summaryrefslogtreecommitdiffstats
path: root/kexi/tools/sql_keywords/sql_keywords.sh
blob: 6a6cb003bfd30b9788e8e02e000135a13afa8360 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
#!/bin/bash
################################################################################
# sql_keywords.sh
#
# Generate sets of driver-specific keywords.
# This program generates files that can be used as part of KexiDB drivers
# that list keywords specific to that driver, i.e. words that have to be
# escaped if they are to be used as identifiers in the database.
#
# It extracts keywords from the lexer of the DB sources, deletes keywords that
# are already going to be escaped because they are part of Kexi's SQL dialect,
# and writes the resulting keywords to a "char *keywords[]" construct in a .cpp 
# file that can then be used in the driver.
#
# To use:
# Put the DB source tarballs (e.g. mysql-4.1.7.tar.gz, 
# postgresql-base-7.4.6.tar.gz) in the current directory
# then run. (Makefile provided for installs)
#
# Sed, awk, grep have been used without much thought -
# CHECK THE OUTPUT BEFORE INCLUDING IT IN A DRIVER!
#
# Martin Ellis <[email protected]>
# 11/2004

set -e
progname="sql_keywords.sh"

################################################################################
# C++ file generator
# params : array - scoped name of the array to generate
#          include - a file to include (or "" if none)
#          inFile - file containing raw keywords
#          outfile - file to write 
header () {
  local array="$1"
  local include="$2"
  local inFile="$3"
  local outFile="$4"
  echo "Writing keywords in $inFile to $outFile"
  cat <<EOF1 > "$outFile";
 /*
 * This file has been automatically generated from
 * koffice/kexi/tools/sql_keywords/$progname and
 * $inFile.
 *
 * Please edit the $progname, not this file!
 */
EOF1
  if [ "$include" != "" ] ; then
    echo "#include <$include>" >> "$outFile"
  fi
  cat <<EOF2 >> "$outFile";

namespace KexiDB {
  const char* ${array}[] = {
EOF2
}

body() {
  local inFile="$1"
  local outFile="$2"
  awk '/^[a-zA-Z_0-9]*/ { print "\t\t\""$$1"\","; } ' "$inFile" >> "$outFile"
}

footer() {
  local outFile="$1"
  cat <<EOF >> "$outFile";
		0
  };
}
EOF

}

################################################################################
# Keyword comparison functions
# Globals: keywords

# readKeywords
# params: filename - file of keywords to read
# sets:   keywords - array of keywords in the file
readKeywords () {
  local filename="$1" 
  local kexiSQL="$2"
  i=0
  while read keyword ; do
    keywords[$i]="$keyword"
    (( i++ ))
  done < "$filename"
}

# compareKeywords
# reads: kexiSQL - 
#        driverSQL
# sets:  keywords - driver keywords that are not keywords in Kexi
compareKeywords () {
  numFound=0
  for(( i=0; i < ${#driverSQL[@]}; i++ )) ; do
    found="no"
    for(( j=0; j < ${#kexiSQL[@]}; j++ )) ; do
      if [ "${driverSQL[$i]}" == "${kexiSQL[$j]}" ] ; then
        found="yes"
      fi
    done
    if [ "$found" == "no" ] ; then
      keywords[$numFound]="${driverSQL[$i]}"
      (( numFound++ ))
    fi
  done
}


# getDriverKeywords
# params : kexi - 
#          driver - 
#          outFile -
getDriverKeywords () {
  local kexi="$1"
  local driver="$2"
  local outFile="$3"

  declare -a kexiSQL
  declare -a driverSQL

  echo "Looking for driver-specific keywords in \"$driver\""
  readKeywords $kexi
  for(( i=0; i < ${#keywords[@]}; i++ )) ; do
    kexiSQL[$i]=${keywords[$i]}
  done
  unset keywords

  readKeywords $driver
  for(( i=0; i < ${#keywords[@]}; i++ )) ; do
    driverSQL[$i]=${keywords[$i]}
  done
  unset keywords

  compareKeywords
  echo "Writing driver-specific keywords for \"$driver\" to \"$outFile\""
  rm -f $outFile
  for(( i=0; i < ${#keywords[@]}; i++ )) ; do
    echo ${keywords[$i]} >> $outFile
  done
  unset keywords
}
################################################################################


################################################################################
# Kexi lexer

checkKexiKeywords () {
  local scanner="../../kexidb/parser/sqlscanner.l"
  if [ ! -r kexi.all -o "$scanner" -nt "kexi.all" ] ; then
    echo "Getting Kexi keywords"
    grep '^(\?"[a-zA-Z_0-9]' "$scanner" | \
       sed 's/(\?"\([^"]*\)"[^"]*/\1\n/g' | \
       awk '/^[a-zA-Z_0-9]+$/ {print $1;}' | 
       sort | uniq > "kexi.all"
    awk '/^[a-zA-Z_0-9]+$/ {print $1;}' kexi_reserved >> "kexi.all"
  fi
}

################################################################################
# DB lexer functions
# These functions munge the extracted lexers from DBs and write the collected
# keywords to file

