bidi.c 55.5 KB
Newer Older
Eli Zaretskii's avatar
Eli Zaretskii committed
1
/* Low-level bidirectional buffer-scanning functions for GNU Emacs.
2 3
   Copyright (C) 2000, 2001, 2004, 2005, 2009, 2010
   Free Software Foundation, Inc.
Eli Zaretskii's avatar
Eli Zaretskii committed
4 5 6

This file is part of GNU Emacs.

Eli Zaretskii's avatar
Eli Zaretskii committed
7
GNU Emacs is free software: you can redistribute it and/or modify
Eli Zaretskii's avatar
Eli Zaretskii committed
8
it under the terms of the GNU General Public License as published by
Eli Zaretskii's avatar
Eli Zaretskii committed
9 10
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
Eli Zaretskii's avatar
Eli Zaretskii 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
Eli Zaretskii's avatar
Eli Zaretskii committed
18
along with GNU Emacs.  If not, see <http://www.gnu.org/licenses/>.  */
Eli Zaretskii's avatar
Eli Zaretskii committed
19

20 21 22
/* Written by Eli Zaretskii <eliz@gnu.org>.

   A sequential implementation of the Unicode Bidirectional algorithm,
Eli Zaretskii's avatar
Eli Zaretskii committed
23 24 25
   as per UAX#9, a part of the Unicode Standard.

   Unlike the reference and most other implementations, this one is
26 27
   designed to be called once for every character in the buffer or
   string.
Eli Zaretskii's avatar
Eli Zaretskii committed
28

29
   The main entry point is bidi_move_to_visually_next.  Each time it
Eli Zaretskii's avatar
Eli Zaretskii committed
30 31 32
   is called, it finds the next character in the visual order, and
   returns its information in a special structure.  The caller is then
   expected to process this character for display or any other
33 34 35
   purposes, and call bidi_move_to_visually_next for the next
   character.  See the comments in bidi_move_to_visually_next for more
   details about its algorithm that finds the next visual-order
Eli Zaretskii's avatar
Eli Zaretskii committed
36 37
   character by resolving their levels on the fly.

38 39 40 41 42
   The two other entry points are bidi_paragraph_init and
   bidi_mirror_char.  The first determines the base direction of a
   paragraph, while the second returns the mirrored version of its
   argument character.

43 44 45 46
   If you want to understand the code, you will have to read it
   together with the relevant portions of UAX#9.  The comments include
   references to UAX#9 rules, for that very reason.

Eli Zaretskii's avatar
Eli Zaretskii committed
47 48 49 50 51 52 53 54 55 56 57 58 59 60 61
   A note about references to UAX#9 rules: if the reference says
   something like "X9/Retaining", it means that you need to refer to
   rule X9 and to its modifications decribed in the "Implementation
   Notes" section of UAX#9, under "Retaining Format Codes".  */

#ifdef HAVE_CONFIG_H
#include <config.h>
#endif

#include <stdio.h>

#ifdef HAVE_STRING_H
#include <string.h>
#endif

62 63
#include <setjmp.h>

Eli Zaretskii's avatar
Eli Zaretskii committed
64 65 66 67 68 69 70
#include "lisp.h"
#include "buffer.h"
#include "character.h"
#include "dispextern.h"

static int bidi_initialized = 0;

71
static Lisp_Object bidi_type_table, bidi_mirror_table;
Eli Zaretskii's avatar
Eli Zaretskii committed
72

73
/* FIXME: Remove these when bidi_explicit_dir_char uses a lookup table.  */
Eli Zaretskii's avatar
Eli Zaretskii committed
74 75 76 77 78 79 80 81 82
#define LRM_CHAR   0x200E
#define RLM_CHAR   0x200F
#define LRE_CHAR   0x202A
#define RLE_CHAR   0x202B
#define PDF_CHAR   0x202C
#define LRO_CHAR   0x202D
#define RLO_CHAR   0x202E

#define BIDI_EOB   -1
83
#define BIDI_BOB   -2		/* FIXME: Is this needed? */
Eli Zaretskii's avatar
Eli Zaretskii committed
84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104

/* Local data structures.  (Look in dispextern.h for the rest.)  */

/* What we need to know about the current paragraph.  */
struct bidi_paragraph_info {
  int start_bytepos;	/* byte position where it begins */
  int end_bytepos;	/* byte position where it ends */
  int embedding_level;	/* its basic embedding level */
  bidi_dir_t base_dir;	/* its base direction */
};

/* Data type for describing the bidirectional character categories.  */
typedef enum {
  UNKNOWN_BC,
  NEUTRAL,
  WEAK,
  STRONG
} bidi_category_t;

int bidi_ignore_explicit_marks_for_paragraph_level = 1;

Eli Zaretskii's avatar
Eli Zaretskii committed
105
static Lisp_Object paragraph_start_re, paragraph_separate_re;
106
static Lisp_Object Qparagraph_start, Qparagraph_separate;
Eli Zaretskii's avatar
Eli Zaretskii committed
107 108 109 110

static void
bidi_initialize ()
{
111 112

#include "biditype.h"
113
#include "bidimirror.h"
114

Eli Zaretskii's avatar
Eli Zaretskii committed
115 116 117
  int i;

  bidi_type_table = Fmake_char_table (Qnil, make_number (STRONG_L));
118
  staticpro (&bidi_type_table);
Eli Zaretskii's avatar
Eli Zaretskii committed
119 120

  for (i = 0; i < sizeof bidi_type / sizeof bidi_type[0]; i++)
121
    char_table_set_range (bidi_type_table, bidi_type[i].from, bidi_type[i].to,
Eli Zaretskii's avatar
Eli Zaretskii committed
122
			  make_number (bidi_type[i].type));
123

124 125 126 127 128 129 130
  bidi_mirror_table = Fmake_char_table (Qnil, Qnil);
  staticpro (&bidi_mirror_table);

  for (i = 0; i < sizeof bidi_mirror / sizeof bidi_mirror[0]; i++)
    char_table_set (bidi_mirror_table, bidi_mirror[i].from,
		    make_number (bidi_mirror[i].to));

131 132
  Qparagraph_start = intern ("paragraph-start");
  staticpro (&Qparagraph_start);
Eli Zaretskii's avatar
Eli Zaretskii committed
133 134 135 136
  paragraph_start_re = Fsymbol_value (Qparagraph_start);
  if (!STRINGP (paragraph_start_re))
    paragraph_start_re = build_string ("\f\\|[ \t]*$");
  staticpro (&paragraph_start_re);
137 138
  Qparagraph_separate = intern ("paragraph-separate");
  staticpro (&Qparagraph_separate);
Eli Zaretskii's avatar
Eli Zaretskii committed
139 140 141 142
  paragraph_separate_re = Fsymbol_value (Qparagraph_separate);
  if (!STRINGP (paragraph_separate_re))
    paragraph_separate_re = build_string ("[ \t\f]*$");
  staticpro (&paragraph_separate_re);
Eli Zaretskii's avatar
Eli Zaretskii committed
143 144 145
  bidi_initialized = 1;
}

146 147
/* Return the bidi type of a character CH, subject to the current
   directional OVERRIDE.  */
148
static INLINE bidi_type_t
149
bidi_get_type (int ch, bidi_dir_t override)
Eli Zaretskii's avatar
Eli Zaretskii committed
150
{
151 152
  bidi_type_t default_type;

