Mercurial > hgrepos > Python2 > PyMuPDF
comparison mupdf-source/thirdparty/harfbuzz/src/hb-icu.cc @ 2:b50eed0cc0ef upstream
ADD: MuPDF v1.26.7: the MuPDF source as downloaded by a default build of PyMuPDF 1.26.4.
The directory name has changed: no version number in the expanded directory now.
| author | Franz Glasner <fzglas.hg@dom66.de> |
|---|---|
| date | Mon, 15 Sep 2025 11:43:07 +0200 |
| parents | |
| children |
comparison
equal
deleted
inserted
replaced
| 1:1d09e1dec1d9 | 2:b50eed0cc0ef |
|---|---|
| 1 /* | |
| 2 * Copyright © 2009 Red Hat, Inc. | |
| 3 * Copyright © 2009 Keith Stribley | |
| 4 * Copyright © 2011 Google, Inc. | |
| 5 * | |
| 6 * This is part of HarfBuzz, a text shaping library. | |
| 7 * | |
| 8 * Permission is hereby granted, without written agreement and without | |
| 9 * license or royalty fees, to use, copy, modify, and distribute this | |
| 10 * software and its documentation for any purpose, provided that the | |
| 11 * above copyright notice and the following two paragraphs appear in | |
| 12 * all copies of this software. | |
| 13 * | |
| 14 * IN NO EVENT SHALL THE COPYRIGHT HOLDER BE LIABLE TO ANY PARTY FOR | |
| 15 * DIRECT, INDIRECT, SPECIAL, INCIDENTAL, OR CONSEQUENTIAL DAMAGES | |
| 16 * ARISING OUT OF THE USE OF THIS SOFTWARE AND ITS DOCUMENTATION, EVEN | |
| 17 * IF THE COPYRIGHT HOLDER HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH | |
| 18 * DAMAGE. | |
| 19 * | |
| 20 * THE COPYRIGHT HOLDER SPECIFICALLY DISCLAIMS ANY WARRANTIES, INCLUDING, | |
| 21 * BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND | |
| 22 * FITNESS FOR A PARTICULAR PURPOSE. THE SOFTWARE PROVIDED HEREUNDER IS | |
| 23 * ON AN "AS IS" BASIS, AND THE COPYRIGHT HOLDER HAS NO OBLIGATION TO | |
| 24 * PROVIDE MAINTENANCE, SUPPORT, UPDATES, ENHANCEMENTS, OR MODIFICATIONS. | |
| 25 * | |
| 26 * Red Hat Author(s): Behdad Esfahbod | |
| 27 * Google Author(s): Behdad Esfahbod | |
| 28 */ | |
| 29 | |
| 30 #include "hb.hh" | |
| 31 | |
| 32 #ifdef HAVE_ICU | |
| 33 | |
| 34 #include "hb-icu.h" | |
| 35 | |
| 36 #include "hb-machinery.hh" | |
| 37 | |
| 38 #include <unicode/uchar.h> | |
| 39 #include <unicode/unorm2.h> | |
| 40 #include <unicode/ustring.h> | |
| 41 #include <unicode/utf16.h> | |
| 42 #include <unicode/uversion.h> | |
| 43 | |
| 44 /* ICU extra semicolon, fixed since 65, https://github.com/unicode-org/icu/commit/480bec3 */ | |
| 45 #if U_ICU_VERSION_MAJOR_NUM < 65 && (defined(__GNUC__) || defined(__clang__)) | |
| 46 #define HB_ICU_EXTRA_SEMI_IGNORED | |
| 47 #pragma GCC diagnostic push | |
| 48 #pragma GCC diagnostic ignored "-Wextra-semi-stmt" | |
| 49 #endif | |
| 50 | |
| 51 /** | |
| 52 * SECTION:hb-icu | |
| 53 * @title: hb-icu | |
| 54 * @short_description: ICU integration | |
| 55 * @include: hb-icu.h | |
| 56 * | |
| 57 * Functions for using HarfBuzz with the International Components for Unicode | |
| 58 * (ICU) library. HarfBuzz supports using ICU to provide Unicode data, by attaching | |
| 59 * ICU functions to the virtual methods in a #hb_unicode_funcs_t function | |