# getSQLiteKeywords
# params : inFile  - SQLite3 lexer file
#          outFile - all SQLite3 keywords
getSQLiteKeywords () {
  local inFile="$1"
  local outFile="$2"
  
  echo "Getting SQLite keywords ($inFile -> $outFile)"
  sed -n '/^static Keyword aKeywordTable/,/};/p' $inFile | \
    awk '/  { "[a-zA-Z_0-9]*"/ { print $2;}' | \
    sed 's/"\(.*\)".*/\1/g' > $outFile
}

getPostgreSQLKeywords () {
  local inFile="$1"
  local outFile="$2"

  echo "Getting PostgreSQL keywords ($inFile -> $outFile)"
  sed -n '/^static const ScanKeyword ScanKeywords/,/};/p' $inFile | \
    awk '/\t{"[a-zA-Z_0-9]*"/ { print $1;}' | \
    sed 's/.*"\(.*\)".*/\1/g' | tr 'a-z' 'A-Z' > $outFile
}

# getMySQLKeywords
# params : inFile  - MySQL lexer file
#          outFile - all MySQL keywords
getMySQLKeywords () {
  local inFile="$1"
  local outFile="$2"

  echo "Getting MySQL keywords ($inFile -> $outFile)"
  sed -n '/^static SYMBOL symbols/,/};/p' $inFile | \
    awk '/  { "[a-zA-Z_0-9]*"/ { print $2;}' | \
    sed 's/"\(.*\)".*/\1/g' > $outFile
}

################################################################################
# DB tarball functions
# These functions extract the lexer files from the DB source tarballs

# checkExtracted
# params : tarball - tarball containing backend DB source
#          file - file in tarball containing DB's lexer
checkExtracted () {
  local tarball="$1"
  local file="$2"

  if [ ! -r "$file" ] ; then
    echo "Getting file \"$file\" from \"$tarball\""
    tar -zxf "$tarball" "$file"
  fi
}

# checkTarballs
checkTarballs () {
  local pathInTar
  local appName
  local appVer

  # SQLite (native DB backend) keywords
  appName="SQLite"
  appVer=sqlite
  inFile="../../3rdparty/kexisql3/src/tokenize.c"
  filePrefix="sqlite"
  if [ ! -r "$appVer.all" ] || [ ! -r "$appVer.new" ] ; then
    getSQLiteKeywords "$inFile" "$appVer.all"
  fi
  if [ "$appVer.all" -nt "$appVer.new" ] ; then
    getDriverKeywords "kexi.all" "$appVer.all" "$appVer.new"
    header "${appName}Driver::keywords" "${filePrefix}driver.h" "$inFile" "${filePrefix}keywords.cpp"
    body   "$appVer.new" "${filePrefix}keywords.cpp"
    footer "${filePrefix}keywords.cpp"
  fi

  ls mysql-*.tar.gz postgresql-*.tar.gz 2>/dev/null | while read tarball ; do
   case "$tarball" in
     mysql-4.1.[0-9\.]*.tar.gz)
       pathInTar="sql/lex.h"
       appName="MySql"
       filePrefix="mysql"
       appVer="${tarball%.tar.gz}"
       if [ ! -r "$appVer.all" ] || [ ! -r "$appVer.new" ] ; then
         checkExtracted "$tarball" "$appVer/$pathInTar"
         getMySQLKeywords "$appVer/$pathInTar" "$appVer.all"
	 rm -rf "$appVer"
       fi

       if [ "$appVer.all" -nt "$appVer.new" ] ; then
         getDriverKeywords "kexi.all" "$appVer.all" "$appVer.new"
         header "${appName}Driver::keywords" "${filePrefix}driver.h" "$appVer/$pathInTar" "${filePrefix}keywords.cpp"
         body   "$appVer.new" "${filePrefix}keywords.cpp"
         footer "${filePrefix}keywords.cpp"
       fi
       ;;

     postgresql-base-7.4.[0-9\.]*.tar.gz)
       pathInTar="src/backend/parser/keywords.c"
       appName="pqxxSql"
       filePrefix="pqxx"
       appVer=`echo "${tarball%.tar.gz}" | sed 's/-base//'`
       if [ ! -r "$appVer.all" ] || [ ! -r "$appVer.new" ] ; then
         checkExtracted "$tarball" "$appVer/$pathInTar"
         getPostgreSQLKeywords "$appVer/$pathInTar" "$appVer.all"
	 rm -rf "$appVer"
       fi

       if [ "$appVer.all" -nt "$appVer.new" ] ; then
         getDriverKeywords "kexi.all" "$appVer.all" "$appVer.new"
         header "${appName}Driver::keywords" "${filePrefix}driver.h" "$appVer/$pathInTar" "${filePrefix}keywords.cpp"
         body   "$appVer.new" "${filePrefix}keywords.cpp"
         footer "${filePrefix}keywords.cpp"
       fi
       ;;

     *)
       echo "Don't know how to deal with $tarball - ignoring"
       ;;
    esac
  done
}

checkKexiKeywords
src=`printf "koffice/kexi/kexidb/parser/sqlscanner.l\n"\
" * and koffice/kexi/tools/sql_keywords/kexi__reserved"`
header "DriverPrivate::kexiSQLKeywords" "driver_p.h" "$src" "keywords.cpp"
body "kexi.all" "keywords.cpp"
footer "keywords.cpp"

checkTarballs
wc -l *.all *.new | awk '{print $2" "$1}' |sort|awk '{print $1"\t"$2}'