception was added by the Free Software Foundation
+   in version 1.24 of Bison.  */
+
+/* Tokens.  */
+#ifndef YYTOKENTYPE
+# define YYTOKENTYPE
+   /* Put the tokens into the symbol table, so that GDB and other debuggers
+      know about them.  */
+   enum yytokentype {
+     NUM = 258,
+     T_DELIMITER = 259,
+     T_NEWLINE = 260,
+     T_RIGHT_BR = 261,
+     T_LEFT_BR = 262,
+     T_SLASH = 263,
+     T_STRING = 264,
+     T_KEYWORD = 265,
+     T_NUMBER = 266
+   };
+#endif
+#define NUM 258
+#define T_DELIMITER 259
+#define T_NEWLINE 260
+#define T_RIGHT_BR 261
+#define T_LEFT_BR 262
+#define T_SLASH 263
+#define T_STRING 264
+#define T_KEYWORD 265
+#define T_NUMBER 266
+
+
+
+
+#if ! defined (YYSTYPE) && ! defined (YYSTYPE_IS_DECLARED)
+
+typedef union YYSTYPE {
+	char *str;
+	ConfigDefaults	*ConfLine;
+	HtConfiguration	*ConfLines;
+} YYSTYPE;
+/* Line 1240 of yacc.c.  */
+
+# define yystype YYSTYPE /* obsolescent; will be withdrawn */
+# define YYSTYPE_IS_DECLARED 1
+# define YYSTYPE_IS_TRIVIAL 1
+#endif
+
+extern YYSTYPE yylval;
+
+
+
diff --git a/debian/htdig/htdig-3.2.0b6/htcommon/conf_parser.yxx b/debian/htdig/htdig-3.2.0b6/htcommon/conf_parser.yxx
new file mode 100644
index 00000000..85d0213d
--- /dev/null
+++ b/debian/htdig/htdig-3.2.0b6/htcommon/conf_parser.yxx
@@ -0,0 +1,270 @@
+%{
+//
+// conf_parser.yxx
+//
+//             This syntax analyzer is used to parse ht://Dig config
+//             files.
+//
+// Part of the ht://Dig package   <http://www.htdig.org/>
+// Copyright (c) 1999-2004 The ht://Dig Group
+// For copyright details, see the file COPYING in your distribution
+// or the GNU Library General Public License (LGPL) version 2 or later
+// <http://www.gnu.org/copyleft/lgpl.html>
+//
+// $Id: conf_parser.yxx,v 1.8 2004/06/10 14:48:39 angusgb Exp $
+//
+
+#ifdef HAVE_CONFIG_H
+#include "htconfig.h"
+#endif /* HAVE_CONFIG_H */
+
+/* Bison version > 1.25 needed */
+/* TODO: 
+1. Better error handling
+2. ?
+*/
+#include <stdio.h> /* for debug */
+#include <stdlib.h>
+
+#ifdef HAVE_STD
+#include <iostream>
+#ifdef HAVE_NAMESPACES
+using namespace std;
+#endif
+#else
+#include <iostream.h>
+#endif /* HAVE_STD */
+
+#include "HtConfiguration.h"
+#include "htString.h"
+/*#define YYDEBUG 1*/
+#define YYPARSE_PARAM aConf
+int yyerror(char *s);
+int yylex(void);  
+#undef DEBUG
+#ifdef DEBUG
+int sn_debug=3;
+#endif
+%}
+
+%union {
+	char *str;
+	ConfigDefaults	*ConfLine;
+	HtConfiguration	*ConfLines;
+}
+
+%token NUM T_DELIMITER T_NEWLINE T_RIGHT_BR T_LEFT_BR T_SLASH
+%token <str> T_STRING T_KEYWORD T_NUMBER
+%type <str> list 
+%type <ConfLine> simple_expression
+%type <ConfLines> simple_expression_list
+
+/* Grammar follows */
+%%
+
+input:
+         | input block { /* Whole config file */ }
+;
+
+block:        simple_expression		{   
+  // name: value
+               ((HtConfiguration *)aConf)->AddParsed($1->name,$1->value);
+	       #ifdef DEBUG
+	       if (sn_debug>=2) {
+		 cout<<"Added to conf: "<<$1->name<<":"<<$1->value<<endl;
+	       }
+	       #endif
+	       delete [] $1->name; 
+	       delete [] $1->value;
+	       delete $1;
+               }
+        | complex_expression {
+          // <server www.gc.lviv.ua>
+          //    server_max_docs: 456
+          //    ... : ...
+          // </server>
+	}
+        | T_NEWLINE	{ /* Ignore empty lines */  }
+;
+
+simple_expression:      T_KEYWORD T_DELIMITER T_STRING T_NEWLINE	{ 
+  // locale: uk_UA.KOI8-U
+                                        //
+					// We can't do inserting into config
+					// here because we don't know if it's
+                                        // in complex expression or not.
+					$$=new ConfigDefaults;
+					$$->name = $1; $$->value=$3;
+					}
+
+	| T_KEYWORD T_DELIMITER T_NUMBER T_NEWLINE	{ 
+	  // max_head_length: 300000
+	  //
+	                                $$=new ConfigDefaults;
+					$$->name = $1; $$->value=$3;
+					}
+	| T_KEYWORD T_DELIMITER list T_NEWLINE		{
+	  // bad_extensions: .XLS .xls .pdf .PDF .doc .DOC 
+	  //
+	  $$=new ConfigDefaults;
+	  $$->name = $1; $$->value=$3;
+	}
+	| T_KEYWORD T_DELIMITER T_NEWLINE	{
+	  // excude_urls:
+	  //
+	                            $$=new ConfigDefaults;
+				    $$->name = $1;
+				    $$->value=new char[1];
+				    *$$->value='\0';
+					}
+;
+
+complex_expression:	T_LEFT_BR T_KEYWORD T_DELIMITER T_STRING T_RIGHT_BR T_NEWLINE simple_expression_list T_LEFT_BR T_SLASH T_KEYWORD T_RIGHT_BR T_NEWLINE {
+		      // check if "<param> ... </param>" are equal
+		      if (strcmp($2,$10)!=0) {
+			// todo: setup error string, return with error.
+			// Inform about line number
+			cerr<<"Brackets mismatch: Opened: "<<$2<<" Closed: "<<$10<<endl;
+			// exit(1);
+		      }
+		      // Oll right. Append set of parameters to object($2)
+		      ((HtConfiguration *)aConf)->Add($2,$4,$7);
+		      #ifdef DEBUG
+		      if (sn_debug >= 2) {
+			cout<<"Added to conf: "<<$2<<":"<<$4<<":"<<$7<<endl;
+		      }
+		      #endif
+		      delete $2; 
+		      delete $4;
+		      delete [] $10;
+		    } 
+                 ;
+
+simple_expression_list:   simple_expression	{
+  //aaa: nnn
+  //bbb: ccc
+  // ...
+  //
+  // First entry. We need to create conf to store it.
+  HtConfiguration *expressionList=new HtConfiguration();
+  expressionList->AddParsed($1->name,$1->value);
+  $$=expressionList;
+  #ifdef DEBUG
+  if (sn_debug>=2) {
+    cout<<"Create list of properties: "<<expressionList<<endl;
+  }
+  #endif
+  delete $1->name; 
+  delete $1->value;
+  delete $1;
+}
+                        | simple_expression_list simple_expression {
+				$1->AddParsed($2->name,$2->value);
+				#ifdef DEBUG
+				if (sn_debug>=2) {
+				  cout<<$2->name<<":"<<$2->value<<" added to "<<$1<<endl;
+				}
+				#endif
+				delete $2->name; 
+				delete $2->value;
+				delete $2;
+				//$$=$1; //I think $$==$1
+			}
+			| T_NEWLINE	{ /* Ignore empty lines */  }
+                      ;
+
+list:	  T_STRING T_STRING			{ 
+	// Paste 2 components. Reallocate memory for 2 components.
+	if (($$=new char[strlen($1)+strlen($2)+1+1])==NULL) {
+		fprintf(stderr,"Can't allocate memory\n");
+		exit(1);
+	}
+	strcpy($$,$1);
+	strcat($$," ");		// Delimiter in list
+	strcat($$,$2);
+	delete [] $1; 
+	delete [] $2;
+	}
+
+	|  T_NUMBER T_STRING			{ 
+	// Paste 2 components. Reallocate memory for 2 components.
+	if (($$=new char[strlen($1)+strlen($2)+1+1])==NULL) {
+		fprintf(stderr,"Can't allocate memory\n");
+		exit(1);
+	}
+	strcpy($$,$1);
+	strcat($$," ");		// Delimiter in list
+	strcat($$,$2);
+	delete [] $1; 
+	delete [] $2;
+	}
+
+	 | T_STRING T_NUMBER			{ 
+	// Paste 2 components. Reallocate memory for 2 components.
+	if (($$=new char[strlen($1)+strlen($2)+1+1])==NULL) {
+		fprintf(stderr,"Can't allocate memory\n");
+		exit(1);
+	}
+	strcpy($$,$1);
+	strcat($$," ");		// Delimiter in list
+	strcat($$,$2);
+	delete [] $1; 
+	delete [] $2;
+	}
+
+	 | T_NUMBER T_NUMBER			{ 
+	// Paste 2 components. Reallocate memory for 2 components.
+	if (($$=new char[strlen($1)+strlen($2)+1+1])==NULL) {
+		fprintf(stderr,"Can't allocate memory\n");
+		exit(1);
+	}
+	strcpy($$,$1);
+	strcat($$," ");		// Delimiter in list
+	strcat($$,$2);
+	delete [] $1; 
+	delete [] $2;
+	}
+
+	| list T_STRING			{ 
+		char *old=$$;
+		if (($$=new char [strlen($$)+strlen($2)+1+1])==NULL) {
+		  fprintf(stderr,"Can't reallocate memory\n");
+		  exit(1);
+		}
+		strcpy($$,old);
+		delete [] old;
+		strcat($$," ");
+		strcat($$,$2);
+		delete [] $2;
+	}
+	| list T_NUMBER		{
+		char *old=$$;
+		if (($$=new char [strlen($$)+strlen($2)+1+1])==NULL) {
+		  fprintf(stderr,"Can't reallocate memory\n");
+		  exit(1);
+		}
+		strcpy($$,old);
+		delete [] old;
+		strcat($$," ");
+		strcat($$,$2);
+		delete [] $2;
+	}
+;
+%%
+int
+yyerror (char *s)  /* Called by yyparse on error */
+{
+   extern int yylineno;
+   extern int include_stack_ptr;
+   extern String *name_stack[];
+   HtConfiguration* config= HtConfiguration::config();
+   String str;
+   if (include_stack_ptr > 0)
+	str = *name_stack[include_stack_ptr-1];
+   else	// still at top level config
+	str = config->getFileName();
+   //fprintf (stderr, "%s\nIn line %d\n",s,yylineno);
+   fprintf(stderr,"Error in file %s line %d: %s\n",str.get(),yylineno,s);
+   // exit(1);
+   return -1;
+}
diff --git a/debian/htdig/htdig-3.2.0b6/htcommon/defaults.cc b/debian/htdig/htdig-3.2.0b6/htcommon/defaults.cc
new file mode 100644
index 00000000..0148165c
--- /dev/null
+++ b/debian/htdig/htdig-3.2.0b6/htcommon/defaults.cc
@@ -0,0 +1,2832 @@
+//
+// defaults.cc
+//
+// defaults: default values for the ht programs through the
+//           HtConfiguration class
+//
+// Part of the ht://Dig package   <http://www.htdig.org/>
+// Copyright (c) 1995-2004 The ht://Dig Group
+// For copyright details, see the file COPYING in your distribution
+// or the GNU Library General Public License (LGPL) version 2 or later
+// <http://www.gnu.org/copyleft/lgpl.html>
+//
+// $Id: defaults.cc,v 1.112 2004/06/12 13:39:12 lha Exp $
+//
+
+#ifdef HAVE_CONFIG_H
+#include "htconfig.h"
+#endif /* HAVE_CONFIG_H */
+
+#include "HtConfiguration.h"
+
+// Fields and their values:
+//	Attribute name
+//	Default value ("" becomes "no default" in .html docs)
+//	Type (boolean, number, integer, string, string list, quoted string list,
+//				pattern list)
+//	Commands using attribute (all, htdig, htsearch, htfuzzy,
+//				htdump, htload, htnotify, htpurge)
+//	Block (Global, Server, URL)
+//	Versions for which attribute is present
+//	Class	(Extra Output, External:Parsers, External:Protocols,
+//		File Layout,
+//		Indexing:Connection, Indexing:Out, Indexing:What,Indexing:Where,
+//		Presentation:Files, Presentation:How, Presentation:Text,
+//		Searching:Method, Searching:Ranking, Searching:UI,
+//		URLs)
+//	Example
+//	Description
+
+ConfigDefaults	defaults[] =
+{
+
+{ "accents_db", "${database_base}.accents.db",  \
+	"string", "htfuzzy htsearch", "", "all", "File Layout", "accents_db: ${database_base}.uml.db", " \
+	The database file used for the fuzzy \"accents\" search \
+	algorithm. This database is created by \
+	<a href=\"htfuzzy.html\">htfuzzy</a> and used by \
+	<a href=\"htsearch.html\" target=\"_top\">htsearch</a>. \
+" }, \
+{ "accept_language", "",  \
+	"string list", "htdig", "Server", "3.2.0b4", "Indexing:Out", "accept_language: en-us en it", " \
+	This attribute allows you to restrict the set of natural languages \
+	that are preferred as a response to an HTTP request performed by the \
+	digger. This can be done by putting one or more language tags \
+	(as defined by RFC 1766) in the preferred order, separated by spaces. \
+	By doing this, when the server performs a content negotiation based \
+	on the 'accept-language' given by the HTTP user agent, a different \
+	content can be shown depending on the value of this attribute. If \
+	set to an empty list, no language will be sent and the server default \
+	will be returned. \
+" }, \
+{ "add_anchors_to_excerpt", "true",  \
+	"boolean", "htsearch", "", "3.1.0", "Presentation:How", "add_anchors_to_excerpt: no", " \
+	If set to true, the first occurrence of each matched \
+	word in the excerpt will be linked to the closest \
+	anchor in the document. This only has effect if the \
+	<strong>EXCERPT</strong> variable is used in the output \
+	template and the excerpt is actually going to be displayed. \
+" }, \
+{ "allow_double_slash", "false",  \
+	"boolean", "htdig", "", "3.2.0b4", "Indexing:Out", "allow_double_slash: true", " \
+	If set to true, strings of multiple slashes ('/') in URL paths \
+	will be left intact, rather than being collapsed. This is necessary \
+	for some search engine URLs which use slashes to separate fields rather \
+	than to separate directory components.  However, it can lead to multiple database \
+	entries refering to the same file, and it causes '/foo//../' to \
+	be equivalent to '/foo/', rather than to '/'. \
+" }, \
+{ "allow_in_form", "",  \
+	"string list", "htsearch", "", "3.1.0", "Searching:UI", "allow_in_form: search_algorithm search_results_header", " \
+	Allows the specified config file attributes to be specified \
+	in search forms as separate fields. This could be used to \
+	allow form writers to design their own headers and footers \
+	and specify them in the search form. Another example would \
+	be to offer a menu of search_algorithms in the form. \
+	<table> \
+	<tr> \
+	<td nowrap> \
+	<code> \
+	&nbsp;&nbsp;&lt;SELECT NAME=\"search_algorithm\"&gt;<br> \
+	&nbsp;&nbsp;&lt;OPTION VALUE=\"exact:1 prefix:0.6 synonyms:0.5 endings:0.1\" SELECTED&gt;fuzzy<br> \
+	&nbsp;&nbsp;&lt;OPTION VALUE=\"exact:1\"&gt;exact<br> \
+	&nbsp;&nbsp;&lt;/SELECT&gt; \
+	</code></td> \
+	</tr> \
+	</table> \
+	The general idea behind this is to make an input parameter out \
+	of any configuration attribute that's not already automatically \
+	handled by an input parameter. You can even make up your own \
+	configuration attribute names, for purposes of passing data from \
+	the search form to the results output. You're not restricted to \
+	the existing attribute names. The attributes listed in the \
+	allow_in_form list will be settable in the search form using \
+	input parameters of the same name, and will be propagated to \
+	the follow-up search form in the results template using template \
+	variables of the same name in upper-case. \
+	You can also make select lists out of any of these input \
+	parameters, in the follow-up search form, using the \
+	<a href=\"#build_select_lists\">build_select_lists</a> \
+	configuration attribute. \
+	<br>WARNING: Extreme care are should be taken with this option, as \
+	allowing CGI scripts to set file names can open security holes.\
+" }, \
+{ "allow_numbers", "false",  \
+	"boolean", "htdig htsearch", "", "all", "Indexing:What", "allow_numbers: true", " \
+	If set to true, numbers are considered words. This \
+	means that searches can be done on strings of digits as well as \
+	regular words. All the same rules apply to numbers as \
+	to words.  This does not cause numbers containing a decimal point or \
+	commas to be treated as a single entity. \
+	When allow_numbers is false, words are stil \
+	allowed to contain digits, but they must also contain at \
+	least one alphabetic character or \
+	<a href=\"#extra_word_characters\">extra word</a> character. \
+	To disallow digits in words, add the digits to \
+	<a href=\"#valid_punctuation\">valid_punctuation</a>. \
+" }, \
+{ "allow_space_in_url", "false",  \
+	"boolean", "htdig", "", "3.2.0b6", "Indexing:Where", "allow_space_in_url: true", " \
+	If set to true, htdig will handle URLs that contain \
+	embedded spaces. Technically, this is a violation of \
+	RFC 2396, which says spaces should be stripped out \
+	(as htdig does by default).  However, many web browsers \
+	and HTML code generators violate this standard already, \
+	so enabling this attribute allows htdig to handle these \
+	non-compliant URLs.  Even with this attribute set, htdig \
+	still strips out all white space (leading, trailing and \
+	embedded), except that space characters embedded within \
+	the URL will be encoded as %20. \
+" }, \
+{ "allow_virtual_hosts", "true",  \
+	"boolean", "htdig", "", "3.0.8b2", "Indexing:Where", "allow_virtual_hosts: false", " \
+	If set to true, htdig will index virtual web sites as \
+	expected. If false, all URL host names will be \
+	normalized into whatever the DNS server claims the IP \
+	address to map to. If this option is set to false, \
+	there is no way to index either \"soft\" or \"hard\" \
+	virtual web sites. \
+" }, \
+{ "anchor_target", "",  \
+	"string", "htsearch", "", "3.1.6", "Presentation:How", "anchor_target: body", " \
+	When the first matched word in the excerpt is linked \
+	to the closest anchor in the document, this string \
+	can be set to specify a target in the link so the \
+	resulting page is displayed in the desired frame. \
+	This value will only be used if the \
+	<a href=\"#add_anchors_to_excerpt\">add_anchors_to_excerpt</a> \
+	attribute is set to true, the <strong>EXCERPT</strong> \
+	variable is used in the output template and the \
+	excerpt is actually displayed with a link. \
+" }, \
+{ "any_keywords", "false",  \
+	"boolean", "htsearch", "", "3.2.0b2", "Searching:Method", "any_keywords: yes", " \
+	If set to true, the words in the <strong>keywords</strong> \
+	input parameter in the search form will be joined with logical \
+	ORs rather than ANDs, so that any of the words provided will do. \
+	Note that this has nothing to do with limiting the search to \
+	words in META keywords tags. See the <a href=\"hts_form.html\"> \
+	search form</a> documentation for details on this. \
+" }, \
+{ "author_factor", "1",  \
+	"number", "htsearch", "", "3.2.0b4", "Searching:Ranking", "author_factor: 1", " \
+	Weighting applied to words in a &lt;meta name=\"author\" ... &gt; \
+	tag.<br> \
+	See also <a href=\"#heading_factor\">heading_factor</a>. \
+" }, \
+{ "authorization", "",  \
+	"string", "htdig", "URL", "3.1.4", "Indexing:Out", "authorization: myusername:mypassword", " \
+	This tells htdig to send the supplied \
+	<em>username</em><strong>:</strong><em>password</em> with each HTTP request. \
+	The credentials will be encoded using the \"Basic\" authentication \
+	scheme. There <em>must</em> be a colon (:) between the username and \
+	password.<br> \
+	This attribute can also be specified on htdig's command line using \
+	the -u option, and will be blotted out so it won't show up in a \
+	process listing. If you use it directly in a configuration file, \
+	be sure to protect it so it is readable only by you, and do not \
+	use that same configuration file for htsearch. \
+" }, \
+{ "backlink_factor", "0.1",  \
+	"number", "htsearch", "", "3.1.0", "Searching:Ranking", "backlink_factor: 501.1", " \
+	This is a weight of \"how important\" a page is, based on \
+	the number of URLs pointing to it. It's actually \
+	multiplied by the ratio of the incoming URLs (backlinks) \
+	and outgoing URLs (links on the page), to balance out pages \
+	with lots of links to pages that link back to them. The ratio \
+	gives lower weight to \"link farms\", which often have many \
+	links to them.  This factor can \
+	be changed without changing the database in any way. \
+	However, setting this value to something other than 0 \
+	incurs a slowdown on search results. \
+" }, \
+{ "bad_extensions", ".wav .gz .z .sit .au .zip .tar .hqx .exe .com .gif .jpg .jpeg .aiff .class .map .ram .tgz .bin .rpm .mpg .mov .avi .css",  \
+	"string list", "htdig", "URL", "all", "Indexing:Where", "bad_extensions: .foo .bar .bad", " \
+	This is a list of extensions on URLs which are \
+	considered non-parsable. This list is used mainly to \
+	supplement the MIME-types that the HTTP server provides \
+	with documents. Some HTTP servers do not have a correct \
+	list of MIME-types and so can advertise certain \
+	documents as text while they are some binary format. \
+	If the list is empty, then all extensions are acceptable, \
+	provided they pass other criteria for acceptance or rejection. \
+	See also <a href=\"#valid_extensions\">valid_extensions</a>. \
+" }, \
+{ "bad_local_extensions", ".php .shtml .cgi",  \
+	"string list", "htdig", "URL", "all", "Indexing:Where", "bad_extensions: .foo .bar .bad", " \
+	This is a list of extensions on URLs which must be retrieved \
+	using the URL's true transport mechanism (such as HTTP). \
+	If <a href=\"#local_urls\">local_urls</a> is specified, URLs not \
+	ending with these extensions may instead be retrieved through \
+	the local filesystem for efficiency. \
+" },
+{ "bad_querystr", "",  \
+	"pattern list", "htdig", "URL", "3.1.0", "Indexing:Where", "bad_querystr: forum=private section=topsecret&amp;passwd=required", " \
+	This is a list of CGI query strings to be excluded from \
+	indexing. This can be used in conjunction with CGI-generated \
+	portions of a website to control which pages are \
+	indexed. \
+" }, \
+{ "bad_word_list", "${common_dir}/bad_words",  \
+	"string", "htdig htsearch", "", "all", "Indexing:What,Searching:Method", "bad_word_list: ${common_dir}/badwords.txt", " \
+	This specifies a file which contains words which should \
+	be excluded when digging or searching. This list should \
+	include the most common words or other words that you \
+	don't want to be able to search on (things like <em> \
+	sex</em> or <em>smut</em> are examples of these.)<br> \
+	The file should contain one word per line. A sample \
+	bad words file is located in the <code>contrib/examples</code> \
+	directory. \
+" }, \
+{ "bin_dir", BIN_DIR,  \
+	"string", "all", "", "all", "File Layout", "bin_dir: /usr/local/bin", " \
+	This is the directory in which the executables \
+	related to ht://Dig are installed. It is never used \
+	directly by any of the programs, but other attributes \
+	can be defined in terms of this one. \
+	<p> \
+	The default value of this attribute is determined at \
+	compile time. \
+	</p> \
+" }, \
+{ "boolean_keywords", "and or not",  \
+	"string list", "htsearch", "", "3.1.6", "Presentation:How", "boolean_keywords: et ou non", " \
+	These three strings are used as the keywords used in \
+	constructing the \
+	<a href=\"hts_templates.html#LOGICAL_WORDS\">LOGICAL_WORDS</a> \
+	template variable, \
+	and in parsing the <a href=\"hts_form.html#words\">words</a> input \
+	parameter when the <a href=\"hts_form.html#method\">method</a> \
+	parameter or <a href=\"#match_method\">match_method</a> attribute \
+	is set to <code>boolean</code>. \
+	See also the \
+	<a href=\"#boolean_syntax_errors\">boolean_syntax_errors</a> attribute. \
+" },
+{ "boolean_syntax_errors", "Expected \
+	'a search word, a quoted phrase or a boolean expression between ()' \
+		'at the end' 'instead of' 'end of expression' quotes",  \
+	"quoted string list", "htsearch", "", "3.1.6", "Presentation:How",
+	"boolean_syntax_errors: Attendait \"un mot\" \"&agrave; la fin\" \
+	\"au lieu de\" \"fin d'expression\" \"guillemet\"", " \
+	These six strings are used as the keywords used to \
+	construct various syntax error messages for errors encountered in \
+	parsing the <a href=\"hts_form.html#words\">words</a> input \
+	parameter when the <a href=\"hts_form.html#method\">method</a> parameter \
+	or <a href=\"#match_method\">match_method</a> attribute \
+	is set to <code>boolean</code>. \
+	They are used in conjunction with the \
+	<a href=\"#boolean_keywords\">boolean_keywords</a> attribute, and \
+	comprise all \
+	English-specific parts of these error messages.  The order in which \
+	the strings are put together may not be ideal, or even gramatically \
+	correct, for all languages, but they can be used to make fairly \
+	intelligible messages in many languages. \
+" },
+{ "build_select_lists", "",  \
+	"quoted string list", "htsearch", "", "3.2.0b1", "Searching:UI", "build_select_lists: \
+		MATCH_LIST matchesperpage matches_per_page_list \\<br> \
+				1 1 1 matches_per_page \"Previous Amount\" \\<br> \
+		RESTRICT_LIST,multiple restrict restrict_names 2 1 2 restrict \"\" \\<br> \
+		FORMAT_LIST,radio format template_map 3 2 1 template_name \"\"", " \
+	This list allows you to define any htsearch input parameter as \
+	a select list for use in templates, provided you also define \
+	the corresponding name list attribute which enumerates all the \
+	choices to put in the list. It can be used for existing input \
+	parameters, as well as any you define using the \
+	<a href=\"#allow_in_form\">allow_in_form</a> \
+	attribute. The entries in this list each consist of an octuple, \
+	a set of eight strings defining the variables and how they are to \
+	be used to build a select list. The attribute can contain many \
+	of these octuples. The strings in the string list are merely \
+	taken eight at a time. For each octuple of strings specified in \
+	build_select_lists, the elements have the following meaning:  \
+	<ol> \
+	   <li>the name of the template variable to be defined as a list, \
+	   optionally followed by a comma and the type of list, and \
+	   optional formatting codes \
+	   <li>the input parameter name that the select list will set  \
+	   <li>the name of the user-defined attribute containing the \
+	   name list \
+	   <li>the tuple size used in the name list above  \
+	   <li>the index into a name list tuple for the value  \
+	   <li>the index for the corresponding label on the selector \
+	   <li>the configuration attribute where the default value for \
+	   this input parameter is defined \
+	   <li>the default label, if not an empty string, which will be \
+	   used as the label for an additional list item for the current \
+	   input parameter value if it doesn't match any value in the \
+	   given list \
+	</ol> \
+	See the <a href=\"hts_selectors.html\">select list documentation</a> \
+	for more information on this attribute. \
+" }, \
+{ "caps_factor", "1",  \
+	"number", "htsearch", "", "??", "Searching:Ranking", "caps_factor: 1", " \
+	TO BE COMPLETED<br> \
+	See also <a href=\"#heading_factor\">heading_factor</a>. \
+" }, \
+{ "case_sensitive", "true",  \
+	"boolean", "htdig", "", "3.1.0b2", "Indexing:Where", "case_sensitive: false", " \
+	This specifies whether ht://Dig should consider URLs \
+	case-sensitive or not. If your server is case-insensitive, \
+	you should probably set this to false. <br> \
+	Even if this is false, \
+	<a href=\"#common_url_parts\">common_url_parts</a>, \
+	<a href=\"#url_part_aliases\">url_part_aliases</a> and \
+	<a href=\"#url_rewrite_rules\">url_rewrite_rules</a> \
+	are all still case sensitive, and \
+	<a href=\"#server_aliases\">server_aliases</a> \
+	is still case insensitive. \
+" }, \
+{ "check_unique_date", "false",  \
+	"boolean", "htdig", "Global", "3.2.0b3", "", "check_unique_date: false", " \
+	Include the modification date of the page in the MD5 hash, to reduce the \
+	problem with identical but physically separate pages in different parts of the tree pointing to \
+	different pages.  \
+" }, \
+{ "check_unique_md5", "false",  \
+	"boolean", "htdig", "Global", "3.2.0b3", "", "check_unique_md5: false", " \
+	Uses the MD5 hash of pages to reject aliases, prevents multiple entries \
+	in the index caused by such things as symbolic links \
+	Note: May not do the right thing for incremental update \
+" }, \
+{ "collection_names", "", \
+	"string list", "htsearch", "", "3.2.0b2", "", "collection_names: htdig_docs htdig_bugs", " \
+	This is a list of config file names that are used for searching multiple databases. \
+	Simply put, htsearch will loop through the databases specified by each of these config \
+	files and present the result of the search on all of the databases. \
+	The corresponding config files are looked up in the <a href=\"#config_dir\">config_dir</a> directory. \
+	Each listed config file <strong>must</strong> exist, as well as the corresponding databases. \
+" }, \
+{ "common_dir", COMMON_DIR,  \
+	"string", "all", "", "all", "File Layout", "common_dir: /tmp", " \
+	Specifies the directory for files that will or can be \
+	shared among different search databases. The default \
+	value for this attribute is defined at compile time. \
+" }, \
+{ "common_url_parts", "http:// http://www. ftp:// ftp://ftp. /pub/ .html .htm .shtml /index.html /index.htm .com/ .com mailto:",  \
+	"string list", "all", "", "3.1.0", "URLs", "common_url_parts: http://www.htdig.org/ml/ \\<br> \
+.html \\<br> \
+http://dev.htdig.org/ \\<br> \
+http://www.htdig.org/", " \
+	Sub-strings often found in URLs stored in the \
+	database.  These are replaced in the database by an \
+	internal space-saving encoding.  If a string \
+	specified in <a href=\"#url_part_aliases\">url_part_aliases</a>, \
+	overlaps any string in common_url_parts, the \
+	common_url_parts string is ignored.<br> \
+	Note that when this attribute is changed, the \
+	database should be rebuilt, unless the effect of \
+	\"changing\" the affected URLs in the database is \
+	wanted.<br> \
+" }, \
+{ "compression_level", "6",  \
+	"integer", "htdig", "", "3.1.0", "Indexing:How", "compression_level: 0", " \
+	If non-zero and the \
+	<a href=\"http://www.cdrom.com/pub/infozip/zlib/\">zlib</a> \
+	compression library was available when compiled, \
+	this attribute controls the amount of compression used in the \
+	<a href=\"#doc_excerpt\">doc_excerpt</a> file. \
+	<br/>This must be in the range 0-9, and must be non-zero when \
+	<a href=\"#wordlist_compress_zlib\">wordlist_compress_zlib</a> \
+	is used. \
+" }, \
+{ "config", "",  \
+	"string", "all", "", "??", "File Layout", "", " \
+	Name of configuration file to load. \
+	For security reasons, restrictions are placed on the values which \
+	can be specified on the command line to \
+	<a href=\"htsearch.html\" target=\"_top\">htsearch</a>. \
+	The default value of this attribute is determined at \
+	compile time. \
+" }, \
+{ "config_dir", CONFIG_DIR,  \
+	"string", "all", "", "all", "File Layout", "config_dir: /var/htdig/conf", " \
+	This is the directory which contains all configuration \
+	files related to ht://Dig. It is never used \
+	directly by any of the programs, but other attributes \
+	or the <a href=\"#include\">include</a> directive \
+	can be defined in terms of this one. \
+	<p> \
+	The default value of this attribute is determined at \
+	compile time. \
+	</p> \
+" },
+{ "content_classifier", "${bin_dir}/HtFileType",  \
+	"string", "htdig", "", "3.2.0b4", "Indexing:What", "content_classifier: file -i -b", " \
+	When ht://Dig can't determine the type of a <code>file://</code> \
+	URL from its extension, this program is used to determine the type. \
+	The program is called with one argument, the name of (possibly a \
+	temporary copy of) the file. \
+	<p> \
+	See also <a href=\"#mime_types\">mime_types</a>.\
+	</p> \
+" }, \
+{ "cookies_input_file", "",  \
+	"string", "htdig", "", "3.2.0b4", "Indexing:Connection", "cookies_input_file: ${common_dir}/cookies.txt", " \
+	Specifies the location of the file used for importing cookies \
+	for the crawl. These cookies will be preloaded into htdig's \
+	in-memory cookie jar, but aren't written back to the file. \
+	Cookies are specified according to Netscape's format \
+	(tab-separated fields). If this attribute is left blank, \
+	no cookie file will be read. \
+	For more information, see the sample cookies.txt file in the \
+	ht://Dig source distribution. \
+" }, \
+{ "create_image_list", "false",  \
+	"boolean", "htdig", "", "all", "Extra Output", "create_image_list: yes", " \
+	If set to true, a file with all the image URLs that \
+	were seen will be created, one URL per line. This list \
+	will not be in any order and there will be lots of \
+	duplicates, so after htdig has completed, it should be \
+	piped through <code>sort -u</code> to get a unique list. \
+" }, \
+{ "create_url_list", "false",  \
+	"boolean", "htdig", "", "all", "Extra Output", "create_url_list: yes", " \
+	If set to true, a file with all the URLs that were seen \
+	will be created, one URL per line. This list will not \
+	be in any order and there will be lots of duplicates, \
+	so after htdig has completed, it should be piped \
+	through <code>sort -u</code> to get a unique list. \
+" }, \
+{ "database_base", "${database_dir}/db",  \
+	"string", "all", "", "all", "File Layout", "database_base: ${database_dir}/sales", " \
+	This is the common prefix for files that are specific \
+	to a search database. Many different attributes use \
+	this prefix to specify filenames. Several search \
+	databases can share the same directory by just changing \
+	this value for each of the databases. \
+" }, \
+{ "database_dir", DATABASE_DIR,  \
+	"string", "all", "", "all", "File Layout", "database_dir: /var/htdig", " \
+	This is the directory which contains all database and \
+	other files related to ht://Dig. It is never used \
+	directly by any of the programs, but other attributes \
+	are defined in terms of this one. \
+	<p> \
+	The default value of this attribute is determined at \
+	compile time. \
+	</p> \
+" }, \
+{ "date_factor", "0",  \
+	"number", "htsearch", "", "3.1.0", "Searching:Ranking", "date_factor: 0.35", " \
+	This factor, gives higher \
+	rankings to newer documents and lower rankings to older \
+	documents. Before setting this factor, it's advised to \
+	make sure your servers are returning accurate dates \
+	(check the dates returned in the long format). \
+	Additionally, setting this to a nonzero value incurs a \
+	small performance hit on searching. \
+" }, \
+{ "date_format", "",  \
+	"string", "htsearch", "", "3.1.2", "Presentation:How", "date_format: %Y-%m-%d", " \
+	This format string determines the output format for \
+	modification dates of documents in the search results. \
+	It is interpreted by your system's <em>strftime</em> \
+	function. Please refer to your system's manual page \
+	for this function, for a description of available \
+	format codes. If this format string is empty, as it \
+	is by default,  \
+	<a href=\"htsearch.html\" target=\"_top\">htsearch</a> \
+	will pick a format itself. In this case, the <a \
+	href=\"#iso_8601\">iso_8601</a> attribute can be used \
+	to modify the appearance of the date. \
+" }, \
+{ "description_factor", "150",  \
+	"number", "htsearch", "", "3.1.0b3", "Searching:Ranking", "description_factor: 350", " \
+	Plain old \"descriptions\" are the text of a link pointing \
+	to a document. This factor gives weight to the words of \
+	these descriptions of the document. Not surprisingly, \
+	these can be pretty accurate summaries of a document's \
+	content. See also <a href=\"#heading_factor\">heading_factor</a> \
+	and <a href=\"#meta_description_factor\">meta_description_factor</a>. \
+" }, \
+{ "description_meta_tag_names", "description",  \
+	"string list", "htdig", "", "3.1.6", "Searching:Ranking", "description_meta_tag_names: \"description htdig-description\"", " \
+	The words in this list are used to search for descriptions in HTML \
+	<em>META</em> tags. This list can contain any number of strings \
+	that each will be seen as the name for whatever description \
+	convention is used. While words in any of the specified \
+	description contents will be indexed, only the last meta tag \
+	containing a description will be kept for the \
+	<a href=\"hts_templates.html#METADESCRIPTION\"METADESCRIPTION</a> \
+	variable in search results. The order in \
+	which the names are specified in this configuration attribute \
+	is irrelevant, as it is the order in which the tags appear in \
+	the documents that matters.<br> The <em>META</em> tags have the \
+	following format:<br> \
+	<tt> &nbsp;&nbsp;&lt;META name=\"<em>somename</em>\" \
+	                       content=\"<em>somevalue</em>\"&gt; </tt><br> \
+	See also <a href=\"#meta_description_factor\">meta_description_factor</a>. \
+" }, \
+{ "disable_cookies", "true",  \
+	"boolean", "htdig", "Server", "3.2.0b4", "Indexing:Connection", "disable_cookies: true", " \
+        This option, if set to true, will disable HTTP cookies. \
+" }, \
+{ "doc_db", "${database_base}.docdb",  \
+	"string", "all", "", "all", "File Layout", "doc_db: ${database_base}documents.db", " \
+	This file will contain a Berkeley database of documents \
+	indexed by document number. It contains all the information \
+	gathered for each document, except the document excerpts \
+	which are stored in the <a href=\"#doc_excerpt\"><em> \
+	doc_excerpt</em></a> file. \
+" }, \
+{ "doc_excerpt", "${database_base}.excerpts",  \
+	"string", "all", "", "3.2.0b1", "File Layout", "doc_excerpt: ${database_base}excerpts.db", " \
+	This file will contain a Berkeley database of document excerpts \
+	indexed by document number. It contains all the text \
+	gathered for each document, so this file can become \
+	rather large if <a href=\"#max_head_length\"><em> \
+	max_head_length</em></a> is set to a large value. \
+	The size can be reduced by setting the \
+	<a href=\"#compression_level\"><em>compression_level</em></a>, \
+	if supported on your system. \
+" }, \
+{ "doc_index", "${database_base}.docs.index",  \
+	"string", "htdig", "", "all", "File Layout", "doc_index: documents.index.db", " \
+	This file contains a mapping of document numbers to URLs and is \
+	used by htdig during indexing. It is used on updates if it exists. \
+" }, \
+{ "doc_list", "${database_base}.docs",  \
+	"string", "htdig htdump htload", "", "all", "File Layout", "doc_list: /tmp/documents.text", " \
+	This file is basically a text version of the file \
