Annotation of src/usr.bin/less/charset.c, Revision 1.8
1.1 etheisen 1: /*
1.8 ! shadchin 2: * Copyright (C) 1984-2011 Mark Nudelman
1.1 etheisen 3: *
1.5 millert 4: * You may distribute under the terms of either the GNU General Public
5: * License or the Less License, as specified in the README file.
1.1 etheisen 6: *
1.5 millert 7: * For more information about less, or for information on how to
8: * contact the author, see the README file.
1.1 etheisen 9: */
10:
11:
12: /*
13: * Functions to define the character set
14: * and do things specific to the character set.
15: */
16:
17: #include "less.h"
18: #if HAVE_LOCALE
19: #include <locale.h>
20: #include <ctype.h>
1.8 ! shadchin 21: #include <langinfo.h>
1.1 etheisen 22: #endif
23:
1.8 ! shadchin 24: #include "charset.h"
! 25:
1.5 millert 26: public int utf_mode = 0;
27:
1.6 millert 28: #if !SMALL
1.1 etheisen 29: /*
30: * Predefined character sets,
31: * selected by the LESSCHARSET environment variable.
32: */
33: struct charset {
34: char *name;
1.5 millert 35: int *p_flag;
1.1 etheisen 36: char *desc;
37: } charsets[] = {
1.8 ! shadchin 38: { "ascii", NULL, "8bcccbcc18b95.b" },
! 39: { "utf-8", &utf_mode, "8bcccbcc18b95.b126.bb" },
! 40: { "iso8859", NULL, "8bcccbcc18b95.33b." },
! 41: { "latin3", NULL, "8bcccbcc18b95.33b5.b8.b15.b4.b12.b18.b12.b." },
! 42: { "arabic", NULL, "8bcccbcc18b95.33b.3b.7b2.13b.3b.b26.5b19.b" },
! 43: { "greek", NULL, "8bcccbcc18b95.33b4.2b4.b3.b35.b44.b" },
! 44: { "greek2005", NULL, "8bcccbcc18b95.33b14.b35.b44.b" },
! 45: { "hebrew", NULL, "8bcccbcc18b95.33b.b29.32b28.2b2.b" },
! 46: { "koi8-r", NULL, "8bcccbcc18b95.b." },
! 47: { "KOI8-T", NULL, "8bcccbcc18b95.b8.b6.b8.b.b.5b7.3b4.b4.b3.b.b.3b." },
! 48: { "georgianps", NULL, "8bcccbcc18b95.3b11.4b12.2b." },
! 49: { "tcvn", NULL, "b..b...bcccbccbbb7.8b95.b48.5b." },
! 50: { "TIS-620", NULL, "8bcccbcc18b95.b.4b.11b7.8b." },
! 51: { "next", NULL, "8bcccbcc18b95.bb125.bb" },
! 52: { "dos", NULL, "8bcccbcc12bc5b95.b." },
! 53: { "windows-1251", NULL, "8bcccbcc12bc5b95.b24.b." },
! 54: { "windows-1252", NULL, "8bcccbcc12bc5b95.b.b11.b.2b12.b." },
! 55: { "windows-1255", NULL, "8bcccbcc12bc5b95.b.b8.b.5b9.b.4b." },
! 56: { "ebcdic", NULL, "5bc6bcc7bcc41b.9b7.9b5.b..8b6.10b6.b9.7b9.8b8.17b3.3b9.7b9.8b8.6b10.b.b.b." },
! 57: { "IBM-1047", NULL, "4cbcbc3b9cbccbccbb4c6bcc5b3cbbc4bc4bccbc191.b" },
1.5 millert 58: { NULL, NULL, NULL }
59: };
60:
1.8 ! shadchin 61: /*
! 62: * Support "locale charmap"/nl_langinfo(CODESET) values, as well as others.
! 63: */
1.5 millert 64: struct cs_alias {
65: char *name;
66: char *oname;
67: } cs_aliases[] = {
1.8 ! shadchin 68: { "UTF-8", "utf-8" },
! 69: { "ANSI_X3.4-1968", "ascii" },
! 70: { "US-ASCII", "ascii" },
! 71: { "latin1", "iso8859" },
! 72: { "ISO-8859-1", "iso8859" },
! 73: { "latin9", "iso8859" },
! 74: { "ISO-8859-15", "iso8859" },
! 75: { "latin2", "iso8859" },
! 76: { "ISO-8859-2", "iso8859" },
! 77: { "ISO-8859-3", "latin3" },
! 78: { "latin4", "iso8859" },
! 79: { "ISO-8859-4", "iso8859" },
! 80: { "cyrillic", "iso8859" },
! 81: { "ISO-8859-5", "iso8859" },
! 82: { "ISO-8859-6", "arabic" },
! 83: { "ISO-8859-7", "greek" },
! 84: { "IBM9005", "greek2005" },
! 85: { "ISO-8859-8", "hebrew" },
! 86: { "latin5", "iso8859" },
! 87: { "ISO-8859-9", "iso8859" },
! 88: { "latin6", "iso8859" },
! 89: { "ISO-8859-10", "iso8859" },
! 90: { "latin7", "iso8859" },
! 91: { "ISO-8859-13", "iso8859" },
! 92: { "latin8", "iso8859" },
! 93: { "ISO-8859-14", "iso8859" },
! 94: { "latin10", "iso8859" },
! 95: { "ISO-8859-16", "iso8859" },
! 96: { "IBM437", "dos" },
! 97: { "EBCDIC-US", "ebcdic" },
! 98: { "IBM1047", "IBM-1047" },
! 99: { "KOI8-R", "koi8-r" },
! 100: { "KOI8-U", "koi8-r" },
! 101: { "GEORGIAN-PS", "georgianps" },
! 102: { "TCVN5712-1", "tcvn" },
! 103: { "NEXTSTEP", "next" },
! 104: { "windows", "windows-1252" }, /* backward compatibility */
! 105: { "CP1251", "windows-1251" },
! 106: { "CP1252", "windows-1252" },
! 107: { "CP1255", "windows-1255" },
1.5 millert 108: { NULL, NULL }
1.1 etheisen 109: };
110:
111: #define IS_BINARY_CHAR 01
112: #define IS_CONTROL_CHAR 02
113:
114: static char chardef[256];
115: static char *binfmt = NULL;
1.8 ! shadchin 116: static char *utfbinfmt = NULL;
1.1 etheisen 117: public int binattr = AT_STANDOUT;
118:
119:
120: /*
121: * Define a charset, given a description string.
122: * The string consists of 256 letters,
123: * one for each character in the charset.
124: * If the string is shorter than 256 letters, missing letters
125: * are taken to be identical to the last one.
126: * A decimal number followed by a letter is taken to be a
127: * repetition of the letter.
128: *
129: * Each letter is one of:
130: * . normal character
131: * b binary character
132: * c control character
133: */
134: static void
135: ichardef(s)
136: char *s;
137: {
1.5 millert 138: register char *cp;
139: register int n;
140: register char v;
1.1 etheisen 141:
142: n = 0;
143: v = 0;
144: cp = chardef;
145: while (*s != '\0')
146: {
147: switch (*s++)
148: {
149: case '.':
150: v = 0;
151: break;
152: case 'c':
153: v = IS_CONTROL_CHAR;
154: break;
155: case 'b':
156: v = IS_BINARY_CHAR|IS_CONTROL_CHAR;
157: break;
158:
159: case '0': case '1': case '2': case '3': case '4':
160: case '5': case '6': case '7': case '8': case '9':
161: n = (10 * n) + (s[-1] - '0');
162: continue;
163:
164: default:
165: error("invalid chardef", NULL_PARG);
166: quit(QUIT_ERROR);
167: /*NOTREACHED*/
168: }
169:
170: do
171: {
172: if (cp >= chardef + sizeof(chardef))
173: {
174: error("chardef longer than 256", NULL_PARG);
175: quit(QUIT_ERROR);
176: /*NOTREACHED*/
177: }
178: *cp++ = v;
179: } while (--n > 0);
180: n = 0;
181: }
182:
183: while (cp < chardef + sizeof(chardef))
184: *cp++ = v;
185: }
186:
187: /*
188: * Define a charset, given a charset name.
189: * The valid charset names are listed in the "charsets" array.
190: */
191: static int
1.8 ! shadchin 192: icharset(name, no_error)
1.5 millert 193: register char *name;
1.8 ! shadchin 194: int no_error;
1.1 etheisen 195: {
1.5 millert 196: register struct charset *p;
197: register struct cs_alias *a;
1.1 etheisen 198:
199: if (name == NULL || *name == '\0')
200: return (0);
201:
1.5 millert 202: /* First see if the name is an alias. */
203: for (a = cs_aliases; a->name != NULL; a++)
204: {
205: if (strcmp(name, a->name) == 0)
206: {
207: name = a->oname;
208: break;
209: }
210: }
211:
1.1 etheisen 212: for (p = charsets; p->name != NULL; p++)
213: {
214: if (strcmp(name, p->name) == 0)
215: {
216: ichardef(p->desc);
1.5 millert 217: if (p->p_flag != NULL)
218: *(p->p_flag) = 1;
1.1 etheisen 219: return (1);
220: }
221: }
222:
1.8 ! shadchin 223: if (!no_error) {
! 224: error("invalid charset name", NULL_PARG);
! 225: quit(QUIT_ERROR);
! 226: }
1.5 millert 227: return (0);
1.1 etheisen 228: }
229:
230: #if HAVE_LOCALE
231: /*
232: * Define a charset, given a locale name.
