syntax.c 102 KB
Newer Older
Richard M. Stallman's avatar
Richard M. Stallman committed
1
/* GNU Emacs routines to deal with syntax tables; also word and list parsing.
2
   Copyright (C) 1985, 1987, 1993-1995, 1997-1999, 2001-2011
3
                 Free Software Foundation, Inc.
Richard M. Stallman's avatar
Richard M. Stallman committed
4 5 6

This file is part of GNU Emacs.

7
GNU Emacs is free software: you can redistribute it and/or modify
Richard M. Stallman's avatar
Richard M. Stallman committed
8
it under the terms of the GNU General Public License as published by
9 10
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
Richard M. Stallman's avatar
Richard M. Stallman committed
11 12 13 14 15 16 17

GNU Emacs 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
18
along with GNU Emacs.  If not, see <http://www.gnu.org/licenses/>.  */
Richard M. Stallman's avatar
Richard M. Stallman committed
19 20


21
#include <config.h>
22

Richard M. Stallman's avatar
Richard M. Stallman committed
23
#include <ctype.h>
24
#include <sys/types.h>
25
#include <setjmp.h>
Richard M. Stallman's avatar
Richard M. Stallman committed
26 27 28
#include "lisp.h"
#include "commands.h"
#include "buffer.h"
29
#include "character.h"
Stefan Monnier's avatar
Stefan Monnier committed
30
#include "keymap.h"
Richard M. Stallman's avatar
Richard M. Stallman committed
31
#include "regex.h"
32 33 34 35

/* Make syntax table lookup grant data in gl_state.  */
#define SYNTAX_ENTRY_VIA_PROPERTY

Richard M. Stallman's avatar
Richard M. Stallman committed
36
#include "syntax.h"
37
#include "intervals.h"
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
#include "category.h"

/* Then there are seven single-bit flags that have the following meanings:
  1. This character is the first of a two-character comment-start sequence.
  2. This character is the second of a two-character comment-start sequence.
  3. This character is the first of a two-character comment-end sequence.
  4. This character is the second of a two-character comment-end sequence.
  5. This character is a prefix, for backward-prefix-chars.
  6. The char is part of a delimiter for comments of style "b".
  7. This character is part of a nestable comment sequence.
  8. The char is part of a delimiter for comments of style "c".
  Note that any two-character sequence whose first character has flag 1
  and whose second character has flag 2 will be interpreted as a comment start.

  bit 6 and 8 are used to discriminate between different comment styles.
  Languages such as C++ allow two orthogonal syntax start/end pairs
  and bit 6 is used to determine whether a comment-end or Scommentend
  ends style a or b.  Comment markers can start style a, b, c, or bc.
  Style a is always the default.
  For 2-char comment markers, the style b flag is only looked up on the second
  char of the comment marker and on the first char of the comment ender.
  For style c (like to for the nested flag), the flag can be placed on any
  one of the chars.
  */

/* These macros extract specific flags from an integer
   that holds the syntax code and the flags.  */

#define SYNTAX_FLAGS_COMSTART_FIRST(flags) (((flags) >> 16) & 1)

#define SYNTAX_FLAGS_COMSTART_SECOND(flags) (((flags) >> 17) & 1)

#define SYNTAX_FLAGS_COMEND_FIRST(flags) (((flags) >> 18) & 1)

#define SYNTAX_FLAGS_COMEND_SECOND(flags) (((flags) >> 19) & 1)

#define SYNTAX_FLAGS_PREFIX(flags) (((flags) >> 20) & 1)

#define SYNTAX_FLAGS_COMMENT_STYLEB(flags) (((flags) >> 21) & 1)
#define SYNTAX_FLAGS_COMMENT_STYLEC(flags) (((flags) >> 22) & 2)
/* FLAGS should be the flags of the main char of the comment marker, e.g.
   the second for comstart and the first for comend.  */
#define SYNTAX_FLAGS_COMMENT_STYLE(flags, other_flags) \
  (SYNTAX_FLAGS_COMMENT_STYLEB (flags) \
   | SYNTAX_FLAGS_COMMENT_STYLEC (flags) \
   | SYNTAX_FLAGS_COMMENT_STYLEC (other_flags))

#define SYNTAX_FLAGS_COMMENT_NESTED(flags) (((flags) >> 22) & 1)

/* These macros extract a particular flag for a given character.  */

#define SYNTAX_COMEND_FIRST(c) \
  (SYNTAX_FLAGS_COMEND_FIRST (SYNTAX_WITH_FLAGS (c)))
#define SYNTAX_PREFIX(c) (SYNTAX_FLAGS_PREFIX (SYNTAX_WITH_FLAGS (c)))
92 93 94 95 96 97 98

/* We use these constants in place for comment-style and
   string-ender-char to distinguish  comments/strings started by
   comment_fence and string_fence codes.  */

#define ST_COMMENT_STYLE (256 + 1)
#define ST_STRING_STYLE (256 + 2)
Richard M. Stallman's avatar
Richard M. Stallman committed
99

100 101
static Lisp_Object Qsyntax_table_p;
static Lisp_Object Qsyntax_table, Qscan_error;
Richard M. Stallman's avatar
Richard M. Stallman committed
102

103
#ifndef __GNUC__
104 105 106 107
/* Used as a temporary in SYNTAX_ENTRY and other macros in syntax.h,
   if not compiled with GCC.  No need to mark it, since it is used
   only very temporarily.  */
Lisp_Object syntax_temp;
108
#endif
109

