unofficial mirror of emacs-devel@gnu.org 
 help / color / mirror / code / Atom feed
blob 8639c0ab990cddc0d7c1ff16e9df4ed3f1ecd34d 30414 bytes (raw)
name: src/character.c 	 # note: path name is non-authoritative(*)

   1
   2
   3
   4
   5
   6
   7
   8
   9
  10
  11
  12
  13
  14
  15
  16
  17
  18
  19
  20
  21
  22
  23
  24
  25
  26
  27
  28
  29
  30
  31
  32
  33
  34
  35
  36
  37
  38
  39
  40
  41
  42
  43
  44
  45
  46
  47
  48
  49
  50
  51
  52
  53
  54
  55
  56
  57
  58
  59
  60
  61
  62
  63
  64
  65
  66
  67
  68
  69
  70
  71
  72
  73
  74
  75
  76
  77
  78
  79
  80
  81
  82
  83
  84
  85
  86
  87
  88
  89
  90
  91
  92
  93
  94
  95
  96
  97
  98
  99
 100
 101
 102
 103
 104
 105
 106
 107
 108
 109
 110
 111
 112
 113
 114
 115
 116
 117
 118
 119
 120
 121
 122
 123
 124
 125
 126
 127
 128
 129
 130
 131
 132
 133
 134
 135
 136
 137
 138
 139
 140
 141
 142
 143
 144
 145
 146
 147
 148
 149
 150
 151
 152
 153
 154
 155
 156
 157
 158
 159
 160
 161
 162
 163
 164
 165
 166
 167
 168
 169
 170
 171
 172
 173
 174
 175
 176
 177
 178
 179
 180
 181
 182
 183
 184
 185
 186
 187
 188
 189
 190
 191
 192
 193
 194
 195
 196
 197
 198
 199
 200
 201
 202
 203
 204
 205
 206
 207
 208
 209
 210
 211
 212
 213
 214
 215
 216
 217
 218
 219
 220
 221
 222
 223
 224
 225
 226
 227
 228
 229
 230
 231
 232
 233
 234
 235
 236
 237
 238
 239
 240
 241
 242
 243
 244
 245
 246
 247
 248
 249
 250
 251
 252
 253
 254
 255
 256
 257
 258
 259
 260
 261
 262
 263
 264
 265
 266
 267
 268
 269
 270
 271
 272
 273
 274
 275
 276
 277
 278
 279
 280
 281
 282
 283
 284
 285
 286
 287
 288
 289
 290
 291
 292
 293
 294
 295
 296
 297
 298
 299
 300
 301
 302
 303
 304
 305
 306
 307
 308
 309
 310
 311
 312
 313
 314
 315
 316
 317
 318
 319
 320
 321
 322
 323
 324
 325
 326
 327
 328
 329
 330
 331
 332
 333
 334
 335
 336
 337
 338
 339
 340
 341
 342
 343
 344
 345
 346
 347
 348
 349
 350
 351
 352
 353
 354
 355
 356
 357
 358
 359
 360
 361
 362
 363
 364
 365
 366
 367
 368
 369
 370
 371
 372
 373
 374
 375
 376
 377
 378
 379
 380
 381
 382
 383
 384
 385
 386
 387
 388
 389
 390
 391
 392
 393
 394
 395
 396
 397
 398
 399
 400
 401
 402
 403
 404
 405
 406
 407
 408
 409
 410
 411
 412
 413
 414
 415
 416
 417
 418
 419
 420
 421
 422
 423
 424
 425
 426
 427
 428
 429
 430
 431
 432
 433
 434
 435
 436
 437
 438
 439
 440
 441
 442
 443
 444
 445
 446
 447
 448
 449
 450
 451
 452
 453
 454
 455
 456
 457
 458
 459
 460
 461
 462
 463
 464
 465
 466
 467
 468
 469
 470
 471
 472
 473
 474
 475
 476
 477
 478
 479
 480
 481
 482
 483
 484
 485
 486
 487
 488
 489
 490
 491
 492
 493
 494
 495
 496
 497
 498
 499
 500
 501
 502
 503
 504
 505
 506
 507
 508
 509
 510
 511
 512
 513
 514
 515
 516
 517
 518
 519
 520
 521
 522
 523
 524
 525
 526
 527
 528
 529
 530
 531
 532
 533
 534
 535
 536
 537
 538
 539
 540
 541
 542
 543
 544
 545
 546
 547
 548
 549
 550
 551
 552
 553
 554
 555
 556
 557
 558
 559
 560
 561
 562
 563
 564
 565
 566
 567
 568
 569
 570
 571
 572
 573
 574
 575
 576
 577
 578
 579
 580
 581
 582
 583
 584
 585
 586
 587
 588
 589
 590
 591
 592
 593
 594
 595
 596
 597
 598
 599
 600
 601
 602
 603
 604
 605
 606
 607
 608
 609
 610
 611
 612
 613
 614
 615
 616
 617
 618
 619
 620
 621
 622
 623
 624
 625
 626
 627
 628
 629
 630
 631
 632
 633
 634
 635
 636
 637
 638
 639
 640
 641
 642
 643
 644
 645
 646
 647
 648
 649
 650
 651
 652
 653
 654
 655
 656
 657
 658
 659
 660
 661
 662
 663
 664
 665
 666
 667
 668
 669
 670
 671
 672
 673
 674
 675
 676
 677
 678
 679
 680
 681
 682
 683
 684
 685
 686
 687
 688
 689
 690
 691
 692
 693
 694
 695
 696
 697
 698
 699
 700
 701
 702
 703
 704
 705
 706
 707
 708
 709
 710
 711
 712
 713
 714
 715
 716
 717
 718
 719
 720
 721
 722
 723
 724
 725
 726
 727
 728
 729
 730
 731
 732
 733
 734
 735
 736
 737
 738
 739
 740
 741
 742
 743
 744
 745
 746
 747
 748
 749
 750
 751
 752
 753
 754
 755
 756
 757
 758
 759
 760
 761
 762
 763
 764
 765
 766
 767
 768
 769
 770
 771
 772
 773
 774
 775
 776
 777
 778
 779
 780
 781
 782
 783
 784
 785
 786
 787
 788
 789
 790
 791
 792
 793
 794
 795
 796
 797
 798
 799
 800
 801
 802
 803
 804
 805
 806
 807
 808
 809
 810
 811
 812
 813
 814
 815
 816
 817
 818
 819
 820
 821
 822
 823
 824
 825
 826
 827
 828
 829
 830
 831
 832
 833
 834
 835
 836
 837
 838
 839
 840
 841
 842
 843
 844
 845
 846
 847
 848
 849
 850
 851
 852
 853
 854
 855
 856
 857
 858
 859
 860
 861
 862
 863
 864
 865
 866
 867
 868
 869
 870
 871
 872
 873
 874
 875
 876
 877
 878
 879
 880
 881
 882
 883
 884
 885
 886
 887
 888
 889
 890
 891
 892
 893
 894
 895
 896
 897
 898
 899
 900
 901
 902
 903
 904
 905
 906
 907
 908
 909
 910
 911
 912
 913
 914
 915
 916
 917
 918
 919
 920
 921
 922
 923
 924
 925
 926
 927
 928
 929
 930
 931
 932
 933
 934
 935
 936
 937
 938
 939
 940
 941
 942
 943
 944
 945
 946
 947
 948
 949
 950
 951
 952
 953
 954
 955
 956
 957
 958
 959
 960
 961
 962
 963
 964
 965
 966
 967
 968
 969
 970
 971
 972
 973
 974
 975
 976
 977
 978
 979
 980
 981
 982
 983
 984
 985
 986
 987
 988
 989
 990
 991
 992
 993
 994
 995
 996
 997
 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
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
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
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
 
