Fossil

Check-in [1c84a0c1]
Login

Many hyperlinks are disabled.
Use anonymous login to enable hyperlinks.

Overview
Comment:Improvements to the command-line comment formatter so that it works better with non-ASCII characters.
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | trunk
Files: files | file ages | folders
SHA3-256: 1c84a0c14ac3e00e830309881ebf89077a39de942b3f770a4a9fc3afc3bfc31e
User & Date: drh 2018-11-29 11:09:44
Context
2018-11-29
21:38
Update custom mingw makefile. Update openssl version check-in: 71399243 user: jan.nijtmans tags: trunk
11:09
Improvements to the command-line comment formatter so that it works better with non-ASCII characters. check-in: 1c84a0c1 user: drh tags: trunk
2018-11-28
23:43
Minor stylistic changes to the comment formatter. Closed-Leaf check-in: cc9c422d user: drh tags: comment-formatter-utf8
18:57
The /setup page can now be seen by both Admin and Setup users, as requested by drh via private email. The set of links shown is culled for Admin-only users. Also changed some comments to match the code with respect to Admin vs Setup capability. The only change to user capability interpretation in this checkin is to the /setup page. check-in: 7d034d34 user: wyoung tags: trunk
Changes
Hide Diffs Unified Diffs Ignore Whitespace Patch

Changes to src/comformat.c.

1
2
3
4
5
6
7
8
9
10
11
12
13
14
..
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
...
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
...
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
...
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
/*
** Copyright (c) 2007 D. Richard Hipp
**
** This program is free software; you can redistribute it and/or
** modify it under the terms of the Simplified BSD License (also
** known as the "2-Clause License" or "FreeBSD License".)

** 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.
**
** Author contact information:
**   drh@hwaci.com
**   http://www.hwaci.com/drh/
................................................................................
  *pMaxChars = COMMENT_LEGACY_LINE_LENGTH - indent;
  return -1;
#endif
}

/*
** This function checks the current line being printed against the original
** comment text.  Upon matching, it emits a new line and updates the provided
** character and line counts, if applicable.
*/
static int comment_check_orig(
  const char *zOrigText, /* [in] Original comment text ONLY, may be NULL. */
  const char *zLine,     /* [in] The comment line to print. */
  int *pCharCnt,         /* [in/out] Pointer to the line character count. */
  int *pLineCnt          /* [in/out] Pointer to the total line count. */
){
  if( zOrigText && fossil_strcmp(zLine, zOrigText)==0 ){
    fossil_print("\n");
    if( pCharCnt ) *pCharCnt = 0;
    if( pLineCnt ) (*pLineCnt)++;
    return 1;
  }
  return 0;
}

................................................................................
** This function scans the specified comment line starting just after the
** initial index and returns the index of the next spacing character -OR-
** zero if such a character cannot be found.  For the purposes of this
** algorithm, the NUL character is treated the same as a spacing character.
*/
static int comment_next_space(
  const char *zLine, /* [in] The comment line being printed. */
  int index          /* [in] The current character index being handled. */

){
  int nextIndex = index + 1;

  for(;;){
    char c = zLine[nextIndex];

    if( c==0 || fossil_isspace(c) ){







      return nextIndex;
    }
    nextIndex++;
  }
  return 0; /* NOT REACHED */
}

/*
































** This function is called when printing a logical comment line to perform
** the necessary indenting.
*/
static void comment_print_indent(
  const char *zLine, /* [in] The comment line being printed. */
  int indent,        /* [in] Number of spaces to indent, zero for none. */
  int trimCrLf,      /* [in] Non-zero to trim leading/trailing CR/LF. */
  int trimSpace,     /* [in] Non-zero to trim leading/trailing spaces. */
  int *piIndex       /* [in/out] Pointer to first non-space character. */
){
  if( indent>0 ){
    fossil_print("%*s", indent, "");
  }
  if( zLine && piIndex ){
    int index = *piIndex;
    if( trimCrLf ){
      while( zLine[index]=='\r' || zLine[index]=='\n' ){ index++; }
    }
    if( trimSpace ){
      while( fossil_isspace(zLine[index]) ){ index++; }
................................................................................
  int trimCrLf,          /* [in] Non-zero to trim leading/trailing CR/LF. */
  int trimSpace,         /* [in] Non-zero to trim leading/trailing spaces. */
  int wordBreak,         /* [in] Non-zero to try breaking on word boundaries. */
  int origBreak,         /* [in] Non-zero to break before original comment. */
  int *pLineCnt,         /* [in/out] Pointer to the total line count. */
  const char **pzLine    /* [out] Pointer to the end of the logical line. */
){
  int index = 0, charCnt = 0, lineCnt = 0, maxChars;


