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>
Richard M. Stallman's avatar
Richard M. Stallman committed
22
#include <ctype.h>
23
#include <setjmp.h>
Richard M. Stallman's avatar
Richard M. Stallman committed
24 25 26
#include "lisp.h"
#include "commands.h"
#include "buffer.h"
27
#include "character.h"
Stefan Monnier's avatar
Stefan Monnier committed
28
#include "keymap.h"
Richard M. Stallman's avatar
Richard M. Stallman committed
29
#include "regex.h"
30 31 32 33

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

Richard M. Stallman's avatar
Richard M. Stallman committed
34
#include "syntax.h"
35
#include "intervals.h"
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
#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)))
90 91 92 93 94 95 96

/* 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
97

98
Lisp_Object Qsyntax_table_p, Qsyntax_table, Qscan_error;
Richard M. Stallman's avatar
Richard M. Stallman committed
99

100 101 102 103 104
/* 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;

105 106 107 108
/* This is the internal form of the parse state used in parse-partial-sexp.  */

struct lisp_parse_state
  {
109 110 111 112 113 114 115 116 117 118 119 120 121 122
    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).  */
123 124
  };

125 126 127
/* 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.
128
   find_start_value_byte is the corresponding byte position.
129 130 131 132
   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.  */

133 134 135
static EMACS_INT find_start_pos;
static EMACS_INT find_start_value;
static EMACS_INT find_start_value_byte;
136
static struct buffer *find_start_buffer;
137
static EMACS_INT find_start_begv;
138
static int find_start_modiff;
139 140


141 142 143 144 145 146 147
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);
148

149 150 151 152 153
/* Whether the syntax of the character C has the prefix flag set.  */
int syntax_prefix_flag_p (int c)
{
  return SYNTAX_PREFIX (c);
}
154 155 156 157 158 159

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.  */

160 161
/* Update gl_state to an appropriate interval which contains CHARPOS.  The
   sign of COUNT give the relative position of CHARPOS wrt the previously
162
   valid interval.  If INIT, only [be]_property fields of gl_state are
163
   valid at start, the rest is filled basing on OBJECT.
164

165
   `gl_state.*_i' are the intervals, and CHARPOS is further in the search
166 167
   direction than the intervals - or in an interval.  We update the
   current syntax-table basing on the property of this interval, and
168
   update the interval to start further than CHARPOS - or be
169
   NULL_INTERVAL.  We also update lim_property to be the next value of
170
   charpos to call this subroutine again - or be before/after the
171 172 173
   start/end of OBJECT.  */

void
174 175
update_syntax_table (EMACS_INT charpos, int count, int init,
		     Lisp_Object object)
176 177
{
  Lisp_Object tmp_table;
178
  int cnt = 0, invalidate = 1;
179
  INTERVAL i;
180 181 182

  if (init)
    {
183
      gl_state.old_prop = Qnil;
184 185
      gl_state.start = gl_state.b_property;
      gl_state.stop = gl_state.e_property;
186 187
      i = interval_of (charpos, object);
      gl_state.backward_i = gl_state.forward_i = i;
188 189 190
      invalidate = 0;
      if (NULL_INTERVAL_P (i))
	return;
191
      /* interval_of updates only ->position of the return value, so
192
	 update the parents manually to speed up update_interval.  */
193
      while (!NULL_PARENT (i))
194 195
	{
	  if (AM_RIGHT_CHILD (i))
196
	    INTERVAL_PARENT (i)->position = i->position
197
	      - LEFT_TOTAL_LENGTH (i) + TOTAL_LENGTH (i) /* right end */
198 199
	      - TOTAL_LENGTH (INTERVAL_PARENT (i))
	      + LEFT_TOTAL_LENGTH (INTERVAL_PARENT (i));
200
	  else
201
	    INTERVAL_PARENT (i)->position = i->position - LEFT_TOTAL_LENGTH (i)
202
	      + TOTAL_LENGTH (i);
203
	  i = INTERVAL_PARENT (i);
204 205
	}
      i = gl_state.forward_i;
206
      gl_state.b_property = i->position - gl_state.offset;
207
      gl_state.e_property = INTERVAL_LAST_POS (i) - gl_state.offset;
208 209
      goto update;
    }
210
  i = count > 0 ? gl_state.forward_i : gl_state.backward_i;
211