233: */
234: static void
235: ilocale()
236: {
1.5 millert 237: register int c;
1.1 etheisen 238:
1.5 millert 239: for (c = 0; c < (int) sizeof(chardef); c++)
1.1 etheisen 240: {
241: if (isprint(c))
242: chardef[c] = 0;
243: else if (iscntrl(c))
244: chardef[c] = IS_CONTROL_CHAR;
245: else
246: chardef[c] = IS_BINARY_CHAR|IS_CONTROL_CHAR;
247: }
248: }
249: #endif
250:
251: /*
1.8 ! shadchin 252: * Define the printing format for control (or binary utf) chars.
1.1 etheisen 253: */
1.8 ! shadchin 254: static void
! 255: setbinfmt(s, fmtvarptr, default_fmt)
1.1 etheisen 256: char *s;
1.8 ! shadchin 257: char **fmtvarptr;
! 258: char *default_fmt;
1.1 etheisen 259: {
1.8 ! shadchin 260: if (s && utf_mode)
! 261: {
! 262: /* It would be too hard to account for width otherwise. */
! 263: char *t = s;
! 264: while (*t)
! 265: {
! 266: if (*t < ' ' || *t > '~')
! 267: {
! 268: s = default_fmt;
! 269: goto attr;
! 270: }
! 271: t++;
! 272: }
! 273: }
! 274:
! 275: /* %n is evil */
! 276: if (s == NULL || *s == '\0' ||
! 277: (*s == '*' && (s[1] == '\0' || s[2] == '\0' || strchr(s + 2, 'n'))) ||
! 278: (*s != '*' && strchr(s, 'n')))
! 279: s = default_fmt;
! 280:
1.1 etheisen 281: /*
282: * Select the attributes if it starts with "*".
283: */
1.8 ! shadchin 284: attr:
1.1 etheisen 285: if (*s == '*')
286: {
287: switch (s[1])
288: {
289: case 'd': binattr = AT_BOLD; break;
290: case 'k': binattr = AT_BLINK; break;
291: case 's': binattr = AT_STANDOUT; break;
292: case 'u': binattr = AT_UNDERLINE; break;
293: default: binattr = AT_NORMAL; break;
294: }
295: s += 2;
296: }
1.8 ! shadchin 297: *fmtvarptr = s;
1.1 etheisen 298: }
299:
300: /*
1.8 ! shadchin 301: *
1.1 etheisen 302: */
1.8 ! shadchin 303: static void
! 304: set_charset()
1.1 etheisen 305: {
1.8 ! shadchin 306: char *s;
1.1 etheisen 307:
308: /*
309: * See if environment variable LESSCHARSET is defined.
310: */
1.5 millert 311: s = lgetenv("LESSCHARSET");
1.8 ! shadchin 312: if (icharset(s, 0))
1.1 etheisen 313: return;
1.8 ! shadchin 314:
1.1 etheisen 315: /*
316: * LESSCHARSET is not defined: try LESSCHARDEF.
317: */
1.5 millert 318: s = lgetenv("LESSCHARDEF");
1.1 etheisen 319: if (s != NULL && *s != '\0')
320: {
321: ichardef(s);
322: return;
323: }
1.5 millert 324:
1.8 ! shadchin 325: #if HAVE_LOCALE
! 326: #ifdef CODESET
! 327: /*
! 328: * Try using the codeset name as the charset name.
! 329: */
! 330: s = nl_langinfo(CODESET);
! 331: if (icharset(s, 1))
! 332: return;
! 333: #endif
! 334: #endif
! 335:
1.5 millert 336: #if HAVE_STRSTR
337: /*
338: * Check whether LC_ALL, LC_CTYPE or LANG look like UTF-8 is used.
339: */
340: if ((s = lgetenv("LC_ALL")) != NULL ||
341: (s = lgetenv("LC_CTYPE")) != NULL ||
342: (s = lgetenv("LANG")) != NULL)
343: {
1.8 ! shadchin 344: if ( strstr(s, "UTF-8") != NULL || strstr(s, "utf-8") != NULL
! 345: || strstr(s, "UTF8") != NULL || strstr(s, "utf8") != NULL)
! 346: if (icharset("utf-8", 1))
1.5 millert 347: return;
348: }
349: #endif
350:
1.1 etheisen 351: #if HAVE_LOCALE
352: /*
1.8 ! shadchin 353: * Get character definitions from locale functions,
! 354: * rather than from predefined charset entry.
1.1 etheisen 355: */
356: ilocale();
1.5 millert 357: #if MSDOS_COMPILER
1.1 etheisen 358: /*
1.5 millert 359: * Default to "dos".
1.1 etheisen 360: */
1.8 ! shadchin 361: (void) icharset("dos", 1);
1.5 millert 362: #else
363: /*
364: * Default to "latin1".
365: */
1.8 ! shadchin 366: (void) icharset("latin1", 1);
1.5 millert 367: #endif
1.1 etheisen 368: #endif
369: }
370:
371: /*
1.8 ! shadchin 372: * Initialize charset data structures.
! 373: */
! 374: public void
! 375: init_charset()
! 376: {
! 377: char *s;
! 378:
! 379: #if HAVE_LOCALE
! 380: setlocale(LC_ALL, "");
! 381: #endif
! 382:
! 383: set_charset();
! 384:
! 385: s = lgetenv("LESSBINFMT");
! 386: setbinfmt(s, &binfmt, "*s<%02X>");
! 387:
! 388: s = lgetenv("LESSUTFBINFMT");
! 389: setbinfmt(s, &utfbinfmt, "<U+%04lX>");
! 390: }
! 391:
! 392: /*
1.1 etheisen 393: * Is a given character a "binary" character?
394: */
395: public int
396: binary_char(c)
1.8 ! shadchin 397: LWCHAR c;
1.1 etheisen 398: {
1.8 ! shadchin 399: if (utf_mode)
! 400: return (is_ubin_char(c));
1.1 etheisen 401: c &= 0377;
402: return (chardef[c] & IS_BINARY_CHAR);
403: }
404:
405: /*
406: * Is a given character a "control" character?
407: */
408: public int
409: control_char(c)
1.8 ! shadchin 410: LWCHAR c;
1.1 etheisen 411: {
412: c &= 0377;
413: return (chardef[c] & IS_CONTROL_CHAR);
414: }
415:
416: /*
417: * Return the printable form of a character.
418: * For example, in the "ascii" charset '\3' is printed as "^C".
419: */
420: public char *
421: prchar(c)
1.8 ! shadchin 422: LWCHAR c;
1.1 etheisen 423: {
1.8 ! shadchin 424: /* {{ This buffer can be overrun if LESSBINFMT is a long string. }} */
! 425: static char buf[32];
1.1 etheisen 426:
427: c &= 0377;
1.8 ! shadchin 428: if ((c < 128 || !utf_mode) && !control_char(c))
! 429: SNPRINTF1(buf, sizeof(buf), "%c", (int) c);
1.1 etheisen 430: else if (c == ESC)
1.5 millert 431: snprintf(buf, sizeof(buf), "ESC");
432: #if IS_EBCDIC_HOST
433: else if (!binary_char(c) && c < 64)
1.8 ! shadchin 434: SNPRINTF1(buf, sizeof(buf), "^%c",
1.5 millert 435: /*
436: * This array roughly inverts CONTROL() #defined in less.h,
437: * and should be kept in sync with CONTROL() and IBM-1047.
438: */
439: "@ABC.I.?...KLMNO"
440: "PQRS.JH.XY.."
441: "\\]^_"
442: "......W[.....EFG"
443: "..V....D....TU.Z"[c]);
444: #else
445: else if (c < 128 && !control_char(c ^ 0100))
1.8 ! shadchin 446: SNPRINTF1(buf, sizeof(buf), "^%c", (int) (c ^ 0100));
1.5 millert 447: #endif
1.1 etheisen 448: else
1.8 ! shadchin 449: SNPRINTF1(buf, sizeof(buf), binfmt, c);
! 450: return (buf);
! 451: }
! 452:
! 453: /*
! 454: * Return the printable form of a UTF-8 character.
