gfx/thebes/src/nsUnicodeRange.cpp

   1 /* -*- Mode: C++; tab-width: 2; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
   2 /* ***** BEGIN LICENSE BLOCK *****
   3  * Version: MPL 1.1/GPL 2.0/LGPL 2.1
   4  *
   5  * The contents of this file are subject to the Mozilla Public License Version
   6  * 1.1 (the "License"); you may not use this file except in compliance with
   7  * the License. You may obtain a copy of the License at
   8  * http://www.mozilla.org/MPL/
   9  *
  10  * Software distributed under the License is distributed on an "AS IS" basis,
  11  * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
  12  * for the specific language governing rights and limitations under the
  13  * License.
  14  *
  15  * The Original Code is mozilla.org code.
  16  *
  17  * The Initial Developer of the Original Code is
  18  * Netscape Communications Corporation.
  19  * Portions created by the Initial Developer are Copyright (C) 1998
  20  * the Initial Developer. All Rights Reserved.
  21  *
  22  * Contributor(s):
  23  *
  24  * Alternatively, the contents of this file may be used under the terms of
  25  * either of the GNU General Public License Version 2 or later (the "GPL"),
  26  * or the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
  27  * in which case the provisions of the GPL or the LGPL are applicable instead
  28  * of those above. If you wish to allow use of your version of this file only
  29  * under the terms of either the GPL or the LGPL, and not to allow others to
  30  * use your version of this file under the terms of the MPL, indicate your
  31  * decision by deleting the provisions above and replace them with the notice
  32  * and other provisions required by the GPL or the LGPL. If you do not delete
  33  * the provisions above, a recipient may use your version of this file under
  34  * the terms of any one of the MPL, the GPL or the LGPL.
  35  *
  36  * ***** END LICENSE BLOCK ***** */
  37
  38 #include "nsUnicodeRange.h"
  39
  40 // This table depends on unicode range definitions.
  41 // Each item's index must correspond unicode range value
  42 // eg. x-cyrillic = LangGroupTable[kRangeCyrillic]
  43 static const char *gUnicodeRangeToLangGroupTable[] =
  44 {
  45   "x-cyrillic",
  46   "el",
  47   "tr",
  48   "he",
  49   "ar",
  50   "x-baltic",
  51   "th",
  52   "ko",
  53   "ja",
  54   "zh-CN",
  55   "zh-TW",
  56   "x-devanagari",
  57   "x-tamil",
  58   "x-armn",
  59   "x-beng",
  60   "x-cans",
  61   "x-ethi",
  62   "x-geor",
  63   "x-gujr",
  64   "x-guru",
  65   "x-khmr",
  66   "x-mlym",
  67   "x-orya",
  68   "x-telu",
  69   "x-knda",
  70   "x-sinh"
  71 };
  72
  73 /**********************************************************************
  74  * Unicode subranges as defined in unicode 3.0
  75  * x-western, x-central-euro, tr, x-baltic  -> latin
  76  *  0000 - 036f
  77  *  1e00 - 1eff
  78  *  2000 - 206f  (general punctuation)
  79  *  20a0 - 20cf  (currency symbols)
  80  *  2100 - 214f  (letterlike symbols)
  81  *  2150 - 218f  (Number Forms)
  82  * el         -> greek
  83  *  0370 - 03ff
  84  *  1f00 - 1fff
  85  * x-cyrillic -> cyrillic
  86  *  0400 - 04ff
  87  * he         -> hebrew
  88  *  0590 - 05ff
  89  * ar         -> arabic
  90  *  0600 - 06ff
  91  *  fb50 - fdff (arabic presentation forms)
  92  *  fe70 - feff (arabic presentation forms b)
  93  * th - thai
  94  *  0e00 - 0e7f
  95  * ko        -> korean