212
  /* We are guaranteed to be called with CHARPOS either in i,
213
     or further off.  */
214 215
  if (NULL_INTERVAL_P (i))
    error ("Error in syntax_table logic for to-the-end intervals");
216
  else if (charpos < i->position)		/* Move left.  */
217 218
    {
      if (count > 0)
219
	error ("Error in syntax_table logic for intervals <-");
220
      /* Update the interval.  */
221
      i = update_interval (i, charpos);
222
      if (INTERVAL_LAST_POS (i) != gl_state.b_property)
223 224 225
	{
	  invalidate = 0;
	  gl_state.forward_i = i;
226
	  gl_state.e_property = INTERVAL_LAST_POS (i) - gl_state.offset;
227
	}
228
    }
229
  else if (charpos >= INTERVAL_LAST_POS (i)) /* Move right.  */
230 231
    {
      if (count < 0)
232
	error ("Error in syntax_table logic for intervals ->");
233
      /* Update the interval.  */
234
      i = update_interval (i, charpos);
235
      if (i->position != gl_state.e_property)
236 237 238
	{
	  invalidate = 0;
	  gl_state.backward_i = i;
239
	  gl_state.b_property = i->position - gl_state.offset;
240 241 242 243 244 245 246 247
	}
    }

  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
248

249 250 251
  if (invalidate)		/* Did not get to adjacent interval.  */
    {				/* with the same table => */
				/* invalidate the old range.  */
252 253 254
      if (count > 0)
	{
	  gl_state.backward_i = i;
255 256 257
	  gl_state.b_property = i->position - gl_state.offset;
	}
      else
258
	{
259
	  gl_state.forward_i = i;
260
	  gl_state.e_property = INTERVAL_LAST_POS (i) - gl_state.offset;
261 262
	}
    }
263

264
  if (!EQ (tmp_table, gl_state.old_prop))
265
    {
266 267 268 269 270
      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
271
	}
272 273 274 275 276
      else if (CONSP (tmp_table))
	{
	  gl_state.use_global = 1;
	  gl_state.global_code = tmp_table;
	}
Juanma Barranquero's avatar
Juanma Barranquero committed
277
      else
278 279
	{
	  gl_state.use_global = 0;
Tom Tromey's avatar
Tom Tromey committed
280
	  gl_state.current_syntax_table = BVAR (current_buffer, syntax_table);
281
	}
282 283 284 285 286 287 288
    }

  while (!NULL_INTERVAL_P (i))
    {
      if (cnt && !EQ (tmp_table, textget (i->plist, Qsyntax_table)))
	{
	  if (count > 0)
289 290 291 292 293 294
	    {
	      gl_state.e_property = i->position - gl_state.offset;
	      gl_state.forward_i = i;
	    }
	  else
	    {
295 296
	      gl_state.b_property
		= i->position + LENGTH (i) - gl_state.offset;
297 298 299
	      gl_state.backward_i = i;
	    }
	  return;
300
	}
Juanma Barranquero's avatar
Juanma Barranquero committed
301
      else if (cnt == INTERVALS_AT_ONCE)
302 303
	{
	  if (count > 0)
304
	    {
305 306 307 308 309 310
	      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);
311 312 313 314 315 316 317 318
	      gl_state.forward_i = i;
	    }
	  else
	    {
	      gl_state.b_property = i->position - gl_state.offset;
	      gl_state.backward_i = i;
	    }
	  return;
319 320 321 322
	}
      cnt++;
      i = count > 0 ? next_interval (i) : previous_interval (i);
    }
323 324 325 326 327
  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;
328 329
}

330 331 332
/* 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. */
333 334

static int
335
char_quoted (EMACS_INT charpos, EMACS_INT bytepos)
336 337
{
  register enum syntaxcode code;
338
  register EMACS_INT beg = BEGV;
339
  register int quoted = 0;
340
  EMACS_INT orig = charpos;
341

342
  while (charpos > beg)
343
    {
344
      int c;
345
      DEC_BOTH (charpos, bytepos);
346