  if( !zLine ) return;
  if( lineChars<=0 ) return;








  comment_print_indent(zLine, indent, trimCrLf, trimSpace, &index);









  maxChars = lineChars;
  for(;;){
    int useChars = 1;
    char c = zLine[index];








    if( c==0 ){
      break;
    }else{
      if( origBreak && index>0 ){
        const char *zCurrent = &zLine[index];
        if( comment_check_orig(zOrigText, zCurrent, &charCnt, &lineCnt) ){

          comment_print_indent(zCurrent, origIndent, trimCrLf, trimSpace,
                               &index);



          maxChars = lineChars;
        }
      }
      index++;
    }
    if( c=='\n' ){
      lineCnt++;
      charCnt = 0;
      useChars = 0;
    }else if( c=='\t' ){

      int nextIndex = comment_next_space(zLine, index);
      if( nextIndex<=0 || (nextIndex-index)>maxChars ){
        break;
      }
      charCnt++;
      useChars = COMMENT_TAB_WIDTH;
      if( maxChars<useChars ){
        fossil_print(" ");
        break;
      }
    }else if( wordBreak && fossil_isspace(c) ){

      int nextIndex = comment_next_space(zLine, index);
      if( nextIndex<=0 || (nextIndex-index)>maxChars ){
        break;
      }
      charCnt++;
    }else{
      charCnt++;
    }
    assert( c!='\n' || charCnt==0 );
    fossil_print("%c", c);











    if( (c&0x80)==0 || (zLine[index+1]&0xc0)!=0xc0 ) maxChars -= useChars;
    if( maxChars<=0 ) break;
    if( c=='\n' ) break;
  }
  if( charCnt>0 ){
    fossil_print("\n");
    lineCnt++;






  }
  if( pLineCnt ){
    *pLineCnt += lineCnt;
  }
  if( pzLine ){
    *pzLine = zLine + index;
  }
................................................................................
*/
static int comment_print_legacy(
  const char *zText, /* The comment text to be printed. */
  int indent,        /* Number of spaces to indent each non-initial line. */
  int width          /* Maximum number of characters per line. */
){
  int maxChars = width - indent;
  int si, sk, i, k;
  int doIndent = 0;
  char *zBuf;
  char zBuffer[400];
  int lineCnt = 0;


  if( width<0 ){
    comment_set_maxchars(indent, &maxChars);
  }
  if( zText==0 ) zText = "(NULL)";
  if( maxChars<=0 ){
    maxChars = strlen(zText);
  }

  if( maxChars >= (sizeof(zBuffer)) ){
    zBuf = fossil_malloc(maxChars+1);
  }else{
    zBuf = zBuffer;
  }
  for(;;){
    while( fossil_isspace(zText[0]) ){ zText++; }
    if( zText[0]==0 ){
      if( doIndent==0 ){
        fossil_print("\n");
        lineCnt = 1;
      }
      if( zBuf!=zBuffer) fossil_free(zBuf);
      return lineCnt;
    }
    for(sk=si=i=k=0; zText[i] && k<maxChars; i++){
      char c = zText[i];















      if( fossil_isspace(c) ){
        si = i;
        sk = k;
        if( k==0 || zBuf[k-1]!=' ' ){
          zBuf[k++] = ' ';
        }
      }else{
        zBuf[k] = c;






|







 







|
|








<







 







|
>


>


>

>
>
>
>
>
>
>








>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
|
|

|






<
<
<







 







|
>
>


>
>
>
>
>
>
>
>
|
>
>
>
>
>
>
>
>
>




>
>
>
>
>
>
>
>






>
|
<
>
>
>










>
|
|





|



>
|
|







|
>
>
>
>
>
>
>
>
>
>
>
|




|

>
>
>
>
>
>







 







|




>








>
|
|













|

>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
|







1
2
3
4
5
6
7
8
9
10
11
12
13
14
..
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109