  96  *  ac00 - d7af  (hangul Syllables)
  97  *  1100 - 11ff    (jamo)
  98  *  3130 - 318f (hangul compatibility jamo)
  99  * ja
 100  *  3040 - 309f (hiragana)
 101  *  30a0 - 30ff (katakana)
 102  * zh-CN
 103  * zh-TW
 104  *
 105  * CJK
 106  *  3100 - 312f (bopomofo)
 107  *  31a0 - 31bf (bopomofo extended)
 108  *  3000 - 303f (CJK Symbols and Punctuation)
 109  *  2e80 - 2eff (CJK radicals supplement)
 110  *  2f00 - 2fdf (Kangxi Radicals)
 111  *  2ff0 - 2fff (Ideographic Description Characters)
 112  *  3190 - 319f (kanbun)
 113  *  3200 - 32ff (Enclosed CJK letters and Months)
 114  *  3300 - 33ff (CJK compatibility)
 115  *  3400 - 4dbf (CJK Unified Ideographs Extension A)
 116  *  4e00 - 9faf (CJK Unified Ideographs)
 117  *  f900 - fa5f (CJK Compatibility Ideographs)
 118  *  fe30 - fe4f (CJK compatibility Forms)
 119  *  ff00 - ffef (halfwidth and fullwidth forms)
 120  *
 121  * Armenian
 122  *  0530 - 058f
 123  * Sriac
 124  *  0700 - 074f
 125  * Thaana
 126  *  0780 - 07bf
 127  * Devanagari
 128  *  0900 - 097f
 129  * Bengali
 130  *  0980 - 09ff
 131  * Gurmukhi
 132  *  0a00 - 0a7f
 133  * Gujarati
 134  *  0a80 - 0aff
 135  * Oriya
 136  *  0b00 - 0b7f
 137  * Tamil
 138  *  0b80 - 0bff
 139  * Telugu
 140  *  0c00 - 0c7f
 141  * Kannada
 142  *  0c80 - 0cff
 143  * Malayalam
 144  *  0d00 - 0d7f
 145  * Sinhala
 146  *  0d80 - 0def
 147  * Lao
 148  *  0e80 - 0eff
 149  * Tibetan
 150  *  0f00 - 0fbf
 151  * Myanmar
 152  *  1000 - 109f
 153  * Georgian
 154  *  10a0 - 10ff
 155  * Ethiopic
 156  *  1200 - 137f
 157  * Cherokee
 158  *  13a0 - 13ff
 159  * Canadian Aboriginal Syllabics
 160  *  1400 - 167f
 161  * Ogham
 162  *  1680 - 169f
 163  * Runic
 164  *  16a0 - 16ff
 165  * Khmer
 166  *  1780 - 17ff
 167  * Mongolian
 168  *  1800 - 18af
 169  * Misc - superscripts and subscripts
 170  *  2070 - 209f
 171  * Misc - Combining Diacritical Marks for Symbols
 172  *  20d0 - 20ff
 173  * Misc - Arrows
 174  *  2190 - 21ff
 175  * Misc - Mathematical Operators
 176  *  2200 - 22ff
 177  * Misc - Miscellaneous Technical
 178  *  2300 - 23ff
 179  * Misc - Control picture
 180  *  2400 - 243f
 181  * Misc - Optical character recognition
 182  *  2440 - 2450
 183  * Misc - Enclose Alphanumerics
 184  *  2460 - 24ff
 185  * Misc - Box Drawing
 186  *  2500 - 257f
 187  * Misc - Block Elements
 188  *  2580 - 259f
 189  * Misc - Geometric Shapes
 190  *  25a0 - 25ff
 191  * Misc - Miscellaneous Symbols
 192  *  2600 - 267f
 193  * Misc - Dingbats
 194  *  2700 - 27bf
 195  * Misc - Braille Patterns
 196  *  2800 - 28ff
 197  * Yi Syllables
 198  *  a000 - a48f
 199  * Yi radicals
 200  *  a490 - a4cf
 201  * Alphabetic Presentation Forms
 202  *  fb00 - fb4f
 203  * Misc - Combining half Marks
 204  *  fe20 - fe2f
 205  * Misc - small form variants
 206  *  fe50 - fe6f
 207  * Misc - Specials
 208  *  fff0 - ffff
 209  *********************************************************************/
 210
 211
 212
 213 #define NUM_OF_SUBTABLES      9
 214 #define SUBTABLE_SIZE         16
 215
 216 static const PRUint8 gUnicodeSubrangeTable[NUM_OF_SUBTABLES][SUBTABLE_SIZE] =
 217 {
 218   { // table for X---
 219     kRangeTableBase+1,  //u0xxx
 220     kRangeTableBase+2,  //u1xxx
 221     kRangeTableBase+3,  //u2xxx
 222     kRangeSetCJK,       //u3xxx
 223     kRangeSetCJK,       //u4xxx
 224     kRangeSetCJK,       //u5xxx
 225     kRangeSetCJK,       //u6xxx
 226     kRangeSetCJK,       //u7xxx
 227     kRangeSetCJK,       //u8xxx
