summaryrefslogtreecommitdiff
path: root/Source/cmListFileLexer.in.l
blob: a520c7221b4fc6919749162beb9fd36ce29b3c3a (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
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
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
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
%{
/*============================================================================
  CMake - Cross Platform Makefile Generator
  Copyright 2000-2009 Kitware, Inc., Insight Software Consortium

  Distributed under the OSI-approved BSD License (the "License");
  see accompanying file Copyright.txt for details.

  This software is distributed WITHOUT ANY WARRANTY; without even the
  implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
  See the License for more information.
============================================================================*/
/*

This file must be translated to C and modified to build everywhere.

Run flex like this:

  flex --prefix=cmListFileLexer_yy -ocmListFileLexer.c cmListFileLexer.in.l

Modify cmListFileLexer.c:
  - remove TABs
  - remove use of the 'register' storage class specifier
  - remove the yyunput function
  - add a statement "(void)yyscanner;" to the top of these methods:
      yy_fatal_error, cmListFileLexer_yyalloc, cmListFileLexer_yyrealloc, cmListFileLexer_yyfree
  - remove statement "yyscanner = NULL;" from cmListFileLexer_yylex_destroy
  - remove all YY_BREAK lines occurring right after return statements
  - remove the isatty forward declaration

*/

#include "cmStandardLexer.h"
#ifdef WIN32
#include <cmsys/Encoding.h>
#endif

/* Setup the proper cmListFileLexer_yylex declaration.  */
#define YY_EXTRA_TYPE cmListFileLexer*
#define YY_DECL int cmListFileLexer_yylex (yyscan_t yyscanner, cmListFileLexer* lexer)

#include "cmListFileLexer.h"

/*--------------------------------------------------------------------------*/
struct cmListFileLexer_s
{
  cmListFileLexer_Token token;
  int bracket;
  int comment;
  int line;
  int column;
  int size;
  FILE* file;
  size_t cr;
  char* string_buffer;
  char* string_position;
  int string_left;
  yyscan_t scanner;
};

static void cmListFileLexerSetToken(cmListFileLexer* lexer, const char* text,
                                    int length);
static void cmListFileLexerAppend(cmListFileLexer* lexer, const char* text,
                                  int length);
static int cmListFileLexerInput(cmListFileLexer* lexer, char* buffer,
                                size_t bufferSize);
static void cmListFileLexerInit(cmListFileLexer* lexer);
static void cmListFileLexerDestroy(cmListFileLexer* lexer);

/* Replace the lexer input function.  */
#undef YY_INPUT
#define YY_INPUT(buf, result, max_size) \
  { result = cmListFileLexerInput(cmListFileLexer_yyget_extra(yyscanner), buf, max_size); }

/*--------------------------------------------------------------------------*/
%}

%option reentrant
%option yylineno
%option noyywrap
%pointer
%x STRING
%x BRACKET
%x BRACKETEND
%x COMMENT

MAKEVAR \$\([A-Za-z0-9_]*\)
UNQUOTED ([^ \t\r\n\(\)#\\\"[=]|\\.)
LEGACY {MAKEVAR}|{UNQUOTED}|\"({MAKEVAR}|{UNQUOTED}|[ \t[=])*\"

%%

<INITIAL,COMMENT>\n {
  lexer->token.type = cmListFileLexer_Token_Newline;
  cmListFileLexerSetToken(lexer, yytext, yyleng);
  ++lexer->line;
  lexer->column = 1;
  BEGIN(INITIAL);
  return 1;
}

#?\[=*\[\n? {
  const char* bracket = yytext;
  lexer->comment = yytext[0] == '#';
  if(lexer->comment)
    {
    lexer->token.type = cmListFileLexer_Token_CommentBracket;
    bracket += 1;
    }
  else
    {
    lexer->token.type = cmListFileLexer_Token_ArgumentBracket;
    }
  cmListFileLexerSetToken(lexer, "", 0);
  lexer->bracket = (int)(strchr(bracket+1, '[') - bracket);
  if(yytext[yyleng-1] == '\n')
    {
    ++lexer->line;
    lexer->column = 1;
    }
  else
    {
    lexer->column += yyleng;
    }
  BEGIN(BRACKET);
}

# {
  lexer->column += yyleng;
  BEGIN(COMMENT);
}

<COMMENT>.* {
  lexer->column += yyleng;
}

\( {
  lexer->token.type = cmListFileLexer_Token_ParenLeft;
  cmListFileLexerSetToken(lexer, yytext, yyleng);
  lexer->column += yyleng;
  return 1;
}