| 60 * structure. | |
| 61 **/ | |
| 62 | |
| 63 /** | |
| 64 * hb_icu_script_to_script: | |
| 65 * @script: The UScriptCode identifier to query | |
| 66 * | |
| 67 * Fetches the #hb_script_t script that corresponds to the | |
| 68 * specified UScriptCode identifier. | |
| 69 * | |
| 70 * Return value: the #hb_script_t script found | |
| 71 * | |
| 72 **/ | |
| 73 | |
| 74 hb_script_t | |
| 75 hb_icu_script_to_script (UScriptCode script) | |
| 76 { | |
| 77 if (unlikely (script == USCRIPT_INVALID_CODE)) | |
| 78 return HB_SCRIPT_INVALID; | |
| 79 | |
| 80 return hb_script_from_string (uscript_getShortName (script), -1); | |
| 81 } | |
| 82 | |
| 83 /** | |
| 84 * hb_icu_script_from_script: | |
| 85 * @script: The #hb_script_t script to query | |
| 86 * | |
| 87 * Fetches the UScriptCode identifier that corresponds to the | |
| 88 * specified #hb_script_t script. | |
| 89 * | |
| 90 * Return value: the UScriptCode identifier found | |
| 91 * | |
| 92 **/ | |
| 93 UScriptCode | |
| 94 hb_icu_script_from_script (hb_script_t script) | |
| 95 { | |
| 96 if (unlikely (script == HB_SCRIPT_INVALID)) | |
| 97 return USCRIPT_INVALID_CODE; | |
| 98 | |
| 99 unsigned int numScriptCode = 1 + u_getIntPropertyMaxValue (UCHAR_SCRIPT); | |
| 100 for (unsigned int i = 0; i < numScriptCode; i++) | |
| 101 if (unlikely (hb_icu_script_to_script ((UScriptCode) i) == script)) | |
| 102 return (UScriptCode) i; | |
| 103 | |
| 104 return USCRIPT_UNKNOWN; | |
| 105 } | |
| 106 | |
| 107 | |
| 108 static hb_unicode_combining_class_t | |
| 109 hb_icu_unicode_combining_class (hb_unicode_funcs_t *ufuncs HB_UNUSED, | |
| 110 hb_codepoint_t unicode, | |
| 111 void *user_data HB_UNUSED) | |
| 112 | |
| 113 { | |
| 114 return (hb_unicode_combining_class_t) u_getCombiningClass (unicode); | |
| 115 } | |
| 116 | |
| 117 static hb_unicode_general_category_t | |
| 118 hb_icu_unicode_general_category (hb_unicode_funcs_t *ufuncs HB_UNUSED, | |
| 119 hb_codepoint_t unicode, | |
| 120 void *user_data HB_UNUSED) | |
| 121 { | |
| 122 switch (u_getIntPropertyValue(unicode, UCHAR_GENERAL_CATEGORY)) | |
| 123 { | |
| 124 case U_UNASSIGNED: return HB_UNICODE_GENERAL_CATEGORY_UNASSIGNED; | |
| 125 | |
| 126 case U_UPPERCASE_LETTER: return HB_UNICODE_GENERAL_CATEGORY_UPPERCASE_LETTER; | |
| 127 case U_LOWERCASE_LETTER: return HB_UNICODE_GENERAL_CATEGORY_LOWERCASE_LETTER; | |
| 128 case U_TITLECASE_LETTER: return HB_UNICODE_GENERAL_CATEGORY_TITLECASE_LETTER; | |
| 129 case U_MODIFIER_LETTER: return HB_UNICODE_GENERAL_CATEGORY_MODIFIER_LETTER; | |
| 130 case U_OTHER_LETTER: return HB_UNICODE_GENERAL_CATEGORY_OTHER_LETTER; | |
| 131 | |
| 132 case U_NON_SPACING_MARK: return HB_UNICODE_GENERAL_CATEGORY_NON_SPACING_MARK; | |
| 133 case U_ENCLOSING_MARK: return HB_UNICODE_GENERAL_CATEGORY_ENCLOSING_MARK; | |
| 134 case U_COMBINING_SPACING_MARK: return HB_UNICODE_GENERAL_CATEGORY_SPACING_MARK; | |
| 135 | |
| 136 case U_DECIMAL_DIGIT_NUMBER: return HB_UNICODE_GENERAL_CATEGORY_DECIMAL_NUMBER; | |
| 137 case U_LETTER_NUMBER: return HB_UNICODE_GENERAL_CATEGORY_LETTER_NUMBER; | |
