Training courses

Kernel and Embedded Linux

Bootlin training courses

Embedded Linux, kernel,
Yocto Project, Buildroot, real-time,
graphics, boot time, debugging...

Bootlin logo

Elixir Cross Referencer

  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
/* xgettext Smalltalk backend.
   Copyright (C) 2002-2003, 2005 Free Software Foundation, Inc.

   This file was written by Bruno Haible <haible@clisp.cons.org>, 2002.

   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., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.  */

#ifdef HAVE_CONFIG_H
# include "config.h"
#endif

#include <errno.h>
#include <stdio.h>
#include <stdlib.h>

#include "message.h"
#include "xgettext.h"
#include "x-smalltalk.h"
#include "error.h"
#include "xalloc.h"
#include "exit.h"
#include "gettext.h"

#define _(s) gettext(s)

#define SIZEOF(a) (sizeof(a) / sizeof(a[0]))


/* The relevant parts of the Smalltalk syntax are:

     stringliteral ::= string | stringconst | symconst
     stringconst ::= "#"string
     string      ::= "'"[char]*"'"
     symconst    ::= "#"symbol
     symbol      ::= id | binsel | keysel[keysel]*
     keysel      ::= id":"
     id          ::= letter[letter|digit]*
     letter      ::= "A".."Z" | "a".."z"
     digit       ::= "0".."9"
     binsel      ::= selchar[selchar]
     selchar     ::= "+" | "-" | "*" | "/" | "~" | "|" | "," | "<" | ">"
                     | "=" | "&" | "@" | "?" | "%" | "\"

   Strings can contain any characters; to include the string delimiter itself,
   it must be duplicated.

   Character constants are written  "$"char

   Comments are enclosed within double quotes.

   In well-formed expressions, {} and [] and () are balanced.
 */


/* ======================== Reading of characters.  ======================== */


/* Real filename, used in error messages about the input file.  */
static const char *real_file_name;

/* Logical filename and line number, used to label the extracted messages.  */
static char *logical_file_name;
static int line_number;

/* The input file stream.  */
static FILE *fp;


/* 1. line_number handling.  */

static int
phase1_getc ()
{
  int c = getc (fp);

  if (c == EOF)
    {
      if (ferror (fp))
	error (EXIT_FAILURE, errno, _("error while reading \"%s\""),
	       real_file_name);
      return EOF;
    }

  if (c == '\n')
    line_number++;

  return c;
}

/* Supports only one pushback character.  */
static void
phase1_ungetc (int c)
{
  if (c != EOF)
    {
      if (c == '\n')
	--line_number;

      ungetc (c, fp);
    }
}


/* Accumulating comments.  */

static char *buffer;
static size_t bufmax;
static size_t buflen;

static inline void
comment_start ()
{
  buflen = 0;
}

static inline void
comment_add (int c)
{
  if (buflen >= bufmax)
    {
      bufmax = 2 * bufmax + 10;
      buffer = xrealloc (buffer, bufmax);
    }
  buffer[buflen++] = c;
}

static inline void
comment_line_end ()
{
  while (buflen >= 1
	 && (buffer[buflen - 1] == ' ' || buffer[buflen - 1] == '\t'))
    --buflen;
  if (buflen >= bufmax)
    {
      bufmax = 2 * bufmax + 10;
      buffer = xrealloc (buffer, bufmax);
    }
  buffer[buflen] = '\0';
  savable_comment_add (buffer);
}


/* These are for tracking whether comments count as immediately before
   keyword.  */
static int last_comment_line;
static int last_non_comment_line;


/* ========================== Reading of tokens.  ========================== */


enum token_type_ty
{
  token_type_eof,
  token_type_uniq,		/* # */
  token_type_symbol,		/* symbol */
  token_type_string_literal,	/* string, stringconst, symbolconst */
  token_type_other		/* misc. operator */
};
typedef enum token_type_ty token_type_ty;

typedef struct token_ty token_ty;
struct token_ty
{
  token_type_ty type;
  char *string;		/* for token_type_string_literal, token_type_symbol */
  int line_number;
};


/* 2. Combine characters into tokens.  Discard comments and whitespace.  */

static token_ty phase2_pushback[1];
static int phase2_pushback_length;

static void
phase2_get (token_ty *tp)
{
  static char *buffer;
  static int bufmax;
  int bufpos;
  int c;

  if (phase2_pushback_length)
    {
      *tp = phase2_pushback[--phase2_pushback_length];
      return;
    }

  tp->string = NULL;

  for (;;)
    {
      tp->line_number = line_number;
      c = phase1_getc ();
      switch (c)
	{
	case EOF:
	  tp->type = token_type_eof;
	  return;

	case '"':
	  {
	    /* Comment.  */
	    int lineno;

	    comment_start ();
	    lineno = line_number;
	    for (;;)
	      {
		c = phase1_getc ();
		if (c == '"' || c == EOF)
		  break;
		if (c == '\n')
		  {
		    comment_line_end ();
		    comment_start ();
		  }
		else
		  {
		    /* We skip all leading white space, but not EOLs.  */
		    if (!(buflen == 0 && (c == ' ' || c == '\t')))
		      comment_add (c);
		  }
	      }
	    comment_line_end ();
	    last_comment_line = lineno;
	    continue;
	  }