+	specified in <em><a href=\"#doc_db\">doc_db</a></em>. Its \
+	only use is to have a human readable database of all \
+	documents. The file is easy to parse with tools like \
+	perl or tcl. \
+" }, \
+{ "endday", "",  \
+	"integer", "htsearch", "", "3.1.6", "Searching:Method", "endday: 31", " \
+	Day component of last date allowed as last-modified date \
+	of returned docutments. \
+	This is most usefully specified as a \
+	<a href=\"hts_form.html#startyear\">GCI argument</a>. \
+	See also <a href=\"#startyear\">startyear</a>. \
+" }, \
+{ "end_ellipses", "<strong><code> ...</code></strong>",  \
+	"string", "htsearch", "", "all", "Presentation:Text", "end_ellipses: ...", " \
+	When excerpts are displayed in the search output, this \
+	string will be appended to the excerpt if there is text \
+	following the text displayed. This is just a visual \
+	reminder to the user that the excerpt is only part of \
+	the complete document. \
+" }, \
+{ "end_highlight", "</strong>",  \
+	"string", "htsearch", "", "3.1.4", "Presentation:Text", "end_highlight: &lt;/font&gt;", " \
+	When excerpts are displayed in the search output, matched \
+	words will be highlighted using <a href=\"#start_highlight\"> \
+	start_highlight</a> and this string. \
+	You should ensure that highlighting tags are balanced, \
+	that is, this string should close any formatting \
+	tag opened by start_highlight. \
+" }, \
+{ "endings_affix_file", "${common_dir}/english.aff",  \
+	"string", "htfuzzy", "", "all", "File Layout", "endings_affix_file: /var/htdig/affix_rules", " \
+	Specifies the location of the file which contains the \
+	affix rules used to create the endings search algorithm \
+	databases. Consult the documentation on \
+	<a href=\"htfuzzy.html\">htfuzzy</a> for more information on the \
+	format of this file. \
+" }, \
+{ "endings_dictionary", "${common_dir}/english.0",  \
+	"string", "htfuzzy", "", "all", "File Layout", "endings_dictionary: /var/htdig/dictionary", " \
+	Specifies the location of the file which contains the \
+	dictionary used to create the endings search algorithm \
+	databases. Consult the documentation on \
+	<a href=\"htfuzzy.html\">htfuzzy</a> for more information on the \
+	format of this file. \
+" }, \
+{ "endings_root2word_db", "${common_dir}/root2word.db",  \
+	"string", "htfuzzy htsearch", "", "all", "File Layout", "endings_root2word_db: /var/htdig/r2w.db", " \
+	This attributes specifies the database filename to be \
+	used in the 'endings' fuzzy search algorithm. The \
+	database maps word roots to all legal words with that \
+	root. For more information about this and other fuzzy \
+	search algorithms, consult the \
+	<a href=\"htfuzzy.html\">htfuzzy</a> documentation.<br> \
+	Note that the default value uses the \
+	<a href=\"#common_dir\">common_dir</a> attribute instead of the \
+	<a href=\"#database_dir\">database_dir</a> attribute. \
+	This is because this database can be shared with \
+	different search databases. \
+" }, \
+{ "endings_word2root_db", "${common_dir}/word2root.db",  \
+	"string", "htfuzzy htsearch", "", "all", "File Layout", "endings_word2root_db: /var/htdig/w2r.bm", " \
+	This attributes specifies the database filename to be \
+	used in the 'endings' fuzzy search algorithm. The \
+	database maps words to their root. For more information \
+	about this and other fuzzy search algorithms, consult \
+	the <a href=\"htfuzzy.html\">htfuzzy</a> \
+	documentation.<br> \
+	Note that the default value uses the \
+	<a href=\"#common_dir\">common_dir</a> attribute instead of the \
+	<a href=\"#database_dir\">database_dir</a> attribute. \
+	This is because this database can be shared with \
+	different search databases. \
+" }, \
+{ "endmonth", "",  \
+	"integer", "htsearch", "", "3.1.6", "Searching:Method", "endmonth: 12", " \
+	Month component of last date allowed as last-modified date \
+	of returned docutments. \
+	This is most usefully specified as a \
+	<a href=\"hts_form.html#startyear\">GCI argument</a>. \
+	See also <a href=\"#startyear\">startyear</a>. \
+" }, \
+{ "endyear", "",  \
+	"integer", "htsearch", "", "3.1.6", "Searching:Method", "endyear: 2002", " \
+	Year component of last date allowed as last-modified date \
+	of returned docutments. \
+	This is most usefully specified as a \
+	<a href=\"hts_form.html#startyear\">GCI argument</a>. \
+	See also <a href=\"#startyear\">startyear</a>. \
+" }, \
+{ "excerpt_length", "300",  \
+	"integer", "htsearch", "", "all", "Presentation:How", "excerpt_length: 500", " \
+	This is the maximum number of characters the displayed \
+	excerpt will be limited to. The first matched word will \
+	be highlighted in the middle of the excerpt so that there is \
+	some surrounding context.<br> \
+	The <em><a href=\"#start_ellipses\"> \
+	start_ellipses</a></em> and \
+	<em><a href=\"#end_ellipses\">end_ellipses</a></em> are used to \
+	indicate that the document contains text before and \
+	after the displayed excerpt respectively. \
+	The <em><a href=\"#start_highlight\">start_highlight</a></em> and \
+	<em><a href=\"#end_highlight\">end_highlight</a></em> are used to \
+	specify what formatting tags are used to highlight matched words. \
+" }, \
+{ "excerpt_show_top", "false",  \
+	"boolean", "htsearch", "", "all", "Presentation:How", "excerpt_show_top: yes", " \
+	If set to true, the excerpt of a match will always show \
+	the top of the matching document. If it is false (the \
+	default), the excerpt will attempt to show the part of \
+	the document that actually contains one of the words. \
+" }, \
+{ "exclude", "",  \
+	"pattern list", "htsearch", "", "3.2.0b4", "Searching:Method", "exclude: myhost.com/mailarchive/", " \
+	If a URL contains any of the space separated patterns, it will be \
+	discarded in the searching phase. This is used to exclude certain \
+	URLs from search results. The list can be specified from within \
+	the configuration file, and can be overridden with the \"exclude\" \
+	input parameter in the search form. \
+" }, \
+{ "exclude_urls", "/cgi-bin/ .cgi",  \
+	"pattern list", "htdig", "URL", "all", "Indexing:Where", "exclude_urls: students.html cgi-bin", " \
+	If a URL contains any of the space separated patterns, \
+	it will be rejected. This is used to exclude such \
+	common things such as an infinite virtual web-tree \
+	which start with cgi-bin. \
+" }, \
+{ "external_parsers", "",  \
+	"quoted string list", "htdig", "", "3.0.7", "External:Parsers", "external_parsers: text/html /usr/local/bin/htmlparser \\<br> \
+	application/pdf /usr/local/bin/parse_doc.pl \\<br> \
+	application/msword-&gt;text/plain \"/usr/local/bin/mswordtotxt -w\" \\<br> \
+	application/x-gunzip-&gt;user-defined /usr/local/bin/ungzipper", " \
+	This attribute is used to specify a list of \
+	content-type/parsers that are to be used to parse \
+	documents that cannot by parsed by any of the internal \
+	parsers. The list of external parsers is examined \
+	before the builtin parsers are checked, so this can be \
+	used to override the internal behavior without \
+	recompiling htdig.<br> \
+	 The external parsers are specified as pairs of \
+	strings. The first string of each pair is the \
+	content-type that the parser can handle while the \
+	second string of each pair is the path to the external \
+	parsing program. If quoted, it may contain parameters, \
+	separated by spaces.<br> \
+	 External parsing can also be done with external \
+	converters, which convert one content-type to \
+	another. To do this, instead of just specifying \
+	a single content-type as the first string \
+	of a pair, you specify two types, in the form \
+	<em>type1</em><strong>-&gt;</strong><em>type2</em>, \
+	as a single string with no spaces. The second \
+	string will define an external converter \
+	rather than an external parser, to convert \
+	the first type to the second. If the second \
+	type is <strong>user-defined</strong>, then \
+	it's up to the converter script to put out a \
+	\"Content-Type:&nbsp;<em>type</em>\" header followed \
+	by a blank line, to indicate to htdig what type it \
+	should expect for the output, much like what a CGI \
+	script would do. The resulting content-type must \
+	be one that htdig can parse, either internally, \
+	or with another external parser or converter.<br> \
+	 Only one external parser or converter can be \
+	specified for any given content-type. However, \
+	an external converter for one content-type can be \
+	chained to the internal parser for the same type, \
+	by appending <strong>-internal</strong> to the \
+	second type string (e.g. text/html->text/html-internal) \
+	to perform external preprocessing on documents of \
+	this type before internal parsing. \
+	There are two internal parsers, for text/html and \
+	text/plain.<p> \
+	The parser program takes four command-line \
+	parameters, not counting any parameters already \
+	given in the command string:<br> \
+	<em>infile content-type URL configuration-file</em><br> \
+	<table border=\"1\"> \
+	  <tr> \
+		<th> Parameter </th> \
+		<th> Description </th> \
+		<th> Example </th> \
+	  </tr> \
+	  <tr> \
+		<td valign=\"top\"> infile </td> \
+		<td> A temporary file with the contents to be parsed.  </td> \
+		<td> /var/tmp/htdext.14242 </td> \
+	  </tr> \
+	  <tr> \
+		<td valign=\"top\"> content-type </td> \
+		<td> The MIME-type of the contents.  </td> \
+		<td> text/html </td> \
+	  </tr> \
+	  <tr> \
+		<td valign=\"top\"> URL </td> \
+		<td> The URL of the contents.  </td> \
+		<td> http://www.htdig.org/attrs.html </td> \
+	  </tr> \
+	  <tr> \
+		<td valign=\"top\"> configuration-file </td> \
+		<td> The configuration-file in effect.  </td> \
+		<td> /etc/htdig/htdig.conf </td> \
+	  </tr> \
+	</table><p> \
+	The external parser is to write information for \
+	htdig on its standard output. Unless it is an \
+	external converter, which will output a document \
+	of a different content-type, then its output must \
+	follow the format described here.<br> \
+	 The output consists of records, each record terminated \
+	with a newline. Each record is a series of (unless \
+	expressively allowed to be empty) non-empty tab-separated \
+	fields. The first field is a single character \
+	that specifies the record type. The rest of the fields \
+	are determined by the record type. \
+	<table border=\"1\"> \
+	  <tr> \
+		<th> Record type </th> \
+		<th> Fields </th> \
+		<th> Description </th> \
+	  </tr> \
+	  <tr> \
+		<th rowspan=\"3\" valign=\"top\"> w </th> \
+		<td valign=\"top\"> word </td> \
+		<td> A word that was found in the document.  </td> \
+	  </tr> \
+	  <tr> \
+		<td valign=\"top\"> location </td> \
+		<td> \
+		  A number indicating the normalized location of \
+		  the word within the document. The number has to \
+		  fall in the range 0-1000 where 0 means the top of \
+		  the document. \
+		</td> \
+	  </tr> \
+	  <tr> \
+		<td valign=\"top\"> heading level </td> \
+		<td> \
+		  A heading level that is used to compute the \
+		  weight of the word depending on its context in \
+		  the document itself. The level is in the range of \
+		  0-11 and are defined as follows: \
+		  <dl compact> \
+			<dt> 0 </dt> <dd> Normal text </dd> \
+			<dt> 1 </dt> <dd> Title text </dd> \
+			<dt> 2 </dt> <dd> Heading 1 text </dd> \
+			<dt> 3 </dt> <dd> Heading 2 text </dd> \
+			<dt> 4 </dt> <dd> Heading 3 text </dd> \
+			<dt> 5 </dt> <dd> Heading 4 text </dd> \
+			<dt> 6 </dt> <dd> Heading 5 text </dd> \
+			<dt> 7 </dt> <dd> Heading 6 text </dd> \
+			<dt> 8 </dt> <dd> text alternative to images </dd> \
+			<dt> 9 </dt> <dd> Keywords </dd> \
+			<dt> 10 </dt> <dd> Meta-description </dd> \
+			<dt> 11 </dt> <dd> Author </dd> \
+		  </dl> \
+		</td> \
+	  </tr> \
+	  <tr> \
+		<th rowspan=\"2\" valign=\"top\"> u </th> \
+		<td valign=\"top\"> document URL </td> \
+		<td> \
+		  A hyperlink to another document that is \
+		  referenced by the current document.  It must be \
+		  complete and non-relative, using the URL parameter to \
+		  resolve any relative references found in the document. \
+		</td> \
+	  </tr> \
+	  <tr> \
+		<td valign=\"top\"> hyperlink description </td> \
+		<td> \
+		  For HTML documents, this would be the text \
+		  between the &lt;a href...&gt; and &lt;/a&gt; \
+		  tags. \
+		</td> \
+	  </tr> \
+	  <tr> \
+		<th valign=\"top\"> t </th> \
+		<td valign=\"top\"> title </td> \
+		<td> The title of the document </td> \
+	  </tr> \
+	  <tr> \
+		<th valign=\"top\"> h </th> \
+		<td valign=\"top\"> head </td> \
+		<td> \
+		  The top of the document itself. This is used to \
+		  build the excerpt. This should only contain \
+		  normal ASCII text \
+		</td> \
+	  </tr> \
+	  <tr> \
+		<th valign=\"top\"> a </th> \
+		<td valign=\"top\"> anchor </td> \
+		<td> \
+		  The label that identifies an anchor that can be \
+		  used as a target in an URL. This really only \
+		  makes sense for HTML documents. \
+		</td> \
+	  </tr> \
+	  <tr> \
+		<th valign=\"top\"> i </th> \
+		<td valign=\"top\"> image URL </td> \
+		<td> \
+		  An URL that points at an image that is part of \
+		  the document. \
+        </td> \
+	  </tr> \
+	  <tr> \
+		<th rowspan=\"3\" valign=\"top\"> m </th> \
+		<td valign=\"top\"> http-equiv </td> \
+		<td> \
+		  The HTTP-EQUIV attribute of a \
+		  <a href=\"meta.html\"><em>META</em> tag</a>. \
+		  May be empty. \
+		</td> \
+	  </tr> \
+	  <tr> \
+		<td valign=\"top\"> name </td> \
+		<td> \
+		  The NAME attribute of this \
+		  <a href=\"meta.html\"><em>META</em> tag</a>. \
+		  May be empty. \
+		</td> \
+	  </tr> \
+	  <tr> \
+		<td valign=\"top\"> contents </td> \
+		<td> \
+		  The CONTENTS attribute of this \
+		  <a href=\"meta.html\"><em>META</em> tag</a>. \
+		  May be empty. \
+		</td> \
+	  </tr> \
+	</table> \
+	<p><em>See also FAQ questions <a href=\"FAQ.html#q4.8\">4.8</a> and \
+	<a href=\"FAQ.html#q4.9\">4.9</a> for more examples.</em></p> \
+" }, \
+{ "external_protocols", "", \
+	"quoted string list", "htdig", "", "3.2.0b1", "External:Protocols", "external_protocols: https /usr/local/bin/handler.pl \\<br> \
+	ftp /usr/local/bin/ftp-handler.pl", " \
+	This attribute is a bit like \
+	<a href=\"#external_parsers\">external_parsers</a> since it specifies \
+	a list of protocols/handlers that are used to download documents \
+	that cannot be retrieved using the internal methods. This enables \
+	htdig to index documents with URL schemes it does not understand, \
+	or to use more advanced authentication for the documents it is \
+	retrieving. This list is checked before HTTP or other methods, \
+	so this can override the internal behavior without writing additional \
+	code for htdig.<br> \
+	  The external protocols are specified as pairs of strings, the first \
+	being the URL scheme that the script can handle while the second \
+	is the path to the script itself. If the second is \
+	quoted, then additional command-line arguments may be given.<br> \
+	If the external protocol does not contain a colon (:), it is assumed \
+	to have the standard format \
+	\"protocol://[usr[:password]@]address[:port]/path\". \
+	If it ends with a colon, then it is assumed to have the simpler format \
+	\"protocol:path\". If it ends with \"://\" then the standard form is \
+	again assumed. <br> \
+	  The program takes three command-line parameters, not counting any \
+	parameters already given in the command string:<br> \
+	<em>protocol URL configuration-file</em><br> \
+	<table border=\"1\"> \
+	  <tr> \
+		<th> Parameter </th> \
+		<th> Description </th> \
+		<th> Example </th> \
+	  </tr> \
+	  <tr> \
+		<td valign=\"top\"> protocol </td> \
+		<td> The URL scheme to be used.  </td> \
+		<td> https </td> \
+	  </tr> \
+	  <tr> \
+		<td valign=\"top\"> URL </td> \
+		<td> The URL to be retrieved.  </td> \
+		<td> https://www.htdig.org:8008/attrs.html </td> \
+	  </tr> \
+	  <tr> \
+		<td valign=\"top\"> configuration-file </td> \
+		<td> The configuration-file in effect.  </td> \
+		<td> /etc/htdig/htdig.conf </td> \
+	  </tr> \
+	</table><p> \
+	The external protocol script is to write information for htdig on the  \
+	standard output. The output must follow the form described here. The \
+	output consists of a header followed by a blank line, followed by \
+	the contents of the document. Each record in the header is terminated \
+	with a newline.  Each record is a series of (unless expressively \
+	allowed to be empty) non-empty tab-separated fields. The first field \
+	is a single character that specifies the record type. The rest of \
+	the fields are determined by the record type. \
+	<table border=\"1\"> \
+	  <tr> \
+		<th> Record type </th> \
+		<th> Fields </th> \
+		<th> Description </th> \
+	  </tr> \
+	  <tr> \
+		<th valign=\"top\"> s </th> \
+		<td valign=\"top\"> status code </td> \
+		<td> \
+		  An HTTP-style status code, e.g. 200, 404. Typical codes include: \
+		    <dl compact> \
+			<dt> 200 </dt> \
+			    <dd> Successful retrieval </dd> \
+			<dt> 304 </dt> \
+			<dd> \
+			  Not modified (for example, if the document hasn\'t \
+			  changed since the last dig) \
+			</dd> \
+			<dt> 301 </dt> \
+			    <dd> Redirect (to another URL) </dd> \
+			<dt> 401 </dt> \
+			    <dd> Not authorized </dd> \
+			<dt> 404 </dt> \
+			    <dd> Not found </dd> \
+		    </dl> \
+		</td> \
+	  </tr> \
+	  <tr> \
+		<th valign=\"top\"> r </th> \
+		<td valign=\"top\"> reason </td> \
+		<td> \
+		  A text string describing the status code, \
+		  e.g \"Redirect\" or \"Not Found.\" \
+		</td> \
+	  </tr> \
+	  <tr> \
+		<th valign=\"top\"> m </th> \
+		<td valign=\"top\"> status code </td> \
+		<td> \
+		  The modification time of this document. While the code is \
+		  fairly flexible about the time/date formats it accepts, it \
+		  is recommended to use something standard, like \
+		  RFC1123: Sun, 06 Nov 1994 08:49:37 GMT, or \
+		  ISO-8601:  1994-11-06 08:49:37 GMT. \
+		</td> \
+	  </tr> \
+	  <tr> \
+		<th valign=\"top\"> t </th> \
+		<td valign=\"top\"> content-type </td> \
+		<td> \
+		  A valid MIME type for the document, like text/html or text/plain. \
+		</td> \
+	  </tr> \
+	  <tr> \
+		<th valign=\"top\"> l </th> \
+		<td valign=\"top\"> content-length </td> \
+		<td> \
+		  The length of the document on the server, which may not \
+		  necessarily be the length of the buffer returned. \
+		</td> \
+	  </tr> \
+	  <tr> \
+		<th valign=\"top\"> u </th> \
+		<td valign=\"top\"> url </td> \
+		<td> \
+		  The URL of the document, or in the case of a redirect, the \
+		  URL that should be indexed as a result of the redirect. \
+		</td> \
+	  </tr> \
+      </table>	   \
+" }, \
+{ "extra_word_characters", "",  \
+	"string", "htdig htsearch", "", "3.1.2", "Indexing:What", "extra_word_characters: _", " \
+	These characters are considered part of a word. \
+	In contrast to the characters in the \
+	<a href=\"#valid_punctuation\">valid_punctuation</a> \
+	attribute, they are treated just like letter \
+	characters.  See also the <a href=\"#allow_numbers\">allow_numbers</a>\
+	attribute.<br> \
+	Note that the <a href=\"#locale\">locale</a> attribute \
+	is normally used to configure which characters \
+	constitute letter characters.<br> \
+	Note also that it is an error to have characters in both \
+	extra_word_characters and \
+	<a href=\"#valid_punctuation\">valid_punctuation</a>. \
+	To add one of the characters in the default valid_punctuation to \
+	extra_word_characters, an explicit valid_punctuation entry must be \
+	added to the configuration file.<br> \
+	See also the comments about special characters at \
+	<a href=\"#valid_punctuation\">valid_punctuation</a>. \
+" }, \
+{ "head_before_get", "true",  \
+	"boolean", "htdig", "Server", "3.2.0b1", "Indexing:Connection", "head_before_get: false", " \
+    If set to true, an HTTP/1.1 <em>HEAD</em> \
+    call is made in order to retrieve header information about a document. \
+    If the status code and the content-type returned show that the \
+    document is parsable, then a subsequent 'GET' call is made.  In \
+    general, it is recommended that this attribute be set to 'true', \
+    as it can really improve performance (especially when used with \
+    persistent connections).  This is particularly so during an \
+    incremental dig, since in this case 'htdig' can ask the server if the \
+    document has been modified since last dig. However there are a few \
+    cases when it is better to switch it off: \
+    <ul> \
+        <li>the majority of documents are parsable (HTML or a type for which \
+        an external parser has been provided) and must be retrieved anyway \
+        (initial dig);</li> \
+        <li>the server does not support the HEAD method or it is \
+        disabled;</li> \
+        <li>in some cases <a href=\"#persistent_connections\">persistent_connections</a> may \
+        not work properly and either the 'head_before_get' attribute or the \
+        'persistent_connections' attribute must be turned off.</li> \
+    </ul> \
+" }, \
+{ "heading_factor", "5",  \
+	"number", "htsearch", "", "3.2.0b1", "Searching:Ranking", "heading_factor: 20", " \
+			This is a factor which will be used to multiply the \
+			weight of words between &lt;h1&gt; and &lt;/h1&gt; \
+			tags, as well as headings of levels &lt;h2&gt; through \
+			&lt;h6&gt;. It is used to assign the level of importance \
+			to headings. Setting a factor to 0 will cause words \
+			in these headings to be ignored. The number may be a \
+	floating point number. See also \
+	<a href=\"#author_factor\">author_factor</a> \
+	<a href=\"#backlink_factor\">backlink_factor</a> \
+	<a href=\"#caps_factor\">caps_factor</a> \
+	<a href=\"#date_factor\">date_factor</a> \
+	<a href=\"#description_factor\">description_factor</a> \
+	<a href=\"#keywords_factor\">keywords_factor</a> \
+	<a href=\"#meta_description_factor\">meta_description_factor</a> \
+	<a href=\"#text_factor\">text_factor</a> \
+	<a href=\"#title_factor\">title_factor</a> \
+	<a href=\"#url_text_factor\">url_text_factor</a> \
+" }, \
+{ "htnotify_prefix_file", "", \
+    "string", "htnotify", "", "3.2.0b3", "Extra Output", "htnotify_prefix_file: ${common_dir}/notify_prefix.txt", " \
+	Specifies the file containing text to be inserted in each mail  \
+	message sent by htnotify before the list of expired webpages. If omitted,  \
+	nothing is inserted. \
+" }, \
+{ "htnotify_replyto", "", \
+    "string", "htnotify", "", "3.2.0b3", "Extra Output", "htnotify_replyto: [email protected]", " \
+	This specifies the email address that htnotify email messages \
+	include in the Reply-to: field. \
+" }, \
+{ "htnotify_sender", "webmaster@www",  \
+	"string", "htnotify", "", "all", "Extra Output", "htnotify_sender: [email protected]", " \
+	This specifies the email address that htnotify email \
+	messages get sent out from. The address is forged using \
+	/usr/lib/sendmail. Check htnotify/htnotify.cc for \
+	detail on how this is done. \
+" }, \
+{ "htnotify_suffix_file", "", \
+    "string", "htnotify", "", "3.2.0b3", "Extra Output", "htnotify_suffix_file: ${common_dir}/notify_suffix.txt", " \
+	Specifies the file containing text to be inserted in each mail message  \
+	sent by htnotify after the list of expired webpages. If omitted, htnotify  \
+	will insert a standard message. \
+" }, \
+{ "htnotify_webmaster",	 "ht://Dig Notification Service", \
+    "string", "htnotify", "", "3.2.0b3", "Extra Output", "htnotify_webmaster: Notification Service", " \
+	This provides a name for the From field, in addition to the email \
+	address for the email messages sent out by htnotify. \
+" }, \
+{ "http_proxy", "",  \
+	"string", "htdig", "URL", "3.0", "Indexing:Connection", "http_proxy: http://proxy.bigbucks.com:3128", " \
+	When this attribute is set, all HTTP document \
+	retrievals will be done using the HTTP-PROXY protocol. \
+	The URL specified in this attribute points to the host \
+	and port where the proxy server resides.<br> \
+	Later, this should be able to be overridden by the \
+	<code>http_proxy</code> environement variable, but it currently cannot.\
+	The use of a proxy server greatly improves performance \
+	of the indexing process.<br> \
+	See also \
+	<a href=\"#http_proxy_authorization\">http_proxy_authorization</a> and \
+	<a href=\"#http_proxy_exclude\">#http_proxy_exclude</a>. \
+" }, \
+{ "http_proxy_authorization", "",  \
+	"string", "htdig", "URL", "3.2.0b4", "Indexing:Connection", "http_proxy_authorization: myusername:mypassword", " \
+	This tells htdig to send the supplied \
+	<em>username</em><strong>:</strong><em>password</em> with each HTTP request, \
+	when using a proxy with authorization requested. \
+	The credentials will be encoded using the \"Basic\" authentication \
+	scheme. There <em>must</em> be a colon (:) between the username and \
+	password.<br> \
+	If you use this option, be sure to protect the configuration file \
+	so it is readable only by you, and do not \
+	use that same configuration file for htsearch. \
+" }, \
+{ "http_proxy_exclude", "", \
+	"pattern list", "htdig", "", "3.1.0b3", "Indexing:Connection", "http_proxy_exclude: http://intranet.foo.com/", " \
+	When this is set, URLs matching this will not use the \
+	proxy. This is useful when you have a mixture of sites \
+	near to the digging server and far away. \
+" }, \
+{ "ignore_alt_text", "false",  \
+	"boolean", "htdig", "", "3.1.6", "Indexing:What", "ignore_alt_text: true", " \
+	If set, this causes the text of the ALT field in an &lt;IMG...&gt; tag \
+	not to be indexed as part of the text of the document, nor included in \
+	excerpts. \
+" }, \
+{ "ignore_dead_servers", "true",  \
+	"boolean", "htdig", "", "3.1.6", "Indexing:Connection", "ignore_dead_servers: false", " \
+	Determines whether htdig will continue to index URLs from a \
+	server after an attempted connection to the server fails as \
+	&quot;no host found&quot; or &quot;host not found (port).&quot; If \
+	set to false, htdig will try <em>every</em> URL from that server. \
+" }, \
+{ "image_list", "${database_base}.images",  \
+	"string", "htdig", "", "all", "Extra Output", "image_list: allimages", " \
+	This is the file that a list of image URLs gets written \
+	to by <a href=\"htdig.html\">htdig</a> when the \
+	<a href=\"#create_image_list\">create_image_list</a> is set to \
+	true. As image URLs are seen, they are just appended to \
+	this file, so after htdig finishes it is probably a \
+	good idea to run <code>sort -u</code> on the file to \
+	eliminate duplicates from the file. \
+" }, \
+{ "image_url_prefix", IMAGE_URL_PREFIX,  \
+	"string", "htsearch", "", "all", "Presentation:Text", "image_url_prefix: /images/htdig", " \
+	This specifies the directory portion of the URL used \
+	to display star images. This attribute isn't directly \
+	used by htsearch, but is used in the default URL for \
+	the <a href=\"#star_image\">star_image</a> and \
+	<a href=\"#star_blank\">star_blank</a> attributes, and \
+	other attributes may be defined in terms of this one. \
+	<p> \
+	The default value of this attribute is determined at \
+	compile time. \
+	</p> \
+" }, \
+{ "include", "", \
+	"string", "all", "", "3.1.0", "", "include: ${config_dir}/htdig.conf", " \
+	This is not quite a configuration attribute, but \
+	rather a directive. It can be used within one \
+	configuration file to include the definitions of \
+	another file. The last definition of an attribute \
+	is the one that applies, so after including a file, \
+	any of its definitions can be overridden with \
+	subsequent definitions. This can be useful when \
+	setting up many configurations that are mostly the \
+	same, so all the common attributes can be maintained \
+	in a single configuration file. The include directives \
+	can be nested, but watch out for nesting loops. \
+" }, \
+{ "iso_8601", "false",  \
+	"boolean", "htsearch htnotify", "", "3.1.0b2", "Presentation:How,Extra Output", "iso_8601: true", " \
+	This sets whether dates should be output in ISO 8601 \
+	format. For example, this was written on: 1998-10-31 11:28:13 EST. \
+	See also the <a \
+	href=\"#date_format\">date_format</a> attribute, which \
+	can override any date format that \
+	<a href=\"htsearch.html\" target=\"_top\">htsearch</a> \
+	picks by default.<br> \
+	This attribute also affects the format of the date \
+	<a href=\"htnotify.html\">htnotify</a> expects to find \
+	in a <strong>htdig-notification-date</strong> field. \
+" }, \
+{ "keywords", "", \
+    "string list", "htsearch", "", "??", "Searching:Method", "keywords: documentation", " \
+	Keywords which <strong>must</strong> be found on all pages returned, \
+    	even if the \"or\" (\"Any\") <a href=\"#method\">method</a> is \
+	selected. \
+" }, \
+{ "keywords_factor", "100",  \
+	"number", "htsearch", "", "all", "Searching:Ranking", "keywords_factor: 12", " \
+	This is a factor which will be used to multiply the \
+	weight of words in the list of \
+	<a href=\"#keywords_meta_tag_names\">meta keywords</a> of a document. \
+	The number may be a floating point number. See also the \
+	<a href=\"#heading_factor\">heading_factor</a> attribute. \
+" }, \
+{ "keywords_meta_tag_names", "keywords htdig-keywords",  \
+	"string list", "htdig", "", "3.0.6", "Indexing:What", "keywords_meta_tag_names: keywords description", " \
+	The words in this list are used to search for keywords \
+	in HTML <em>META</em> tags. This list can contain any \
+	number of strings that each will be seen as the name \
+	for whatever keyword convention is used.<br> \
+	The <em>META</em> tags have the following format:<br> \
+<code> \
+&nbsp;&nbsp;&lt;META name=\"<em>somename</em>\" content=\"<em>somevalue</em>\"&gt; \
+</code> \
+" }, \
+{ "limit_normalized", "",  \
+	"pattern list", "htdig", "", "3.1.0b2", "Indexing:Where", "limit_normalized: http://www.mydomain.com", " \
+	This specifies a set of patterns that all URLs have to \
+	match against in order for them to be included in the \
+	search. Unlike the limit_urls_to attribute, this is done \
+	<strong>after</strong> the URL is normalized and the \
+	<a href=\"#server_aliases\">server_aliases</a> \
+	attribute is applied. This allows filtering after any \
+	hostnames and DNS aliases are resolved. Otherwise, this \
+	attribute is the same as the <a \
+	href=\"#limit_urls_to\">limit_urls_to</a> attribute. \
+" }, \
+{ "limit_urls_to", "${start_url}",  \
+	"pattern list", "htdig", "", "all", "Indexing:Where", "limit_urls_to: .sdsu.edu kpbs [.*\\.html]", " \
+	This specifies a set of patterns that all URLs have to \
+	match against in order for them to be included in the \
+	search. Any number of strings can be specified, \
+	separated by spaces. If multiple patterns are given, at \
+	least one of the patterns has to match the URL.<br> \
+	Matching, by default, is a case-sensitive string match on the URL \
+	to be used, unless the <a href=\"#case_sensitive\">case_sensitive</a> \
+	attribute is false. The match will be performed <em>after</em> \
+	the relative references have been converted to a valid \
+	URL. This means that the URL will <em>always</em> start \
+	with a transport specifier (<code>http://</code> if none is \
+	specified).<br> \
+	Granted, this is not the perfect way of doing this, \
+	but it is simple enough and it covers most cases.<br> \
+	To limit URLs in htsearch, use \
+	<a href=\"#restrict\">restrict</a>. \
+" }, \
+{ "local_default_doc", "index.html",  \
+	"string list", "htdig", "Server", "3.0.8b2", "Indexing:Where", "local_default_doc: default.html default.htm index.html index.htm", " \
+	Set this to the default documents in a directory used by the \
+	server. This is used for local filesystem access, \
+	using <a href=\"#local_urls\">local_urls</a>, to \
+	translate URLs like http://foo.com/ into something like \
+	/home/foo.com/index.html \
+	(see also <a href=\"#remove_default_doc\">remove_default_doc</a>). \
+	<br>The list should only contain names that the local server \
+	recognizes as default documents for directory URLs, as defined \
+	by the DirectoryIndex setting in Apache's srm.conf, for example. \
+	As of version 3.1.5, this can be a string list rather than a single \
+	name, and htdig will use the first name that works. Since this \
+	requires a loop, setting the most common name first will improve \
+	performance.  Special characters can be embedded in these names \
+	using %xx hex encoding. \
+" }, \
+{ "local_urls", "",  \
+	"string list", "htdig", "", "3.0.8b2", "Indexing:Where", "local_urls: http://www.foo.com/=/usr/www/htdocs/", " \
+	Set this to tell ht://Dig to access certain URLs through \
+	local filesystems. At first ht://Dig will try to access \
+	pages with URLs matching the patterns through the \
+	filesystems specified. If it cannot find the file, or \
+	if it doesn't recognize the file name extension, it will \
+	try the URL through HTTP instead. Note the example--the \
+	equal sign and the final slashes in both the URL and the \
+	directory path are critical. \
+	<br>The fallback to HTTP can be disabled by setting the \
+	<a href=\"#local_urls_only\">local_urls_only</a> attribute to true. \
+	To access user directory URLs through the local filesystem, \
+	set <a href=\"#local_user_urls\">local_user_urls</a>.  \
+	File types which need processing by the HTTP server may be \
+	specified by the \
+	<a href=\"#bad_local_extensions\">bad_local_extensions</a> \
+	attribute. \
+	As of version 3.1.5, you can provide multiple mappings of a given \
+	URL to different directories, and htdig will use the first \
+	mapping that works. \
+	Special characters can be embedded in these names using %xx hex encoding. \
+	For example, you can use %3D to embed an \"=\" sign in an URL pattern. \
+	<br> \
+	See also <a href=\"#local_default_doc\">local_default_doc</a>. \
+" }, \
+{ "local_urls_only", "false",  \
+	"boolean", "htdig", "", "3.1.4", "Indexing:Where", "local_urls_only: true", " \
+	Set this to tell ht://Dig to access files only through the  \
+	local filesystem, for URLs matching the patterns in the \
+	<a href=\"#local_urls\">local_urls</a> or \
+	<a href=\"#local_user_urls\">local_user_urls</a> attribute. If it \
+	cannot find the file, it will give up rather than trying HTTP or \
+	another protocol.  With this option, even <code>file://</code> urls \
+	are not retrieved, except throught the local_urls mechanism.\
+" }, \
+{ "local_user_urls", "",  \
+	"string list", "htdig", "", "3.0.8b2", "Indexing:Where", "local_user_urls: http://www.my.org/=/home/,/www/", " \
+	Set this to access user directory URLs through the local \
+	filesystem. If you leave the \"path\" portion out, it will \
+	look up the user's home directory in /etc/password (or NIS \
+	or whatever). As with <a href=\"#local_urls\">local_urls</a>, \
+	if the files are not found, ht://Dig will try with HTTP or the \
+	appropriate protocol. Again, note the \
+	example's format. To map http://www.my.org/~joe/foo/bar.html \
+	to /home/joe/www/foo/bar.html, try the example below. \
+	<br>The fallback to HTTP can be disabled by setting the \
+	<a href=\"#local_urls_only\">local_urls_only</a> attribute to true. \
+	As of version 3.1.5, you can provide multiple mappings of a given \
+	URL to different directories, and htdig will use the first \
+	mapping that works. \
+	Special characters can be embedded in these names using %xx hex encoding. \
+	For example, you can use %3D to embed an \"=\" sign in an URL pattern. \
+" }, \
+{ "locale", "C",  \
+	"string", "htdig", "", "3.0", "Indexing:What,Presentation:How", "locale: en_US", " \
+	Set this to whatever locale you want your search \
+	database cover. It affects the way international \
+	characters are dealt with. On most systems a list of \
+	legal locales can be found in /usr/lib/locale. Also \
+	check the <strong>setlocale(3C)</strong> man page. \
+	Note that depending the locale you choose, and whether \
+	your system's locale implementation affects floating \
+	point input, you may need to specify the decimal point \
+	as a comma rather than a period. This will affect \
+	settings of <a href=\"#search_algorithm\">search_algorithm</a> \
+	and any of the scoring factors. \
+" }, \
+{ "logging", "false",  \
+	"boolean", "htsearch", "", "3.1.0b2", "Extra Output", "logging: true", " \
+	This sets whether htsearch should use the syslog() to log \
+	search requests. If set, this will log requests with a \
+	default level of LOG_INFO and a facility of LOG_LOCAL5. For \
+	details on redirecting the log into a separate file or other \