153 154
  if (ch == BIDI_EOB)
    return NEUTRAL_B;
155 156
  if (ch < 0 || ch > MAX_CHAR)
    abort ();
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

  default_type = (bidi_type_t) XINT (CHAR_TABLE_REF (bidi_type_table, ch));

  if (override == NEUTRAL_DIR)
    return default_type;

  switch (default_type)
    {
      /* Although UAX#9 does not tell, it doesn't make sense to
	 override NEUTRAL_B and LRM/RLM characters.  */
      case NEUTRAL_B:
      case LRE:
      case LRO:
      case RLE:
      case RLO:
      case PDF:
	return default_type;
      default:
	switch (ch)
	  {
	    case LRM_CHAR:
	    case RLM_CHAR:
	      return default_type;
	    default:
	      if (override == L2R) /* X6 */
		return STRONG_L;
	      else if (override == R2L)
		return STRONG_R;
	      else
		abort ();	/* can't happen: handled above */
	  }
    }
Eli Zaretskii's avatar
Eli Zaretskii committed
189 190
}

191 192 193 194 195 196 197
void
bidi_check_type (bidi_type_t type)
{
  if (type < UNKNOWN_BT || type > NEUTRAL_ON)
    abort ();
}

Eli Zaretskii's avatar
Eli Zaretskii committed
198
/* Given a bidi TYPE of a character, return its category.  */
199
static INLINE bidi_category_t
Eli Zaretskii's avatar
Eli Zaretskii committed
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
bidi_get_category (bidi_type_t type)
{
  switch (type)
    {
      case UNKNOWN_BT:
	return UNKNOWN_BC;
      case STRONG_L:
      case STRONG_R:
      case STRONG_AL:
      case LRE:
      case LRO:
      case RLE:
      case RLO:
	return STRONG;
      case PDF:		/* ??? really?? */
      case WEAK_EN:
      case WEAK_ES:
      case WEAK_ET:
      case WEAK_AN:
      case WEAK_CS:
      case WEAK_NSM:
      case WEAK_BN:
	return WEAK;
      case NEUTRAL_B:
      case NEUTRAL_S:
      case NEUTRAL_WS:
      case NEUTRAL_ON:
	return NEUTRAL;
      default:
	abort ();
    }
}

233 234 235 236
/* Return the mirrored character of C, if any.

   Note: The conditions in UAX#9 clause L4 must be tested by the
   caller.  */
Eli Zaretskii's avatar
Eli Zaretskii committed
237 238 239
int
bidi_mirror_char (int c)
{
240 241 242 243 244 245
  Lisp_Object val;

  if (c == BIDI_EOB)
    return c;
  if (c < 0 || c > MAX_CHAR)
    abort ();
Eli Zaretskii's avatar
Eli Zaretskii committed
246

247 248
  val = CHAR_TABLE_REF (bidi_mirror_table, c);
  if (INTEGERP (val))
Eli Zaretskii's avatar
Eli Zaretskii committed
249
    {
250
      int v = XINT (val);
Eli Zaretskii's avatar
Eli Zaretskii committed
251

252 253 254 255
      if (v < 0 || v > MAX_CHAR)
	abort ();

      return v;
Eli Zaretskii's avatar
Eli Zaretskii committed
256
    }
257

Eli Zaretskii's avatar
Eli Zaretskii committed
258 259 260 261 262
  return c;
}

/* Copy the bidi iterator from FROM to TO.  To save cycles, this only
   copies the part of the level stack that is actually in use.  */
263
static INLINE void
Eli Zaretskii's avatar
Eli Zaretskii committed
264 265 266 267
bidi_copy_it (struct bidi_it *to, struct bidi_it *from)
{
  int i;

268 269
  /* Copy everything except the level stack and beyond.  */
  memcpy (to, from, ((size_t)&((struct bidi_it *)0)->level_stack[0]));
Eli Zaretskii's avatar
Eli Zaretskii committed
270 271 272 273 274 275 276 277 278

  /* Copy the active part of the level stack.  */
  to->level_stack[0] = from->level_stack[0]; /* level zero is always in use */
  for (i = 1; i <= from->stack_idx; i++)
    to->level_stack[i] = from->level_stack[i];
}

/* Caching the bidi iterator states.  */

279 280 281
#define BIDI_CACHE_CHUNK 200
static struct bidi_it *bidi_cache;
static size_t bidi_cache_size = 0;
282
static size_t elsz = sizeof (struct bidi_it);
283 284
static int bidi_cache_idx;	/* next unused cache slot */
static int bidi_cache_last_idx;	/* slot of last cache hit */
Eli Zaretskii's avatar
Eli Zaretskii committed
285

286
static INLINE void
Eli Zaretskii's avatar
Eli Zaretskii committed
287 288 289 290 291 292
bidi_cache_reset (void)
{
  bidi_cache_idx = 0;
  bidi_cache_last_idx = -1;
}

293 294 295 296 297
static INLINE void
bidi_cache_shrink (void)
{
  if (bidi_cache_size > BIDI_CACHE_CHUNK)
    {
298 299 300
      bidi_cache_size = BIDI_CACHE_CHUNK;
      bidi_cache =
	(struct bidi_it *) xrealloc (bidi_cache, bidi_cache_size * elsz);
301 302 303 304
    }
  bidi_cache_reset ();
}

305
static INLINE void
Eli Zaretskii's avatar
Eli Zaretskii committed
306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321
bidi_cache_fetch_state (int idx, struct bidi_it *bidi_it)
{
  int current_scan_dir = bidi_it->scan_dir;

  if (idx < 0 || idx >= bidi_cache_idx)
    abort ();

  bidi_copy_it (bidi_it, &bidi_cache[idx]);
  bidi_it->scan_dir = current_scan_dir;
  bidi_cache_last_idx = idx;
}

/* Find a cached state with a given CHARPOS and resolved embedding
   level less or equal to LEVEL.  if LEVEL is -1, disregard the
   resolved levels in cached states.  DIR, if non-zero, means search
   in that direction from the last cache hit.  */
322
static INLINE int
Eli Zaretskii's avatar
Eli Zaretskii committed
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
bidi_cache_search (int charpos, int level, int dir)
{
  int i, i_start;

  if (bidi_cache_idx)
    {
      if (charpos < bidi_cache[bidi_cache_last_idx].charpos)
	dir = -1;
      else if (charpos > bidi_cache[bidi_cache_last_idx].charpos)
	dir = 1;
      if (dir)
	i_start = bidi_cache_last_idx;
      else
	{
	  dir = -1;
	  i_start = bidi_cache_idx - 1;
	}

      if (dir < 0)
	{
	  /* Linear search for now; FIXME!  */
	  for (i = i_start; i >= 0; i--)
	    if (bidi_cache[i].charpos == charpos
		&& (level == -1 || bidi_cache[i].resolved_level <= level))
	      return i;
	}
      else
	{
	  for (i = i_start; i < bidi_cache_idx; i++)
	    if (bidi_cache[i].charpos == charpos
		&& (level == -1 || bidi_cache[i].resolved_level <= level))
	      return i;
	}
    }

  return -1;
}

/* Find a cached state where the resolved level changes to a value
   that is lower than LEVEL, and return its cache slot index.  DIR is
   the direction to search, starting with the last used cache slot.
   BEFORE, if non-zero, means return the index of the slot that is
   ``before'' the level change in the search direction.  That is,
   given the cached levels like this:

	 1122333442211
	  AB        C

   and assuming we are at the position cached at the slot marked with
   C, searching backwards (DIR = -1) for LEVEL = 2 will return the
   index of slot B or A, depending whether BEFORE is, respectively,
   non-zero or zero.  */
static int
bidi_cache_find_level_change (int level, int dir, int before)
{
  if (bidi_cache_idx)
    {
      int i = dir ? bidi_cache_last_idx : bidi_cache_idx - 1;
      int incr = before ? 1 : 0;

      if (!dir)
	dir = -1;
      else if (!incr)
	i += dir;

      if (dir < 0)
	{
	  while (i >= incr)
	    {
	      if (bidi_cache[i - incr].resolved_level >= 0
		  && bidi_cache[i - incr].resolved_level < level)
		return i;
	      i--;
	    }
	}
      else
	{
	  while (i < bidi_cache_idx - incr)
	    {
	      if (bidi_cache[i + incr].resolved_level >= 0
		  && bidi_cache[i + incr].resolved_level < level)
		return i;
	      i++;
	    }
	}
    }

  return -1;
}

413
static INLINE void
Eli Zaretskii's avatar
Eli Zaretskii committed
414 415 416 417 418 419 420 421 422 423 424 425
bidi_cache_iterator_state (struct bidi_it *bidi_it, int resolved)
{
  int idx;

