1 /* $Id: test_icu_I18N.c,v 1.16 2007-05-11 08:27:29 marc Exp $
2 Copyright (c) 2006-2007, Index Data.
4 This file is part of Pazpar2.
6 Pazpar2 is free software; you can redistribute it and/or modify it under
7 the terms of the GNU General Public License as published by the Free
8 Software Foundation; either version 2, or (at your option) any later
11 Pazpar2 is distributed in the hope that it will be useful, but WITHOUT ANY
12 WARRANTY; without even the implied warranty of MERCHANTABILITY or
13 FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
16 You should have received a copy of the GNU General Public License
17 along with Pazpar2; see the file LICENSE. If not, write to the
18 Free Software Foundation, 59 Temple Place - Suite 330, Boston, MA
22 // DO NOT EDIT THIS FILE IF YOUR EDITOR DOES NOT SUPPORT UTF-8
31 #include <yaz/timing.h>
44 //#include <unicode/ustring.h>
45 // DO NOT EDIT THIS FILE IF YOUR EDITOR DOES NOT SUPPORT UTF-8
48 #define MAX_KEY_SIZE 256
51 uint8_t sort_key[MAX_KEY_SIZE]; // standard C string '\0' terminated
52 char disp_term[MAX_KEY_SIZE]; // standard C utf-8 string
57 int icu_termmap_cmp(const void *vp1, const void *vp2)
59 struct icu_termmap *itmp1 = *(struct icu_termmap **) vp1;
60 struct icu_termmap *itmp2 = *(struct icu_termmap **) vp2;
64 cmp = strcmp((const char *)itmp1->sort_key,
65 (const char *)itmp2->sort_key);
72 int test_icu_casemap(const char * locale, char action,
73 const char * src8cstr, const char * chk8cstr)
76 UErrorCode status = U_ZERO_ERROR;
78 struct icu_buf_utf8 * src8 = icu_buf_utf8_create(0);
79 struct icu_buf_utf8 * dest8 = icu_buf_utf8_create(0);
80 struct icu_buf_utf16 * src16 = icu_buf_utf16_create(0);
81 struct icu_buf_utf16 * dest16 = icu_buf_utf16_create(0);
84 int src8cstr_len = strlen(src8cstr);
85 int chk8cstr_len = strlen(chk8cstr);
87 // converting to UTF16
88 icu_utf16_from_utf8_cstr(src16, src8cstr, &status);
90 // perform case mapping
91 icu_utf16_casemap(dest16, src16, locale, action, &status);
94 icu_utf16_to_utf8(dest8, dest16, &status);
100 && (dest8->utf8_len == strlen(chk8cstr))
101 && !strcmp(chk8cstr, (const char *) dest8->utf8))
109 printf("original string: '%s' (%d)\n", src8cstr, src8cstr_len);
110 printf("icu_casemap '%s:%c' '%s' (%d)\n",
111 locale, action, dest8->utf8, dest8->utf8_len);
112 printf("expected string: '%s' (%d)\n", chk8cstr, chk8cstr_len);
116 icu_buf_utf8_destroy(src8);
117 icu_buf_utf8_destroy(dest8);
118 icu_buf_utf16_destroy(src16);
119 icu_buf_utf16_destroy(dest16);
127 // DO NOT EDIT THIS FILE IF YOUR EDITOR DOES NOT SUPPORT UTF-8
129 void test_icu_I18N_casemap(int argc, char **argv)
135 YAZ_CHECK(test_icu_casemap("en", 'l',
136 "A ReD fOx hunTS sQUirriLs",
137 "a red fox hunts squirrils"));
139 YAZ_CHECK(test_icu_casemap("en", 'u',
140 "A ReD fOx hunTS sQUirriLs",
141 "A RED FOX HUNTS SQUIRRILS"));
143 YAZ_CHECK(test_icu_casemap("en", 'f',
144 "A ReD fOx hunTS sQUirriLs",
145 "a red fox hunts squirrils"));
147 YAZ_CHECK(test_icu_casemap("en", 't',
148 "A ReD fOx hunTS sQUirriLs",
149 "A Red Fox Hunts Squirrils"));