/* Basic character support.

Copyright (C) 2001-2016 Free Software Foundation, Inc.
Copyright (C) 1995, 1997, 1998, 2001 Electrotechnical Laboratory, JAPAN.
  Licensed to the Free Software Foundation.
Copyright (C) 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011
  National Institute of Advanced Industrial Science and Technology (AIST)
  Registration Number H13PRO009

This file is part of GNU Emacs.

GNU Emacs is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or (at
your option) any later version.

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
along with GNU Emacs.  If not, see <http://www.gnu.org/licenses/>.  */

/* At first, see the document in `character.h' to understand the code
   in this file.  */

#include <config.h>

#include <stdio.h>

#include <sys/types.h>
#include <intprops.h>
#include "lisp.h"
#include "character.h"
#include "buffer.h"
#include "composite.h"
#include "disptab.h"

/* Char-table of information about which character to unify to which
   Unicode character.  Mainly used by the macro MAYBE_UNIFY_CHAR.  */
Lisp_Object Vchar_unify_table;

\f

/* If character code C has modifier masks, reflect them to the
   character code if possible.  Return the resulting code.  */

EMACS_INT
char_resolve_modifier_mask (EMACS_INT c)
{
  /* A non-ASCII character can't reflect modifier bits to the code.  */
  if (! ASCII_CHAR_P ((c & ~CHAR_MODIFIER_MASK)))
    return c;

  /* For Meta, Shift, and Control modifiers, we need special care.  */
  if (c & CHAR_SHIFT)
    {
      /* Shift modifier is valid only with [A-Za-z].  */
      if ((c & 0377) >= 'A' && (c & 0377) <= 'Z')
	c &= ~CHAR_SHIFT;
      else if ((c & 0377) >= 'a' && (c & 0377) <= 'z')
	c = (c & ~CHAR_SHIFT) - ('a' - 'A');
      /* Shift modifier for control characters and SPC is ignored.  */
      else if ((c & ~CHAR_MODIFIER_MASK) <= 0x20)
	c &= ~CHAR_SHIFT;
    }
  if (c & CHAR_CTL)
    {
      /* Simulate the code in lread.c.  */
      /* Allow `\C- ' and `\C-?'.  */
      if ((c & 0377) == ' ')
	c &= ~0177 & ~ CHAR_CTL;
      else if ((c & 0377) == '?')
	c = 0177 | (c & ~0177 & ~CHAR_CTL);
      /* ASCII control chars are made from letters (both cases),
	 as well as the non-letters within 0100...0137.  */
      else if ((c & 0137) >= 0101 && (c & 0137) <= 0132)
	c &= (037 | (~0177 & ~CHAR_CTL));
      else if ((c & 0177) >= 0100 && (c & 0177) <= 0137)
	c &= (037 | (~0177 & ~CHAR_CTL));
    }
#if 0	/* This is outside the scope of this function.  (bug#4751)  */
  if (c & CHAR_META)
    {
      /* Move the meta bit to the right place for a string.  */
      c = (c & ~CHAR_META) | 0x80;
    }
#endif

  return c;
}


/* Store multibyte form of character C at P.  If C has modifier bits,
   handle them appropriately.  */

int
char_string (unsigned int c, unsigned char *p)
{
  int bytes;

  if (c & CHAR_MODIFIER_MASK)
    {
      c = char_resolve_modifier_mask (c);
      /* If C still has any modifier bits, just ignore it.  */
      c &= ~CHAR_MODIFIER_MASK;
    }

