Mercurial > hgrepos > Python2 > PyMuPDF
comparison mupdf-source/include/mupdf/fitz/text.h @ 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 // Copyright (C) 2004-2024 Artifex Software, Inc. | |
| 2 // | |
| 3 // This file is part of MuPDF. | |
| 4 // | |
| 5 // MuPDF is free software: you can redistribute it and/or modify it under the | |
| 6 // terms of the GNU Affero General Public License as published by the Free | |
| 7 // Software Foundation, either version 3 of the License, or (at your option) | |
| 8 // any later version. | |
| 9 // | |
| 10 // MuPDF is distributed in the hope that it will be useful, but WITHOUT ANY | |
| 11 // WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS | |
| 12 // FOR A PARTICULAR PURPOSE. See the GNU Affero General Public License for more | |
| 13 // details. | |
| 14 // | |
| 15 // You should have received a copy of the GNU Affero General Public License | |
| 16 // along with MuPDF. If not, see <https://www.gnu.org/licenses/agpl-3.0.en.html> | |
| 17 // | |
| 18 // Alternative licensing terms are available from the licensor. | |
| 19 // For commercial licensing, see <https://www.artifex.com/> or contact | |
| 20 // Artifex Software, Inc., 39 Mesa Street, Suite 108A, San Francisco, | |
| 21 // CA 94129, USA, for further information. | |
| 22 | |
| 23 #ifndef MUPDF_FITZ_TEXT_H | |
| 24 #define MUPDF_FITZ_TEXT_H | |
| 25 | |
| 26 #include "mupdf/fitz/system.h" | |
| 27 #include "mupdf/fitz/context.h" | |
| 28 #include "mupdf/fitz/font.h" | |
| 29 #include "mupdf/fitz/path.h" | |
| 30 #include "mupdf/fitz/bidi.h" | |
| 31 | |
| 32 /** | |
| 33 Text buffer. | |
| 34 | |
| 35 The trm field contains the a, b, c and d coefficients. | |
| 36 The e and f coefficients come from the individual elements, | |
| 37 together they form the transform matrix for the glyph. | |
| 38 | |
| 39 Glyphs are referenced by glyph ID. | |
| 40 The Unicode text equivalent is kept in a separate array | |
| 41 with indexes into the glyph array. | |
| 42 */ | |
| 43 | |
| 44 typedef struct | |
| 45 { | |
| 46 float x, y; | |
| 47 float adv; /* advance width given by input format */ | |
| 48 int gid; /* -1 for one gid to many ucs mappings */ | |
| 49 int ucs; /* -1 for one ucs to many gid mappings */ | |
| 50 int cid; /* CID for CJK fonts, raw character code for other fonts; or unicode for non-PDF formats. */ | |
| 51 } fz_text_item; | |
| 52 | |
| 53 #define FZ_LANG_TAG2(c1,c2) ((c1-'a'+1) + ((c2-'a'+1)*27)) | |
| 54 #define FZ_LANG_TAG3(c1,c2,c3) ((c1-'a'+1) + ((c2-'a'+1)*27) + ((c3-'a'+1)*27*27)) | |
| 55 | |
| 56 typedef enum | |
| 57 { | |
| 58 FZ_LANG_UNSET = 0, | |
| 59 FZ_LANG_ur = FZ_LANG_TAG2('u','r'), | |
| 60 FZ_LANG_urd = FZ_LANG_TAG3('u','r','d'), | |
| 61 FZ_LANG_ko = FZ_LANG_TAG2('k','o'), | |
| 62 FZ_LANG_ja = FZ_LANG_TAG2('j','a'), | |
| 63 FZ_LANG_zh = FZ_LANG_TAG2('z','h'), | |
| 64 FZ_LANG_zh_Hans = FZ_LANG_TAG3('z','h','s'), | |
| 65 FZ_LANG_zh_Hant = FZ_LANG_TAG3('z','h','t'), | |
| 66 } fz_text_language; | |
| 67 | |
| 68 typedef struct fz_text_span | |
| 69 { | |
| 70 fz_font *font; | |
| 71 fz_matrix trm; | |
| 72 unsigned wmode : 1; /* 0 horizontal, 1 vertical */ | |
| 73 unsigned bidi_level : 7; /* The bidirectional level of text */ | |
| 74 unsigned markup_dir : 2; /* The direction of text as marked in the original document */ | |
| 75 unsigned language : 15; /* The language as marked in the original document */ | |
| 76 int len, cap; | |
| 77 fz_text_item *items; | |
| 78 struct fz_text_span *next; | |
| 79 } fz_text_span; | |
| 80 | |
| 81 typedef struct | |
| 82 { | |
| 83 int refs; | |
| 84 fz_text_span *head, *tail; | |
| 85 } fz_text; | |
| 86 | |
| 87 /** | |
| 88 Create a new empty fz_text object. | |
| 89 | |
| 90 Throws exception on failure to allocate. | |
| 91 */ | |
| 92 fz_text *fz_new_text(fz_context *ctx); | |
| 93 | |
| 94 /** | |
| 95 Increment the reference count for the text object. The same | |
| 96 pointer is returned. | |
| 97 | |
| 98 Never throws exceptions. | |
| 99 */ | |
| 100 fz_text *fz_keep_text(fz_context *ctx, const fz_text *text); | |
| 101 | |
| 102 /** | |
| 103 Decrement the reference count for the text object. When the | |
| 104 reference count hits zero, the text object is freed. | |