347
      UPDATE_SYNTAX_TABLE_BACKWARD (charpos);
348
      c = FETCH_CHAR_AS_MULTIBYTE (bytepos);
349
      code = SYNTAX (c);
350 351 352 353
      if (! (code == Scharquote || code == Sescape))
	break;

      quoted = !quoted;
354
    }
355 356

  UPDATE_SYNTAX_TABLE (orig);
357 358
  return quoted;
}
359 360 361 362

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

363
static INLINE EMACS_INT
364
dec_bytepos (EMACS_INT bytepos)
365
{
Tom Tromey's avatar
Tom Tromey committed
366
  if (NILP (BVAR (current_buffer, enable_multibyte_characters)))
367 368
    return bytepos - 1;

369 370 371
  DEC_POS (bytepos);
  return bytepos;
}
372

Juanma Barranquero's avatar
Juanma Barranquero committed
373
/* Return a defun-start position before POS and not too far before.
Richard M. Stallman's avatar
Richard M. Stallman committed
374 375 376
   It should be the last one before POS, or nearly the last.

   When open_paren_in_column_0_is_defun_start is nonzero,
377
   only the beginning of the buffer is treated as a defun-start.
Richard M. Stallman's avatar
Richard M. Stallman committed
378 379 380 381

   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.
382 383 384 385

   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.  */
386

387
static EMACS_INT
388
find_defun_start (EMACS_INT pos, EMACS_INT pos_byte)
389
{
390
  EMACS_INT opoint = PT, opoint_byte = PT_BYTE;
391

392 393 394 395 396 397
  if (!open_paren_in_column_0_is_defun_start)
    {
      find_start_value_byte = BEGV_BYTE;
      return BEGV;
    }

398 399 400 401 402 403 404 405 406 407 408 409
  /* 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.  */
410
  scan_newline (pos, pos_byte, BEGV, BEGV_BYTE, -1, 1);
411

412 413 414
  /* We optimize syntax-table lookup for rare updates.  Thus we accept
     only those `^\s(' which are good in global _and_ text-property
     syntax-tables.  */
415
  SETUP_BUFFER_SYNTAX_TABLE ();
416
  while (PT > BEGV)
417
    {
418 419
      int c;

420 421
      /* Open-paren at start of line means we may have found our
	 defun-start.  */
422
      c = FETCH_CHAR_AS_MULTIBYTE (PT_BYTE);
423
      if (SYNTAX (c) == Sopen)
424
	{
425
	  SETUP_SYNTAX_TABLE (PT + 1, -1);	/* Try again... */
426
	  c = FETCH_CHAR_AS_MULTIBYTE (PT_BYTE);
427
	  if (SYNTAX (c) == Sopen)
428 429
	    break;
	  /* Now fallback to the default value.  */
430
	  SETUP_BUFFER_SYNTAX_TABLE ();
431
	}
432 433
      /* Move to beg of previous line.  */
      scan_newline (PT, PT_BYTE, BEGV, BEGV_BYTE, -2, 1);
434 435 436
    }

  /* Record what we found, for the next try.  */
437 438
  find_start_value = PT;
  find_start_value_byte = PT_BYTE;
439 440 441 442 443
  find_start_buffer = current_buffer;
  find_start_modiff = MODIFF;
  find_start_begv = BEGV;
  find_start_pos = pos;

444 445
  TEMP_SET_PT_BOTH (opoint, opoint_byte);

446 447 448
  return find_start_value;
}

449 450 451
/* Return the SYNTAX_COMEND_FIRST of the character before POS, POS_BYTE.  */

static int
452
prev_char_comend_first (EMACS_INT pos, EMACS_INT pos_byte)
453 454 455 456 457 458 459 460 461 462 463 464 465
{
  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.  */

466 467 468 469 470
/* static int
 * prev_char_comstart_first (pos, pos_byte)
 *      int pos, pos_byte;
 * {
 *   int c, val;
Juanma Barranquero's avatar
Juanma Barranquero committed
471
 *
472 473 474 475 476 477 478
 *   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;
 * } */
479

480 481 482 483 484 485 486 487 488
/* 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.
489 490 491