+	actions, see the <strong>syslog.conf(5)</strong> man \
+	page. To set the level and facility used in logging, change \
+	LOG_LEVEL and LOG_FACILITY in the include/htconfig.h file \
+	before compiling. \
+	<dl> \
+	  <dt> \
+	    Each line logged by htsearch contains the following: \
+	  </dt> \
+	  <dd> \
+	    REMOTE_ADDR [config] (match_method) [words] \
+	    [logicalWords] (matches/matches_per_page) - \
+	    page, HTTP_REFERER \
+	  </dd> \
+	</dl> \
+	where any of the above are null or empty, it \
+	either puts in '-' or 'default' (for config). \
+" }, \
+{ "maintainer", "[email protected]",  \
+	"string", "htdig", "Server", "all", "Indexing:Out", "maintainer: [email protected]", " \
+	This should be the email address of the person in \
+	charge of the digging operation. This string is added \
+	to the user-agent: field when the digger sends a \
+	request to a server. \
+" }, \
+{ "match_method", "and",  \
+	"string", "htsearch", "", "3.0", "Searching:Method", "match_method: boolean", " \
+	This is the default method for matching that htsearch \
+	uses. The valid choices are: \
+	<ul> \
+	  <li> or </li> \
+	  <li> and </li> \
+	  <li> boolean </li> \
+	</ul> \
+	This attribute will only be used if the HTML form that \
+	calls htsearch didn't have the \
+	<a href=\"hts_form.html#method\">method</a> value set. \
+" }, \
+{ "matches_per_page", "10",  \
+	"integer", "htsearch", "", "3.0", "Searching:Method", "matches_per_page: 999", " \
+	If this is set to a relatively small number, the \
+	matches will be shown in pages instead of all at once. \
+	This attribute will only be used if the HTML form that \
+	calls htsearch didn't have the \
+	<a href=\"hts_form.html#matchesperpage\">matchesperpage</a> value set. \
+" }, \
+{ "max_connection_requests", "-1", \
+	"integer", "htdig", "", "3.2.0b1", "Indexing:Connection", "max_connection_requests: 100", " \
+	This attribute tells htdig to limit the number of requests it will \
+	send to a server using a single, persistent HTTP connection. This \
+	only applies when the \
+	<a href=\"#persistent_connections\">persistent_connections</a> \
+	attribute is set. You may set the limit as high as you want, \
+	but it must be at least 1. A value of -1 specifies no limit. \
+	Requests in the queue for a server will be combined until either \
+	the limit is reached, or the queue is empty. \
+" }, \
+{ "max_description_length", "60",  \
+	"integer", "htdig", "", "all", "Indexing:What", "max_description_length: 40", " \
+	While gathering descriptions of URLs, \
+	<a href=\"htdig.html\">htdig</a> will only record \
+	up to this many bytes of hyperlink descriptions for use in the \
+	<a href=\"hts_templates.html#DESCRIPTION\">DESCRIPTION</a> template \
+	variable.  This is used mostly to deal with broken HTML. (If a \
+	hyperlink is not terminated with a &lt;/a&gt; the \
+	description will go on until the end of the document.) \
+" }, \
+{ "max_descriptions", "5",  \
+	"integer", "htdig", "", "all", "Indexing:What", "max_descriptions: 1", " \
+	While gathering <a href=\"#description_factor\">descriptions</a> of \
+	URLs for the \
+	<a href=\"hts_templates.html#DESCRIPTIONS\">DESCRIPTIONS</a> template \
+	variable, <a href=\"htdig.html\">htdig</a> will only record up to this \
+	number of descriptions, in the order in which it encounters \
+	them. This is used to prevent the database entry for a document \
+	from growing out of control if the document has a huge number \
+	of links to it. <br> \
+	Note that all descriptions are used for indexing. \
+" }, \
+{ "max_doc_size", "100000",  \
+	"integer", "htdig", "URL", "3.0", "Indexing:What", "max_doc_size: 5000000", " \
+	This is the upper limit to the amount of data retrieved \
+	for documents (in bytes). This is mainly used to prevent \
+	unreasonable memory consumption since each document \
+	will be read into memory by <a href=\"htdig.html\"> \
+	htdig</a>. \
+" }, \
+{ "max_excerpts", "1",  \
+	"integer", "htsearch", "URL", "3.1.6", "Presentation:How", "max_excerpts: 10", " \
+	This value determines the maximum number of excerpts \
+	that can be displayed for one matching document in the \
+	search results. \
+" }, \
+{ "max_head_length", "512",  \
+	"integer", "htdig", "", "all", "Indexing:How", "max_head_length: 50000", " \
+	For each document retrieved, the top of the document is \
+	stored. This attribute determines the size of this \
+	block (in bytes). The text that will be stored is only the text; \
+	no markup is stored.<br> \
+	We found that storing 50,000 bytes will store about \
+	95% of all the documents completely. This really \
+	depends on how much storage is available and how much \
+	you want to show.  Currently, this is must not be 0. \
+" }, \
+{ "max_hop_count", "999999",  \
+	"integer", "htdig", "", "all", "Indexing:Where", "max_hop_count: 4", " \
+	Instead of limiting the indexing process by URL \
+	pattern, it can also be limited by the number of hops \
+	or clicks a document is removed from the starting URL. \
+	<br> \
+	The starting page or pages will have hop count 0. \
+" }, \
+{ "max_keywords", "-1",  \
+	"integer", "htdig", "", "3.2.0b1", "Indexing:What", "max_keywords: 10", " \
+	This attribute can be used to limit the number of keywords \
+	per document that htdig will accept from meta keywords tags. \
+	A value of -1 or less means no limit. This can help combat meta \
+	keyword spamming, by limiting the amount of keywords that will be \
+	indexed, but it will not completely prevent irrelevant matches \
+	in a search if the first few keywords in an offending document \
+	are not relevant to its contents. \
+" }, \
+{ "max_meta_description_length", "512",  \
+	"integer", "htdig", "", "3.1.0b1", "Indexing:How", "max_meta_description_length: 1000", " \
+	While gathering descriptions from meta description tags, \
+	<a href=\"htdig.html\">htdig</a> will only store up to  \
+	this much of the text (in bytes) for each document to fill the \
+	<a href=\"hts_templates.html#METADESCRIPTION\">METADESCRIPTION</a> \
+	template variable.  All words in the meta description are still \
+	used for indexing. \
+" }, \
+{ "max_prefix_matches", "1000",  \
+	"integer", "htsearch", "", "3.1.0b1", "Searching:Method", "max_prefix_matches: 100", " \
+	The Prefix <a href=\"#search_algorithm\">fuzzy algorithm</a> \
+	could potentially match a \
+	very large number of words. This value limits the \
+	number of words each prefix can match. Note \
+	that this does not limit the number of documents that \
+	are matched in any way. \
+" }, \
+{ "max_retries", "3",  \
+	"integer", "htdig", "", "3.2.0b1", "Indexing:Connection", "max_retries: 6", " \
+	 This option set the maximum number of retries when retrieving a document \
+	 fails (mainly for reasons of connection). \
+" }, \
+{ "max_stars", "4",  \
+	"integer", "htsearch", "", "all", "Presentation:How", "max_stars: 6", " \
+	When stars are used to display the score of a match, \
+	this value determines the maximum number of stars that \
+	can be displayed. \
+" }, \
+{ "maximum_page_buttons", "${maximum_pages}",  \
+	"integer", "htsearch", "", "3.2.0b3", "Presentation:How", "maximum_page_buttons: 20", " \
+	This value limits the number of page links that will be \
+	included in the page list at the bottom of the search \
+	results page. By default, it takes on the value of the \
+	<a href=\"#maximum_pages\">maximum_pages</a> \
+	attribute, but you can set it to something lower to allow \
+	more pages than buttons. In this case, pages above this \
+	number will have no corresponding button. \
+" }, \
+{ "maximum_pages", "10",  \
+	"integer", "htsearch", "", "all", "Presentation:How", "maximum_pages: 20", " \
+	This value limits the number of page links that will be \
+	included in the page list at the bottom of the search \
+	results page. As of version 3.1.4, this will limit the \
+	total number of matching documents that are shown. \
+	You can make the number of page buttons smaller than the \
+	number of allowed pages by setting the \
+	<a href=\"#maximum_page_buttons\">maximum_page_buttons</a> \
+	attribute. \
+" }, \
+{ "maximum_word_length", "32",  \
+	"integer", "htdig htsearch htfuzzy", "", "3.1.3", "Indexing:What", "maximum_word_length: 15", " \
+	This sets the maximum length of words that will be \
+	indexed. Words longer than this value will be silently \
+	truncated when put into the index, or searched in the \
+	index. \
+" }, \
+{ "md5_db", "${database_base}.md5hash.db",  \
+	"string", "htdig", "", "3.2.0b3", "File Layout", "md5_db: ${database_base}.md5.db", " \
+	This file holds a database of md5 and date hashes of pages to \
+	catch and eliminate duplicates of pages. See also the \
+	<a href=\"#check_unique_md5\">check_unique_md5</a> and \
+	<a href=\"#check_unique_date\">check_unique_date</a> attributes. \
+" }, \
+{ "meta_description_factor", "50",  \
+	"number", "htsearch", "", "3.1.0b1", "Searching:Ranking", "meta_description_factor: 20", " \
+	This is a factor which will be used to multiply the \
+	weight of words in any META description tags in a document. \
+	The number may be a floating point number. See also the \
+	<a href=\"#heading_factor\">heading_factor</a> attribute and the \
+	<a href=\"#description_factor\">description_factor</a> attribute. \
+" }, \
+{ "metaphone_db", "${database_base}.metaphone.db",  \
+	"string", "htfuzzy htsearch", "", "all", "File Layout", "metaphone_db: ${database_base}.mp.db", " \
+	The database file used for the fuzzy \"metaphone\" search \
+	algorithm. This database is created by \
+	<a href=\"htfuzzy.html\">htfuzzy</a> and used by \
+	<a href=\"htsearch.html\" target=\"_top\">htsearch</a>. \
+" }, \
+{ "method_names", "and All or Any boolean Boolean",  \
+	"quoted string list", "htsearch", "", "all", "Searching:UI", "method_names: or Or and And", " \
+	These values are used to create the <strong> \
+	method</strong> menu. It consists of pairs. The first \
+	element of each pair is one of the known methods, the \
+	second element is the text that will be shown in the \
+	menu for that method. This text needs to be quoted if \
+	it contains spaces. \
+	See the <a href=\"hts_selectors.html\">select list documentation</a> \
+	for more information on how this attribute is used. \
+" }, \
+{ "mime_types", "${config_dir}/mime.types", \
+	"string", "htdig", "", "3.2.0b1", "Indexing:Where", "mime_types: /etc/mime.types", " \
+	This file is used by htdig for local file access and resolving \
+	file:// URLs to ensure the files are parsable. If you are running \
+	a webserver with its own MIME file, you should set this attribute \
+	to point to that file. \
+	<p> \
+	See also <a href=\"#content_classifier\">content_classifier</a>.\
+"}, \
+{ "minimum_prefix_length", "1",  \
+	"integer", "htsearch", "", "3.1.0b1", "Searching:Method", "minimum_prefix_length: 2", " \
+	This sets the minimum length of prefix matches used by the \
+	\"prefix\" fuzzy matching algorithm. Words shorter than this \
+	will not be used in prefix matching. \
+" }, \
+{ "minimum_speling_length", "5",  \
+	"integer", "htsearch", "", "3.2.0b1", "Searching:Method", "minimum_speling_length: 3", " \
+	This sets the minimum length of words used by the \
+	\"speling\" fuzzy matching algorithm. Words shorter than this \
+	will not be used in this fuzzy matching. \
+" }, \
+{ "minimum_word_length", "3",  \
+	"integer", "htdig htsearch", "", "all", "Indexing:What", "minimum_word_length: 2", " \
+	This sets the minimum length of words that will be \
+	indexed. Words shorter than this value will be silently \
+	ignored but still put into the excerpt.<br> \
+	Note that by making this value less than 3, a lot more \
+	words that are very frequent will be indexed. It might \
+	be advisable to add some of these to the \
+	<a href=\"#bad_word_list\">bad_words list</a>. \
+" }, \
+{ "multimatch_factor", "1",  \
+	"number", "htsearch", "", "3.1.6", "Searching:Ranking", "multimatch_factor: 1000", " \
+    	This factor gives higher rankings to documents that have more than \
+	one matching search word when the <strong>or</strong> \
+	<a href=\"#match_method\">match_method</a> is used. \
+	In version 3.1.6, the matching words' combined scores were multiplied \
+	by this factor for each additional matching word.  Currently, this \
+	multiplier is applied at most once. \
+" },
+{ "next_page_text", "[next]",  \
+	"string", "htsearch", "", "3.1.0", "Presentation:Text", "next_page_text: &lt;img src=\"/htdig/buttonr.gif\"&gt;", " \
+	The text displayed in the hyperlink to go to the next \
+	page of matches. \
+" }, \
+{ "no_excerpt_show_top", "false",  \
+	"boolean", "htsearch", "", "3.1.0b3", "Presentation:How", "no_excerpt_show_top: yes", " \
+	If no excerpt is available, this option will act the \
+	same as <a \
+	href=\"#excerpt_show_top\">excerpt_show_top</a>, that is, \
+	it will show the top of the document. \
+" }, \
+{ "no_excerpt_text", "<em>(None of the search words were found in the top of this document.)</em>",  \
+	"string", "htsearch", "", "3.0", "Presentation:Text", "no_excerpt_text:", " \
+	This text will be displayed in place of the excerpt if \
+	there is no excerpt available. If this attribute is set \
+	to nothing (blank), the excerpt label will not be \
+	displayed in this case. \
+" }, \
+{ "no_next_page_text", "${next_page_text}",  \
+	"string", "htsearch", "", "3.0", "Presentation:Text", "no_next_page_text:", " \
+	The text displayed where there would normally be a \
+	hyperlink to go to the next page of matches. \
+" }, \
+{ "no_page_list_header", "",  \
+	"string", "htsearch", "", "3.0", "Presentation:Text", "no_page_list_header: &lt;hr noshade size=2&gt;All results on this page.&lt;br&gt;", " \
+	This text will be used as the value of the PAGEHEADER \
+	variable, for use in templates or the \
+	<a href=\"#search_results_footer\">search_results_footer</a> \
+	file, when all search results fit on a single page. \
+" }, \
+{ "no_page_number_text", "",  \
+	"quoted string list", "htsearch", "", "3.0", "Presentation:Text", "no_page_number_text: \
+				  &lt;strong&gt;1&lt;/strong&gt; &lt;strong&gt;2&lt;/strong&gt; \\<br> \
+				  &lt;strong&gt;3&lt;/strong&gt; &lt;strong&gt;4&lt;/strong&gt; \\<br> \
+				  &lt;strong&gt;5&lt;/strong&gt; &lt;strong&gt;6&lt;/strong&gt; \\<br> \
+				  &lt;strong&gt;7&lt;/strong&gt; &lt;strong&gt;8&lt;/strong&gt; \\<br> \
+				  &lt;strong&gt;9&lt;/strong&gt; &lt;strong&gt;10&lt;/strong&gt; \
+", " \
+	The text strings in this list will be used when putting \
+	together the PAGELIST variable, for use in templates or \
+	the <a href=\"#search_results_footer\">search_results_footer</a> \
+	file, when search results fit on more than page. The PAGELIST \
+	is the list of links at the bottom of the search results page. \
+	There should be as many strings in the list as there are \
+	pages allowed by the <a href=\"#maximum_page_buttons\">maximum_page_buttons</a> \
+	attribute. If there are not enough, or the list is empty, \
+	the page numbers alone will be used as the text for the links. \
+	An entry from this list is used for the current page, as the \
+	current page is shown in the page list without a hypertext link, \
+	while entries from the <a href=\"#page_number_text\"> \
+	page_number_text</a> list are used for the links to other pages. \
+	The text strings can contain HTML tags to highlight page numbers \
+	or embed images. The strings need to be quoted if they contain \
+	spaces. \
+" }, \
+{ "no_prev_page_text", "${prev_page_text}",  \
+	"string", "htsearch", "", "3.0", "Presentation:Text", "no_prev_page_text:", " \
+	The text displayed where there would normally be a \
+	hyperlink to go to the previous page of matches. \
+" }, \
+{ "no_title_text", "filename",  \
+	"string", "htsearch", "", "3.1.0", "Presentation:Text", "no_title_text: \"No Title Found\"", " \
+	This specifies the text to use in search results when no \
+	title is found in the document itself. If it is set to \
+	filename, htsearch will use the name of the file itself, \
+	enclosed in brackets (e.g. [index.html]). \
+" }, \
+{ "noindex_end", "<!--/htdig_noindex--> </SCRIPT>",  \
+	"quoted string list", "htdig", "", "3.1.0", "Indexing:What", "noindex_end: &lt;/SCRIPT&gt;", " \
+	This string marks the end of a section of an HTML file that should be \
+	completely ignored when indexing.  Note that text between noindex_start\
+	and noindex_end isn't even counted as white space; the text \
+	\"<code>foo<!--htdig_noindex-->something<!--/htdig_noindex-->bar</code>\" \
+	matches the word \"foobar\", not the phrase \"foo bar\".  White space \
+	following noindex_end <em>is</em> counted as white space. See also \
+	<a href=\"#noindex_start\">noindex_start</a>. \
+" }, \
+{ "noindex_start", "<!--htdig_noindex--> <SCRIPT",  \
+	"quoted string list", "htdig", "", "3.1.0", "Indexing:What", "noindex_start: &lt;SCRIPT", " \
+	These strings mark the start of a section of an HTML file that should \
+	be completely ignored when indexing. They work together with \
+	<a href=\"#noindex_end\">noindex_end</a>.  Once a string in \
+	noindex_start is found, text is ignored until the string at the \
+	<em>same position</em> within <a href=\"#noindex_end\">noindex_end</a> \
+	is encountered.  The sections marked off this way cannot overlap. \
+	As in the first default pattern, this can be SGML comment \
+	declarations that can be inserted anywhere in the documents to exclude \
+	different sections from being indexed. However, existing tags can also \
+	be used; this is especially useful to exclude some sections from being \
+	indexed where the files to be indexed can not be edited. The second \
+	default pattern shows how SCRIPT sections in 'uneditable' documents \
+	can be skipped; note how noindex_start does not contain an ending \
+	&gt;: this allows for all SCRIPT tags to be matched regardless of \
+	attributes defined (different types or languages). \
+	Note that the match for this string is case insensitive. \
+" }, \
+{ "nothing_found_file", "${common_dir}/nomatch.html",  \
+	"string", "htsearch", "", "all", "Presentation:Files", "nothing_found_file: /www/searching/nothing.html", " \
+	This specifies the file which contains the <code> \
+	HTML</code> text to display when no matches were found. \
+	The file should contain a complete <code>HTML</code> \
+	document.<br> \
+	Note that this attribute could also be defined in \
+	terms of <a href=\"#database_base\">database_base</a> to \
+	make is specific to the current search database. \
+" }, \
+{ "nph", "false",  \
+	"boolean", "htsearch", "", "3.2.0b2", "Presentation:How", "nph: true", " \
+	This attribute determines whether htsearch sends out full HTTP \
+	headers as required for an NPH (non-parsed header) CGI. Some \
+	servers assume CGIs will act in this fashion, for example MS \
+	IIS. If your server does not send out full HTTP headers, you \
+	should set this to true. \
+" }, \
+{ "page_list_header", "<hr noshade size=2>Pages:<br>",  \
+	"string", "htsearch", "", "3.0", "Presentation:Text", "page_list_header:", " \
+	This text will be used as the value of the PAGEHEADER \
+	variable, for use in templates or the \
+	<a href=\"#search_results_footer\">search_results_footer</a> \
+	file, when all search results fit on more than one page. \
+" }, \
+{ "page_number_separator", "\" \"",  \
+	"quoted string list", "htsearch", "", "3.1.4", "Presentation:Text", "page_number_separator: \"&lt;/td&gt; &lt;td&gt;\"", " \
+	The text strings in this list will be used when putting \
+	together the PAGELIST variable, for use in templates or \
+	the <a href=\"#search_results_footer\">search_results_footer</a> \
+	file, when search results fit on more than page. The PAGELIST \
+	is the list of links at the bottom of the search results page. \
+	The strings in the list will be used in rotation, and will \
+	separate individual entries taken from \
+	<a href=\"#page_number_text\">page_number_text</a> and \
+	<a href=\"#no_page_number_text\">no_page_number_text</a>. \
+	There can be as many or as few strings in the list as you like. \
+	If there are not enough for the number of pages listed, it goes \
+	back to the start of the list. If the list is empty, a space is \
+	used. The text strings can contain HTML tags. The strings need \
+	to be quoted if they contain spaces, or to specify an empty string. \
+" }, \
+{ "page_number_text", "",  \
+	"quoted string list", "htsearch", "", "3.0", "Presentation:Text", "page_number_text: \
+				  &lt;em&gt;1&lt;/em&gt; &lt;em&gt;2&lt;/em&gt; \\<br> \
+				  &lt;em&gt;3&lt;/em&gt; &lt;em&gt;4&lt;/em&gt; \\<br> \
+				  &lt;em&gt;5&lt;/em&gt; &lt;em&gt;6&lt;/em&gt; \\<br> \
+				  &lt;em&gt;7&lt;/em&gt; &lt;em&gt;8&lt;/em&gt; \\<br> \
+				  &lt;em&gt;9&lt;/em&gt; &lt;em&gt;10&lt;/em&gt; \
+", " \
+	The text strings in this list will be used when putting \
+	together the PAGELIST variable, for use in templates or \
+	the <a href=\"#search_results_footer\">search_results_footer</a> \
+	file, when search results fit on more than page. The PAGELIST \
+	is the list of links at the bottom of the search results page. \
+	There should be as many strings in the list as there are \
+	pages allowed by the <a href=\"#maximum_page_buttons\">maximum_page_buttons</a> \
+	attribute. If there are not enough, or the list is empty, \
+	the page numbers alone will be used as the text for the links. \
+	Entries from this list are used for the links to other pages, \
+	while an entry from the <a href=\"#no_page_number_text\"> \
+	no_page_number_text</a> list is used for the current page, as the \
+	current page is shown in the page list without a hypertext link. \
+	The text strings can contain HTML tags to highlight page numbers \
+	or embed images. The strings need to be quoted if they contain \
+	spaces. \
+" }, \
+{ "persistent_connections", "true",  \
+	"boolean", "htdig", "Server", "3.2.0b1", "Indexing:Connection", "persistent_connections: false", " \
+	If set to true, when servers make it possible, htdig can take advantage \
+	of persistent connections, as defined by HTTP/1.1 (<em>RFC2616</em>). This permits \
+	to reduce the number of open/close operations of connections, when retrieving \
+	a document with HTTP. \
+" }, \
+{ "plural_suffix", "s", \
+	"string", "htsearch", "", "3.2.0b2", "Presentation: Text", "plural_suffix: en", " \
+	Specifies the value of the PLURAL_MATCHES template \
+	variable used in the header, footer and template files. \
+	This can be used for localization for non-English languages \
+	where 's' is not the appropriate suffix. \
+" }, \
+{ "prefix_match_character", "*",  \
+	"string", "htsearch", "", "3.1.0b1", "Searching:Method", "prefix_match_character: ing", " \
+	A null prefix character means that prefix matching should be \
+	applied to every search word. Otherwise prefix matching is \
+	done on any search word ending with the characters specified \
+	in this string, with the string being stripped off before \
+	looking for matches. The \"prefix\" algorithm must be enabled \
+	in <a href=\"#search_algorithm\">search_algorithm</a> \
+	for this to work. You may also want to set the <a \
+	href=\"#max_prefix_matches\">max_prefix_matches</a> and <a \
+	href=\"#minimum_prefix_length\">minimum_prefix_length</a> attributes \
+	to get it working as you want.<br> As a special case, in version \
+	3.1.6 and later, if this string is non-null and is entered alone \
+	as a search word, it is taken as a wildcard that matches all \
+	documents in the database. If this string is null, the wildcard \
+	for this special case will be <strong>*</strong>. This wildcard \
+	doesn't require the prefix algorithm to be enabled. \
+" }, \
+{ "prev_page_text", "[prev]",  \
+	"string", "htsearch", "", "3.0", "Presentation:Text", "prev_page_text: &lt;img src=\"/htdig/buttonl.gif\"&gt;", " \
+	The text displayed in the hyperlink to go to the \
+	previous page of matches. \
+" }, \
+{ "regex_max_words", "25",  \
+	"integer", "htsearch", "", "3.2.0b1", "Searching:Method", "regex_max_words: 10", " \
+	The \"regex\" <a href=\"#search_algorithm\">fuzzy algorithm</a> \
+	could potentially match a \
+	very large number of words. This value limits the \
+	number of words each regular expression can match. Note \
+	that this does not limit the number of documents that \
+	are matched in any way. \
+" }, \
+{ "remove_bad_urls", "true",  \
+	"boolean", "htpurge", "Server", "all", "Indexing:How", "remove_bad_urls: true", " \
+	If TRUE, htpurge will remove any URLs which were marked \
+	as unreachable by htdig from the database. If FALSE, it \
+	will not do this. When htdig is run in initial mode, \
+	documents which were referred to but could not be \
+	accessed should probably be removed, and hence this \
+	option should then be set to TRUE, however, if htdig is \
+	run to update the database, this may cause documents on \
+	a server which is temporarily unavailable to be \
+	removed. This is probably NOT what was intended, so \
+	hence this option should be set to FALSE in that case. \
+" }, \
+{ "remove_default_doc", "index.html",  \
+	"string list", "htdig", "", "3.1.0", "Indexing:How", "remove_default_doc: default.html default.htm index.html index.htm", " \
+	Set this to the default documents in a directory used by the \
+	servers you are indexing. These document names will be stripped \
+	off of URLs when they are normalized, if one of these names appears \
+	after the final slash, to translate URLs like \
+	http://foo.com/index.html into http://foo.com/<br> \
+	Note that you can disable stripping of these names during \
+	normalization by setting the list to an empty string. \
+	The list should only contain names that all servers you index \
+	recognize as default documents for directory URLs, as defined \
+	by the DirectoryIndex setting in Apache's srm.conf, for example. \
+	This does not apply to  file:///  or  ftp://  URLS. \
+	<br>See also <a href=\"#local_default_doc\">local_default_doc</a>. \
+" }, \
+{ "remove_unretrieved_urls", "false",  \
+	"boolean", "htpurge", "Server", "3.2.0b1", "Indexing:How", "remove_unretrieved_urls: true", " \
+	If TRUE, htpurge will remove any URLs which were discovered \
+	and included as stubs in the database but not yet retrieved. If FALSE, it \
+	will not do this. When htdig is run in initial mode with no restrictions  \
+	on hopcount or maximum documents, these should probably be removed and set \
+	to true. However, if you are hoping to index a small set of documents and  \
+	eventually get to the rest, you should probably leave this as false. \
+" }, \
+{ "restrict", "",  \
+	"pattern list", "htsearch", "", "3.2.0b4", "Searching:Method", "restrict: http://www.acme.com/widgets/", " \
+	This specifies a set of patterns that all URLs have to \
+	match against in order for them to be included in the search \
+	results. Any number of strings can be specified, separated by \
+	spaces. If multiple patterns are given, at least one of the \
+	patterns has to match the URL. The list can be specified \
+	from within the configuration file, and can be overridden \
+	with the \"restrict\" input parameter in the search form. Note \
+	that the restrict list does not take precedence over the \
+	<a href=\"#exclude\">exclude</a> list - if a URL matches patterns \
+	in both lists it is still excluded from the search results. \
+	<br>To restrict URLs in htdig, use \
+	<a href=\"#limit_urls_to\">limit_urls_to</a>. \
+" }, \
+{ "robotstxt_name", "htdig",  \
+	"string", "htdig", "Server", "3.0.7", "Indexing:Out", "robotstxt_name: myhtdig", " \
+	Sets the name that htdig will look for when parsing \
+	robots.txt files. This can be used to make htdig appear \
+	as a different spider than ht://Dig. Useful to \
+	distinguish between a private and a global index. \
+" }, \
+{ "script_name", "",  \
+	"string", "htsearch", "", "3.1.4", "Presentation:Text", "script_name: /search/results.shtml", " \
+	Overrides the value of the SCRIPT_NAME \
+	environment attribute. This is useful if \
+	htsearch is not being called directly as a CGI \
+	program, but indirectly from within a dynamic \
+	.shtml page using SSI directives. Previously, \
+	you needed a wrapper script to do this, but \
+	this configuration attribute makes wrapper \
+	scripts obsolete for SSI and possibly for \
+	other server scripting languages, as \
+	well. (You still need a wrapper script when \
+	using PHP, though.)<br> \
+	Check out the <code>contrib/scriptname</code> \
+	directory for a small example. Note that this \
+	attribute also affects the value of the <a \
+	href=\"hts_templates.html#CGI\">CGI</a> variable \
+	used in htsearch templates. \
+" }, \
+{ "search_algorithm", "exact:1",  \
+	"string list", "htsearch", "", "all", "Searching:Method", "search_algorithm: exact:1 soundex:0.3", " \
+			Specifies the search algorithms and their weight to use \
+			when searching. Each entry in the list consists of the \
+			algorithm name, followed by a colon (:) followed by a \
+			weight multiplier. The multiplier is a floating point \
+			number between 0 and 1. Note that depending on your \
+			<a href=\"#locale\">locale</a> setting, and whether your \
+			system's locale implementation affects floating point \
+			input, you may need to specify the decimal point as a \
+			comma rather than a period.<br> \
+			<strong>Note:</strong>If the exact  \
+			method is not listed, the search may not work since the  \
+			original terms will not be used.<br> \
+			Current algorithms supported are: \
+			<dl> \
+			  <dt> \
+				exact \
+			  </dt> \
+			  <dd> \
+				The default exact word matching algorithm. This \
+				will find only exactly matched words. \
+			  </dd> \
+			  <dt> \
+				soundex \
+			  </dt> \
+			  <dd> \
+				Uses a slightly modified <a href=\"http://www.sog.org.uk/cig/vol6/605tdrake.pdf\">soundex</a> algorithm to match \
+				words. This requires that the soundex database be \
+				present. It is generated with the \
+				<a href=\"htfuzzy.html\">htfuzzy</a> program. \
+			  </dd> \
+			  <dt> \
+				metaphone \
+			  </dt> \
+			  <dd> \
+				Uses the metaphone algorithm for matching words. \
+				This algorithm is more specific to the english \
+				language than soundex. It requires the metaphone \
+				database, which is generated with the <a \
+				href=\"htfuzzy.html\">htfuzzy</a> program. \
+			  </dd> \
+			  <dt> \
+				accents \
+			  </dt> \
+			  <dd> \
+				Uses the accents algorithm for matching words. \
+				This algorithm will treat all accented letters \
+				as equivalent to their unaccented counterparts. \
+				It requires the accents database, which is \
+				generated with the <a \
+				href=\"htfuzzy.html\">htfuzzy</a> program. \
+			  </dd> \
+			  <dt> \
+				endings \
+			  </dt> \
+			  <dd> \
+				This algorithm uses language specific word endings \
+				to find matches. Each word is first reduced to its \
+				word root and then all known legal endings are used \
+				for the matching. This algorithm uses two databases \
+				which are generated with <a href=\"htfuzzy.html\"> \
+				htfuzzy</a>. \
+			  </dd> \
+			  <dt> \
+				synonyms \
+			  </dt> \
+			  <dd> \
+				Performs a dictionary lookup on all the words. This \
+				algorithm uses a database generated with the <a \
+				href=\"htfuzzy.html\">htfuzzy</a> program. \
+			  </dd> \
+			<dt> \
+			substring \
+			</dt> \
+			<dd> \
+			  Matches all words containing the queries as \
+			  substrings. Since this requires checking every word in \
+			  the database, this can really slow down searches \
+			  considerably. \
+			<dd> \
+			<dt> \
+			  prefix \
+			</dt> \
+			<dd> \
+			  Matches all words beginning with the query \
+			  strings. Uses the option <a \
+			  href=\"#prefix_match_character\">prefix_match_character</a> \
+			  to decide whether a query requires prefix \
+			  matching. For example \"abc*\" would perform prefix \
+			  matching on \"abc\" since * is the default \
+			  prefix_match_character. \
+			</dd> \
+			<dt> \
+			regex \
+			</dt> \
+			<dd> \
+			  Matches all words that match the patterns given as regular  \
+			  expressions. Since this requires checking every word in \
+			  the database, this can really slow down searches \
+			  considerably.  The config file used for searching \
+			  must include the regex meta-characters (^$\\[-]|.*) \
+			  included in <a href=\"#extra_word_characters\">extra_word_characters</a>, \
+			  while the config file used for digging should not.\
+			<dd> \
+			<dt> \
+			speling \
+			</dt> \
+			<dd> \
+			  A simple fuzzy algorithm that tries to find one-off spelling  \
+			  mistakes, such as transposition of two letters or an extra character. \
+			  Since this usually generates just a few possibilities, it is  \
+			  relatively quick. \
+			<dd> \
+			</dl> \
+" }, \
+{ "search_results_contenttype", "text/html",  \
+	"string", "htsearch", "", "all", "Presentation:Files", "search_results_contenttype: text/xml", " \
+	This specifies a Content-type to be output as an HTTP header \
+	at the start of search results. If set to an empty string, \
+	the Content-type header will be omitted altogether. \
+" },
+{ "search_results_footer", "${common_dir}/footer.html",  \
+	"string", "htsearch", "", "all", "Presentation:Files", "search_results_footer: /usr/local/etc/ht/end-stuff.html", " \
+			This specifies a filename to be output at the end of \
+			search results. While outputting the footer, some \
+			variables will be expanded. Variables use the same \
+			syntax as the Bourne shell. If there is a variable VAR, \
+			the following will all be recognized: \
+			<ul> \
+			  <li> \
+				$VAR \
+			  </li> \
+			  <li> \
+				$(VAR) \
+			  </li> \
+			  <li> \
+				${VAR} \
+			  </li> \
+			</ul> \
+	The following variables are available.  See \
+	<a href=\"hts_template.html\">hts_template.html</a> for a complete \
+	list. \
+			<dl> \
+			  <dt> \
+				MATCHES \
+			  </dt> \
+			  <dd> \
+				The number of documents that were matched. \
+			  </dd> \
+			  <dt> \
+				PLURAL_MATCHES \
+			  </dt> \
+			  <dd> \
+				If MATCHES is not 1, this will be the string \"s\", \
+				else it is an empty string. This can be used to say \
+				something like \"$(MATCHES) \
+				document$(PLURAL_MATCHES) were found\" \
+			  </dd> \
+			  <dt> \
+				MAX_STARS \
+			  </dt> \
+			  <dd> \
+				The value of the <a href=\"#max_stars\">max_stars</a> \
+				attribute. \
+			  </dd> \
+			  <dt> \
+				LOGICAL_WORDS \
+			  </dt> \
+			  <dd> \
+				A string of the search words with either \"and\" or \
+				\"or\" between the words, depending on the type of \
+				search. \
+			  </dd> \
+			  <dt> \
+				WORDS \
+			  </dt> \
+			  <dd> \
+				A string of the search words with spaces in \
+				between. \
+			  </dd> \
+			  <dt> \
+				PAGEHEADER \
+			  </dt> \
+			  <dd> \
+				This expands to either the value of the \
+				<a href=\"#page_list_header\">page_list_header</a> or \
+				<a href=\"#no_page_list_header\">no_page_list_header</a> \
+				attribute depending on how many pages there are. \
+			  </dd> \
+			</dl> \
+			Note that this file will <strong>NOT</strong> be output \
+			if no matches were found. In this case the \
+			<a href=\"#nothing_found_file\">nothing_found_file</a> \
+			attribute is used instead. \
+			Also, this file will not be output if it is \
+			overridden by defining the \
+			<a href=\"#search_results_wrapper\">search_results_wrapper</a> \
+			attribute. \
+" }, \
+{ "search_results_header", "${common_dir}/header.html",  \
+	"string", "htsearch", "", "all", "Presentation:Files", "search_results_header: /usr/local/etc/ht/start-stuff.html", " \
+			This specifies a filename to be output at the start of \
+			search results. While outputting the header, some \
+			variables will be expanded. Variables use the same \
+			syntax as the Bourne shell. If there is a variable VAR, \
+			the following will all be recognized: \
+			<ul> \
+			  <li> \
+				$VAR \
+			  </li> \
+			  <li> \
+				$(VAR) \
+			  </li> \
+			  <li> \
+				${VAR} \
+			  </li> \
+			</ul> \
+	The following variables are available.  See \
+	<a href=\"hts_template.html\">hts_template.html</a> for a complete \
+	list. \
+	<!-- Do these need to be listed for both _footer and _header? --> \
+			<dl> \
+			  <dt> \
+				MATCHES \
+			  </dt> \
+			  <dd> \
+				The number of documents that were matched. \
+			  </dd> \
+			  <dt> \
+				PLURAL_MATCHES \
+			  </dt> \
+			  <dd> \
+				If MATCHES is not 1, this will be the string \"s\", \