! 455: */
! 456: public char *
! 457: prutfchar(ch)
! 458: LWCHAR ch;
! 459: {
! 460: static char buf[32];
! 461:
! 462: if (ch == ESC)
! 463: strlcpy(buf, "ESC", sizeof(buf));
! 464: else if (ch < 128 && control_char(ch))
! 465: {
! 466: if (!control_char(ch ^ 0100))
! 467: SNPRINTF1(buf, sizeof(buf), "^%c", ((char) ch) ^ 0100);
! 468: else
! 469: SNPRINTF1(buf, sizeof(buf), binfmt, (char) ch);
! 470: } else if (is_ubin_char(ch))
! 471: SNPRINTF1(buf, sizeof(buf), utfbinfmt, ch);
! 472: else
! 473: {
! 474: int len;
! 475: if (ch >= 0x80000000)
! 476: {
! 477: len = 3;
! 478: ch = 0xFFFD;
! 479: } else
! 480: {
! 481: len = (ch < 0x80) ? 1
! 482: : (ch < 0x800) ? 2
! 483: : (ch < 0x10000) ? 3
! 484: : (ch < 0x200000) ? 4
! 485: : (ch < 0x4000000) ? 5
! 486: : 6;
! 487: }
! 488: buf[len] = '\0';
! 489: if (len == 1)
! 490: *buf = (char) ch;
! 491: else
! 492: {
! 493: *buf = ((1 << len) - 1) << (8 - len);
! 494: while (--len > 0)
! 495: {
! 496: buf[len] = (char) (0x80 | (ch & 0x3F));
! 497: ch >>= 6;
! 498: }
! 499: *buf |= ch;
! 500: }
! 501: }
1.1 etheisen 502: return (buf);
503: }
1.6 millert 504:
1.8 ! shadchin 505: /*
! 506: * Get the length of a UTF-8 character in bytes.
! 507: */
! 508: public int
! 509: utf_len(ch)
! 510: char ch;
! 511: {
! 512: if ((ch & 0x80) == 0)
! 513: return 1;
! 514: if ((ch & 0xE0) == 0xC0)
! 515: return 2;
! 516: if ((ch & 0xF0) == 0xE0)
! 517: return 3;
! 518: if ((ch & 0xF8) == 0xF0)
! 519: return 4;
! 520: if ((ch & 0xFC) == 0xF8)
! 521: return 5;
! 522: if ((ch & 0xFE) == 0xFC)
! 523: return 6;
! 524: /* Invalid UTF-8 encoding. */
! 525: return 1;
! 526: }
! 527:
! 528: /*
! 529: * Is a UTF-8 character well-formed?
! 530: */
! 531: public int
! 532: is_utf8_well_formed(s)
! 533: unsigned char *s;
! 534: {
! 535: int i;
! 536: int len;
! 537:
! 538: if (IS_UTF8_INVALID(s[0]))
! 539: return (0);
! 540:
! 541: len = utf_len((char) s[0]);
! 542: if (len == 1)
! 543: return (1);
! 544: if (len == 2)
! 545: {
! 546: if (s[0] < 0xC2)
! 547: return (0);
! 548: } else
! 549: {
! 550: unsigned char mask;
! 551: mask = (~((1 << (8-len)) - 1)) & 0xFF;
! 552: if (s[0] == mask && (s[1] & mask) == 0x80)
! 553: return (0);
! 554: }
! 555:
! 556: for (i = 1; i < len; i++)
! 557: if (!IS_UTF8_TRAIL(s[i]))
! 558: return (0);
! 559: return (1);
! 560: }
! 561:
! 562: /*
! 563: * Get the value of a UTF-8 character.
! 564: */
! 565: public LWCHAR
! 566: get_wchar(p)
! 567: char *p;
! 568: {
! 569: switch (utf_len(p[0]))
! 570: {
! 571: case 1:
! 572: default:
! 573: /* 0xxxxxxx */
! 574: return (LWCHAR)
! 575: (p[0] & 0xFF);
! 576: case 2:
! 577: /* 110xxxxx 10xxxxxx */
! 578: return (LWCHAR) (
! 579: ((p[0] & 0x1F) << 6) |
! 580: (p[1] & 0x3F));
! 581: case 3:
! 582: /* 1110xxxx 10xxxxxx 10xxxxxx */
! 583: return (LWCHAR) (
! 584: ((p[0] & 0x0F) << 12) |
! 585: ((p[1] & 0x3F) << 6) |
! 586: (p[2] & 0x3F));
! 587: case 4:
! 588: /* 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx */
! 589: return (LWCHAR) (
! 590: ((p[0] & 0x07) << 18) |
! 591: ((p[1] & 0x3F) << 12) |
! 592: ((p[2] & 0x3F) << 6) |
! 593: (p[3] & 0x3F));
! 594: case 5:
! 595: /* 111110xx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx */
! 596: return (LWCHAR) (
! 597: ((p[0] & 0x03) << 24) |
! 598: ((p[1] & 0x3F) << 18) |
! 599: ((p[2] & 0x3F) << 12) |
! 600: ((p[3] & 0x3F) << 6) |
! 601: (p[4] & 0x3F));
! 602: case 6:
! 603: /* 1111110x 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx */
! 604: return (LWCHAR) (
! 605: ((p[0] & 0x01) << 30) |
! 606: ((p[1] & 0x3F) << 24) |
! 607: ((p[2] & 0x3F) << 18) |
! 608: ((p[3] & 0x3F) << 12) |
! 609: ((p[4] & 0x3F) << 6) |
! 610: (p[5] & 0x3F));
! 611: }
! 612: }
! 613:
! 614: /*
! 615: * Store a character into a UTF-8 string.
! 616: */
! 617: public void
! 618: put_wchar(pp, ch)
! 619: char **pp;
! 620: LWCHAR ch;
! 621: {
! 622: if (!utf_mode || ch < 0x80)
! 623: {
! 624: /* 0xxxxxxx */
! 625: *(*pp)++ = (char) ch;
! 626: } else if (ch < 0x800)
! 627: {
! 628: /* 110xxxxx 10xxxxxx */
! 629: *(*pp)++ = (char) (0xC0 | ((ch >> 6) & 0x1F));
! 630: *(*pp)++ = (char) (0x80 | (ch & 0x3F));
! 631: } else if (ch < 0x10000)
! 632: {
! 633: /* 1110xxxx 10xxxxxx 10xxxxxx */
! 634: *(*pp)++ = (char) (0xE0 | ((ch >> 12) & 0x0F));
! 635: *(*pp)++ = (char) (0x80 | ((ch >> 6) & 0x3F));
! 636: *(*pp)++ = (char) (0x80 | (ch & 0x3F));
! 637: } else if (ch < 0x200000)
! 638: {
! 639: /* 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx */
! 640: *(*pp)++ = (char) (0xF0 | ((ch >> 18) & 0x07));
! 641: *(*pp)++ = (char) (0x80 | ((ch >> 12) & 0x3F));
! 642: *(*pp)++ = (char) (0x80 | ((ch >> 6) & 0x3F));
! 643: *(*pp)++ = (char) (0x80 | (ch & 0x3F));
! 644: } else if (ch < 0x4000000)
! 645: {
! 646: /* 111110xx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx */
! 647: *(*pp)++ = (char) (0xF0 | ((ch >> 24) & 0x03));
! 648: *(*pp)++ = (char) (0x80 | ((ch >> 18) & 0x3F));
! 649: *(*pp)++ = (char) (0x80 | ((ch >> 12) & 0x3F));
! 650: *(*pp)++ = (char) (0x80 | ((ch >> 6) & 0x3F));
! 651: *(*pp)++ = (char) (0x80 | (ch & 0x3F));
! 652: } else
! 653: {
! 654: /* 1111110x 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx */
! 655: *(*pp)++ = (char) (0xF0 | ((ch >> 30) & 0x01));
! 656: *(*pp)++ = (char) (0x80 | ((ch >> 24) & 0x3F));
! 657: *(*pp)++ = (char) (0x80 | ((ch >> 18) & 0x3F));
! 658: *(*pp)++ = (char) (0x80 | ((ch >> 12) & 0x3F));
! 659: *(*pp)++ = (char) (0x80 | ((ch >> 6) & 0x3F));
! 660: *(*pp)++ = (char) (0x80 | (ch & 0x3F));
! 661: }
! 662: }
! 663:
! 664: /*
! 665: * Step forward or backward one character in a string.