   Global syntax data remains valid for backward search starting at
   the returned value (or at FROM, if the search was not successful).  */
492 493

static int
494
back_comment (EMACS_INT from, EMACS_INT from_byte, EMACS_INT stop, int comnested, int comstyle, EMACS_INT *charpos_ptr, EMACS_INT *bytepos_ptr)
495 496 497 498 499 500 501 502 503 504
{
  /* 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.  */
505
  int string_style = -1;	/* Presumed outside of any string. */
506
  int string_lossage = 0;
507
  /* Not a real lossage: indicates that we have passed a matching comment
Juanma Barranquero's avatar
Juanma Barranquero committed
508
     starter plus a non-matching comment-ender, meaning that any matching
509 510 511 512
     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;
513 514 515
  EMACS_INT comment_end = from;
  EMACS_INT comment_end_byte = from_byte;
  EMACS_INT comstart_pos = 0;
516
  EMACS_INT comstart_byte IF_LINT (= 0);
517 518
  /* Place where the containing defun starts,
     or 0 if we didn't come across it yet.  */
519 520
  EMACS_INT defun_start = 0;
  EMACS_INT defun_start_byte = 0;
521
  register enum syntaxcode code;
522
  int nesting = 1;		/* current comment nesting */
523
  int c;
524 525 526 527 528
  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.  */
529 530 531 532 533

  /* At beginning of range to scan, we're outside of strings;
     that determines quote parity to the comment-end.  */
  while (from != stop)
    {
534 535
      EMACS_INT temp_byte;
      int prev_syntax, com2start, com2end;
536
      int comstart;
537

538
      /* Move back and examine a character.  */
539
      DEC_BOTH (from, from_byte);
540 541
      UPDATE_SYNTAX_TABLE_BACKWARD (from);

542
      prev_syntax = syntax;
543
      c = FETCH_CHAR_AS_MULTIBYTE (from_byte);
544
      syntax = SYNTAX_WITH_FLAGS (c);
545 546
      code = SYNTAX (c);

547 548 549
      /* Check for 2-char comment markers.  */
      com2start = (SYNTAX_FLAGS_COMSTART_FIRST (syntax)
		   && SYNTAX_FLAGS_COMSTART_SECOND (prev_syntax)
550 551
		   && (comstyle
		       == SYNTAX_FLAGS_COMMENT_STYLE (prev_syntax, syntax))
552 553 554 555
		   && (SYNTAX_FLAGS_COMMENT_NESTED (prev_syntax)
		       || SYNTAX_FLAGS_COMMENT_NESTED (syntax)) == comnested);
      com2end = (SYNTAX_FLAGS_COMEND_FIRST (syntax)
		 && SYNTAX_FLAGS_COMEND_SECOND (prev_syntax));
556
      comstart = (com2start || code == Scomment);
557

558 559 560 561 562 563 564 565 566 567
      /* 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,
568 569 570
	 we don't try to be clever.  E.g. |*| in C, or }% in modes that
	 have %..\n and %{..}%.  */
      if (from > stop && (com2end || comstart))
571
	{
572 573
	  EMACS_INT next = from, next_byte = from_byte;
	  int next_c, next_syntax;
574 575
	  DEC_BOTH (next, next_byte);
	  UPDATE_SYNTAX_TABLE_BACKWARD (next);
576
	  next_c = FETCH_CHAR_AS_MULTIBYTE (next_byte);
577
	  next_syntax = SYNTAX_WITH_FLAGS (next_c);
578
	  if (((comstart || comnested)
579 580 581 582
	       && SYNTAX_FLAGS_COMEND_SECOND (syntax)
	       && SYNTAX_FLAGS_COMEND_FIRST (next_syntax))
	      || ((com2end || comnested)
		  && SYNTAX_FLAGS_COMSTART_SECOND (syntax)
583 584
		  && (comstyle
		      == SYNTAX_FLAGS_COMMENT_STYLE (syntax, prev_syntax))
585 586 587
		  && SYNTAX_FLAGS_COMSTART_FIRST (next_syntax)))
	    goto lossage;
	  /* UPDATE_SYNTAX_TABLE_FORWARD (next + 1); */
588
	}
589 590 591 592 593 594 595 596 597 598 599 600 601 602 603