110 111 112 113
/* This is the internal form of the parse state used in parse-partial-sexp.  */

struct lisp_parse_state
  {
114 115 116 117 118 119 120 121 122 123 124 125 126 127
    int depth;	   /* Depth at end of parsing.  */
    int instring;  /* -1 if not within string, else desired terminator.  */
    int incomment; /* -1 if in unnestable comment else comment nesting */
    int comstyle;  /* comment style a=0, or b=1, or ST_COMMENT_STYLE.  */
    int quoted;	   /* Nonzero if just after an escape char at end of parsing */
    int mindepth;  /* Minimum depth seen while scanning.  */
    /* Char number of most recent start-of-expression at current level */
    EMACS_INT thislevelstart;
    /* Char number of start of containing expression */
    EMACS_INT prevlevelstart;
    EMACS_INT location;	     /* Char number at which parsing stopped.  */
    EMACS_INT comstr_start;  /* Position of last comment/string starter.  */
    Lisp_Object levelstarts; /* Char numbers of starts-of-expression
				of levels (starting from outermost).  */
128 129
  };

130 131 132
/* These variables are a cache for finding the start of a defun.
   find_start_pos is the place for which the defun start was found.
   find_start_value is the defun start position found for it.
133
   find_start_value_byte is the corresponding byte position.
134 135 136 137
   find_start_buffer is the buffer it was found in.
   find_start_begv is the BEGV value when it was found.
   find_start_modiff is the value of MODIFF when it was found.  */

138 139 140
static EMACS_INT find_start_pos;
static EMACS_INT find_start_value;
static EMACS_INT find_start_value_byte;
141
static struct buffer *find_start_buffer;
142
static EMACS_INT find_start_begv;
143
static int find_start_modiff;
144 145


146
static Lisp_Object Fsyntax_table_p (Lisp_Object);
147 148 149 150 151 152 153
static Lisp_Object skip_chars (int, Lisp_Object, Lisp_Object, int);
static Lisp_Object skip_syntaxes (int, Lisp_Object, Lisp_Object);
static Lisp_Object scan_lists (EMACS_INT, EMACS_INT, EMACS_INT, int);
static void scan_sexps_forward (struct lisp_parse_state *,
                                EMACS_INT, EMACS_INT, EMACS_INT, int,
                                int, Lisp_Object, int);
static int in_classes (int, Lisp_Object);
154

155 156 157 158 159
/* Whether the syntax of the character C has the prefix flag set.  */
int syntax_prefix_flag_p (int c)
{
  return SYNTAX_PREFIX (c);
}
160 161 162 163 164 165

struct gl_state_s gl_state;		/* Global state of syntax parser.  */

#define INTERVALS_AT_ONCE 10		/* 1 + max-number of intervals
					   to scan to property-change.  */

166 167
/* Update gl_state to an appropriate interval which contains CHARPOS.  The
   sign of COUNT give the relative position of CHARPOS wrt the previously
168
   valid interval.  If INIT, only [be]_property fields of gl_state are
169
   valid at start, the rest is filled basing on OBJECT.
170

171
   `gl_state.*_i' are the intervals, and CHARPOS is further in the search
172 173
   direction than the intervals - or in an interval.  We update the
   current syntax-table basing on the property of this interval, and
174
   update the interval to start further than CHARPOS - or be
175
   NULL_INTERVAL.  We also update lim_property to be the next value of
176
   charpos to call this subroutine again - or be before/after the
177 178 179
   start/end of OBJECT.  */

void
180
update_syntax_table (EMACS_INT charpos, EMACS_INT count, int init,
181
		     Lisp_Object object)
182 183
{
  Lisp_Object tmp_table;
184 185
  unsigned cnt = 0;
  int invalidate = 1;
186
  INTERVAL i;
187 188 189

  if (init)
    {
190
      gl_state.old_prop = Qnil;
191 192
      gl_state.start = gl_state.b_property;
      gl_state.stop = gl_state.e_property;
193 194
      i = interval_of (charpos, object);
      gl_state.backward_i = gl_state.forward_i = i;
195 196 197
      invalidate = 0;
      if (NULL_INTERVAL_P (i))
	return;
198
      /* interval_of updates only ->position of the return value, so
199
	 update the parents manually to speed up update_interval.  */
200
      while (!NULL_PARENT (i))
201 202
	{
	  if (AM_RIGHT_CHILD (i))
203
	    INTERVAL_PARENT (i)->position = i->position
204
	      - LEFT_TOTAL_LENGTH (i) + TOTAL_LENGTH (i) /* right end */
205 206
	      - TOTAL_LENGTH (INTERVAL_PARENT (i))
	      + LEFT_TOTAL_LENGTH (INTERVAL_PARENT (i));
207
	  else
208
	    INTERVAL_PARENT (i)->position = i->position - LEFT_TOTAL_LENGTH (i)
209
	      + TOTAL_LENGTH (i);
210
	  i = INTERVAL_PARENT (i);
211 212
	}
      i = gl_state.forward_i;
213
      gl_state.b_property = i->position - gl_state.offset;
214
      gl_state.e_property = INTERVAL_LAST_POS (i) - gl_state.offset;
215 216
      goto update;
    }
217
  i = count > 0 ? gl_state.forward_i : gl_state.backward_i;
218

