2 * Copyright (c) 1995-2007, Index Data
4 * Redistribution and use in source and binary forms, with or without
5 * modification, are permitted provided that the following conditions are met:
7 * * Redistributions of source code must retain the above copyright
8 * notice, this list of conditions and the following disclaimer.
9 * * Redistributions in binary form must reproduce the above copyright
10 * notice, this list of conditions and the following disclaimer in the
11 * documentation and/or other materials provided with the distribution.
12 * * Neither the name of Index Data nor the names of its contributors
13 * may be used to endorse or promote products derived from this
14 * software without specific prior written permission.
16 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND ANY
17 * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
18 * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
19 * DISCLAIMED. IN NO EVENT SHALL THE REGENTS AND CONTRIBUTORS BE LIABLE FOR ANY
20 * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
21 * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
22 * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
23 * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
24 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
25 * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
33 #include <libxml/parser.h>
34 #include <libxml/tree.h>
36 #include <unicode/utypes.h> /* Basic ICU data types */
37 #include <unicode/uchar.h> /* char names */
39 #include <unicode/ucol.h>
40 #include <unicode/ubrk.h>
41 #include <unicode/utrans.h>
44 /* declared structs and functions */
46 int icu_check_status (UErrorCode status);
55 struct icu_buf_utf16 * icu_buf_utf16_create(size_t capacity);
57 struct icu_buf_utf16 * icu_buf_utf16_clear(struct icu_buf_utf16 * buf16);
59 struct icu_buf_utf16 * icu_buf_utf16_resize(struct icu_buf_utf16 * buf16,
62 struct icu_buf_utf16 * icu_buf_utf16_copy(struct icu_buf_utf16 * dest16,
63 struct icu_buf_utf16 * src16);
65 void icu_buf_utf16_destroy(struct icu_buf_utf16 * buf16);
76 struct icu_buf_utf8 * icu_buf_utf8_create(size_t capacity);
78 struct icu_buf_utf8 * icu_buf_utf8_clear(struct icu_buf_utf8 * buf8);
80 struct icu_buf_utf8 * icu_buf_utf8_resize(struct icu_buf_utf8 * buf8,
83 void icu_buf_utf8_destroy(struct icu_buf_utf8 * buf8);
86 UErrorCode icu_utf16_from_utf8(struct icu_buf_utf16 * dest16,
87 struct icu_buf_utf8 * src8,
90 UErrorCode icu_utf16_from_utf8_cstr(struct icu_buf_utf16 * dest16,
91 const char * src8cstr,
95 UErrorCode icu_utf16_to_utf8(struct icu_buf_utf8 * dest8,
96 struct icu_buf_utf16 * src16,
105 struct icu_casemap * icu_casemap_create(const char *locale, char action,
108 void icu_casemap_destroy(struct icu_casemap * casemap);
110 int icu_casemap_casemap(struct icu_casemap * casemap,
111 struct icu_buf_utf16 * dest16,
112 struct icu_buf_utf16 * src16,
115 int icu_utf16_casemap(struct icu_buf_utf16 * dest16,
116 struct icu_buf_utf16 * src16,
117 const char *locale, char action,
120 UErrorCode icu_sortkey8_from_utf16(UCollator *coll,
121 struct icu_buf_utf8 * dest8,
122 struct icu_buf_utf16 * src16,
123 UErrorCode * status);
130 struct icu_buf_utf16 * buf16;
136 keep always invariant
141 0 <= token_id <= token_count
145 struct icu_tokenizer * icu_tokenizer_create(const char *locale, char action,
148 void icu_tokenizer_destroy(struct icu_tokenizer * tokenizer);
150 int icu_tokenizer_attach(struct icu_tokenizer * tokenizer,
151 struct icu_buf_utf16 * src16, UErrorCode *status);
153 int32_t icu_tokenizer_next_token(struct icu_tokenizer * tokenizer,
154 struct icu_buf_utf16 * tkn16,
157 int32_t icu_tokenizer_token_id(struct icu_tokenizer * tokenizer);
158 int32_t icu_tokenizer_token_start(struct icu_tokenizer * tokenizer);
159 int32_t icu_tokenizer_token_end(struct icu_tokenizer * tokenizer);
160 int32_t icu_tokenizer_token_length(struct icu_tokenizer * tokenizer);
161 int32_t icu_tokenizer_token_count(struct icu_tokenizer * tokenizer);
165 struct icu_normalizer
168 struct icu_buf_utf16 * rules16;
169 UParseError parse_error[256];
170 UTransliterator * trans;
173 struct icu_normalizer * icu_normalizer_create(const char *rules, char action,
177 void icu_normalizer_destroy(struct icu_normalizer * normalizer);
179 int icu_normalizer_normalize(struct icu_normalizer * normalizer,
180 struct icu_buf_utf16 * dest16,
181 struct icu_buf_utf16 * src16,
184 enum icu_chain_step_type {
185 ICU_chain_step_type_none,
186 ICU_chain_step_type_display, /* convert to utf8 display format */
187 ICU_chain_step_type_casemap, /* apply utf16 charmap */
188 ICU_chain_step_type_normalize, /* apply utf16 normalization */
189 ICU_chain_step_type_tokenize /* apply utf16 tokenization */
194 struct icu_chain_step
196 /* type and action object */
197 enum icu_chain_step_type type;
199 struct icu_casemap * casemap;
200 struct icu_normalizer * normalizer;
201 struct icu_tokenizer * tokenizer;
203 /* temprary post-action utf16 buffer */
204 struct icu_buf_utf16 * buf16;
205 struct icu_chain_step * previous;
213 struct icu_chain_step * icu_chain_step_create(struct icu_chain * chain,
214 enum icu_chain_step_type type,
215 const uint8_t * rule,
216 struct icu_buf_utf16 * buf16,
220 void icu_chain_step_destroy(struct icu_chain_step * step);
228 const char * src8cstr;
232 /* number of tokens returned so far */
235 /* utf8 output buffers */
236 struct icu_buf_utf8 * display8;
237 struct icu_buf_utf8 * norm8;
238 struct icu_buf_utf8 * sort8;
240 /* utf16 source buffer */
241 struct icu_buf_utf16 * src16;
243 /* linked list of chain steps */
244 struct icu_chain_step * steps;
247 struct icu_chain * icu_chain_create(const uint8_t * locale,
249 UErrorCode * status);
251 void icu_chain_destroy(struct icu_chain * chain);
253 struct icu_chain * icu_chain_xml_config(xmlNode *xml_node,
254 const uint8_t * locale,
256 UErrorCode * status);
258 struct icu_chain_step * icu_chain_insert_step(struct icu_chain * chain,
259 enum icu_chain_step_type type,
260 const uint8_t * rule,
263 int icu_chain_step_next_token(struct icu_chain * chain,
264 struct icu_chain_step * step,
267 int icu_chain_assign_cstr(struct icu_chain * chain,
268 const char * src8cstr,
271 int icu_chain_next_token(struct icu_chain * chain,
274 int icu_chain_token_number(struct icu_chain * chain);
276 const char * icu_chain_token_display(struct icu_chain * chain);
278 const char * icu_chain_token_norm(struct icu_chain * chain);
280 const char * icu_chain_token_sortkey(struct icu_chain * chain);
282 const UCollator * icu_chain_get_coll(struct icu_chain * chain);
284 #endif /* ICU_I18NL_H */
289 * indent-tabs-mode: nil
291 * vim: shiftwidth=4 tabstop=8 expandtab