| 138 case U_OTHER_NUMBER: return HB_UNICODE_GENERAL_CATEGORY_OTHER_NUMBER; | |
| 139 | |
| 140 case U_SPACE_SEPARATOR: return HB_UNICODE_GENERAL_CATEGORY_SPACE_SEPARATOR; | |
| 141 case U_LINE_SEPARATOR: return HB_UNICODE_GENERAL_CATEGORY_LINE_SEPARATOR; | |
| 142 case U_PARAGRAPH_SEPARATOR: return HB_UNICODE_GENERAL_CATEGORY_PARAGRAPH_SEPARATOR; | |
| 143 | |
| 144 case U_CONTROL_CHAR: return HB_UNICODE_GENERAL_CATEGORY_CONTROL; | |
| 145 case U_FORMAT_CHAR: return HB_UNICODE_GENERAL_CATEGORY_FORMAT; | |
| 146 case U_PRIVATE_USE_CHAR: return HB_UNICODE_GENERAL_CATEGORY_PRIVATE_USE; | |
| 147 case U_SURROGATE: return HB_UNICODE_GENERAL_CATEGORY_SURROGATE; | |
| 148 | |
| 149 | |
| 150 case U_DASH_PUNCTUATION: return HB_UNICODE_GENERAL_CATEGORY_DASH_PUNCTUATION; | |
| 151 case U_START_PUNCTUATION: return HB_UNICODE_GENERAL_CATEGORY_OPEN_PUNCTUATION; | |
| 152 case U_END_PUNCTUATION: return HB_UNICODE_GENERAL_CATEGORY_CLOSE_PUNCTUATION; | |
| 153 case U_CONNECTOR_PUNCTUATION: return HB_UNICODE_GENERAL_CATEGORY_CONNECT_PUNCTUATION; | |
| 154 case U_OTHER_PUNCTUATION: return HB_UNICODE_GENERAL_CATEGORY_OTHER_PUNCTUATION; | |
| 155 | |
| 156 case U_MATH_SYMBOL: return HB_UNICODE_GENERAL_CATEGORY_MATH_SYMBOL; | |
| 157 case U_CURRENCY_SYMBOL: return HB_UNICODE_GENERAL_CATEGORY_CURRENCY_SYMBOL; | |
| 158 case U_MODIFIER_SYMBOL: return HB_UNICODE_GENERAL_CATEGORY_MODIFIER_SYMBOL; | |
| 159 case U_OTHER_SYMBOL: return HB_UNICODE_GENERAL_CATEGORY_OTHER_SYMBOL; | |
| 160 | |
| 161 case U_INITIAL_PUNCTUATION: return HB_UNICODE_GENERAL_CATEGORY_INITIAL_PUNCTUATION; | |
| 162 case U_FINAL_PUNCTUATION: return HB_UNICODE_GENERAL_CATEGORY_FINAL_PUNCTUATION; | |
| 163 } | |
| 164 | |
| 165 return HB_UNICODE_GENERAL_CATEGORY_UNASSIGNED; | |
| 166 } | |
| 167 | |
| 168 static hb_codepoint_t | |
| 169 hb_icu_unicode_mirroring (hb_unicode_funcs_t *ufuncs HB_UNUSED, | |
| 170 hb_codepoint_t unicode, | |
| 171 void *user_data HB_UNUSED) | |
| 172 { | |
| 173 return u_charMirror(unicode); | |
| 174 } | |
| 175 | |
| 176 static hb_script_t | |
| 177 hb_icu_unicode_script (hb_unicode_funcs_t *ufuncs HB_UNUSED, | |
| 178 hb_codepoint_t unicode, | |
| 179 void *user_data HB_UNUSED) | |
| 180 { | |
| 181 UErrorCode status = U_ZERO_ERROR; | |
| 182 UScriptCode scriptCode = uscript_getScript(unicode, &status); | |
| 183 | |
| 184 if (unlikely (U_FAILURE (status))) | |
| 185 return HB_SCRIPT_UNKNOWN; | |
| 186 | |
| 187 return hb_icu_script_to_script (scriptCode); | |
| 188 } | |
| 189 | |
| 190 static hb_bool_t | |
| 191 hb_icu_unicode_compose (hb_unicode_funcs_t *ufuncs HB_UNUSED, | |
| 192 hb_codepoint_t a, | |
| 193 hb_codepoint_t b, | |
| 194 hb_codepoint_t *ab, | |
| 195 void *user_data) | |
| 196 { | |
| 197 const UNormalizer2 *normalizer = (const UNormalizer2 *) user_data; | |
| 198 UChar32 ret = unorm2_composePair (normalizer, a, b); | |
| 199 if (ret < 0) return false; | |
| 200 *ab = ret; | |
| 201 return true; | |
| 202 } | |
| 203 | |
| 204 static hb_bool_t | |
| 205 hb_icu_unicode_decompose (hb_unicode_funcs_t *ufuncs HB_UNUSED, | |