  /* We should never cache on backward scans.  */
  if (bidi_it->scan_dir == -1)
    abort ();
  idx = bidi_cache_search (bidi_it->charpos, -1, 1);

  if (idx < 0)
    {
      idx = bidi_cache_idx;
426 427 428
      /* Enlarge the cache as needed.  */
      if (idx >= bidi_cache_size)
	{
429
	  bidi_cache_size += BIDI_CACHE_CHUNK;
430
	  bidi_cache =
431
	    (struct bidi_it *) xrealloc (bidi_cache, bidi_cache_size * elsz);
432
	}
433 434 435 436 437 438 439 440 441 442
      /* Character positions should correspond to cache positions 1:1.
	 If we are outside the range of cached positions, the cache is
	 useless and must be reset.  */
      if (idx > 0 &&
	  (bidi_it->charpos > bidi_cache[idx - 1].charpos + 1
	   || bidi_it->charpos < bidi_cache[0].charpos))
	{
	  bidi_cache_reset ();
	  idx = 0;
	}
Eli Zaretskii's avatar
Eli Zaretskii committed
443 444 445 446 447 448 449 450 451
      bidi_copy_it (&bidi_cache[idx], bidi_it);
      if (!resolved)
	bidi_cache[idx].resolved_level = -1;
    }
  else
    {
      /* Copy only the members which could have changed, to avoid
	 costly copying of the entire struct.  */
      bidi_cache[idx].type = bidi_it->type;
452
      bidi_check_type (bidi_it->type);
453 454
      bidi_cache[idx].type_after_w1 = bidi_it->type_after_w1;
      bidi_check_type (bidi_it->type_after_w1);
Eli Zaretskii's avatar
Eli Zaretskii committed
455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470
      if (resolved)
	bidi_cache[idx].resolved_level = bidi_it->resolved_level;
      else
	bidi_cache[idx].resolved_level = -1;
      bidi_cache[idx].invalid_levels = bidi_it->invalid_levels;
      bidi_cache[idx].invalid_rl_levels = bidi_it->invalid_rl_levels;
      bidi_cache[idx].next_for_neutral = bidi_it->next_for_neutral;
      bidi_cache[idx].next_for_ws = bidi_it->next_for_ws;
      bidi_cache[idx].ignore_bn_limit = bidi_it->ignore_bn_limit;
    }

  bidi_cache_last_idx = idx;
  if (idx >= bidi_cache_idx)
    bidi_cache_idx = idx + 1;
}

471
static INLINE bidi_type_t
Eli Zaretskii's avatar
Eli Zaretskii committed
472 473 474 475 476 477 478 479
bidi_cache_find (int charpos, int level, struct bidi_it *bidi_it)
{
  int i = bidi_cache_search (charpos, level, bidi_it->scan_dir);

  if (i >= 0)
    {
      bidi_dir_t current_scan_dir = bidi_it->scan_dir;

480
      bidi_copy_it (bidi_it, &bidi_cache[i]);
Eli Zaretskii's avatar
Eli Zaretskii committed
481 482 483 484 485 486 487 488 489 490
      bidi_cache_last_idx = i;
      /* Don't let scan direction from from the cached state override
	 the current scan direction.  */
      bidi_it->scan_dir = current_scan_dir;
      return bidi_it->type;
    }

  return UNKNOWN_BT;
}

491
static INLINE int
Eli Zaretskii's avatar
Eli Zaretskii committed
492 493 494 495 496 497 498
bidi_peek_at_next_level (struct bidi_it *bidi_it)
{
  if (bidi_cache_idx == 0 || bidi_cache_last_idx == -1)
    abort ();
  return bidi_cache[bidi_cache_last_idx + bidi_it->scan_dir].resolved_level;
}

499 500 501 502 503
/* Check if buffer position CHARPOS/BYTEPOS is the end of a paragraph.
   Value is the non-negative length of the paragraph separator
   following the buffer position, -1 if position is at the beginning
   of a new paragraph, or -2 if position is neither at beginning nor
   at end of a paragraph.  */
504
static EMACS_INT
505
bidi_at_paragraph_end (EMACS_INT charpos, EMACS_INT bytepos)
Eli Zaretskii's avatar
Eli Zaretskii committed
506
{
507
  /* FIXME: Why Fbuffer_local_value rather than just Fsymbol_value?  */
Eli Zaretskii's avatar
Eli Zaretskii committed
508 509
  Lisp_Object sep_re;
  Lisp_Object start_re;
510 511
  EMACS_INT val;

Eli Zaretskii's avatar
Eli Zaretskii committed
512 513
  sep_re = paragraph_separate_re;
  start_re = paragraph_start_re;
514 515 516 517 518 519 520 521 522

  val = fast_looking_at (sep_re, charpos, bytepos, ZV, ZV_BYTE, Qnil);
  if (val < 0)
    {
      if (fast_looking_at (start_re, charpos, bytepos, ZV, ZV_BYTE, Qnil) >= 0)
	val = -1;
      else
	val = -2;
    }
Eli Zaretskii's avatar
Eli Zaretskii committed
523

524
  return val;
Eli Zaretskii's avatar
Eli Zaretskii committed
525 526 527 528 529 530
}

/* Determine the start-of-run (sor) directional type given the two
   embedding levels on either side of the run boundary.  Also, update
   the saved info about previously seen characters, since that info is
   generally valid for a single level run.  */
531
static INLINE void
Eli Zaretskii's avatar
Eli Zaretskii committed
532 533 534 535 536 537 538 539 540 541 542
bidi_set_sor_type (struct bidi_it *bidi_it, int level_before, int level_after)
{
  int higher_level = level_before > level_after ? level_before : level_after;

  /* The prev_was_pdf gork is required for when we have several PDFs
     in a row.  In that case, we want to compute the sor type for the
     next level run only once: when we see the first PDF.  That's
     because the sor type depends only on the higher of the two levels
     that we find on the two sides of the level boundary (see UAX#9,
     clause X10), and so we don't need to know the final embedding
     level to which we descend after processing all the PDFs.  */
543
  if (!bidi_it->prev_was_pdf || level_before < level_after)
Eli Zaretskii's avatar
Eli Zaretskii committed
544 545 546 547 548 549
    /* FIXME: should the default sor direction be user selectable?  */
    bidi_it->sor = (higher_level & 1) != 0 ? R2L : L2R;
  if (level_before > level_after)
    bidi_it->prev_was_pdf = 1;

  bidi_it->prev.type = UNKNOWN_BT;
550 551
  bidi_it->last_strong.type = bidi_it->last_strong.type_after_w1 =
    bidi_it->last_strong.orig_type = UNKNOWN_BT;
Eli Zaretskii's avatar
Eli Zaretskii committed
552 553 554
  bidi_it->prev_for_neutral.type = bidi_it->sor == R2L ? STRONG_R : STRONG_L;
  bidi_it->prev_for_neutral.charpos = bidi_it->charpos;
  bidi_it->prev_for_neutral.bytepos = bidi_it->bytepos;
555 556
  bidi_it->next_for_neutral.type = bidi_it->next_for_neutral.type_after_w1 =
    bidi_it->next_for_neutral.orig_type = UNKNOWN_BT;
Eli Zaretskii's avatar
Eli Zaretskii committed
557 558 559
  bidi_it->ignore_bn_limit = 0; /* meaning it's unknown */
}