      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
604
	       && (comstyle != SYNTAX_FLAGS_COMMENT_STYLE (syntax, 0)
605
		   || SYNTAX_FLAGS_COMMENT_NESTED (syntax) != comnested))
606
	continue;
607

608 609
      /* Ignore escaped characters, except comment-enders.  */
      if (code != Sendcomment && char_quoted (from, from_byte))
610 611
	continue;

612
      switch (code)
613
	{
614 615 616 617 618 619 620 621 622 623 624 625 626 627
	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.  */
628
	    string_lossage = 1;
629
	  break;
Juanma Barranquero's avatar
Juanma Barranquero committed
630

631 632
	case Scomment:
	  /* We've already checked that it is the relevant comstyle.  */
633
	  if (string_style != -1 || comment_lossage || string_lossage)
634 635 636 637
	    /* There are odd string quotes involved, so let's be careful.
	       Test case in Pascal: " { " a { " } */
	    goto lossage;

638 639 640 641 642 643 644
	  if (!comnested)
	    {
	      /* Record best comment-starter so far.  */
	      comstart_pos = from;
	      comstart_byte = from_byte;
	    }
	  else if (--nesting <= 0)
645 646 647 648 649 650
	    /* 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;
651 652
	  break;

653
	case Sendcomment:
654
	  if (SYNTAX_FLAGS_COMMENT_STYLE (syntax, 0) == comstyle
655
	      && ((com2end && SYNTAX_FLAGS_COMMENT_NESTED (prev_syntax))
656
		  || SYNTAX_FLAGS_COMMENT_NESTED (syntax)) == comnested)
657 658 659 660 661 662 663 664 665
	    /* 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.  */
	    }
666 667 668 669 670 671 672 673 674
	  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;
675
	  break;
676

677 678 679 680 681 682 683 684 685 686 687
	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.  */
	    }
688
	  break;
689 690

	default:
691
	  break;
692
	}
693 694 695 696 697
    }

  if (comstart_pos == 0)
    {
      from = comment_end;
698
      from_byte = comment_end_byte;
699 700
      UPDATE_SYNTAX_TABLE_FORWARD (comment_end - 1);
    }
701 702 703
  /* 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 */
704 705
    {
      from = comstart_pos;
706
      from_byte = comstart_byte;
707
      UPDATE_SYNTAX_TABLE_FORWARD (from - 1);
708 709 710
    }
  else
    {
711 712
      struct lisp_parse_state state;
    lossage:
713 714
      /* We had two kinds of string delimiters mixed up
	 together.  Decode this going forwards.
715
	 Scan fwd from a known safe place (beginning-of-defun)
716 717
	 to the one in question; this records where we
	 last passed a comment starter.  */
718 719 720 721 722 723
      /* 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;
	}
724
      do
725
	{
726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747
	  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);

748
      from_byte = CHAR_TO_BYTE (from);
749 750
      UPDATE_SYNTAX_TABLE_FORWARD (from - 1);
    }
Juanma Barranquero's avatar
Juanma Barranquero committed
751

752
 done:
753 754 755
  *charpos_ptr = from;
  *bytepos_ptr = from_byte;

756
  return (from == comment_end) ? -1 : from;
757 758
}

Richard M. Stallman's avatar
Richard M. Stallman committed
759
DEFUN ("syntax-table-p", Fsyntax_table_p, Ssyntax_table_p, 1, 1, 0,
760 761
       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
762
  (Lisp_Object object)
Richard M. Stallman's avatar
Richard M. Stallman committed
763
{
764
  if (CHAR_TABLE_P (object)
765
      && EQ (XCHAR_TABLE (object)->purpose, Qsyntax_table))
Richard M. Stallman's avatar
Richard M. Stallman committed
766 767 768 769
    return Qt;
  return Qnil;
}

770
static void
771
check_syntax_table (Lisp_Object obj)
Richard M. Stallman's avatar
Richard M. Stallman committed
772
{
773 774
  CHECK_TYPE (CHAR_TABLE_P (obj) && EQ (XCHAR_TABLE (obj)->purpose, Qsyntax_table),
	      Qsyntax_table_p, obj);
Juanma Barranquero's avatar
Juanma Barranquero committed
775
}
Richard M. Stallman's avatar
Richard M. Stallman committed
776 777