+				else it is an empty string. This can be used to say \
+				something like \"$(MATCHES) \
+				document$(PLURAL_MATCHES) were found\" \
+			  </dd> \
+			  <dt> \
+				MAX_STARS \
+			  </dt> \
+			  <dd> \
+				The value of the <a href=\"#max_stars\">max_stars</a> \
+				attribute. \
+			  </dd> \
+			  <dt> \
+				LOGICAL_WORDS \
+			  </dt> \
+			  <dd> \
+				A string of the search words with either \"and\" or \
+				\"or\" between the words, depending on the type of \
+				search. \
+			  </dd> \
+			  <dt> \
+				WORDS \
+			  </dt> \
+			  <dd> \
+				A string of the search words with spaces in \
+				between. \
+			  </dd> \
+			</dl> \
+			Note that this file will <strong>NOT</strong> be output \
+			if no matches were found. In this case the \
+			<a href=\"#nothing_found_file\">nothing_found_file</a> \
+			attribute is used instead. \
+			Also, this file will not be output if it is \
+			overridden by defining the \
+			<a href=\"#search_results_wrapper\">search_results_wrapper</a> \
+			attribute. \
+" }, \
+{ "search_results_order", "", \
+	"string list", "htsearch", "", "3.2.0b2", "Searching:Ranking", "search_results_order:  \
+	 /docs/|faq.html * /maillist/ /testresults/", " \
+	This specifies a list of patterns for URLs in \
+	search results.  Results will be displayed in the \
+	specified order, with the search algorithm result \
+	as the second order.  Remaining areas, that do not \
+	match any of the specified patterns, can be placed \
+	by using * as the pattern.  If no * is specified, \
+	one will be implicitly placed at the end of the \
+	list.<br> \
+	See also <a href=\"#url_seed_score\">url_seed_score</a>. \
+" }, \
+{ "search_results_wrapper", "",  \
+	"string", "htsearch", "", "3.1.0", "Presentation:Files", "search_results_wrapper: ${common_dir}/wrapper.html", " \
+	This specifies a filename to be output at the start and \
+	end of search results. This file replaces the \
+	<a href=\"#search_results_header\">search_results_header</a> and \
+	<a href=\"#search_results_footer\">search_results_footer</a> \
+	files, with the contents of both in one file, and uses the \
+	pseudo-variable <strong>$(HTSEARCH_RESULTS)</strong> as a \
+	separator for the header and footer sections. \
+	If the filename is not specified, the file is unreadable, \
+	or the pseudo-variable above is not found, htsearch reverts \
+	to the separate header and footer files instead. \
+	While outputting the wrapper, \
+	some variables will be expanded, just as for the \
+	<a href=\"#search_results_header\">search_results_header</a> and \
+	<a href=\"#search_results_footer\">search_results_footer</a> \
+	files.<br> \
+	Note that this file will <strong>NOT</strong> be output \
+	if no matches were found. In this case the \
+	<a href=\"#nothing_found_file\">nothing_found_file</a> \
+	attribute is used instead. \
+" }, \
+{ "search_rewrite_rules", "",
+	"string list", "htsearch", "", "3.1.6", "URLs", "search_rewrite_rules: http://(.*)\\\\.mydomain\\\\.org/([^/]*)  http://\\\\2.\\\\1.com \\<br> \
+	       http://www\\\\.myschool\\\\.edu/myorgs/([^/]*)  http://\\\\1.org", " \
+	This is a list of pairs, <em>regex</em> <em>replacement</em>, used \
+	to rewrite URLs in the search results. The left hand string is a \
+	regular expression; the right hand string is a literal string with \
+	embedded placeholders for fragments that matched inside brackets in \
+	the regular expression. \\0 is the whole matched string, \\1 to \\9 \
+	are bracketted substrings. The backslash must be doubled-up in the \
+	attribute setting to get past the variable expansion parsing. Rewrite \
+	rules are applied sequentially to each URL before it is displayed \
+	or checked against the <a href=\"#restrict\">restrict</a> or \
+	<a href=\"#exclude\">exclude</a> lists. Rewriting does not stop once a \
+	match has been made, so multiple rules may affect a given URL. See \
+	also <a href=\"#url_part_aliases\">url_part_aliases</a> which allows \
+	URLs to be of one form during indexing and translated for results, \
+	and <a href=\"#url_rewrite_rules\">url_rewrite_rules</a> which allows \
+	URLs to be rewritten while indexing. \
+" },
+{ "server_aliases", "",  \
+	"string list", "htdig", "", "3.1.0b2", "Indexing:Where", "server_aliases: \
+				  foo.mydomain.com:80=www.mydomain.com:80 \\<br> \
+				  bar.mydomain.com:80=www.mydomain.com:80 \
+", " \
+	This attribute tells the indexer that servers have several \
+	DNS aliases, which all point to the same machine and are NOT \
+	virtual hosts. This allows you to ensure pages are indexed \
+	only once on a given machine, despite the alias used in a URL. \
+	As shown in the example, the mapping goes from left to right, \
+	so the server name on the right hand side is the one that is \
+	used. As of version 3.1.3, the port number is optional, and is \
+	assumed to be 80 if omitted. There is no easy way to map all \
+	ports from one alias to another without listing them all. \
+" }, \
+{ "server_max_docs", "-1",  \
+	"integer", "htdig", "Server", "3.1.0b3", "Indexing:Where", "server_max_docs: 50", " \
+	This attribute tells htdig to limit the dig to retrieve a maximum \
+	number of documents from each server. This can cause \
+	unusual behavior on update digs since the old URLs are \
+	stored alphabetically. Therefore, update digs will add \
+	additional URLs in pseudo-alphabetical order, up to the \
+	limit of the attribute. However, it is most useful to \
+	partially index a server as the URLs of additional \
+	documents are entered into the database, marked as never \
+	retrieved.<br> \
+	A value of -1 specifies no limit. \
+" }, \
+{ "server_wait_time", "0",  \
+	"integer", "htdig", "Server", "3.1.0b3", "Indexing:Connection", "server_wait_time: 20", " \
+	This attribute tells htdig to ensure a server has had a \
+	delay (in seconds) from the beginning of the last \
+	connection. This can be used to prevent \"server abuse\" \
+	by digging without delay. It's recommended to set this \
+	to 10-30 (seconds) when indexing servers that you don't \
+	monitor yourself. Additionally, this attribute can slow \
+	down local indexing if set, which may or may not be what \
+	you intended. \
+" }, \
+{ "sort", "score",  \
+	"string", "htsearch", "", "3.1.0", "Presentation:How", "sort: revtime", " \
+	This is the default sorting method that htsearch \
+	uses to determine the order in which matches are displayed. \
+	The valid choices are: \
+	<table border=\"0\"> \
+	<tr> \
+	<td> \
+	<ul> \
+	     <li> score </li> \
+	     <li> time </li> \
+	     <li> title </li> \
+	</ul> \
+	</td> \
+	<td> \
+	<ul> \
+	     <li> revscore </li> \
+	     <li> revtime </li> \
+	     <li> revtitle </li> \
+	</ul> \
+	</td> \
+	</tr> \
+	</table> \
+	This attribute will only be used if the HTML form that \
+	calls htsearch didn't have the <strong>sort</strong> \
+	value set. The words date and revdate can be used instead \
+	of time and revtime, as both will sort by the time that \
+	the document was last modified, if this information is \
+	given by the server. The default is to sort by the score, \
+	which ranks documents by best match. The sort methods that \
+	begin with \"rev\" simply reverse the order of the \
+	sort. Note that setting this to something other than \
+	\"score\" will incur a slowdown in searches. \
+" }, \
+{ "sort_names", "score Score time Time title Title revscore 'Reverse Score' revtime 'Reverse Time' revtitle 'Reverse Title'",  \
+	"quoted string list", "htsearch", "", "3.1.0", "Searching:UI", "sort_names: \
+				  score 'Best Match' time Newest title A-Z \\<br> \
+				  revscore 'Worst Match' revtime Oldest revtitle Z-A \
+", " \
+	These values are used to create the <strong> \
+	sort</strong> menu. It consists of pairs. The first \
+	element of each pair is one of the known sort methods, the \
+	second element is the text that will be shown in the \
+	menu for that sort method. This text needs to be quoted if \
+	it contains spaces. \
+	See the <a href=\"hts_selectors.html\">select list documentation</a> \
+	for more information on how this attribute is used. \
+" }, \
+{ "soundex_db", "${database_base}.soundex.db",  \
+	"string", "htfuzzy htsearch", "", "all", "File Layout", "soundex_db: ${database_base}.snd.db", " \
+	The database file used for the fuzzy \"soundex\" search \
+	algorithm. This database is created by \
+	<a href=\"htfuzzy.html\">htfuzzy</a> and used by \
+	<a href=\"htsearch.html\" target=\"_top\">htsearch</a>. \
+" }, \
+{ "star_blank", "${image_url_prefix}/star_blank.gif",  \
+	"string", "htsearch", "", "all", "Presentation:Text", "star_blank: http://www.somewhere.org/icons/noelephant.gif", " \
+	This specifies the URL to use to display a blank of the \
+	same size as the star defined in the \
+	<a href=\"#star_image\">star_image</a> attribute or in the \
+	<a href=\"#star_patterns\">star_patterns</a> attribute. \
+" }, \
+{ "star_image", "${image_url_prefix}/star.gif",  \
+	"string", "htsearch", "", "all", "Presentation:Text", "star_image: http://www.somewhere.org/icons/elephant.gif", " \
+	This specifies the URL to use to display a star. This \
+	allows you to use some other icon instead of a star. \
+	(We like the star...)<br> \
+	The display of stars can be turned on or off with the \
+	<em><a href=\"#use_star_image\">use_star_image</a></em> \
+	attribute and the maximum number of stars that can be \
+	displayed is determined by the \
+	<em><a href=\"#max_stars\">max_stars</a></em> attribute.<br> \
+	Even though the image can be changed, the ALT value \
+	for the image will always be a '*'. \
+" }, \
+{ "star_patterns", "",  \
+	"string list", "htsearch", "", "3.0", "Presentation:How", "star_patterns: \
+				  http://www.sdsu.edu /sdsu.gif \\<br> \
+				  http://www.ucsd.edu /ucsd.gif \
+", " \
+	This attribute allows the star image to be changed \
+	depending on the URL or the match it is used for. This \
+	is mainly to make a visual distinction between matches \
+	on different web sites. The star image could be \
+	replaced with the logo of the company the match refers \
+	to.<br> \
+	It is advisable to keep all the images the same size \
+	in order to line things up properly in a short result \
+	listing.<br> \
+	The format is simple. It is a list of pairs. The first \
+	element of each pair is a pattern, the second element \
+	is a URL to the image for that pattern. \
+" }, \
+{ "startday", "",  \
+	"integer", "htsearch", "", "3.1.6", "Searching:Method", "startday: 1", " \
+	Day component of first date allowed as last-modified date \
+	of returned docutments. \
+	This is most usefully specified as a \
+	<a href=\"hts_form.html#startyear\">GCI argument</a>. \
+	See also <a href=\"#startyear\">startyear</a>. \
+" }, \
+{ "start_ellipses", "<strong><code>... </code></strong>",  \
+	"string", "htsearch", "", "all", "Presentation:Text", "start_ellipses: ...", " \
+	When excerpts are displayed in the search output, this \
+	string will be prepended to the excerpt if there is \
+	text before the text displayed. This is just a visual \
+	reminder to the user that the excerpt is only part of \
+	the complete document. \
+" }, \
+{ "start_highlight", "<strong>",  \
+	"string", "htsearch", "", "3.1.4", "Presentation:Text", "start_highlight: &lt;font color=\"#FF0000\"&gt;", " \
+	When excerpts are displayed in the search output, matched \
+	words will be highlighted using this string and \
+	<a href=\"#end_highlight\"> end_highlight</a>. \
+	You should ensure that highlighting tags are balanced, \
+	that is, any formatting tags that this string \
+	opens should be closed by end_highlight. \
+" }, \
+{ "startmonth", "",  \
+	"integer", "htsearch", "", "3.1.6", "Searching:Method", "startmonth: 1", " \
+	Month component of first date allowed as last-modified date \
+	of returned docutments. \
+	This is most usefully specified as a \
+	<a href=\"hts_form.html#startyear\">GCI argument</a>. \
+	See also <a href=\"#startyear\">startyear</a>. \
+" }, \
+{ "start_url", "http://www.htdig.org/",  \
+	"string list", "htdig", "", "all", "Indexing:Where", "start_url: http://www.somewhere.org/alldata/index.html", " \
+	This is the list of URLs that will be used to start a \
+	dig when there was no existing database. Note that \
+	multiple URLs can be given here. \
+	<br>Note also that the value of <em>start_url</em> \
+	will be the default value for \
+	<a href=\"#limit_urls_to\">limit_urls_to</a>, so if \
+	you set start_url to the URLs for specific files, \
+	rather than a site or subdirectory URL, you may need \
+	to set limit_urls_to to something less restrictive \
+	so htdig doesn't reject links in the documents. \
+" }, \
+{ "startyear", "",  \
+	"integer", "htsearch", "", "3.1.6", "Searching:Method", "startyear: 2001", " \
+	This specifies the year of the cutoff start date for \
+	search results. If the start or end date are specified, \
+	only results with a last modified date within this \
+	range are shown. If a start or end date is specified, but startyear \
+	is not, then it defaults to 1970. \
+	See also <a href=\"#startday\">startday</a>, \
+	<a href=\"#startmonth\">startmonth</a>, \
+	<a href=\"#endday\">endday</a>, \
+	<a href=\"#endmonth\">endmonth</a>, \
+	<a href=\"#endyear\">endyear</a>. \
+	These are most usefully specified as a \
+	<a href=\"hts_form.html#startyear\">GCI argument</a>.<br> \
+	For each component, if a negative number is given, \
+	it is taken as relative to the current date. \
+	Relative days can span several months or even years if desired, \
+	and relative months can span several years. A startday of \
+	-90 will select matching documents modified within \
+	the last 90 days. \
+" }, \
+{ "store_phrases", "true",  \
+	"boolean", "htdig", "", "3.2.0b5", "Indexing:How", "startyear: false", " \
+	Causes htdig to record all occurrences of each word in a document, \
+	to allow accurate phrase searches.  If this is false, only the first \
+	occurrence of each word will be stored, causing many phrases to be \
+	missed. Setting this false increases indexing speed by about 20%, \
+	and reduces disk requirements by about 60%.\
+" }, \
+{ "substring_max_words", "25",  \
+	"integer", "htsearch", "", "3.0.8b1", "Searching:Method", "substring_max_words: 100", " \
+	The Substring <a href=\"#search_algorithm\">fuzzy algorithm</a> \
+	could potentially match a \
+	very large number of words. This value limits the \
+	number of words each substring pattern can match. Note \
+	that this does not limit the number of documents that \
+	are matched in any way. \
+" }, \
+{ "synonym_db", "${common_dir}/synonyms.db",  \
+	"string", "htsearch htfuzzy", "", "3.0", "File Layout", "synonym_db: ${database_base}.syn.db", " \
+	Points to the database that <a href=\"htfuzzy.html\"> \
+	htfuzzy</a> creates when the <strong>synonyms</strong> \
+	algorithm is used.<br> \
+	<a href=\"htsearch.html\" target=\"_top\">htsearch</a> \
+	uses this to perform synonym dictionary lookups. \
+" }, \
+{ "synonym_dictionary", "${common_dir}/synonyms",  \
+	"string", "htfuzzy", "", "3.0", "File Layout", "synonym_dictionary: /usr/dict/synonyms", " \
+	This points to a text file containing the synonym \
+	dictionary used for the synonyms search algorithm.<br> \
+	Each line of this file has at least two words. The \
+	first word is the word to replace, the rest of the \
+	words are synonyms for that word. \
+" }, \
+{ "syntax_error_file", "${common_dir}/syntax.html",  \
+	"string", "htsearch", "", "all", "Presentation:Files", "syntax_error_file: ${common_dir}/synerror.html", " \
+	This points to the file which will be displayed if a \
+	boolean expression syntax error was found. \
+" }, \
+{ "tcp_max_retries", "1",  \
+	"integer", "htdig", "Server", "3.2.0b1", "Indexing:Connection", "tcp_max_retries: 6", " \
+	 This option set the maximum number of attempts when a connection \
+	 <A href=\"#timeout\">timeout</A>s. \
+	 After all these retries, the connection attempt results <timed out>. \
+" }, \
+{ "tcp_wait_time", "5",  \
+	"integer", "htdig", "Server", "3.2.0b1", "Indexing:Connection", "tcp_wait_time: 10", " \
+	 This attribute sets the wait time (in seconds) after a connection \
+	 fails and the <A href=\"#timeout\">timeout</A> is raised. \
+" }, \
+{ "template_map", "Long builtin-long builtin-long Short builtin-short builtin-short",  \
+	"quoted string list", "htsearch", "", "3.0", "Presentation:Files,Searching:UI", "template_map: \
+				  Short short ${common_dir}/short.html \\<br> \
+				  Normal normal builtin-long \\<br> \
+				  Detailed detail ${common_dir}/detail.html \
+", " \
+	This maps match template names to internal names and \
+	template file names. It is a list of triplets. The \
+	first element in each triplet is the name that will be \
+	displayed in the FORMAT menu. The second element is the \
+	name used internally and the third element is a \
+	filename of the template to use.<br> \
+	There are two predefined templates, namely <strong> \
+	builtin-long</strong> and <strong> \
+	builtin-short</strong>. If the filename is one of \
+	those, they will be used instead.<br> \
+	More information about templates can be found in the \
+	<a href=\"htsearch.html\" target=\"_top\">htsearch</a> \
+	documentation.  The particular template is selecterd by the \
+	<a href=\"hts_form.html#format\">format</a> cgi argument, and the \
+	default is given by <a href=\"#template_name\">template_name</a> in \
+	the config file. \
+" }, \
+{ "template_name", "builtin-long",  \
+	"string", "htsearch", "", "3.0", "Searching:UI,Presentation:How", "template_name: long", " \
+	Specifies the default template if no \
+	<a href=\"hts_form.html#format\">format</a> field is given by the \
+	search form. This needs to map to the \
+	<a href=\"#template_map\">template_map</a>. \
+" }, \
+{ "template_patterns", "",  \
+	"string list", "htsearch", "", "3.1.4", "Presentation:How", "template_patterns: \
+				  http://www.sdsu.edu ${common_dir}/sdsu.html \\<br> \
+				  http://www.ucsd.edu ${common_dir}/ucsd.html \
+", " \
+	This attribute allows the results template to be changed \
+	depending on the URL or the match it is used for. This \
+	is mainly to make a visual distinction between matches \
+	on different web sites. The results for each site could \
+	thus be shown in a style matching that site.<br> \
+	The format is simply a list of pairs. The first \
+	element of each pair is a pattern, the second element \
+	is the name of the template file for that pattern.<br> \
+	More information about templates can be found in the \
+	<a href=\"htsearch.html\" target=\"_top\">htsearch</a> \
+	documentation.<br> \
+	Normally, when using this template selection method, you \
+	would disable user selection of templates via the <strong>format</strong> \
+	input parameter in search forms, as the two methods were not \
+	really designed to interact. Templates selected by URL patterns \
+	would override any user selection made in the form. If you want \
+	to use the two methods together, see the notes on \
+	<a href=\"hts_selectors.html#template_patterns\">combining</a> \
+	them for an example of how to do this. \
+" }, \
+{ "text_factor", "1",  \
+	"number", "htsearch", "", "3.0", "Searching:Ranking", "text_factor: 0", " \
+	This is a factor which will be used to multiply the \
+	weight of words that are not in any special part of a \
+	document. Setting a factor to 0 will cause normal words \
+	to be ignored. The number may be a floating point \
+	number. See also the <a href=\"#heading_factor\"> heading_factor</a> \
+	attribute. \
+" }, \
+{ "timeout", "30",  \
+	"integer", "htdig", "Server", "all", "Indexing:Connection", "timeout: 42", " \
+	Specifies the time the digger will wait to complete a \
+	network read. This is just a safeguard against \
+	unforeseen things like the all too common \
+	transformation from a network to a notwork.<br> \
+	The timeout is specified in seconds. \
+" }, \
+{ "title_factor", "100",  \
+	"number", "htsearch", "", "all", "Searching:Ranking", "title_factor: 12", " \
+	This is a factor which will be used to multiply the \
+	weight of words in the title of a document. Setting a \
+	factor to 0 will cause words in the title to be \
+	ignored. The number may be a floating point number. See \
+	also the <a href=\"#heading_factor\"> \
+	heading_factor</a> attribute. \
+" }, \
+{ "translate_latin1", "true",  \
+	"boolean", "htdig htsearch", "", "3.2.0b5", "Indexing:What", "translate_latin1: false", " \
+	If set to false, the SGML entities for ISO-8859-1 (or \
+	Latin 1) characters above &amp;nbsp; (or &amp;#160;) \
+	will not be translated into their 8-bit equivalents. \
+	This attribute should be set to false when using a \
+	<a href=\"#locale\">locale</a> that doesn't use the \
+	ISO-8859-1 character set, to avoid these entities \
+	being mapped to inappropriate 8-bit characters, or \
+	perhaps more importantly to avoid 8-bit characters from \
+	your locale being mapped back to Latin 1 SGML entities \
+	in search results. \
+" }, \
+{ "url_list", "${database_base}.urls",  \
+	"string", "htdig", "", "all", "Extra Output", "url_list: /tmp/urls", " \
+	This file is only created if \
+	<em><a href=\"#create_url_list\">create_url_list</a></em> is set to \
+	true. It will contain a list of all URLs that were \
+	seen. \
+" }, \
+{ "url_log", "${database_base}.log",  \
+	"string", "htdig", "", "3.1.0", "Extra Output", "url_log: /tmp/htdig.progress", " \
+	If <a href=\"htdig.html\">htdig</a> is \
+	interrupted, it will write out its progress to this \
+	file. Note that if it has a large number of URLs to write, \
+	it may take some time to exit. This can especially happen \
+	when running update digs and the run is interrupted soon \
+	after beginning. \
+" }, \
+{ "url_part_aliases", "",  \
+	"string list", "all", "", "3.1.0", "URLs", "url_part_aliases: \
+				   http://search.example.com/~htdig *site \\<br> \
+				   http://www.htdig.org/this/ *1 \\<br> \
+				   .html *2 \
+url_part_aliases: \
+				   http://www.htdig.org/ *site \\<br> \
+				   http://www.htdig.org/that/ *1 \\<br> \
+				   .htm *2 \
+", " \
+	A list of translations pairs <em>from</em> and \
+	<em>to</em>, used when accessing the database. \
+	If a part of an URL matches with the \
+	<em>from</em>-string of each pair, it will be \
+	translated into the <em>to</em>-string just before \
+	writing the URL to the database, and translated \
+	back just after reading it from the database.<br> \
+	This is primarily used to provide an easy way to \
+	rename parts of URLs for e.g. changing \
+	www.example.com/~htdig to www.htdig.org.  Two \
+	different configuration files for digging and \
+	searching are then used, with url_part_aliases \
+	having different <em>from</em> strings, but \
+	identical <em>to</em>-strings.<br> \
+	See also <a \
+	href=\"#common_url_parts\">common_url_parts</a>.<br> \
+	Strings that are normally incorrect in URLs or \
+	very seldom used, should be used as \
+	<em>to</em>-strings, since extra storage will be \
+	used each time one is found as normal part of a \
+	URL.  Translations will be performed with priority \
+	for the leftmost longest match.	 Each \
+	<em>to</em>-string must be unique and not be a \
+	part of any other <em>to</em>-string.  It also helps \
+	to keep the <em>to</em>-strings short to save space \
+	in the database. Other than that, the choice of \
+	<em>to</em>-strings is pretty arbitrary, as they \
+	just provide a temporary, internal encoding in the \
+	databases, and none of the characters in these \
+	strings have any special meaning.<br> \
+	Note that when this attribute is changed, the \
+	database should be rebuilt, unless the effect of \
+	\"moving\" the affected URLs in the database is \
+	wanted, as described above.<br> \
+	<strong>Please note:</strong> Don't just copy the \
+	example below into a single configuration file. \
+	There are two separate settings of \
+	<em>url_part_aliases</em> below; the first one is \
+	for the configuration file to be used by htdig, \
+	htmerge, and htnotify, and the second one is for the \
+	configuration file to be used by htsearch. \
+	In this example, htdig will encode the URL \
+	\"http://search.example.com/~htdig/contrib/stuff.html\" \
+	as \"*sitecontrib/stuff*2\" in the databases, and \
+	htsearch will decode it as \
+	\"http://www.htdig.org/contrib/stuff.htm\".<br> \
+	As of version 3.1.6, you can also do more complex \
+	rewriting of URLs using \
+	<a href=\"#url_rewrite_rules\">url_rewrite_rules</a> and \
+	<a href=\"#search_rewrite_rules\">search_rewrite_rules</a>. \
+" }, \
+{ "url_rewrite_rules", "", \
+    "string list", "htdig", "", "3.2.0b3", "URLs", "url_rewrite_rules:	(.*)\\\\?JServSessionIdroot=.*		\\\\1 \\<br> \
+			(.*)\\\\&amp;JServSessionIdroot=.*		\\\\1 \\<br> \
+			(.*)&amp;context=.*				\\\\1<br>", " \
+	This is a list of pairs, <em>regex</em> <em>replacement</em> used to \
+	permanently rewrite URLs as they are indexed. The left hand string is \
+	a regular expression; the right hand string is  a literal string with \
+	embedded placeholders for fragments that matched  inside brackets in \
+	the regex. \\0 is the whole matched string, \\1 to \\9 are  bracketted \
+	substrings. Note that the <strong>entire</strong> URL is replaced by \
+	the right hand string (not just the portion which matches the left hand\
+	string).  Thus, a leading and trailing (.*) should be included in the \
+	pattern, with matching placeholders in the replacement string.<br> \
+	Rewrite rules are applied sequentially to each  \
+	incoming URL before normalization occurs. Rewriting does not stop \
+	once a match has been made, so multiple rules may affect a given URL. \
+	See also <a href=\"#url_part_aliases\">url_part_aliases</a> which \
+	allows URLs to be of one  \
+form during indexing and translated for results. \
+"}, \
+{ "url_seed_score", "", \
+    "string list", "htsearch", "", "3.2.0b2", "Searching::Ranking", "url_seed_score:  \
+	      /mailinglist/ *.5-1e6 <br> \
+	      /docs/|/news/ *1.5 <br> \
+	      /testresults/ &quot;*.7 -200&quot; <br> \
+	      /faq-area/ *2+10000", " \
+	This is a list of pairs, <em>pattern</em> \
+	<em>formula</em>, used to weigh the score of \
+	hits, depending on the URL of the document.<br> \
+	The <em>pattern</em> part is a substring to match \
+	against the URL.  Pipe ('|') characters can be \
+	used in the pattern to concatenate substrings for \
+	web-areas that have the same formula.<br> \
+	The formula describes a <em>factor</em> and a \
+	<em>constant</em>, by which the hit score is \
+	weighed.  The <em>factor</em> part is multiplied \
+	to the original score, then the <em>constant</em> \
+	part is added.<br> \
+	The format of the formula is the factor part: \
+	&quot;*<em>N</em>&quot; optionally followed by comma and \
+	spaces, followed by the constant part : \
+	&quot;+<em>M</em>&quot;, where the plus sign may be emitted \
+	for negative numbers.  Either part is optional, \
+	but must come in this order.<br> \
+	The numbers <em>N</em> and <em>M</em> are floating \
+	point constants.<br> \
+	More straightforward is to think of the format as \
+	&quot;newscore = oldscore*<em>N</em>+<em>M</em>&quot;, \
+	but with the &quot;newscore = oldscore&quot; part left out. \
+" }, \
+{ "url_text_factor", "1",  \
+	"number", "htsearch", "", "??", "Searching:Ranking", "url_text_factor: 1", " \
+	TO BE COMPLETED<br> \
+	See also <a href=\"#heading_factor\">heading_factor</a>. \
+" }, \
+{ "use_doc_date", "false",  \
+	"boolean", "htdig", "", "3.2.0b1", "Indexing:How", "use_doc_date: true", " \
+	If set to true, htdig will use META date tags in documents, \
+	overriding the modification date returned by the server. \
+	Any documents that do not have META date tags will retain \
+	the last modified date returned by the server or found on \
+	the local file system. \
+	As of version 3.1.6, in addition to META date tags, htdig will also \
+	recognize dc.date, dc.date.created and dc.date.modified. \
+" }, \
+{ "use_meta_description", "false",  \
+	"boolean", "htsearch", "", "3.1.0b1", "Presentation:How", "use_meta_description: true", " \
+	If set to true, any META description tags will be used as \
+	excerpts by htsearch. Any documents that do not have META \
+	descriptions will retain their normal excerpts. \
+" }, \
+{ "use_star_image", "true",  \
+	"boolean", "htsearch", "", "all", "Presentation:How", "use_star_image: no", " \
+	If set to true, the <em><a href=\"#star_image\"> \
+	star_image</a></em> attribute is used to display upto \
+	<em><a href=\"#max_stars\">max_stars</a></em> images for \
+	each match. \
+" }, \
+{ "user_agent", "htdig",  \
+	"string", "htdig", "Server", "3.1.0b2", "Indexing:Out", "user_agent: htdig-digger", " \
+	This allows customization of the user_agent: field sent when \
+	the digger requests a file from a server. \
+" }, \
+{ "valid_extensions", "",  \
+	"string list", "htdig", "URL", "3.1.4", "Indexing:Where", "valid_extensions: .html .htm .shtml", " \
+	This is a list of extensions on URLs which are \
+	the only ones considered acceptable. This list is used to \
+	supplement the MIME-types that the HTTP server provides \
+	with documents. Some HTTP servers do not have a correct \
+	list of MIME-types and so can advertise certain \
+	documents as text while they are some binary format. \
+	If the list is empty, then all extensions are acceptable, \
+	provided they pass other criteria for acceptance or rejection. \
+	If the list is not empty, only documents with one of the \
+	extensions in the list are parsed. \
+	See also <a href=\"#bad_extensions\">bad_extensions</a>. \
+" }, \
+{ "valid_punctuation", ".-_/!#\\$%^&'",  \
+	"string", "htdig htsearch", "", "all", "Indexing:What", "valid_punctuation: -'", " \
+	This is the set of characters which may be deleted \
+	from the document before determining what a word is. \
+	This means that if a document contains something like \
+	<code>half-hearted</code> the digger will see this as the three \
+	words <code> half</code>, <code>hearted</code> and \
+	<code>halfhearted</code>.<br> \
+	These characters are also removed before keywords are passed to the \
+	search engine, so a search for \"half-hearted\" works as expected.<br> \
+	Note that the dollar sign ($) and backslash (\\) must be escaped by a \
+	backslash in both valid_punctuation and extra_word_characters. \
+	Moreover, the backslash should not be the last character on the line. \
+	There is currently no way to include a back-quote (`) in \
+	extra_word_characters or valid_punctuation.<br> \
+	See also the \
+	<a href=\"#extra_word_characters\">extra_word_characters</a> \
+	and <a href=\"#allow_numbers\">allow_numbers</a> \
+	attributes.  \
+" }, \
+{ "version", VERSION,  \
+	"string", "htsearch", "", "all", "Presentation:Text", "version: 3.2.0", " \
+	This specifies the value of the VERSION \
+	variable which can be used in search templates. \
+	The default value of this attribute is determined \
+	at compile time, and will not normally be set \
+	in configuration files. \
+" }, \
+{ "word_db", "${database_base}.words.db",  \
+	"string", "all", "", "all", "File Layout", "word_db: ${database_base}.allwords.db", " \
+	This is the main word database. It is an index of all \
+	the words to a list of documents that contain the \
+	words. This database can grow large pretty quickly. \
+" }, \
+{ "word_dump", "${database_base}.worddump",  \
+	"string", "htdig htdump htload", "", "3.2.0b1", "File Layout", "word_dump: /tmp/words.txt", " \
+	This file is basically a text version of the file \
+	specified in <em><a href=\"#word_db\">word_db</a></em>. Its \
+	only use is to have a human readable database of all \
+	words. The file is easy to parse with tools like \
+	perl or tcl. \
+" }, \
+{ "wordlist_cache_inserts", "false",  \
+	"boolean", "???", "", "???", "Indexing:How", "wordlist_cache_inserts: true", " \
+	 If true, create a cache of size  wordlist_cache_size/2  for class \
+	 WordListOne. <em>I don't know what this is for.  Does anyone?</em> \
+" }, \
+{ "wordlist_cache_size", "10000000",  \
+	"integer", "all", "", "3.2.0b1", "Indexing:How", "wordlist_cache_size: 40000000", " \
+	Size (in bytes) of memory cache used by Berkeley DB (DB used by the indexer) \
+	IMPORTANT: It  makes a <strong>huge</strong> difference. The rule  \
+	is that the cache size should be at least 2% of the expected index size. The \
+	Berkeley DB file has 1% of internal pages that <em>must</em> be cached for good \
+	performances. Giving an additional 1% leaves room for caching leaf pages. \
+" }, \
+{ "wordlist_compress", "true",  \
+	"boolean", "all", "", "3.2.0b1", "Indexing:How", "wordlist_compress: false", " \
+	Enables or disables the default compression system for the indexer. \
+	This currently attempts to compress the index by a factor of 8. If the \
+	Zlib library is not found on the system, the default is false. \
+" }, \
+{ "wordlist_compress_zlib", "true",  \
+	"boolean", "all", "", "3.2.0b4", "Indexing:How", "wordlist_compress_zlib: false", " \
+	Enables or disables the zlib compression system for the indexer. \
+	Both <a href=\"#wordlist_compress\">wordlist_compress</a> and \
+	<a href=\"#compression_level\">compression_level</a> must be true \
+	(non-zero) to use this option!\
+" }, \
+{ "wordlist_monitor", "false", \
+	"boolean", "all", "", "3.2.0b1", "Extra Output", "wordlist_monitor: true", " \
+	This enables monitoring of what's happening in the indexer. \
+	It can help to detect performance/configuration problems. \
+" }, \
+{ "wordlist_monitor_period","0", \
+	"number", "all", "", "3.2.0b1", "Extra Output", "wordlist_monitor_period: .1", " \
+	Sets the number of seconds between each monitor output. \
+" }, \
+{ "wordlist_monitor_output","", \
+	"string", "all", "", "3.2.0b1", "Extra Output", "wordlist_monitor_output: myfile", " \
+	Print monitoring output on file instead of the default stderr. \
+" }, 
+{ "wordlist_page_size", "0",  \
+	"integer", "all", "", "3.2.0b1", "Indexing:How", "wordlist_page_size: 8192", " \
+	Size (in bytes) of pages used by Berkeley DB (DB used by the indexer). \
+	Must be a power of two. \
+" }, \
+{ "wordlist_verbose", "",  \
+	"integer", "", "", "", "", "wordlist_verbose: true", " \
+	wordlist_verbose 1 walk logic<br>    \
+	wordlist_verbose 2 walk logic details<br>    \
+	wordlist_verbose 2 walk logic lots of details<br>    \
+" }, \
+{ "wordlist_wordkey_description", "Word/DocID 32/Flags 8/Location 16", \
+	"string", "all", "", "3.2.0b1", "Indexing:How", "**this should not be configured by user**", " \
+	Internal key description: *not user configurable* \
+" }, \
+{ "wordlist_wordrecord_description", "DATA", \
+	"string", "all", "", "3.2.0b1", "Indexing:How", "**this should not be configured by user**", " \
+	Internal data description: *not user configurable* \
+" }, \
+{0, 0, 0, 0, 0, 0, 0, 0, 0}
+};
+
+HtConfiguration	config;
diff --git a/debian/htdig/htdig-3.2.0b6/htcommon/defaults.h b/debian/htdig/htdig-3.2.0b6/htcommon/defaults.h
new file mode 100644
index 00000000..35bf6da2
--- /dev/null
+++ b/debian/htdig/htdig-3.2.0b6/htcommon/defaults.h
@@ -0,0 +1,26 @@
+//
+// defaults.h
+//
+// defaults: Default configuration values for the ht programs
+//
+// Part of the ht://Dig package   <http://www.htdig.org/>
+// Copyright (c) 1995-2004 The ht://Dig Group
+// For copyright details, see the file COPYING in your distribution
+// or the GNU Library General Public License (LGPL) version 2 or later
+// <http://www.gnu.org/copyleft/lgpl.html>
+//
+// $Id: defaults.h,v 1.7 2004/05/28 13:15:13 lha Exp $
+//
+#ifndef _defaults_h_
+#define _defaults_h_
+
+#include "HtConfiguration.h"
+
+
+extern ConfigDefaults	defaults[];
+//extern HtConfiguration	config;
+
+
+#endif
+
+
diff --git a/debian/htdig/htdig-3.2.0b6/htcommon/defaults.xml b/debian/htdig/htdig-3.2.0b6/htcommon/defaults.xml
new file mode 100644
index 00000000..f3fd2eb7
--- /dev/null
+++ b/debian/htdig/htdig-3.2.0b6/htcommon/defaults.xml
@@ -0,0 +1,4379 @@
+<!DOCTYPE HtdigAttributes SYSTEM "defaults.dtd" >
+<HtdigAttributes>
+   <attribute name="accents_db" 
+              type="string" 
+              programs="htfuzzy htsearch" 
+              version="all" 
+              category="File Layout" >
+     <default>${database_base}.accents.db</default>
+     <example>${database_base}.uml.db</example>
+     <description> 
+	The database file used for the fuzzy "accents" search 
+	algorithm. This database is created by 
+	<ref type="program">htfuzzy</ref> and used by 
+	<ref type="program">htsearch</ref>. 