  if (c <= MAX_3_BYTE_CHAR)
    {
      bytes = CHAR_STRING (c, p);
    }
  else if (c <= MAX_4_BYTE_CHAR)
    {
      p[0] = (0xF0 | (c >> 18));
      p[1] = (0x80 | ((c >> 12) & 0x3F));
      p[2] = (0x80 | ((c >> 6) & 0x3F));
      p[3] = (0x80 | (c & 0x3F));
      bytes = 4;
    }
  else if (c <= MAX_5_BYTE_CHAR)
    {
      p[0] = 0xF8;
      p[1] = (0x80 | ((c >> 18) & 0x0F));
      p[2] = (0x80 | ((c >> 12) & 0x3F));
      p[3] = (0x80 | ((c >> 6) & 0x3F));
      p[4] = (0x80 | (c & 0x3F));
      bytes = 5;
    }
  else if (c <= MAX_CHAR)
    {
      c = CHAR_TO_BYTE8 (c);
      bytes = BYTE8_STRING (c, p);
    }
  else
    error ("Invalid character: %x", c);

  return bytes;
}


/* Return a character whose multibyte form is at P.  If LEN is not
   NULL, it must be a pointer to integer.  In that case, set *LEN to
   the byte length of the multibyte form.  If ADVANCED is not NULL, it
   must be a pointer to unsigned char.  In that case, set *ADVANCED to
   the ending address (i.e., the starting address of the next
   character) of the multibyte form.  */

int
string_char (const unsigned char *p, const unsigned char **advanced, int *len)
{
  int c;
  const unsigned char *saved_p = p;

  if (*p < 0x80 || ! (*p & 0x20) || ! (*p & 0x10))
    {
      /* 1-, 2-, and 3-byte sequences can be handled by the macro.  */
      c = STRING_CHAR_ADVANCE (p);
    }
  else if (! (*p & 0x08))
    {
      /* A 4-byte sequence of this form:
	 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx  */
      c = ((((p)[0] & 0x7) << 18)
	   | (((p)[1] & 0x3F) << 12)
	   | (((p)[2] & 0x3F) << 6)
	   | ((p)[3] & 0x3F));
      p += 4;
    }
  else
    {
      /* A 5-byte sequence of this form:

	 111110xx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx

	 Note that the top 4 `x's are always 0, so shifting p[1] can
	 never exceed the maximum valid character codepoint. */
      c = (/* (((p)[0] & 0x3) << 24) ... always 0, so no need to shift. */
	   (((p)[1] & 0x3F) << 18)
	   | (((p)[2] & 0x3F) << 12)
	   | (((p)[3] & 0x3F) << 6)
	   | ((p)[4] & 0x3F));
      p += 5;
    }

  if (len)
    *len = p - saved_p;
  if (advanced)
    *advanced = p;
  return c;
}


/* Translate character C by translation table TABLE.  If no translation is
   found in TABLE, return the untranslated character.  If TABLE is a list,
   elements are char tables.  In that case, recursively translate C by all the
   tables in the list.  */

int
translate_char (Lisp_Object table, int c)
{
  if (CHAR_TABLE_P (table))
    {
      Lisp_Object ch;

      ch = CHAR_TABLE_REF (table, c);
      if (CHARACTERP (ch))
	c = XINT (ch);
    }
  else
    {
      for (; CONSP (table); table = XCDR (table))
	c = translate_char (XCAR (table), c);
    }
  return c;
}

DEFUN ("characterp", Fcharacterp, Scharacterp, 1, 2, 0,
       doc: /* Return non-nil if OBJECT is a character.
In Emacs Lisp, characters are represented by character codes, which
are non-negative integers.  The function `max-char' returns the
maximum character code.
usage: (characterp OBJECT)  */
       attributes: const)
  (Lisp_Object object, Lisp_Object ignore)
{
  return (CHARACTERP (object) ? Qt : Qnil);
}

DEFUN ("max-char", Fmax_char, Smax_char, 0, 0, 0,
       doc: /* Return the character of the maximum code.  */
       attributes: const)
  (void)
{
  return make_number (MAX_CHAR);
}

DEFUN ("unibyte-char-to-multibyte", Funibyte_char_to_multibyte,
       Sunibyte_char_to_multibyte, 1, 1, 0,
       doc: /* Convert the byte CH to multibyte character.  */)
  (Lisp_Object ch)
{
  int c;

  CHECK_CHARACTER (ch);
  c = XFASTINT (ch);
  if (c >= 0x100)
    error ("Not a unibyte character: %d", c);
  MAKE_CHAR_MULTIBYTE (c);
  return make_number (c);
}

DEFUN ("multibyte-char-to-unibyte", Fmultibyte_char_to_unibyte,
       Smultibyte_char_to_unibyte, 1, 1, 0,
       doc: /* Convert the multibyte character CH to a byte.
If the multibyte character does not represent a byte, return -1.  */)
  (Lisp_Object ch)
{
  int cm;

  CHECK_CHARACTER (ch);
  cm = XFASTINT (ch);
  if (cm < 256)
    /* Can't distinguish a byte read from a unibyte buffer from
       a latin1 char, so let's let it slide.  */
    return ch;
  else
    {
      int cu = CHAR_TO_BYTE_SAFE (cm);
      return make_number (cu);
    }
}


/* Return width (columns) of C considering the buffer display table DP. */

static ptrdiff_t
char_width (int c, struct Lisp_Char_Table *dp)
{
  ptrdiff_t width = CHARACTER_WIDTH (c);

  if (dp)
    {
      Lisp_Object disp = DISP_CHAR_VECTOR (dp, c), ch;
      int i;

      if (VECTORP (disp))
	for (i = 0, width = 0; i < ASIZE (disp); i++)
	  {
	    ch = AREF (disp, i);
	    if (CHARACTERP (ch))
	      {
		int w = CHARACTER_WIDTH (XFASTINT (ch));
		if (INT_ADD_WRAPV (width, w, &width))
		  string_overflow ();
	      }
	  }
    }
  return width;
}


