summaryrefslogtreecommitdiffstats
path: root/tdespell2/filter.cpp
blob: 745d8f6891eaff373e4de9ae8ed6c6716bc16758 (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
300
301
302
303
304
305
306
307
308
/*
 * filter.cpp
 *
 * Copyright (C)  2004  Zack Rusin <[email protected]>
 *
 * This library is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation; either
 * version 2.1 of the License, or (at your option) any later version.
 *
 * This library 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
 * Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public
 * License along with this library; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
 * 02110-1301  USA
 */

#include "filter.h"

#include "settings.h"

#include <kstaticdeleter.h>
#include <kdebug.h>

#include <tqstring.h>

namespace KSpell2
{

static Word endWord;
static KStaticDeleter<Filter> sd;
static Filter* defFilter = 0;

class Filter::Private
{
public:
    // The reason it's not in the class directly is that
    // i'm not 100% sure that having the settings() here is
    // the way i want to be doing this.
    Settings *settings;
};

Filter* Filter::defaultFilter()
{
    if ( !defFilter )
        sd.setObject( defFilter, new Filter() );
    return defFilter;
}

Word Filter::end()
{
    return endWord;
}

Filter::Filter()
    : m_currentPosition( 0 )
{
    d = new Private;
    d->settings = 0;
}

Filter::~Filter()
{
    delete d; d = 0;
}

void Filter::setSettings( Settings *conf )
{
    d->settings = conf;
}

Settings *Filter::settings() const
{
    return d->settings;
}

void Filter::restart()
{
    m_currentPosition = 0;
}

void Filter::setBuffer( const TQString& buffer )
{
    m_buffer          = buffer;
    m_currentPosition = 0;
}

TQString Filter::buffer() const
{
    return m_buffer;
}

bool Filter::atEnd() const
{
    if ( m_currentPosition >= m_buffer.length() ) {
        return true;
    } else
        return false;
}

Word Filter::nextWord() const
{
    TQChar currentChar = skipToLetter( m_currentPosition );

    if ( m_currentPosition >= m_buffer.length() ) {
        return Filter::end();
    }

    bool allUppercase = currentChar.category() & TQChar::Letter_Uppercase;
    bool runTogether = false;

    TQString foundWord;
    int start = m_currentPosition;
    while ( currentChar.isLetter() ) {
        if ( currentChar.category() & TQChar::Letter_Lowercase )
            allUppercase = false;

	/* FIXME: this does not work for Hebrew for example
        //we consider run-together words as mixed-case words
        if ( !allUppercase &&
             currentChar.category() & TQChar::Letter_Uppercase )
            runTogether = true;
	*/

        foundWord += currentChar;
        ++m_currentPosition;
        currentChar = m_buffer[ m_currentPosition ];
    }

    if ( shouldBeSkipped( allUppercase, runTogether, foundWord ) )
        return nextWord();

    return Word( foundWord, start );
}

Word Filter::previousWord() const
{
    while ( !m_buffer[ m_currentPosition ].isLetter() &&
            m_currentPosition != 0) {
        --m_currentPosition;
    }

    if ( m_currentPosition == 0 ) {
        return Filter::end();
    }

    TQString foundWord;
    int start = m_currentPosition;
    while ( m_buffer[ start ].isLetter() ) {
        foundWord.prepend( m_buffer[ m_currentPosition ] );
        --start;
    }

    return Word( foundWord, start );
}

Word Filter::wordAtPosition( unsigned int pos ) const
{
    if ( pos > m_buffer.length() )
        return Filter::end();

    int currentPosition = pos - 1;
    TQString foundWord;
    while ( currentPosition >= 0 &&
            m_buffer[ currentPosition ].isLetter() ) {
        foundWord.prepend( m_buffer[ currentPosition ] );
        --currentPosition;
    }

    // currentPosition == 0 means the first char is not letter
    // currentPosition == -1 means we reached the beginning
    int start = (currentPosition < 0) ? 0 : ++currentPosition;
    currentPosition = pos ;
    if ( m_buffer[ currentPosition ].isLetter() ) {
        while ( m_buffer[ currentPosition ].isLetter() ) {
            foundWord.append( m_buffer[ currentPosition ] );
            ++currentPosition;
        }
    }

    return Word( foundWord, start );
}


void Filter::setCurrentPosition( int i )
{
    m_currentPosition = i;

    //go back to the last word so that next word returns something
    //useful
    while ( m_buffer[m_currentPosition].isLetter() && m_currentPosition > 0 )
        --m_currentPosition;
}

int Filter::currentPosition() const
{
    return m_currentPosition;
}

void Filter::replace( const Word& w, const TQString& newWord)
{
    int oldLen = w.word.length();
    int newLen = newWord.length();

    if ( oldLen != newLen && m_currentPosition > w.start ) {
        if ( m_currentPosition > w.start ) {
            int len = newLen - oldLen;
            m_currentPosition += len;
        }
    }
    m_buffer = m_buffer.replace( w.start, oldLen, newWord );
}

TQString Filter::context() const
{
    int len = 60;
    //we don't want the expression underneath casted to an unsigned int
    //which would cause it to always evaluate to false
    int signedPosition = m_currentPosition;
    bool begin = ( (signedPosition - len/2)<=0 ) ? true : false;


    TQString buffer = m_buffer;
    Word word = wordAtPosition( m_currentPosition );
    buffer = buffer.replace( word.start, word.word.length(),
                             TQString( "<b>%1</b>" ).arg( word.word ) );

    TQString context;
    if ( begin )
        context = TQString( "%1...")
                  .arg( buffer.mid(  0, len ) );
    else
        context = TQString( "...%1..." )
                  .arg( buffer.mid(  m_currentPosition - 20, len ) );

    context = context.replace( '\n', ' ' );

    return context;
}

bool Filter::trySkipLinks() const
{
    TQChar currentChar = m_buffer[ m_currentPosition ];

    uint length = m_buffer.length();
    //URL - if so skip
    if ( currentChar == ':' &&
         ( m_buffer[ ++m_currentPosition] == '/' || ( m_currentPosition + 1 ) >= length ) ) {
        //in both cases url is considered finished at the first whitespace occurence
        while ( !m_buffer[ m_currentPosition++ ].isSpace() && m_currentPosition < length )
            ;
        return true;
    }

    //Email - if so skip
    if ( currentChar == '@' ) {
        while ( !m_buffer[ ++m_currentPosition ].isSpace() && m_currentPosition < length )
            ;
        return true;
    }

    return false;
}

bool Filter::ignore( const TQString& word ) const
{
    if ( d->settings ) {
        return d->settings->ignore( word );
    }
    return false;
}

TQChar Filter::skipToLetter( uint &fromPosition ) const
{

    TQChar currentChar = m_buffer[ fromPosition ];
    while ( !currentChar.isLetter() &&
            ++fromPosition < m_buffer.length() ) {
        currentChar = m_buffer[ fromPosition ];
    }
    return currentChar;
}

bool Filter::shouldBeSkipped( bool wordWasUppercase, bool wordWasRunTogether,
                             const TQString& foundWord ) const
{
    bool checkUpper = ( d->settings ) ?
                      d->settings->checkUppercase () : true;
    bool skipRunTogether = ( d->settings ) ?
                           d->settings->skipRunTogether() : true;

    if ( trySkipLinks() )
        return true;

    if ( wordWasUppercase && !checkUpper )
        return true;

    if ( wordWasRunTogether && skipRunTogether )
        return true;

    return ignore( foundWord );
}

}