dlls/dwrite/analyzer.c

   1 /*
   2  *    Text analyzer
   3  *
   4  * Copyright 2012 Nikolay Sivov for CodeWeavers
   5  *
   6  * This library is free software; you can redistribute it and/or
   7  * modify it under the terms of the GNU Lesser General Public
   8  * License as published by the Free Software Foundation; either
   9  * version 2.1 of the License, or (at your option) any later version.
  10  *
  11  * This library is distributed in the hope that it will be useful,
  12  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  13  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  14  * Lesser General Public License for more details.
  15  *
  16  * You should have received a copy of the GNU Lesser General Public
  17  * License along with this library; if not, write to the Free Software
  18  * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301, USA
  19  */
  20
  21 #define COBJMACROS
  22
  23 #include "dwrite.h"
  24 #include "dwrite_private.h"
  25
  26 #include "wine/debug.h"
  27
  28 WINE_DEFAULT_DEBUG_CHANNEL(dwrite);
  29
  30 enum scriptcode {
  31     Script_Arabic = 0,
  32     Script_Armenian = 1,
  33     Script_Balinese = 2,
  34     Script_Bengali = 3,
  35     Script_Buginese = 6,
  36     Script_Canadian = 8,
  37     Script_Cherokee = 11,
  38     Script_Controls = 12,
  39     Script_Coptic = 13,
  40     Script_Cyrillic = 16,
  41     Script_Devanagari = 18,
  42     Script_Ethiopic = 19,
  43     Script_Georgian = 20,
  44     Script_Glagolitic = 22,
  45     Script_Greek = 23,
  46     Script_Gujarati = 24,
  47     Script_Gurmukhi = 25,
  48     Script_Hangul = 27,
  49     Script_Hebrew = 29,
  50     Script_Kannada = 32,
  51     Script_Khmer = 36,
  52     Script_Lao = 37,
  53     Script_Latin = 38,
  54     Script_Lepcha = 39,
  55     Script_Limbu = 40,
  56     Script_Malayalam = 44,
  57     Script_Mongolian = 45,
  58     Script_Myanmar = 46,
  59     Script_New_TaiLue = 47,
  60     Script_NKo = 48,
  61     Script_Ogham = 49,
  62     Script_OlChiki = 50,
  63     Script_Oriya = 53,
  64     Script_Runic = 58,
  65     Script_Sinhala = 61,
  66     Script_Sundanese = 62,
  67     Script_Syriac = 64,
  68     Script_TaiLe = 67,
  69     Script_Tamil = 68,
  70     Script_Telugu = 69,
  71     Script_Thaana = 70,
  72     Script_Thai = 71,
  73     Script_Tibetan = 72,
  74     Script_Tifinagh = 73,
  75     Script_Symbol = 77,
  76     Script_Unknown = (UINT16)-1
  77 };
  78
  79 struct script_range {
  80     UINT16 script;
  81     DWORD first;
  82     DWORD last;
  83 };
  84
  85 static const struct script_range script_ranges[] = {
  86     /* C0 Controls: U+0000–U+001F */
  87     /* ASCII punctuation and symbols: U+0020–U+002F */
  88     /* ASCII digits: U+0030–U+0039 */
  89     /* ASCII punctuation and symbols: U+003A–U+0040 */
  90     { Script_Symbol, 0x00, 0x040 },
  91     /* Latin uppercase: U+0041–U+005A */
  92     { Script_Latin, 0x41, 0x5a },
  93     /* ASCII punctuation and symbols: U+005B–U+0060 */