DEFUN ("char-width", Fchar_width, Schar_width, 1, 1, 0,
       doc: /* Return width of CHAR when displayed in the current buffer.
The width is measured by how many columns it occupies on the screen.
Tab is taken to occupy `tab-width' columns.
usage: (char-width CHAR)  */)
  (Lisp_Object ch)
{
  int c;
  ptrdiff_t width;

  CHECK_CHARACTER (ch);
  c = XINT (ch);
  width = char_width (c, buffer_display_table ());
  return make_number (width);
}

/* Return width of string STR of length LEN when displayed in the
   current buffer.  The width is measured by how many columns it
   occupies on the screen.  If PRECISION > 0, return the width of
   longest substring that doesn't exceed PRECISION, and set number of
   characters and bytes of the substring in *NCHARS and *NBYTES
   respectively.  */

ptrdiff_t
c_string_width (const unsigned char *str, ptrdiff_t len, int precision,
		ptrdiff_t *nchars, ptrdiff_t *nbytes)
{
  ptrdiff_t i = 0, i_byte = 0;
  ptrdiff_t width = 0;
  struct Lisp_Char_Table *dp = buffer_display_table ();

  while (i_byte < len)
    {
      int bytes;
      int c = STRING_CHAR_AND_LENGTH (str + i_byte, bytes);
      ptrdiff_t thiswidth = char_width (c, dp);

      if (0 < precision && precision - width < thiswidth)
	{
	  *nchars = i;
	  *nbytes = i_byte;
	  return width;
	}
      if (INT_ADD_WRAPV (thiswidth, width, &width))
	string_overflow ();
      i++;
      i_byte += bytes;
  }

  if (precision > 0)
    {
      *nchars = i;
      *nbytes = i_byte;
    }

  return width;
}

/* Return width of string STR of length LEN when displayed in the
   current buffer.  The width is measured by how many columns it
   occupies on the screen.  */

ptrdiff_t
strwidth (const char *str, ptrdiff_t len)
{
  return c_string_width ((const unsigned char *) str, len, -1, NULL, NULL);
}

/* Return width of Lisp string STRING when displayed in the current
   buffer.  The width is measured by how many columns it occupies on
   the screen while paying attention to compositions.  If PRECISION >
   0, return the width of longest substring that doesn't exceed
   PRECISION, and set number of characters and bytes of the substring
   in *NCHARS and *NBYTES respectively.  */

ptrdiff_t
lisp_string_width (Lisp_Object string, ptrdiff_t precision,
		   ptrdiff_t *nchars, ptrdiff_t *nbytes)
{
  ptrdiff_t len = SCHARS (string);
  /* This set multibyte to 0 even if STRING is multibyte when it
     contains only ascii and eight-bit-graphic, but that's
     intentional.  */
  bool multibyte = len < SBYTES (string);
  unsigned char *str = SDATA (string);
  ptrdiff_t i = 0, i_byte = 0;
  ptrdiff_t width = 0;
  struct Lisp_Char_Table *dp = buffer_display_table ();

  while (i < len)
    {
      ptrdiff_t chars, bytes, thiswidth;
      Lisp_Object val;
      ptrdiff_t cmp_id;
      ptrdiff_t ignore, end;

      if (find_composition (i, -1, &ignore, &end, &val, string)
	  && ((cmp_id = get_composition_id (i, i_byte, end - i, val, string))
	      >= 0))
	{
	  thiswidth = composition_table[cmp_id]->width;
	  chars = end - i;
	  bytes = string_char_to_byte (string, end) - i_byte;
	}
      else
	{
	  int c;

	  if (multibyte)
	    {
	      int cbytes;
	      c = STRING_CHAR_AND_LENGTH (str + i_byte, cbytes);
	      bytes = cbytes;
	    }
	  else
	    c = str[i_byte], bytes = 1;
	  chars = 1;
	  thiswidth = char_width (c, dp);
	}

      if (0 < precision && precision - width < thiswidth)
	{
	  *nchars = i;
	  *nbytes = i_byte;
	  return width;
	}
      if (INT_ADD_WRAPV (thiswidth, width, &width))
	string_overflow ();
      i += chars;
      i_byte += bytes;
    }

  if (precision > 0)
    {
      *nchars = i;
      *nbytes = i_byte;
    }

  return width;
}

DEFUN ("string-width", Fstring_width, Sstring_width, 1, 1, 0,
       doc: /* Return width of STRING when displayed in the current buffer.
Width is measured by how many columns it occupies on the screen.
When calculating width of a multibyte character in STRING,
only the base leading-code is considered; the validity of
the following bytes is not checked.  Tabs in STRING are always
taken to occupy `tab-width' columns.
usage: (string-width STRING)  */)
  (Lisp_Object str)
{
  Lisp_Object val;

  CHECK_STRING (str);
  XSETFASTINT (val, lisp_string_width (str, -1, NULL, NULL));
  return val;
}