\) {
  lexer->token.type = cmListFileLexer_Token_ParenRight;
  cmListFileLexerSetToken(lexer, yytext, yyleng);
  lexer->column += yyleng;
  return 1;
}

[A-Za-z_][A-Za-z0-9_]* {
  lexer->token.type = cmListFileLexer_Token_Identifier;
  cmListFileLexerSetToken(lexer, yytext, yyleng);
  lexer->column += yyleng;
  return 1;
}

<BRACKET>\]=* {
  /* Handle ]]====]=======]*/
  cmListFileLexerAppend(lexer, yytext, yyleng);
  lexer->column += yyleng;
  if(yyleng == lexer->bracket)
    {
    BEGIN(BRACKETEND);
    }
}

<BRACKETEND>\] {
  lexer->column += yyleng;
  /* Erase the partial bracket from the token.  */
  lexer->token.length -= lexer->bracket;
  lexer->token.text[lexer->token.length] = 0;
  BEGIN(INITIAL);
  return 1;
}

<BRACKET>([^]\n])+ {
  cmListFileLexerAppend(lexer, yytext, yyleng);
  lexer->column += yyleng;
}

<BRACKET,BRACKETEND>\n {
  cmListFileLexerAppend(lexer, yytext, yyleng);
  ++lexer->line;
  lexer->column = 1;
  BEGIN(BRACKET);
}

<BRACKET,BRACKETEND>. {
  cmListFileLexerAppend(lexer, yytext, yyleng);
  lexer->column += yyleng;
  BEGIN(BRACKET);
}

<BRACKET,BRACKETEND><<EOF>> {
  lexer->token.type = cmListFileLexer_Token_BadBracket;
  BEGIN(INITIAL);
  return 1;
}

({UNQUOTED}|=|\[=*{UNQUOTED})({UNQUOTED}|[[=])* {
  lexer->token.type = cmListFileLexer_Token_ArgumentUnquoted;
  cmListFileLexerSetToken(lexer, yytext, yyleng);
  lexer->column += yyleng;
  return 1;
}

({MAKEVAR}|{UNQUOTED}|=|\[=*{LEGACY})({LEGACY}|[[=])* {
  lexer->token.type = cmListFileLexer_Token_ArgumentUnquoted;
  cmListFileLexerSetToken(lexer, yytext, yyleng);
  lexer->column += yyleng;
  return 1;
}

\[ {
  lexer->token.type = cmListFileLexer_Token_ArgumentUnquoted;
  cmListFileLexerSetToken(lexer, yytext, yyleng);
  lexer->column += yyleng;
  return 1;
}

\" {
  lexer->token.type = cmListFileLexer_Token_ArgumentQuoted;
  cmListFileLexerSetToken(lexer, "", 0);
  lexer->column += yyleng;
  BEGIN(STRING);
}

<STRING>([^\\\n\"]|\\.)+ {
  cmListFileLexerAppend(lexer, yytext, yyleng);
  lexer->column += yyleng;
}

<STRING>\\\n {
  /* Continuation: text is not part of string */
  ++lexer->line;
  lexer->column = 1;
}

<STRING>\n {
  cmListFileLexerAppend(lexer, yytext, yyleng);
  ++lexer->line;
  lexer->column = 1;
}

<STRING>\" {
  lexer->column += yyleng;
  BEGIN(INITIAL);
  return 1;
}

<STRING>. {
  cmListFileLexerAppend(lexer, yytext, yyleng);
  lexer->column += yyleng;
}

<STRING><<EOF>> {
  lexer->token.type = cmListFileLexer_Token_BadString;
  BEGIN(INITIAL);
  return 1;
}

[ \t\r]+ {
  lexer->token.type = cmListFileLexer_Token_Space;
  cmListFileLexerSetToken(lexer, yytext, yyleng);
  lexer->column += yyleng;
  return 1;
}

. {
  lexer->token.type = cmListFileLexer_Token_BadCharacter;
  cmListFileLexerSetToken(lexer, yytext, yyleng);
  lexer->column += yyleng;
  return 1;
}

<<EOF>> {
  lexer->token.type = cmListFileLexer_Token_None;
  cmListFileLexerSetToken(lexer, 0, 0);
  return 0;
}

%%

/*--------------------------------------------------------------------------*/
static void cmListFileLexerSetToken(cmListFileLexer* lexer, const char* text,
                                    int length)
{
  /* Set the token line and column number.  */
  lexer->token.line = lexer->line;
  lexer->token.column = lexer->column;