! 666: */
! 667: public LWCHAR
! 668: step_char(pp, dir, limit)
! 669: char **pp;
! 670: signed int dir;
! 671: char *limit;
! 672: {
! 673: LWCHAR ch;
! 674: int len;
! 675: char *p = *pp;
! 676:
! 677: if (!utf_mode)
! 678: {
! 679: /* It's easy if chars are one byte. */
! 680: if (dir > 0)
! 681: ch = (LWCHAR) ((p < limit) ? *p++ : 0);
! 682: else
! 683: ch = (LWCHAR) ((p > limit) ? *--p : 0);
! 684: } else if (dir > 0)
! 685: {
! 686: len = utf_len(*p);
! 687: if (p + len > limit)
! 688: {
! 689: ch = 0;
! 690: p = limit;
! 691: } else
! 692: {
! 693: ch = get_wchar(p);
! 694: p += len;
! 695: }
! 696: } else
! 697: {
! 698: while (p > limit && IS_UTF8_TRAIL(p[-1]))
! 699: p--;
! 700: if (p > limit)
! 701: ch = get_wchar(--p);
! 702: else
! 703: ch = 0;
! 704: }
! 705: *pp = p;
! 706: return ch;
! 707: }
! 708:
! 709: /*
! 710: * Unicode characters data
! 711: */
! 712: struct wchar_range { LWCHAR first, last; };
! 713:
! 714: /*
! 715: * Characters with general category values
! 716: * Mn: Mark, Nonspacing
! 717: * Me: Mark, Enclosing
! 718: * Last synched with
! 719: * <http://www.unicode.org/Public/5.0.0/ucd/UnicodeData-5.0.0d7.txt>
! 720: * dated 2005-11-30T00:58:48Z
! 721: */
! 722: static struct wchar_range comp_table[] = {
! 723: { 0x0300, 0x036F} /* Mn */, { 0x0483, 0x0486} /* Mn */,
! 724: { 0x0488, 0x0489} /* Me */,
! 725: { 0x0591, 0x05BD} /* Mn */, { 0x05BF, 0x05BF} /* Mn */,
! 726: { 0x05C1, 0x05C2} /* Mn */, { 0x05C4, 0x05C5} /* Mn */,
! 727: { 0x05C7, 0x05C7} /* Mn */, { 0x0610, 0x0615} /* Mn */,
! 728: { 0x064B, 0x065E} /* Mn */, { 0x0670, 0x0670} /* Mn */,
! 729: { 0x06D6, 0x06DC} /* Mn */,
! 730: { 0x06DE, 0x06DE} /* Me */,
! 731: { 0x06DF, 0x06E4} /* Mn */, { 0x06E7, 0x06E8} /* Mn */,
! 732: { 0x06EA, 0x06ED} /* Mn */, { 0x0711, 0x0711} /* Mn */,
! 733: { 0x0730, 0x074A} /* Mn */, { 0x07A6, 0x07B0} /* Mn */,
! 734: { 0x07EB, 0x07F3} /* Mn */, { 0x0901, 0x0902} /* Mn */,
! 735: { 0x093C, 0x093C} /* Mn */, { 0x0941, 0x0948} /* Mn */,
! 736: { 0x094D, 0x094D} /* Mn */, { 0x0951, 0x0954} /* Mn */,
! 737: { 0x0962, 0x0963} /* Mn */, { 0x0981, 0x0981} /* Mn */,
! 738: { 0x09BC, 0x09BC} /* Mn */, { 0x09C1, 0x09C4} /* Mn */,
! 739: { 0x09CD, 0x09CD} /* Mn */, { 0x09E2, 0x09E3} /* Mn */,
! 740: { 0x0A01, 0x0A02} /* Mn */, { 0x0A3C, 0x0A3C} /* Mn */,
! 741: { 0x0A41, 0x0A42} /* Mn */, { 0x0A47, 0x0A48} /* Mn */,
! 742: { 0x0A4B, 0x0A4D} /* Mn */, { 0x0A70, 0x0A71} /* Mn */,
! 743: { 0x0A81, 0x0A82} /* Mn */, { 0x0ABC, 0x0ABC} /* Mn */,
! 744: { 0x0AC1, 0x0AC5} /* Mn */, { 0x0AC7, 0x0AC8} /* Mn */,
! 745: { 0x0ACD, 0x0ACD} /* Mn */, { 0x0AE2, 0x0AE3} /* Mn */,
! 746: { 0x0B01, 0x0B01} /* Mn */, { 0x0B3C, 0x0B3C} /* Mn */,
! 747: { 0x0B3F, 0x0B3F} /* Mn */, { 0x0B41, 0x0B43} /* Mn */,
! 748: { 0x0B4D, 0x0B4D} /* Mn */, { 0x0B56, 0x0B56} /* Mn */,
! 749: { 0x0B82, 0x0B82} /* Mn */, { 0x0BC0, 0x0BC0} /* Mn */,
! 750: { 0x0BCD, 0x0BCD} /* Mn */, { 0x0C3E, 0x0C40} /* Mn */,
! 751: { 0x0C46, 0x0C48} /* Mn */, { 0x0C4A, 0x0C4D} /* Mn */,
! 752: { 0x0C55, 0x0C56} /* Mn */, { 0x0CBC, 0x0CBC} /* Mn */,
! 753: { 0x0CBF, 0x0CBF} /* Mn */, { 0x0CC6, 0x0CC6} /* Mn */,
! 754: { 0x0CCC, 0x0CCD} /* Mn */, { 0x0CE2, 0x0CE3} /* Mn */,
! 755: { 0x0D41, 0x0D43} /* Mn */, { 0x0D4D, 0x0D4D} /* Mn */,
! 756: { 0x0DCA, 0x0DCA} /* Mn */, { 0x0DD2, 0x0DD4} /* Mn */,
! 757: { 0x0DD6, 0x0DD6} /* Mn */, { 0x0E31, 0x0E31} /* Mn */,
! 758: { 0x0E34, 0x0E3A} /* Mn */, { 0x0E47, 0x0E4E} /* Mn */,
! 759: { 0x0EB1, 0x0EB1} /* Mn */, { 0x0EB4, 0x0EB9} /* Mn */,
! 760: { 0x0EBB, 0x0EBC} /* Mn */, { 0x0EC8, 0x0ECD} /* Mn */,
! 761: { 0x0F18, 0x0F19} /* Mn */, { 0x0F35, 0x0F35} /* Mn */,
! 762: { 0x0F37, 0x0F37} /* Mn */, { 0x0F39, 0x0F39} /* Mn */,
! 763: { 0x0F71, 0x0F7E} /* Mn */, { 0x0F80, 0x0F84} /* Mn */,
! 764: { 0x0F86, 0x0F87} /* Mn */, { 0x0F90, 0x0F97} /* Mn */,
! 765: { 0x0F99, 0x0FBC} /* Mn */, { 0x0FC6, 0x0FC6} /* Mn */,
! 766: { 0x102D, 0x1030} /* Mn */, { 0x1032, 0x1032} /* Mn */,
! 767: { 0x1036, 0x1037} /* Mn */, { 0x1039, 0x1039} /* Mn */,
! 768: { 0x1058, 0x1059} /* Mn */, { 0x135F, 0x135F} /* Mn */,
! 769: { 0x1712, 0x1714} /* Mn */, { 0x1732, 0x1734} /* Mn */,
! 770: { 0x1752, 0x1753} /* Mn */, { 0x1772, 0x1773} /* Mn */,
! 771: { 0x17B7, 0x17BD} /* Mn */, { 0x17C6, 0x17C6} /* Mn */,
! 772: { 0x17C9, 0x17D3} /* Mn */, { 0x17DD, 0x17DD} /* Mn */,
! 773: { 0x180B, 0x180D} /* Mn */, { 0x18A9, 0x18A9} /* Mn */,
! 774: { 0x1920, 0x1922} /* Mn */, { 0x1927, 0x1928} /* Mn */,
! 775: { 0x1932, 0x1932} /* Mn */, { 0x1939, 0x193B} /* Mn */,
! 776: { 0x1A17, 0x1A18} /* Mn */, { 0x1B00, 0x1B03} /* Mn */,
! 777: { 0x1B34, 0x1B34} /* Mn */, { 0x1B36, 0x1B3A} /* Mn */,
! 778: { 0x1B3C, 0x1B3C} /* Mn */, { 0x1B42, 0x1B42} /* Mn */,
! 779: { 0x1B6B, 0x1B73} /* Mn */, { 0x1DC0, 0x1DCA} /* Mn */,
! 780: { 0x1DFE, 0x1DFF} /* Mn */, { 0x20D0, 0x20DC} /* Mn */,
! 781: { 0x20DD, 0x20E0} /* Me */,
! 782: { 0x20E1, 0x20E1} /* Mn */,
! 783: { 0x20E2, 0x20E4} /* Me */,
! 784: { 0x20E5, 0x20EF} /* Mn */, { 0x302A, 0x302F} /* Mn */,
! 785: { 0x3099, 0x309A} /* Mn */, { 0xA806, 0xA806} /* Mn */,
! 786: { 0xA80B, 0xA80B} /* Mn */, { 0xA825, 0xA826} /* Mn */,
! 787: { 0xFB1E, 0xFB1E} /* Mn */, { 0xFE00, 0xFE0F} /* Mn */,
! 788: { 0xFE20, 0xFE23} /* Mn */, { 0x10A01, 0x10A03} /* Mn */,
! 789: { 0x10A05, 0x10A06} /* Mn */, { 0x10A0C, 0x10A0F} /* Mn */,
! 790: { 0x10A38, 0x10A3A} /* Mn */, { 0x10A3F, 0x10A3F} /* Mn */,
! 791: { 0x1D167, 0x1D169} /* Mn */, { 0x1D17B, 0x1D182} /* Mn */,
! 792: { 0x1D185, 0x1D18B} /* Mn */, { 0x1D1AA, 0x1D1AD} /* Mn */,
! 793: { 0x1D242, 0x1D244} /* Mn */, { 0xE0100, 0xE01EF} /* Mn */,
! 794: };
! 795:
! 796: /*
! 797: * Special pairs, not ranges.