 228     kRangeSetCJK,       //u9xxx
 229     kRangeTableBase+4,  //uaxxx
 230     kRangeKorean,       //ubxxx
 231     kRangeKorean,       //ucxxx
 232     kRangeTableBase+5,  //udxxx
 233     kRangePrivate,      //uexxx
 234     kRangeTableBase+6   //ufxxx
 235   },
 236   { //table for 0X--
 237     kRangeSetLatin,          //u00xx
 238     kRangeSetLatin,          //u01xx
 239     kRangeSetLatin,          //u02xx
 240     kRangeGreek,             //u03xx     XXX 0300-036f is in fact kRangeCombiningDiacriticalMarks
 241     kRangeCyrillic,          //u04xx
 242     kRangeTableBase+7,       //u05xx, includes Cyrillic supplement, Hebrew, and Armenian
 243     kRangeArabic,            //u06xx
 244     kRangeTertiaryTable,     //u07xx
 245     kRangeUnassigned,        //u08xx
 246     kRangeTertiaryTable,     //u09xx
 247     kRangeTertiaryTable,     //u0axx
 248     kRangeTertiaryTable,     //u0bxx
 249     kRangeTertiaryTable,     //u0cxx
 250     kRangeTertiaryTable,     //u0dxx
 251     kRangeTertiaryTable,     //u0exx
 252     kRangeTibetan,           //u0fxx
 253   },
 254   { //table for 1x--
 255     kRangeTertiaryTable,     //u10xx
 256     kRangeKorean,            //u11xx
 257     kRangeEthiopic,          //u12xx
 258     kRangeTertiaryTable,     //u13xx
 259     kRangeCanadian,          //u14xx
 260     kRangeCanadian,          //u15xx
 261     kRangeTertiaryTable,     //u16xx
 262     kRangeKhmer,             //u17xx
 263     kRangeMongolian,         //u18xx
 264     kRangeUnassigned,        //u19xx
 265     kRangeUnassigned,        //u1axx
 266     kRangeUnassigned,        //u1bxx
 267     kRangeUnassigned,        //u1cxx
 268     kRangeUnassigned,        //u1dxx
 269     kRangeSetLatin,          //u1exx
 270     kRangeGreek,             //u1fxx
 271   },
 272   { //table for 2x--
 273     kRangeSetLatin,          //u20xx
 274     kRangeSetLatin,          //u21xx
 275     kRangeMathOperators,     //u22xx
 276     kRangeMiscTechnical,     //u23xx
 277     kRangeControlOpticalEnclose, //u24xx
 278     kRangeBoxBlockGeometrics, //u25xx
 279     kRangeMiscSymbols,       //u26xx
 280     kRangeDingbats,          //u27xx
 281     kRangeBraillePattern,    //u28xx
 282     kRangeUnassigned,        //u29xx
 283     kRangeUnassigned,        //u2axx
 284     kRangeUnassigned,        //u2bxx
 285     kRangeUnassigned,        //u2cxx
 286     kRangeUnassigned,        //u2dxx
 287     kRangeSetCJK,            //u2exx
 288     kRangeSetCJK,            //u2fxx
 289   },
 290   {  //table for ax--
 291     kRangeYi,                //ua0xx
 292     kRangeYi,                //ua1xx
 293     kRangeYi,                //ua2xx
 294     kRangeYi,                //ua3xx
 295     kRangeYi,                //ua4xx
 296     kRangeUnassigned,        //ua5xx
 297     kRangeUnassigned,        //ua6xx
 298     kRangeUnassigned,        //ua7xx
 299     kRangeUnassigned,        //ua8xx
 300     kRangeUnassigned,        //ua9xx
 301     kRangeUnassigned,        //uaaxx
 302     kRangeUnassigned,        //uabxx
 303     kRangeKorean,            //uacxx
 304     kRangeKorean,            //uadxx
 305     kRangeKorean,            //uaexx
 306     kRangeKorean,            //uafxx
 307   },
 308   {  //table for dx--
 309     kRangeKorean,            //ud0xx
 310     kRangeKorean,            //ud1xx
 311     kRangeKorean,            //ud2xx
 312     kRangeKorean,            //ud3xx
 313     kRangeKorean,            //ud4xx
 314     kRangeKorean,            //ud5xx