/* Return the number of characters in the NBYTES bytes at PTR.
   This works by looking at the contents and checking for multibyte
   sequences while assuming that there's no invalid sequence.
   However, if the current buffer has enable-multibyte-characters =
   nil, we treat each byte as a character.  */

ptrdiff_t
chars_in_text (const unsigned char *ptr, ptrdiff_t nbytes)
{
  /* current_buffer is null at early stages of Emacs initialization.  */
  if (current_buffer == 0
      || NILP (BVAR (current_buffer, enable_multibyte_characters)))
    return nbytes;

  return multibyte_chars_in_text (ptr, nbytes);
}

/* Return the number of characters in the NBYTES bytes at PTR.
   This works by looking at the contents and checking for multibyte
   sequences while assuming that there's no invalid sequence.  It
   ignores enable-multibyte-characters.  */

ptrdiff_t
multibyte_chars_in_text (const unsigned char *ptr, ptrdiff_t nbytes)
{
  const unsigned char *endp = ptr + nbytes;
  ptrdiff_t chars = 0;

  while (ptr < endp)
    {
      int len = MULTIBYTE_LENGTH (ptr, endp);

      if (len == 0)
	emacs_abort ();
      ptr += len;
      chars++;
    }

  return chars;
}

/* Parse unibyte text at STR of LEN bytes as a multibyte text, count
   characters and bytes in it, and store them in *NCHARS and *NBYTES
   respectively.  On counting bytes, pay attention to that 8-bit
   characters not constructing a valid multibyte sequence are
   represented by 2-byte in a multibyte text.  */

void
parse_str_as_multibyte (const unsigned char *str, ptrdiff_t len,
			ptrdiff_t *nchars, ptrdiff_t *nbytes)
{
  const unsigned char *endp = str + len;
  int n;
  ptrdiff_t chars = 0, bytes = 0;

  if (len >= MAX_MULTIBYTE_LENGTH)
    {
      const unsigned char *adjusted_endp = endp - MAX_MULTIBYTE_LENGTH;
      while (str < adjusted_endp)
	{
	  if (! CHAR_BYTE8_HEAD_P (*str)
	      && (n = MULTIBYTE_LENGTH_NO_CHECK (str)) > 0)
	    str += n, bytes += n;
	  else
	    str++, bytes += 2;
	  chars++;
	}
    }
  while (str < endp)
    {
      if (! CHAR_BYTE8_HEAD_P (*str)
	  && (n = MULTIBYTE_LENGTH (str, endp)) > 0)
	str += n, bytes += n;
      else
	str++, bytes += 2;
      chars++;
    }

  *nchars = chars;
  *nbytes = bytes;
  return;
}

/* Arrange unibyte text at STR of NBYTES bytes as a multibyte text.
   It actually converts only such 8-bit characters that don't construct
   a multibyte sequence to multibyte forms of Latin-1 characters.  If
   NCHARS is nonzero, set *NCHARS to the number of characters in the
   text.  It is assured that we can use LEN bytes at STR as a work
   area and that is enough.  Return the number of bytes of the
   resulting text.  */

ptrdiff_t
str_as_multibyte (unsigned char *str, ptrdiff_t len, ptrdiff_t nbytes,
		  ptrdiff_t *nchars)
{
  unsigned char *p = str, *endp = str + nbytes;
  unsigned char *to;
  ptrdiff_t chars = 0;
  int n;

  if (nbytes >= MAX_MULTIBYTE_LENGTH)
    {
      unsigned char *adjusted_endp = endp - MAX_MULTIBYTE_LENGTH;
      while (p < adjusted_endp
	     && ! CHAR_BYTE8_HEAD_P (*p)
	     && (n = MULTIBYTE_LENGTH_NO_CHECK (p)) > 0)
	p += n, chars++;
    }
  while (p < endp
	 && ! CHAR_BYTE8_HEAD_P (*p)
	 && (n = MULTIBYTE_LENGTH (p, endp)) > 0)
    p += n, chars++;
  if (nchars)
    *nchars = chars;
  if (p == endp)
    return nbytes;

  to = p;
  nbytes = endp - p;
  endp = str + len;
  memmove (endp - nbytes, p, nbytes);
  p = endp - nbytes;

  if (nbytes >= MAX_MULTIBYTE_LENGTH)
    {
      unsigned char *adjusted_endp = endp - MAX_MULTIBYTE_LENGTH;
      while (p < adjusted_endp)
	{
	  if (! CHAR_BYTE8_HEAD_P (*p)
	      && (n = MULTIBYTE_LENGTH_NO_CHECK (p)) > 0)
	    {
	      while (n--)
		*to++ = *p++;
	    }
	  else
	    {
	      int c = *p++;
	      c = BYTE8_TO_CHAR (c);
	      to += CHAR_STRING (c, to);
	    }
	}
      chars++;
    }
  while (p < endp)
    {
      if (! CHAR_BYTE8_HEAD_P (*p)
	  && (n = MULTIBYTE_LENGTH (p, endp)) > 0)
	{
	  while (n--)
	    *to++ = *p++;
	}
      else
	{
	  int c = *p++;
	  c = BYTE8_TO_CHAR (c);
	  to += CHAR_STRING (c, to);
	}
      chars++;
    }
  if (nchars)
    *nchars = chars;
  return (to - str);
}

/* Parse unibyte string at STR of LEN bytes, and return the number of
   bytes it may occupy when converted to multibyte string by
   `str_to_multibyte'.  */

ptrdiff_t
count_size_as_multibyte (const unsigned char *str, ptrdiff_t len)
{
  const unsigned char *endp = str + len;
  ptrdiff_t bytes;

  for (bytes = 0; str < endp; str++)
    {
      int n = *str < 0x80 ? 1 : 2;
      if (INT_ADD_WRAPV (bytes, n, &bytes))
	string_overflow ();
    }
  return bytes;
}


/* Convert unibyte text at STR of BYTES bytes to a multibyte text
   that contains the same single-byte characters.  It actually
   converts all 8-bit characters to multibyte forms.  It is assured
   that we can use LEN bytes at STR as a work area and that is
   enough.  */

ptrdiff_t
str_to_multibyte (unsigned char *str, ptrdiff_t len, ptrdiff_t bytes)
{
  unsigned char *p = str, *endp = str + bytes;
  unsigned char *to;

  while (p < endp && *p < 0x80) p++;
  if (p == endp)
    return bytes;
  to = p;
  bytes = endp - p;
  endp = str + len;
  memmove (endp - bytes, p, bytes);
  p = endp - bytes;
  while (p < endp)
    {
      int c = *p++;

      if (c >= 0x80)
	c = BYTE8_TO_CHAR (c);
      to += CHAR_STRING (c, to);
    }
  return (to - str);
}