560
static void
561 562 563 564 565 566 567 568 569
bidi_line_init (struct bidi_it *bidi_it)
{
  bidi_it->scan_dir = 1; /* FIXME: do we need to have control on this? */
  bidi_it->resolved_level = bidi_it->level_stack[0].level;
  bidi_it->level_stack[0].override = NEUTRAL_DIR; /* X1 */
  bidi_it->invalid_levels = 0;
  bidi_it->invalid_rl_levels = -1;
  bidi_it->next_en_pos = -1;
  bidi_it->next_for_ws.type = UNKNOWN_BT;
570 571
  bidi_set_sor_type (bidi_it,
		     bidi_it->paragraph_dir == R2L ? 1 : 0,
572 573 574 575 576 577 578 579
		     bidi_it->level_stack[0].level); /* X10 */

  bidi_cache_reset ();
}

/* Find the beginning of this paragraph by looking back in the buffer.
   Value is the byte position of the paragraph's beginning.  */
static EMACS_INT
580
bidi_find_paragraph_start (EMACS_INT pos, EMACS_INT pos_byte)
581
{
Eli Zaretskii's avatar
Eli Zaretskii committed
582
  Lisp_Object re = paragraph_start_re;
583 584 585 586 587
  EMACS_INT limit = ZV, limit_byte = ZV_BYTE;

  while (pos_byte > BEGV_BYTE
	 && fast_looking_at (re, pos, pos_byte, limit, limit_byte, Qnil) < 0)
    {
588 589
      pos = find_next_newline_no_quit (pos - 1, -1);
      pos_byte = CHAR_TO_BYTE (pos);
590
    }
591
  return pos_byte;
592 593
}

594
/* Determine the direction, a.k.a. base embedding level, of the
595 596 597 598 599 600 601
   paragraph we are about to iterate through.  If DIR is either L2R or
   R2L, just use that.  Otherwise, determine the paragraph direction
   from the first strong character of the paragraph.

   Note that this gives the paragraph separator the same direction as
   the preceding paragraph, even though Emacs generally views the
   separartor as not belonging to any paragraph.  */
Eli Zaretskii's avatar
Eli Zaretskii committed
602 603 604
void
bidi_paragraph_init (bidi_dir_t dir, struct bidi_it *bidi_it)
{
605
  EMACS_INT bytepos = bidi_it->bytepos;
606

607 608 609
  /* Special case for an empty buffer. */
  if (bytepos == BEGV_BYTE && bytepos == ZV_BYTE)
    dir = L2R;
610
  /* We should never be called at EOB or before BEGV.  */
611
  else if (bytepos >= ZV_BYTE || bytepos < BEGV_BYTE)
612 613
    abort ();

614 615 616 617 618 619 620 621 622 623
  if (dir == L2R)
    {
      bidi_it->paragraph_dir = L2R;
      bidi_it->new_paragraph = 0;
    }
  else if (dir == R2L)
    {
      bidi_it->paragraph_dir = R2L;
      bidi_it->new_paragraph = 0;
    }
Eli Zaretskii's avatar
Eli Zaretskii committed
624 625
  else if (dir == NEUTRAL_DIR)	/* P2 */
    {
626 627 628
      int ch, ch_len;
      EMACS_INT pos;
      bidi_type_t type;
629

630 631 632
      if (!bidi_initialized)
	bidi_initialize ();

633 634
      /* If we are inside a paragraph separator, we are just waiting
	 for the separator to be exhausted; use the previous paragraph
635 636 637 638
	 direction.  But don't do that if we have been just reseated,
	 because we need to reinitialize below in that case.  */
      if (!bidi_it->first_elt
	  && bidi_it->charpos < bidi_it->separator_limit)
639 640
	return;

641
      /* If we are on a newline, get past it to where the next
642 643 644
	 paragraph might start.  But don't do that at BEGV since then
	 we are potentially in a new paragraph that doesn't yet
	 exist.  */
645
      pos = bidi_it->charpos;
646
      if (bytepos > BEGV_BYTE && FETCH_CHAR (bytepos) == '\n')
647
	{
648
	  bytepos++;
649
	  pos++;
650
	}
651 652 653 654

      /* We are either at the beginning of a paragraph or in the
	 middle of it.  Find where this paragraph starts.  */
      bytepos = bidi_find_paragraph_start (pos, bytepos);
655

656 657
      bidi_it->separator_limit = -1;
      bidi_it->new_paragraph = 0;
658 659
      ch = FETCH_CHAR (bytepos);
      ch_len = CHAR_BYTES (ch);
660
      pos = BYTE_TO_CHAR (bytepos);
661
      type = bidi_get_type (ch, NEUTRAL_DIR);
Eli Zaretskii's avatar
Eli Zaretskii committed
662

663
      for (pos++, bytepos += ch_len;
Eli Zaretskii's avatar
Eli Zaretskii committed
664 665 666 667 668 669 670 671
	   /* NOTE: UAX#9 says to search only for L, AL, or R types of
	      characters, and ignore RLE, RLO, LRE, and LRO.  However,
	      I'm not sure it makes sense to omit those 4; should try
	      with and without that to see the effect.  */
	   (bidi_get_category (type) != STRONG)
	     || (bidi_ignore_explicit_marks_for_paragraph_level
		 && (type == RLE || type == RLO
		     || type == LRE || type == LRO));
672
	   type = bidi_get_type (ch, NEUTRAL_DIR))
Eli Zaretskii's avatar
Eli Zaretskii committed
673
	{
674
	  if (type == NEUTRAL_B && bidi_at_paragraph_end (pos, bytepos) >= -1)
Eli Zaretskii's avatar
Eli Zaretskii committed
675
	    break;
676 677 678 679 680 681
	  if (bytepos >= ZV_BYTE)
	    {
	      /* Pretend there's a paragraph separator at end of buffer.  */
	      type = NEUTRAL_B;
	      break;
	    }
Eli Zaretskii's avatar
Eli Zaretskii committed
682 683 684
	  FETCH_CHAR_ADVANCE (ch, pos, bytepos);
	}
      if (type == STRONG_R || type == STRONG_AL) /* P3 */
685 686 687
	bidi_it->paragraph_dir = R2L;
      else if (type == STRONG_L)
	bidi_it->paragraph_dir = L2R;
Eli Zaretskii's avatar
Eli Zaretskii committed
688
    }
689 690
  else
    abort ();
Eli Zaretskii's avatar
Eli Zaretskii committed
691

692 693 694
  /* Contrary to UAX#9 clause P3, we only default the paragraph
     direction to L2R if we have no previous usable paragraph
     direction.  */
695
  if (bidi_it->paragraph_dir != L2R && bidi_it->paragraph_dir != R2L)
696
    bidi_it->paragraph_dir = L2R; /* P3 and ``higher protocols'' */
697
  if (bidi_it->paragraph_dir == R2L)
698
    bidi_it->level_stack[0].level = 1;
699
  else
700
    bidi_it->level_stack[0].level = 0;
701 702

  bidi_line_init (bidi_it);
Eli Zaretskii's avatar
Eli Zaretskii committed
703 704
}

705 706
/* Do whatever UAX#9 clause X8 says should be done at paragraph's
   end.  */
707
static INLINE void
Eli Zaretskii's avatar
Eli Zaretskii committed
708 709 710 711 712 713 714 715
bidi_set_paragraph_end (struct bidi_it *bidi_it)
{
  bidi_it->invalid_levels = 0;
  bidi_it->invalid_rl_levels = -1;
  bidi_it->stack_idx = 0;
  bidi_it->resolved_level = bidi_it->level_stack[0].level;
}