DEFUN ("syntax-table", Fsyntax_table, Ssyntax_table, 0, 0, 0,
778 779
       doc: /* Return the current syntax table.
This is the one specified by the current buffer.  */)
Dan Nicolaescu's avatar
Dan Nicolaescu committed
780
  (void)
Richard M. Stallman's avatar
Richard M. Stallman committed
781
{
Tom Tromey's avatar
Tom Tromey committed
782
  return BVAR (current_buffer, syntax_table);
Richard M. Stallman's avatar
Richard M. Stallman committed
783 784 785 786
}

DEFUN ("standard-syntax-table", Fstandard_syntax_table,
   Sstandard_syntax_table, 0, 0, 0,
787 788
       doc: /* Return the standard syntax table.
This is the one used for new buffers.  */)
Dan Nicolaescu's avatar
Dan Nicolaescu committed
789
  (void)
Richard M. Stallman's avatar
Richard M. Stallman committed
790 791 792 793 794
{
  return Vstandard_syntax_table;
}

DEFUN ("copy-syntax-table", Fcopy_syntax_table, Scopy_syntax_table, 0, 1, 0,
795 796
       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
797
  (Lisp_Object table)
Richard M. Stallman's avatar
Richard M. Stallman committed
798
{
799 800
  Lisp_Object copy;

Jim Blandy's avatar
Jim Blandy committed
801
  if (!NILP (table))
802 803 804 805 806
    check_syntax_table (table);
  else
    table = Vstandard_syntax_table;

  copy = Fcopy_sequence (table);
807 808 809 810 811 812 813 814 815 816

  /* 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);
817
  return copy;
Richard M. Stallman's avatar
Richard M. Stallman committed
818 819 820
}

DEFUN ("set-syntax-table", Fset_syntax_table, Sset_syntax_table, 1, 1, 0,
821 822
       doc: /* Select a new syntax table for the current buffer.
One argument, a syntax table.  */)
Dan Nicolaescu's avatar
Dan Nicolaescu committed
823
  (Lisp_Object table)
Richard M. Stallman's avatar
Richard M. Stallman committed
824
{
825
  int idx;
826
  check_syntax_table (table);
Tom Tromey's avatar
Tom Tromey committed
827
  BVAR (current_buffer, syntax_table) = table;
Richard M. Stallman's avatar
Richard M. Stallman committed
828
  /* Indicate that this buffer now has a specified syntax table.  */
Gerd Moellmann's avatar
Gerd Moellmann committed
829 830
  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
831 832 833 834 835
  return table;
}

/* Convert a letter which signifies a syntax code
 into the code it signifies.
836
 This is used by modify-syntax-entry, and other things.  */
Richard M. Stallman's avatar
Richard M. Stallman committed
837 838 839 840 841 842

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,
843
    (char) Swhitespace, (char) Scomment_fence, (char) Sstring, 0377,
Richard M. Stallman's avatar
Richard M. Stallman committed
844 845 846 847 848 849
        (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,
850
    (char) Sinherit, 0377, 0377, 0377, 0377, 0377, 0377, 0377,   /* @, A ... */
Richard M. Stallman's avatar
Richard M. Stallman committed
851 852 853 854 855 856
    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,
857
    0377, 0377, 0377, 0377, (char) Sstring_fence, 0377, 0377, 0377
Richard M. Stallman's avatar
Richard M. Stallman committed
858 859
  };

860
/* Indexed by syntax code, give the letter that describes it.  */
Richard M. Stallman's avatar
Richard M. Stallman committed
861

862
char syntax_code_spec[16] =
Richard M. Stallman's avatar
Richard M. Stallman committed
863
  {
864 865
    ' ', '.', 'w', '_', '(', ')', '\'', '\"', '$', '\\', '/', '<', '>', '@',
    '!', '|'
Richard M. Stallman's avatar
Richard M. Stallman committed
866
  };
Karl Heuer's avatar
Karl Heuer committed
867 868 869 870 871 872 873 874

