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.
29 \brief Internal header for ICU utilities
35 #include <yaz/yconfig.h>
37 #include <libxml/tree.h>
39 #include <unicode/utypes.h> /* Basic ICU data types */
40 #include <unicode/uchar.h> /* char names */
42 #include <unicode/ucol.h>
43 #include <unicode/ubrk.h>
44 #include <unicode/utrans.h>
48 /* declared structs and functions */
50 int icu_check_status (UErrorCode status);
59 struct icu_buf_utf16 * icu_buf_utf16_create(size_t capacity);
61 struct icu_buf_utf16 * icu_buf_utf16_clear(struct icu_buf_utf16 * buf16);
63 struct icu_buf_utf16 * icu_buf_utf16_resize(struct icu_buf_utf16 * buf16,
66 struct icu_buf_utf16 * icu_buf_utf16_copy(struct icu_buf_utf16 * dest16,
67 struct icu_buf_utf16 * src16);
69 void icu_buf_utf16_destroy(struct icu_buf_utf16 * buf16);
80 struct icu_buf_utf8 * icu_buf_utf8_create(size_t capacity);
82 struct icu_buf_utf8 * icu_buf_utf8_clear(struct icu_buf_utf8 * buf8);
84 struct icu_buf_utf8 * icu_buf_utf8_resize(struct icu_buf_utf8 * buf8,
87 void icu_buf_utf8_destroy(struct icu_buf_utf8 * buf8);
90 UErrorCode icu_utf16_from_utf8(struct icu_buf_utf16 * dest16,
91 struct icu_buf_utf8 * src8,
94 UErrorCode icu_utf16_from_utf8_cstr(struct icu_buf_utf16 * dest16,
95 const char * src8cstr,
99 UErrorCode icu_utf16_to_utf8(struct icu_buf_utf8 * dest8,
100 struct icu_buf_utf16 * src16,
101 UErrorCode * status);
108 struct icu_casemap * icu_casemap_create(char action, UErrorCode *status);
110 void icu_casemap_destroy(struct icu_casemap * casemap);
112 int icu_casemap_casemap(struct icu_casemap * casemap,
113 struct icu_buf_utf16 * dest16,
114 struct icu_buf_utf16 * src16,
118 int icu_utf16_casemap(struct icu_buf_utf16 * dest16,
119 struct icu_buf_utf16 * src16,
120 const char *locale, char action,
123 UErrorCode icu_sortkey8_from_utf16(UCollator *coll,
124 struct icu_buf_utf8 * dest8,
125 struct icu_buf_utf16 * src16,
126 UErrorCode * status);
132 struct icu_buf_utf16 * buf16;
138 keep always invariant
143 0 <= token_id <= token_count
147 struct icu_tokenizer * icu_tokenizer_create(const char *locale, char action,
150 void icu_tokenizer_destroy(struct icu_tokenizer * tokenizer);
152 int icu_tokenizer_attach(struct icu_tokenizer * tokenizer,
153 struct icu_buf_utf16 * src16, UErrorCode *status);
155 int32_t icu_tokenizer_next_token(struct icu_tokenizer * tokenizer,
156 struct icu_buf_utf16 * tkn16,
159 int32_t icu_tokenizer_token_id(struct icu_tokenizer * tokenizer);
160 int32_t icu_tokenizer_token_start(struct icu_tokenizer * tokenizer);
161 int32_t icu_tokenizer_token_end(struct icu_tokenizer * tokenizer);
162 int32_t icu_tokenizer_token_length(struct icu_tokenizer * tokenizer);
163 int32_t icu_tokenizer_token_count(struct icu_tokenizer * tokenizer);
167 struct icu_normalizer
170 struct icu_buf_utf16 * rules16;
171 UParseError parse_error[256];
172 UTransliterator * trans;
175 struct icu_normalizer * icu_normalizer_create(const char *rules, char action,
179 void icu_normalizer_destroy(struct icu_normalizer * normalizer);
181 int icu_normalizer_normalize(struct icu_normalizer * normalizer,
182 struct icu_buf_utf16 * dest16,
183 struct icu_buf_utf16 * src16,
186 enum icu_chain_step_type {
187 ICU_chain_step_type_none,
188 ICU_chain_step_type_display, /* convert to utf8 display format */
189 ICU_chain_step_type_casemap, /* apply utf16 charmap */
190 ICU_chain_step_type_normalize, /* apply utf16 normalization */
191 ICU_chain_step_type_tokenize /* apply utf16 tokenization */
196 struct icu_chain_step
198 /* type and action object */
199 enum icu_chain_step_type type;
201 struct icu_casemap * casemap;
202 struct icu_normalizer * normalizer;
203 struct icu_tokenizer * tokenizer;
205 /* temprary post-action utf16 buffer */
206 struct icu_buf_utf16 * buf16;
207 struct icu_chain_step * previous;
215 struct icu_chain_step * icu_chain_step_create(yaz_icu_chain_t chain,
216 enum icu_chain_step_type type,
217 const uint8_t * rule,
218 struct icu_buf_utf16 * buf16,
222 void icu_chain_step_destroy(struct icu_chain_step * step);
230 const char * src8cstr;
234 /* number of tokens returned so far */
237 /* utf8 output buffers */
238 struct icu_buf_utf8 * display8;
239 struct icu_buf_utf8 * norm8;
240 struct icu_buf_utf8 * sort8;
242 /* utf16 source buffer */
243 struct icu_buf_utf16 * src16;
245 /* linked list of chain steps */
246 struct icu_chain_step * steps;
249 struct icu_chain_step * icu_chain_insert_step(yaz_icu_chain_t chain,
250 enum icu_chain_step_type type,
251 const uint8_t * rule,
254 int icu_chain_step_next_token(yaz_icu_chain_t chain,
255 struct icu_chain_step * step,
258 int icu_chain_token_number(yaz_icu_chain_t chain);
260 const UCollator * icu_chain_get_coll(yaz_icu_chain_t chain);
262 #endif /* ICU_I18NL_H */
267 * indent-tabs-mode: nil
269 * vim: shiftwidth=4 tabstop=8 expandtab