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_Greek = 23,
  45     Script_Gujarati = 24,
  46     Script_Gurmukhi = 25,
  47     Script_Hangul = 27,
  48     Script_Hebrew = 29,
  49     Script_Kannada = 32,
  50     Script_Khmer = 36,
  51     Script_Lao = 37,
  52     Script_Latin = 38,
  53     Script_Lepcha = 39,
  54     Script_Limbu = 40,
  55     Script_Malayalam = 44,
  56     Script_Mongolian = 45,
  57     Script_Myanmar = 46,
  58     Script_New_TaiLue = 47,
  59     Script_NKo = 48,
  60     Script_Ogham = 49,
  61     Script_OlChiki = 50,
  62     Script_Oriya = 53,
  63     Script_Runic = 58,
  64     Script_Sinhala = 61,
  65     Script_Sundanese = 62,
  66     Script_Syriac = 64,
  67     Script_TaiLe = 67,
  68     Script_Tamil = 68,
  69     Script_Telugu = 69,
  70     Script_Thaana = 70,
  71     Script_Thai = 71,
  72     Script_Tibetan = 72,
  73     Script_Symbol = 77,
  74     Script_Unknown = (UINT16)-1
  75 };
  76
  77 struct script_range {
  78     UINT16 script;
  79     DWORD first;
  80     DWORD last;
  81 };
  82
  83 static const struct script_range script_ranges[] = {
  84     /* C0 Controls: U+0000–U+001F */
  85     /* ASCII punctuation and symbols: U+0020–U+002F */
  86     /* ASCII digits: U+0030–U+0039 */
  87     /* ASCII punctuation and symbols: U+003A–U+0040 */
  88     { Script_Symbol, 0x00, 0x040 },
  89     /* Latin uppercase: U+0041–U+005A */
  90     { Script_Latin, 0x41, 0x5a },
  91     /* ASCII punctuation and symbols: U+005B–U+0060 */
  92     { Script_Symbol, 0x5b, 0x060 },
  93     /* Latin lowercase: U+0061–U+007A */
  94     { Script_Latin, 0x61, 0x7a },
  95     /* ASCII punctuation and symbols, control char DEL: U+007B–U+007F */
  96     { Script_Symbol, 0x7b, 0x7f },
  97     /* C1 Controls: U+0080–U+009F */
  98     { Script_Controls, 0x80, 0x9f },
  99     /* Latin-1 Supplement: U+00A0–U+00FF */
 100     /* Latin Extended-A: U+0100–U+017F */
 101     /* Latin Extended-B: U+0180–U+024F */
 102     /* IPA Extensions: U+0250–U+02AF */
 103     /* Spacing Modifier Letters: U+02B0–U+02FF */
 104     { Script_Latin, 0xa0, 0x2ff },
 105     /* Combining Diacritical Marks: U+0300–U+036F */
 106     { Script_Symbol, 0x300, 0x36f },
 107     /* Greek: U+0370–U+03E1 */
 108     { Script_Greek, 0x370, 0x3e1 },
 109     /* Coptic: U+03E2–U+03Ef */
 110     { Script_Coptic, 0x3e2, 0x3ef },
 111     /* Greek: U+03F0–U+03FF */
 112     { Script_Greek, 0x3f0, 0x3ff },
 113     /* Cyrillic: U+0400–U+04FF */
 114     /* Cyrillic Supplement: U+0500–U+052F */
 115     /* Cyrillic Supplement range is incomplete cause it's based on Unicode 5.2
 116        that doesn't define some Abkhaz and Azerbaijani letters, we support Unicode 6.0 range here */
 117     { Script_Cyrillic, 0x400, 0x52f },
 118     /* Armenian: U+0530–U+058F */
 119     { Script_Armenian, 0x530, 0x58f },