! 798: */
! 799: static struct wchar_range comb_table[] = {
! 800: {0x0644,0x0622}, {0x0644,0x0623}, {0x0644,0x0625}, {0x0644,0x0627},
! 801: };
! 802:
! 803: /*
! 804: * Characters with general category values
! 805: * Cc: Other, Control
! 806: * Cf: Other, Format
! 807: * Cs: Other, Surrogate
! 808: * Co: Other, Private Use
! 809: * Cn: Other, Not Assigned
! 810: * Zl: Separator, Line
! 811: * Zp: Separator, Paragraph
! 812: * Last synched with
! 813: * <http://www.unicode.org/Public/5.0.0/ucd/UnicodeData-5.0.0d7.txt>
! 814: * dated 2005-11-30T00:58:48Z
! 815: */
! 816: static struct wchar_range ubin_table[] = {
! 817: { 0x0000, 0x0007} /* Cc */,
! 818: { 0x000B, 0x000C} /* Cc */,
! 819: { 0x000E, 0x001A} /* Cc */,
! 820: { 0x001C, 0x001F} /* Cc */,
! 821: { 0x007F, 0x009F} /* Cc */,
! 822: #if 0
! 823: { 0x00AD, 0x00AD} /* Cf */,
! 824: #endif
! 825: { 0x0370, 0x0373} /* Cn */, { 0x0376, 0x0379} /* Cn */,
! 826: { 0x037F, 0x0383} /* Cn */, { 0x038B, 0x038B} /* Cn */,
! 827: { 0x038D, 0x038D} /* Cn */, { 0x03A2, 0x03A2} /* Cn */,
! 828: { 0x03CF, 0x03CF} /* Cn */, { 0x0487, 0x0487} /* Cn */,
! 829: { 0x0514, 0x0530} /* Cn */, { 0x0557, 0x0558} /* Cn */,
! 830: { 0x0560, 0x0560} /* Cn */, { 0x0588, 0x0588} /* Cn */,
! 831: { 0x058B, 0x0590} /* Cn */, { 0x05C8, 0x05CF} /* Cn */,
! 832: { 0x05EB, 0x05EF} /* Cn */, { 0x05F5, 0x05FF} /* Cn */,
! 833: #if 0
! 834: { 0x0600, 0x0603} /* Cf */,
! 835: #endif
! 836: { 0x0604, 0x060A} /* Cn */, { 0x0616, 0x061A} /* Cn */,
! 837: { 0x061C, 0x061D} /* Cn */, { 0x0620, 0x0620} /* Cn */,
! 838: { 0x063B, 0x063F} /* Cn */, { 0x065F, 0x065F} /* Cn */,
! 839: #if 0
! 840: { 0x06DD, 0x06DD} /* Cf */,
! 841: #endif
! 842: { 0x070E, 0x070E} /* Cn */,
! 843: #if 0
! 844: { 0x070F, 0x070F} /* Cf */,
! 845: #endif
! 846: { 0x074B, 0x074C} /* Cn */, { 0x076E, 0x077F} /* Cn */,
! 847: { 0x07B2, 0x07BF} /* Cn */, { 0x07FB, 0x0900} /* Cn */,
! 848: { 0x093A, 0x093B} /* Cn */, { 0x094E, 0x094F} /* Cn */,
! 849: { 0x0955, 0x0957} /* Cn */, { 0x0971, 0x097A} /* Cn */,
! 850: { 0x0980, 0x0980} /* Cn */, { 0x0984, 0x0984} /* Cn */,
! 851: { 0x098D, 0x098E} /* Cn */, { 0x0991, 0x0992} /* Cn */,
! 852: { 0x09A9, 0x09A9} /* Cn */, { 0x09B1, 0x09B1} /* Cn */,
! 853: { 0x09B3, 0x09B5} /* Cn */, { 0x09BA, 0x09BB} /* Cn */,
! 854: { 0x09C5, 0x09C6} /* Cn */, { 0x09C9, 0x09CA} /* Cn */,
! 855: { 0x09CF, 0x09D6} /* Cn */, { 0x09D8, 0x09DB} /* Cn */,
! 856: { 0x09DE, 0x09DE} /* Cn */, { 0x09E4, 0x09E5} /* Cn */,
! 857: { 0x09FB, 0x0A00} /* Cn */, { 0x0A04, 0x0A04} /* Cn */,
! 858: { 0x0A0B, 0x0A0E} /* Cn */, { 0x0A11, 0x0A12} /* Cn */,
! 859: { 0x0A29, 0x0A29} /* Cn */, { 0x0A31, 0x0A31} /* Cn */,
! 860: { 0x0A34, 0x0A34} /* Cn */, { 0x0A37, 0x0A37} /* Cn */,
! 861: { 0x0A3A, 0x0A3B} /* Cn */, { 0x0A3D, 0x0A3D} /* Cn */,
! 862: { 0x0A43, 0x0A46} /* Cn */, { 0x0A49, 0x0A4A} /* Cn */,
! 863: { 0x0A4E, 0x0A58} /* Cn */, { 0x0A5D, 0x0A5D} /* Cn */,
! 864: { 0x0A5F, 0x0A65} /* Cn */, { 0x0A75, 0x0A80} /* Cn */,
! 865: { 0x0A84, 0x0A84} /* Cn */, { 0x0A8E, 0x0A8E} /* Cn */,
! 866: { 0x0A92, 0x0A92} /* Cn */, { 0x0AA9, 0x0AA9} /* Cn */,
! 867: { 0x0AB1, 0x0AB1} /* Cn */, { 0x0AB4, 0x0AB4} /* Cn */,
! 868: { 0x0ABA, 0x0ABB} /* Cn */, { 0x0AC6, 0x0AC6} /* Cn */,
! 869: { 0x0ACA, 0x0ACA} /* Cn */, { 0x0ACE, 0x0ACF} /* Cn */,
! 870: { 0x0AD1, 0x0ADF} /* Cn */, { 0x0AE4, 0x0AE5} /* Cn */,
! 871: { 0x0AF0, 0x0AF0} /* Cn */, { 0x0AF2, 0x0B00} /* Cn */,
! 872: { 0x0B04, 0x0B04} /* Cn */, { 0x0B0D, 0x0B0E} /* Cn */,
! 873: { 0x0B11, 0x0B12} /* Cn */, { 0x0B29, 0x0B29} /* Cn */,
! 874: { 0x0B31, 0x0B31} /* Cn */, { 0x0B34, 0x0B34} /* Cn */,
! 875: { 0x0B3A, 0x0B3B} /* Cn */, { 0x0B44, 0x0B46} /* Cn */,
! 876: { 0x0B49, 0x0B4A} /* Cn */, { 0x0B4E, 0x0B55} /* Cn */,
! 877: { 0x0B58, 0x0B5B} /* Cn */, { 0x0B5E, 0x0B5E} /* Cn */,
! 878: { 0x0B62, 0x0B65} /* Cn */, { 0x0B72, 0x0B81} /* Cn */,
! 879: { 0x0B84, 0x0B84} /* Cn */, { 0x0B8B, 0x0B8D} /* Cn */,
! 880: { 0x0B91, 0x0B91} /* Cn */, { 0x0B96, 0x0B98} /* Cn */,
! 881: { 0x0B9B, 0x0B9B} /* Cn */, { 0x0B9D, 0x0B9D} /* Cn */,
! 882: { 0x0BA0, 0x0BA2} /* Cn */, { 0x0BA5, 0x0BA7} /* Cn */,
! 883: { 0x0BAB, 0x0BAD} /* Cn */, { 0x0BBA, 0x0BBD} /* Cn */,
! 884: { 0x0BC3, 0x0BC5} /* Cn */, { 0x0BC9, 0x0BC9} /* Cn */,
! 885: { 0x0BCE, 0x0BD6} /* Cn */, { 0x0BD8, 0x0BE5} /* Cn */,
! 886: { 0x0BFB, 0x0C00} /* Cn */, { 0x0C04, 0x0C04} /* Cn */,
! 887: { 0x0C0D, 0x0C0D} /* Cn */, { 0x0C11, 0x0C11} /* Cn */,
! 888: { 0x0C29, 0x0C29} /* Cn */, { 0x0C34, 0x0C34} /* Cn */,
! 889: { 0x0C3A, 0x0C3D} /* Cn */, { 0x0C45, 0x0C45} /* Cn */,
! 890: { 0x0C49, 0x0C49} /* Cn */, { 0x0C4E, 0x0C54} /* Cn */,
! 891: { 0x0C57, 0x0C5F} /* Cn */, { 0x0C62, 0x0C65} /* Cn */,
! 892: { 0x0C70, 0x0C81} /* Cn */, { 0x0C84, 0x0C84} /* Cn */,
! 893: { 0x0C8D, 0x0C8D} /* Cn */, { 0x0C91, 0x0C91} /* Cn */,
! 894: { 0x0CA9, 0x0CA9} /* Cn */, { 0x0CB4, 0x0CB4} /* Cn */,
! 895: { 0x0CBA, 0x0CBB} /* Cn */, { 0x0CC5, 0x0CC5} /* Cn */,
! 896: { 0x0CC9, 0x0CC9} /* Cn */, { 0x0CCE, 0x0CD4} /* Cn */,
! 897: { 0x0CD7, 0x0CDD} /* Cn */, { 0x0CDF, 0x0CDF} /* Cn */,
! 898: { 0x0CE4, 0x0CE5} /* Cn */, { 0x0CF0, 0x0CF0} /* Cn */,
! 899: { 0x0CF3, 0x0D01} /* Cn */, { 0x0D04, 0x0D04} /* Cn */,
! 900: { 0x0D0D, 0x0D0D} /* Cn */, { 0x0D11, 0x0D11} /* Cn */,
