1 | /* Pango |
2 | * pango-break.h: |
3 | * |
4 | * Copyright (C) 1999 Red Hat Software |
5 | * |
6 | * This library is free software; you can redistribute it and/or |
7 | * modify it under the terms of the GNU Library General Public |
8 | * License as published by the Free Software Foundation; either |
9 | * version 2 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 | * Library General Public License for more details. |
15 | * |
16 | * You should have received a copy of the GNU Library General Public |
17 | * License along with this library; if not, write to the |
18 | * Free Software Foundation, Inc., 59 Temple Place - Suite 330, |
19 | * Boston, MA 02111-1307, USA. |
20 | */ |
21 | |
22 | #ifndef __PANGO_BREAK_H__ |
23 | #define __PANGO_BREAK_H__ |
24 | |
25 | #include <glib.h> |
26 | |
27 | G_BEGIN_DECLS |
28 | |
29 | #include <pango/pango-item.h> |
30 | |
31 | /* Logical attributes of a character. |
32 | */ |
33 | /** |
34 | * PangoLogAttr: |
35 | * @is_line_break: if set, can break line in front of character |
36 | * @is_mandatory_break: if set, must break line in front of character |
37 | * @is_char_break: if set, can break here when doing character wrapping |
38 | * @is_white: is whitespace character |
39 | * @is_cursor_position: if set, cursor can appear in front of character. |
40 | * i.e. this is a grapheme boundary, or the first character in the text. |
41 | * This flag implements Unicode's |
42 | * [Grapheme Cluster Boundaries](http://www.unicode.org/reports/tr29/) |
43 | * semantics. |
44 | * @is_word_start: is first character in a word |
45 | * @is_word_end: is first non-word char after a word |
46 | * Note that in degenerate cases, you could have both @is_word_start |
47 | * and @is_word_end set for some character. |
48 | * @is_sentence_boundary: is a sentence boundary. |
49 | * There are two ways to divide sentences. The first assigns all |
50 | * inter-sentence whitespace/control/format chars to some sentence, |
51 | * so all chars are in some sentence; @is_sentence_boundary denotes |
52 | * the boundaries there. The second way doesn't assign |
53 | * between-sentence spaces, etc. to any sentence, so |
54 | * @is_sentence_start/@is_sentence_end mark the boundaries of those sentences. |
55 | * @is_sentence_start: is first character in a sentence |
56 | * @is_sentence_end: is first char after a sentence. |
57 | * Note that in degenerate cases, you could have both @is_sentence_start |
58 | * and @is_sentence_end set for some character. (e.g. no space after a |
59 | * period, so the next sentence starts right away) |
60 | * @backspace_deletes_character: if set, backspace deletes one character |
61 | * rather than the entire grapheme cluster. This field is only meaningful |
62 | * on grapheme boundaries (where @is_cursor_position is set). In some languages, |
63 | * the full grapheme (e.g. letter + diacritics) is considered a unit, while in |
64 | * others, each decomposed character in the grapheme is a unit. In the default |
65 | * implementation of [func@break], this bit is set on all grapheme boundaries |
66 | * except those following Latin, Cyrillic or Greek base characters. |
67 | * @is_expandable_space: is a whitespace character that can possibly be |
68 | * expanded for justification purposes. (Since: 1.18) |
69 | * @is_word_boundary: is a word boundary, as defined by UAX#29. |
70 | * More specifically, means that this is not a position in the middle of a word. |
71 | * For example, both sides of a punctuation mark are considered word boundaries. |
72 | * This flag is particularly useful when selecting text word-by-word. This flag |
73 | * implements Unicode's [Word Boundaries](http://www.unicode.org/reports/tr29/) |
74 | * semantics. (Since: 1.22) |
75 | * @break_inserts_hyphen: when breaking lines before this char, insert a hyphen. |
76 | * Since: 1.50 |
77 | * @break_removes_preceding: when breaking lines before this char, remove the |
78 | * preceding char. Since 1.50 |
79 | * |
80 | * The `PangoLogAttr` structure stores information about the attributes of a |
81 | * single character. |
82 | */ |
83 | struct _PangoLogAttr |
84 | { |
85 | guint is_line_break : 1; |
86 | guint is_mandatory_break : 1; |
87 | guint is_char_break : 1; |
88 | guint is_white : 1; |
89 | guint is_cursor_position : 1; |
90 | guint is_word_start : 1; |
91 | guint is_word_end : 1; |
92 | guint is_sentence_boundary : 1; |
93 | guint is_sentence_start : 1; |
94 | guint is_sentence_end : 1; |
95 | guint backspace_deletes_character : 1; |
96 | guint is_expandable_space : 1; |
97 | guint is_word_boundary : 1; |
98 | guint break_inserts_hyphen : 1; |
99 | guint break_removes_preceding : 1; |
100 | |
101 | guint reserved : 17; |
102 | }; |
103 | |
104 | PANGO_DEPRECATED_IN_1_44 |
105 | void pango_break (const char *text, |
106 | int length, |
107 | PangoAnalysis *analysis, |
108 | PangoLogAttr *attrs, |
109 | int attrs_len); |
110 | |
111 | PANGO_AVAILABLE_IN_ALL |
112 | void pango_get_log_attrs (const char *text, |
113 | int length, |
114 | int level, |
115 | PangoLanguage *language, |
116 | PangoLogAttr *attrs, |
117 | int attrs_len); |
118 | |
119 | PANGO_AVAILABLE_IN_ALL |
120 | void pango_default_break (const char *text, |
121 | int length, |
122 | PangoAnalysis *analysis, |
123 | PangoLogAttr *attrs, |
124 | int attrs_len); |
125 | |
126 | PANGO_AVAILABLE_IN_1_44 |
127 | void pango_tailor_break (const char *text, |
128 | int length, |
129 | PangoAnalysis *analysis, |
130 | int offset, |
131 | PangoLogAttr *attrs, |
132 | int attrs_len); |
133 | |
134 | PANGO_AVAILABLE_IN_1_50 |
135 | void pango_attr_break (const char *text, |
136 | int length, |
137 | PangoAttrList *attr_list, |
138 | int offset, |
139 | PangoLogAttr *attrs, |
140 | int attrs_len); |
141 | |
142 | G_END_DECLS |
143 | |
144 | #endif /* __PANGO_BREAK_H__ */ |
145 | |