219
  /* We are guaranteed to be called with CHARPOS either in i,
220
     or further off.  */
221 222
  if (NULL_INTERVAL_P (i))
    error ("Error in syntax_table logic for to-the-end intervals");
223
  else if (charpos < i->position)		/* Move left.  */
224 225
    {
      if (count > 0)
226
	error ("Error in syntax_table logic for intervals <-");
227
      /* Update the interval.  */
228
      i = update_interval (i, charpos);
229
      if (INTERVAL_LAST_POS (i) != gl_state.b_property)
230 231 232
	{
	  invalidate = 0;
	  gl_state.forward_i = i;
233
	  gl_state.e_property = INTERVAL_LAST_POS (i) - gl_state.offset;
234
	}
235
    }
236
  else if (charpos >= INTERVAL_LAST_POS (i)) /* Move right.  */
237 238
    {
      if (count < 0)
239
	error ("Error in syntax_table logic for intervals ->");
240
      /* Update the interval.  */
241
      i = update_interval (i, charpos);
242
      if (i->position != gl_state.e_property)
243 244 245
	{
	  invalidate = 0;
	  gl_state.backward_i = i;
246
	  gl_state.b_property = i->position - gl_state.offset;
247 248 249 250 251 252 253 254
	}
    }

  update:
  tmp_table = textget (i->plist, Qsyntax_table);

  if (invalidate)
    invalidate = !EQ (tmp_table, gl_state.old_prop); /* Need to invalidate? */
Juanma Barranquero's avatar
Juanma Barranquero committed
255

256 257 258
  if (invalidate)		/* Did not get to adjacent interval.  */
    {				/* with the same table => */
				/* invalidate the old range.  */
259 260 261
      if (count > 0)
	{
	  gl_state.backward_i = i;
262 263 264
	  gl_state.b_property = i->position - gl_state.offset;
	}
      else
265
	{
266
	  gl_state.forward_i = i;
267
	  gl_state.e_property = INTERVAL_LAST_POS (i) - gl_state.offset;
268 269
	}
    }
270

271
  if (!EQ (tmp_table, gl_state.old_prop))
272
    {
273 274 275 276 277
      gl_state.current_syntax_table = tmp_table;
      gl_state.old_prop = tmp_table;
      if (EQ (Fsyntax_table_p (tmp_table), Qt))
	{
	  gl_state.use_global = 0;
Juanma Barranquero's avatar
Juanma Barranquero committed
278
	}
279 280 281 282 283
      else if (CONSP (tmp_table))
	{
	  gl_state.use_global = 1;
	  gl_state.global_code = tmp_table;
	}
Juanma Barranquero's avatar
Juanma Barranquero committed
284
      else
285 286
	{
	  gl_state.use_global = 0;
Tom Tromey's avatar
Tom Tromey committed
287
	  gl_state.current_syntax_table = BVAR (current_buffer, syntax_table);
288
	}
289 290 291 292 293 294 295
    }

  while (!NULL_INTERVAL_P (i))
    {
      if (cnt && !EQ (tmp_table, textget (i->plist, Qsyntax_table)))
	{
	  if (count > 0)
296 297 298 299 300 301
	    {
	      gl_state.e_property = i->position - gl_state.offset;
	      gl_state.forward_i = i;
	    }
	  else
	    {
302 303
	      gl_state.b_property
		= i->position + LENGTH (i) - gl_state.offset;
304 305 306
	      gl_state.backward_i = i;
	    }
	  return;
307
	}
Juanma Barranquero's avatar
Juanma Barranquero committed
308
      else if (cnt == INTERVALS_AT_ONCE)
309 310
	{
	  if (count > 0)
311
	    {
312 313 314 315 316 317
	      gl_state.e_property
		= i->position + LENGTH (i) - gl_state.offset
		/* e_property at EOB is not set to ZV but to ZV+1, so that
		   we can do INC(from);UPDATE_SYNTAX_TABLE_FORWARD without
		   having to check eob between the two.  */
		+ (NULL_INTERVAL_P (next_interval (i)) ? 1 : 0);
318 319 320 321 322 323 324 325
	      gl_state.forward_i = i;
	    }
	  else
	    {
	      gl_state.b_property = i->position - gl_state.offset;
	      gl_state.backward_i = i;
	    }
	  return;
326 327 328 329
	}
      cnt++;
      i = count > 0 ? next_interval (i) : previous_interval (i);
    }
330 331 332 333 334
  eassert (NULL_INTERVAL_P (i)); /* This property goes to the end.  */
  if (count > 0)
    gl_state.e_property = gl_state.stop;
  else
    gl_state.b_property = gl_state.start;
335 336
}

337 338 339
/* Returns TRUE if char at CHARPOS is quoted.
   Global syntax-table data should be set up already to be good at CHARPOS
   or after.  On return global syntax data is good for lookup at CHARPOS. */
340 341

static int
342
char_quoted (EMACS_INT charpos, EMACS_INT bytepos)
343 344
{
  register enum syntaxcode code;
345
  register EMACS_INT beg = BEGV;
346
  register int quoted = 0;
347
  EMACS_INT orig = charpos;
348

349
  while (charpos > beg)
350
    {
351
      int c;
352
      DEC_BOTH (charpos, bytepos);
353

354
      UPDATE_SYNTAX_TABLE_BACKWARD (charpos);
355
      c = FETCH_CHAR_AS_MULTIBYTE (bytepos);
356
      code = SYNTAX (c);
357 358 359 360
      if (! (code == Scharquote || code == Sescape))
	break;

      quoted = !quoted;
361
    }
362 363

  UPDATE_SYNTAX_TABLE (orig);
364 365
  return quoted;
}
366 367 368 369

/* Return the bytepos one character before BYTEPOS.
   We assume that BYTEPOS is not at the start of the buffer.  */

Paul Eggert's avatar
Paul Eggert committed
370
static inline EMACS_INT
371
dec_bytepos (EMACS_INT bytepos)
372
{
Tom Tromey's avatar
Tom Tromey committed
373
  if (NILP (BVAR (current_buffer, enable_multibyte_characters)))
374 375
    return bytepos - 1;

376 377 378
  DEC_POS (bytepos);
  return bytepos;
}
379

Juanma Barranquero's avatar
Juanma Barranquero committed
380
/* Return a defun-start position before POS and not too far before.
Richard M. Stallman's avatar
Richard M. Stallman committed
381 382 383
   It should be the last one before POS, or nearly the last.