  94     { Script_Symbol, 0x5b, 0x060 },
  95     /* Latin lowercase: U+0061–U+007A */
  96     { Script_Latin, 0x61, 0x7a },
  97     /* ASCII punctuation and symbols, control char DEL: U+007B–U+007F */
  98     { Script_Symbol, 0x7b, 0x7f },
  99     /* C1 Controls: U+0080–U+009F */
 100     { Script_Controls, 0x80, 0x9f },
 101     /* Latin-1 Supplement: U+00A0–U+00FF */
 102     /* Latin Extended-A: U+0100–U+017F */
 103     /* Latin Extended-B: U+0180–U+024F */
 104     /* IPA Extensions: U+0250–U+02AF */
 105     /* Spacing Modifier Letters: U+02B0–U+02FF */
 106     { Script_Latin, 0xa0, 0x2ff },
 107     /* Combining Diacritical Marks: U+0300–U+036F */
 108     { Script_Symbol, 0x300, 0x36f },
 109     /* Greek: U+0370–U+03E1 */
 110     { Script_Greek, 0x370, 0x3e1 },
 111     /* Coptic: U+03E2–U+03Ef */
 112     { Script_Coptic, 0x3e2, 0x3ef },
 113     /* Greek: U+03F0–U+03FF */
 114     { Script_Greek, 0x3f0, 0x3ff },
 115     /* Cyrillic: U+0400–U+04FF */
 116     /* Cyrillic Supplement: U+0500–U+052F */
 117     /* Cyrillic Supplement range is incomplete cause it's based on Unicode 5.2
 118        that doesn't define some Abkhaz and Azerbaijani letters, we support Unicode 6.0 range here */
 119     { Script_Cyrillic, 0x400, 0x52f },
 120     /* Armenian: U+0530–U+058F */
 121     { Script_Armenian, 0x530, 0x58f },
 122     /* Hebrew: U+0590–U+05FF */
 123     { Script_Hebrew, 0x590, 0x5ff },
 124     /* Arabic: U+0600–U+06FF */
 125     { Script_Arabic, 0x600, 0x6ff },
 126     /* Syriac: U+0600–U+06FF */
 127     { Script_Syriac, 0x700, 0x74f },
 128     /* Arabic Supplement: U+0750–U+077F */
 129     { Script_Arabic, 0x750, 0x77f },
 130     /* Thaana: U+0780–U+07BF */
 131     { Script_Thaana, 0x780, 0x7bf },
 132     /* N'Ko: U+07C0–U+07FF */
 133     { Script_NKo, 0x7c0, 0x7ff },
 134     /* Devanagari: U+0900–U+097F */
 135     { Script_Devanagari, 0x900, 0x97f },
 136     /* Bengali: U+0980–U+09FF */
 137     { Script_Bengali, 0x980, 0x9ff },
 138     /* Gurmukhi: U+0A00–U+0A7F */
 139     { Script_Gurmukhi, 0xa00, 0xa7f },
 140     /* Gujarati: U+0A80–U+0AFF */
 141     { Script_Gujarati, 0xa80, 0xaff },
 142     /* Oriya: U+0B00–U+0B7F */
 143     { Script_Oriya, 0xb00, 0xb7f },
 144     /* Tamil: U+0B80–U+0BFF */
 145     { Script_Tamil, 0xb80, 0xbff },
 146     /* Telugu: U+0C00–U+0C7F */
 147     { Script_Telugu, 0xc00, 0xc7f },
 148     /* Kannada: U+0C80–U+0CFF */
 149     { Script_Kannada, 0xc80, 0xcff },
 150     /* Malayalam: U+0D00–U+0D7F */
 151     { Script_Malayalam, 0xd00, 0xd7f },
 152     /* Sinhala: U+0D80–U+0DFF */
 153     { Script_Sinhala, 0xd80, 0xdff },
 154     /* Thai: U+0E00–U+0E7F */
 155     { Script_Thai, 0xe00, 0xe7f },
 156     /* Lao: U+0E80–U+0EFF */
 157     { Script_Lao, 0xe80, 0xeff },
 158     /* Tibetan: U+0F00–U+0FFF */
 159     { Script_Tibetan, 0xf00, 0xfff },
 160     /* Myanmar: U+1000–U+109F */
 161     { Script_Myanmar, 0x1000, 0x109f },
 162     /* Georgian: U+10A0–U+10FF */
 163     { Script_Georgian, 0x10a0, 0x10ff },