110
111
112
113
114
115
116
...
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
...
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
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
...
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
/*
** Copyright (c) 2007 D. Richard Hipp
**
** This program is free software; you can redistribute it and/or
** modify it under the terms of the Simplified BSD License (also
** known as the "2-Clause License" or "FreeBSD License".)
**
** 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.
**
** Author contact information:
**   drh@hwaci.com
**   http://www.hwaci.com/drh/
................................................................................
  *pMaxChars = COMMENT_LEGACY_LINE_LENGTH - indent;
  return -1;
#endif
}

/*
** This function checks the current line being printed against the original
** comment text.  Upon matching, it updates the provided character and line
** counts, if applicable.  The caller needs to emit a new line, if desired.
*/
static int comment_check_orig(
  const char *zOrigText, /* [in] Original comment text ONLY, may be NULL. */
  const char *zLine,     /* [in] The comment line to print. */
  int *pCharCnt,         /* [in/out] Pointer to the line character count. */
  int *pLineCnt          /* [in/out] Pointer to the total line count. */
){
  if( zOrigText && fossil_strcmp(zLine, zOrigText)==0 ){

    if( pCharCnt ) *pCharCnt = 0;
    if( pLineCnt ) (*pLineCnt)++;
    return 1;
  }
  return 0;
}

................................................................................
** This function scans the specified comment line starting just after the
** initial index and returns the index of the next spacing character -OR-
** zero if such a character cannot be found.  For the purposes of this
** algorithm, the NUL character is treated the same as a spacing character.
*/
static int comment_next_space(
  const char *zLine, /* [in] The comment line being printed. */
  int index,         /* [in] The current character index being handled. */
  int *distUTF8      /* [out] Distance to next space in UTF-8 sequences. */
){
  int nextIndex = index + 1;
  int fNonASCII=0;
  for(;;){
    char c = zLine[nextIndex];
    if( (c&0x80)==0x80 ) fNonASCII=1;
    if( c==0 || fossil_isspace(c) ){
      if( distUTF8 ){
        if( fNonASCII!=0 ){
          *distUTF8 = strlen_utf8(&zLine[index], nextIndex-index);
        }else{
          *distUTF8 = nextIndex-index;
        }
      }
      return nextIndex;
    }
    nextIndex++;
  }
  return 0; /* NOT REACHED */
}

/*
** Count the number of UTF-8 sequences in a string. Incomplete, ill-formed and
** overlong sequences are counted as one sequence. The invalid lead bytes 0xC0
** to 0xC1 and 0xF5 to 0xF7 are allowed to initiate (ill-formed) 2- and 4-byte
** sequences, respectively, the other invalid lead bytes 0xF8 to 0xFF are
** treated as invalid 1-byte sequences (as lone trail bytes).
** Combining characters and East Asian Wide and Fullwidth characters are counted
** as one, so this function does not calculate the effective "display width".
*/
int strlen_utf8(const char *zString, int lengthBytes){
  int i;          /* Counted bytes. */
  int lengthUTF8; /* Counted UTF-8 sequences. */
#if 0
  assert( lengthBytes>=0 );
#endif
  for(i=0, lengthUTF8=0; i<lengthBytes; i++, lengthUTF8++){
    char c = zString[i];
    int cchUTF8=1; /* Code units consumed. */
    int maxUTF8=1; /* Expected sequence length. */
    if( (c&0xe0)==0xc0 )maxUTF8=2;          /* UTF-8 lead byte 110vvvvv */
    else if( (c&0xf0)==0xe0 )maxUTF8=3;     /* UTF-8 lead byte 1110vvvv */
    else if( (c&0xf8)==0xf0 )maxUTF8=4;     /* UTF-8 lead byte 11110vvv */
    while( cchUTF8<maxUTF8 &&
            i<lengthBytes-1 &&
            (zString[i+1]&0xc0)==0x80 ){    /* UTF-8 trail byte 10vvvvvv */
      cchUTF8++;
      i++;
    }
  }
  return lengthUTF8;
}