| 105 | |
| 106 Never throws exceptions. | |
| 107 */ | |
| 108 void fz_drop_text(fz_context *ctx, const fz_text *text); | |
| 109 | |
| 110 /** | |
| 111 Add a glyph/unicode value to a text object. | |
| 112 | |
| 113 text: Text object to add to. | |
| 114 | |
| 115 font: The font the glyph should be added in. | |
| 116 | |
| 117 trm: The transform to use for the glyph. | |
| 118 | |
| 119 glyph: The glyph id to add. | |
| 120 | |
| 121 unicode: The unicode character for the glyph. | |
| 122 | |
| 123 cid: The CJK CID value or raw character code. | |
| 124 | |
| 125 wmode: 1 for vertical mode, 0 for horizontal. | |
| 126 | |
| 127 bidi_level: The bidirectional level for this glyph. | |
| 128 | |
| 129 markup_dir: The direction of the text as specified in the | |
| 130 markup. | |
| 131 | |
| 132 language: The language in use (if known, 0 otherwise) | |
| 133 (e.g. FZ_LANG_zh_Hans). | |
| 134 | |
| 135 Throws exception on failure to allocate. | |
| 136 */ | |
| 137 void fz_show_glyph(fz_context *ctx, fz_text *text, fz_font *font, fz_matrix trm, int glyph, int unicode, int wmode, int bidi_level, fz_bidi_direction markup_dir, fz_text_language language); | |
| 138 void fz_show_glyph_aux(fz_context *ctx, fz_text *text, fz_font *font, fz_matrix trm, float adv, int glyph, int unicode, int cid, int wmode, int bidi_level, fz_bidi_direction markup_dir, fz_text_language lang); | |
| 139 | |
| 140 /** | |
| 141 Add a UTF8 string to a text object. | |
| 142 | |
| 143 text: Text object to add to. | |
| 144 | |
| 145 font: The font the string should be added in. | |
| 146 | |
| 147 trm: The transform to use. | |
| 148 | |
| 149 s: The utf-8 string to add. | |
| 150 | |
| 151 wmode: 1 for vertical mode, 0 for horizontal. | |
| 152 | |
| 153 bidi_level: The bidirectional level for this glyph. | |
| 154 | |
| 155 markup_dir: The direction of the text as specified in the markup. | |
| 156 | |
| 157 language: The language in use (if known, 0 otherwise) | |
| 158 (e.g. FZ_LANG_zh_Hans). | |
| 159 | |
| 160 Returns the transform updated with the advance width of the | |
| 161 string. | |
| 162 */ | |
| 163 fz_matrix fz_show_string(fz_context *ctx, fz_text *text, fz_font *font, fz_matrix trm, const char *s, int wmode, int bidi_level, fz_bidi_direction markup_dir, fz_text_language language); | |
| 164 | |
| 165 /** | |
| 166 Measure the advance width of a UTF8 string should it be added to a text object. | |
| 167 | |
| 168 This uses the same layout algorithms as fz_show_string, and can be used | |
| 169 to calculate text alignment adjustments. | |
| 170 */ | |
| 171 fz_matrix | |
| 172 fz_measure_string(fz_context *ctx, fz_font *user_font, fz_matrix trm, const char *s, int wmode, int bidi_level, fz_bidi_direction markup_dir, fz_text_language language); | |
| 173 | |
| 174 /** | |
| 175 Find the bounds of a given text object. | |
| 176 | |
| 177 text: The text object to find the bounds of. | |
| 178 | |
| 179 stroke: Pointer to the stroke attributes (for stroked | |
| 180 text), or NULL (for filled text). | |
| 181 | |
| 182 ctm: The matrix in use. | |
| 183 | |
| 184 r: pointer to storage for the bounds. | |
| 185 | |
| 186 Returns a pointer to r, which is updated to contain the | |
| 187 bounding box for the text object. | |
| 188 */ | |
| 189 fz_rect fz_bound_text(fz_context *ctx, const fz_text *text, const fz_stroke_state *stroke, fz_matrix ctm); | |
| 190 | |
| 191 /** | |
| 192 Convert ISO 639 (639-{1,2,3,5}) language specification | |
| 193 strings losslessly to a 15 bit fz_text_language code. | |
| 194 | |
| 195 No validation is carried out. Obviously invalid (out | |
| 196 of spec) codes will be mapped to FZ_LANG_UNSET, but | |
| 197 well-formed (but undefined) codes will be blithely | |
| 198 accepted. | |
| 199 */ | |
| 200 fz_text_language fz_text_language_from_string(const char *str); | |
| 201 | |
| 202 /** | |
| 203 Recover ISO 639 (639-{1,2,3,5}) language specification | |
| 204 strings losslessly from a 15 bit fz_text_language code. | |
| 205 | |
| 206 No validation is carried out. See note above. | |
| 207 */ | |
| 208 char *fz_string_from_text_language(char str[8], fz_text_language lang); | |
| 209 | |
| 210 #endif |