	case '\n':
	  if (last_non_comment_line > last_comment_line)
	    savable_comment_reset ();
	  /* FALLTHROUGH */
	case ' ':
	case '\t':
	case '\r':
	  /* Ignore whitespace.  */
	  continue;
	}

      last_non_comment_line = tp->line_number;

      switch (c)
	{
	case '\'':
	  /* String literal.  */
	  bufpos = 0;
	  for (;;)
	    {
	      c = phase1_getc ();
	      if (c == EOF)
		break;
	      if (c == '\'')
		{
		  c = phase1_getc ();
		  if (c != '\'')
		    {
		      phase1_ungetc (c);
		      break;
		    }
		}
	      if (bufpos >= bufmax)
		{
		  bufmax = 2 * bufmax + 10;
		  buffer = xrealloc (buffer, bufmax);
		}
	      buffer[bufpos++] = c;
	    }
	  if (bufpos >= bufmax)
	    {
	      bufmax = 2 * bufmax + 10;
	      buffer = xrealloc (buffer, bufmax);
	    }
	  buffer[bufpos] = 0;
	  tp->type = token_type_string_literal;
	  tp->string = xstrdup (buffer);
	  return;

	case '+':
	case '-':
	case '*':
	case '/':
	case '~':
	case '|':
	case ',':
	case '<':
	case '>':
	case '=':
	case '&':
	case '@':
	case '?':
	case '%':
	case '\\':
	  {
	    char *name;
	    int c2 = phase1_getc ();
	    switch (c2)
	      {
	      case '+':
	      case '-':
	      case '*':
	      case '/':
	      case '~':
	      case '|':
	      case ',':
	      case '<':
	      case '>':
	      case '=':
	      case '&':
	      case '@':
	      case '?':
	      case '%':
		name = xmalloc (3);
		name[0] = c;
		name[1] = c2;
		name[2] = '\0';
		tp->type = token_type_symbol;
		tp->string = name;
		return;
	      default:
		phase1_ungetc (c2);
		break;
	      }
	    name = xmalloc (2);
	    name[0] = c;
	    name[1] = '\0';
	    tp->type = token_type_symbol;
	    tp->string = name;
	    return;
	  }

	case 'A': case 'B': case 'C': case 'D': case 'E': case 'F':
	case 'G': case 'H': case 'I': case 'J': case 'K': case 'L':
	case 'M': case 'N': case 'O': case 'P': case 'Q': case 'R':
	case 'S': case 'T': case 'U': case 'V': case 'W': case 'X':
	case 'Y': case 'Z':
	case 'a': case 'b': case 'c': case 'd': case 'e': case 'f':
	case 'g': case 'h': case 'i': case 'j': case 'k': case 'l':
	case 'm': case 'n': case 'o': case 'p': case 'q': case 'r':
	case 's': case 't': case 'u': case 'v': case 'w': case 'x':
	case 'y': case 'z':
	  /* Recognize id or id":"[id":"]* or id":"[id":"]*id.  */
	  bufpos = 0;
	  for (;;)
	    {
	      if (bufpos >= bufmax)
		{
		  bufmax = 2 * bufmax + 10;
		  buffer = xrealloc (buffer, bufmax);
		}
	      buffer[bufpos++] = c;
	      c = phase1_getc ();
	      switch (c)
		{
		case 'A': case 'B': case 'C': case 'D': case 'E': case 'F':
		case 'G': case 'H': case 'I': case 'J': case 'K': case 'L':
		case 'M': case 'N': case 'O': case 'P': case 'Q': case 'R':
		case 'S': case 'T': case 'U': case 'V': case 'W': case 'X':
		case 'Y': case 'Z':
		case 'a': case 'b': case 'c': case 'd': case 'e': case 'f':
		case 'g': case 'h': case 'i': case 'j': case 'k': case 'l':
		case 'm': case 'n': case 'o': case 'p': case 'q': case 'r':
		case 's': case 't': case 'u': case 'v': case 'w': case 'x':
		case 'y': case 'z':
		case '0': case '1': case '2': case '3': case '4':
		case '5': case '6': case '7': case '8': case '9':
		  continue;
		case ':':
		  if (bufpos >= bufmax)
		    {
		      bufmax = 2 * bufmax + 10;
		      buffer = xrealloc (buffer, bufmax);
		    }
		  buffer[bufpos++] = c;
		  c = phase1_getc ();
		  switch (c)
		    {
		    case 'A': case 'B': case 'C': case 'D': case 'E': case 'F':
		    case 'G': case 'H': case 'I': case 'J': case 'K': case 'L':
		    case 'M': case 'N': case 'O': case 'P': case 'Q': case 'R':
		    case 'S': case 'T': case 'U': case 'V': case 'W': case 'X':
		    case 'Y': case 'Z':
		    case 'a': case 'b': case 'c': case 'd': case 'e': case 'f':
		    case 'g': case 'h': case 'i': case 'j': case 'k': case 'l':
		    case 'm': case 'n': case 'o': case 'p': case 'q': case 'r':
		    case 's': case 't': case 'u': case 'v': case 'w': case 'x':
		    case 'y': case 'z':
		      continue;
		    default:
		      phase1_ungetc (c);
		      break;
		    }
		  break;
		default:
		  phase1_ungetc (c);
		  break;
		}
	      break;
	    }
	  if (bufpos >= bufmax)
	    {
	      bufmax = 2 * bufmax + 10;
	      buffer = xrealloc (buffer, bufmax);
	    }
	  buffer[bufpos] = '\0';
	  tp->string = xstrdup (buffer);
	  tp->type = token_type_symbol;
	  return;