155 YAZ_CHECK(test_icu_casemap("da", 'l',
156 "åh ÆbLE, øs fLØde i Åen efter bLåBærGRødeN",
157 "åh æble, øs fløde i åen efter blåbærgrøden"));
159 YAZ_CHECK(test_icu_casemap("da", 'u',
160 "åh ÆbLE, øs fLØde i Åen efter bLåBærGRødeN",
161 "ÅH ÆBLE, ØS FLØDE I ÅEN EFTER BLÅBÆRGRØDEN"));
163 YAZ_CHECK(test_icu_casemap("da", 'f',
164 "åh ÆbLE, øs fLØde i Åen efter bLåBærGRødeN",
165 "åh æble, øs fløde i åen efter blåbærgrøden"));
167 YAZ_CHECK(test_icu_casemap("da", 't',
168 "åh ÆbLE, øs fLØde i Åen efter bLåBærGRødeN",
169 "Åh Æble, Øs Fløde I Åen Efter Blåbærgrøden"));
174 YAZ_CHECK(test_icu_casemap("de", 'l',
175 "zWÖlf ärgerliche Würste rollen ÜBer die StRAße",
176 "zwölf ärgerliche würste rollen über die straße"));
178 YAZ_CHECK(test_icu_casemap("de", 'u',
179 "zWÖlf ärgerliche Würste rollen ÜBer die StRAße",
180 "ZWÖLF ÄRGERLICHE WÜRSTE ROLLEN ÜBER DIE STRASSE"));
182 YAZ_CHECK(test_icu_casemap("de", 'f',
183 "zWÖlf ärgerliche Würste rollen ÜBer die StRAße",
184 "zwölf ärgerliche würste rollen über die strasse"));
186 YAZ_CHECK(test_icu_casemap("de", 't',
187 "zWÖlf ärgerliche Würste rollen ÜBer die StRAße",
188 "Zwölf Ärgerliche Würste Rollen Über Die Straße"));
193 // DO NOT EDIT THIS FILE IF YOUR EDITOR DOES NOT SUPPORT UTF-8
195 int test_icu_sortmap(const char * locale, int src_list_len,
196 const char ** src_list, const char ** chk_list)
200 UErrorCode status = U_ZERO_ERROR;
202 struct icu_buf_utf8 * buf8 = icu_buf_utf8_create(0);
203 struct icu_buf_utf16 * buf16 = icu_buf_utf16_create(0);
207 struct icu_termmap * list[src_list_len];
209 UCollator *coll = ucol_open(locale, &status);
210 icu_check_status(status);
212 if(U_FAILURE(status))
215 // assigning display terms and sort keys using buf 8 and buf16
216 for( i = 0; i < src_list_len; i++)
219 list[i] = (struct icu_termmap *) malloc(sizeof(struct icu_termmap));
222 strcpy(list[i]->disp_term, src_list[i]);
224 // transforming to UTF16
225 icu_utf16_from_utf8_cstr(buf16, list[i]->disp_term, &status);
226 icu_check_status(status);
228 // computing sortkeys
229 icu_sortkey8_from_utf16(coll, buf8, buf16, &status);
230 icu_check_status(status);
232 // assigning sortkeys
233 memcpy(list[i]->sort_key, buf8->utf8, buf8->utf8_len);
234 //strncpy(list[i]->sort_key, buf8->utf8, buf8->utf8_len);
235 //strcpy((char *) list[i]->sort_key, (const char *) buf8->utf8);
240 qsort(list, src_list_len,
241 sizeof(struct icu_termmap *), icu_termmap_cmp);
243 // checking correct sorting
244 for (i = 0; i < src_list_len; i++){
245 if (0 != strcmp(list[i]->disp_term, chk_list[i])){
252 printf("Input str: '%s' : ", locale);
253 for (i = 0; i < src_list_len; i++) {
254 printf(" '%s'", list[i]->disp_term);
257 printf("ICU sort: '%s' : ", locale);
258 for (i = 0; i < src_list_len; i++) {
259 printf(" '%s'", list[i]->disp_term);
260 //printf("(%d|%d)", list[i]->sort_key[0],list[i]->sort_key[1]);
263 printf("Expected: '%s' : ", locale);
264 for (i = 0; i < src_list_len; i++) {
265 printf(" '%s'", chk_list[i]);
273 icu_buf_utf8_destroy(buf8);
274 icu_buf_utf16_destroy(buf16);