/*
** This function is called when printing a logical comment line to calculate
** the necessary indenting.  The caller needs to emit the indenting spaces.
*/
static void comment_calc_indent(
  const char *zLine, /* [in] The comment line being printed. */
  int indent,        /* [in] Number of spaces to indent, zero for none. */
  int trimCrLf,      /* [in] Non-zero to trim leading/trailing CR/LF. */
  int trimSpace,     /* [in] Non-zero to trim leading/trailing spaces. */
  int *piIndex       /* [in/out] Pointer to first non-space character. */
){



  if( zLine && piIndex ){
    int index = *piIndex;
    if( trimCrLf ){
      while( zLine[index]=='\r' || zLine[index]=='\n' ){ index++; }
    }
    if( trimSpace ){
      while( fossil_isspace(zLine[index]) ){ index++; }
................................................................................
  int trimCrLf,          /* [in] Non-zero to trim leading/trailing CR/LF. */
  int trimSpace,         /* [in] Non-zero to trim leading/trailing spaces. */
  int wordBreak,         /* [in] Non-zero to try breaking on word boundaries. */
  int origBreak,         /* [in] Non-zero to break before original comment. */
  int *pLineCnt,         /* [in/out] Pointer to the total line count. */
  const char **pzLine    /* [out] Pointer to the end of the logical line. */
){
  int index = 0, charCnt = 0, lineCnt = 0, maxChars, i;
  char zBuf[400]; int iBuf=0; /* Output buffer and counter. */
  int cchUTF8, maxUTF8;       /* Helper variables to count UTF-8 sequences. */
  if( !zLine ) return;
  if( lineChars<=0 ) return;
#if 0
  assert( indent<sizeof(zBuf)-5 );       /* See following comments to explain */
  assert( origIndent<sizeof(zBuf)-5 );   /* these limits. */
#endif
  if( indent>sizeof(zBuf)-6 ){
    /* Limit initial indent to fit output buffer. */
    indent = sizeof(zBuf)-6;
  }
  comment_calc_indent(zLine, indent, trimCrLf, trimSpace, &index);
  if( indent>0 ){
    for(i=0; i<indent; i++){
      zBuf[iBuf++] = ' ';
    }
  }
  if( origIndent>sizeof(zBuf)-6 ){
    /* Limit line indent to fit output buffer. */
    origIndent = sizeof(zBuf)-6;
  }
  maxChars = lineChars;
  for(;;){
    int useChars = 1;
    char c = zLine[index];
    /* Flush the output buffer if there's no space left for at least one more
    ** (potentially 4-byte) UTF-8 sequence, one level of indentation spaces,
    ** a new line, and a terminating NULL. */
    if( iBuf>sizeof(zBuf)-origIndent-6 ){
      zBuf[iBuf]=0;
      iBuf=0;
      fossil_print("%s", zBuf);
    }
    if( c==0 ){
      break;
    }else{
      if( origBreak && index>0 ){
        const char *zCurrent = &zLine[index];
        if( comment_check_orig(zOrigText, zCurrent, &charCnt, &lineCnt) ){
          zBuf[iBuf++] = '\n';
          comment_calc_indent(zLine, origIndent, trimCrLf, trimSpace, &index);