716
/* Initialize the bidi iterator from buffer position CHARPOS.  */
Eli Zaretskii's avatar
Eli Zaretskii committed
717
void
718
bidi_init_it (EMACS_INT charpos, EMACS_INT bytepos, struct bidi_it *bidi_it)
Eli Zaretskii's avatar
Eli Zaretskii committed
719 720 721
{
  if (! bidi_initialized)
    bidi_initialize ();
722 723
  bidi_it->charpos = charpos;
  bidi_it->bytepos = bytepos;
724 725 726
  bidi_it->first_elt = 1;
  bidi_set_paragraph_end (bidi_it);
  bidi_it->new_paragraph = 1;
727
  bidi_it->separator_limit = -1;
Eli Zaretskii's avatar
Eli Zaretskii committed
728
  bidi_it->type = NEUTRAL_B;
729 730
  bidi_it->type_after_w1 = NEUTRAL_B;
  bidi_it->orig_type = NEUTRAL_B;
Eli Zaretskii's avatar
Eli Zaretskii committed
731
  bidi_it->prev_was_pdf = 0;
732 733
  bidi_it->prev.type = bidi_it->prev.type_after_w1 =
    bidi_it->prev.orig_type = UNKNOWN_BT;
734 735
  bidi_it->last_strong.type = bidi_it->last_strong.type_after_w1 =
    bidi_it->last_strong.orig_type = UNKNOWN_BT;
Eli Zaretskii's avatar
Eli Zaretskii committed
736 737
  bidi_it->next_for_neutral.charpos = -1;
  bidi_it->next_for_neutral.type =
738 739
    bidi_it->next_for_neutral.type_after_w1 =
    bidi_it->next_for_neutral.orig_type = UNKNOWN_BT;
Eli Zaretskii's avatar
Eli Zaretskii committed
740 741
  bidi_it->prev_for_neutral.charpos = -1;
  bidi_it->prev_for_neutral.type =
742 743
    bidi_it->prev_for_neutral.type_after_w1 =
    bidi_it->prev_for_neutral.orig_type = UNKNOWN_BT;
Eli Zaretskii's avatar
Eli Zaretskii committed
744
  bidi_it->sor = L2R;	 /* FIXME: should it be user-selectable? */
745
  bidi_cache_shrink ();
Eli Zaretskii's avatar
Eli Zaretskii committed
746 747 748 749
}

/* Push the current embedding level and override status; reset the
   current level to LEVEL and the current override status to OVERRIDE.  */
750
static INLINE void
Eli Zaretskii's avatar
Eli Zaretskii committed
751 752 753 754 755 756 757 758 759 760 761 762
bidi_push_embedding_level (struct bidi_it *bidi_it,
			   int level, bidi_dir_t override)
{
  bidi_it->stack_idx++;
  if (bidi_it->stack_idx >= BIDI_MAXLEVEL)
    abort ();
  bidi_it->level_stack[bidi_it->stack_idx].level = level;
  bidi_it->level_stack[bidi_it->stack_idx].override = override;
}

/* Pop the embedding level and directional override status from the
   stack, and return the new level.  */
763
static INLINE int
Eli Zaretskii's avatar
Eli Zaretskii committed
764 765 766 767 768 769 770 771 772
bidi_pop_embedding_level (struct bidi_it *bidi_it)
{
  /* UAX#9 says to ignore invalid PDFs.  */
  if (bidi_it->stack_idx > 0)
    bidi_it->stack_idx--;
  return bidi_it->level_stack[bidi_it->stack_idx].level;
}

/* Record in SAVED_INFO the information about the current character.  */
773
static INLINE void
Eli Zaretskii's avatar
Eli Zaretskii committed
774 775 776 777 778 779
bidi_remember_char (struct bidi_saved_info *saved_info,
		    struct bidi_it *bidi_it)
{
  saved_info->charpos = bidi_it->charpos;
  saved_info->bytepos = bidi_it->bytepos;
  saved_info->type = bidi_it->type;
780
  bidi_check_type (bidi_it->type);
781 782
  saved_info->type_after_w1 = bidi_it->type_after_w1;
  bidi_check_type (bidi_it->type_after_w1);
Eli Zaretskii's avatar
Eli Zaretskii committed
783
  saved_info->orig_type = bidi_it->orig_type;
784
  bidi_check_type (bidi_it->orig_type);
Eli Zaretskii's avatar
Eli Zaretskii committed
785 786 787 788
}

/* Resolve the type of a neutral character according to the type of
   surrounding strong text and the current embedding level.  */
789
static INLINE bidi_type_t
Eli Zaretskii's avatar
Eli Zaretskii committed
790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805
bidi_resolve_neutral_1 (bidi_type_t prev_type, bidi_type_t next_type, int lev)
{
  /* N1: European and Arabic numbers are treated as though they were R.  */
  if (next_type == WEAK_EN || next_type == WEAK_AN)
    next_type = STRONG_R;
  if (prev_type == WEAK_EN || prev_type == WEAK_AN)
    prev_type = STRONG_R;

  if (next_type == prev_type)	/* N1 */
    return next_type;
  else if ((lev & 1) == 0)	/* N2 */
    return STRONG_L;
  else
    return STRONG_R;
}

806
static INLINE int
Eli Zaretskii's avatar
Eli Zaretskii committed
807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827
bidi_explicit_dir_char (int c)
{
  /* FIXME: this should be replaced with a lookup table with suitable
     bits set, like standard C ctype macros do.  */
  return (c == LRE_CHAR || c == LRO_CHAR
	  || c == RLE_CHAR || c == RLO_CHAR || c == PDF_CHAR);
}

/* A helper function for bidi_resolve_explicit.  It advances to the
   next character in logical order and determines the new embedding
   level and directional override, but does not take into account
   empty embeddings.  */
static int
bidi_resolve_explicit_1 (struct bidi_it *bidi_it)
{
  int curchar;
  bidi_type_t type;
  int current_level;
  int new_level;
  bidi_dir_t override;

828 829
  if (bidi_it->bytepos < BEGV_BYTE	/* after reseat to BEGV? */
      || bidi_it->first_elt)
830
    {
831 832 833 834
      bidi_it->first_elt = 0;
      if (bidi_it->charpos < BEGV)
	bidi_it->charpos = BEGV;
      bidi_it->bytepos = CHAR_TO_BYTE (bidi_it->charpos);
835
    }
836
  else if (bidi_it->bytepos < ZV_BYTE)	/* don't move at ZV */
Eli Zaretskii's avatar
Eli Zaretskii committed
837 838
    {
      bidi_it->charpos++;
839 840
      if (bidi_it->ch_len == 0)
	abort ();
Eli Zaretskii's avatar
Eli Zaretskii committed
841 842 843 844 845 846 847 848 849
      bidi_it->bytepos += bidi_it->ch_len;
    }

  current_level = bidi_it->level_stack[bidi_it->stack_idx].level; /* X1 */
  override = bidi_it->level_stack[bidi_it->stack_idx].override;
  new_level = current_level;

  /* in case it is a unibyte character (not yet implemented) */
  /* _fetch_multibyte_char_len = 1; */
850 851 852 853 854 855 856 857 858 859
  if (bidi_it->bytepos >= ZV_BYTE)
    {
      curchar = BIDI_EOB;
      bidi_it->ch_len = 1;
    }
  else
    {
      curchar = FETCH_CHAR (bidi_it->bytepos);
      bidi_it->ch_len = CHAR_BYTES (curchar);
    }
Eli Zaretskii's avatar
Eli Zaretskii committed
860 861
  bidi_it->ch = curchar;