+     </description>
+   </attribute>
+
+   <attribute name="accept_language" 
+              type="string_list" 
+              programs="htdig" 
+              version="3.2.0b4" 
+              category="Indexing:Out" 
+              block="Server" >
+     <default></default>
+     <example>en-us en it</example>
+     <description> 
+	This attribute allows you to restrict the set of natural languages 
+	that are preferred as a response to an HTTP request performed by the 
+	digger. This can be done by putting one or more language tags 
+	(as defined by RFC 1766) in the preferred order, separated by spaces. 
+	By doing this, when the server performs a content negotiation based 
+	on the 'accept-language' given by the HTTP user agent, a different 
+	content can be shown depending on the value of this attribute. If 
+	set to an empty list, no language will be sent and the server default 
+	will be returned. 
+     </description>
+   </attribute>
+
+   <attribute name="add_anchors_to_excerpt" 
+              type="boolean" 
+              programs="htsearch" 
+              version="3.1.0" 
+              category="Presentation:How" >
+     <default>true</default>
+     <example>no</example>
+     <description> 
+	If set to true, the first occurrence of each matched 
+	word in the excerpt will be linked to the closest 
+	anchor in the document. This only has effect if the 
+	<strong>EXCERPT</strong> variable is used in the output 
+	template and the excerpt is actually going to be displayed. 
+     </description>
+   </attribute>
+
+   <attribute name="allow_double_slash" 
+              type="boolean" 
+              programs="htdig" 
+              version="3.2.0b4" 
+              category="Indexing:Out" >
+     <default>false</default>
+     <example>true</example>
+     <description> 
+	If set to true, strings of multiple slashes ('/') in URL paths 
+	will be left intact, rather than being collapsed. This is necessary 
+	for some search engine URLs which use slashes to separate fields rather 
+	than to separate directory components.  However, it can lead to multiple database 
+	entries refering to the same file, and it causes '/foo//../' to 
+	be equivalent to '/foo/', rather than to '/'. 
+     </description>
+   </attribute>
+
+   <attribute name="allow_in_form" 
+              type="string_list" 
+              programs="htsearch" 
+              version="3.1.0" 
+              category="Searching:UI" >
+     <default></default>
+     <example>search_algorithm search_results_header</example>
+     <description>	Allows the specified config file attributes to be specified
+	in search forms as separate fields. This could be used to
+	allow form writers to design their own headers and footers
+	and specify them in the search form. Another example would
+	be to offer a menu of search_algorithms in the form.
+	<codeblock>
+	&lt;SELECT NAME="search_algorithm"&gt;
+	&lt;OPTION VALUE="exact:1 prefix:0.6 synonyms:0.5 endings:0.1" SELECTED&gt;fuzzy
+	&lt;OPTION VALUE="exact:1"&gt;exact
+	&lt;/SELECT&gt;
+	</codeblock>
+	The general idea behind this is to make an input parameter out
+	of any configuration attribute that's not already automatically
+	handled by an input parameter. You can even make up your own
+	configuration attribute names, for purposes of passing data from
+	the search form to the results output. You're not restricted to
+	the existing attribute names. The attributes listed in the
+	allow_in_form list will be settable in the search form using
+	input parameters of the same name, and will be propagated to
+	the follow-up search form in the results template using template
+	variables of the same name in upper-case.
+	You can also make select lists out of any of these input
+	parameters, in the follow-up search form, using the
+	<ref type="attr">build_select_lists</ref>
+	configuration attribute.
+</description>
+   </attribute>
+
+   <attribute name="allow_numbers" 
+              type="boolean" 
+              programs="htdig htsearch" 
+              version="all" 
+              category="Indexing:What" >
+     <default>false</default>
+     <example>true</example>
+     <description> 
+	If set to true, numbers are considered words. This 
+	means that searches can be done on number as well as 
+	regular words. All the same rules apply to numbers as 
+	to words. See the description of 
+	<ref type="attr">valid_punctuation</ref> for the 
+	rules used to determine what a word is. 
+     </description>
+   </attribute>
+
+   <attribute name="allow_space_in_url" 
+              type="boolean" 
+              programs="htdig" 
+              version="3.2.0b6" 
+              category="Indexing:Where" >
+     <default>false</default>
+     <example>true</example>
+     <description> 
+	If set to true, htdig will handle URLs that contain
+	embedded spaces. Technically, this is a violation of
+	<em>RFC 2396</em>, which says spaces should be stripped out
+	(as htdig does by default).  However, many web browsers
+	and HTML code generators violate this standard already,
+	so enabling this attribute allows htdig to handle these
+	non-compliant URLs.  Even with this attribute set, htdig
+	still strips out all white space (leading, trailing and
+	embedded), except that space characters embedded within
+	the URL will be encoded as %20.
+     </description>
+   </attribute>
+
+   <attribute name="allow_virtual_hosts" 
+              type="boolean" 
+              programs="htdig" 
+              version="3.0.8b2" 
+              category="Indexing:Where" >
+     <default>true</default>
+     <example>false</example>
+     <description> 
+	If set to true, htdig will index virtual web sites as 
+	expected. If false, all URL host names will be 
+	normalized into whatever the DNS server claims the IP 
+	address to map to. If this option is set to false, 
+	there is no way to index either "soft" or "hard" 
+	virtual web sites. 
+     </description>
+   </attribute>
+
+   <attribute name="anchor_target" 
+              type="string" 
+              programs="htdig" 
+              version="3.1.6" 
+              category="Presentation:How" >
+     <default></default>
+     <example>body</example>
+     <description> 
+	When the first matched word in the excerpt is linked 
+	to the closest anchor in the document, this string 
+	can be set to specify a target in the link so the 
+	resulting page is displayed in the desired frame. 
+	This value will only be used if the 
+	<ref type="attr">add_anchors_to_excerpt</ref> 
+	attribute is set to true, the <strong>EXCERPT</strong> 
+	variable is used in the output template and the 
+	excerpt is actually displayed with a link. 
+     </description>
+   </attribute>
+
+   <attribute name="any_keywords" 
+              type="boolean" 
+              programs="htsearch" 
+              version="3.2.0b2" 
+              category="Searching:Method" >
+     <default>false</default>
+     <example>yes</example>
+     <description> 
+	If set to true, the words in the <strong>keywords</strong> 
+	input parameter in the search form will be joined with logical 
+	ORs rather than ANDs, so that any of the words provided will do. 
+	Note that this has nothing to do with limiting the search to 
+	words in META keywords tags. See the <a href="hts_form.html"> 
+	search form</a> documentation for details on this. 
+     </description>
+   </attribute>
+
+   <attribute name="author_factor" 
+              type="number" 
+              programs="htsearch" 
+              version="??" 
+              category="Searching:Ranking" >
+     <default>1</default>
+     <example>1</example>
+     <description> 
+	TO BE COMPLETED<br/> 
+	See also <ref type="attr">heading_factor</ref>. 
+     </description>
+   </attribute>
+
+   <attribute name="authorization" 
+              type="string" 
+              programs="htdig" 
+              version="3.1.4" 
+              category="Indexing:Out" 
+              block="URL" >
+     <default></default>
+     <example>mypassword</example>
+     <description> 
+	This tells htdig to send the supplied 
+	<em>username</em><strong>:</strong><em>password</em> with each HTTP request. 
+	The credentials will be encoded using the "Basic" authentication 
+	scheme. There <em>must</em> be a colon (:) between the username and 
+	password.<br/> 
+	This attribute can also be specified on htdig's command line using 
+	the -u option, and will be blotted out so it won't show up in a 
+	process listing. If you use it directly in a configuration file, 
+	be sure to protect it so it is readable only by you, and do not 
+	use that same configuration file for htsearch. 
+     </description>
+   </attribute>
+
+   <attribute name="backlink_factor" 
+              type="number" 
+              programs="htsearch" 
+              version="3.1.0" 
+              category="Searching:Ranking" >
+     <default>1000</default>
+     <example>501.1</example>
+     <description> 
+	This is a weight of "how important" a page is, based on 
+	the number of URLs pointing to it. It's actually 
+	multiplied by the ratio of the incoming URLs (backlinks) 
+	and outgoing URLs (links on the page), to balance out pages 
+	with lots of links to pages that link back to them. The ratio 
+	gives lower weight to "link farms", which often have many 
+	links to them.  This factor can 
+	be changed without changing the database in any way. 
+	However, setting this value to something other than 0 
+	incurs a slowdown on search results. 
+     </description>
+   </attribute>
+
+   <attribute name="bad_extensions" 
+              type="string_list" 
+              programs="htdig" 
+              version="all" 
+              category="Indexing:Where" 
+              block="URL" >
+     <default>.wav .gz .z .sit .au .zip .tar .hqx .exe .com .gif .jpg .jpeg .aiff .class .map .ram .tgz .bin .rpm .mpg .mov .avi .css</default>
+     <example>.foo .bar .bad</example>
+     <description> 
+	This is a list of extensions on URLs which are 
+	considered non-parsable. This list is used mainly to 
+	supplement the MIME-types that the HTTP server provides 
+	with documents. Some HTTP servers do not have a correct 
+	list of MIME-types and so can advertise certain 
+	documents as text while they are some binary format. 
+	If the list is empty, then all extensions are acceptable, 
+	provided they pass other criteria for acceptance or rejection. 
+	See also <ref type="attr">valid_extensions</ref>. 
+     </description>
+   </attribute>
+
+   <attribute name="bad_querystr" 
+              type="pattern_list" 
+              programs="htdig" 
+              version="3.1.0" 
+              category="Indexing:Where" 
+              block="URL" >
+     <default></default>
+     <example>forum=private section=topsecret&amp;passwd=required</example>
+     <description> 
+	This is a list of CGI query strings to be excluded from 
+	indexing. This can be used in conjunction with CGI-generated 
+	portions of a website to control which pages are 
+	indexed. 
+     </description>
+   </attribute>
+
+   <attribute name="bad_word_list" 
+              type="string" 
+              programs="htdig htsearch" 
+              version="all" 
+              category="Indexing:What,Searching:Method" >
+     <default>${common_dir}/bad_words</default>
+     <example>${common_dir}/badwords.txt</example>
+     <description> 
+	This specifies a file which contains words which should 
+	be excluded when digging or searching. This list should 
+	include the most common words or other words that you 
+	don't want to be able to search on (things like <em> 
+	sex</em> or <em>smut</em> are examples of these.)<br/> 
+	The file should contain one word per line. A sample 
+	bad words file is located in the <code>contrib/examples</code> 
+	directory. 
+     </description>
+   </attribute>
+
+   <attribute name="bin_dir" 
+              type="string" 
+              programs="all" 
+              version="all" 
+              category="File Layout" >
+     <default configmacro="true">BIN_DIR</default>
+     <example>/usr/local/bin</example>
+     <description> 
+	This is the directory in which the executables 
+	related to ht://Dig are installed. It is never used 
+	directly by any of the programs, but other attributes 
+	can be defined in terms of this one. 
+	<p> 
+	The default value of this attribute is determined at 
+	compile time. 
+	</p> 
+     </description>
+   </attribute>
+
+   <attribute name="boolean_keywords" 
+              type="string list" 
+              programs="htsearch" 
+              version="3.1.6" 
+	      category="Presentation:How" >
+     <default configmacro="true">and or not</default>
+     <example>et ou non</example>
+     <description> 
+	These three strings are used as the keywords used in
+	constructing the LOGICAL_WORDS template variable,
+	and in parsing the <a href="hts_form.html#words">words</a> input
+	parameter when the <a href="hts_form.html#method">method</a> parameter
+	or <ref type="attr">match_method</ref> attribute
+	is set to <code>boolean</code>.
+	See also the <ref type="attr">boolean_syntax_errors</ref> attribute.
+     </description>
+   </attribute>
+
+   <attribute name="boolean_syntax_errors" 
+              type="quoted string list" 
+              programs="htsearch" 
+              version="3.1.6" 
+	      category="Presentation:How" >
+     <default configmacro="true">Expected 'a search word, a quoted phrase, a boolean expression between ()' 'at the end' 'instead of' 'end of expression' quotes</default>
+     <example> Attendait "un mot" "&agrave; la fin" "au lieu de" "fin d'expression" "points de quotation" </example>
+     <description> 
+	These six strings are used as the keywords used to
+	construct various syntax error messages for errors encountered in
+	parsing the <a href="hts_form.html#words">words</a> input
+	parameter when the <a href="hts_form.html#method">method</a> parameter
+	or <ref type="attr">match_method</ref> attribute
+	is set to <code>boolean</code>.
+	They are used in conjunction with the
+	<ref type="attr">boolean_keywords</ref> attribute, and comprise all
+	English-specific parts of these error messages.  The order in which
+	the strings are put together may not be ideal, or even gramatically
+	correct, for all languages, but they can be used to make fairly
+	intelligible messages in many languages.
+     </description>
+   </attribute>
+
+   <attribute name="build_select_lists" 
+              type="quoted_string_list" 
+              programs="htsearch" 
+              version="3.2.0b1" 
+              category="Searching:UI" >
+     <default></default>
+     <example>MATCH_LIST matchesperpage matches_per_page_list \ 
+				1 1 1 matches_per_page "Previous Amount" \ 
+		RESTRICT_LIST,multiple restrict restrict_names 2 1 2 restrict "" \ 
+		FORMAT_LIST,radio format template_map 3 2 1 template_name ""</example>
+     <description> 
+	This list allows you to define any htsearch input parameter as 
+	a select list for use in templates, provided you also define 
+	the corresponding name list attribute which enumerates all the 
+	choices to put in the list. It can be used for existing input 
+	parameters, as well as any you define using the 
+	<ref type="attr">allow_in_form</ref> 
+	attribute. The entries in this list each consist of an octuple, 
+	a set of eight strings defining the variables and how they are to 
+	be used to build a select list. The attribute can contain many 
+	of these octuples. The strings in the string list are merely 
+	taken eight at a time. For each octuple of strings specified in 
+	build_select_lists, the elements have the following meaning:  
+	<ol> 
+	   <li>the name of the template variable to be defined as a list, 
+	   optionally followed by a comma and the type of list, and 
+	   optional formatting codes</li> 
+	   <li>the input parameter name that the select list will set</li>  
+	   <li>the name of the user-defined attribute containing the 
+	   name list</li> 
+	   <li>the tuple size used in the name list above</li>  
+	   <li>the index into a name list tuple for the value</li>  
+	   <li>the index for the corresponding label on the selector</li> 
+	   <li>the configuration attribute where the default value for 
+	   this input parameter is defined</li> 
+	   <li>the default label, if not an empty string, which will be 
+	   used as the label for an additional list item for the current 
+	   input parameter value if it doesn't match any value in the 
+	   given list</li> 
+	</ol> 
+	See the <a href="hts_selectors.html">select list documentation</a> 
+	for more information on this attribute. 
+     </description>
+   </attribute>
+
+   <attribute name="caps_factor" 
+              type="number" 
+              programs="htsearch" 
+              version="??" 
+              category="Searching:Ranking" >
+     <default>1</default>
+     <example>1</example>
+     <description> 
+	TO BE COMPLETED<br/> 
+	See also <ref type="attr">heading_factor</ref>. 
+     </description>
+   </attribute>
+
+   <attribute name="case_sensitive" 
+              type="boolean" 
+              programs="htdig" 
+              version="3.1.0b2" 
+              category="Indexing:Where" >
+     <default>true</default>
+     <example>false</example>
+     <description> 
+	This specifies whether ht://Dig should consider URLs 
+	case-sensitive or not. If your server is case-insensitive, 
+	you should probably set this to false. 
+     </description>
+   </attribute>
+
+   <attribute name="check_unique_date" 
+              type="boolean" 
+              programs="htdig" 
+              version="3.2.0b3" 
+              category="" 
+              block="Global" >
+     <default>false</default>
+     <example>false</example>
+     <description> 
+	Include the modification date of the page in the MD5 hash, to reduce the 
+	problem with identical but physically separate pages in different parts of the tree pointing to 
+	different pages.  
+     </description>
+   </attribute>
+
+   <attribute name="check_unique_md5" 
+              type="boolean" 
+              programs="htdig" 
+              version="3.2.0b3" 
+              category="" 
+              block="Global" >
+     <default>false</default>
+     <example>false</example>
+     <description> 
+	Uses the MD5 hash of pages to reject aliases, prevents multiple entries 
+	in the index caused by such things as symbolic links 
+	Note: May not do the right thing for incremental update 
+     </description>
+   </attribute>
+
+   <attribute name="collection_names" 
+              type="string_list" 
+              programs="htsearch" 
+              version="3.2.0b2" 
+              category="" >
+     <default></default>
+     <example>htdig_docs htdig_bugs</example>
+     <description> 
+	This is a list of config file names that are used for searching multiple databases. 
+	Simply put, htsearch will loop through the databases specified by each of these config 
+	files and present the result of the search on all of the databases. 
+	The corresponding config files are looked up in the <ref type="attr">config_dir</ref> directory. 
+	Each listed config file <strong>must</strong> exist, as well as the corresponding databases. 
+     </description>
+   </attribute>
+
+   <attribute name="common_dir" 
+              type="string" 
+              programs="all" 
+              version="all" 
+              category="File Layout" >
+     <default configmacro="true">COMMON_DIR</default>
+     <example>/tmp</example>
+     <description> 
+	Specifies the directory for files that will or can be 
+	shared among different search databases. The default 
+	value for this attribute is defined at compile time. 
+     </description>
+   </attribute>
+
+   <attribute name="common_url_parts" 
+              type="string_list" 
+              programs="all" 
+              version="3.1.0" 
+              category="URLs" >
+     <default>http:// http://www. ftp:// ftp://ftp. /pub/ .html .htm .gif .jpg .jpeg /index.html /index.htm .com/ .com mailto:</default>
+     <example>//www.htdig.org/ml/ \ 
+.html \ 
+http://dev.htdig.org/ \ 
+http://www.htdig.org/</example>
+     <description> 
+	Sub-strings often found in URLs stored in the 
+	database.  These are replaced in the database by an 
+	internal space-saving encoding.  If a string 
+	specified in <ref type="attr">url_part_aliases</ref>, 
+	overlaps any string in common_url_parts, the 
+	common_url_parts string is ignored.<br/> 
+	Note that when this attribute is changed, the 
+	database should be rebuilt, unless the effect of 
+	"changing" the affected URLs in the database is 
+	wanted.<br/> 
+     </description>
+   </attribute>
+
+   <attribute name="compression_level" 
+              type="integer" 
+              programs="htdig" 
+              version="3.1.0" 
+              category="Indexing:How" >
+     <default>0</default>
+     <example>6</example>
+     <description> 
+	If specified and the <a 
+	href="http://www.cdrom.com/pub/infozip/zlib/">zlib</a> 
+	compression library was available when compiled, 
+	this attribute controls 
+	the amount of compression used in the <ref type="attr">doc_excerpt</ref> file. 
+     </description>
+   </attribute>
+
+   <attribute name="config" 
+              type="string" 
+              programs="all" 
+              version="??" 
+              category="File Layout" >
+     <default configmacro="true">DEFAULT_CONFIG_FILE</default>
+     <example></example>
+     <description> 
+	Name of configuration file to load. 
+	For security reasons, restrictions are placed on the values which 
+	can be specified on the command line to 
+	<ref type="program">htsearch</ref>. 
+	The default value of this attribute is determined at 
+	compile time. 
+     </description>
+   </attribute>
+
+   <attribute name="config_dir" 
+              type="string" 
+              programs="all" 
+              version="all" 
+              category="File Layout" >
+     <default configmacro="true">CONFIG_DIR</default>
+     <example>/var/htdig/conf</example>
+     <description> 
+	This is the directory which contains all configuration 
+	files related to ht://Dig. It is never used 
+	directly by any of the programs, but other attributes 
+	or the <ref type="attr">include</ref> directive 
+	can be defined in terms of this one. 
+	<p> 
+	The default value of this attribute is determined at 
+	compile time. 
+	</p> 
+     </description>
+   </attribute>
+
+   <attribute name="cookies_input_file" 
+              type="string" 
+              programs="htdig" 
+              version="3.2.0b4" 
+              category="Indexing:Connection" >
+     <default></default>
+     <example>${common_dir}/cookies.txt</example>
+     <description> 
+	Specifies the location of the file used for importing cookies
+	for the crawl. These cookies will be preloaded into htdig's
+	in-memory cookie jar, but aren't written back to the file.
+	Cookies are specified according to Netscape's format
+	(tab-separated fields). If this attribute is left blank,
+	no cookie file will be read.
+	<p> 
+	For more information, see the sample cookies.txt file in the
+	ht://Dig source distribution.
+	</p> 
+     </description>
+   </attribute>
+
+   <attribute name="create_image_list" 
+              type="boolean" 
+              programs="htdig" 
+              version="all" 
+              category="Extra Output" >
+     <default>false</default>
+     <example>yes</example>
+     <description> 
+	If set to true, a file with all the image URLs that 
+	were seen will be created, one URL per line. This list 
+	will not be in any order and there will be lots of 
+	duplicates, so after htdig has completed, it should be 
+	piped through <code>sort -u</code> to get a unique list. 
+     </description>
+   </attribute>
+
+   <attribute name="create_url_list" 
+              type="boolean" 
+              programs="htdig" 
+              version="all" 
+              category="Extra Output" >
+     <default>false</default>
+     <example>yes</example>
+     <description> 
+	If set to true, a file with all the URLs that were seen 
+	will be created, one URL per line. This list will not 
+	be in any order and there will be lots of duplicates, 
+	so after htdig has completed, it should be piped 
+	through <code>sort -u</code> to get a unique list. 
+     </description>
+   </attribute>
+
+   <attribute name="database_base" 
+              type="string" 
+              programs="all" 
+              version="all" 
+              category="File Layout" >
+     <default>${database_dir}/db</default>
+     <example>${database_dir}/sales</example>
+     <description> 
+	This is the common prefix for files that are specific 
+	to a search database. Many different attributes use 
+	this prefix to specify filenames. Several search 
+	databases can share the same directory by just changing 
+	this value for each of the databases. 
+     </description>
+   </attribute>
+
+   <attribute name="database_dir" 
+              type="string" 
+              programs="all" 
+              version="all" 
+              category="File Layout" >
+     <default configmacro="true">DATABASE_DIR</default>
+     <example>/var/htdig</example>
+     <description> 
+	This is the directory which contains all database and 
+	other files related to ht://Dig. It is never used 
+	directly by any of the programs, but other attributes 
+	are defined in terms of this one. 
+	<p> 
+	The default value of this attribute is determined at 
+	compile time. 
+	</p> 
+     </description>
+   </attribute>
+
+   <attribute name="date_factor" 
+              type="number" 
+              programs="htsearch" 
+              version="3.1.0" 
+              category="Searching:Ranking" >
+     <default>0</default>
+     <example>0.35</example>
+     <description> 
+	This factor, gives higher 
+	rankings to newer documents and lower rankings to older 
+	documents. Before setting this factor, it's advised to 
+	make sure your servers are returning accurate dates 
+	(check the dates returned in the long format). 
+	Additionally, setting this to a nonzero value incurs a 
+	small performance hit on searching. 
+     </description>
+   </attribute>
+
+   <attribute name="date_format" 
+              type="string" 
+              programs="htsearch" 
+              version="3.1.2" 
+              category="Presentation:How" >
+     <default></default>
+     <example>%Y-%m-%d</example>
+     <description> 
+	This format string determines the output format for 
+	modification dates of documents in the search results. 
+	It is interpreted by your system's <em>strftime</em> 
+	function. Please refer to your system's manual page 
+	for this function, for a description of available 
+	format codes. If this format string is empty, as it 
+	is by default,  
+	<ref type="program">htsearch</ref> 
+	will pick a format itself. In this case, the <ref type="attr">iso_8601</ref> attribute can be used 
+	to modify the appearance of the date. 
+     </description>
+   </attribute>
+
+   <attribute name="description_factor" 
+              type="number" 
+              programs="htsearch" 
+              version="3.1.0b3" 
+              category="Searching:Ranking" >
+     <default>150</default>
+     <example>350</example>
+     <description> 
+	Plain old "descriptions" are the text of a link pointing 
+	to a document. This factor gives weight to the words of 
+	these descriptions of the document. Not surprisingly, 
+	these can be pretty accurate summaries of a document's 
+	content. See also <ref type="attr">heading_factor</ref> 
+	and <ref type="attr">meta_description_factor</ref>. 
+     </description>
+   </attribute>
+
+   <attribute name="description_meta_tag_names" 
+              type="number" 
+              programs="htsearch" 
+              version="3.1.6" 
+              category="Searching:Ranking" >
+     <default>description</default>
+     <example>"description htdig-description"</example>
+     <description> 
+	The words in this list are used to search for descriptions in HTML 
+	<em>META</em> tags. This list can contain any number of strings 
+	that each will be seen as the name for whatever description 
+	convention is used. While words in any of the specified 
+	description contents will be indexed, only the last meta tag 
+	containing a description will be kept as the meta description 
+	field for the document, for use in search results. The order in 
+	which the names are specified in this configuration attribute 
+	is irrelevant, as it is the order in which the tags appear in 
+	the documents that matters.<br/> The <em>META</em> tags have the 
+	following format:<br/> 
+	<code>   &lt;META name="<em>somename</em>" 
+	                       content="<em>somevalue</em>"&gt; </code><br/> 
+	See also <ref type="attr">meta_description_factor</ref>. 
+     </description>
+   </attribute>
+
+   <attribute name="disable_cookies" 
+              type="boolean" 
+              programs="htdig" 
+              version="3.2.0b4" 
+              category="Indexing:Connection" 
+              block="Server" >
+     <default>true</default>
+     <example>true</example>
+     <description> 
+        This option, if set to true, will disable HTTP cookies. 
+     </description>
+   </attribute>
+
+   <attribute name="doc_db" 
+              type="string" 
+              programs="all" 
+              version="all" 
+              category="File Layout" >
+     <default>${database_base}.docdb</default>
+     <example>${database_base}documents.db</example>
+     <description> 
+	This file will contain a Berkeley database of documents 
+	indexed by document number. It contains all the information 
+	gathered for each document, except the document excerpts 
+	which are stored in the <ref type="attr">doc_excerpt</ref> file. 
+     </description>
+   </attribute>
+
+   <attribute name="doc_excerpt" 
+              type="string" 
+              programs="all" 
+              version="3.2.0b1" 
+              category="File Layout" >
+     <default>${database_base}.excerpts</default>
+     <example>${database_base}excerpts.db</example>
+     <description> 
+	This file will contain a Berkeley database of document excerpts 
+	indexed by document number. It contains all the text 
+	gathered for each document, so this file can become 
+	rather large if <ref type="attr">max_head_length</ref> is set to a large value. 
+	The size can be reduced by setting the 
+	<ref type="attr">compression_level</ref>, 
+	if supported on your system. 
+     </description>
+   </attribute>
+
+   <attribute name="doc_index" 
+              type="string" 
+              programs="htdig" 
+              version="all" 
+              category="File Layout" >
+     <default>${database_base}.docs.index</default>
+     <example>documents.index.db</example>
+     <description> 
+	This file contains a mapping of document numbers to URLs and is 
+	used by htdig during indexing. It is used on updates if it exists. 
+     </description>
+   </attribute>
+
+   <attribute name="doc_list" 
+              type="string" 
+              programs="htdig htdump htload" 
+              version="all" 
+              category="File Layout" >
+     <default>${database_base}.docs</default>
+     <example>/tmp/documents.text</example>
+     <description> 
+	This file is basically a text version of the file 
+	specified in <ref type="attr">doc_db</ref>. Its 
+	only use is to have a human readable database of all 
+	documents. The file is easy to parse with tools like 
+	perl or tcl. 
+     </description>
+   </attribute>
+
+   <attribute name="endday" 
+              type="integer" 
+              programs="htsearch" 
+              version="3.1.6" 
+              category="Searching:Method" >
+     <default></default>
+     <example>31</example>
+     <description> 
+	Day component of last date allowed as last-modified date 
+	of returned docutments. 
+	This is most usefully specified as a 
+	<a href="hts_form.html#startyear">GCI argument</a>. 
+	See also <ref type="attr">startyear</ref>. 
+     </description>
+   </attribute>
+
+   <attribute name="end_ellipses" 
+              type="string" 
+              programs="htsearch" 
+              version="all" 
+              category="Presentation:Text" >
+     <default>&lt;strong&gt;&lt;code&gt; ...&lt;/code&gt;&lt;/strong&gt;</default>
+     <example>...</example>
+     <description> 
+	When excerpts are displayed in the search output, this 
+	string will be appended to the excerpt if there is text 
+	following the text displayed. This is just a visual 
+	reminder to the user that the excerpt is only part of 
+	the complete document. 
+     </description>
+   </attribute>
+
+   <attribute name="end_highlight" 
+              type="string" 
+              programs="htsearch" 
+              version="3.1.4" 
+              category="Presentation:Text" >
+     <default>&lt;/strong&gt;</default>
+     <example>&lt;/font&gt;</example>
+     <description> 
+	When excerpts are displayed in the search output, matched 
+	words will be highlighted using <ref type="attr">start_highlight</ref> and this string. 
+	You should ensure that highlighting tags are balanced, 
+	that is, this string should close any formatting 
+	tag opened by start_highlight. 
+     </description>
+   </attribute>
+
+   <attribute name="endings_affix_file" 
+              type="string" 
+              programs="htfuzzy" 
+              version="all" 
+              category="File Layout" >
+     <default>${common_dir}/english.aff</default>
+     <example>/var/htdig/affix_rules</example>
+     <description> 
+	Specifies the location of the file which contains the 
+	affix rules used to create the endings search algorithm 
+	databases. Consult the documentation on 
+	<ref type="program">htfuzzy</ref> for more information on the 
+	format of this file. 
+     </description>
+   </attribute>
+
+   <attribute name="endings_dictionary" 
+              type="string" 
+              programs="htfuzzy" 
+              version="all" 
+              category="File Layout" >
+     <default>${common_dir}/english.0</default>
+     <example>/var/htdig/dictionary</example>
+     <description> 
+	Specifies the location of the file which contains the 
+	dictionary used to create the endings search algorithm 
+	databases. Consult the documentation on 
+	<ref type="program">htfuzzy</ref> for more information on the 
+	format of this file. 
+     </description>
+   </attribute>
+
+   <attribute name="endings_root2word_db" 
+              type="string" 
+              programs="htfuzzy htsearch" 
+              version="all" 
+              category="File Layout" >
+     <default>${common_dir}/root2word.db</default>
+     <example>/var/htdig/r2w.db</example>
+     <description> 
+	This attributes specifies the database filename to be 
+	used in the 'endings' fuzzy search algorithm. The 
+	database maps word roots to all legal words with that 
+	root. For more information about this and other fuzzy 
+	search algorithms, consult the 
+	<ref type="program">htfuzzy</ref> documentation.<br/> 
+	Note that the default value uses the 
+	<ref type="attr">common_dir</ref> attribute instead of the 
+	<ref type="attr">database_dir</ref> attribute. 
+	This is because this database can be shared with 
+	different search databases. 
+     </description>
+   </attribute>
+
+   <attribute name="endings_word2root_db" 
+              type="string" 
+              programs="htfuzzy htsearch" 
+              version="all" 
+              category="File Layout" >
+     <default>${common_dir}/word2root.db</default>
+     <example>/var/htdig/w2r.bm</example>
+     <description> 
+	This attributes specifies the database filename to be 
+	used in the 'endings' fuzzy search algorithm. The 
+	database maps words to their root. For more information 
+	about this and other fuzzy search algorithms, consult 
+	the <ref type="program">htfuzzy</ref> 
+	documentation.<br/> 
+	Note that the default value uses the 
+	<ref type="attr">common_dir</ref> attribute instead of the 
+	<ref type="attr">database_dir</ref> attribute. 
+	This is because this database can be shared with 
+	different search databases. 
+     </description>
+   </attribute>
+
+   <attribute name="endmonth" 
+              type="integer" 
+              programs="htsearch" 
+              version="3.1.6" 
+              category="Searching:Method" >
+     <default></default>
+     <example>12</example>
+     <description> 
+	Month component of last date allowed as last-modified date 
+	of returned docutments. 
+	This is most usefully specified as a 
+	<a href="hts_form.html#startyear">GCI argument</a>. 
+	See also <ref type="attr">startyear</ref>. 
+     </description>
+   </attribute>
+
+   <attribute name="endyear" 
+              type="integer" 
+              programs="htsearch" 
+              version="3.1.6" 
+              category="Searching:Method" >
+     <default></default>
+     <example>2002</example>
+     <description> 
+	Year component of last date allowed as last-modified date 
+	of returned docutments. 
+	This is most usefully specified as a 
+	<a href="hts_form.html#startyear">GCI argument</a>. 
+	See also <ref type="attr">startyear</ref>. 
+     </description>
+   </attribute>
+
+   <attribute name="excerpt_length" 
+              type="integer" 
+              programs="htsearch" 
+              version="all" 
+              category="Presentation:How" >
+     <default>300</default>
+     <example>500</example>
+     <description> 
+	This is the maximum number of characters the displayed 
+	excerpt will be limited to. The first matched word will 
+	be highlighted in the middle of the excerpt so that there is 
+	some surrounding context.<br/> 
+	The <ref type="attr">start_ellipses</ref> and 
+	<ref type="attr">end_ellipses</ref> are used to 
+	indicate that the document contains text before and 
+	after the displayed excerpt respectively. 