! 901: { 0x0D29, 0x0D29} /* Cn */, { 0x0D3A, 0x0D3D} /* Cn */,
! 902: { 0x0D44, 0x0D45} /* Cn */, { 0x0D49, 0x0D49} /* Cn */,
! 903: { 0x0D4E, 0x0D56} /* Cn */, { 0x0D58, 0x0D5F} /* Cn */,
! 904: { 0x0D62, 0x0D65} /* Cn */, { 0x0D70, 0x0D81} /* Cn */,
! 905: { 0x0D84, 0x0D84} /* Cn */, { 0x0D97, 0x0D99} /* Cn */,
! 906: { 0x0DB2, 0x0DB2} /* Cn */, { 0x0DBC, 0x0DBC} /* Cn */,
! 907: { 0x0DBE, 0x0DBF} /* Cn */, { 0x0DC7, 0x0DC9} /* Cn */,
! 908: { 0x0DCB, 0x0DCE} /* Cn */, { 0x0DD5, 0x0DD5} /* Cn */,
! 909: { 0x0DD7, 0x0DD7} /* Cn */, { 0x0DE0, 0x0DF1} /* Cn */,
! 910: { 0x0DF5, 0x0E00} /* Cn */, { 0x0E3B, 0x0E3E} /* Cn */,
! 911: { 0x0E5C, 0x0E80} /* Cn */, { 0x0E83, 0x0E83} /* Cn */,
! 912: { 0x0E85, 0x0E86} /* Cn */, { 0x0E89, 0x0E89} /* Cn */,
! 913: { 0x0E8B, 0x0E8C} /* Cn */, { 0x0E8E, 0x0E93} /* Cn */,
! 914: { 0x0E98, 0x0E98} /* Cn */, { 0x0EA0, 0x0EA0} /* Cn */,
! 915: { 0x0EA4, 0x0EA4} /* Cn */, { 0x0EA6, 0x0EA6} /* Cn */,
! 916: { 0x0EA8, 0x0EA9} /* Cn */, { 0x0EAC, 0x0EAC} /* Cn */,
! 917: { 0x0EBA, 0x0EBA} /* Cn */, { 0x0EBE, 0x0EBF} /* Cn */,
! 918: { 0x0EC5, 0x0EC5} /* Cn */, { 0x0EC7, 0x0EC7} /* Cn */,
! 919: { 0x0ECE, 0x0ECF} /* Cn */, { 0x0EDA, 0x0EDB} /* Cn */,
! 920: { 0x0EDE, 0x0EFF} /* Cn */, { 0x0F48, 0x0F48} /* Cn */,
! 921: { 0x0F6B, 0x0F70} /* Cn */, { 0x0F8C, 0x0F8F} /* Cn */,
! 922: { 0x0F98, 0x0F98} /* Cn */, { 0x0FBD, 0x0FBD} /* Cn */,
! 923: { 0x0FCD, 0x0FCE} /* Cn */, { 0x0FD2, 0x0FFF} /* Cn */,
! 924: { 0x1022, 0x1022} /* Cn */, { 0x1028, 0x1028} /* Cn */,
! 925: { 0x102B, 0x102B} /* Cn */, { 0x1033, 0x1035} /* Cn */,
! 926: { 0x103A, 0x103F} /* Cn */, { 0x105A, 0x109F} /* Cn */,
! 927: { 0x10C6, 0x10CF} /* Cn */, { 0x10FD, 0x10FF} /* Cn */,
! 928: { 0x115A, 0x115E} /* Cn */, { 0x11A3, 0x11A7} /* Cn */,
! 929: { 0x11FA, 0x11FF} /* Cn */, { 0x1249, 0x1249} /* Cn */,
! 930: { 0x124E, 0x124F} /* Cn */, { 0x1257, 0x1257} /* Cn */,
! 931: { 0x1259, 0x1259} /* Cn */, { 0x125E, 0x125F} /* Cn */,
! 932: { 0x1289, 0x1289} /* Cn */, { 0x128E, 0x128F} /* Cn */,
! 933: { 0x12B1, 0x12B1} /* Cn */, { 0x12B6, 0x12B7} /* Cn */,
! 934: { 0x12BF, 0x12BF} /* Cn */, { 0x12C1, 0x12C1} /* Cn */,
! 935: { 0x12C6, 0x12C7} /* Cn */, { 0x12D7, 0x12D7} /* Cn */,
! 936: { 0x1311, 0x1311} /* Cn */, { 0x1316, 0x1317} /* Cn */,
! 937: { 0x135B, 0x135E} /* Cn */, { 0x137D, 0x137F} /* Cn */,
! 938: { 0x139A, 0x139F} /* Cn */, { 0x13F5, 0x1400} /* Cn */,
! 939: { 0x1677, 0x167F} /* Cn */, { 0x169D, 0x169F} /* Cn */,
! 940: { 0x16F1, 0x16FF} /* Cn */, { 0x170D, 0x170D} /* Cn */,
! 941: { 0x1715, 0x171F} /* Cn */, { 0x1737, 0x173F} /* Cn */,
! 942: { 0x1754, 0x175F} /* Cn */, { 0x176D, 0x176D} /* Cn */,
! 943: { 0x1771, 0x1771} /* Cn */, { 0x1774, 0x177F} /* Cn */,
! 944: #if 0
! 945: { 0x17B4, 0x17B5} /* Cf */,
! 946: #endif
! 947: { 0x17DE, 0x17DF} /* Cn */, { 0x17EA, 0x17EF} /* Cn */,
! 948: { 0x17FA, 0x17FF} /* Cn */, { 0x180F, 0x180F} /* Cn */,
! 949: { 0x181A, 0x181F} /* Cn */, { 0x1878, 0x187F} /* Cn */,
! 950: { 0x18AA, 0x18FF} /* Cn */, { 0x191D, 0x191F} /* Cn */,
! 951: { 0x192C, 0x192F} /* Cn */, { 0x193C, 0x193F} /* Cn */,
! 952: { 0x1941, 0x1943} /* Cn */, { 0x196E, 0x196F} /* Cn */,
! 953: { 0x1975, 0x197F} /* Cn */, { 0x19AA, 0x19AF} /* Cn */,
! 954: { 0x19CA, 0x19CF} /* Cn */, { 0x19DA, 0x19DD} /* Cn */,
! 955: { 0x1A1C, 0x1A1D} /* Cn */, { 0x1A20, 0x1AFF} /* Cn */,
! 956: { 0x1B4C, 0x1B4F} /* Cn */, { 0x1B7D, 0x1CFF} /* Cn */,
! 957: { 0x1DCB, 0x1DFD} /* Cn */, { 0x1E9C, 0x1E9F} /* Cn */,
! 958: { 0x1EFA, 0x1EFF} /* Cn */, { 0x1F16, 0x1F17} /* Cn */,
! 959: { 0x1F1E, 0x1F1F} /* Cn */, { 0x1F46, 0x1F47} /* Cn */,
! 960: { 0x1F4E, 0x1F4F} /* Cn */, { 0x1F58, 0x1F58} /* Cn */,
! 961: { 0x1F5A, 0x1F5A} /* Cn */, { 0x1F5C, 0x1F5C} /* Cn */,
! 962: { 0x1F5E, 0x1F5E} /* Cn */, { 0x1F7E, 0x1F7F} /* Cn */,
! 963: { 0x1FB5, 0x1FB5} /* Cn */, { 0x1FC5, 0x1FC5} /* Cn */,
! 964: { 0x1FD4, 0x1FD5} /* Cn */, { 0x1FDC, 0x1FDC} /* Cn */,
! 965: { 0x1FF0, 0x1FF1} /* Cn */, { 0x1FF5, 0x1FF5} /* Cn */,
! 966: { 0x1FFF, 0x1FFF} /* Cn */,
! 967: { 0x200B, 0x200F} /* Cf */,
! 968: { 0x2028, 0x2028} /* Zl */,
! 969: { 0x2029, 0x2029} /* Zp */,
! 970: { 0x202A, 0x202E} /* Cf */,
! 971: { 0x2060, 0x2063} /* Cf */,
! 972: { 0x2064, 0x2069} /* Cn */,
! 973: { 0x206A, 0x206F} /* Cf */,
! 974: { 0x2072, 0x2073} /* Cn */, { 0x208F, 0x208F} /* Cn */,
! 975: { 0x2095, 0x209F} /* Cn */, { 0x20B6, 0x20CF} /* Cn */,
! 976: { 0x20F0, 0x20FF} /* Cn */, { 0x214F, 0x2152} /* Cn */,
! 977: { 0x2185, 0x218F} /* Cn */, { 0x23E8, 0x23FF} /* Cn */,
! 978: { 0x2427, 0x243F} /* Cn */, { 0x244B, 0x245F} /* Cn */,
! 979: { 0x269D, 0x269F} /* Cn */, { 0x26B3, 0x2700} /* Cn */,
! 980: { 0x2705, 0x2705} /* Cn */, { 0x270A, 0x270B} /* Cn */,
! 981: { 0x2728, 0x2728} /* Cn */, { 0x274C, 0x274C} /* Cn */,
! 982: { 0x274E, 0x274E} /* Cn */, { 0x2753, 0x2755} /* Cn */,
! 983: { 0x2757, 0x2757} /* Cn */, { 0x275F, 0x2760} /* Cn */,
! 984: { 0x2795, 0x2797} /* Cn */, { 0x27B0, 0x27B0} /* Cn */,
! 985: { 0x27BF, 0x27BF} /* Cn */, { 0x27CB, 0x27CF} /* Cn */,
! 986: { 0x27EC, 0x27EF} /* Cn */, { 0x2B1B, 0x2B1F} /* Cn */,
! 987: { 0x2B24, 0x2BFF} /* Cn */, { 0x2C2F, 0x2C2F} /* Cn */,
! 988: { 0x2C5F, 0x2C5F} /* Cn */, { 0x2C6D, 0x2C73} /* Cn */,
! 989: { 0x2C78, 0x2C7F} /* Cn */, { 0x2CEB, 0x2CF8} /* Cn */,