862 863 864 865 866
  /* Don't apply directional override here, as all the types we handle
     below will not be affected by the override anyway, and we need
     the original type unaltered.  The override will be applied in
     bidi_resolve_weak.  */
  type = bidi_get_type (curchar, NEUTRAL_DIR);
867 868
  bidi_it->orig_type = type;
  bidi_check_type (bidi_it->orig_type);
Eli Zaretskii's avatar
Eli Zaretskii committed
869 870 871 872

  if (type != PDF)
    bidi_it->prev_was_pdf = 0;

873
  bidi_it->type_after_w1 = UNKNOWN_BT;
Eli Zaretskii's avatar
Eli Zaretskii committed
874 875 876 877 878

  switch (type)
    {
      case RLE:	/* X2 */
      case RLO:	/* X4 */
879 880
	bidi_it->type_after_w1 = type;
	bidi_check_type (bidi_it->type_after_w1);
Eli Zaretskii's avatar
Eli Zaretskii committed
881 882 883 884 885 886 887 888
	type = WEAK_BN; /* X9/Retaining */
	if (bidi_it->ignore_bn_limit <= 0)
	  {
	    if (current_level <= BIDI_MAXLEVEL - 4)
	      {
		/* Compute the least odd embedding level greater than
		   the current level.  */
		new_level = ((current_level + 1) & ~1) + 1;
889
		if (bidi_it->type_after_w1 == RLE)
Eli Zaretskii's avatar
Eli Zaretskii committed
890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905
		  override = NEUTRAL_DIR;
		else
		  override = R2L;
		if (current_level == BIDI_MAXLEVEL - 4)
		  bidi_it->invalid_rl_levels = 0;
		bidi_push_embedding_level (bidi_it, new_level, override);
	      }
	    else
	      {
		bidi_it->invalid_levels++;
		/* See the commentary about invalid_rl_levels below.  */
		if (bidi_it->invalid_rl_levels < 0)
		  bidi_it->invalid_rl_levels = 0;
		bidi_it->invalid_rl_levels++;
	      }
	  }
906
	else if (bidi_it->prev.type_after_w1 == WEAK_EN /* W5/Retaining */
Eli Zaretskii's avatar
Eli Zaretskii committed
907 908 909 910 911
		 || bidi_it->next_en_pos > bidi_it->charpos)
	  type = WEAK_EN;
	break;
      case LRE:	/* X3 */
      case LRO:	/* X5 */
912 913
	bidi_it->type_after_w1 = type;
	bidi_check_type (bidi_it->type_after_w1);
Eli Zaretskii's avatar
Eli Zaretskii committed
914 915 916 917 918 919 920 921
	type = WEAK_BN; /* X9/Retaining */
	if (bidi_it->ignore_bn_limit <= 0)
	  {
	    if (current_level <= BIDI_MAXLEVEL - 5)
	      {
		/* Compute the least even embedding level greater than
		   the current level.  */
		new_level = ((current_level + 2) & ~1);
922
		if (bidi_it->type_after_w1 == LRE)
Eli Zaretskii's avatar
Eli Zaretskii committed
923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941
		  override = NEUTRAL_DIR;
		else
		  override = L2R;
		bidi_push_embedding_level (bidi_it, new_level, override);
	      }
	    else
	      {
		bidi_it->invalid_levels++;
		/* invalid_rl_levels counts invalid levels encountered
		   while the embedding level was already too high for
		   LRE/LRO, but not for RLE/RLO.  That is because
		   there may be exactly one PDF which we should not
		   ignore even though invalid_levels is non-zero.
		   invalid_rl_levels helps to know what PDF is
		   that.  */
		if (bidi_it->invalid_rl_levels >= 0)
		  bidi_it->invalid_rl_levels++;
	      }
	  }
942
	else if (bidi_it->prev.type_after_w1 == WEAK_EN /* W5/Retaining */
Eli Zaretskii's avatar
Eli Zaretskii committed
943 944 945 946
		 || bidi_it->next_en_pos > bidi_it->charpos)
	  type = WEAK_EN;
	break;
      case PDF:	/* X7 */
947 948
	bidi_it->type_after_w1 = type;
	bidi_check_type (bidi_it->type_after_w1);
Eli Zaretskii's avatar
Eli Zaretskii committed
949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967
	type = WEAK_BN; /* X9/Retaining */
	if (bidi_it->ignore_bn_limit <= 0)
	  {
	    if (!bidi_it->invalid_rl_levels)
	      {
		new_level = bidi_pop_embedding_level (bidi_it);
		bidi_it->invalid_rl_levels = -1;
		if (bidi_it->invalid_levels)
		  bidi_it->invalid_levels--;
		/* else nothing: UAX#9 says to ignore invalid PDFs */
	      }
	    if (!bidi_it->invalid_levels)
	      new_level = bidi_pop_embedding_level (bidi_it);
	    else
	      {
		bidi_it->invalid_levels--;
		bidi_it->invalid_rl_levels--;
	      }
	  }
968
	else if (bidi_it->prev.type_after_w1 == WEAK_EN /* W5/Retaining */
Eli Zaretskii's avatar
Eli Zaretskii committed
969 970 971 972 973 974 975 976 977
		 || bidi_it->next_en_pos > bidi_it->charpos)
	  type = WEAK_EN;
	break;
      default:
	/* Nothing.  */
	break;
    }

  bidi_it->type = type;
978
  bidi_check_type (bidi_it->type);
Eli Zaretskii's avatar
Eli Zaretskii committed
979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996

  return new_level;
}

/* Given an iterator state in BIDI_IT, advance one character position
   in the buffer to the next character (in the logical order), resolve
   any explicit embeddings and directional overrides, and return the
   embedding level of the character after resolving explicit
   directives and ignoring empty embeddings.  */
static int
bidi_resolve_explicit (struct bidi_it *bidi_it)
{
  int prev_level = bidi_it->level_stack[bidi_it->stack_idx].level;
  int new_level  = bidi_resolve_explicit_1 (bidi_it);

  if (prev_level < new_level
      && bidi_it->type == WEAK_BN
      && bidi_it->ignore_bn_limit == 0 /* only if not already known */
997
      && bidi_it->bytepos < ZV_BYTE    /* not already at EOB */
Eli Zaretskii's avatar
Eli Zaretskii committed
998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044
      && bidi_explicit_dir_char (FETCH_CHAR (bidi_it->bytepos
					     + bidi_it->ch_len)))
    {
      /* Avoid pushing and popping embedding levels if the level run
	 is empty, as this breaks level runs where it shouldn't.
	 UAX#9 removes all the explicit embedding and override codes,
	 so empty embeddings disappear without a trace.  We need to
	 behave as if we did the same.  */
      struct bidi_it saved_it;
      int level = prev_level;

      bidi_copy_it (&saved_it, bidi_it);

      while (bidi_explicit_dir_char (FETCH_CHAR (bidi_it->bytepos
						 + bidi_it->ch_len)))
	{
	  level = bidi_resolve_explicit_1 (bidi_it);
	}

      if (level == prev_level)	/* empty embedding */
	saved_it.ignore_bn_limit = bidi_it->charpos + 1;
      else			/* this embedding is non-empty */
	saved_it.ignore_bn_limit = -1;

      bidi_copy_it (bidi_it, &saved_it);
      if (bidi_it->ignore_bn_limit > 0)
	{
	  /* We pushed a level, but we shouldn't have.  Undo that. */
	  if (!bidi_it->invalid_rl_levels)
	    {
	      new_level = bidi_pop_embedding_level (bidi_it);
	      bidi_it->invalid_rl_levels = -1;
	      if (bidi_it->invalid_levels)
		bidi_it->invalid_levels--;
	    }
	  if (!bidi_it->invalid_levels)
	    new_level = bidi_pop_embedding_level (bidi_it);
	  else
	    {
	      bidi_it->invalid_levels--;
	      bidi_it->invalid_rl_levels--;
	    }
	}
    }