+	The <ref type="attr">start_highlight</ref> and 
+	<ref type="attr">end_highlight</ref> are used to 
+	specify what formatting tags are used to highlight matched words. 
+     </description>
+   </attribute>
+
+   <attribute name="excerpt_show_top" 
+              type="boolean" 
+              programs="htsearch" 
+              version="all" 
+              category="Presentation:How" >
+     <default>false</default>
+     <example>yes</example>
+     <description> 
+	If set to true, the excerpt of a match will always show 
+	the top of the matching document. If it is false (the 
+	default), the excerpt will attempt to show the part of 
+	the document that actually contains one of the words. 
+     </description>
+   </attribute>
+
+   <attribute name="exclude" 
+              type="pattern_list" 
+              programs="htsearch" 
+              version="3.2.0b4" 
+              category="Searching:Method" >
+     <default></default>
+     <example>myhost.com/mailarchive/</example>
+     <description> 
+	If a URL contains any of the space separated patterns, it will be 
+	discarded in the searching phase. This is used to exclude certain 
+	URLs from search results. The list can be specified from within 
+	the configuration file, and can be overridden with the "exclude" 
+	input parameter in the search form. 
+     </description>
+   </attribute>
+
+   <attribute name="exclude_urls" 
+              type="pattern_list" 
+              programs="htdig" 
+              version="all" 
+              category="Indexing:Where" 
+              block="URL" >
+     <default>/cgi-bin/ .cgi</default>
+     <example>students.html cgi-bin</example>
+     <description> 
+	If a URL contains any of the space separated patterns, 
+	it will be rejected. This is used to exclude such 
+	common things such as an infinite virtual web-tree 
+	which start with cgi-bin. 
+     </description>
+   </attribute>
+
+   <attribute name="external_parsers" 
+              type="quoted_string_list" 
+              programs="htdig" 
+              version="3.0.7" 
+              category="External:Parsers" >
+     <default></default>
+     <example>text/html /usr/local/bin/htmlparser \ 
+	application/pdf /usr/local/bin/parse_doc.pl \ 
+	application/msword-&gt;text/plain "/usr/local/bin/mswordtotxt -w" \ 
+	application/x-gunzip-&gt;user-defined /usr/local/bin/ungzipper</example>
+     <description> 
+			This attribute is used to specify a list of 
+			content-type/parsers that are to be used to parse 
+			documents that cannot by parsed by any of the internal 
+			parsers. The list of external parsers is examined 
+			before the builtin parsers are checked, so this can be 
+			used to override the internal behavior without 
+			recompiling htdig.<br/> 
+			 The external parsers are specified as pairs of 
+			strings. The first string of each pair is the 
+			content-type that the parser can handle while the 
+			second string of each pair is the path to the external 
+			parsing program. If quoted, it may contain parameters, 
+			separated by spaces.<br/> 
+			 External parsing can also be done with external 
+			converters, which convert one content-type to 
+			another. To do this, instead of just specifying 
+			a single content-type as the first string 
+			of a pair, you specify two types, in the form 
+			<em>type1</em><strong>-&gt;</strong><em>type2</em>, 
+			as a single string with no spaces. The second 
+			string will define an external converter 
+			rather than an external parser, to convert 
+			the first type to the second. If the second 
+			type is <strong>user-defined</strong>, then 
+			it's up to the converter script to put out a 
+			"Content-Type: <em>type</em>" header followed 
+			by a blank line, to indicate to htdig what type it 
+			should expect for the output, much like what a CGI 
+			script would do. The resulting content-type must 
+			be one that htdig can parse, either internally, 
+			or with another external parser or converter.<br/> 
+			 Only one external parser or converter can be 
+			specified for any given content-type. However, 
+			an external converter for one content-type can be 
+			chained to the internal parser for the same type, 
+			by appending <strong>-internal</strong> to the 
+			second type string (e.g. text/html-&gt;text/html-internal) 
+			to perform external preprocessing on documents of 
+			this type before internal parsing. 
+			There are two internal parsers, for text/html and 
+			text/plain.<p> 
+			 The parser program takes four command-line 
+			parameters, not counting any parameters already 
+			given in the command string:<br/> 
+			<em>infile content-type URL configuration-file</em><br/> 
+			</p>
+<table border="1"> 
+			  <tr> 
+				<th> 
+				  Parameter 
+				</th> 
+				<th> 
+				  Description 
+				</th> 
+				<th> 
+				  Example 
+				</th> 
+			  </tr> 
+			  <tr> 
+				<td valign="top"> 
+				  infile 
+				</td> 
+				<td> 
+				  A temporary file with the contents to be parsed. 
+				</td> 
+				<td> 
+				  /var/tmp/htdext.14242 
+				</td> 
+			  </tr> 
+			  <tr> 
+				<td valign="top"> 
+				  content-type 
+				</td> 
+				<td> 
+				  The MIME-type of the contents. 
+				</td> 
+				<td> 
+				  text/html 
+				</td> 
+			  </tr> 
+			  <tr> 
+				<td valign="top"> 
+				  URL 
+				</td> 
+				<td> 
+				  The URL of the contents. 
+				</td> 
+				<td> 
+				  http://www.htdig.org/attrs.html 
+				</td> 
+			  </tr> 
+			  <tr> 
+				<td valign="top"> 
+				  configuration-file 
+				</td> 
+				<td> 
+				  The configuration-file in effect. 
+				</td> 
+				<td> 
+				  /etc/htdig/htdig.conf 
+				</td> 
+			  </tr> 
+			</table><p> 
+			The external parser is to write information for 
+			htdig on its standard output. Unless it is an 
+			external converter, which will output a document 
+			of a different content-type, then its output must 
+			follow the format described here.<br/> 
+			 The output consists of records, each record terminated 
+			with a newline. Each record is a series of (unless 
+			expressively allowed to be empty) non-empty tab-separated 
+			fields. The first field is a single character 
+			that specifies the record type. The rest of the fields 
+			are determined by the record type. 
+			</p>
+<table border="1"> 
+			  <tr> 
+				<th> 
+				  Record type 
+				</th> 
+				<th> 
+				  Fields 
+				</th> 
+				<th> 
+				  Description 
+				</th> 
+			  </tr> 
+			  <tr> 
+				<th rowspan="3" valign="top"> 
+				  w 
+				</th> 
+				<td valign="top"> 
+				  word 
+				</td> 
+				<td> 
+				  A word that was found in the document. 
+				</td> 
+			  </tr> 
+			  <tr> 
+				<td valign="top"> 
+				  location 
+				</td> 
+				<td> 
+				  A number indicating the normalized location of 
+				  the word within the document. The number has to 
+				  fall in the range 0-1000 where 0 means the top of 
+				  the document. 
+				</td> 
+			  </tr> 
+			  <tr> 
+				<td valign="top"> 
+				  heading level 
+				</td> 
+				<td> 
+				  A heading level that is used to compute the 
+				  weight of the word depending on its context in 
+				  the document itself. The level is in the range of 
+				  0-10 and are defined as follows: 
+				  <dl compact="true"> 
+					<dt> 
+					  0 
+					</dt> 
+					<dd> 
+					  Normal text 
+					</dd> 
+					<dt> 
+					  1 
+					</dt> 
+					<dd> 
+					  Title text 
+					</dd> 
+					<dt> 
+					  2 
+					</dt> 
+					<dd> 
+					  Heading 1 text 
+					</dd> 
+					<dt> 
+					  3 
+					</dt> 
+					<dd> 
+					  Heading 2 text 
+					</dd> 
+					<dt> 
+					  4 
+					</dt> 
+					<dd> 
+					  Heading 3 text 
+					</dd> 
+					<dt> 
+					  5 
+					</dt> 
+					<dd> 
+					  Heading 4 text 
+					</dd> 
+					<dt> 
+					  6 
+					</dt> 
+					<dd> 
+					  Heading 5 text 
+					</dd> 
+					<dt> 
+					  7 
+					</dt> 
+					<dd> 
+					  Heading 6 text 
+					</dd> 
+					<dt> 
+					  8 
+					</dt> 
+					<dd> 
+					  <em>unused</em> 
+					</dd> 
+					<dt> 
+					  9 
+					</dt> 
+					<dd> 
+					  <em>unused</em> 
+					</dd> 
+					<dt> 
+					  10 
+					</dt> 
+					<dd> 
+					  Keywords 
+					</dd> 
+				  </dl> 
+				</td> 
+			  </tr> 
+			  <tr> 
+				<th rowspan="2" valign="top"> 
+				  u 
+				</th> 
+				<td valign="top"> 
+				  document URL 
+				</td> 
+				<td> 
+				  A hyperlink to another document that is 
+				  referenced by the current document.  It must be 
+				  complete and non-relative, using the URL parameter to 
+				  resolve any relative references found in the document. 
+				</td> 
+			  </tr> 
+			  <tr> 
+				<td valign="top"> 
+				  hyperlink description 
+				</td> 
+				<td> 
+				  For HTML documents, this would be the text 
+				  between the &lt;a href...&gt; and &lt;/a&gt; 
+				  tags. 
+				</td> 
+			  </tr> 
+			  <tr> 
+				<th valign="top"> 
+				  t 
+				</th> 
+				<td valign="top"> 
+				  title 
+				</td> 
+				<td> 
+				  The title of the document 
+				</td> 
+			  </tr> 
+			  <tr> 
+				<th valign="top"> 
+				  h 
+				</th> 
+				<td valign="top"> 
+				  head 
+				</td> 
+				<td> 
+				  The top of the document itself. This is used to 
+				  build the excerpt. This should only contain 
+				  normal ASCII text 
+				</td> 
+			  </tr> 
+			  <tr> 
+				<th valign="top"> 
+				  a 
+				</th> 
+				<td valign="top"> 
+				  anchor 
+				</td> 
+				<td> 
+				  The label that identifies an anchor that can be 
+				  used as a target in an URL. This really only 
+				  makes sense for HTML documents. 
+				</td> 
+			  </tr> 
+			  <tr> 
+				<th valign="top"> 
+				  i 
+				</th> 
+				<td valign="top"> 
+				  image URL 
+				</td> 
+				<td> 
+				  An URL that points at an image that is part of 
+				  the document. 
+				</td> 
+			  </tr> 
+			  <tr> 
+				<th rowspan="3" valign="top"> 
+				  m 
+				</th> 
+				<td valign="top"> 
+				  http-equiv 
+				</td> 
+				<td> 
+				  The HTTP-EQUIV attribute of a 
+				  <a href="meta.html"><em>META</em> tag</a>. 
+				  May be empty. 
+				</td> 
+			  </tr> 
+			  <tr> 
+				<td valign="top"> 
+				  name 
+				</td> 
+				<td> 
+				  The NAME attribute of this 
+				  <a href="meta.html"><em>META</em> tag</a>. 
+				  May be empty. 
+				</td> 
+			  </tr> 
+			  <tr> 
+				<td valign="top"> 
+				  contents 
+				</td> 
+				<td> 
+				  The CONTENTS attribute of this 
+				  <a href="meta.html"><em>META</em> tag</a>. 
+				  May be empty. 
+				</td> 
+			  </tr> 
+			</table> 
+	<p><em>See also FAQ questions <ref type="faq">4.8</ref> and <ref type="faq">4.9</ref> for more 
+	examples.</em></p> 
+     </description>
+   </attribute>
+
+   <attribute name="external_protocols" 
+              type="quoted_string_list" 
+              programs="htdig" 
+              version="3.2.0b1" 
+              category="External:Protocols" >
+     <default></default>
+     <example>https /usr/local/bin/handler.pl \ 
+	ftp /usr/local/bin/ftp-handler.pl</example>
+     <description> 
+	This attribute is a bit like <ref type="attr">external_parsers</ref> 
+	since it specifies a list of protocols/handlers that are used to download documents 
+	that cannot be retrieved using the internal methods. This enables htdig to index 
+	documents with URL schemes it does not understand, or to use more advanced authentication 
+	for the documents it is retrieving. This list is checked before HTTP or other methods, 
+	so this can override the internal behavior without writing additional code for htdig.<br/> 
+	  The external protocols are specified as pairs of strings, the first being the URL scheme that 
+	the script can handle while the second is the path to the script itself. If the second is 
+	quoted, then additional command-line arguments may be given.<br/> 
+	If the external protocol does not contain a colon (:), it is assumed 
+	to have the standard format 
+	"protocol://[usr[:password]@]address[:port]/path". 
+	If it ends with a colon, then it is assumed to have the simpler format 
+	"protocol:path". If it ends with "://" then the standard form is 
+	again assumed. <br/> 
+	If the external protocol does not contain a colon (:), it is assumed 
+	to have the standard format 
+	"protocol://[usr[:password]@]address[:port]/path". 
+	If it ends with a colon, then it is assumed to have the simpler format 
+	"protocol:path". If it ends with "://" then the standard form is 
+	again assumed. <br/> 
+	  The program takes three command-line parameters, not counting any parameters already given  
+	in the command string:<br/> 
+	<em>protocol URL configuration-file</em><br/> 
+	<table border="1"> 
+	  <tr> 
+		<th> 
+		  Parameter 
+		</th> 
+		<th> 
+		  Description 
+		</th> 
+		<th> 
+		  Example 
+		</th> 
+	  </tr> 
+	  <tr> 
+		<td valign="top"> 
+		  protocol 
+		</td> 
+		<td> 
+		  The URL scheme to be used. 
+		</td> 
+		<td> 
+		  https 
+		</td> 
+	  </tr> 
+	  <tr> 
+		<td valign="top"> 
+		  URL 
+		</td> 
+		<td> 
+		  The URL to be retrieved. 
+		</td> 
+		<td> 
+		  https://www.htdig.org:8008/attrs.html 
+		</td> 
+	  </tr> 
+	  <tr> 
+		<td valign="top"> 
+		  configuration-file 
+		</td> 
+		<td> 
+		  The configuration-file in effect. 
+		</td> 
+		<td> 
+		  /etc/htdig/htdig.conf 
+		</td> 
+	  </tr> 
+	</table><p> 
+	The external protocol script is to write information for htdig on the  
+	standard output. The output must follow the form described here. The output  
+	consists of a header followed by a blank line, followed by the contents of  
+	the document. Each record in the header is terminated with a newline.  
+	Each record is a series of (unless expressively allowed to be empty) non-empty  
+	tab-separated fields. The first field is a single character that specifies the  
+	record type. The rest of the fields are determined by the record type. 
+	</p>
+<table border="1"> 
+	  <tr> 
+		<th> 
+		  Record type 
+		</th> 
+		<th> 
+		  Fields 
+		</th> 
+		<th> 
+		  Description 
+		</th> 
+	  </tr> 
+	  <tr> 
+		<th valign="top"> 
+		  s 
+		</th> 
+		<td valign="top"> 
+		  status code 
+		</td> 
+		<td> 
+		  An HTTP-style status code, e.g. 200, 404. Typical codes include: 
+		    <dl compact="true"> 
+			<dt> 
+			  200 
+			</dt> 
+			<dd> 
+			  Successful retrieval 
+			</dd> 
+			<dt> 
+			  304 
+			</dt> 
+			<dd> 
+			  Not modified (for example, if the document hasn't changed) 
+			</dd> 
+			<dt> 
+			  301 
+			</dt> 
+			<dd> 
+			  Redirect (to another URL) 
+			</dd> 
+			<dt> 
+			  401 
+			</dt> 
+			<dd> 
+			  Not authorized 
+			</dd> 
+			<dt> 
+			  404 
+			</dt> 
+			<dd> 
+			  Not found 
+			</dd> 
+		  </dl> 
+		</td> 
+	  </tr> 
+	  <tr> 
+		<th valign="top"> 
+		  r 
+		</th> 
+		<td valign="top"> 
+		  reason 
+		</td> 
+		<td> 
+		  A text string describing the status code, e.g "Redirect" or "Not Found." 
+		</td> 
+	  </tr> 
+	  <tr> 
+		<th valign="top"> 
+		  m 
+		</th> 
+		<td valign="top"> 
+		  status code 
+		</td> 
+		<td> 
+		  The modification time of this document. While the code is fairly flexible 
+		  about the time/date formats it accepts, it is recommended to use something 
+		  standard, like RFC1123: Sun, 06 Nov 1994 08:49:37 GMT, or ISO-8601:  
+		  1994-11-06 08:49:37 GMT. 
+		</td> 
+	  </tr> 
+	  <tr> 
+		<th valign="top"> 
+		  t 
+		</th> 
+		<td valign="top"> 
+		  content-type 
+		</td> 
+		<td> 
+		  A valid MIME type for the document, like text/html or text/plain. 
+		</td> 
+	  </tr> 
+	  <tr> 
+		<th valign="top"> 
+		  l 
+		</th> 
+		<td valign="top"> 
+		  content-length 
+		</td> 
+		<td> 
+		  The length of the document on the server, which may not necessarily 
+		  be the length of the buffer returned. 
+		</td> 
+	  </tr> 
+	  <tr> 
+		<th valign="top"> 
+		  u 
+		</th> 
+		<td valign="top"> 
+		  url 
+		</td> 
+		<td> 
+		  The URL of the document, or in the case of a redirect, the URL 
+		  that should be indexed as a result of the redirect. 
+		</td> 
+	  </tr> 
+      </table>	   
+     </description>
+   </attribute>
+
+   <attribute name="extra_word_characters" 
+              type="string" 
+              programs="htdig htsearch" 
+              version="3.1.2" 
+              category="Indexing:What" >
+     <default></default>
+     <example>_</example>
+     <description> 
+	These characters are considered part of a word. 
+	In contrast to the characters in the 
+	<ref type="attr">valid_punctuation</ref> 
+	attribute, they are treated just like letter 
+	characters.<br/> 
+	Note that the <ref type="attr">locale</ref> attribute 
+	is normally used to configure which characters 
+	constitute letter characters. 
+     </description>
+   </attribute>
+
+   <attribute name="head_before_get" 
+              type="boolean" 
+              programs="htdig" 
+              version="3.2.0b1" 
+              category="Indexing:Connection" 
+              block="Server" >
+     <default>false</default>
+     <example>true</example>
+     <description> 
+	This option works only if we take advantage of persistent connections (see 
+	persistent_connections attribute). If set to true an HTTP/1.1 <em>HEAD</em> 
+	call is made in order to retrieve header information about a document. 
+	If the status code and the content-type returned let the document be parsable, 
+	then a following 'GET' call is made. 
+     </description>
+   </attribute>
+
+   <attribute name="heading_factor" 
+              type="number" 
+              programs="htsearch" 
+              version="3.2.0b1" 
+              category="Searching:Ranking" >
+     <default>5</default>
+     <example>20</example>
+     <description> 
+			This is a factor which will be used to multiply the 
+			weight of words between &lt;h1&gt; and &lt;/h1&gt; 
+			tags, as well as headings of levels &lt;h2&gt; through 
+			&lt;h6&gt;. It is used to assign the level of importance 
+			to headings. Setting a factor to 0 will cause words 
+			in these headings to be ignored. The number may be a 
+	floating point number. See also 
+	<ref type="attr">author_factor</ref> 
+	<ref type="attr">backlink_factor</ref> 
+	<ref type="attr">caps_factor</ref> 
+	<ref type="attr">date_factor</ref> 
+	<ref type="attr">description_factor</ref> 
+	<ref type="attr">keywords_factor</ref> 
+	<ref type="attr">meta_description_factor</ref> 
+	<ref type="attr">text_factor</ref> 
+	<ref type="attr">title_factor</ref> 
+	<ref type="attr">url_text_factor</ref> 
+     </description>
+   </attribute>
+
+   <attribute name="htnotify_prefix_file" 
+              type="string" 
+              programs="htnotify" 
+              version="3.2.0b3" 
+              category="Extra Output" >
+     <default></default>
+     <example>${common_dir}/notify_prefix.txt</example>
+     <description> 
+	Specifies the file containing text to be inserted in each mail  
+	message sent by htnotify before the list of expired webpages. If omitted,  
+	nothing is inserted. 
+     </description>
+   </attribute>
+
+   <attribute name="htnotify_replyto" 
+              type="string" 
+              programs="htnotify" 
+              version="3.2.0b3" 
+              category="Extra Output" >
+     <default></default>
+     <example>[email protected]</example>
+     <description> 
+	This specifies the email address that htnotify email messages 
+	include in the Reply-to: field. 
+     </description>
+   </attribute>
+
+   <attribute name="htnotify_sender" 
+              type="string" 
+              programs="htnotify" 
+              version="all" 
+              category="Extra Output" >
+     <default>webmaster@www</default>
+     <example>[email protected]</example>
+     <description> 
+	This specifies the email address that htnotify email 
+	messages get sent out from. The address is forged using 
+	/usr/lib/sendmail. Check htnotify/htnotify.cc for 
+	detail on how this is done. 
+     </description>
+   </attribute>
+
+   <attribute name="htnotify_suffix_file" 
+              type="string" 
+              programs="htnotify" 
+              version="3.2.0b3" 
+              category="Extra Output" >
+     <default></default>
+     <example>${common_dir}/notify_suffix.txt</example>
+     <description> 
+	Specifies the file containing text to be inserted in each mail message  
+	sent by htnotify after the list of expired webpages. If omitted, htnotify  
+	will insert a standard message. 
+     </description>
+   </attribute>
+
+   <attribute name="htnotify_webmaster" 
+              type="string" 
+              programs="htnotify" 
+              version="3.2.0b3" 
+              category="Extra Output" >
+     <default>ht://Dig Notification Service</default>
+     <example>Notification Service</example>
+     <description> 
+	This provides a name for the From field, in addition to the email address 
+	for the email messages sent out by htnotify. 
+     </description>
+   </attribute>
+
+   <attribute name="http_proxy" 
+              type="string" 
+              programs="htdig" 
+              version="3.0" 
+              category="Indexing:Connection" 
+              block="URL" >
+     <default></default>
+     <example>3128</example>
+     <description> 
+	When this attribute is set, all HTTP document 
+	retrievals will be done using the HTTP-PROXY protocol. 
+	The URL specified in this attribute points to the host 
+	and port where the proxy server resides.<br/> 
+	The use of a proxy server greatly improves performance 
+	of the indexing process. 
+     </description>
+   </attribute>
+
+   <attribute name="http_proxy_authorization" 
+              type="string" 
+              programs="htdig" 
+              version="3.2.0b4" 
+              category="Indexing:Connection" 
+              block="URL" >
+     <default></default>
+     <example>mypassword</example>
+     <description> 
+	This tells htdig to send the supplied 
+	<em>username</em><strong>:</strong><em>password</em> with each HTTP request, 
+	when using a proxy with authorization requested. 
+	The credentials will be encoded using the "Basic" authentication 
+	scheme. There <em>must</em> be a colon (:) between the username and 
+	password. 
+     </description>
+   </attribute>
+
+   <attribute name="http_proxy_exclude" 
+              type="pattern_list" 
+              programs="htdig" 
+              version="3.1.0b3" 
+              category="Indexing:Connection" >
+     <default></default>
+     <example>//intranet.foo.com/</example>
+     <description> 
+	When this is set, URLs matching this will not use the 
+	proxy. This is useful when you have a mixture of sites 
+	near to the digging server and far away. 
+     </description>
+   </attribute>
+
+   <attribute name="ignore_alt_text" 
+              type="boolean" 
+              programs="htdig" 
+              version="3.1.6" 
+              category="Indexing:What" >
+     <default>false</default>
+     <example>true</example>
+     <description> 
+	If set, this causes the text of the ALT field in an &lt;IMG...&gt; tag 
+	not to be indexed as part of the text of the document, nor included in 
+	excerpts. 
+     </description>
+   </attribute>
+
+   <attribute name="ignore_dead_servers" 
+              type="boolean" 
+              programs="htdig" 
+              version="3.1.6" 
+              category="Indexing:Connection" >
+     <default>true</default>
+     <example>false</example>
+     <description> 
+	Determines whether htdig will continue to index URLs from a 
+	server after an attempted connection to the server fails as 
+	&quot;no host found&quot; or &quot;host not found (port).&quot; If 
+	set to false, htdig will try <em>every</em> URL from that server. 
+     </description>
+   </attribute>
+
+   <attribute name="image_list" 
+              type="string" 
+              programs="htdig" 
+              version="all" 
+              category="Extra Output" >
+     <default>${database_base}.images</default>
+     <example>allimages</example>
+     <description> 
+	This is the file that a list of image URLs gets written 
+	to by <ref type="program">htdig</ref> when the 
+	<ref type="attr">create_image_list</ref> is set to 
+	true. As image URLs are seen, they are just appended to 
+	this file, so after htdig finishes it is probably a 
+	good idea to run <code>sort -u</code> on the file to 
+	eliminate duplicates from the file. 
+     </description>
+   </attribute>
+
+   <attribute name="image_url_prefix" 
+              type="string" 
+              programs="htsearch" 
+              version="all" 
+              category="Presentation:Text" >
+     <default configmacro="true">IMAGE_URL_PREFIX</default>
+     <example>/images/htdig</example>
+     <description> 
+	This specifies the directory portion of the URL used 
+	to display star images. This attribute isn't directly 
+	used by htsearch, but is used in the default URL for 
+	the <ref type="attr">star_image</ref> and 
+	<ref type="attr">star_blank</ref> attributes, and 
+	other attributes may be defined in terms of this one. 
+	<p> 
+	The default value of this attribute is determined at 
+	compile time. 
+	</p> 
+     </description>
+   </attribute>
+
+   <attribute name="include" 
+              type="string" 
+              programs="all" 
+              version="3.1.0" 
+              category="" >
+     <default></default>
+     <example>${config_dir}/htdig.conf</example>
+     <description> 
+	This is not quite a configuration attribute, but 
+	rather a directive. It can be used within one 
+	configuration file to include the definitions of 
+	another file. The last definition of an attribute 
+	is the one that applies, so after including a file, 
+	any of its definitions can be overridden with 
+	subsequent definitions. This can be useful when 
+	setting up many configurations that are mostly the 
+	same, so all the common attributes can be maintained 
+	in a single configuration file. The include directives 
+	can be nested, but watch out for nesting loops. 
+     </description>
+   </attribute>
+
+   <attribute name="iso_8601" 
+              type="boolean" 
+              programs="htsearch htnotify" 
+              version="3.1.0b2" 
+              category="Presentation:How,Extra Output" >
+     <default>false</default>
+     <example>true</example>
+     <description> 
+	This sets whether dates should be output in ISO 8601 
+	format. For example, this was written on: 1998-10-31 11:28:13 EST. 
+	See also the <ref type="attr">date_format</ref> attribute, which 
+	can override any date format that 
+	<ref type="program">htsearch</ref> 
+	picks by default.<br/> 
+	This attribute also affects the format of the date 
+	<ref type="program">htnotify</ref> expects to find 
+	in a <strong>htdig-notification-date</strong> field. 
+     </description>
+   </attribute>
+
+   <attribute name="keywords" 
+              type="string_list" 
+              programs="htsearch" 
+              version="??" 
+              category="Searching:Method" >
+     <default></default>
+     <example>documentation</example>
+     <description> 
+	Keywords which <strong>must</strong> be found on all pages returned, 
+    	even if the "or" ("Any") <ref type="attr">method</ref> is 
+	selected. 
+     </description>
+   </attribute>
+
+   <attribute name="keywords_factor" 
+              type="number" 
+              programs="htsearch" 
+              version="all" 
+              category="Searching:Ranking" >
+     <default>100</default>
+     <example>12</example>
+     <description> 
+	This is a factor which will be used to multiply the 
+	weight of words in the list of keywords of a document. 
+	The number may be a floating point number. See also the 
+	<ref type="attr">heading_factor</ref>attribute. 
+     </description>
+   </attribute>
+
+   <attribute name="keywords_meta_tag_names" 
+              type="string_list" 
+              programs="htdig" 
+              version="3.0.6" 
+              category="Indexing:What" >
+     <default>keywords htdig-keywords</default>
+     <example>keywords description</example>
+     <description>	The words in this list are used to search for keywords 
+	in HTML <em>META</em> tags. This list can contain any 
+	number of strings that each will be seen as the name 
+	for whatever keyword convention is used.<br/> 
+	The <em>META</em> tags have the following format: 
+    <codeblock> 
+    &lt;META name="<em>somename</em>" content="<em>somevalue</em>"&gt; 
+    </codeblock> 
+</description>
+   </attribute>
+
+   <attribute name="limit_normalized" 
+              type="pattern_list" 
+              programs="htdig" 
+              version="3.1.0b2" 
+              category="Indexing:Where" >
+     <default></default>
+     <example>//www.mydomain.com</example>
+     <description> 
+	This specifies a set of patterns that all URLs have to 
+	match against in order for them to be included in the 
+	search. Unlike the limit_urls_to attribute, this is done 
+	<strong>after</strong> the URL is normalized and the 
+	<ref type="attr">server_aliases</ref> 
+	attribute is applied. This allows filtering after any 
+	hostnames and DNS aliases are resolved. Otherwise, this 
+	attribute is the same as the <ref type="attr">limit_urls_to</ref> attribute. 
+     </description>
+   </attribute>
+
+   <attribute name="limit_urls_to" 
+              type="pattern_list" 
+              programs="htdig" 
+              version="all" 
+              category="Indexing:Where" >
+     <default>${start_url}</default>
+     <example>.sdsu.edu kpbs [.*\.html]</example>
+     <description> 
+	This specifies a set of patterns that all URLs have to 
+	match against in order for them to be included in the 
+	search. Any number of strings can be specified, 
+	separated by spaces. If multiple patterns are given, at 
+	least one of the patterns has to match the URL.<br/> 
+	Matching, by default, is a case-insensitive string match on the URL 
+	to be used, unless the <ref type="attr">case_sensitive</ref>  
+	attribute is set. The match will be performed <em>after</em> 
+	the relative references have been converted to a valid 
+	URL. This means that the URL will <em>always</em> start 
+	with <code>http://</code>.<br/> 
+	Granted, this is not the perfect way of doing this, 
+	but it is simple enough and it covers most cases. 
+     </description>
+   </attribute>
+
+   <attribute name="local_default_doc" 
+              type="string_list" 
+              programs="htdig" 
+              version="3.0.8b2" 
+              category="Indexing:Where" 
+              block="Server" >
+     <default>index.html</default>
+     <example>default.html default.htm index.html index.htm</example>
+     <description> 
+	Set this to the default documents in a directory used by the 
+	server. This is used for local filesystem access to 
+	translate URLs like http://foo.com/ into something like 
+	/home/foo.com/index.html<br/> 
+	The list should only contain names that the local server 
+	recognizes as default documents for directory URLs, as defined 
+	by the DirectoryIndex setting in Apache's srm.conf, for example. 
+	As of version 3.1.5, this can be a string list rather than a single name, 
+	and htdig will use the first name that works. Since this requires a 
+	loop, setting the most common name first will improve performance. 
+	Special characters can be embedded in these names using %xx hex encoding. 
+     </description>
+   </attribute>
+
+   <attribute name="local_urls" 
+              type="string_list" 
+              programs="htdig" 
+              version="3.0.8b2" 
+              category="Indexing:Where" >
+     <default></default>
+     <example>//www.foo.com/=/usr/www/htdocs/</example>
+     <description> 
+	Set this to tell ht://Dig to access certain URLs through 
+	local filesystems. At first ht://Dig will try to access 
+	pages with URLs matching the patterns through the 
+	filesystems specified. If it cannot find the file, or 
+	if it doesn't recognize the file name extension, it will 
+	try the URL through HTTP instead. Note the example--the 
+	equal sign and the final slashes in both the URL and the 
+	directory path are critical. 
+	<br/>The fallback to HTTP can be disabled by setting the 
+	<ref type="attr">local_urls_only</ref> attribute to true. 
+	To access user directory URLs through the local filesystem, 
+	set <ref type="attr">local_user_urls</ref>.  The only 
+	file name extensions currently recognized for local filesystem 
+	access are .html, .htm, .txt, .asc, .ps, .eps and .pdf. For 
+	anything else, htdig must ask the HTTP server for the file, 
+	so it can determine the MIME content-type of it. 
+	As of version 3.1.5, you can provide multiple mappings of a given 
+	URL to different directories, and htdig will use the first 
+	mapping that works. 
+	Special characters can be embedded in these names using %xx hex encoding. 
+	For example, you can use %3D to embed an "=" sign in an URL pattern. 
+     </description>
+   </attribute>
+
+   <attribute name="local_urls_only" 
+              type="boolean" 
+              programs="htdig" 
+              version="3.1.4" 
+              category="Indexing:Where" >
+     <default>false</default>
+     <example>true</example>
+     <description> 
+	Set this to tell ht://Dig to access files only through the  
+	local filesystem, for URLs matching the patterns in the 
+	<ref type="attr">local_urls</ref> or 
+	<ref type="attr">local_user_urls</ref> attribute. If it cannot  
+	find the file, it will give up rather than trying HTTP or another protocol. 
+     </description>
+   </attribute>
+
+   <attribute name="local_user_urls" 
+              type="string_list" 
+              programs="htdig" 
+              version="3.0.8b2" 
+              category="Indexing:Where" >
+     <default></default>
+     <example>//www.my.org/=/home/,/www/</example>
+     <description> 
+	Set this to access user directory URLs through the local 
+	filesystem. If you leave the "path" portion out, it will 
+	look up the user's home directory in /etc/password (or NIS 
+	or whatever). As with <ref type="attr">local_urls</ref>, 
+	if the files are not found, ht://Dig will try with HTTP or the 
+	appropriate protocol. Again, note the 
+	example's format. To map http://www.my.org/~joe/foo/bar.html 
+	to /home/joe/www/foo/bar.html, try the example below. 
+	<br/>The fallback to HTTP can be disabled by setting the 
+	<ref type="attr">local_urls_only</ref> attribute to true. 
+	As of version 3.1.5, you can provide multiple mappings of a given 
+	URL to different directories, and htdig will use the first 
+	mapping that works. 
+	Special characters can be embedded in these names using %xx hex encoding. 
+	For example, you can use %3D to embed an "=" sign in an URL pattern. 
+     </description>
+   </attribute>
+
+   <attribute name="locale" 
+              type="string" 
+              programs="htdig" 
+              version="3.0" 
+              category="Indexing:What,Presentation:How" >
+     <default>C</default>
+     <example>en_US</example>
+     <description> 
+	Set this to whatever locale you want your search 
+	database cover. It affects the way international 
+	characters are dealt with. On most systems a list of 
+	legal locales can be found in /usr/lib/locale. Also 
+	check the <strong>setlocale(3C)</strong> man page. 
+	Note that depending the locale you choose, and whether 
+	your system's locale implementation affects floating 
+	point input, you may need to specify the decimal point 
+	as a comma rather than a period. This will affect 
+	settings of <ref type="attr">search_algorithm</ref> 
+	and any of the scoring factors. 
+     </description>
+   </attribute>
+
+   <attribute name="logging" 
+              type="boolean" 
+              programs="htsearch" 
+              version="3.1.0b2" 
+              category="Extra Output" >
+     <default>false</default>
+     <example>true</example>
+     <description> 
+	This sets whether htsearch should use the syslog() to log 
+	search requests. If set, this will log requests with a 
+	default level of LOG_INFO and a facility of LOG_LOCAL5. For 
+	details on redirecting the log into a separate file or other 
+	actions, see the <strong>syslog.conf(5)</strong> man 
+	page. To set the level and facility used in logging, change 
+	LOG_LEVEL and LOG_FACILITY in the include/htconfig.h file 
+	before compiling. 
+	<dl> 
+	  <dt> 
+	    Each line logged by htsearch contains the following: 
+	  </dt> 
+	  <dd> 
+	    REMOTE_ADDR [config] (match_method) [words] 
+	    [logicalWords] (matches/matches_per_page) - 
+	    page, HTTP_REFERER 
+	  </dd> 
+	</dl> 
+	where any of the above are null or empty, it 
+	either puts in '-' or 'default' (for config). 
+     </description>
+   </attribute>
+
+   <attribute name="maintainer" 
+              type="string" 
+              programs="htdig" 
+              version="all" 
+              category="Indexing:Out" 
+              block="Server" >
+     <default>[email protected]</default>
+     <example>[email protected]</example>
+     <description> 
+	This should be the email address of the person in 
+	charge of the digging operation. This string is added 
+	to the user-agent: field when the digger sends a 
+	request to a server. 
+     </description>
+   </attribute>
+
+   <attribute name="match_method" 
+              type="string" 
+              programs="htsearch" 
+              version="3.0" 
+              category="Searching:Method" >
+     <default>and</default>
+     <example>boolean</example>
+     <description> 
+	This is the default method for matching that htsearch 
+	uses. The valid choices are: 
+	<ul> 
+	  <li> or </li> 
+	  <li> and </li> 
+	  <li> boolean </li> 
+	</ul> 
+	This attribute will only be used if the HTML form that 
+	calls htsearch didn't have the <a href="hts_form.html#method">method</a> 
+	value set. 