   When open_paren_in_column_0_is_defun_start is nonzero,
384
   only the beginning of the buffer is treated as a defun-start.
Richard M. Stallman's avatar
Richard M. Stallman committed
385 386 387 388

   We record the information about where the scan started
   and what its result was, so that another call in the same area
   can return the same value very quickly.
389 390 391 392

   There is no promise at which position the global syntax data is
   valid on return from the subroutine, so the caller should explicitly
   update the global data.  */
393

394
static EMACS_INT
395
find_defun_start (EMACS_INT pos, EMACS_INT pos_byte)
396
{
397
  EMACS_INT opoint = PT, opoint_byte = PT_BYTE;
398

399 400
  if (!open_paren_in_column_0_is_defun_start)
    {
401
      find_start_value = BEGV;
402
      find_start_value_byte = BEGV_BYTE;
403 404 405 406
      find_start_buffer = current_buffer;
      find_start_modiff = MODIFF;
      find_start_begv = BEGV;
      find_start_pos = pos;
407 408 409
      return BEGV;
    }

410 411 412 413 414 415 416 417 418 419 420 421
  /* Use previous finding, if it's valid and applies to this inquiry.  */
  if (current_buffer == find_start_buffer
      /* Reuse the defun-start even if POS is a little farther on.
	 POS might be in the next defun, but that's ok.
	 Our value may not be the best possible, but will still be usable.  */
      && pos <= find_start_pos + 1000
      && pos >= find_start_value
      && BEGV == find_start_begv
      && MODIFF == find_start_modiff)
    return find_start_value;

  /* Back up to start of line.  */
422
  scan_newline (pos, pos_byte, BEGV, BEGV_BYTE, -1, 1);
423

424 425 426
  /* We optimize syntax-table lookup for rare updates.  Thus we accept
     only those `^\s(' which are good in global _and_ text-property
     syntax-tables.  */
427
  SETUP_BUFFER_SYNTAX_TABLE ();
428
  while (PT > BEGV)
429
    {
430 431
      int c;

432 433
      /* Open-paren at start of line means we may have found our
	 defun-start.  */
434
      c = FETCH_CHAR_AS_MULTIBYTE (PT_BYTE);
435
      if (SYNTAX (c) == Sopen)
436
	{
437
	  SETUP_SYNTAX_TABLE (PT + 1, -1);	/* Try again... */
438
	  c = FETCH_CHAR_AS_MULTIBYTE (PT_BYTE);
439
	  if (SYNTAX (c) == Sopen)
440 441
	    break;
	  /* Now fallback to the default value.  */
442
	  SETUP_BUFFER_SYNTAX_TABLE ();
443
	}
444 445
      /* Move to beg of previous line.  */
      scan_newline (PT, PT_BYTE, BEGV, BEGV_BYTE, -2, 1);
446 447 448
    }

  /* Record what we found, for the next try.  */
449 450
  find_start_value = PT;
  find_start_value_byte = PT_BYTE;
451 452 453 454 455
  find_start_buffer = current_buffer;
  find_start_modiff = MODIFF;
  find_start_begv = BEGV;
  find_start_pos = pos;

456 457
  TEMP_SET_PT_BOTH (opoint, opoint_byte);

458 459 460
  return find_start_value;
}

461 462 463
/* Return the SYNTAX_COMEND_FIRST of the character before POS, POS_BYTE.  */

static int
464
prev_char_comend_first (EMACS_INT pos, EMACS_INT pos_byte)
465 466 467 468 469 470 471 472 473 474 475 476 477
{
  int c, val;

  DEC_BOTH (pos, pos_byte);
  UPDATE_SYNTAX_TABLE_BACKWARD (pos);
  c = FETCH_CHAR (pos_byte);
  val = SYNTAX_COMEND_FIRST (c);
  UPDATE_SYNTAX_TABLE_FORWARD (pos + 1);
  return val;
}

/* Return the SYNTAX_COMSTART_FIRST of the character before POS, POS_BYTE.  */

478 479 480 481 482
/* static int
 * prev_char_comstart_first (pos, pos_byte)
 *      int pos, pos_byte;
 * {
 *   int c, val;
Juanma Barranquero's avatar
Juanma Barranquero committed
483
 *
484 485 486 487 488 489 490
 *   DEC_BOTH (pos, pos_byte);
 *   UPDATE_SYNTAX_TABLE_BACKWARD (pos);
 *   c = FETCH_CHAR (pos_byte);
 *   val = SYNTAX_COMSTART_FIRST (c);
 *   UPDATE_SYNTAX_TABLE_FORWARD (pos + 1);
 *   return val;
 * } */
491

492 493 494 495 496 497 498 499 500
/* Checks whether charpos FROM is at the end of a comment.
   FROM_BYTE is the bytepos corresponding to FROM.
   Do not move back before STOP.

   Return a positive value if we find a comment ending at FROM/FROM_BYTE;
   return -1 otherwise.

   If successful, store the charpos of the comment's beginning
   into *CHARPOS_PTR, and the bytepos into *BYTEPOS_PTR.
501 502 503

   Global syntax data remains valid for backward search starting at
   the returned value (or at FROM, if the search was not successful).  */
504 505

static int
506
back_comment (EMACS_INT from, EMACS_INT from_byte, EMACS_INT stop, int comnested, int comstyle, EMACS_INT *charpos_ptr, EMACS_INT *bytepos_ptr)
507 508 509 510 511 512 513 514 515 516
{
  /* Look back, counting the parity of string-quotes,
     and recording the comment-starters seen.
     When we reach a safe place, assume that's not in a string;
     then step the main scan to the earliest comment-starter seen
     an even number of string quotes away from the safe place.