! 990: { 0x2D26, 0x2D2F} /* Cn */, { 0x2D66, 0x2D6E} /* Cn */,
! 991: { 0x2D70, 0x2D7F} /* Cn */, { 0x2D97, 0x2D9F} /* Cn */,
! 992: { 0x2DA7, 0x2DA7} /* Cn */, { 0x2DAF, 0x2DAF} /* Cn */,
! 993: { 0x2DB7, 0x2DB7} /* Cn */, { 0x2DBF, 0x2DBF} /* Cn */,
! 994: { 0x2DC7, 0x2DC7} /* Cn */, { 0x2DCF, 0x2DCF} /* Cn */,
! 995: { 0x2DD7, 0x2DD7} /* Cn */, { 0x2DDF, 0x2DFF} /* Cn */,
! 996: { 0x2E18, 0x2E1B} /* Cn */, { 0x2E1E, 0x2E7F} /* Cn */,
! 997: { 0x2E9A, 0x2E9A} /* Cn */, { 0x2EF4, 0x2EFF} /* Cn */,
! 998: { 0x2FD6, 0x2FEF} /* Cn */, { 0x2FFC, 0x2FFF} /* Cn */,
! 999: { 0x3040, 0x3040} /* Cn */, { 0x3097, 0x3098} /* Cn */,
! 1000: { 0x3100, 0x3104} /* Cn */, { 0x312D, 0x3130} /* Cn */,
! 1001: { 0x318F, 0x318F} /* Cn */, { 0x31B8, 0x31BF} /* Cn */,
! 1002: { 0x31D0, 0x31EF} /* Cn */, { 0x321F, 0x321F} /* Cn */,
! 1003: { 0x3244, 0x324F} /* Cn */, { 0x32FF, 0x32FF} /* Cn */,
! 1004: { 0x4DB6, 0x4DBF} /* Cn */, { 0x9FBC, 0x9FFF} /* Cn */,
! 1005: { 0xA48D, 0xA48F} /* Cn */, { 0xA4C7, 0xA6FF} /* Cn */,
! 1006: { 0xA71B, 0xA71F} /* Cn */, { 0xA722, 0xA7FF} /* Cn */,
! 1007: { 0xA82C, 0xA83F} /* Cn */, { 0xA878, 0xABFF} /* Cn */,
! 1008: { 0xD7A4, 0xD7FF} /* Cn */,
! 1009: { 0xD800, 0xDFFF} /* Cs */,
! 1010: { 0xE000, 0xF8FF} /* Co */,
! 1011: { 0xFA2E, 0xFA2F} /* Cn */, { 0xFA6B, 0xFA6F} /* Cn */,
! 1012: { 0xFADA, 0xFAFF} /* Cn */, { 0xFB07, 0xFB12} /* Cn */,
! 1013: { 0xFB18, 0xFB1C} /* Cn */, { 0xFB37, 0xFB37} /* Cn */,
! 1014: { 0xFB3D, 0xFB3D} /* Cn */, { 0xFB3F, 0xFB3F} /* Cn */,
! 1015: { 0xFB42, 0xFB42} /* Cn */, { 0xFB45, 0xFB45} /* Cn */,
! 1016: { 0xFBB2, 0xFBD2} /* Cn */, { 0xFD40, 0xFD4F} /* Cn */,
! 1017: { 0xFD90, 0xFD91} /* Cn */, { 0xFDC8, 0xFDEF} /* Cn */,
! 1018: { 0xFDFE, 0xFDFF} /* Cn */, { 0xFE1A, 0xFE1F} /* Cn */,
! 1019: { 0xFE24, 0xFE2F} /* Cn */, { 0xFE53, 0xFE53} /* Cn */,
! 1020: { 0xFE67, 0xFE67} /* Cn */, { 0xFE6C, 0xFE6F} /* Cn */,
! 1021: { 0xFE75, 0xFE75} /* Cn */, { 0xFEFD, 0xFEFE} /* Cn */,
! 1022: { 0xFEFF, 0xFEFF} /* Cf */,
! 1023: { 0xFF00, 0xFF00} /* Cn */, { 0xFFBF, 0xFFC1} /* Cn */,
! 1024: { 0xFFC8, 0xFFC9} /* Cn */, { 0xFFD0, 0xFFD1} /* Cn */,
! 1025: { 0xFFD8, 0xFFD9} /* Cn */, { 0xFFDD, 0xFFDF} /* Cn */,
! 1026: { 0xFFE7, 0xFFE7} /* Cn */, { 0xFFEF, 0xFFF8} /* Cn */,
! 1027: { 0xFFF9, 0xFFFB} /* Cf */,
! 1028: { 0xFFFE, 0xFFFF} /* Cn */, { 0x1000C, 0x1000C} /* Cn */,
! 1029: { 0x10027, 0x10027} /* Cn */, { 0x1003B, 0x1003B} /* Cn */,
! 1030: { 0x1003E, 0x1003E} /* Cn */, { 0x1004E, 0x1004F} /* Cn */,
! 1031: { 0x1005E, 0x1007F} /* Cn */, { 0x100FB, 0x100FF} /* Cn */,
! 1032: { 0x10103, 0x10106} /* Cn */, { 0x10134, 0x10136} /* Cn */,
! 1033: { 0x1018B, 0x102FF} /* Cn */, { 0x1031F, 0x1031F} /* Cn */,
! 1034: { 0x10324, 0x1032F} /* Cn */, { 0x1034B, 0x1037F} /* Cn */,
! 1035: { 0x1039E, 0x1039E} /* Cn */, { 0x103C4, 0x103C7} /* Cn */,
! 1036: { 0x103D6, 0x103FF} /* Cn */,
! 1037: { 0x1049E, 0x1049F} /* Cn */, { 0x104AA, 0x107FF} /* Cn */,
! 1038: { 0x10806, 0x10807} /* Cn */, { 0x10809, 0x10809} /* Cn */,
! 1039: { 0x10836, 0x10836} /* Cn */, { 0x10839, 0x1083B} /* Cn */,
! 1040: { 0x1083D, 0x1083E} /* Cn */, { 0x10840, 0x108FF} /* Cn */,
! 1041: { 0x1091A, 0x1091E} /* Cn */, { 0x10920, 0x109FF} /* Cn */,
! 1042: { 0x10A04, 0x10A04} /* Cn */, { 0x10A07, 0x10A0B} /* Cn */,
! 1043: { 0x10A14, 0x10A14} /* Cn */, { 0x10A18, 0x10A18} /* Cn */,
! 1044: { 0x10A34, 0x10A37} /* Cn */, { 0x10A3B, 0x10A3E} /* Cn */,
! 1045: { 0x10A48, 0x10A4F} /* Cn */, { 0x10A59, 0x11FFF} /* Cn */,
! 1046: { 0x1236F, 0x123FF} /* Cn */, { 0x12463, 0x1246F} /* Cn */,
! 1047: { 0x12474, 0x1CFFF} /* Cn */, { 0x1D0F6, 0x1D0FF} /* Cn */,
! 1048: { 0x1D127, 0x1D129} /* Cn */,
! 1049: { 0x1D173, 0x1D17A} /* Cf */,
! 1050: { 0x1D1DE, 0x1D1FF} /* Cn */, { 0x1D246, 0x1D2FF} /* Cn */,
! 1051: { 0x1D357, 0x1D35F} /* Cn */, { 0x1D372, 0x1D3FF} /* Cn */,
! 1052: { 0x1D455, 0x1D455} /* Cn */, { 0x1D49D, 0x1D49D} /* Cn */,
! 1053: { 0x1D4A0, 0x1D4A1} /* Cn */, { 0x1D4A3, 0x1D4A4} /* Cn */,
! 1054: { 0x1D4A7, 0x1D4A8} /* Cn */, { 0x1D4AD, 0x1D4AD} /* Cn */,
! 1055: { 0x1D4BA, 0x1D4BA} /* Cn */, { 0x1D4BC, 0x1D4BC} /* Cn */,
! 1056: { 0x1D4C4, 0x1D4C4} /* Cn */, { 0x1D506, 0x1D506} /* Cn */,
! 1057: { 0x1D50B, 0x1D50C} /* Cn */, { 0x1D515, 0x1D515} /* Cn */,
! 1058: { 0x1D51D, 0x1D51D} /* Cn */, { 0x1D53A, 0x1D53A} /* Cn */,
! 1059: { 0x1D53F, 0x1D53F} /* Cn */, { 0x1D545, 0x1D545} /* Cn */,
! 1060: { 0x1D547, 0x1D549} /* Cn */, { 0x1D551, 0x1D551} /* Cn */,
! 1061: { 0x1D6A6, 0x1D6A7} /* Cn */, { 0x1D7CC, 0x1D7CD} /* Cn */,
! 1062: { 0x1D800, 0x1FFFF} /* Cn */, { 0x2A6D7, 0x2F7FF} /* Cn */,
! 1063: { 0x2FA1E, 0xE0000} /* Cn */,
! 1064: { 0xE0001, 0xE0001} /* Cf */,
! 1065: { 0xE0002, 0xE001F} /* Cn */,
! 1066: { 0xE0020, 0xE007F} /* Cf */,
! 1067: { 0xE0080, 0xE00FF} /* Cn */, { 0xE01F0, 0xEFFFF} /* Cn */,
! 1068: { 0xF0000, 0xFFFFD} /* Co */,
! 1069: { 0xFFFFE, 0xFFFFF} /* Cn */,
! 1070: {0x100000,0x10FFFD} /* Co */,
! 1071: {0x10FFFE,0x10FFFF} /* Cn */,
! 1072: {0x110000,0x7FFFFFFF} /* ISO 10646?? */
! 1073: };
! 1074:
! 1075: /*
! 1076: * Double width characters
! 1077: * W: East Asian Wide
! 1078: * F: East Asian Full-width
! 1079: * Unassigned code points may be included when they allow ranges to be merged.