+     </description>
+   </attribute>
+
+   <attribute name="matches_per_page" 
+              type="integer" 
+              programs="htsearch" 
+              version="3.0" 
+              category="Searching:Method" >
+     <default>10</default>
+     <example>999</example>
+     <description> 
+	If this is set to a relatively small number, the 
+	matches will be shown in pages instead of all at once. 
+	This attribute will only be used if the HTML form that 
+	calls htsearch didn't have the 
+	<a href="hts_form.html#matchesperpage">matchesperpage</a> value set. 
+     </description>
+   </attribute>
+
+   <attribute name="max_connection_requests" 
+              type="integer" 
+              programs="htdig" 
+              version="3.2.0b1" 
+              category="Indexing:Connection" >
+     <default>-1</default>
+     <example>100</example>
+     <description> 
+	This attribute tells htdig to limit the number of requests it will 
+	send to a server using a single, persistent HTTP connection. This 
+	only applies when the 
+	<ref type="attr">persistent_connections</ref> 
+	attribute is set. You may set the limit as high as you want, 
+	but it must be at least 1. A value of -1 specifies no limit. 
+	Requests in the queue for a server will be combined until either 
+	the limit is reached, or the queue is empty. 
+     </description>
+   </attribute>
+
+   <attribute name="max_description_length" 
+              type="integer" 
+              programs="htdig" 
+              version="all" 
+              category="Indexing:What" >
+     <default>60</default>
+     <example>40</example>
+     <description> 
+	While gathering descriptions of URLs, 
+	<ref type="program">htdig</ref> will only record those 
+	descriptions which are shorter than this length. This 
+	is used mostly to deal with broken HTML. (If a 
+	hyperlink is not terminated with a &lt;/a&gt; the 
+	description will go on until the end of the document.) 
+     </description>
+   </attribute>
+
+   <attribute name="max_descriptions" 
+              type="integer" 
+              programs="htdig" 
+              version="all" 
+              category="Indexing:What" >
+     <default>5</default>
+     <example>15</example>
+     <description> 
+	While gathering descriptions of URLs, 
+	<ref type="program">htdig</ref> will only record up to this 
+	number of descriptions, in the order in which it encounters 
+	them. This is used to prevent the database entry for a document 
+	from growing out of control if the document has a huge number 
+	of links to it. 
+     </description>
+   </attribute>
+
+   <attribute name="max_doc_size" 
+              type="integer" 
+              programs="htdig" 
+              version="3.0" 
+              category="Indexing:What" 
+              block="URL" >
+     <default>100000</default>
+     <example>5000000</example>
+     <description> 
+	This is the upper limit to the amount of data retrieved 
+	for documents. This is mainly used to prevent 
+	unreasonable memory consumption since each document 
+	will be read into memory by <ref type="program">htdig</ref>. 
+     </description>
+   </attribute>
+
+   <attribute name="max_excerpts" 
+              type="integer" 
+              programs="htsearch" 
+              version="3.1.6" 
+              category="Presentation:How" 
+              block="URL" >
+     <default>1</default>
+     <example>10</example>
+     <description> 
+	This value determines the maximum number of excerpts 
+	that can be displayed for one matching document in the 
+	search results. 
+     </description>
+   </attribute>
+
+   <attribute name="max_head_length" 
+              type="integer" 
+              programs="htdig" 
+              version="all" 
+              category="Indexing:How" >
+     <default>512</default>
+     <example>50000</example>
+     <description> 
+	For each document retrieved, the top of the document is 
+	stored. This attribute determines the size of this 
+	block. The text that will be stored is only the text; 
+	no markup is stored.<br/> 
+	We found that storing 50,000 bytes will store about 
+	95% of all the documents completely. This really 
+	depends on how much storage is available and how much 
+	you want to show. 
+     </description>
+   </attribute>
+
+   <attribute name="max_hop_count" 
+              type="integer" 
+              programs="htdig" 
+              version="all" 
+              category="Indexing:Where" >
+     <default>999999</default>
+     <example>4</example>
+     <description> 
+	Instead of limiting the indexing process by URL 
+	pattern, it can also be limited by the number of hops 
+	or clicks a document is removed from the starting URL. 
+	<br/> 
+	The starting page or pages will have hop count 0. 
+     </description>
+   </attribute>
+
+   <attribute name="max_keywords" 
+              type="integer" 
+              programs="htdig" 
+              version="3.2.0b1" 
+              category="Indexing:What" >
+     <default>-1</default>
+     <example>10</example>
+     <description> 
+	This attribute can be used to limit the number of keywords 
+	per document that htdig will accept from meta keywords tags. 
+	A value of -1 or less means no limit. This can help combat meta 
+	keyword spamming, by limiting the amount of keywords that will be 
+	indexed, but it will not completely prevent irrelevant matches 
+	in a search if the first few keywords in an offending document 
+	are not relevant to its contents. 
+     </description>
+   </attribute>
+
+   <attribute name="max_meta_description_length" 
+              type="integer" 
+              programs="htdig" 
+              version="3.1.0b1" 
+              category="Indexing:How" >
+     <default>512</default>
+     <example>1000</example>
+     <description> 
+	While gathering descriptions from meta description tags, 
+	<ref type="program">htdig</ref> will only store up to  
+	this much of the text for each document. 
+     </description>
+   </attribute>
+
+   <attribute name="max_prefix_matches" 
+              type="integer" 
+              programs="htsearch" 
+              version="3.1.0b1" 
+              category="Searching:Method" >
+     <default>1000</default>
+     <example>100</example>
+     <description> 
+	The Prefix fuzzy algorithm could potentially match a 
+	very large number of words. This value limits the 
+	number of words each prefix can match. Note 
+	that this does not limit the number of documents that 
+	are matched in any way. 
+     </description>
+   </attribute>
+
+   <attribute name="max_retries" 
+              type="number" 
+              programs="htdig" 
+              version="3.2.0b1" 
+              category="Indexing:Connection" >
+     <default>3</default>
+     <example>6</example>
+     <description> 
+	 This option set the maximum number of retries when retrieving a document 
+	 fails (mainly for reasons of connection). 
+     </description>
+   </attribute>
+
+   <attribute name="max_stars" 
+              type="number" 
+              programs="htsearch" 
+              version="all" 
+              category="Presentation:How" >
+     <default>4</default>
+     <example>6</example>
+     <description> 
+	When stars are used to display the score of a match, 
+	this value determines the maximum number of stars that 
+	can be displayed. 
+     </description>
+   </attribute>
+
+   <attribute name="maximum_page_buttons" 
+              type="integer" 
+              programs="htsearch" 
+              version="3.2.0b3" 
+              category="Presentation:How" >
+     <default>${maximum_pages}</default>
+     <example>20</example>
+     <description> 
+	This value limits the number of page links that will be 
+	included in the page list at the bottom of the search 
+	results page. By default, it takes on the value of the 
+	<ref type="attr">maximum_pages</ref> 
+	attribute, but you can set it to something lower to allow 
+	more pages than buttons. In this case, pages above this 
+	number will have no corresponding button. 
+     </description>
+   </attribute>
+
+   <attribute name="maximum_pages" 
+              type="integer" 
+              programs="htsearch" 
+              version="all" 
+              category="Presentation:How" >
+     <default>10</default>
+     <example>20</example>
+     <description> 
+	This value limits the number of page links that will be 
+	included in the page list at the bottom of the search 
+	results page. As of version 3.1.4, this will limit the 
+	total number of matching documents that are shown. 
+	You can make the number of page buttons smaller than the 
+	number of allowed pages by setting the 
+	<ref type="attr">maximum_page_buttons</ref> 
+	attribute. 
+     </description>
+   </attribute>
+
+   <attribute name="maximum_word_length" 
+              type="integer" 
+              programs="htdig htsearch" 
+              version="3.1.3" 
+              category="Indexing:What" >
+     <default>32</default>
+     <example>15</example>
+     <description> 
+	This sets the maximum length of words that will be 
+	indexed. Words longer than this value will be silently 
+	truncated when put into the index, or searched in the 
+	index. 
+     </description>
+   </attribute>
+
+   <attribute name="md5_db" 
+              type="string" 
+              programs="htdig" 
+              version="3.2.0b3" 
+              category="File Layout" >
+     <default>${database_base}.md5hash.db</default>
+     <example>${database_base}.md5.db</example>
+     <description> 
+	This file holds a database of md5 and date hashes of pages to 
+	catch and eliminate duplicates of pages. See also the 
+	<ref type="attr">check_unique_md5</ref> and 
+	<ref type="attr">check_unique_date</ref> attributes. 
+     </description>
+   </attribute>
+
+   <attribute name="meta_description_factor" 
+              type="number" 
+              programs="htsearch" 
+              version="3.1.0b1" 
+              category="Searching:Ranking" >
+     <default>50</default>
+     <example>20</example>
+     <description> 
+	This is a factor which will be used to multiply the 
+	weight of words in any META description tags in a document. 
+	The number may be a floating point number. See also the 
+	<ref type="attr">heading_factor</ref> attribute and the 
+	<ref type="attr">description_factor</ref> attribute. 
+     </description>
+   </attribute>
+
+   <attribute name="metaphone_db" 
+              type="string" 
+              programs="htfuzzy htsearch" 
+              version="all" 
+              category="File Layout" >
+     <default>${database_base}.metaphone.db</default>
+     <example>${database_base}.mp.db</example>
+     <description> 
+	The database file used for the fuzzy "metaphone" search 
+	algorithm. This database is created by 
+	<ref type="program">htfuzzy</ref> and used by 
+	<ref type="program">htsearch</ref>. 
+     </description>
+   </attribute>
+
+   <attribute name="method_names" 
+              type="quoted_string_list" 
+              programs="htsearch" 
+              version="all" 
+              category="Searching:UI" >
+     <default>and All or Any boolean Boolean</default>
+     <example>or Or and And</example>
+     <description> 
+	These values are used to create the <strong> 
+	method</strong> menu. It consists of pairs. The first 
+	element of each pair is one of the known methods, the 
+	second element is the text that will be shown in the 
+	menu for that method. This text needs to be quoted if 
+	it contains spaces. 
+	See the <a href="hts_selectors.html">select list documentation</a> 
+	for more information on how this attribute is used. 
+     </description>
+   </attribute>
+
+   <attribute name="mime_types" 
+              type="string" 
+              programs="htdig" 
+              version="3.2.0b1" 
+              category="Indexing:Where" >
+     <default>${config_dir}/mime.types</default>
+     <example>/etc/mime.types</example>
+     <description> 
+	This file is used by htdig for local file access and resolving 
+	file:// URLs to ensure the files are parsable. If you are running 
+	a webserver with its own MIME file, you should set this attribute 
+	to point to that file. 
+     </description>
+   </attribute>
+
+   <attribute name="minimum_prefix_length" 
+              type="integer" 
+              programs="htsearch" 
+              version="3.1.0b1" 
+              category="Searching:Method" >
+     <default>1</default>
+     <example>2</example>
+     <description> 
+	This sets the minimum length of prefix matches used by the 
+	"prefix" fuzzy matching algorithm. Words shorter than this 
+	will not be used in prefix matching. 
+     </description>
+   </attribute>
+
+   <attribute name="minimum_speling_length" 
+              type="integer" 
+              programs="htsearch" 
+              version="3.2.0b1" 
+              category="Searching:Method" >
+     <default>5</default>
+     <example>3</example>
+     <description> 
+	This sets the minimum length of words used by the 
+	"speling" fuzzy matching algorithm. Words shorter than this 
+	will not be used in this fuzzy matching. 
+     </description>
+   </attribute>
+
+   <attribute name="minimum_word_length" 
+              type="integer" 
+              programs="htdig htsearch" 
+              version="all" 
+              category="Indexing:What" >
+     <default>3</default>
+     <example>2</example>
+     <description> 
+	This sets the minimum length of words that will be 
+	indexed. Words shorter than this value will be silently 
+	ignored but still put into the excerpt.<br/> 
+	Note that by making this value less than 3, a lot more 
+	words that are very frequent will be indexed. It might 
+	be advisable to add some of these to the
+	<ref type="attr">bad_word_list</ref>. 
+     </description>
+   </attribute>
+
+   <attribute name="multimatch_factor" 
+              type="number" 
+              programs="htsearch" 
+              version="3.1.6" 
+              category="Searching:Ranking" >
+     <default>1</default>
+     <example>1000</example>
+     <description> 
+	This factor gives higher rankings to documents that have more than
+	one matching search word when the <strong>or</strong>
+	<ref type="attr">match_method</ref> is used.
+	In version 3.1.6, the matching words' combined scores were multiplied
+	by this factor for each additional matching word.  Currently, this
+	multiplier is applied at most once.
+     </description>
+   </attribute>
+
+   <attribute name="next_page_text" 
+              type="string" 
+              programs="htsearch" 
+              version="3.1.0" 
+              category="Presentation:Text" >
+     <default>[next]</default>
+     <example>&lt;img src="/htdig/buttonr.gif"&gt;</example>
+     <description> 
+	The text displayed in the hyperlink to go to the next 
+	page of matches. 
+     </description>
+   </attribute>
+
+   <attribute name="no_excerpt_show_top" 
+              type="boolean" 
+              programs="htsearch" 
+              version="3.1.0b3" 
+              category="Presentation:How" >
+     <default>false</default>
+     <example>yes</example>
+     <description> 
+	If no excerpt is available, this option will act the 
+	same as <ref type="attr">excerpt_show_top</ref>, that is, 
+	it will show the top of the document. 
+     </description>
+   </attribute>
+
+   <attribute name="no_excerpt_text" 
+              type="string" 
+              programs="htsearch" 
+              version="3.0" 
+              category="Presentation:Text" >
+     <default>&lt;em&gt;(None of the search words were found in the top of this document.)&lt;/em&gt;</default>
+     <example></example>
+     <description> 
+	This text will be displayed in place of the excerpt if 
+	there is no excerpt available. If this attribute is set 
+	to nothing (blank), the excerpt label will not be 
+	displayed in this case. 
+     </description>
+   </attribute>
+
+   <attribute name="no_next_page_text" 
+              type="string" 
+              programs="htsearch" 
+              version="3.0" 
+              category="Presentation:Text" >
+     <default>[next]</default>
+     <example></example>
+     <description> 
+	The text displayed where there would normally be a 
+	hyperlink to go to the next page of matches. 
+     </description>
+   </attribute>
+
+   <attribute name="no_page_list_header" 
+              type="string" 
+              programs="htsearch" 
+              version="3.0" 
+              category="Presentation:Text" >
+     <default></default>
+     <example>&lt;hr noshade size=2&gt;All results on this page.&lt;br&gt;</example>
+     <description> 
+	This text will be used as the value of the PAGEHEADER 
+	variable, for use in templates or the 
+	<ref type="attr">search_results_footer</ref> 
+	file, when all search results fit on a single page. 
+     </description>
+   </attribute>
+
+   <attribute name="no_page_number_text" 
+              type="quoted_string_list" 
+              programs="htsearch" 
+              version="3.0" 
+              category="Presentation:Text" >
+     <default></default>
+     <example>&lt;strong&gt;1&lt;/strong&gt; &lt;strong&gt;2&lt;/strong&gt; \ 
+				  &lt;strong&gt;3&lt;/strong&gt; &lt;strong&gt;4&lt;/strong&gt; \ 
+				  &lt;strong&gt;5&lt;/strong&gt; &lt;strong&gt;6&lt;/strong&gt; \ 
+				  &lt;strong&gt;7&lt;/strong&gt; &lt;strong&gt;8&lt;/strong&gt; \ 
+				  &lt;strong&gt;9&lt;/strong&gt; &lt;strong&gt;10&lt;/strong&gt; 
+</example>
+     <description> 
+	The text strings in this list will be used when putting 
+	together the PAGELIST variable, for use in templates or 
+	the <ref type="attr">search_results_footer</ref> 
+	file, when search results fit on more than page. The PAGELIST 
+	is the list of links at the bottom of the search results page. 
+	There should be as many strings in the list as there are 
+	pages allowed by the <ref type="attr">maximum_page_buttons</ref> 
+	attribute. If there are not enough, or the list is empty, 
+	the page numbers alone will be used as the text for the links. 
+	An entry from this list is used for the current page, as the 
+	current page is shown in the page list without a hypertext link, 
+	while entries from the <ref type="attr">page_number_text</ref> list are used for the links to other pages. 
+	The text strings can contain HTML tags to highlight page numbers 
+	or embed images. The strings need to be quoted if they contain 
+	spaces. 
+     </description>
+   </attribute>
+
+   <attribute name="no_prev_page_text" 
+              type="string" 
+              programs="htsearch" 
+              version="3.0" 
+              category="Presentation:Text" >
+     <default>[prev]</default>
+     <example></example>
+     <description> 
+	The text displayed where there would normally be a 
+	hyperlink to go to the previous page of matches. 
+     </description>
+   </attribute>
+
+   <attribute name="no_title_text" 
+              type="string" 
+              programs="htsearch" 
+              version="3.1.0" 
+              category="Presentation:Text" >
+     <default>filename</default>
+     <example>"No Title Found"</example>
+     <description> 
+	This specifies the text to use in search results when no 
+	title is found in the document itself. If it is set to 
+	filename, htsearch will use the name of the file itself, 
+	enclosed in brackets (e.g. [index.html]). 
+     </description>
+   </attribute>
+
+   <attribute name="noindex_end" 
+              type="string" 
+              programs="htdig" 
+              version="3.1.0" 
+              category="Indexing:What" >
+     <default>&lt;!--/htdig_noindex--&gt;</default>
+     <example>&lt;/SCRIPT&gt;</example>
+     <description> 
+	This string marks the end of a section of an HTML file that should be 
+	completely ignored when indexing. It works together with 
+	<ref type="attr">noindex_start</ref>. 
+	As in the defaults, this can be SGML comment  
+	declarations that can be inserted anywhere in the documents to exclude  
+	different sections from being indexed. However, existing tags can also be  
+	used; this is especially useful to exclude some sections from being indexed  
+	where the files to be indexed can not be edited. The example shows how 
+	SCRIPT sections in 'uneditable' documents can be skipped. 
+	Note that the match for this string is case insensitive. 
+     </description>
+   </attribute>
+
+   <attribute name="noindex_start" 
+              type="string" 
+              programs="htdig" 
+              version="3.1.0" 
+              category="Indexing:What" >
+     <default>&lt;!--htdig_noindex--&gt;</default>
+     <example>&lt;SCRIPT</example>
+     <description> 
+	This string marks the start of a section of an HTML file that should be 
+	completely ignored when indexing. It works together with 
+	<ref type="attr">noindex_end</ref>. 
+	As in the defaults, this can be SGML comment 
+	declarations that can be inserted anywhere in the documents to exclude 
+	different sections from being indexed. However, existing tags can also be 
+	used; this is especially useful to exclude some sections from being indexed 
+	where the files to be indexed can not be edited. The example shows how 
+	SCRIPT sections in 'uneditable' documents can be skipped; note how 
+	noindex_start does not contain an ending &gt;: this allows for all SCRIPT 
+	tags to be matched regardless of attributes defined (different types or 
+	languages). Note that the match for this string is case insensitive. 
+     </description>
+   </attribute>
+
+   <attribute name="nothing_found_file" 
+              type="string" 
+              programs="htsearch" 
+              version="all" 
+              category="Presentation:Files" >
+     <default>${common_dir}/nomatch.html</default>
+     <example>/www/searching/nothing.html</example>
+     <description> 
+	This specifies the file which contains the <code> 
+	HTML</code> text to display when no matches were found. 
+	The file should contain a complete <code>HTML</code> 
+	document.<br/> 
+	Note that this attribute could also be defined in 
+	terms of <ref type="attr">database_base</ref> to 
+	make is specific to the current search database. 
+     </description>
+   </attribute>
+
+   <attribute name="nph" 
+              type="boolean" 
+              programs="htsearch" 
+              version="3.2.0b2" 
+              category="Presentation:How" >
+     <default>false</default>
+     <example>true</example>
+     <description> 
+	This attribute determines whether htsearch sends out full HTTP 
+	headers as required for an NPH (non-parsed header) CGI. Some 
+	servers assume CGIs will act in this fashion, for example MS 
+	IIS. If your server does not send out full HTTP headers, you 
+	should set this to true. 
+     </description>
+   </attribute>
+
+   <attribute name="page_list_header" 
+              type="string" 
+              programs="htsearch" 
+              version="3.0" 
+              category="Presentation:Text" >
+     <default>&lt;hr noshade size=2&gt;Pages:&lt;br&gt;</default>
+     <example></example>
+     <description> 
+	This text will be used as the value of the PAGEHEADER 
+	variable, for use in templates or the 
+	<ref type="attr">search_results_footer</ref> 
+	file, when all search results fit on more than one page. 
+     </description>
+   </attribute>
+
+   <attribute name="page_number_separator" 
+              type="quoted_string_list" 
+              programs="htsearch" 
+              version="3.1.4" 
+              category="Presentation:Text" >
+     <default>" "</default>
+     <example>"&lt;/td&gt; &lt;td&gt;"</example>
+     <description> 
+	The text strings in this list will be used when putting 
+	together the PAGELIST variable, for use in templates or 
+	the <ref type="attr">search_results_footer</ref> 
+	file, when search results fit on more than page. The PAGELIST 
+	is the list of links at the bottom of the search results page. 
+	The strings in the list will be used in rotation, and will 
+	separate individual entries taken from 
+	<ref type="attr">page_number_text</ref> and 
+	<ref type="attr">no_page_number_text</ref>. 
+	There can be as many or as few strings in the list as you like. 
+	If there are not enough for the number of pages listed, it goes 
+	back to the start of the list. If the list is empty, a space is 
+	used. The text strings can contain HTML tags. The strings need 
+	to be quoted if they contain spaces, or to specify an empty string. 
+     </description>
+   </attribute>
+
+   <attribute name="page_number_text" 
+              type="quoted_string_list" 
+              programs="htsearch" 
+              version="3.0" 
+              category="Presentation:Text" >
+     <default></default>
+     <example>&lt;em&gt;1&lt;/em&gt; &lt;em&gt;2&lt;/em&gt; \ 
+				  &lt;em&gt;3&lt;/em&gt; &lt;em&gt;4&lt;/em&gt; \ 
+				  &lt;em&gt;5&lt;/em&gt; &lt;em&gt;6&lt;/em&gt; \ 
+				  &lt;em&gt;7&lt;/em&gt; &lt;em&gt;8&lt;/em&gt; \ 
+				  &lt;em&gt;9&lt;/em&gt; &lt;em&gt;10&lt;/em&gt; 
+</example>
+     <description> 
+	The text strings in this list will be used when putting 
+	together the PAGELIST variable, for use in templates or 
+	the <ref type="attr">search_results_footer</ref> 
+	file, when search results fit on more than page. The PAGELIST 
+	is the list of links at the bottom of the search results page. 
+	There should be as many strings in the list as there are 
+	pages allowed by the <ref type="attr">maximum_page_buttons</ref> 
+	attribute. If there are not enough, or the list is empty, 
+	the page numbers alone will be used as the text for the links. 
+	Entries from this list are used for the links to other pages, 
+	while an entry from the <ref type="attr">no_page_number_text</ref> list is used for the current page, as the 
+	current page is shown in the page list without a hypertext link. 
+	The text strings can contain HTML tags to highlight page numbers 
+	or embed images. The strings need to be quoted if they contain 
+	spaces. 
+     </description>
+   </attribute>
+
+   <attribute name="persistent_connections" 
+              type="boolean" 
+              programs="htdig" 
+              version="3.2.0b1" 
+              category="Indexing:Connection" 
+              block="Server" >
+     <default>true</default>
+     <example>false</example>
+     <description> 
+	If set to true, when servers make it possible, htdig can take advantage 
+	of persistent connections, as defined by HTTP/1.1 (<em>RFC2616</em>). This permits 
+	to reduce the number of open/close operations of connections, when retrieving 
+	a document with HTTP. 
+     </description>
+   </attribute>
+
+   <attribute name="plural_suffix" 
+              type="string" 
+              programs="htsearch" 
+              version="3.2.0b2" 
+              category="Presentation: Text" >
+     <default>s</default>
+     <example>en</example>
+     <description> 
+	Specifies the value of the PLURAL_MATCHES template 
+	variable used in the header, footer and template files. 
+	This can be used for localization for non-English languages 
+	where 's' is not the appropriate suffix. 
+     </description>
+   </attribute>
+
+   <attribute name="prefix_match_character" 
+              type="string" 
+              programs="htsearch" 
+              version="3.1.0b1" 
+              category="Searching:Method" >
+     <default>*</default>
+     <example>ing</example>
+     <description> 
+	A null prefix character means that prefix matching should be 
+	applied to every search word. Otherwise a match is 
+	returned only if the word does not end in the characters specified. 
+     </description>
+   </attribute>
+
+   <attribute name="prev_page_text" 
+              type="string" 
+              programs="htsearch" 
+              version="3.0" 
+              category="Presentation:Text" >
+     <default>[prev]</default>
+     <example>&lt;img src="/htdig/buttonl.gif"&gt;</example>
+     <description> 
+	The text displayed in the hyperlink to go to the 
+	previous page of matches. 
+     </description>
+   </attribute>
+
+   <attribute name="regex_max_words" 
+              type="integer" 
+              programs="htsearch" 
+              version="3.2.0b1" 
+              category="Searching:Method" >
+     <default>25</default>
+     <example>10</example>
+     <description> 
+	The "regex" fuzzy algorithm could potentially match a 
+	very large number of words. This value limits the 
+	number of words each regular expression can match. Note 
+	that this does not limit the number of documents that 
+	are matched in any way. 
+     </description>
+   </attribute>
+
+   <attribute name="remove_bad_urls" 
+              type="boolean" 
+              programs="htpurge" 
+              version="all" 
+              category="Indexing:How" 
+              block="Server" >
+     <default>true</default>
+     <example>true</example>
+     <description> 
+	If TRUE, htpurge will remove any URLs which were marked 
+	as unreachable by htdig from the database. If FALSE, it 
+	will not do this. When htdig is run in initial mode, 
+	documents which were referred to but could not be 
+	accessed should probably be removed, and hence this 
+	option should then be set to TRUE, however, if htdig is 
+	run to update the database, this may cause documents on 
+	a server which is temporarily unavailable to be 
+	removed. This is probably NOT what was intended, so 
+	hence this option should be set to FALSE in that case. 
+     </description>
+   </attribute>
+
+   <attribute name="remove_default_doc" 
+              type="string_list" 
+              programs="htdig" 
+              version="3.1.0" 
+              category="Indexing:How" >
+     <default>index.html</default>
+     <example>default.html default.htm index.html index.htm</example>
+     <description> 
+	Set this to the default documents in a directory used by the 
+	servers you are indexing. These document names will be stripped 
+	off of URLs when they are normalized, if one of these names appears 
+	after the final slash, to translate URLs like 
+	http://foo.com/index.html into http://foo.com/<br/> 
+	Note that you can disable stripping of these names during 
+	normalization by setting the list to an empty string. 
+	The list should only contain names that all servers you index 
+	recognize as default documents for directory URLs, as defined 
+	by the DirectoryIndex setting in Apache's srm.conf, for example. 
+	This only applies to http:// and https:// URLS. 
+     </description>
+   </attribute>
+
+   <attribute name="remove_unretrieved_urls" 
+              type="boolean" 
+              programs="htpurge" 
+              version="3.2.0b1" 
+              category="Indexing:How" 
+              block="Server" >
+     <default>false</default>
+     <example>true</example>
+     <description> 
+	If TRUE, htpurge will remove any URLs which were discovered 
+	and included as stubs in the database but not yet retrieved. If FALSE, it 
+	will not do this. When htdig is run in initial mode with no restrictions  
+	on hopcount or maximum documents, these should probably be removed and set 
+	to true. However, if you are hoping to index a small set of documents and  
+	eventually get to the rest, you should probably leave this as false. 
+     </description>
+   </attribute>
+
+   <attribute name="restrict" 
+              type="pattern_list" 
+              programs="htsearch" 
+              version="3.2.0b4" 
+              category="Searching:Method" >
+     <default></default>
+     <example>//www.acme.com/widgets/</example>
+     <description> 
+	This specifies a set of patterns that all URLs have to 
+	match against in order for them to be included in the search 
+	results. Any number of strings can be specified, separated by 
+	spaces. If multiple patterns are given, at least one of the 
+	patterns has to match the URL. The list can be specified 
+	from within the configuration file, and can be overridden 
+	with the "restrict" input parameter in the search form. Note 
+	that the restrict list does not take precedence over the 
+	<ref type="attr">exclude</ref> list - if a URL matches patterns 
+	in both lists it is still excluded from the search results. 
+     </description>
+   </attribute>
+
+   <attribute name="robotstxt_name" 
+              type="string" 
+              programs="htdig" 
+              version="3.0.7" 
+              category="Indexing:Out" 
+              block="Server" >
+     <default>htdig</default>
+     <example>myhtdig</example>
+     <description> 
+	Sets the name that htdig will look for when parsing 
+	robots.txt files. This can be used to make htdig appear 
+	as a different spider than ht://Dig. Useful to 
+	distinguish between a private and a global index. 
+     </description>
+   </attribute>
+
+   <attribute name="script_name" 
+              type="string" 
+              programs="htsearch" 
+              version="3.1.4" 
+              category="Presentation:Text" >
+     <default></default>
+     <example>/search/results.shtml</example>
+     <description> 
+	Overrides the value of the SCRIPT_NAME 
+	environment attribute. This is useful if 
+	htsearch is not being called directly as a CGI 
+	program, but indirectly from within a dynamic 
+	.shtml page using SSI directives. Previously, 
+	you needed a wrapper script to do this, but 
+	this configuration attribute makes wrapper 
+	scripts obsolete for SSI and possibly for 
+	other server scripting languages, as 
+	well. (You still need a wrapper script when 
+	using PHP, though.)<br/> 
+	Check out the <code>contrib/scriptname</code> 
+	directory for a small example. Note that this 
+	attribute also affects the value of the <a 
+	href="hts_templates.html#CGI">CGI</a> variable 
+	used in htsearch templates. 
+     </description>
+   </attribute>
+
+   <attribute name="search_algorithm" 
+              type="string_list" 
+              programs="htsearch" 
+              version="all" 
+              category="Searching:Method" >
+     <default>exact:1</default>
+     <example>0.3</example>
+     <description> 
+			Specifies the search algorithms and their weight to use 
+			when searching. Each entry in the list consists of the 
+			algorithm name, followed by a colon (:) followed by a 
+			weight multiplier. The multiplier is a floating point 
+			number between 0 and 1. Note that depending on your 
+			<ref type="attr">locale</ref> setting, and whether your 
+			system's locale implementation affects floating point 
+			input, you may need to specify the decimal point as a 
+			comma rather than a period.<br/> 
+			<strong>Note:</strong>If the exact  
+			method is not listed, the search may not work since the  
+			original terms will not be used.<br/> 
+			Current algorithms supported are: 
+			<dl> 
+			  <dt> 
+				exact 
+			  </dt> 
+			  <dd> 
+				The default exact word matching algorithm. This 
+				will find only exactly matched words. 
+			  </dd> 
+			  <dt> 
+				soundex 
+			  </dt> 
+			  <dd> 
+				Uses a slightly modified soundex algorithm to match 
+				words. This requires that the soundex database be 
+				present. It is generated with the 
+				<ref type="program">htfuzzy</ref> program. 
+			  </dd> 
+			  <dt> 
+				metaphone 
+			  </dt> 
+			  <dd> 
+				Uses the metaphone algorithm for matching words. 
+				This algorithm is more specific to the english 
+				language than soundex. It requires the metaphone 
+				database, which is generated with the <ref type="program">htfuzzy</ref> program. 
+			  </dd> 
+			  <dt> 
+				accents 
+			  </dt> 
+			  <dd> 
+				Uses the accents algorithm for matching words. 
+				This algorithm will treat all accented letters 
+				as equivalent to their unaccented counterparts. 
+				It requires the accents database, which is 
+				generated with the <ref type="program">htfuzzy</ref> program. 
+			  </dd> 
+			  <dt> 
+				endings 
+			  </dt> 
+			  <dd> 
+				This algorithm uses language specific word endings 
+				to find matches. Each word is first reduced to its 
+				word root and then all known legal endings are used 
+				for the matching. This algorithm uses two databases 
+				which are generated with <ref type="program">htfuzzy</ref>. 
+			  </dd> 
+			  <dt> 
+				synonyms 
+			  </dt> 
+			  <dd> 
+				Performs a dictionary lookup on all the words. This 
+				algorithm uses a database generated with the <ref type="program">htfuzzy</ref> program. 
+			  </dd> 
+			<dt> 
+			substring 
+			</dt> 
+			<dd> 
+			  Matches all words containing the queries as 
+			  substrings. Since this requires checking every word in 
+			  the database, this can really slow down searches 
+			  considerably. 
+			</dd> 
+			<dt> 
+			  prefix 
+			</dt> 
+			<dd> 
+			  Matches all words beginning with the query 
+			  strings. Uses the option <ref type="attr">prefix_match_character</ref> 
+			  to decide whether a query requires prefix 
+			  matching. For example "abc*" would perform prefix 
+			  matching on "abc" since * is the default 
+			  prefix_match_character. 
+			</dd> 
+			<dt> 
+			regex 
+			</dt> 
+			<dd> 
+			  Matches all words that match the patterns given as regular  
+			  expressions. Since this requires checking every word in 
+			  the database, this can really slow down searches 
+			  considerably. 
+			</dd> 
+			<dt> 
+			speling 
+			</dt> 
+			<dd> 
+			  A simple fuzzy algorithm that tries to find one-off spelling  
+			  mistakes, such as transposition of two letters or an extra character. 
+			  Since this usually generates just a few possibilities, it is  
+			  relatively quick. 
+			</dd> 
+			</dl> 
+     </description>
+   </attribute>
+
+   <attribute name="search_results_footer" 
+              type="string" 
+              programs="htsearch" 
+              version="all" 
+              category="Presentation:Files" >
+     <default>${common_dir}/footer.html</default>
+     <example>/usr/local/etc/ht/end-stuff.html</example>
+     <description> 
+			This specifies a filename to be output at the end of 
+			search results. While outputting the footer, some 
+			variables will be expanded. Variables use the same 
+			syntax as the Bourne shell. If there is a variable VAR, 
+			the following will all be recognized: 
+			<ul> 
+			  <li> 
+				$VAR 
+			  </li> 
+			  <li> 
+				$(VAR) 
+			  </li> 
+			  <li> 
+				${VAR} 
+			  </li> 
+			</ul> 
+	The following variables are available.  See 
+	<a href="hts_template.html">hts_template.html</a> for a complete 
+	list. 
+			<dl> 
+			  <dt> 
+				MATCHES 
+			  </dt> 
+			  <dd> 
+				The number of documents that were matched. 
+			  </dd> 
+			  <dt> 
+				PLURAL_MATCHES 
+			  </dt> 
+			  <dd> 
+				If MATCHES is not 1, this will be the string "s", 
+				else it is an empty string. This can be used to say 
+				something like "$(MATCHES) 
+				document$(PLURAL_MATCHES) were found" 
+			  </dd> 
+			  <dt> 
+				MAX_STARS 
+			  </dt> 
+			  <dd> 
+				The value of the <ref type="attr">max_stars</ref> 
+				attribute. 
+			  </dd> 
+			  <dt> 
+				LOGICAL_WORDS 
+			  </dt> 
+			  <dd> 
+				A string of the search words with either "and" or 
+				"or" between the words, depending on the type of 
+				search. 
+			  </dd> 
+			  <dt> 
+				WORDS 
+			  </dt> 
+			  <dd> 
+				A string of the search words with spaces in 
+				between. 
+			  </dd> 
+			  <dt> 
+				PAGEHEADER 
+			  </dt> 
+			  <dd> 
+				This expands to either the value of the 
+				<ref type="attr">page_list_header</ref> or 
+				<ref type="attr">no_page_list_header</ref> 
+				attribute depending on how many pages there are. 
+			  </dd> 
+			</dl> 
+			Note that this file will <strong>NOT</strong> be output 
+			if no matches were found. In this case the 
+			<ref type="attr">nothing_found_file</ref> 
+			attribute is used instead. 
+			Also, this file will not be output if it is 
+			overridden by defining the 
+			<ref type="attr">search_results_wrapper</ref> 
+			attribute. 
+     </description>
+   </attribute>
+
+   <attribute name="search_results_header" 
+              type="string" 
+              programs="htsearch" 
+              version="all" 
+              category="Presentation:Files" >
+     <default>${common_dir}/header.html</default>
+     <example>/usr/local/etc/ht/start-stuff.html</example>
+     <description> 
+			This specifies a filename to be output at the start of 
+			search results. While outputting the header, some 
+			variables will be expanded. Variables use the same 
+			syntax as the Bourne shell. If there is a variable VAR, 
+			the following will all be recognized: 
+			<ul> 
+			  <li> 
+				$VAR 
+			  </li> 
+			  <li> 
+				$(VAR) 
+			  </li> 
+			  <li> 
+				${VAR} 
+			  </li> 
+			</ul> 
+	The following variables are available.  See 
+	<a href="hts_template.html">hts_template.html</a> for a complete 
+	list. 