	case '#':
	  /* Uniquification operator.  */
	  tp->type = token_type_uniq;
	  return;

	case '$':
	  c = phase1_getc ();
	  tp->type = token_type_other;
	  return;

	default:
	  tp->type = token_type_other;
	  return;
	}
    }
}

/* Supports only one pushback token.  */
static void
phase2_unget (token_ty *tp)
{
  if (tp->type != token_type_eof)
    {
      if (phase2_pushback_length == SIZEOF (phase2_pushback))
	abort ();
      phase2_pushback[phase2_pushback_length++] = *tp;
    }
}


/* 3. Combine "# string_literal" and "# symbol" to a single token.  */

static void
x_smalltalk_lex (token_ty *tp)
{
  phase2_get (tp);
  if (tp->type == token_type_uniq)
    {
      token_ty token2;

      phase2_get (&token2);
      if (token2.type == token_type_symbol
	  || token2.type == token_type_string_literal)
	{
	  tp->type = token_type_string_literal;
	  tp->string = token2.string;
	}
      else
	phase2_unget (&token2);
    }
}


/* ========================= Extracting strings.  ========================== */

/* The file is broken into tokens.  Scan the token stream, looking for the
   following patterns
      NLS ? <string>
      NLS at: <string>
      NLS at: <string> plural: <string>
   where <string> is one of
      string_literal
      # string_literal
      # symbol
 */

void
extract_smalltalk (FILE *f,
		   const char *real_filename, const char *logical_filename,
		   flag_context_list_table_ty *flag_table,
		   msgdomain_list_ty *mdlp)
{
  message_list_ty *mlp = mdlp->item[0]->messages;

  fp = f;
  real_file_name = real_filename;
  logical_file_name = xstrdup (logical_filename);
  line_number = 1;

  last_comment_line = -1;
  last_non_comment_line = -1;

  /* Eat tokens until eof is seen.  */
  {
    /* 0 when no "NLS" has been seen.
       1 after "NLS".
       2 after "NLS ?".
       3 after "NLS at:".
       4 after "NLS at: <string>".
       5 after "NLS at: <string> plural:".  */
    int state;
    /* Remember the message containing the msgid, for msgid_plural.
       Non-NULL in states 4, 5.  */
    message_ty *plural_mp = NULL;

    /* Start state is 0.  */
    state = 0;

    for (;;)
      {
	token_ty token;

	x_smalltalk_lex (&token);

	switch (token.type)
	  {
	  case token_type_symbol:
	    state = (strcmp (token.string, "NLS") == 0 ? 1 :
		     strcmp (token.string, "?") == 0 && state == 1 ? 2 :
		     strcmp (token.string, "at:") == 0 && state == 1 ? 3 :
		     strcmp (token.string, "plural:") == 0 && state == 4 ? 5 :
		     0);
	    free (token.string);
	    break;

	  case token_type_string_literal:
	    if (state == 2)
	      {
		lex_pos_ty pos;
		pos.file_name = logical_file_name;
		pos.line_number = token.line_number;
		remember_a_message (mlp, NULL, token.string, null_context,
				    &pos, savable_comment);
		state = 0;
		break;
	      }
	    if (state == 3)
	      {
		lex_pos_ty pos;
		pos.file_name = logical_file_name;
		pos.line_number = token.line_number;
		plural_mp = remember_a_message (mlp, NULL, token.string,
						null_context, &pos,
						savable_comment);
		state = 4;
		break;
	      }
	    if (state == 5)
	      {
		lex_pos_ty pos;
		pos.file_name = logical_file_name;
		pos.line_number = token.line_number;
		remember_a_message_plural (plural_mp, token.string,
					   null_context, &pos,
					   savable_comment);
		state = 0;
		break;
	      }
	    state = 0;
	    free (token.string);
	    break;

	  case token_type_uniq:
	  case token_type_other:
	    state = 0;
	    break;

	  case token_type_eof:
	    break;

	  default:
	    abort ();
	  }

	if (token.type == token_type_eof)
	  break;
      }
  }

  /* Close scanner.  */
  fp = NULL;
  real_file_name = NULL;
  logical_file_name = NULL;
  line_number = 0;
}