 120     /* Hebrew: U+0590–U+05FF */
 121     { Script_Hebrew, 0x590, 0x5ff },
 122     /* Arabic: U+0600–U+06FF */
 123     { Script_Arabic, 0x600, 0x6ff },
 124     /* Syriac: U+0600–U+06FF */
 125     { Script_Syriac, 0x700, 0x74f },
 126     /* Arabic Supplement: U+0750–U+077F */
 127     { Script_Arabic, 0x750, 0x77f },
 128     /* Thaana: U+0780–U+07BF */
 129     { Script_Thaana, 0x780, 0x7bf },
 130     /* N'Ko: U+07C0–U+07FF */
 131     { Script_NKo, 0x7c0, 0x7ff },
 132     /* Devanagari: U+0900–U+097F */
 133     { Script_Devanagari, 0x900, 0x97f },
 134     /* Bengali: U+0980–U+09FF */
 135     { Script_Bengali, 0x980, 0x9ff },
 136     /* Gurmukhi: U+0A00–U+0A7F */
 137     { Script_Gurmukhi, 0xa00, 0xa7f },
 138     /* Gujarati: U+0A80–U+0AFF */
 139     { Script_Gujarati, 0xa80, 0xaff },
 140     /* Oriya: U+0B00–U+0B7F */
 141     { Script_Oriya, 0xb00, 0xb7f },
 142     /* Tamil: U+0B80–U+0BFF */
 143     { Script_Tamil, 0xb80, 0xbff },
 144     /* Telugu: U+0C00–U+0C7F */
 145     { Script_Telugu, 0xc00, 0xc7f },
 146     /* Kannada: U+0C80–U+0CFF */
 147     { Script_Kannada, 0xc80, 0xcff },
 148     /* Malayalam: U+0D00–U+0D7F */
 149     { Script_Malayalam, 0xd00, 0xd7f },
 150     /* Sinhala: U+0D80–U+0DFF */
 151     { Script_Sinhala, 0xd80, 0xdff },
 152     /* Thai: U+0E00–U+0E7F */
 153     { Script_Thai, 0xe00, 0xe7f },
 154     /* Lao: U+0E80–U+0EFF */
 155     { Script_Lao, 0xe80, 0xeff },
 156     /* Tibetan: U+0F00–U+0FFF */
 157     { Script_Tibetan, 0xf00, 0xfff },
 158     /* Myanmar: U+1000–U+109F */
 159     { Script_Myanmar, 0x1000, 0x109f },
 160     /* Georgian: U+10A0–U+10FF */
 161     { Script_Georgian, 0x10a0, 0x10ff },
 162     /* Hangul Jamo: U+1100–U+11FF */
 163     { Script_Hangul, 0x1100, 0x11ff },
 164     /* Ethiopic: U+1200–U+137F */
 165     /* Ethiopic Extensions: U+1380–U+139F */
 166     { Script_Ethiopic, 0x1200, 0x139f },
 167     /* Cherokee: U+13A0–U+13FF */
 168     { Script_Cherokee, 0x13a0, 0x13ff },
 169     /* Canadian Aboriginal Syllabics: U+1400–U+167F */
 170     { Script_Canadian, 0x1400, 0x167f },
 171     /* Ogham: U+1680–U+169F */
 172     { Script_Ogham, 0x1680, 0x169f },
 173     /* Runic: U+16A0–U+16F0 */
 174     { Script_Runic, 0x16a0, 0x16f0 },
 175     /* Khmer: U+1780–U+17FF */
 176     { Script_Khmer, 0x1780, 0x17ff },
 177     /* Mongolian: U+1800–U+18AF */
 178     { Script_Mongolian, 0x1800, 0x18af },
 179     /* Limbu: U+1900–U+194F */
 180     { Script_Limbu, 0x1900, 0x194f },
 181     /* Tai Le: U+1950–U+197F */
 182     { Script_TaiLe, 0x1950, 0x197f },
 183     /* New Tai Lue: U+1980–U+19DF */
 184     { Script_New_TaiLue, 0x1980, 0x19df },
 185     /* Khmer Symbols: U+19E0–U+19FF */
 186     { Script_Khmer, 0x19e0, 0x19ff },
 187     /* Buginese: U+1A00–U+1A1F */
 188     { Script_Buginese, 0x1a00, 0x1a1f },
 189     /* Tai Tham: U+1A20–U+1AAF */