+	<!-- Do these need to be listed for both _footer and _header? --> 
+			<dl> 
+			  <dt> 
+				MATCHES 
+			  </dt> 
+			  <dd> 
+				The number of documents that were matched. 
+			  </dd> 
+			  <dt> 
+				PLURAL_MATCHES 
+			  </dt> 
+			  <dd> 
+				If MATCHES is not 1, this will be the string "s", 
+				else it is an empty string. This can be used to say 
+				something like "$(MATCHES) 
+				document$(PLURAL_MATCHES) were found" 
+			  </dd> 
+			  <dt> 
+				MAX_STARS 
+			  </dt> 
+			  <dd> 
+				The value of the <ref type="attr">max_stars</ref> 
+				attribute. 
+			  </dd> 
+			  <dt> 
+				LOGICAL_WORDS 
+			  </dt> 
+			  <dd> 
+				A string of the search words with either "and" or 
+				"or" between the words, depending on the type of 
+				search. 
+			  </dd> 
+			  <dt> 
+				WORDS 
+			  </dt> 
+			  <dd> 
+				A string of the search words with spaces in 
+				between. 
+			  </dd> 
+			</dl> 
+			Note that this file will <strong>NOT</strong> be output 
+			if no matches were found. In this case the 
+			<ref type="attr">nothing_found_file</ref> 
+			attribute is used instead. 
+			Also, this file will not be output if it is 
+			overridden by defining the 
+			<ref type="attr">search_results_wrapper</ref> 
+			attribute. 
+     </description>
+   </attribute>
+
+   <attribute name="search_results_order" 
+              type="string_list" 
+              programs="htsearch" 
+              version="3.2.0b2" 
+              category="Searching:Ranking" >
+     <default></default>
+     <example>/docs/|faq.html * /maillist/ /testresults/</example>
+     <description> 
+	This specifies a list of patterns for URLs in 
+	search results.  Results will be displayed in the 
+	specified order, with the search algorithm result 
+	as the second order.  Remaining areas, that do not 
+	match any of the specified patterns, can be placed 
+	by using * as the pattern.  If no * is specified, 
+	one will be implicitly placed at the end of the 
+	list.<br/> 
+	See also <ref type="attr">url_seed_score</ref>. 
+     </description>
+   </attribute>
+
+   <attribute name="search_results_wrapper" 
+              type="string" 
+              programs="htsearch" 
+              version="3.1.0" 
+              category="Presentation:Files" >
+     <default></default>
+     <example>${common_dir}/wrapper.html</example>
+     <description> 
+	This specifies a filename to be output at the start and 
+	end of search results. This file replaces the 
+	<ref type="attr">search_results_header</ref> and 
+	<ref type="attr">search_results_footer</ref> 
+	files, with the contents of both in one file, and uses the 
+	pseudo-variable <strong>$(HTSEARCH_RESULTS)</strong> as a 
+	separator for the header and footer sections. 
+	If the filename is not specified, the file is unreadable, 
+	or the pseudo-variable above is not found, htsearch reverts 
+	to the separate header and footer files instead. 
+	While outputting the wrapper, 
+	some variables will be expanded, just as for the 
+	<ref type="attr">search_results_header</ref> and 
+	<ref type="attr">search_results_footer</ref> 
+	files.<br/> 
+	Note that this file will <strong>NOT</strong> be output 
+	if no matches were found. In this case the 
+	<ref type="attr">nothing_found_file</ref> 
+	attribute is used instead. 
+     </description>
+   </attribute>
+
+   <attribute name="search_rewrite_rules" 
+              type="string list" 
+              programs="htsearch" 
+              version="3.1.6" 
+              category="URLs" >
+     <default></default>
+     <example> http://(.*)\\.mydomain\\.org/([^/]*)  http://\\2.\\1.com \
+	       http://www\\.myschool\\.edu/myorgs/([^/]*)  http://\\1.org
+     </example>
+     <description> 
+	This is a list of pairs, <em>regex</em> <em>replacement</em>, used
+	to rewrite URLs in the search results. The left hand string is a
+	regular expression; the right hand string is a literal string with
+	embedded placeholders for fragments that matched inside brackets in the
+	regular expression. \0 is the whole matched string, \1 to \9 are
+	bracketted substrings. The backslash must be doubled-up in the
+	attribute setting to get past the variable expansion parsing. Rewrite
+	rules are applied sequentially to each URL before it is displayed
+	or checked against the <ref type="attr">restrict</ref> or
+	<ref type="attr">exclude</ref> lists. Rewriting does not stop once a
+	match has been made, so multiple rules may affect a given URL. See
+	also <ref type="attr">url_part_aliases</ref> which allows URLs
+	to be of one form during indexing and translated for results,
+	and <ref type="attr">url_rewrite_rules</ref> which allows URLs
+	to be rewritten while indexing.
+     </description>
+   </attribute>
+
+   <attribute name="server_aliases" 
+              type="string_list" 
+              programs="htdig" 
+              version="3.1.0b2" 
+              category="Indexing:Where" >
+     <default></default>
+     <example>foo.mydomain.com:80=www.mydomain.com:80 \ 
+				  bar.mydomain.com:80=www.mydomain.com:80 
+</example>
+     <description> 
+	This attribute tells the indexer that servers have several 
+	DNS aliases, which all point to the same machine and are NOT 
+	virtual hosts. This allows you to ensure pages are indexed 
+	only once on a given machine, despite the alias used in a URL. 
+	As shown in the example, the mapping goes from left to right, 
+	so the server name on the right hand side is the one that is 
+	used. As of version 3.1.3, the port number is optional, and is 
+	assumed to be 80 if omitted. There is no easy way to map all 
+	ports from one alias to another without listing them all. 
+     </description>
+   </attribute>
+
+   <attribute name="server_max_docs" 
+              type="integer" 
+              programs="htdig" 
+              version="3.1.0b3" 
+              category="Indexing:Where" 
+              block="Server" >
+     <default>-1</default>
+     <example>50</example>
+     <description> 
+	This attribute tells htdig to limit the dig to retrieve a maximum 
+	number of documents from each server. This can cause 
+	unusual behavior on update digs since the old URLs are 
+	stored alphabetically. Therefore, update digs will add 
+	additional URLs in pseudo-alphabetical order, up to the 
+	limit of the attribute. However, it is most useful to 
+	partially index a server as the URLs of additional 
+	documents are entered into the database, marked as never 
+	retrieved.<br/> 
+	A value of -1 specifies no limit. 
+     </description>
+   </attribute>
+
+   <attribute name="server_wait_time" 
+              type="integer" 
+              programs="htdig" 
+              version="3.1.0b3" 
+              category="Indexing:Connection" 
+              block="Server" >
+     <default>0</default>
+     <example>20</example>
+     <description> 
+	This attribute tells htdig to ensure a server has had a 
+	delay (in seconds) from the beginning of the last 
+	connection. This can be used to prevent "server abuse" 
+	by digging without delay. It's recommended to set this 
+	to 10-30 (seconds) when indexing servers that you don't 
+	monitor yourself. Additionally, this attribute can slow 
+	down local indexing if set, which may or may not be what 
+	you intended. 
+     </description>
+   </attribute>
+
+   <attribute name="sort" 
+              type="string" 
+              programs="htsearch" 
+              version="3.1.0" 
+              category="Presentation:How" >
+     <default>score</default>
+     <example>revtime</example>
+     <description> 
+	This is the default sorting method that htsearch 
+	uses to determine the order in which matches are displayed. 
+	The valid choices are: 
+	<table border="0"> 
+	<tr> 
+	<td> 
+	<ul> 
+	     <li> score </li> 
+	     <li> time </li> 
+	     <li> title </li> 
+	</ul> 
+	</td> 
+	<td> 
+	<ul> 
+	     <li> revscore </li> 
+	     <li> revtime </li> 
+	     <li> revtitle </li> 
+	</ul> 
+	</td> 
+	</tr> 
+	</table> 
+	This attribute will only be used if the HTML form that 
+	calls htsearch didn't have the <strong>sort</strong> 
+	value set. The words date and revdate can be used instead 
+	of time and revtime, as both will sort by the time that 
+	the document was last modified, if this information is 
+	given by the server. The default is to sort by the score, 
+	which ranks documents by best match. The sort methods that 
+	begin with "rev" simply reverse the order of the 
+	sort. Note that setting this to something other than 
+	"score" will incur a slowdown in searches. 
+     </description>
+   </attribute>
+
+   <attribute name="sort_names" 
+              type="quoted_string_list" 
+              programs="htsearch" 
+              version="3.1.0" 
+              category="Searching:UI" >
+     <default>score Score time Time title Title revscore 'Reverse Score' revtime 'Reverse Time' revtitle 'Reverse Title'</default>
+     <example>score 'Best Match' time Newest title A-Z \ 
+				  revscore 'Worst Match' revtime Oldest revtitle Z-A 
+</example>
+     <description> 
+	These values are used to create the <strong> 
+	sort</strong> menu. It consists of pairs. The first 
+	element of each pair is one of the known sort methods, the 
+	second element is the text that will be shown in the 
+	menu for that sort method. This text needs to be quoted if 
+	it contains spaces. 
+	See the <a href="hts_selectors.html">select list documentation</a> 
+	for more information on how this attribute is used. 
+     </description>
+   </attribute>
+
+   <attribute name="soundex_db" 
+              type="string" 
+              programs="htfuzzy htsearch" 
+              version="all" 
+              category="File Layout" >
+     <default>${database_base}.soundex.db</default>
+     <example>${database_base}.snd.db</example>
+     <description> 
+	The database file used for the fuzzy "soundex" search 
+	algorithm. This database is created by 
+	<ref type="program">htfuzzy</ref> and used by 
+	<ref type="program">htsearch</ref>. 
+     </description>
+   </attribute>
+
+   <attribute name="star_blank" 
+              type="string" 
+              programs="htsearch" 
+              version="all" 
+              category="Presentation:Text" >
+     <default>${image_url_prefix}/star_blank.gif</default>
+     <example>//www.somewhere.org/icons/noelephant.gif</example>
+     <description> 
+	This specifies the URL to use to display a blank of the 
+	same size as the star defined in the 
+	<ref type="attr">star_image</ref> attribute or in the 
+	<ref type="attr">star_patterns</ref> attribute. 
+     </description>
+   </attribute>
+
+   <attribute name="star_image" 
+              type="string" 
+              programs="htsearch" 
+              version="all" 
+              category="Presentation:Text" >
+     <default>${image_url_prefix}/star.gif</default>
+     <example>//www.somewhere.org/icons/elephant.gif</example>
+     <description> 
+	This specifies the URL to use to display a star. This 
+	allows you to use some other icon instead of a star. 
+	(We like the star...)<br/> 
+	The display of stars can be turned on or off with the 
+	<ref type="attr">use_star_image</ref> 
+	attribute and the maximum number of stars that can be 
+	displayed is determined by the 
+	<ref type="attr">max_stars</ref> attribute.<br/> 
+	Even though the image can be changed, the ALT value 
+	for the image will always be a '*'. 
+     </description>
+   </attribute>
+
+   <attribute name="star_patterns" 
+              type="string_list" 
+              programs="htsearch" 
+              version="3.0" 
+              category="Presentation:How" >
+     <default></default>
+     <example>http://www.sdsu.edu /sdsu.gif \ 
+				  http://www.ucsd.edu /ucsd.gif 
+</example>
+     <description> 
+	This attribute allows the star image to be changed 
+	depending on the URL or the match it is used for. This 
+	is mainly to make a visual distinction between matches 
+	on different web sites. The star image could be 
+	replaced with the logo of the company the match refers 
+	to.<br/> 
+	It is advisable to keep all the images the same size 
+	in order to line things up properly in a short result 
+	listing.<br/> 
+	The format is simple. It is a list of pairs. The first 
+	element of each pair is a pattern, the second element 
+	is a URL to the image for that pattern. 
+     </description>
+   </attribute>
+
+   <attribute name="startday" 
+              type="integer" 
+              programs="htsearch" 
+              version="3.1.6" 
+              category="Searching:Method" >
+     <default></default>
+     <example>1</example>
+     <description> 
+	Day component of first date allowed as last-modified date 
+	of returned docutments. 
+	This is most usefully specified as a 
+	<a href="hts_form.html#startyear">GCI argument</a>. 
+	See also <ref type="attr">startyear</ref>. 
+     </description>
+   </attribute>
+
+   <attribute name="start_ellipses" 
+              type="string" 
+              programs="htsearch" 
+              version="all" 
+              category="Presentation:Text" >
+     <default>&lt;strong&gt;&lt;code&gt;... &lt;/code&gt;&lt;/strong&gt;</default>
+     <example>...</example>
+     <description> 
+	When excerpts are displayed in the search output, this 
+	string will be prepended to the excerpt if there is 
+	text before the text displayed. This is just a visual 
+	reminder to the user that the excerpt is only part of 
+	the complete document. 
+     </description>
+   </attribute>
+
+   <attribute name="start_highlight" 
+              type="string" 
+              programs="htsearch" 
+              version="3.1.4" 
+              category="Presentation:Text" >
+     <default>&lt;strong&gt;</default>
+     <example>&lt;font color="#FF0000"&gt;</example>
+     <description> 
+	When excerpts are displayed in the search output, matched 
+	words will be highlighted using this string and 
+	<ref type="attr">end_highlight</ref>. 
+	You should ensure that highlighting tags are balanced, 
+	that is, any formatting tags that this string 
+	opens should be closed by end_highlight. 
+     </description>
+   </attribute>
+
+   <attribute name="startmonth" 
+              type="integer" 
+              programs="htsearch" 
+              version="3.1.6" 
+              category="Searching:Method" >
+     <default></default>
+     <example>1</example>
+     <description> 
+	Month component of first date allowed as last-modified date 
+	of returned docutments. 
+	This is most usefully specified as a 
+	<a href="hts_form.html#startyear">GCI argument</a>. 
+	See also <ref type="attr">startyear</ref>. 
+     </description>
+   </attribute>
+
+   <attribute name="start_url" 
+              type="string_list" 
+              programs="htdig" 
+              version="all" 
+              category="Indexing:Where" >
+     <default>http://www.htdig.org/</default>
+     <example>//www.somewhere.org/alldata/index.html</example>
+     <description> 
+	This is the list of URLs that will be used to start a 
+	dig when there was no existing database. Note that 
+	multiple URLs can be given here. 
+	<br/>Note also that the value of <em>start_url</em>
+	will be the default value for
+	<href type="attr">limit_urls_to</ref>, so if
+	you set start_url to the URLs for specific files,
+	rather than a site or subdirectory URL, you may need
+	to set limit_urls_to to something less restrictive
+	so htdig doesn't reject links in the documents.
+     </description>
+   </attribute>
+
+   <attribute name="startyear" 
+              type="integer" 
+              programs="htsearch" 
+              version="3.1.6" 
+              category="Searching:Method" >
+     <default>1970</default>
+     <example>2001</example>
+     <description> 
+	This specifies the year of the cutoff start date for 
+	search results. If the start or end date are specified, 
+	only results with a last modified date within this 
+	range are shown. 
+	See also <ref type="attr">startday</ref>, 
+	<ref type="attr">startmonth</ref>, 
+	<ref type="attr">endday</ref>, 
+	<ref type="attr">endmonth</ref>, 
+	<a href="endyear">endyear</a>. 
+	These are most usefully specified as a 
+	<a href="hts_form.html#startyear">GCI argument</a>.<br/> 
+	For each component, if a negative number is given, 
+	it is taken as relative to the current date. 
+	Relative days can span several months or even years if desired, 
+	and relative months can span several years. A startday of 
+	-90 will select matching documents modified within 
+	the last 90 days. 
+     </description>
+   </attribute>
+
+   <attribute name="substring_max_words" 
+              type="integer" 
+              programs="htsearch" 
+              version="3.0.8b1" 
+              category="Searching:Method" >
+     <default>25</default>
+     <example>100</example>
+     <description> 
+	The Substring fuzzy algorithm could potentially match a 
+	very large number of words. This value limits the 
+	number of words each substring pattern can match. Note 
+	that this does not limit the number of documents that 
+	are matched in any way. 
+     </description>
+   </attribute>
+
+   <attribute name="synonym_db" 
+              type="string" 
+              programs="htsearch htfuzzy" 
+              version="3.0" 
+              category="File Layout" >
+     <default>${common_dir}/synonyms.db</default>
+     <example>${database_base}.syn.db</example>
+     <description> 
+	Points to the database that <ref type="program">htfuzzy</ref> creates when the <strong>synonyms</strong> 
+	algorithm is used.<br/> 
+	<ref type="program">htsearch</ref> 
+	uses this to perform synonym dictionary lookups. 
+     </description>
+   </attribute>
+
+   <attribute name="synonym_dictionary" 
+              type="string" 
+              programs="htfuzzy" 
+              version="3.0" 
+              category="File Layout" >
+     <default>${common_dir}/synonyms</default>
+     <example>/usr/dict/synonyms</example>
+     <description> 
+	This points to a text file containing the synonym 
+	dictionary used for the synonyms search algorithm.<br/> 
+	Each line of this file has at least two words. The 
+	first word is the word to replace, the rest of the 
+	words are synonyms for that word. 
+     </description>
+   </attribute>
+
+   <attribute name="syntax_error_file" 
+              type="string" 
+              programs="htsearch" 
+              version="all" 
+              category="Presentation:Files" >
+     <default>${common_dir}/syntax.html</default>
+     <example>${common_dir}/synerror.html</example>
+     <description> 
+	This points to the file which will be displayed if a 
+	boolean expression syntax error was found. 
+     </description>
+   </attribute>
+
+   <attribute name="tcp_max_retries" 
+              type="integer" 
+              programs="htdig" 
+              version="3.2.0b1" 
+              category="Indexing:Connection" 
+              block="Server" >
+     <default>1</default>
+     <example>6</example>
+     <description> 
+	 This option set the maximum number of attempts when a connection 
+	 <ref type="attr">timeout</ref>s. 
+	 After all these retries, the connection attempt results &lt;timed out&gt;. 
+     </description>
+   </attribute>
+
+   <attribute name="tcp_wait_time" 
+              type="integer" 
+              programs="htdig" 
+              version="3.2.0b1" 
+              category="Indexing:Connection" 
+              block="Server" >
+     <default>5</default>
+     <example>10</example>
+     <description> 
+	 This attribute sets the wait time (in seconds) after a connection 
+	 fails and the <ref type="attr">timeout</ref> is raised. 
+     </description>
+   </attribute>
+
+   <attribute name="template_map" 
+              type="quoted_string_list" 
+              programs="htsearch" 
+              version="3.0" 
+              category="Presentation:Files,Searching:UI" >
+     <default>Long builtin-long builtin-long Short builtin-short builtin-short</default>
+     <example>Short short ${common_dir}/short.html \ 
+				  Normal normal builtin-long \ 
+				  Detailed detail ${common_dir}/detail.html 
+</example>
+     <description> 
+	This maps match template names to internal names and 
+	template file names. It is a list of triplets. The 
+	first element in each triplet is the name that will be 
+	displayed in the FORMAT menu. The second element is the 
+	name used internally and the third element is a 
+	filename of the template to use.<br/> 
+	There are two predefined templates, namely <strong> 
+	builtin-long</strong> and <strong> 
+	builtin-short</strong>. If the filename is one of 
+	those, they will be used instead.<br/> 
+	More information about templates can be found in the 
+	<ref type="program">htsearch</ref> 
+	documentation.  The particular template is selecterd by the 
+	<a href="hts_form.html#format">format</a> cgi argument, and the 
+	default is given by <ref type="attr">template_name</ref> in 
+	the config file. 
+     </description>
+   </attribute>
+
+   <attribute name="template_name" 
+              type="string" 
+              programs="htsearch" 
+              version="3.0" 
+              category="Searching:UI,Presentation:How" >
+     <default>builtin-long</default>
+     <example>long</example>
+     <description> 
+	Specifies the default template if no
+	<a href="hts_form.html#format">format</a> field is given by the 
+	search form. This needs to map to the 
+	<ref type="attr">template_map</ref>. 
+     </description>
+   </attribute>
+
+   <attribute name="template_patterns" 
+              type="string_list" 
+              programs="htsearch" 
+              version="3.1.4" 
+              category="Presentation:How" >
+     <default></default>
+     <example>http://www.sdsu.edu ${common_dir}/sdsu.html \ 
+				  http://www.ucsd.edu ${common_dir}/ucsd.html 
+</example>
+     <description> 
+	This attribute allows the results template to be changed 
+	depending on the URL or the match it is used for. This 
+	is mainly to make a visual distinction between matches 
+	on different web sites. The results for each site could 
+	thus be shown in a style matching that site.<br/> 
+	The format is simply a list of pairs. The first 
+	element of each pair is a pattern, the second element 
+	is the name of the template file for that pattern.<br/> 
+	More information about templates can be found in the 
+	<ref type="program">htsearch</ref> 
+	documentation.<br/> 
+	Normally, when using this template selection method, you 
+	would disable user selection of templates via the <strong>format</strong> 
+	input parameter in search forms, as the two methods were not 
+	really designed to interact. Templates selected by URL patterns 
+	would override any user selection made in the form. If you want 
+	to use the two methods together, see the notes on 
+	<a href="hts_selectors.html#template_patterns">combining</a> 
+	them for an example of how to do this. 
+     </description>
+   </attribute>
+
+   <attribute name="text_factor" 
+              type="number" 
+              programs="htsearch" 
+              version="3.0" 
+              category="Searching:Ranking" >
+     <default>1</default>
+     <example>0</example>
+     <description> 
+	This is a factor which will be used to multiply the 
+	weight of words that are not in any special part of a 
+	document. Setting a factor to 0 will cause normal words 
+	to be ignored. The number may be a floating point 
+	number. See also the <ref type="attr">heading_factor</ref> 
+	attribute. 
+     </description>
+   </attribute>
+
+   <attribute name="timeout" 
+              type="integer" 
+              programs="htdig" 
+              version="all" 
+              category="Indexing:Connection" 
+              block="Server" >
+     <default>30</default>
+     <example>42</example>
+     <description> 
+	Specifies the time the digger will wait to complete a 
+	network read. This is just a safeguard against 
+	unforeseen things like the all too common 
+	transformation from a network to a notwork.<br/> 
+	The timeout is specified in seconds. 
+     </description>
+   </attribute>
+
+   <attribute name="title_factor" 
+              type="number" 
+              programs="htsearch" 
+              version="all" 
+              category="Searching:Ranking" >
+     <default>100</default>
+     <example>12</example>
+     <description> 
+	This is a factor which will be used to multiply the 
+	weight of words in the title of a document. Setting a 
+	factor to 0 will cause words in the title to be 
+	ignored. The number may be a floating point number. See 
+	also the <ref type="attr">heading_factor</ref> attribute. 
+     </description>
+   </attribute>
+
+   <attribute name="url_list" 
+              type="string" 
+              programs="htdig" 
+              version="all" 
+              category="Extra Output" >
+     <default>${database_base}.urls</default>
+     <example>/tmp/urls</example>
+     <description> 
+	This file is only created if 
+	<ref type="attr">create_url_list</ref> is set to 
+	true. It will contain a list of all URLs that were 
+	seen. 
+     </description>
+   </attribute>
+
+   <attribute name="url_log" 
+              type="string" 
+              programs="htdig" 
+              version="3.1.0" 
+              category="Extra Output" >
+     <default>${database_base}.log</default>
+     <example>/tmp/htdig.progress</example>
+     <description> 
+	If <ref type="program">htdig</ref> is run with the -l option 
+	and interrupted, it will write out its progress to this 
+	file. Note that if it has a large number of URLs to write, 
+	it may take some time to exit. This can especially happen 
+	when running update digs and the run is interrupted soon 
+	after beginning. 
+     </description>
+   </attribute>
+
+   <attribute name="url_part_aliases" 
+              type="string_list" 
+              programs="all" 
+              version="3.1.0" 
+              category="URLs" >
+     <default></default>
+     <example>http://search.example.com/~htdig *site \ 
+				   http://www.htdig.org/this/ *1 \ 
+				   .html *2
+     </example>
+     <example>http://www.htdig.org/ *site \ 
+				   http://www.htdig.org/that/ *1 \ 
+				   .htm *2 
+</example>
+     <description> 
+	A list of translations pairs <em>from</em> and 
+	<em>to</em>, used when accessing the database. 
+	If a part of an URL matches with the 
+	<em>from</em>-string of each pair, it will be 
+	translated into the <em>to</em>-string just before 
+	writing the URL to the database, and translated 
+	back just after reading it from the database.<br/> 
+	This is primarily used to provide an easy way to 
+	rename parts of URLs for e.g. changing 
+	www.example.com/~htdig to www.htdig.org.  Two 
+	different configuration files for digging and 
+	searching are then used, with url_part_aliases 
+	having different <em>from</em> strings, but 
+	identical <em>to</em>-strings.<br/> 
+	See also <ref type="attr">common_url_parts</ref>.<br/> 
+	Strings that are normally incorrect in URLs or 
+	very seldom used, should be used as 
+	<em>to</em>-strings, since extra storage will be 
+	used each time one is found as normal part of a 
+	URL.  Translations will be performed with priority 
+	for the leftmost longest match.	 Each 
+	<em>to</em>-string must be unique and not be a 
+	part of any other <em>to</em>-string.<br/> 
+	Note that when this attribute is changed, the 
+	database should be rebuilt, unless the effect of 
+	"moving" the affected URLs in the database is 
+	wanted, as described above.<br/> 
+	<strong>Please note:</strong> Don't just copy the 
+	example below into a single configuration file. 
+	There are two separate settings of 
+	<em>url_part_aliases</em> below; the first one is 
+	for the configuration file to be used by htdig, 
+	htmerge, and htnotify, and the second one is for the 
+	configuration file to be used by htsearch. 
+     </description>
+   </attribute>
+
+   <attribute name="url_rewrite_rules" 
+              type="string_list" 
+              programs="htdig" 
+              version="3.2.0b3" 
+              category="URLs" >
+     <default></default>
+     <example>(.*)\\?JServSessionIdroot=.*		\\1 \ 
+			(.*)\\&amp;JServSessionIdroot=.*		\\1 \ 
+			(.*)&amp;context=.*				\\1</example>
+     <description> 
+	This is a list of pairs, <em>regex</em> <em>replacement</em> used to 
+	permanently rewrite URLs as they are indexed. The left hand string is 
+	a regex; the right hand string is  a literal string with embedded 
+	placeholders for fragments that matched  inside brackets in the 
+	regex. \0 is the whole matched string, \1 to \9 are  bracketted 
+	substrings. Rewrite rules are applied sequentially to each  
+	incoming URL  before normalization occurs. Rewriting does not stop 
+	once a match has been made, so multiple rules may affect a given URL. 
+	See also <ref type="attr">url_part_aliases</ref> which 
+	allows URLs to be of one  
+form during indexing and translated for results. 
+     </description>
+   </attribute>
+
+   <attribute name="url_seed_score" 
+              type="string_list" 
+              programs="htsearch" 
+              version="3.2.0b2" 
+              category="Searching::Ranking" >
+     <default></default>
+     <example>/mailinglist/ *.5-1e6  
+	      /docs/|/news/ *1.5  
+	      /testresults/ &quot;*.7 -200&quot;  
+	      /faq-area/ *2+10000</example>
+     <description> 
+	This is a list of pairs, <em>pattern</em> 
+	<em>formula</em>, used to weigh the score of 
+	hits, depending on the URL of the document.<br/> 
+	The <em>pattern</em> part is a substring to match 
+	against the URL.  Pipe ('|') characters can be 
+	used in the pattern to concatenate substrings for 
+	web-areas that have the same formula.<br/> 
+	The formula describes a <em>factor</em> and a 
+	<em>constant</em>, by which the hit score is 
+	weighed.  The <em>factor</em> part is multiplied 
+	to the original score, then the <em>constant</em> 
+	part is added.<br/> 
+	The format of the formula is the factor part: 
+	&quot;*<em>N</em>&quot; optionally followed by comma and 
+	spaces, followed by the constant part : 
+	&quot;+<em>M</em>&quot;, where the plus sign may be emitted 
+	for negative numbers.  Either part is optional, 
+	but must come in this order.<br/> 
+	The numbers <em>N</em> and <em>M</em> are floating 
+	point constants.<br/> 
+	More straightforward is to think of the format as 
+	&quot;newscore = oldscore*<em>N</em>+<em>M</em>&quot;, 
+	but with the &quot;newscore = oldscore&quot; part left out. 
+     </description>
+   </attribute>
+
+   <attribute name="url_text_factor" 
+              type="number" 
+              programs="htsearch" 
+              version="??" 
+              category="Searching:Ranking" >
+     <default>1</default>
+     <example>1</example>
+     <description> 
+	TO BE COMPLETED<br/> 
+	See also <ref type="attr">heading_factor</ref>. 
+     </description>
+   </attribute>
+
+   <attribute name="use_doc_date" 
+              type="boolean" 
+              programs="htdig" 
+              version="3.2.0b1" 
+              category="Indexing:How" >
+     <default>false</default>
+     <example>true</example>
+     <description> 
+	If set to true, htdig will use META date tags in documents, 
+	overriding the modification date returned by the server. 
+	Any documents that do not have META date tags will retain 
+	the last modified date returned by the server or found on 
+	the local file system. 
+     </description>
+   </attribute>
+
+   <attribute name="use_meta_description" 
+              type="boolean" 
+              programs="htsearch" 
+              version="3.1.0b1" 
+              category="Presentation:How" >
+     <default>false</default>
+     <example>true</example>
+     <description> 
+	If set to true, any META description tags will be used as 
+	excerpts by htsearch. Any documents that do not have META 
+	descriptions will retain their normal excerpts. 
+     </description>
+   </attribute>
+
+   <attribute name="use_star_image" 
+              type="boolean" 
+              programs="htsearch" 
+              version="all" 
+              category="Presentation:How" >
+     <default>true</default>
+     <example>no</example>
+     <description> 
+	If set to true, the <ref type="attr">star_image</ref> attribute is used to display upto 
+	<ref type="attr">max_stars</ref> images for 
+	each match. 
+     </description>
+   </attribute>
+
+   <attribute name="user_agent" 
+              type="string" 
+              programs="htdig" 
+              version="3.1.0b2" 
+              category="Indexing:Out" 
+              block="Server" >
+     <default>htdig</default>
+     <example>htdig-digger</example>
+     <description> 
+	This allows customization of the user_agent: field sent when 
+	the digger requests a file from a server. 
+     </description>
+   </attribute>
+
+   <attribute name="valid_extensions" 
+              type="string_list" 
+              programs="htdig" 
+              version="3.1.4" 
+              category="Indexing:Where" 
+              block="URL" >
+     <default></default>
+     <example>.html .htm .shtml</example>
+     <description> 
+	This is a list of extensions on URLs which are 
+	the only ones considered acceptable. This list is used to 
+	supplement the MIME-types that the HTTP server provides 
+	with documents. Some HTTP servers do not have a correct 
+	list of MIME-types and so can advertise certain 
+	documents as text while they are some binary format. 
+	If the list is empty, then all extensions are acceptable, 
+	provided they pass other criteria for acceptance or rejection. 
+	If the list is not empty, only documents with one of the 
+	extensions in the list are parsed. 
+	See also <ref type="attr">bad_extensions</ref>. 
+     </description>
+   </attribute>
+
+   <attribute name="valid_punctuation" 
+              type="string" 
+              programs="htdig htsearch" 
+              version="all" 
+              category="Indexing:What" >
+     <default>.-_/!#$%^&amp;'</default>
+     <example>-'</example>
+     <description> 
+	This is the set of characters which will be deleted 
+	from the document before determining what a word is. 
+	This means that if a document contains something like 
+	<code>Andrew's</code> the digger will see this as <code> 
+	Andrews</code>.<br/> 
+	The same transformation is performed on the keywords 
+	the search engine gets.<br/> 
+	See also the <ref type="attr">extra_word_characters</ref> 
+	attribute. 
+     </description>
+   </attribute>
+
+   <attribute name="version" 
+              type="string" 
+              programs="htsearch" 
+              version="all" 
+              category="Presentation:Text" >
+     <default configmacro="true">VERSION</default>
+     <example>3.2.0</example>
+     <description> 
+	This specifies the value of the VERSION 
+	variable which can be used in search templates. 
+	The default value of this attribute is determined 
+	at compile time, and will not normally be set 
+	in configuration files. 
+     </description>
+   </attribute>
+
+   <attribute name="word_db" 
+              type="string" 
+              programs="all" 
+              version="all" 
+              category="File Layout" >
+     <default>${database_base}.words.db</default>
+     <example>${database_base}.allwords.db</example>
+     <description> 
+	This is the main word database. It is an index of all 
+	the words to a list of documents that contain the 
+	words. This database can grow large pretty quickly. 
+     </description>
+   </attribute>
+
+   <attribute name="word_dump" 
+              type="string" 
+              programs="htdig htdump htload" 
+              version="3.2.0b1" 
+              category="File Layout" >
+     <default>${database_base}.worddump</default>
+     <example>/tmp/words.txt</example>
+     <description> 
+	This file is basically a text version of the file 
+	specified in <ref type="attr">word_db</ref>. Its 
+	only use is to have a human readable database of all 
+	words. The file is easy to parse with tools like 
+	perl or tcl. 
+     </description>
+   </attribute>
+
+   <attribute name="wordlist_cache_size" 
+              type="integer" 
+              programs="all" 
+              version="3.2.0b1" 
+              category="Indexing:How" >
+     <default>10000000</default>
+     <example>40000000</example>
+     <description> 
+	Size of memory cache used by Berkeley DB (DB used by the indexer) 
+	IMPORTANT: It  makes a <strong>huge</strong> difference. The rule  
+	is that the cache size should be at least 2% of the expected index size. The 
+	Berkeley DB file has 1% of internal pages that *must* be cached for good 
+	performances. Giving an additional 1% leaves room for caching leaf pages. 
+     </description>
+   </attribute>
+
+   <attribute name="wordlist_compress" 
+              type="boolean" 
+              programs="all" 
+              version="3.2.0b1" 
+              category="Indexing:How" >
+     <default>true</default>
+     <example>true</example>
+     <description> 
+	Enables or disables the default compression system for the indexer. 
+	This currently compresses the index by a factor of 8. If the 
+	Zlib library is not found on the system, the default is false. 
+     </description>
+   </attribute>
+
+   <attribute name="wordlist_compress_zlib" 
+              type="boolean" 
+              programs="all" 
+              version="3.2.0b4" 
+              category="Indexing:How" >
+     <default>true</default>
+     <example>true</example>
+     <description> 
+	Enables or disables the zlib compression system for the indexer. 
+	wordlist_compress must be true to use this option!`
+     </description>
+   </attribute>
+
+   <attribute name="wordlist_monitor" 
+              type="boolean" 
+              programs="all" 
+              version="3.2.0b1" 
+              category="Extra Output" >
+     <default>false</default>
+     <example>true</example>
+     <description> 
+	This enables monitoring of what's happening in the indexer. 
+	It can help to detect performance/configuration problems. 
+     </description>
+   </attribute>
+
+   <attribute name="wordlist_monitor_period" 
+              type="number" 
+              programs="all" 
+              version="3.2.0b1" 
+              category="Extra Output" >
+     <default>0</default>
+     <example>.1</example>
+     <description> 
+	Sets the number of seconds between each monitor output. 
+     </description>
+   </attribute>
+
+   <attribute name="wordlist_monitor_output" 
+              type="string" 
+              programs="all" 
+              version="3.2.0b1" 
+              category="Extra Output" >
+     <default></default>
+     <example>myfile</example>
+     <description> 
+	Print monitoring output on file instead of the default stderr. 
+     </description>
+   </attribute>
+
+   <attribute name="wordlist_page_size" 
+              type="integer" 
+              programs="all" 
+              version="3.2.0b1" 
+              category="Indexing:How" >
+     <default>0</default>
+     <example>8192</example>
+     <description> 
+	Size of pages used by Berkeley DB (DB used by the indexer) 
+     </description>
+   </attribute>
+
+   <attribute name="wordlist_verbose" 
+              type="integer" 
+              programs="" 
+              version="" 
+              category="" >
+     <default></default>
+     <example>true</example>
+     <description> 
+	wordlist_verbose 1 walk logic<br/>    
+	wordlist_verbose 2 walk logic details<br/>    
+	wordlist_verbose 2 walk logic lots of details<br/>    
+     </description>
+   </attribute>
+
+   <attribute name="wordlist_wordkey_description" 
+              type="string" 
+              programs="all" 
+              version="3.2.0b1" 
+              category="Indexing:How" >
+     <default>Word/DocID 32/Flags 8/Location 16</default>
+     <nodocs/>
+   </attribute>
+
+   <attribute name="wordlist_wordrecord_description" 
+              type="string" 
+              programs="all" 
+              version="3.2.0b1" 
+              category="Indexing:How" >
+     <default>DATA</default>
+     <nodocs/>
+   </attribute>
+
+</HtdigAttributes>