  /* Use the same buffer if possible.  */
  if(lexer->token.text)
    {
    if(text && length < lexer->size)
      {
      strcpy(lexer->token.text, text);
      lexer->token.length = length;
      return;
      }
    free(lexer->token.text);
    lexer->token.text = 0;
    lexer->size = 0;
    }

  /* Need to extend the buffer.  */
  if(text)
    {
    lexer->token.text = strdup(text);
    lexer->token.length = length;
    lexer->size = length+1;
    }
  else
    {
    lexer->token.length = 0;
    }
}

/*--------------------------------------------------------------------------*/
static void cmListFileLexerAppend(cmListFileLexer* lexer, const char* text,
                                  int length)
{
  char* temp;
  int newSize;

  /* If the appended text will fit in the buffer, do not reallocate.  */
  newSize = lexer->token.length + length + 1;
  if(lexer->token.text && newSize <= lexer->size)
    {
    strcpy(lexer->token.text+lexer->token.length, text);
    lexer->token.length += length;
    return;
    }

  /* We need to extend the buffer.  */
  temp = malloc(newSize);
  if(lexer->token.text)
    {
    memcpy(temp, lexer->token.text, lexer->token.length);
    free(lexer->token.text);
    }
  memcpy(temp+lexer->token.length, text, length);
  temp[lexer->token.length+length] = 0;
  lexer->token.text = temp;
  lexer->token.length += length;
  lexer->size = newSize;
}

/*--------------------------------------------------------------------------*/
static int cmListFileLexerInput(cmListFileLexer* lexer, char* buffer,
                                size_t bufferSize)
{
  if(lexer)
    {
    if(lexer->file)
      {
      /* Convert CRLF -> LF explicitly.  The C FILE "t"ext mode
         does not convert newlines on all platforms.  Move any
         trailing CR to the start of the buffer for the next read. */
      size_t cr = lexer->cr;
      size_t n;
      buffer[0] = '\r';
      n = fread(buffer+cr, 1, bufferSize-cr, lexer->file);
      if(n)
        {
        char* o = buffer;
        const char* i = buffer;
        const char* e;
        n += cr;
        cr = (buffer[n-1] == '\r')? 1:0;
        e = buffer + n - cr;
        while(i != e)
          {
          if(i[0] == '\r' && i[1] == '\n')
            {
            ++i;
            }
          *o++ = *i++;
          }
        n = o - buffer;
        }
      else
        {
        n = cr;
        cr = 0;
        }
      lexer->cr = cr;
      return n;
      }
    else if(lexer->string_left)
      {
      int length = lexer->string_left;
      if((int)bufferSize < length) { length = (int)bufferSize; }
      memcpy(buffer, lexer->string_position, length);
      lexer->string_position += length;
      lexer->string_left -= length;
      return length;
      }
    }
  return 0;
}

/*--------------------------------------------------------------------------*/
static void cmListFileLexerInit(cmListFileLexer* lexer)
{
  if(lexer->file || lexer->string_buffer)
    {
    cmListFileLexer_yylex_init(&lexer->scanner);
    cmListFileLexer_yyset_extra(lexer, lexer->scanner);
    }
}

/*--------------------------------------------------------------------------*/
static void cmListFileLexerDestroy(cmListFileLexer* lexer)
{
  cmListFileLexerSetToken(lexer, 0, 0);
  if(lexer->file || lexer->string_buffer)
    {
    cmListFileLexer_yylex_destroy(lexer->scanner);
    if(lexer->file)
      {
      fclose(lexer->file);
      lexer->file = 0;
      }
    if(lexer->string_buffer)
      {
      free(lexer->string_buffer);
      lexer->string_buffer = 0;
      lexer->string_left = 0;
      lexer->string_position = 0;
      }
    }
}

/*--------------------------------------------------------------------------*/
cmListFileLexer* cmListFileLexer_New()
{
  cmListFileLexer* lexer = (cmListFileLexer*)malloc(sizeof(cmListFileLexer));
  if(!lexer)
    {
    return 0;
    }
  memset(lexer, 0, sizeof(*lexer));
  lexer->line = 1;
  lexer->column = 1;
  return lexer;
}

/*--------------------------------------------------------------------------*/
void cmListFileLexer_Delete(cmListFileLexer* lexer)
{
  cmListFileLexer_SetFileName(lexer, 0, 0);
  free(lexer);
}