/* Arrange multibyte text at STR of LEN bytes as a unibyte text.  It
   actually converts characters in the range 0x80..0xFF to
   unibyte.  */

ptrdiff_t
str_as_unibyte (unsigned char *str, ptrdiff_t bytes)
{
  const unsigned char *p = str, *endp = str + bytes;
  unsigned char *to;
  int c, len;

  while (p < endp)
    {
      c = *p;
      len = BYTES_BY_CHAR_HEAD (c);
      if (CHAR_BYTE8_HEAD_P (c))
	break;
      p += len;
    }
  to = str + (p - str);
  while (p < endp)
    {
      c = *p;
      len = BYTES_BY_CHAR_HEAD (c);
      if (CHAR_BYTE8_HEAD_P (c))
	{
	  c = STRING_CHAR_ADVANCE (p);
	  *to++ = CHAR_TO_BYTE8 (c);
	}
      else
	{
	  while (len--) *to++ = *p++;
	}
    }
  return (to - str);
}

/* Convert eight-bit chars in SRC (in multibyte form) to the
   corresponding byte and store in DST.  CHARS is the number of
   characters in SRC.  The value is the number of bytes stored in DST.
   Usually, the value is the same as CHARS, but is less than it if SRC
   contains a non-ASCII, non-eight-bit character.  */

ptrdiff_t
str_to_unibyte (const unsigned char *src, unsigned char *dst, ptrdiff_t chars)
{
  ptrdiff_t i;

  for (i = 0; i < chars; i++)
    {
      int c = STRING_CHAR_ADVANCE (src);

      if (CHAR_BYTE8_P (c))
	c = CHAR_TO_BYTE8 (c);
      else if (! ASCII_CHAR_P (c))
	return i;
      *dst++ = c;
    }
  return i;
}


static ptrdiff_t
string_count_byte8 (Lisp_Object string)
{
  bool multibyte = STRING_MULTIBYTE (string);
  ptrdiff_t nbytes = SBYTES (string);
  unsigned char *p = SDATA (string);
  unsigned char *pend = p + nbytes;
  ptrdiff_t count = 0;
  int c, len;

  if (multibyte)
    while (p < pend)
      {
	c = *p;
	len = BYTES_BY_CHAR_HEAD (c);

	if (CHAR_BYTE8_HEAD_P (c))
	  count++;
	p += len;
      }
  else
    while (p < pend)
      {
	if (*p++ >= 0x80)
	  count++;
      }
  return count;
}


Lisp_Object
string_escape_byte8 (Lisp_Object string)
{
  ptrdiff_t nchars = SCHARS (string);
  ptrdiff_t nbytes = SBYTES (string);
  bool multibyte = STRING_MULTIBYTE (string);
  ptrdiff_t byte8_count;
  ptrdiff_t thrice_byte8_count, uninit_nchars, uninit_nbytes;
  const unsigned char *src, *src_end;
  unsigned char *dst;
  Lisp_Object val;
  int c, len;

  if (multibyte && nchars == nbytes)
    return string;

  byte8_count = string_count_byte8 (string);

  if (byte8_count == 0)
    return string;

  if (INT_MULTIPLY_WRAPV (byte8_count, 3, &thrice_byte8_count))
    string_overflow ();

  if (multibyte)
    {
      /* Convert 2-byte sequence of byte8 chars to 4-byte octal.  */
      if (INT_ADD_WRAPV (nchars, thrice_byte8_count, &uninit_nchars)
	  || INT_ADD_WRAPV (nbytes, 2 * byte8_count, &uninit_nbytes))
	string_overflow ();
      val = make_uninit_multibyte_string (uninit_nchars, uninit_nbytes);
    }
  else
    {
      /* Convert 1-byte sequence of byte8 chars to 4-byte octal.  */
      if (INT_ADD_WRAPV (thrice_byte8_count, nbytes, &uninit_nbytes))
	string_overflow ();
      val = make_uninit_string (uninit_nbytes);
    }

  src = SDATA (string);
  src_end = src + nbytes;
  dst = SDATA (val);
  if (multibyte)
    while (src < src_end)
      {
	c = *src;
	len = BYTES_BY_CHAR_HEAD (c);

	if (CHAR_BYTE8_HEAD_P (c))
	  {
	    c = STRING_CHAR_ADVANCE (src);
	    c = CHAR_TO_BYTE8 (c);
	    dst += sprintf ((char *) dst, "\\%03o", c + 0u);
	  }
	else
	  while (len--) *dst++ = *src++;
      }
  else
    while (src < src_end)
      {
	c = *src++;
	if (c >= 0x80)
	  dst += sprintf ((char *) dst, "\\%03o", c + 0u);
	else
	  *dst++ = c;
      }
  return val;
}

\f
DEFUN ("string", Fstring, Sstring, 0, MANY, 0,
       doc: /*
Concatenate all the argument characters and make the result a string.
usage: (string &rest CHARACTERS)  */)
  (ptrdiff_t n, Lisp_Object *args)
{
  ptrdiff_t i;
  int c;
  unsigned char *buf, *p;
  Lisp_Object str;
  USE_SAFE_ALLOCA;

  SAFE_NALLOCA (buf, MAX_MULTIBYTE_LENGTH, n);
  p = buf;

  for (i = 0; i < n; i++)
    {
      CHECK_CHARACTER (args[i]);
      c = XINT (args[i]);
      p += CHAR_STRING (c, p);
    }

  str = make_string_from_bytes ((char *) buf, n, p - buf);
  SAFE_FREE ();
  return str;
}