 164     /* Hangul Jamo: U+1100–U+11FF */
 165     { Script_Hangul, 0x1100, 0x11ff },
 166     /* Ethiopic: U+1200–U+137F */
 167     /* Ethiopic Extensions: U+1380–U+139F */
 168     { Script_Ethiopic, 0x1200, 0x139f },
 169     /* Cherokee: U+13A0–U+13FF */
 170     { Script_Cherokee, 0x13a0, 0x13ff },
 171     /* Canadian Aboriginal Syllabics: U+1400–U+167F */
 172     { Script_Canadian, 0x1400, 0x167f },
 173     /* Ogham: U+1680–U+169F */
 174     { Script_Ogham, 0x1680, 0x169f },
 175     /* Runic: U+16A0–U+16F0 */
 176     { Script_Runic, 0x16a0, 0x16f0 },
 177     /* Khmer: U+1780–U+17FF */
 178     { Script_Khmer, 0x1780, 0x17ff },
 179     /* Mongolian: U+1800–U+18AF */
 180     { Script_Mongolian, 0x1800, 0x18af },
 181     /* Limbu: U+1900–U+194F */
 182     { Script_Limbu, 0x1900, 0x194f },
 183     /* Tai Le: U+1950–U+197F */
 184     { Script_TaiLe, 0x1950, 0x197f },
 185     /* New Tai Lue: U+1980–U+19DF */
 186     { Script_New_TaiLue, 0x1980, 0x19df },
 187     /* Khmer Symbols: U+19E0–U+19FF */
 188     { Script_Khmer, 0x19e0, 0x19ff },
 189     /* Buginese: U+1A00–U+1A1F */
 190     { Script_Buginese, 0x1a00, 0x1a1f },
 191     /* Tai Tham: U+1A20–U+1AAF */
 192     { Script_Symbol, 0x1a20, 0x1aaf },
 193     /* Balinese: U+1B00–U+1B7F */
 194     { Script_Balinese, 0x1b00, 0x1b7f },
 195     /* Sundanese: U+1B80–U+1BBF */
 196     { Script_Sundanese, 0x1b80, 0x1bbf },
 197     /* Batak: U+1BC0–U+1BFF */
 198     { Script_Symbol, 0x1bc0, 0x1bff },
 199     /* Lepcha: U+1C00–U+1C4F */
 200     { Script_Lepcha, 0x1c00, 0x1c4f },
 201     /* Ol Chiki: U+1C50–U+1C7F */
 202     { Script_OlChiki, 0x1c50, 0x1c7f },
 203     /* Sundanese Supplement: U+1CC0–U+1CCF */
 204     { Script_Symbol, 0x1cc0, 0x1ccf },
 205     /* Vedic Extensions: U+1CD0-U+1CFF */
 206     { Script_Devanagari, 0x1cd0, 0x1cff },
 207     /* Phonetic Extensions: U+1D00–U+1DBF */
 208     { Script_Latin, 0x1d00, 0x1dbf },
 209     /* Combining Diacritical Marks Supplement: U+1DC0–U+1DFF */
 210     { Script_Symbol, 0x1dc0, 0x1dff },
 211     /* Latin Extended Additional: U+1E00–U+1EFF */
 212     { Script_Latin, 0x1e00, 0x1eff },
 213     /* Greek Extended: U+1F00–U+1F00 */
 214     { Script_Greek, 0x1f00, 0x1fff },
 215     /* General Punctuation: U+2000–U+206f */
 216     /* Superscripts and Subscripts: U+2070–U+209f */
 217     /* Currency Symbols: U+20A0–U+20CF */
 218     /* Combining Diacritical Marks for Symbols: U+20D0–U+20FF */
 219     /* Letterlike Symbols: U+2100–U+214F */
 220     /* Number Forms: U+2150–U+218F */
 221     /* Arrows: U+2190–U+21FF */
 222     /* Mathematical Operators: U+2200–U+22FF */
 223     /* Miscellaneous Technical: U+2300–U+23FF */
 224     /* Control Pictures: U+2400–U+243F */
 225     /* Optical Character Recognition: U+2440–U+245F */
 226     /* Enclosed Alphanumerics: U+2460–U+24FF */
 227     /* Box Drawing: U+2500–U+25FF */
 228     /* Block Elements: U+2580–U+259F */
 229     /* Geometric Shapes: U+25A0–U+25FF */
 230     /* Miscellaneous Symbols: U+2600–U+26FF */