 315     kRangeKorean,            //ud6xx
 316     kRangeKorean,            //ud7xx
 317     kRangeSurrogate,         //ud8xx
 318     kRangeSurrogate,         //ud9xx
 319     kRangeSurrogate,         //udaxx
 320     kRangeSurrogate,         //udbxx
 321     kRangeSurrogate,         //udcxx
 322     kRangeSurrogate,         //uddxx
 323     kRangeSurrogate,         //udexx
 324     kRangeSurrogate,         //udfxx
 325   },
 326   { // table for fx--
 327     kRangePrivate,           //uf0xx
 328     kRangePrivate,           //uf1xx
 329     kRangePrivate,           //uf2xx
 330     kRangePrivate,           //uf3xx
 331     kRangePrivate,           //uf4xx
 332     kRangePrivate,           //uf5xx
 333     kRangePrivate,           //uf6xx
 334     kRangePrivate,           //uf7xx
 335     kRangePrivate,           //uf8xx
 336     kRangeSetCJK,            //uf9xx
 337     kRangeSetCJK,            //ufaxx
 338     kRangeArabic,            //ufbxx, includes alphabic presentation form
 339     kRangeArabic,            //ufcxx
 340     kRangeArabic,            //ufdxx
 341     kRangeArabic,            //ufexx, includes Combining half marks,
 342                              //                CJK compatibility forms,
 343                              //                CJK compatibility forms,
 344                              //                small form variants
 345     kRangeTableBase+8,       //uffxx, halfwidth and fullwidth forms, includes Specials
 346   },
 347   { //table for 0x0500 - 0x05ff
 348     kRangeCyrillic,          //u050x
 349     kRangeCyrillic,          //u051x
 350     kRangeCyrillic,          //u052x
 351     kRangeArmenian,          //u053x
 352     kRangeArmenian,          //u054x
 353     kRangeArmenian,          //u055x
 354     kRangeArmenian,          //u056x
 355     kRangeArmenian,          //u057x
 356     kRangeArmenian,          //u058x
 357     kRangeHebrew,            //u059x
 358     kRangeHebrew,            //u05ax
 359     kRangeHebrew,            //u05bx
 360     kRangeHebrew,            //u05cx
 361     kRangeHebrew,            //u05dx
 362     kRangeHebrew,            //u05ex
 363     kRangeHebrew,            //u05fx
 364   },
 365   { //table for 0xff00 - 0xffff
 366     kRangeSetCJK,            //uff0x, fullwidth latin
 367     kRangeSetCJK,            //uff1x, fullwidth latin
 368     kRangeSetCJK,            //uff2x, fullwidth latin
 369     kRangeSetCJK,            //uff3x, fullwidth latin
 370     kRangeSetCJK,            //uff4x, fullwidth latin
 371     kRangeSetCJK,            //uff5x, fullwidth latin
 372     kRangeSetCJK,            //uff6x, halfwidth katakana
 373     kRangeSetCJK,            //uff7x, halfwidth katakana
 374     kRangeSetCJK,            //uff8x, halfwidth katakana
 375     kRangeSetCJK,            //uff9x, halfwidth katakana
 376     kRangeSetCJK,            //uffax, halfwidth hangul jamo
 377     kRangeSetCJK,            //uffbx, halfwidth hangul jamo
 378     kRangeSetCJK,            //uffcx, halfwidth hangul jamo
 379     kRangeSetCJK,            //uffdx, halfwidth hangul jamo
 380     kRangeSetCJK,            //uffex, fullwidth symbols
 381     kRangeSpecials,          //ufffx, Specials
 382   },
 383 };
 384
 385 // Most scripts between U+0700 and U+16FF are assigned a chunk of 128 (0x80)
 386 // code points  so that the number of entries in the tertiary range
 387 // table for that range is obtained by dividing (0x1700 - 0x0700) by 128.