DEFUN ("unibyte-string", Funibyte_string, Sunibyte_string, 0, MANY, 0,
       doc: /* Concatenate all the argument bytes and make the result a unibyte string.
usage: (unibyte-string &rest BYTES)  */)
  (ptrdiff_t n, Lisp_Object *args)
{
  ptrdiff_t i;
  Lisp_Object str;
  USE_SAFE_ALLOCA;
  unsigned char *buf = SAFE_ALLOCA (n);
  unsigned char *p = buf;

  for (i = 0; i < n; i++)
    {
      CHECK_RANGED_INTEGER (args[i], 0, 255);
      *p++ = XINT (args[i]);
    }

  str = make_string_from_bytes ((char *) buf, n, p - buf);
  SAFE_FREE ();
  return str;
}

DEFUN ("char-resolve-modifiers", Fchar_resolve_modifiers,
       Schar_resolve_modifiers, 1, 1, 0,
       doc: /* Resolve modifiers in the character CHAR.
The value is a character with modifiers resolved into the character
code.  Unresolved modifiers are kept in the value.
usage: (char-resolve-modifiers CHAR)  */)
  (Lisp_Object character)
{
  EMACS_INT c;

  CHECK_NUMBER (character);
  c = XINT (character);
  return make_number (char_resolve_modifier_mask (c));
}

DEFUN ("get-byte", Fget_byte, Sget_byte, 0, 2, 0,
       doc: /* Return a byte value of a character at point.
Optional 1st arg POSITION, if non-nil, is a position of a character to get
a byte value.
Optional 2nd arg STRING, if non-nil, is a string of which first
character is a target to get a byte value.  In this case, POSITION, if
non-nil, is an index of a target character in the string.

If the current buffer (or STRING) is multibyte, and the target
character is not ASCII nor 8-bit character, an error is signaled.  */)
  (Lisp_Object position, Lisp_Object string)
{
  int c;
  ptrdiff_t pos;
  unsigned char *p;

  if (NILP (string))
    {
      if (NILP (position))
	{
	  p = PT_ADDR;
	}
      else
	{
	  CHECK_NUMBER_COERCE_MARKER (position);
	  if (XINT (position) < BEGV || XINT (position) >= ZV)
	    args_out_of_range_3 (position, make_number (BEGV), make_number (ZV));
	  pos = XFASTINT (position);
	  p = CHAR_POS_ADDR (pos);
	}
      if (NILP (BVAR (current_buffer, enable_multibyte_characters)))
	return make_number (*p);
    }
  else
    {
      CHECK_STRING (string);
      if (NILP (position))
	{
	  p = SDATA (string);
	}
      else
	{
	  CHECK_NATNUM (position);
	  if (XINT (position) >= SCHARS (string))
	    args_out_of_range (string, position);
	  pos = XFASTINT (position);
	  p = SDATA (string) + string_char_to_byte (string, pos);
	}
      if (! STRING_MULTIBYTE (string))
	return make_number (*p);
    }
  c = STRING_CHAR (p);
  if (CHAR_BYTE8_P (c))
    c = CHAR_TO_BYTE8 (c);
  else if (! ASCII_CHAR_P (c))
    error ("Not an ASCII nor an 8-bit character: %d", c);
  return make_number (c);
}

/* Return true if C is an alphabetic character.  */
bool
alphabeticp (int c)
{
  Lisp_Object category = CHAR_TABLE_REF (Vunicode_category_table, c);
  if (! INTEGERP (category))
    return false;
  EMACS_INT gen_cat = XINT (category);

  /* See UTS #18.  There are additional characters that should be
     here, those designated as Other_uppercase, Other_lowercase,
     and Other_alphabetic; FIXME.  */
  return (gen_cat == UNICODE_CATEGORY_Lu
	  || gen_cat == UNICODE_CATEGORY_Ll
	  || gen_cat == UNICODE_CATEGORY_Lt
	  || gen_cat == UNICODE_CATEGORY_Lm
	  || gen_cat == UNICODE_CATEGORY_Lo
	  || gen_cat == UNICODE_CATEGORY_Mn
	  || gen_cat == UNICODE_CATEGORY_Mc
	  || gen_cat == UNICODE_CATEGORY_Me
	  || gen_cat == UNICODE_CATEGORY_Nl);
}

/* Return true if C is a alphabetic or decimal-number character.  */
bool
alphanumericp (int c)
{
  Lisp_Object category = CHAR_TABLE_REF (Vunicode_category_table, c);
  if (! INTEGERP (category))
    return false;
  EMACS_INT gen_cat = XINT (category);

  /* See UTS #18.  Same comment as for alphabeticp applies.  FIXME. */
  return (gen_cat == UNICODE_CATEGORY_Lu
	  || gen_cat == UNICODE_CATEGORY_Ll
	  || gen_cat == UNICODE_CATEGORY_Lt
	  || gen_cat == UNICODE_CATEGORY_Lm
	  || gen_cat == UNICODE_CATEGORY_Lo
	  || gen_cat == UNICODE_CATEGORY_Mn
	  || gen_cat == UNICODE_CATEGORY_Mc
	  || gen_cat == UNICODE_CATEGORY_Me
	  || gen_cat == UNICODE_CATEGORY_Nl
	  || gen_cat == UNICODE_CATEGORY_Nd);
}

/* Return true if C is a graphic character.  */
bool
graphicp (int c)
{
  Lisp_Object category = CHAR_TABLE_REF (Vunicode_category_table, c);
  if (! INTEGERP (category))
    return false;
  EMACS_INT gen_cat = XINT (category);