 231     /* Dingbats: U+2700–U+27BF */
 232     /* Miscellaneous Mathematical Symbols-A: U+27C0–U+27EF */
 233     /* Supplemental Arrows-A: U+27F0–U+27FF */
 234     /* Braille Patterns: U+2800–U+28FF */
 235     /* Supplemental Arrows-B: U+2900–U+297F */
 236     /* Miscellaneous Mathematical Symbols-B: U+2980–U+29FF */
 237     /* Supplemental Mathematical Operators: U+2A00–U+2AFF */
 238     /* Miscellaneous Symbols and Arrows: U+2B00–U+2BFF */
 239     { Script_Symbol, 0x2000, 0x2bff },
 240     /* Glagolitic: U+2C00–U+2C5F */
 241     { Script_Glagolitic, 0x2c00, 0x2c5f },
 242     /* Latin Extended-C: U+2C60–U+2C7F */
 243     { Script_Latin, 0x2c60, 0x2c7f },
 244     /* Coptic: U+2C80–U+2CFF */
 245     { Script_Coptic, 0x2c80, 0x2cff },
 246     /* Georgian Supplement: U+2D00–U+2D2F */
 247     { Script_Georgian, 0x2d00, 0x2d2f },
 248     /* Tifinagh: U+2D30–U+2D7F */
 249     { Script_Tifinagh, 0x2d30, 0x2d7f },
 250     /* unsupported range */
 251     { Script_Unknown }
 252 };
 253
 254 static UINT16 get_char_script( WCHAR c )
 255 {
 256     DWORD ch = c;
 257     unsigned int i;
 258
 259     for (i = 0; i < sizeof(script_ranges)/sizeof(struct script_range); i++)
 260     {
 261         const struct script_range *range = &script_ranges[i];
 262         if (range->script == Script_Unknown || (range->first <= ch && range->last >= ch))
 263             return range->script;
 264     }
 265
 266     return Script_Unknown;
 267 }
 268
 269 static HRESULT analyze_script(const WCHAR *text, UINT32 len, IDWriteTextAnalysisSink *sink)
 270 {
 271     DWRITE_SCRIPT_ANALYSIS sa;
 272     UINT32 pos, i, length;
 273
 274     if (!len) return S_OK;
 275
 276     sa.script = get_char_script(*text);
 277
 278     pos = 0;
 279     length = 1;
 280
 281     for (i = 1; i < len; i++)
 282     {
 283         UINT16 script = get_char_script(text[i]);
 284
 285         /* Script_Latin_Symb script type is ignored when preceded or followed by another script */
 286         if (sa.script == Script_Symbol) sa.script = script;
 287         if (script    == Script_Symbol) script = sa.script;
 288         /* this is a length of a sequence to be reported next */
 289         if (sa.script == script) length++;
 290
 291         if (sa.script != script)
 292         {
 293             HRESULT hr;
 294
 295             sa.shapes = sa.script != Script_Controls ? DWRITE_SCRIPT_SHAPES_DEFAULT : DWRITE_SCRIPT_SHAPES_NO_VISUAL;
 296             hr = IDWriteTextAnalysisSink_SetScriptAnalysis(sink, pos, length, &sa);
 297             if (FAILED(hr)) return hr;
 298             pos = i;
 299             length = 1;
 300             sa.script = script;
 301         }
 302     }
 303
 304     /* 1 length case or normal completion call */
 305     sa.shapes = sa.script != Script_Controls ? DWRITE_SCRIPT_SHAPES_DEFAULT : DWRITE_SCRIPT_SHAPES_NO_VISUAL;
 306     return IDWriteTextAnalysisSink_SetScriptAnalysis(sink, pos, length, &sa);
 307 }
 308
 309 static HRESULT WINAPI dwritetextanalyzer_QueryInterface(IDWriteTextAnalyzer *iface, REFIID riid, void **obj)