/* 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
875 876

DEFUN ("char-syntax", Fchar_syntax, Schar_syntax, 1, 1, 0,
877
       doc: /* Return the syntax code of CHARACTER, described by a character.
878 879
For example, if CHARACTER is a word constituent, the
character `w' (119) is returned.
880 881
The characters that correspond to various syntax codes
are listed in the documentation of `modify-syntax-entry'.  */)
Dan Nicolaescu's avatar
Dan Nicolaescu committed
882
  (Lisp_Object character)
Richard M. Stallman's avatar
Richard M. Stallman committed
883
{
884
  int char_int;
885
  CHECK_CHARACTER (character);
886
  char_int = XINT (character);
887
  SETUP_BUFFER_SYNTAX_TABLE ();
888
  return make_number (syntax_code_spec[(int) SYNTAX (char_int)]);
889 890 891
}

DEFUN ("matching-paren", Fmatching_paren, Smatching_paren, 1, 1, 0,
892
       doc: /* Return the matching parenthesis of CHARACTER, or nil if none.  */)
Dan Nicolaescu's avatar
Dan Nicolaescu committed
893
  (Lisp_Object character)
894
{
895
  int char_int, code;
896
  CHECK_NUMBER (character);
897
  char_int = XINT (character);
898
  SETUP_BUFFER_SYNTAX_TABLE ();
899
  code = SYNTAX (char_int);
900
  if (code == Sopen || code == Sclose)
901
    return SYNTAX_MATCH (char_int);
902
  return Qnil;
Richard M. Stallman's avatar
Richard M. Stallman committed
903 904
}

905
DEFUN ("string-to-syntax", Fstring_to_syntax, Sstring_to_syntax, 1, 1, 0,
906 907 908
       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
909
\(CODE . MATCHING-CHAR) that can be used as value of a `syntax-table'
910
text property.  */)
Dan Nicolaescu's avatar
Dan Nicolaescu committed
911
  (Lisp_Object string)
Richard M. Stallman's avatar
Richard M. Stallman committed
912
{
913
  register const unsigned char *p;
Richard M. Stallman's avatar
Richard M. Stallman committed
914
  register enum syntaxcode code;
915
  int val;
916
  Lisp_Object match;
Richard M. Stallman's avatar
Richard M. Stallman committed
917

918
  CHECK_STRING (string);
Richard M. Stallman's avatar
Richard M. Stallman committed
919

920
  p = SDATA (string);
Richard M. Stallman's avatar
Richard M. Stallman committed
921 922
  code = (enum syntaxcode) syntax_spec_code[*p++];
  if (((int) code & 0377) == 0377)
923
    error ("Invalid syntax description letter: %c", p[-1]);
Richard M. Stallman's avatar
Richard M. Stallman committed
924

925
  if (code == Sinherit)
926
    return Qnil;
927 928

  if (*p)
929
    {
Karl Heuer's avatar
Karl Heuer committed
930
      int len;
931
      int character = STRING_CHAR_AND_LENGTH (p, len);
Karl Heuer's avatar
Karl Heuer committed
932
      XSETINT (match, character);
933 934
      if (XFASTINT (match) == ' ')
	match = Qnil;
Karl Heuer's avatar
Karl Heuer committed
935
      p += len;
936 937
    }
  else
938
    match = Qnil;
Richard M. Stallman's avatar
Richard M. Stallman committed
939

940
  val = (int) code;
Richard M. Stallman's avatar
Richard M. Stallman committed
941 942 943 944
  while (*p)
    switch (*p++)
      {
      case '1':
945
	val |= 1 << 16;
Richard M. Stallman's avatar
Richard M. Stallman committed
946 947 948
	break;

      case '2':
949
	val |= 1 << 17;
Richard M. Stallman's avatar
Richard M. Stallman committed
950 951 952
	break;

      case '3':
953
	val |= 1 << 18;
Richard M. Stallman's avatar
Richard M. Stallman committed
954 955 956
	break;

      case '4':
957
	val |= 1 << 19;
Richard M. Stallman's avatar
Richard M. Stallman committed
958 959 960
	break;

      case 'p':
961
	val |= 1 << 20;
Richard M. Stallman's avatar
Richard M. Stallman committed
962
	break;
963 964

      case 'b':
965
	val |= 1 << 21;
Richard M. Stallman's avatar