/*--------------------------------------------------------------------------*/
static cmListFileLexer_BOM cmListFileLexer_ReadBOM(FILE* f)
{
  unsigned char b[2];
  if(fread(b, 1, 2, f) == 2)
    {
    if(b[0] == 0xEF && b[1] == 0xBB)
      {
      if(fread(b, 1, 1, f) == 1 && b[0] == 0xBF)
        {
        return cmListFileLexer_BOM_UTF8;
        }
      }
    else if(b[0] == 0xFE && b[1] == 0xFF)
      {
      /* UTF-16 BE */
      return cmListFileLexer_BOM_UTF16BE;
      }
    else if(b[0] == 0 && b[1] == 0)
      {
      if(fread(b, 1, 2, f) == 2 && b[0] == 0xFE && b[1] == 0xFF)
        {
        return cmListFileLexer_BOM_UTF32BE;
        }
      }
    else if(b[0] == 0xFF && b[1] == 0xFE)
      {
      fpos_t p;
      fgetpos(f, &p);
      if(fread(b, 1, 2, f) == 2 && b[0] == 0 && b[1] == 0)
        {
        return cmListFileLexer_BOM_UTF32LE;
        }
      fsetpos(f, &p);
      return cmListFileLexer_BOM_UTF16LE;
      }
    }
  rewind(f);
  return cmListFileLexer_BOM_None;
}

/*--------------------------------------------------------------------------*/
int cmListFileLexer_SetFileName(cmListFileLexer* lexer, const char* name,
                                cmListFileLexer_BOM* bom)
{
  int result = 1;
  cmListFileLexerDestroy(lexer);
  if(name)
    {
#ifdef _WIN32
    wchar_t* wname = cmsysEncoding_DupToWide(name);
    lexer->file = _wfopen(wname, L"rb");
    free(wname);
#else
    lexer->file = fopen(name, "rb");
#endif
    if(lexer->file)
      {
      if(bom)
        {
        *bom = cmListFileLexer_ReadBOM(lexer->file);
        }
      }
    else
      {
      result = 0;
      }
    }
  cmListFileLexerInit(lexer);
  return result;
}

/*--------------------------------------------------------------------------*/
int cmListFileLexer_SetString(cmListFileLexer* lexer, const char* text)
{
  int result = 1;
  cmListFileLexerDestroy(lexer);
  if(text)
    {
    int length = (int)strlen(text);
    lexer->string_buffer = (char*)malloc(length+1);
    if(lexer->string_buffer)
      {
      strcpy(lexer->string_buffer, text);
      lexer->string_position = lexer->string_buffer;
      lexer->string_left = length;
      }
    else
      {
      result = 0;
      }
    }
  cmListFileLexerInit(lexer);
  return result;
}

/*--------------------------------------------------------------------------*/
cmListFileLexer_Token* cmListFileLexer_Scan(cmListFileLexer* lexer)
{
  if(!lexer->file)
    {
    return 0;
    }
  if(cmListFileLexer_yylex(lexer->scanner, lexer))
    {
    return &lexer->token;
    }
  else
    {
    cmListFileLexer_SetFileName(lexer, 0, 0);
    return 0;
    }
}

/*--------------------------------------------------------------------------*/
long cmListFileLexer_GetCurrentLine(cmListFileLexer* lexer)
{
  if(lexer->file)
    {
    return lexer->line;
    }
  else
    {
    return 0;
    }
}

/*--------------------------------------------------------------------------*/
long cmListFileLexer_GetCurrentColumn(cmListFileLexer* lexer)
{
  if(lexer->file)
    {
    return lexer->column;
    }
  else
    {
    return 0;
    }
}

/*--------------------------------------------------------------------------*/
const char* cmListFileLexer_GetTypeAsString(cmListFileLexer* lexer,
                                            cmListFileLexer_Type type)
{
  (void)lexer;
  switch(type)
    {
    case cmListFileLexer_Token_None: return "nothing";
    case cmListFileLexer_Token_Space: return "space";
    case cmListFileLexer_Token_Newline: return "newline";
    case cmListFileLexer_Token_Identifier: return "identifier";
    case cmListFileLexer_Token_ParenLeft: return "left paren";
    case cmListFileLexer_Token_ParenRight: return "right paren";
    case cmListFileLexer_Token_ArgumentUnquoted: return "unquoted argument";
    case cmListFileLexer_Token_ArgumentQuoted: return "quoted argument";
    case cmListFileLexer_Token_ArgumentBracket: return "bracket argument";
    case cmListFileLexer_Token_CommentBracket: return "bracket comment";
    case cmListFileLexer_Token_BadCharacter: return "bad character";
    case cmListFileLexer_Token_BadBracket: return "unterminated bracket";
    case cmListFileLexer_Token_BadString: return "unterminated string";
    }
  return "unknown token";
}