     OFROM[I] is position of the earliest comment-starter seen
     which is I+2X quotes from the comment-end.
     PARITY is current parity of quotes from the comment end.  */
517
  int string_style = -1;	/* Presumed outside of any string. */
518
  int string_lossage = 0;
519
  /* Not a real lossage: indicates that we have passed a matching comment
Juanma Barranquero's avatar
Juanma Barranquero committed
520
     starter plus a non-matching comment-ender, meaning that any matching
521 522 523 524
     comment-starter we might see later could be a false positive (hidden
     inside another comment).
     Test case:  { a (* b } c (* d *) */
  int comment_lossage = 0;
525 526 527
  EMACS_INT comment_end = from;
  EMACS_INT comment_end_byte = from_byte;
  EMACS_INT comstart_pos = 0;
528
  EMACS_INT comstart_byte IF_LINT (= 0);
529 530
  /* Place where the containing defun starts,
     or 0 if we didn't come across it yet.  */
531 532
  EMACS_INT defun_start = 0;
  EMACS_INT defun_start_byte = 0;
533
  register enum syntaxcode code;
534
  int nesting = 1;		/* current comment nesting */
535
  int c;
536 537 538 539 540
  int syntax = 0;

  /* FIXME: A }} comment-ender style leads to incorrect behavior
     in the case of {{ c }}} because we ignore the last two chars which are
     assumed to be comment-enders although they aren't.  */
541 542 543 544 545

  /* At beginning of range to scan, we're outside of strings;
     that determines quote parity to the comment-end.  */
  while (from != stop)
    {
546 547
      EMACS_INT temp_byte;
      int prev_syntax, com2start, com2end;
548
      int comstart;
549

550
      /* Move back and examine a character.  */
551
      DEC_BOTH (from, from_byte);
552 553
      UPDATE_SYNTAX_TABLE_BACKWARD (from);

554
      prev_syntax = syntax;
555
      c = FETCH_CHAR_AS_MULTIBYTE (from_byte);
556
      syntax = SYNTAX_WITH_FLAGS (c);
557 558
      code = SYNTAX (c);

559 560 561
      /* Check for 2-char comment markers.  */
      com2start = (SYNTAX_FLAGS_COMSTART_FIRST (syntax)
		   && SYNTAX_FLAGS_COMSTART_SECOND (prev_syntax)
562 563
		   && (comstyle
		       == SYNTAX_FLAGS_COMMENT_STYLE (prev_syntax, syntax))
564 565 566 567
		   && (SYNTAX_FLAGS_COMMENT_NESTED (prev_syntax)
		       || SYNTAX_FLAGS_COMMENT_NESTED (syntax)) == comnested);
      com2end = (SYNTAX_FLAGS_COMEND_FIRST (syntax)
		 && SYNTAX_FLAGS_COMEND_SECOND (prev_syntax));
568
      comstart = (com2start || code == Scomment);
569

570 571 572 573 574 575 576 577 578 579
      /* Nasty cases with overlapping 2-char comment markers:
	 - snmp-mode: -- c -- foo -- c --
	              --- c --
		      ------ c --
	 - c-mode:    *||*
		      |* *|* *|
		      |*| |* |*|
		      ///   */

      /* If a 2-char comment sequence partly overlaps with another,
580 581 582
	 we don't try to be clever.  E.g. |*| in C, or }% in modes that
	 have %..\n and %{..}%.  */
      if (from > stop && (com2end || comstart))
583
	{
584 585
	  EMACS_INT next = from, next_byte = from_byte;
	  int next_c, next_syntax;
586 587
	  DEC_BOTH (next, next_byte);
	  UPDATE_SYNTAX_TABLE_BACKWARD (next);
588
	  next_c = FETCH_CHAR_AS_MULTIBYTE (next_byte);
589
	  next_syntax = SYNTAX_WITH_FLAGS (next_c);
590
	  if (((comstart || comnested)
591 592 593 594
	       && SYNTAX_FLAGS_COMEND_SECOND (syntax)
	       && SYNTAX_FLAGS_COMEND_FIRST (next_syntax))
	      || ((com2end || comnested)
		  && SYNTAX_FLAGS_COMSTART_SECOND (syntax)
595 596
		  && (comstyle
		      == SYNTAX_FLAGS_COMMENT_STYLE (syntax, prev_syntax))
597 598 599
		  && SYNTAX_FLAGS_COMSTART_FIRST (next_syntax)))
	    goto lossage;
	  /* UPDATE_SYNTAX_TABLE_FORWARD (next + 1); */
600
	}
601 602 603 604 605 606 607 608 609 610 611 612 613 614 615

      if (com2start && comstart_pos == 0)
	/* We're looking at a comment starter.  But it might be a comment
	   ender as well (see snmp-mode).  The first time we see one, we
	   need to consider it as a comment starter,
	   and the subsequent times as a comment ender.  */
	com2end = 0;

      /* Turn a 2-char comment sequences into the appropriate syntax.  */
      if (com2end)
	code = Sendcomment;
      else if (com2start)
	code = Scomment;
      /* Ignore comment starters of a different style.  */
      else if (code == Scomment
616
	       && (comstyle != SYNTAX_FLAGS_COMMENT_STYLE (syntax, 0)
617
		   || SYNTAX_FLAGS_COMMENT_NESTED (syntax) != comnested))
618
	continue;
619

620 621
      /* Ignore escaped characters, except comment-enders.  */
      if (code != Sendcomment && char_quoted (from, from_byte))
622 623
	continue;