 190     { Script_Symbol, 0x1a20, 0x1aaf },
 191     /* Balinese: U+1B00–U+1B7F */
 192     { Script_Balinese, 0x1b00, 0x1b7f },
 193     /* Sundanese: U+1B80–U+1BBF */
 194     { Script_Sundanese, 0x1b80, 0x1bbf },
 195     /* Batak: U+1BC0–U+1BFF */
 196     { Script_Symbol, 0x1bc0, 0x1bff },
 197     /* Lepcha: U+1C00–U+1C4F */
 198     { Script_Lepcha, 0x1c00, 0x1c4f },
 199     /* Ol Chiki: U+1C50–U+1C7F */
 200     { Script_OlChiki, 0x1c50, 0x1c7f },
 201     /* Sundanese Supplement: U+1CC0–U+1CCF */
 202     { Script_Symbol, 0x1cc0, 0x1ccf },
 203     /* Vedic Extensions: U+1CD0-U+1CFF */
 204     { Script_Devanagari, 0x1cd0, 0x1cff },
 205     /* Phonetic Extensions: U+1D00–U+1DBF */
 206     { Script_Latin, 0x1d00, 0x1dbf },
 207     /* unsupported range */
 208     { Script_Unknown }
 209 };
 210
 211 static UINT16 get_char_script( WCHAR c )
 212 {
 213     DWORD ch = c;
 214     int i;
 215
 216     for (i = 0; i < sizeof(script_ranges)/sizeof(struct script_range); i++)
 217     {
 218         const struct script_range *range = &script_ranges[i];
 219         if (range->script == Script_Unknown || (range->first <= ch && range->last >= ch))
 220             return range->script;
 221     }
 222
 223     return Script_Unknown;
 224 }
 225
 226 static HRESULT analyze_script(const WCHAR *text, UINT32 len, IDWriteTextAnalysisSink *sink)
 227 {
 228     DWRITE_SCRIPT_ANALYSIS sa;
 229     UINT32 pos, i, length;
 230
 231     if (!len) return S_OK;
 232
 233     sa.script = get_char_script(*text);
 234     sa.shapes = DWRITE_SCRIPT_SHAPES_DEFAULT;
 235
 236     pos = 0;
 237     length = 1;
 238
 239     for (i = 1; i < len; i++)
 240     {
 241         UINT16 script = get_char_script(text[i]);
 242
 243         /* Script_Latin_Symb script type is ignored when preceded or followed by another script */
 244         if (sa.script == Script_Symbol) sa.script = script;
 245         if (script    == Script_Symbol) script = sa.script;
 246         /* this is a length of a sequence to be reported next */
 247         if (sa.script == script) length++;
 248
 249         if (sa.script != script)
 250         {
 251             HRESULT hr = IDWriteTextAnalysisSink_SetScriptAnalysis(sink, pos, length, &sa);
 252             if (FAILED(hr)) return hr;
 253             pos = i;
 254             length = 1;
 255             sa.script = script;
 256         }
 257     }
 258
 259     /* 1 length case or normal completion call */
 260     return IDWriteTextAnalysisSink_SetScriptAnalysis(sink, pos, length, &sa);
 261 }
 262
 263 static HRESULT WINAPI dwritetextanalyzer_QueryInterface(IDWriteTextAnalyzer *iface, REFIID riid, void **obj)
 264 {
 265     TRACE("(%s %p)\n", debugstr_guid(riid), obj);
 266
 267     if (IsEqualIID(riid, &IID_IUnknown) || IsEqualIID(riid, &IID_IDWriteTextAnalyzer))
 268     {
 269         *obj = iface;
 270         return S_OK;