 310 {
 311     TRACE("(%s %p)\n", debugstr_guid(riid), obj);
 312
 313     if (IsEqualIID(riid, &IID_IUnknown) || IsEqualIID(riid, &IID_IDWriteTextAnalyzer))
 314     {
 315         *obj = iface;
 316         return S_OK;
 317     }
 318
 319     *obj = NULL;
 320     return E_NOINTERFACE;
 321
 322 }
 323
 324 static ULONG WINAPI dwritetextanalyzer_AddRef(IDWriteTextAnalyzer *iface)
 325 {
 326     return 2;
 327 }
 328
 329 static ULONG WINAPI dwritetextanalyzer_Release(IDWriteTextAnalyzer *iface)
 330 {
 331     return 1;
 332 }
 333
 334 static HRESULT WINAPI dwritetextanalyzer_AnalyzeScript(IDWriteTextAnalyzer *iface,
 335     IDWriteTextAnalysisSource* source, UINT32 position, UINT32 length, IDWriteTextAnalysisSink* sink)
 336 {
 337     const WCHAR *text;
 338     HRESULT hr;
 339     UINT32 len;
 340
 341     TRACE("(%p %u %u %p)\n", source, position, length, sink);
 342
 343     hr = IDWriteTextAnalysisSource_GetTextAtPosition(source, position, &text, &len);
 344     if (FAILED(hr)) return hr;
 345
 346     return analyze_script(text, len, sink);
 347 }
 348
 349 static HRESULT WINAPI dwritetextanalyzer_AnalyzeBidi(IDWriteTextAnalyzer *iface,
 350     IDWriteTextAnalysisSource* source, UINT32 position, UINT32 length, IDWriteTextAnalysisSink* sink)
 351 {
 352     FIXME("(%p %u %u %p): stub\n", source, position, length, sink);
 353     return E_NOTIMPL;
 354 }
 355
 356 static HRESULT WINAPI dwritetextanalyzer_AnalyzeNumberSubstitution(IDWriteTextAnalyzer *iface,
 357     IDWriteTextAnalysisSource* source, UINT32 position, UINT32 length, IDWriteTextAnalysisSink* sink)
 358 {
 359     FIXME("(%p %u %u %p): stub\n", source, position, length, sink);
 360     return E_NOTIMPL;
 361 }
 362
 363 static HRESULT WINAPI dwritetextanalyzer_AnalyzeLineBreakpoints(IDWriteTextAnalyzer *iface,
 364     IDWriteTextAnalysisSource* source, UINT32 position, UINT32 length, IDWriteTextAnalysisSink* sink)
 365 {
 366     FIXME("(%p %u %u %p): stub\n", source, position, length, sink);
 367     return E_NOTIMPL;
 368 }
 369
 370 static HRESULT WINAPI dwritetextanalyzer_GetGlyphs(IDWriteTextAnalyzer *iface,
 371     WCHAR const* text, UINT32 length, IDWriteFontFace* font_face, BOOL is_sideways,
 372     BOOL is_rtl, DWRITE_SCRIPT_ANALYSIS const* analysis, WCHAR const* locale,
 373     IDWriteNumberSubstitution* substitution, DWRITE_TYPOGRAPHIC_FEATURES const** features,
 374     UINT32 const* feature_range_len, UINT32 feature_ranges, UINT32 max_glyph_count,
 375     UINT16* clustermap, DWRITE_SHAPING_TEXT_PROPERTIES* text_props, UINT16* glyph_indices,
 376     DWRITE_SHAPING_GLYPH_PROPERTIES* glyph_props, UINT32* actual_glyph_count)
 377 {
 378     FIXME("(%s:%u %p %d %d %p %s %p %p %p %u %u %p %p %p %p %p): stub\n", debugstr_wn(text, length),
 379         length, font_face, is_sideways, is_rtl, analysis, debugstr_w(locale), substitution, features, feature_range_len,
 380         feature_ranges, max_glyph_count, clustermap, text_props, glyph_indices, glyph_props, actual_glyph_count);