624
      switch (code)
625
	{
626 627 628 629 630 631 632 633 634 635 636 637 638 639
	case Sstring_fence:
	case Scomment_fence:
	  c = (code == Sstring_fence ? ST_STRING_STYLE : ST_COMMENT_STYLE);
	case Sstring:
	  /* Track parity of quotes.  */
	  if (string_style == -1)
	    /* Entering a string.  */
	    string_style = c;
	  else if (string_style == c)
	    /* Leaving the string.  */
	    string_style = -1;
	  else
	    /* If we have two kinds of string delimiters.
	       There's no way to grok this scanning backwards.  */
640
	    string_lossage = 1;
641
	  break;
Juanma Barranquero's avatar
Juanma Barranquero committed
642

643 644
	case Scomment:
	  /* We've already checked that it is the relevant comstyle.  */
645
	  if (string_style != -1 || comment_lossage || string_lossage)
646 647 648 649
	    /* There are odd string quotes involved, so let's be careful.
	       Test case in Pascal: " { " a { " } */
	    goto lossage;

650 651 652 653 654 655 656
	  if (!comnested)
	    {
	      /* Record best comment-starter so far.  */
	      comstart_pos = from;
	      comstart_byte = from_byte;
	    }
	  else if (--nesting <= 0)
657 658 659 660 661 662
	    /* nested comments have to be balanced, so we don't need to
	       keep looking for earlier ones.  We use here the same (slightly
	       incorrect) reasoning as below:  since it is followed by uniform
	       paired string quotes, this comment-start has to be outside of
	       strings, else the comment-end itself would be inside a string. */
	    goto done;
663 664
	  break;

665
	case Sendcomment:
666
	  if (SYNTAX_FLAGS_COMMENT_STYLE (syntax, 0) == comstyle
667
	      && ((com2end && SYNTAX_FLAGS_COMMENT_NESTED (prev_syntax))
668
		  || SYNTAX_FLAGS_COMMENT_NESTED (syntax)) == comnested)
669 670 671 672 673 674 675 676 677
	    /* This is the same style of comment ender as ours. */
	    {
	      if (comnested)
		nesting++;
	      else
		/* Anything before that can't count because it would match
		   this comment-ender rather than ours.  */
		from = stop;	/* Break out of the loop.  */
	    }
678 679 680 681 682 683 684 685 686
	  else if (comstart_pos != 0 || c != '\n')
	    /* We're mixing comment styles here, so we'd better be careful.
	       The (comstart_pos != 0 || c != '\n') check is not quite correct
	       (we should just always set comment_lossage), but removing it
	       would imply that any multiline comment in C would go through
	       lossage, which seems overkill.
	       The failure should only happen in the rare cases such as
	         { (* } *)   */
	    comment_lossage = 1;
687
	  break;
688

689 690 691 692 693 694 695 696 697 698 699
	case Sopen:
	  /* Assume a defun-start point is outside of strings.  */
	  if (open_paren_in_column_0_is_defun_start
	      && (from == stop
		  || (temp_byte = dec_bytepos (from_byte),
		      FETCH_CHAR (temp_byte) == '\n')))
	    {
	      defun_start = from;
	      defun_start_byte = from_byte;
	      from = stop;	/* Break out of the loop.  */
	    }
700
	  break;
701 702

	default:
703
	  break;
704
	}
705 706 707 708 709
    }

  if (comstart_pos == 0)
    {
      from = comment_end;
710
      from_byte = comment_end_byte;
711 712
      UPDATE_SYNTAX_TABLE_FORWARD (comment_end - 1);
    }
713 714 715
  /* If comstart_pos is set and we get here (ie. didn't jump to `lossage'
     or `done'), then we've found the beginning of the non-nested comment.  */
  else if (1)	/* !comnested */
716 717
    {
      from = comstart_pos;
718
      from_byte = comstart_byte;
719
      UPDATE_SYNTAX_TABLE_FORWARD (from - 1);
720 721 722
    }
  else
    {
723 724
      struct lisp_parse_state state;
    lossage:
725 726
      /* We had two kinds of string delimiters mixed up
	 together.  Decode this going forwards.
727
	 Scan fwd from a known safe place (beginning-of-defun)
728 729
	 to the one in question; this records where we
	 last passed a comment starter.  */
730 731 732 733 734 735
      /* If we did not already find the defun start, find it now.  */
      if (defun_start == 0)
	{
	  defun_start = find_defun_start (comment_end, comment_end_byte);
	  defun_start_byte = find_start_value_byte;
	}
736
      do
737
	{
738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759
	  scan_sexps_forward (&state,
			      defun_start, defun_start_byte,
			      comment_end, -10000, 0, Qnil, 0);
	  defun_start = comment_end;
	  if (state.incomment == (comnested ? 1 : -1)
	      && state.comstyle == comstyle)
	    from = state.comstr_start;
	  else
	    {
	      from = comment_end;
	      if (state.incomment)
		/* If comment_end is inside some other comment, maybe ours
		   is nested, so we need to try again from within the
		   surrounding comment.  Example: { a (* " *)  */
		{
		  /* FIXME: We should advance by one or two chars. */
		  defun_start = state.comstr_start + 2;
		  defun_start_byte = CHAR_TO_BYTE (defun_start);
		}
	    }
	} while (defun_start < comment_end);

760
      from_byte = CHAR_TO_BYTE (from);
761 762
      UPDATE_SYNTAX_TABLE_FORWARD (from - 1);
    }
Juanma Barranquero's avatar
Juanma Barranquero committed
763

764
 done:
765 766 767
  *charpos_ptr = from;
  *bytepos_ptr = from_byte;

