1/* Hyphen - hyphenation library using converted TeX hyphenation patterns
2 *
3 * (C) 1998 Raph Levien
4 * (C) 2001 ALTLinux, Moscow
5 * (C) 2006, 2007, 2008 László Németh
6 *
7 * This was part of libHnj library by Raph Levien.
8 *
9 * Peter Novodvorsky from ALTLinux cut hyphenation part from libHnj
10 * to use it in OpenOffice.org.
11 *
12 * Non-standard and compound word hyphenation support by László Németh.
13 *
14 * License is the original LibHnj license:
15 *
16 * LibHnj is dual licensed under LGPL and MPL. Boilerplate for both
17 * licenses follows.
18 */
19
20/* LibHnj - a library for high quality hyphenation and justification
21 * Copyright (C) 1998 Raph Levien
22 *
23 * This library is free software; you can redistribute it and/or
24 * modify it under the terms of the GNU Library General Public
25 * License as published by the Free Software Foundation; either
26 * version 2 of the License, or (at your option) any later version.
27 *
28 * This library is distributed in the hope that it will be useful,
29 * but WITHOUT ANY WARRANTY; without even the implied warranty of
30 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
31 * Library General Public License for more details.
32 *
33 * You should have received a copy of the GNU Library General Public
34 * License along with this library; if not, write to the
35 * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
36 * Boston, MA 02111-1307 USA.
37*/
38
39/*
40 * The contents of this file are subject to the Mozilla Public License
41 * Version 1.0 (the "MPL"); you may not use this file except in
42 * compliance with the MPL. You may obtain a copy of the MPL at
43 * http://www.mozilla.org/MPL/
44 *
45 * Software distributed under the MPL is distributed on an "AS IS" basis,
46 * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the MPL
47 * for the specific language governing rights and limitations under the
48 * MPL.
49 *
50 */
51#ifndef __HYPHEN_H__
52#define __HYPHEN_H__
53
54#ifdef __cplusplus
55extern "C" {
56#endif /* __cplusplus */
57
58#include <stdio.h>
59
60typedef struct _HyphenDict HyphenDict;
61typedef struct _HyphenState HyphenState;
62typedef struct _HyphenTrans HyphenTrans;
63#define MAX_CHARS 100
64#define MAX_NAME 20
65
66struct _HyphenDict {
67 /* user options */
68 char lhmin; /* lefthyphenmin: min. hyph. distance from the left side */
69 char rhmin; /* righthyphenmin: min. hyph. distance from the right side */
70 char clhmin; /* min. hyph. distance from the left compound boundary */
71 char crhmin; /* min. hyph. distance from the right compound boundary */
72 char * nohyphen; /* comma separated list of characters or character
73 sequences with forbidden hyphenation */
74 int nohyphenl; /* count of elements in nohyphen */
75 /* system variables */
76 int num_states;
77 char cset[MAX_NAME];
78 int utf8;
79 HyphenState *states;
80 HyphenDict *nextlevel;
81};
82
83struct _HyphenState {
84 char *match;
85 char *repl;
86 signed char replindex;
87 signed char replcut;
88 int fallback_state;
89 int num_trans;
90 HyphenTrans *trans;
91};
92
93struct _HyphenTrans {
94 char ch;
95 int new_state;
96};
97
98HyphenDict *hnj_hyphen_load (const char *fn);
99HyphenDict *hnj_hyphen_load_file (FILE *f);
100void hnj_hyphen_free (HyphenDict *dict);
101
102/* obsolete, use hnj_hyphen_hyphenate2() or *hyphenate3() functions) */
103int hnj_hyphen_hyphenate (HyphenDict *dict,
104 const char *word, int word_size,
105 char *hyphens);
106
107/*
108
109 int hnj_hyphen_hyphenate2(): non-standard hyphenation.
110
111 (It supports Catalan, Dutch, German, Hungarian, Norwegian, Swedish
112 etc. orthography, see documentation.)
113
114 input data:
115 word: input word
116 word_size: byte length of the input word
117
118 hyphens: allocated character buffer (size = word_size + 5)
119 hyphenated_word: allocated character buffer (size ~ word_size * 2) or NULL
120 rep, pos, cut: pointers (point to the allocated and _zeroed_ buffers
121 (size=word_size) or with NULL value) or NULL
122
123 output data:
124 hyphens: hyphenation vector (hyphenation points signed with odd numbers)
125 hyphenated_word: hyphenated input word (hyphens signed with `='),
126 optional (NULL input)
127 rep: NULL (only standard hyph.), or replacements (hyphenation points
128 signed with `=' in replacements);
129 pos: NULL, or difference of the actual position and the beginning
130 positions of the change in input words;
131 cut: NULL, or counts of the removed characters of the original words
132 at hyphenation,
133
134 Note: rep, pos, cut are complementary arrays to the hyphens, indexed with the
135 character positions of the input word.
136
137 For example:
138 Schiffahrt -> Schiff=fahrt,
139 pattern: f1f/ff=f,1,2
140 output: rep[5]="ff=f", pos[5] = 1, cut[5] = 2
141
142 Note: hnj_hyphen_hyphenate2() can allocate rep, pos, cut (word_size
143 length arrays):
144
145 char ** rep = NULL;
146 int * pos = NULL;
147 int * cut = NULL;
148 char hyphens[MAXWORDLEN];
149 hnj_hyphen_hyphenate2(dict, "example", 7, hyphens, NULL, &rep, &pos, &cut);
150
151 See example in the source distribution.
152
153*/
154
155int hnj_hyphen_hyphenate2 (HyphenDict *dict,
156 const char *word, int word_size, char * hyphens,
157 char *hyphenated_word, char *** rep, int ** pos, int ** cut);
158
159/* like hnj_hyphen_hyphenate2, but with hyphenmin parameters */
160/* lhmin: lefthyphenmin
161 * rhmin: righthyphenmin
162 * clhmin: compoundlefthyphemin
163 * crhmin: compoundrighthyphenmin
164 * (see documentation) */
165
166int hnj_hyphen_hyphenate3 (HyphenDict *dict,
167 const char *word, int word_size, char * hyphens,
168 char *hyphword, char *** rep, int ** pos, int ** cut,
169 int lhmin, int rhmin, int clhmin, int crhmin);
170
171#ifdef __cplusplus
172}
173#endif /* __cplusplus */
174
175#endif /* __HYPHEN_H__ */
176