| 206 hb_codepoint_t ab, | |
| 207 hb_codepoint_t *a, | |
| 208 hb_codepoint_t *b, | |
| 209 void *user_data) | |
| 210 { | |
| 211 const UNormalizer2 *normalizer = (const UNormalizer2 *) user_data; | |
| 212 UChar decomposed[4]; | |
| 213 int len; | |
| 214 UErrorCode icu_err = U_ZERO_ERROR; | |
| 215 len = unorm2_getRawDecomposition (normalizer, ab, decomposed, | |
| 216 ARRAY_LENGTH (decomposed), &icu_err); | |
| 217 if (U_FAILURE (icu_err) || len < 0) return false; | |
| 218 | |
| 219 len = u_countChar32 (decomposed, len); | |
| 220 if (len == 1) | |
| 221 { | |
| 222 U16_GET_UNSAFE (decomposed, 0, *a); | |
| 223 *b = 0; | |
| 224 return *a != ab; | |
| 225 } | |
| 226 else if (len == 2) | |
| 227 { | |
| 228 len = 0; | |
| 229 U16_NEXT_UNSAFE (decomposed, len, *a); | |
| 230 U16_NEXT_UNSAFE (decomposed, len, *b); | |
| 231 } | |
| 232 return true; | |
| 233 } | |
| 234 | |
| 235 | |
| 236 static inline void free_static_icu_funcs (); | |
| 237 | |
| 238 static struct hb_icu_unicode_funcs_lazy_loader_t : hb_unicode_funcs_lazy_loader_t<hb_icu_unicode_funcs_lazy_loader_t> | |
| 239 { | |
| 240 static hb_unicode_funcs_t *create () | |
| 241 { | |
| 242 void *user_data = nullptr; | |
| 243 UErrorCode icu_err = U_ZERO_ERROR; | |
| 244 user_data = (void *) unorm2_getNFCInstance (&icu_err); | |
| 245 assert (user_data); | |
| 246 | |
| 247 hb_unicode_funcs_t *funcs = hb_unicode_funcs_create (nullptr); | |
| 248 | |
| 249 hb_unicode_funcs_set_combining_class_func (funcs, hb_icu_unicode_combining_class, nullptr, nullptr); | |
| 250 hb_unicode_funcs_set_general_category_func (funcs, hb_icu_unicode_general_category, nullptr, nullptr); | |
| 251 hb_unicode_funcs_set_mirroring_func (funcs, hb_icu_unicode_mirroring, nullptr, nullptr); | |
| 252 hb_unicode_funcs_set_script_func (funcs, hb_icu_unicode_script, nullptr, nullptr); | |
| 253 hb_unicode_funcs_set_compose_func (funcs, hb_icu_unicode_compose, user_data, nullptr); | |
| 254 hb_unicode_funcs_set_decompose_func (funcs, hb_icu_unicode_decompose, user_data, nullptr); | |
| 255 | |
| 256 hb_unicode_funcs_make_immutable (funcs); | |
| 257 | |
| 258 hb_atexit (free_static_icu_funcs); | |
| 259 | |
| 260 return funcs; | |
| 261 } | |
| 262 } static_icu_funcs; | |
| 263 | |
| 264 static inline | |
| 265 void free_static_icu_funcs () | |
| 266 { | |
| 267 static_icu_funcs.free_instance (); | |
| 268 } | |
| 269 | |
| 270 /** | |
| 271 * hb_icu_get_unicode_funcs: | |
| 272 * | |
| 273 * Fetches a Unicode-functions structure that is populated | |
| 274 * with the appropriate ICU function for each method. | |
| 275 * | |
| 276 * Return value: (transfer none): a pointer to the #hb_unicode_funcs_t Unicode-functions structure | |
| 277 * | |
| 278 * Since: 0.9.38 | |
| 279 **/ | |
| 280 hb_unicode_funcs_t * | |
| 281 hb_icu_get_unicode_funcs () | |
| 282 { | |
| 283 return static_icu_funcs.get_unconst (); | |
| 284 } | |
| 285 | |
| 286 #ifdef HB_ICU_EXTRA_SEMI_IGNORED | |
| 287 #pragma GCC diagnostic pop | |
| 288 #endif | |
| 289 | |
| 290 #endif |