768
  return (from == comment_end) ? -1 : from;
769 770
}

Richard M. Stallman's avatar
Richard M. Stallman committed
771
DEFUN ("syntax-table-p", Fsyntax_table_p, Ssyntax_table_p, 1, 1, 0,
772 773
       doc: /* Return t if OBJECT is a syntax table.
Currently, any char-table counts as a syntax table.  */)
Dan Nicolaescu's avatar
Dan Nicolaescu committed
774
  (Lisp_Object object)
Richard M. Stallman's avatar
Richard M. Stallman committed
775
{
776
  if (CHAR_TABLE_P (object)
777
      && EQ (XCHAR_TABLE (object)->purpose, Qsyntax_table))
Richard M. Stallman's avatar
Richard M. Stallman committed
778 779 780 781
    return Qt;
  return Qnil;
}

782
static void
783
check_syntax_table (Lisp_Object obj)
Richard M. Stallman's avatar
Richard M. Stallman committed
784
{
785 786
  CHECK_TYPE (CHAR_TABLE_P (obj) && EQ (XCHAR_TABLE (obj)->purpose, Qsyntax_table),
	      Qsyntax_table_p, obj);
Juanma Barranquero's avatar
Juanma Barranquero committed
787
}
Richard M. Stallman's avatar
Richard M. Stallman committed
788 789

DEFUN ("syntax-table", Fsyntax_table, Ssyntax_table, 0, 0, 0,
790 791
       doc: /* Return the current syntax table.
This is the one specified by the current buffer.  */)
Dan Nicolaescu's avatar
Dan Nicolaescu committed
792
  (void)
Richard M. Stallman's avatar
Richard M. Stallman committed
793
{
Tom Tromey's avatar
Tom Tromey committed
794
  return BVAR (current_buffer, syntax_table);
Richard M. Stallman's avatar
Richard M. Stallman committed
795 796 797 798
}

DEFUN ("standard-syntax-table", Fstandard_syntax_table,
   Sstandard_syntax_table, 0, 0, 0,
799 800
       doc: /* Return the standard syntax table.
This is the one used for new buffers.  */)
Dan Nicolaescu's avatar
Dan Nicolaescu committed
801
  (void)
Richard M. Stallman's avatar
Richard M. Stallman committed
802 803 804 805 806
{
  return Vstandard_syntax_table;
}

DEFUN ("copy-syntax-table", Fcopy_syntax_table, Scopy_syntax_table, 0, 1, 0,
807 808
       doc: /* Construct a new syntax table and return it.
It is a copy of the TABLE, which defaults to the standard syntax table.  */)
Dan Nicolaescu's avatar
Dan Nicolaescu committed
809
  (Lisp_Object table)
Richard M. Stallman's avatar
Richard M. Stallman committed
810
{
811 812
  Lisp_Object copy;

Jim Blandy's avatar
Jim Blandy committed
813
  if (!NILP (table))
814 815 816 817 818
    check_syntax_table (table);
  else
    table = Vstandard_syntax_table;

  copy = Fcopy_sequence (table);
819 820 821 822 823 824 825 826 827 828

  /* Only the standard syntax table should have a default element.
     Other syntax tables should inherit from parents instead.  */
  XCHAR_TABLE (copy)->defalt = Qnil;

  /* Copied syntax tables should all have parents.
     If we copied one with no parent, such as the standard syntax table,
     use the standard syntax table as the copy's parent.  */
  if (NILP (XCHAR_TABLE (copy)->parent))
    Fset_char_table_parent (copy, Vstandard_syntax_table);
829
  return copy;
Richard M. Stallman's avatar
Richard M. Stallman committed
830 831 832
}

DEFUN ("set-syntax-table", Fset_syntax_table, Sset_syntax_table, 1, 1, 0,
833 834
       doc: /* Select a new syntax table for the current buffer.
One argument, a syntax table.  */)
Dan Nicolaescu's avatar
Dan Nicolaescu committed
835
  (Lisp_Object table)
Richard M. Stallman's avatar
Richard M. Stallman committed
836
{
837
  int idx;
838
  check_syntax_table (table);
Tom Tromey's avatar
Tom Tromey committed
839
  BVAR (current_buffer, syntax_table) = table;
Richard M. Stallman's avatar
Richard M. Stallman committed
840
  /* Indicate that this buffer now has a specified syntax table.  */
Gerd Moellmann's avatar
Gerd Moellmann committed
841 842
  idx = PER_BUFFER_VAR_IDX (syntax_table);
  SET_PER_BUFFER_VALUE_P (current_buffer, idx, 1);
Richard M. Stallman's avatar
Richard M. Stallman committed
843 844 845 846 847
  return table;
}

/* Convert a letter which signifies a syntax code
 into the code it signifies.
848
 This is used by modify-syntax-entry, and other things.  */
Richard M. Stallman's avatar
Richard M. Stallman committed
849 850 851 852 853 854

unsigned char syntax_spec_code[0400] =
  { 0377, 0377, 0377, 0377, 0377, 0377, 0377, 0377,
    0377, 0377, 0377, 0377, 0377, 0377, 0377, 0377,
    0377, 0377, 0377, 0377, 0377, 0377, 0377, 0377,
    0377, 0377, 0377, 0377, 0377, 0377, 0377, 0377,
855
    (char) Swhitespace, (char) Scomment_fence, (char) Sstring, 0377,
Richard M. Stallman's avatar
Richard M. Stallman committed
856 857 858 859 860 861
        (char) Smath, 0377, 0377, (char) Squote,
    (char) Sopen, (char) Sclose, 0377, 0377,
	0377, (char) Swhitespace, (char) Spunct, (char) Scharquote,
    0377, 0377, 0377, 0377, 0377, 0377, 0377, 0377,
    0377, 0377, 0377, 0377,
	(char) Scomment, 0377, (char) Sendcomment, 0377,
862
    (char) Sinherit, 0377, 0377, 0377, 0377, 0377, 0377, 0377,   /* @, A ... */
Richard M. Stallman's avatar
Richard M. Stallman committed
863 864 865 866 867 868
    0377, 0377, 0377, 0377, 0377, 0377, 0377, 0377,
    0377, 0377, 0377, 0377, 0377, 0377, 0377, (char) Sword,
    0377, 0377, 0377, 0377, (char) Sescape, 0377, 0377, (char) Ssymbol,
    0377, 0377, 0377, 0377, 0377, 0377, 0377, 0377,   /* `, a, ... */
    0377, 0377, 0377, 0377, 0377, 0377, 0377, 0377,
    0377, 0377, 0377, 0377, 0377, 0377, 0377, (char) Sword,
869
    0377, 0377, 0377, 0377, (char) Sstring_fence, 0377, 0377, 0377
Richard M. Stallman's avatar
Richard M. Stallman committed
870 871
  };