  if (bidi_it->type == NEUTRAL_B)	/* X8 */
    {
1045
      bidi_set_paragraph_end (bidi_it);
1046 1047
      /* This is needed by bidi_resolve_weak below, and in L1.  */
      bidi_it->type_after_w1 = bidi_it->type;
1048
      bidi_check_type (bidi_it->type_after_w1);
Eli Zaretskii's avatar
Eli Zaretskii committed
1049 1050 1051 1052 1053 1054 1055
    }

  return new_level;
}

/* Advance in the buffer, resolve weak types and return the type of
   the next character after weak type resolution.  */
1056
static bidi_type_t
Eli Zaretskii's avatar
Eli Zaretskii committed
1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087
bidi_resolve_weak (struct bidi_it *bidi_it)
{
  bidi_type_t type;
  bidi_dir_t override;
  int prev_level = bidi_it->level_stack[bidi_it->stack_idx].level;
  int new_level  = bidi_resolve_explicit (bidi_it);
  int next_char;
  bidi_type_t type_of_next;
  struct bidi_it saved_it;

  type = bidi_it->type;
  override = bidi_it->level_stack[bidi_it->stack_idx].override;

  if (type == UNKNOWN_BT
      || type == LRE
      || type == LRO
      || type == RLE
      || type == RLO
      || type == PDF)
    abort ();

  if (new_level != prev_level
      || bidi_it->type == NEUTRAL_B)
    {
      /* We've got a new embedding level run, compute the directional
         type of sor and initialize per-run variables (UAX#9, clause
         X10).  */
      bidi_set_sor_type (bidi_it, prev_level, new_level);
    }
  else if (type == NEUTRAL_S || type == NEUTRAL_WS
	   || type == WEAK_BN || type == STRONG_AL)
1088 1089
    bidi_it->type_after_w1 = type;	/* needed in L1 */
  bidi_check_type (bidi_it->type_after_w1);
Eli Zaretskii's avatar
Eli Zaretskii committed
1090 1091 1092 1093 1094 1095 1096

  /* Level and directional override status are already recorded in
     bidi_it, and do not need any change; see X6.  */
  if (override == R2L)		/* X6 */
    type = STRONG_R;
  else if (override == L2R)
    type = STRONG_L;
1097
  else
Eli Zaretskii's avatar
Eli Zaretskii committed
1098
    {
1099
      if (type == WEAK_NSM)	/* W1 */
Eli Zaretskii's avatar
Eli Zaretskii committed
1100
	{
1101
	  /* Note that we don't need to consider the case where the
1102 1103 1104 1105 1106 1107
	     prev character has its type overridden by an RLO or LRO,
	     because then either the type of this NSM would have been
	     also overridden, or the previous character is outside the
	     current level run, and thus not relevant to this NSM.
	     This is why NSM gets the type_after_w1 of the previous
	     character.  */
1108 1109 1110
	  if (bidi_it->prev.type_after_w1 != UNKNOWN_BT
	      /* if type_after_w1 is NEUTRAL_B, this NSM is at sor */
	      && bidi_it->prev.type_after_w1 != NEUTRAL_B)
1111
	    type = bidi_it->prev.type_after_w1;
1112 1113 1114 1115 1116 1117
	  else if (bidi_it->sor == R2L)
	    type = STRONG_R;
	  else if (bidi_it->sor == L2R)
	    type = STRONG_L;
	  else /* shouldn't happen! */
	    abort ();
Eli Zaretskii's avatar
Eli Zaretskii committed
1118
	}
1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130
      if (type == WEAK_EN	/* W2 */
	  && bidi_it->last_strong.type_after_w1 == STRONG_AL)
	type = WEAK_AN;
      else if (type == STRONG_AL) /* W3 */
	type = STRONG_R;
      else if ((type == WEAK_ES	/* W4 */
		&& bidi_it->prev.type_after_w1 == WEAK_EN
		&& bidi_it->prev.orig_type == WEAK_EN)
	       || (type == WEAK_CS
		   && ((bidi_it->prev.type_after_w1 == WEAK_EN
			&& bidi_it->prev.orig_type == WEAK_EN)
		       || bidi_it->prev.type_after_w1 == WEAK_AN)))
Eli Zaretskii's avatar
Eli Zaretskii committed
1131
	{
1132 1133 1134
	  next_char =
	    bidi_it->bytepos + bidi_it->ch_len >= ZV_BYTE
	    ? BIDI_EOB : FETCH_CHAR (bidi_it->bytepos + bidi_it->ch_len);
1135
	  type_of_next = bidi_get_type (next_char, override);
Eli Zaretskii's avatar
Eli Zaretskii committed
1136

1137
	  if (type_of_next == WEAK_BN
Eli Zaretskii's avatar
Eli Zaretskii committed
1138 1139 1140 1141
	      || bidi_explicit_dir_char (next_char))
	    {
	      bidi_copy_it (&saved_it, bidi_it);
	      while (bidi_resolve_explicit (bidi_it) == new_level
1142
		     && bidi_it->type == WEAK_BN)
Eli Zaretskii's avatar
Eli Zaretskii committed
1143 1144 1145 1146
		;
	      type_of_next = bidi_it->type;
	      bidi_copy_it (bidi_it, &saved_it);
	    }
1147 1148 1149 1150 1151 1152 1153 1154 1155 1156

	  /* If the next character is EN, but the last strong-type
	     character is AL, that next EN will be changed to AN when
	     we process it in W2 above.  So in that case, this ES
	     should not be changed into EN.  */
	  if (type == WEAK_ES
	      && type_of_next == WEAK_EN
	      && bidi_it->last_strong.type_after_w1 != STRONG_AL)
	    type = WEAK_EN;
	  else if (type == WEAK_CS)
Eli Zaretskii's avatar
Eli Zaretskii committed
1157
	    {
1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202
	      if (bidi_it->prev.type_after_w1 == WEAK_AN
		  && (type_of_next == WEAK_AN
		      /* If the next character is EN, but the last
			 strong-type character is AL, EN will be later
			 changed to AN when we process it in W2 above.
			 So in that case, this ES should not be
			 changed into EN.  */
		      || (type_of_next == WEAK_EN
			  && bidi_it->last_strong.type_after_w1 == STRONG_AL)))
		type = WEAK_AN;
	      else if (bidi_it->prev.type_after_w1 == WEAK_EN
		       && type_of_next == WEAK_EN
		       && bidi_it->last_strong.type_after_w1 != STRONG_AL)
		type = WEAK_EN;
	    }
	}
      else if (type == WEAK_ET	/* W5: ET with EN before or after it */
	       || type == WEAK_BN)	/* W5/Retaining */
	{
	  if (bidi_it->prev.type_after_w1 == WEAK_EN /* ET/BN w/EN before it */
	      || bidi_it->next_en_pos > bidi_it->charpos)
	    type = WEAK_EN;
	  else			/* W5: ET/BN with EN after it.  */
	    {
	      EMACS_INT en_pos = bidi_it->charpos + 1;

	      next_char =
		bidi_it->bytepos + bidi_it->ch_len >= ZV_BYTE
		? BIDI_EOB : FETCH_CHAR (bidi_it->bytepos + bidi_it->ch_len);
	      type_of_next = bidi_get_type (next_char, override);