 381     return E_NOTIMPL;
 382 }
 383
 384 static HRESULT WINAPI dwritetextanalyzer_GetGlyphPlacements(IDWriteTextAnalyzer *iface,
 385     WCHAR const* text, UINT16 const* clustermap, DWRITE_SHAPING_TEXT_PROPERTIES* props,
 386     UINT32 text_len, UINT16 const* glyph_indices, DWRITE_SHAPING_GLYPH_PROPERTIES const* glyph_props,
 387     UINT32 glyph_count, IDWriteFontFace * font_face, FLOAT fontEmSize, BOOL is_sideways, BOOL is_rtl,
 388     DWRITE_SCRIPT_ANALYSIS const* analysis, WCHAR const* locale, DWRITE_TYPOGRAPHIC_FEATURES const** features,
 389     UINT32 const* feature_range_len, UINT32 feature_ranges, FLOAT* glyph_advances, DWRITE_GLYPH_OFFSET* glyph_offsets)
 390 {
 391     FIXME("(%s %p %p %u %p %p %u %p %f %d %d %p %s %p %p %u %p %p): stub\n", debugstr_w(text),
 392         clustermap, props, text_len, glyph_indices, glyph_props, glyph_count, font_face, fontEmSize, is_sideways,
 393         is_rtl, analysis, debugstr_w(locale), features, feature_range_len, feature_ranges, glyph_advances, glyph_offsets);
 394     return E_NOTIMPL;
 395 }
 396
 397 static HRESULT WINAPI dwritetextanalyzer_GetGdiCompatibleGlyphPlacements(IDWriteTextAnalyzer *iface,
 398     WCHAR const* text, UINT16 const* clustermap, DWRITE_SHAPING_TEXT_PROPERTIES* props,
 399     UINT32 text_len, UINT16 const* glyph_indices, DWRITE_SHAPING_GLYPH_PROPERTIES const* glyph_props,
 400     UINT32 glyph_count, IDWriteFontFace * font_face, FLOAT fontEmSize, FLOAT pixels_per_dip,
 401     DWRITE_MATRIX const* transform, BOOL use_gdi_natural, BOOL is_sideways, BOOL is_rtl,
 402     DWRITE_SCRIPT_ANALYSIS const* analysis, WCHAR const* locale, DWRITE_TYPOGRAPHIC_FEATURES const** features,
 403     UINT32 const* feature_range_lengths, UINT32 feature_ranges, FLOAT* glyph_advances, DWRITE_GLYPH_OFFSET* glyph_offsets)
 404 {
 405     FIXME("(%s %p %p %u %p %p %u %p %f %f %p %d %d %d %p %s %p %p %u %p %p): stub\n", debugstr_w(text),
 406         clustermap, props, text_len, glyph_indices, glyph_props, glyph_count, font_face, fontEmSize, pixels_per_dip,
 407         transform, use_gdi_natural, is_sideways, is_rtl, analysis, debugstr_w(locale), features, feature_range_lengths,
 408         feature_ranges, glyph_advances, glyph_offsets);
 409     return E_NOTIMPL;
 410 }
 411
 412 static const struct IDWriteTextAnalyzerVtbl textanalyzervtbl = {
 413     dwritetextanalyzer_QueryInterface,
 414     dwritetextanalyzer_AddRef,
 415     dwritetextanalyzer_Release,
 416     dwritetextanalyzer_AnalyzeScript,
 417     dwritetextanalyzer_AnalyzeBidi,
 418     dwritetextanalyzer_AnalyzeNumberSubstitution,
 419     dwritetextanalyzer_AnalyzeLineBreakpoints,
 420     dwritetextanalyzer_GetGlyphs,
 421     dwritetextanalyzer_GetGlyphPlacements,
 422     dwritetextanalyzer_GetGdiCompatibleGlyphPlacements
 423 };
 424
 425 static IDWriteTextAnalyzer textanalyzer = { &textanalyzervtbl };
 426
 427 HRESULT get_textanalyzer(IDWriteTextAnalyzer **ret)
 428 {
 429     *ret = &textanalyzer;
 430     return S_OK;
 431 }