 271     }
 272
 273     *obj = NULL;
 274     return E_NOINTERFACE;
 275
 276 }
 277
 278 static ULONG WINAPI dwritetextanalyzer_AddRef(IDWriteTextAnalyzer *iface)
 279 {
 280     return 2;
 281 }
 282
 283 static ULONG WINAPI dwritetextanalyzer_Release(IDWriteTextAnalyzer *iface)
 284 {
 285     return 1;
 286 }
 287
 288 static HRESULT WINAPI dwritetextanalyzer_AnalyzeScript(IDWriteTextAnalyzer *iface,
 289     IDWriteTextAnalysisSource* source, UINT32 position, UINT32 length, IDWriteTextAnalysisSink* sink)
 290 {
 291     const WCHAR *text;
 292     HRESULT hr;
 293     UINT32 len;
 294
 295     TRACE("(%p %u %u %p)\n", source, position, length, sink);
 296
 297     hr = IDWriteTextAnalysisSource_GetTextAtPosition(source, position, &text, &len);
 298     if (FAILED(hr)) return hr;
 299
 300     return analyze_script(text, len, sink);
 301 }
 302
 303 static HRESULT WINAPI dwritetextanalyzer_AnalyzeBidi(IDWriteTextAnalyzer *iface,
 304     IDWriteTextAnalysisSource* source, UINT32 position, UINT32 length, IDWriteTextAnalysisSink* sink)
 305 {
 306     FIXME("(%p %u %u %p): stub\n", source, position, length, sink);
 307     return E_NOTIMPL;
 308 }
 309
 310 static HRESULT WINAPI dwritetextanalyzer_AnalyzeNumberSubstitution(IDWriteTextAnalyzer *iface,
 311     IDWriteTextAnalysisSource* source, UINT32 position, UINT32 length, IDWriteTextAnalysisSink* sink)
 312 {
 313     FIXME("(%p %u %u %p): stub\n", source, position, length, sink);
 314     return E_NOTIMPL;
 315 }
 316
 317 static HRESULT WINAPI dwritetextanalyzer_AnalyzeLineBreakpoints(IDWriteTextAnalyzer *iface,
 318     IDWriteTextAnalysisSource* source, UINT32 position, UINT32 length, IDWriteTextAnalysisSink* sink)
 319 {
 320     FIXME("(%p %u %u %p): stub\n", source, position, length, sink);
 321     return E_NOTIMPL;
 322 }
 323
 324 static HRESULT WINAPI dwritetextanalyzer_GetGlyphs(IDWriteTextAnalyzer *iface,
 325     WCHAR const* text, UINT32 length, IDWriteFontFace* font_face, BOOL is_sideways,
 326     BOOL is_rtl, DWRITE_SCRIPT_ANALYSIS const* analysis, WCHAR const* locale,
 327     IDWriteNumberSubstitution* substitution, DWRITE_TYPOGRAPHIC_FEATURES const** features,
 328     UINT32 const* feature_range_len, UINT32 feature_ranges, UINT32 max_glyph_count,
 329     UINT16* clustermap, DWRITE_SHAPING_TEXT_PROPERTIES* text_props, UINT16* glyph_indices,
 330     DWRITE_SHAPING_GLYPH_PROPERTIES* glyph_props, UINT32* actual_glyph_count)
 331 {
 332     FIXME("(%s:%u %p %d %d %p %s %p %p %p %u %u %p %p %p %p %p): stub\n", debugstr_wn(text, length),
 333         length, font_face, is_sideways, is_rtl, analysis, debugstr_w(locale), substitution, features, feature_range_len,
 334         feature_ranges, max_glyph_count, clustermap, text_props, glyph_indices, glyph_props, actual_glyph_count);
 335     return E_NOTIMPL;
 336 }
 337