  /* See UTS #18.  */
  return (!(gen_cat == UNICODE_CATEGORY_Zs /* space separator */
	    || gen_cat == UNICODE_CATEGORY_Zl /* line separator */
	    || gen_cat == UNICODE_CATEGORY_Zp /* paragraph separator */
	    || gen_cat == UNICODE_CATEGORY_Cc /* control */
	    || gen_cat == UNICODE_CATEGORY_Cs /* surrogate */
	    || gen_cat == UNICODE_CATEGORY_Cn)); /* unassigned */
}

/* Return true if C is a printable character.  */
bool
printablep (int c)
{
  Lisp_Object category = CHAR_TABLE_REF (Vunicode_category_table, c);
  if (! INTEGERP (category))
    return false;
  EMACS_INT gen_cat = XINT (category);

  /* See UTS #18.  */
  return (!(gen_cat == UNICODE_CATEGORY_Cc /* control */
	    || gen_cat == UNICODE_CATEGORY_Cs /* surrogate */
	    || gen_cat == UNICODE_CATEGORY_Cn)); /* unassigned */
}

void
syms_of_character (void)
{
  DEFSYM (Qcharacterp, "characterp");
  DEFSYM (Qauto_fill_chars, "auto-fill-chars");

  staticpro (&Vchar_unify_table);
  Vchar_unify_table = Qnil;

  defsubr (&Smax_char);
  defsubr (&Scharacterp);
  defsubr (&Sunibyte_char_to_multibyte);
  defsubr (&Smultibyte_char_to_unibyte);
  defsubr (&Schar_width);
  defsubr (&Sstring_width);
  defsubr (&Sstring);
  defsubr (&Sunibyte_string);
  defsubr (&Schar_resolve_modifiers);
  defsubr (&Sget_byte);

  DEFVAR_LISP ("translation-table-vector",  Vtranslation_table_vector,
	       doc: /*
Vector recording all translation tables ever defined.
Each element is a pair (SYMBOL . TABLE) relating the table to the
symbol naming it.  The ID of a translation table is an index into this vector.  */);
  Vtranslation_table_vector = Fmake_vector (make_number (16), Qnil);

  DEFVAR_LISP ("auto-fill-chars", Vauto_fill_chars,
	       doc: /*
A char-table for characters which invoke auto-filling.
Such characters have value t in this table.  */);
  Vauto_fill_chars = Fmake_char_table (Qauto_fill_chars, Qnil);
  CHAR_TABLE_SET (Vauto_fill_chars, ' ', Qt);
  CHAR_TABLE_SET (Vauto_fill_chars, '\n', Qt);

  DEFVAR_LISP ("char-width-table", Vchar_width_table,
	       doc: /*
A char-table for width (columns) of each character.  */);
  Vchar_width_table = Fmake_char_table (Qnil, make_number (1));
  char_table_set_range (Vchar_width_table, 0x80, 0x9F, make_number (4));
  char_table_set_range (Vchar_width_table, MAX_5_BYTE_CHAR + 1, MAX_CHAR,
			make_number (4));

  DEFVAR_LISP ("printable-chars", Vprintable_chars,
	       doc: /* A char-table for each printable character.  */);
  Vprintable_chars = Fmake_char_table (Qnil, Qnil);
  Fset_char_table_range (Vprintable_chars,
			 Fcons (make_number (32), make_number (126)), Qt);
  Fset_char_table_range (Vprintable_chars,
			 Fcons (make_number (160),
				make_number (MAX_5_BYTE_CHAR)), Qt);

  DEFVAR_LISP ("char-script-table", Vchar_script_table,
	       doc: /* Char table of script symbols.
It has one extra slot whose value is a list of script symbols.  */);

  DEFSYM (Qchar_script_table, "char-script-table");
  Fput (Qchar_script_table, Qchar_table_extra_slots, make_number (1));
  Vchar_script_table = Fmake_char_table (Qchar_script_table, Qnil);

  DEFVAR_LISP ("script-representative-chars", Vscript_representative_chars,
	       doc: /* Alist of scripts vs the representative characters.
Each element is a cons (SCRIPT . CHARS).
SCRIPT is a symbol representing a script or a subgroup of a script.
CHARS is a list or a vector of characters.
If it is a list, all characters in the list are necessary for supporting SCRIPT.
If it is a vector, one of the characters in the vector is necessary.
This variable is used to find a font for a specific script.  */);
  Vscript_representative_chars = Qnil;

  DEFVAR_LISP ("unicode-category-table", Vunicode_category_table,
	       doc: /* Char table of Unicode's "General Category".
All Unicode characters have one of the following values (symbol):
  Lu, Ll, Lt, Lm, Lo, Mn, Mc, Me, Nd, Nl, No, Pc, Pd, Ps, Pe, Pi, Pf, Po,
  Sm, Sc, Sk, So, Zs, Zl, Zp, Cc, Cf, Cs, Co, Cn
See The Unicode Standard for the meaning of those values.  */);
  /* The correct char-table is setup in characters.el.  */
  Vunicode_category_table = Qnil;
}

debug log:

solving 8639c0a ...
found 8639c0a in https://yhetil.org/emacs-devel/87h95olvg0.fsf@gmail.com/
found 75a7dab in https://git.savannah.gnu.org/cgit/emacs.git
preparing index
index prepared:
100644 75a7dab68459bb7755ac515c89cae9dee06302dc	src/character.c

applying [1/1] https://yhetil.org/emacs-devel/87h95olvg0.fsf@gmail.com/
diff --git a/src/character.c b/src/character.c
index 75a7dab..8639c0a 100644

Checking patch src/character.c...
Applied patch src/character.c cleanly.

index at:
100644 8639c0ab990cddc0d7c1ff16e9df4ed3f1ecd34d	src/character.c

(*) Git path names are given by the tree(s) the blob belongs to.
    Blobs themselves have no identifier aside from the hash of its contents.^

Code repositories for project(s) associated with this public inbox

	https://git.savannah.gnu.org/cgit/emacs.git

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).