 388 // Exceptions: Ethiopic, Tibetan, Hangul Jamo and Canadian aboriginal
 389 // syllabaries take multiple chunks and Ogham and Runic share  a single chunk.
 390 #define TERTIARY_TABLE_SIZE ((0x1700 - 0x0700) / 0x80)
 391
 392 static const PRUint8 gUnicodeTertiaryRangeTable[TERTIARY_TABLE_SIZE] =
 393 { //table for 0x0700 - 0x1600
 394     kRangeSyriac,            //u070x
 395     kRangeThaana,            //u078x
 396     kRangeUnassigned,        //u080x  place holder(resolved in the 2ndary tab.)
 397     kRangeUnassigned,        //u088x  place holder(resolved in the 2ndary tab.)
 398     kRangeDevanagari,        //u090x
 399     kRangeBengali,           //u098x
 400     kRangeGurmukhi,          //u0a0x
 401     kRangeGujarati,          //u0a8x
 402     kRangeOriya,             //u0b0x
 403     kRangeTamil,             //u0b8x
 404     kRangeTelugu,            //u0c0x
 405     kRangeKannada,           //u0c8x
 406     kRangeMalayalam,         //u0d0x
 407     kRangeSinhala,           //u0d8x
 408     kRangeThai,              //u0e0x
 409     kRangeLao,               //u0e8x
 410     kRangeTibetan,           //u0f0x  place holder(resolved in the 2ndary tab.)
 411     kRangeTibetan,           //u0f8x  place holder(resolved in the 2ndary tab.)
 412     kRangeMyanmar,           //u100x
 413     kRangeGeorgian,          //u108x
 414     kRangeKorean,            //u110x  place holder(resolved in the 2ndary tab.)
 415     kRangeKorean,            //u118x  place holder(resolved in the 2ndary tab.)
 416     kRangeEthiopic,          //u120x  place holder(resolved in the 2ndary tab.)
 417     kRangeEthiopic,          //u128x  place holder(resolved in the 2ndary tab.)
 418     kRangeEthiopic,          //u130x
 419     kRangeCherokee,          //u138x
 420     kRangeCanadian,          //u140x  place holder(resolved in the 2ndary tab.)
 421     kRangeCanadian,          //u148x  place holder(resolved in the 2ndary tab.)
 422     kRangeCanadian,          //u150x  place holder(resolved in the 2ndary tab.)
 423     kRangeCanadian,          //u158x  place holder(resolved in the 2ndary tab.)
 424     kRangeCanadian,          //u160x
 425     kRangeOghamRunic,        //u168x  this contains two scripts, Ogham & Runic
 426 };
 427
 428 // A two level index is almost enough for locating a range, with the
 429 // exception of u03xx and u05xx. Since we don't really care about range for
 430 // combining diacritical marks in our font application, they are
 431 // not discriminated further. But future adoption of this module for other use
 432 // should be aware of this limitation. The implementation can be extended if
 433 // there is such a need.
 434 // For Indic, Southeast Asian scripts and some other scripts between
 435 // U+0700 and U+16FF, it's extended to the third level.
 436 PRUint32 FindCharUnicodeRange(PRUnichar ch)
 437 {
 438   PRUint32 range;
 439
 440   //search the first table
 441   range = gUnicodeSubrangeTable[0][ch >> 12];
 442
 443   if (range < kRangeTableBase)
 444     // we try to get a specific range
 445     return range;
 446
 447   // otherwise, we have one more table to look at
 448   range = gUnicodeSubrangeTable[range - kRangeTableBase][(ch & 0x0f00) >> 8];
 449   if (range < kRangeTableBase)
 450     return range;
 451   if (range < kRangeTertiaryTable)
 452     return gUnicodeSubrangeTable[range - kRangeTableBase][(ch & 0x00f0) >> 4];
 453
 454   // Yet another table to look at : U+0700 - U+16FF : 128 code point blocks
 455   return gUnicodeTertiaryRangeTable[(ch - 0x0700) >> 7];
 456 }
 457
 458 const char* LangGroupFromUnicodeRange(PRUint8 unicodeRange)
 459 {
 460   if (kRangeSpecificItemNum > unicodeRange)
 461     return gUnicodeRangeToLangGroupTable[unicodeRange];
 462   return nsnull;
 463 }