	      if (type_of_next == WEAK_ET
		  || type_of_next == WEAK_BN
		  || bidi_explicit_dir_char (next_char))
		{
		  bidi_copy_it (&saved_it, bidi_it);
		  while (bidi_resolve_explicit (bidi_it) == new_level
			 && (bidi_it->type == WEAK_BN
			     || bidi_it->type == WEAK_ET))
		    ;
		  type_of_next = bidi_it->type;
		  en_pos = bidi_it->charpos;
		  bidi_copy_it (bidi_it, &saved_it);
		}
	      if (type_of_next == WEAK_EN)
Eli Zaretskii's avatar
Eli Zaretskii committed
1203
		{
1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214
		  /* If the last strong character is AL, the EN we've
		     found will become AN when we get to it (W2). */
		  if (bidi_it->last_strong.type_after_w1 != STRONG_AL)
		    {
		      type = WEAK_EN;
		      /* Remember this EN position, to speed up processing
			 of the next ETs.  */
		      bidi_it->next_en_pos = en_pos;
		    }
		  else if (type == WEAK_BN)
		    type = NEUTRAL_ON; /* W6/Retaining */
Eli Zaretskii's avatar
Eli Zaretskii committed
1215 1216 1217 1218 1219 1220
		}
	    }
	}
    }

  if (type == WEAK_ES || type == WEAK_ET || type == WEAK_CS /* W6 */
1221 1222 1223 1224
      || (type == WEAK_BN
	  && (bidi_it->prev.type_after_w1 == WEAK_CS	    /* W6/Retaining */
	      || bidi_it->prev.type_after_w1 == WEAK_ES
	      || bidi_it->prev.type_after_w1 == WEAK_ET)))
Eli Zaretskii's avatar
Eli Zaretskii committed
1225 1226 1227 1228 1229 1230
    type = NEUTRAL_ON;

  /* Store the type we've got so far, before we clobber it with strong
     types in W7 and while resolving neutral types.  But leave alone
     the original types that were recorded above, because we will need
     them for the L1 clause.  */
1231 1232 1233
  if (bidi_it->type_after_w1 == UNKNOWN_BT)
    bidi_it->type_after_w1 = type;
  bidi_check_type (bidi_it->type_after_w1);
Eli Zaretskii's avatar
Eli Zaretskii committed
1234 1235 1236

  if (type == WEAK_EN)	/* W7 */
    {
1237
      if ((bidi_it->last_strong.type_after_w1 == STRONG_L)
Eli Zaretskii's avatar
Eli Zaretskii committed
1238 1239 1240 1241 1242
	  || (bidi_it->last_strong.type == UNKNOWN_BT && bidi_it->sor == L2R))
	type = STRONG_L;
    }

  bidi_it->type = type;
1243
  bidi_check_type (bidi_it->type);
Eli Zaretskii's avatar
Eli Zaretskii committed
1244 1245 1246
  return type;
}

1247
static bidi_type_t
Eli Zaretskii's avatar
Eli Zaretskii committed
1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296
bidi_resolve_neutral (struct bidi_it *bidi_it)
{
  int prev_level = bidi_it->level_stack[bidi_it->stack_idx].level;
  bidi_type_t type = bidi_resolve_weak (bidi_it);
  int current_level = bidi_it->level_stack[bidi_it->stack_idx].level;

  if (!(type == STRONG_R
	|| type == STRONG_L
	|| type == WEAK_BN
	|| type == WEAK_EN
	|| type == WEAK_AN
	|| type == NEUTRAL_B
	|| type == NEUTRAL_S
	|| type == NEUTRAL_WS
	|| type == NEUTRAL_ON))
    abort ();

  if (bidi_get_category (type) == NEUTRAL
      || (type == WEAK_BN && prev_level == current_level))
    {
      if (bidi_it->next_for_neutral.type != UNKNOWN_BT)
	type = bidi_resolve_neutral_1 (bidi_it->prev_for_neutral.type,
				       bidi_it->next_for_neutral.type,
				       current_level);
      else
	{
	  /* Arrrgh!!  The UAX#9 algorithm is too deeply entrenched in
	     the assumption of batch-style processing; see clauses W4,
	     W5, and especially N1, which require to look far forward
	     (as well as back) in the buffer.  May the fleas of a
	     thousand camels infest the armpits of those who design
	     supposedly general-purpose algorithms by looking at their
	     own implementations, and fail to consider other possible
	     implementations!  */
	  struct bidi_it saved_it;
	  bidi_type_t next_type;

	  if (bidi_it->scan_dir == -1)
	    abort ();

	  bidi_copy_it (&saved_it, bidi_it);
	  /* Scan the text forward until we find the first non-neutral
	     character, and then use that to resolve the neutral we
	     are dealing with now.  We also cache the scanned iterator
	     states, to salvage some of the effort later.  */
	  bidi_cache_iterator_state (bidi_it, 0);
	  do {
	    /* Record the info about the previous character, so that
	       it will be cached below with this state.  */
1297
	    if (bidi_it->type_after_w1 != WEAK_BN /* W1/Retaining */
Eli Zaretskii's avatar
Eli Zaretskii committed
1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340
		&& bidi_it->type != WEAK_BN)
	      bidi_remember_char (&bidi_it->prev, bidi_it);
	    type = bidi_resolve_weak (bidi_it);
	    /* Paragraph separators have their levels fully resolved
	       at this point, so cache them as resolved.  */
	    bidi_cache_iterator_state (bidi_it, type == NEUTRAL_B);
	    /* FIXME: implement L1 here, by testing for a newline and
	       resetting the level for any sequence of whitespace
	       characters adjacent to it.  */
	  } while (!(type == NEUTRAL_B
		     || (type != WEAK_BN
			 && bidi_get_category (type) != NEUTRAL)
		     /* This is all per level run, so stop when we
			reach the end of this level run.  */
		     || bidi_it->level_stack[bidi_it->stack_idx].level !=
		     current_level));

	  bidi_remember_char (&saved_it.next_for_neutral, bidi_it);

	  switch (type)
	    {
	      case STRONG_L:
	      case STRONG_R:
	      case STRONG_AL:
		next_type = type;
		break;
	      case WEAK_EN:
	      case WEAK_AN:
		/* N1: ``European and Arabic numbers are treated as
		   though they were R.''  */
		next_type = STRONG_R;
		saved_it.next_for_neutral.type = STRONG_R;
		break;
	      case WEAK_BN:
		if (!bidi_explicit_dir_char (bidi_it->ch))
		  abort ();		/* can't happen: BNs are skipped */
		/* FALLTHROUGH */
	      case NEUTRAL_B:
		/* Marched all the way to the end of this level run.
		   We need to use the eor type, whose information is
		   stored by bidi_set_sor_type in the prev_for_neutral
		   member.  */
		if (saved_it.type != WEAK_BN
1341
		    || bidi_get_category (bidi_it->prev.type_after_w1) == NEUTRAL)
Eli Zaretskii's avatar
Eli Zaretskii committed
1342 1343 1344
		  {
		    next_type = bidi_it->prev_for_neutral.type;
		    saved_it.next_for_neutral.type = next_type;
1345
		    bidi_check_type (next_type);
Eli Zaretskii's avatar
Eli Zaretskii committed
1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360
		  }
		else
		  {
		    /* This is a BN which does not adjoin neutrals.
		       Leave its type alone.  */
		    bidi_copy_it (bidi_it, &saved_it);
		    return bidi_it->type;
		  }
		break;
	      default:
		abort ();
	    }
	  type = bidi_resolve_neutral_1 (saved_it.prev_for_neutral.type,
					 next_type, current_level);
	  saved_it.type = type;
1361
	  bidi_check_type (type);
Eli Zaretskii's avatar
Eli Zaretskii committed
1362 1363 1364 1365 1366 1367 1368 1369 1370
	  bidi_copy_it (bidi_it, &saved_it);
	}
    }
  return type;
}

/* Given an iterator state in BIDI_IT, advance one character position
   in the buffer to the next character (in the logical order), resolve
   the bidi type of that next character, and return that type.  */
1371
static bidi_type_t
Eli Zaretskii's avatar
Eli Zaretskii committed
1372 1373