 338 static HRESULT WINAPI dwritetextanalyzer_GetGlyphPlacements(IDWriteTextAnalyzer *iface,
 339     WCHAR const* text, UINT16 const* clustermap, DWRITE_SHAPING_TEXT_PROPERTIES* props,
 340     UINT32 text_len, UINT16 const* glyph_indices, DWRITE_SHAPING_GLYPH_PROPERTIES const* glyph_props,
 341     UINT32 glyph_count, IDWriteFontFace * font_face, FLOAT fontEmSize, BOOL is_sideways, BOOL is_rtl,
 342     DWRITE_SCRIPT_ANALYSIS const* analysis, WCHAR const* locale, DWRITE_TYPOGRAPHIC_FEATURES const** features,
 343     UINT32 const* feature_range_len, UINT32 feature_ranges, FLOAT* glyph_advances, DWRITE_GLYPH_OFFSET* glyph_offsets)
 344 {
 345     FIXME("(%s %p %p %u %p %p %u %p %f %d %d %p %s %p %p %u %p %p): stub\n", debugstr_w(text),
 346         clustermap, props, text_len, glyph_indices, glyph_props, glyph_count, font_face, fontEmSize, is_sideways,
 347         is_rtl, analysis, debugstr_w(locale), features, feature_range_len, feature_ranges, glyph_advances, glyph_offsets);
 348     return E_NOTIMPL;
 349 }
 350
 351 static HRESULT WINAPI dwritetextanalyzer_GetGdiCompatibleGlyphPlacements(IDWriteTextAnalyzer *iface,
 352     WCHAR const* text, UINT16 const* clustermap, DWRITE_SHAPING_TEXT_PROPERTIES* props,
 353     UINT32 text_len, UINT16 const* glyph_indices, DWRITE_SHAPING_GLYPH_PROPERTIES const* glyph_props,
 354     UINT32 glyph_count, IDWriteFontFace * font_face, FLOAT fontEmSize, FLOAT pixels_per_dip,
 355     DWRITE_MATRIX const* transform, BOOL use_gdi_natural, BOOL is_sideways, BOOL is_rtl,
 356     DWRITE_SCRIPT_ANALYSIS const* analysis, WCHAR const* locale, DWRITE_TYPOGRAPHIC_FEATURES const** features,
 357     UINT32 const* feature_range_lengths, UINT32 feature_ranges, FLOAT* glyph_advances, DWRITE_GLYPH_OFFSET* glyph_offsets)
 358 {
 359     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),
 360         clustermap, props, text_len, glyph_indices, glyph_props, glyph_count, font_face, fontEmSize, pixels_per_dip,
 361         transform, use_gdi_natural, is_sideways, is_rtl, analysis, debugstr_w(locale), features, feature_range_lengths,
 362         feature_ranges, glyph_advances, glyph_offsets);
 363     return E_NOTIMPL;
 364 }
 365
 366 static const struct IDWriteTextAnalyzerVtbl textanalyzervtbl = {
 367     dwritetextanalyzer_QueryInterface,
 368     dwritetextanalyzer_AddRef,
 369     dwritetextanalyzer_Release,
 370     dwritetextanalyzer_AnalyzeScript,
 371     dwritetextanalyzer_AnalyzeBidi,
 372     dwritetextanalyzer_AnalyzeNumberSubstitution,
 373     dwritetextanalyzer_AnalyzeLineBreakpoints,
 374     dwritetextanalyzer_GetGlyphs,
 375     dwritetextanalyzer_GetGlyphPlacements,
 376     dwritetextanalyzer_GetGdiCompatibleGlyphPlacements
 377 };
 378
 379 static IDWriteTextAnalyzer textanalyzer = { &textanalyzervtbl };
 380
 381 HRESULT get_textanalyzer(IDWriteTextAnalyzer **ret)
 382 {
 383     *ret = &textanalyzer;
 384     return S_OK;
 385 }