          for( i=0; i<origIndent; i++ ){
            zBuf[iBuf++] = ' ';
          }
          maxChars = lineChars;
        }
      }
      index++;
    }
    if( c=='\n' ){
      lineCnt++;
      charCnt = 0;
      useChars = 0;
    }else if( c=='\t' ){
      int distUTF8;
      int nextIndex = comment_next_space(zLine, index, &distUTF8);
      if( nextIndex<=0 || distUTF8>maxChars ){
        break;
      }
      charCnt++;
      useChars = COMMENT_TAB_WIDTH;
      if( maxChars<useChars ){
        zBuf[iBuf++] = ' ';
        break;
      }
    }else if( wordBreak && fossil_isspace(c) ){
      int distUTF8;
      int nextIndex = comment_next_space(zLine, index, &distUTF8);
      if( nextIndex<=0 || distUTF8>maxChars ){
        break;
      }
      charCnt++;
    }else{
      charCnt++;
    }
    assert( c!='\n' || charCnt==0 );
    zBuf[iBuf++] = c;
    /* Skip over UTF-8 sequences, see comment on strlen_utf8() for details. */
    cchUTF8=1; /* Code units consumed. */
    maxUTF8=1; /* Expected sequence length. */
    if( (c&0xe0)==0xc0 )maxUTF8=2;          /* UTF-8 lead byte 110vvvvv */
    else if( (c&0xf0)==0xe0 )maxUTF8=3;     /* UTF-8 lead byte 1110vvvv */
    else if( (c&0xf8)==0xf0 )maxUTF8=4;     /* UTF-8 lead byte 11110vvv */
    while( cchUTF8<maxUTF8 &&
            (zLine[index]&0xc0)==0x80 ){    /* UTF-8 trail byte 10vvvvvv */
      cchUTF8++;
      zBuf[iBuf++] = zLine[index++];
    }
    maxChars -= useChars;
    if( maxChars<=0 ) break;
    if( c=='\n' ) break;
  }
  if( charCnt>0 ){
    zBuf[iBuf++] = '\n';
    lineCnt++;
  }
  /* Flush the remaining output buffer. */
  if( iBuf>0 ){
    zBuf[iBuf]=0;
    iBuf=0;
    fossil_print("%s", zBuf);
  }
  if( pLineCnt ){
    *pLineCnt += lineCnt;
  }
  if( pzLine ){
    *pzLine = zLine + index;
  }
................................................................................
*/
static int comment_print_legacy(
  const char *zText, /* The comment text to be printed. */
  int indent,        /* Number of spaces to indent each non-initial line. */
  int width          /* Maximum number of characters per line. */
){
  int maxChars = width - indent;
  int si, sk, i, k, kc;
  int doIndent = 0;
  char *zBuf;
  char zBuffer[400];
  int lineCnt = 0;
  int cchUTF8, maxUTF8; /* Helper variables to count UTF-8 sequences. */

  if( width<0 ){
    comment_set_maxchars(indent, &maxChars);
  }
  if( zText==0 ) zText = "(NULL)";
  if( maxChars<=0 ){
    maxChars = strlen(zText);
  }
  /* Ensure the buffer can hold the longest-possible UTF-8 sequences. */
  if( maxChars >= (sizeof(zBuffer)/4-1) ){
    zBuf = fossil_malloc(maxChars*4+1);
  }else{
    zBuf = zBuffer;
  }
  for(;;){
    while( fossil_isspace(zText[0]) ){ zText++; }
    if( zText[0]==0 ){
      if( doIndent==0 ){
        fossil_print("\n");
        lineCnt = 1;
      }
      if( zBuf!=zBuffer) fossil_free(zBuf);
      return lineCnt;
    }
    for(sk=si=i=k=kc=0; zText[i] && kc<maxChars; i++){
      char c = zText[i];
      kc++; /* Count complete UTF-8 sequences. */
      /* Skip over UTF-8 sequences, see comment on strlen_utf8() for details. */
      cchUTF8=1; /* Code units consumed. */
      maxUTF8=1; /* Expected sequence length. */
      if( (c&0xe0)==0xc0 )maxUTF8=2;        /* UTF-8 lead byte 110vvvvv */
      else if( (c&0xf0)==0xe0 )maxUTF8=3;   /* UTF-8 lead byte 1110vvvv */
      else if( (c&0xf8)==0xf0 )maxUTF8=4;   /* UTF-8 lead byte 11110vvv */
      if( maxUTF8>1 ){
        zBuf[k++] = c;
        while( cchUTF8<maxUTF8 &&
                (zText[i+1]&0xc0)==0x80 ){  /* UTF-8 trail byte 10vvvvvv */
          cchUTF8++;
          zBuf[k++] = zText[++i];
        }
      }
      else if( fossil_isspace(c) ){
        si = i;
        sk = k;
        if( k==0 || zBuf[k-1]!=' ' ){
          zBuf[k++] = ' ';
        }
      }else{
        zBuf[k] = c;