! 1080: * Last synched with
! 1081: * <http://www.unicode.org/Public/5.0.0/ucd/EastAsianWidth-5.0.0d2.txt>
! 1082: * dated 2005-11-08T01:32:56Z
! 1083: */
! 1084: static struct wchar_range wide_table[] = {
! 1085: { 0x1100, 0x115F} /* W */, { 0x2329, 0x232A} /* W */,
! 1086: { 0x2E80, 0x2FFB} /* W */,
! 1087: { 0x3000, 0x3000} /* F */,
! 1088: { 0x3001, 0x303E} /* W */, { 0x3041, 0x4DB5} /* W */,
! 1089: { 0x4E00, 0x9FBB} /* W */, { 0xA000, 0xA4C6} /* W */,
! 1090: { 0xAC00, 0xD7A3} /* W */, { 0xF900, 0xFAD9} /* W */,
! 1091: { 0xFE10, 0xFE19} /* W */, { 0xFE30, 0xFE6B} /* W */,
! 1092: { 0xFF01, 0xFF60} /* F */, { 0xFFE0, 0xFFE6} /* F */,
! 1093: { 0x20000, 0x2FFFD} /* W */, { 0x30000, 0x3FFFD} /* W */,
! 1094: };
! 1095:
! 1096: static int
! 1097: is_in_table(ch, table, tsize)
! 1098: LWCHAR ch;
! 1099: struct wchar_range table[];
! 1100: int tsize;
! 1101: {
! 1102: int hi;
! 1103: int lo;
! 1104:
! 1105: /* Binary search in the table. */
! 1106: if (ch < table[0].first)
! 1107: return 0;
! 1108: lo = 0;
! 1109: hi = tsize - 1;
! 1110: while (lo <= hi)
! 1111: {
! 1112: int mid = (lo + hi) / 2;
! 1113: if (ch > table[mid].last)
! 1114: lo = mid + 1;
! 1115: else if (ch < table[mid].first)
! 1116: hi = mid - 1;
! 1117: else
! 1118: return 1;
! 1119: }
! 1120: return 0;
! 1121: }
! 1122:
! 1123: /*
! 1124: * Is a character a UTF-8 composing character?
! 1125: * If a composing character follows any char, the two combine into one glyph.
! 1126: */
! 1127: public int
! 1128: is_composing_char(ch)
! 1129: LWCHAR ch;
! 1130: {
! 1131: return is_in_table(ch, comp_table, (sizeof(comp_table) / sizeof(*comp_table)));
! 1132: }
! 1133:
! 1134: /*
! 1135: * Should this UTF-8 character be treated as binary?
! 1136: */
! 1137: public int
! 1138: is_ubin_char(ch)
! 1139: LWCHAR ch;
! 1140: {
! 1141: return is_in_table(ch, ubin_table, (sizeof(ubin_table) / sizeof(*ubin_table)));
! 1142: }
! 1143:
! 1144: /*
! 1145: * Is this a double width UTF-8 character?
! 1146: */
! 1147: public int
! 1148: is_wide_char(ch)
! 1149: LWCHAR ch;
! 1150: {
! 1151: return is_in_table(ch, wide_table, (sizeof(wide_table) / sizeof(*wide_table)));
! 1152: }
! 1153:
! 1154: /*
! 1155: * Is a character a UTF-8 combining character?
! 1156: * A combining char acts like an ordinary char, but if it follows
! 1157: * a specific char (not any char), the two combine into one glyph.
! 1158: */
! 1159: public int
! 1160: is_combining_char(ch1, ch2)
! 1161: LWCHAR ch1;
! 1162: LWCHAR ch2;
! 1163: {
! 1164: /* The table is small; use linear search. */
! 1165: int i;
! 1166: for (i = 0; i < sizeof(comb_table)/sizeof(*comb_table); i++)
! 1167: {
! 1168: if (ch1 == comb_table[i].first &&
! 1169: ch2 == comb_table[i].last)
! 1170: return 1;
! 1171: }
! 1172: return 0;
! 1173: }
! 1174:
! 1175: #else /* !SMALL */
1.6 millert 1176:
1177: public int binattr = AT_STANDOUT;
1178:
1179: public void
1180: init_charset()
1181: {
1182: return;
1183: }
1184:
1185: /*
1186: * Is a given character a "binary" character?
1187: */
1188: public int
1189: binary_char(c)
1.8 ! shadchin 1190: LWCHAR c;
1.6 millert 1191: {
1.7 millert 1192: return (!isprint(c) && !isspace(c));
1.6 millert 1193: }
1194:
1195: /*
1196: * Is a given character a "control" character?
1197: */
1198: public int
1199: control_char(c)
1.8 ! shadchin 1200: LWCHAR c;
1.6 millert 1201: {
1202: return (iscntrl(c));
1203: }
1204:
1205: /*
1206: * Return the printable form of a character.
1207: * For example, in the "ascii" charset '\3' is printed as "^C".
1208: */
1209: public char *
1210: prchar(c)
1.8 ! shadchin 1211: LWCHAR c;
1.6 millert 1212: {
1213: static char buf[8];
1214:
1215: c &= 0377;
1216: if (!iscntrl(c))
1217: snprintf(buf, sizeof(buf), "%c", c);
1218: else if (c == ESC)
1219: snprintf(buf, sizeof(buf), "ESC");
1.8 ! shadchin 1220: else if (c < 128 && !iscntrl(c ^ 0100))
! 1221: snprintf(buf, sizeof(buf), "^%c", c ^ 0100);
1.6 millert 1222: else
1223: snprintf(buf, sizeof(buf), "*s<%X>", c);
1224: return (buf);
1225: }
1.8 ! shadchin 1226:
! 1227: /*
! 1228: * Step forward or backward one character in a string.
! 1229: */
! 1230: public LWCHAR
! 1231: step_char(pp, dir, limit)
! 1232: char **pp;
! 1233: signed int dir;
! 1234: char *limit;
! 1235: {
! 1236: LWCHAR ch;
! 1237: int len;
! 1238: char *p = *pp;
! 1239:
! 1240: /* It's easy if chars are one byte. */
! 1241: if (dir > 0)
! 1242: ch = (LWCHAR) ((p < limit) ? *p++ : 0);
! 1243: else
! 1244: ch = (LWCHAR) ((p > limit) ? *--p : 0);
! 1245:
! 1246: *pp = p;
! 1247: return ch;
! 1248: }
! 1249:
! 1250: #endif /* !SMALL */