872
/* Indexed by syntax code, give the letter that describes it.  */
Richard M. Stallman's avatar
Richard M. Stallman committed
873

874
char syntax_code_spec[16] =
Richard M. Stallman's avatar
Richard M. Stallman committed
875
  {
876 877
    ' ', '.', 'w', '_', '(', ')', '\'', '\"', '$', '\\', '/', '<', '>', '@',
    '!', '|'
Richard M. Stallman's avatar
Richard M. Stallman committed
878
  };
Karl Heuer's avatar
Karl Heuer committed
879 880 881 882 883 884 885 886

/* Indexed by syntax code, give the object (cons of syntax code and
   nil) to be stored in syntax table.  Since these objects can be
   shared among syntax tables, we generate them in advance.  By
   sharing objects, the function `describe-syntax' can give a more
   compact listing.  */
static Lisp_Object Vsyntax_code_object;

Richard M. Stallman's avatar
Richard M. Stallman committed
887 888

DEFUN ("char-syntax", Fchar_syntax, Schar_syntax, 1, 1, 0,
889
       doc: /* Return the syntax code of CHARACTER, described by a character.
890 891
For example, if CHARACTER is a word constituent, the
character `w' (119) is returned.
892 893
The characters that correspond to various syntax codes
are listed in the documentation of `modify-syntax-entry'.  */)
Dan Nicolaescu's avatar
Dan Nicolaescu committed
894
  (Lisp_Object character)
Richard M. Stallman's avatar
Richard M. Stallman committed
895
{
896
  int char_int;
897
  CHECK_CHARACTER (character);
898
  char_int = XINT (character);
899
  SETUP_BUFFER_SYNTAX_TABLE ();
900
  return make_number (syntax_code_spec[(int) SYNTAX (char_int)]);
901 902 903
}

DEFUN ("matching-paren", Fmatching_paren, Smatching_paren, 1, 1, 0,
904
       doc: /* Return the matching parenthesis of CHARACTER, or nil if none.  */)
Dan Nicolaescu's avatar
Dan Nicolaescu committed
905
  (Lisp_Object character)
906
{
907
  int char_int, code;
908
  CHECK_NUMBER (character);
909
  char_int = XINT (character);
910
  SETUP_BUFFER_SYNTAX_TABLE ();
911
  code = SYNTAX (char_int);
912
  if (code == Sopen || code == Sclose)
913
    return SYNTAX_MATCH (char_int);
914
  return Qnil;
Richard M. Stallman's avatar
Richard M. Stallman committed
915 916
}

917
DEFUN ("string-to-syntax", Fstring_to_syntax, Sstring_to_syntax, 1, 1, 0,
918 919 920
       doc: /* Convert a syntax specification STRING into syntax cell form.
STRING should be a string as it is allowed as argument of
`modify-syntax-entry'.  Value is the equivalent cons cell
921
\(CODE . MATCHING-CHAR) that can be used as value of a `syntax-table'
922
text property.  */)
Dan Nicolaescu's avatar
Dan Nicolaescu committed
923
  (Lisp_Object string)
Richard M. Stallman's avatar
Richard M. Stallman committed
924
{
925
  register const unsigned char *p;
Richard M. Stallman's avatar
Richard M. Stallman committed
926
  register enum syntaxcode code;
927
  int val;
928
  Lisp_Object match;
Richard M. Stallman's avatar
Richard M. Stallman committed
929

930
  CHECK_STRING (string);
Richard M. Stallman's avatar
Richard M. Stallman committed
931

932
  p = SDATA (string);
Richard M. Stallman's avatar
Richard M. Stallman committed
933 934
  code = (enum syntaxcode) syntax_spec_code[*p++];
  if (((int) code & 0377) == 0377)
935
    error ("Invalid syntax description letter: %c", p[-1]);
Richard M. Stallman's avatar
Richard M. Stallman committed
936

937
  if (code == Sinherit)
938
    return Qnil;
939 940

  if (*p)
941
    {
Karl Heuer's avatar
Karl Heuer committed
942
      int len;
943
      int character = STRING_CHAR_AND_LENGTH (p, len);
Karl Heuer's avatar
Karl Heuer committed
944
      XSETINT (match, character);
945 946
      if (XFASTINT (match) == ' ')
	match = Qnil;
Karl Heuer's avatar
Karl Heuer committed
947
      p += len;
948 949
    }
  else
950
    match = Qnil;
Richard M. Stallman's avatar
Richard M. Stallman committed
951

952
  val = (int) code;
Richard M. Stallman's avatar
Richard M. Stallman committed
953 954 955 956
  while (*p)
    switch (*p++)
      {
      case '1':
957
	val |= 1 << 16;
Richard M. Stallman's avatar
Richard M. Stallman committed
958 959 960
	break;

      case '2':