282 // DO NOT EDIT THIS FILE IF YOUR EDITOR DOES NOT SUPPORT UTF-8
284 void test_icu_I18N_sortmap(int argc, char **argv)
289 const char * en_1_src[6] = {"z", "K", "a", "A", "Z", "k"};
290 const char * en_1_cck[6] = {"a", "A", "k", "K", "z", "Z"};
291 YAZ_CHECK(test_icu_sortmap("en", en_1_len, en_1_src, en_1_cck));
292 YAZ_CHECK(test_icu_sortmap("en_AU", en_1_len, en_1_src, en_1_cck));
293 YAZ_CHECK(test_icu_sortmap("en_CA", en_1_len, en_1_src, en_1_cck));
294 YAZ_CHECK(test_icu_sortmap("en_GB", en_1_len, en_1_src, en_1_cck));
295 YAZ_CHECK(test_icu_sortmap("en_US", en_1_len, en_1_src, en_1_cck));
299 const char * da_1_src[6] = {"z", "å", "o", "æ", "a", "ø"};
300 const char * da_1_cck[6] = {"a", "o", "z", "æ", "ø", "å"};
301 YAZ_CHECK(test_icu_sortmap("da", da_1_len, da_1_src, da_1_cck));
302 YAZ_CHECK(test_icu_sortmap("da_DK", da_1_len, da_1_src, da_1_cck));
306 const char * de_1_src[9] = {"u", "ä", "o", "t", "s", "ß", "ü", "ö", "a"};
307 const char * de_1_cck[9] = {"a","ä", "o", "ö", "s", "ß", "t", "u", "ü"};
308 YAZ_CHECK(test_icu_sortmap("de", de_1_len, de_1_src, de_1_cck));
309 YAZ_CHECK(test_icu_sortmap("de_AT", de_1_len, de_1_src, de_1_cck));
310 YAZ_CHECK(test_icu_sortmap("de_DE", de_1_len, de_1_src, de_1_cck));
315 // DO NOT EDIT THIS FILE IF YOUR EDITOR DOES NOT SUPPORT UTF-8
317 void test_icu_I18N_transliterator(int argc, char **argv)
320 UErrorCode status = U_ZERO_ERROR;
321 UParseError parse_error[256];
323 const char * rules8cstr = "[:Punctuation:] Any-Remove";
324 //const char * rules8cstr = "[:Control:] Any-Remove";
325 //const char * rules8cstr = "[:Decimal_Number:] Any-Remove\n";
326 //const char * rules8cstr = "[:Final_Punctuation:] Any-Remove";
327 //const char * rules8cstr = "Lower; [:^Letter:] Remove";
328 //const char * rules8cstr = "[:^Number:] Remove";
329 //const char * rules8cstr = "Lower;[[:WhiteSpace:][:Punctuation:]] Remove";
330 //const char * rules8cstr = "NFD; [:Nonspacing Mark:] Remove; NFC";
335 const char * src8cstr = "Genesis 1\n"
337 "1 In the beginning God created the heavens and the earth.\n"
338 "2 Now the earth was formless and empty, darkness was over "
339 "the surface of the deep, and the Spirit of God was hovering "
341 "3 And God said, Let there be light, and there was light.\n";
345 struct icu_buf_utf16 * rules16 = icu_buf_utf16_create(0);
346 struct icu_buf_utf16 * src16 = icu_buf_utf16_create(0);
347 struct icu_buf_utf16 * dest16 = icu_buf_utf16_create(0);
348 struct icu_buf_utf8 * dest8 = icu_buf_utf8_create(0);
350 icu_utf16_from_utf8_cstr(rules16, rules8cstr, &status);
351 icu_check_status(status);
353 icu_utf16_from_utf8_cstr(src16, src8cstr, &status);
354 icu_check_status(status);
356 UTransliterator * trans
357 = utrans_openU(rules16->utf16, rules16->utf16_len,
360 parse_error, &status);
362 //= utrans_openU(0, 0, UTRANS_FORWARD,
363 // rules16->utf16, rules16->utf16_len,
364 // parse_error, &status);
366 icu_check_status(status);
367 if(U_FAILURE(status)) {
368 printf("Parse Error: \n line %d offset %d \n '%s'\n",
369 parse_error->line, parse_error->offset,
373 utrans_transUChars (trans, src16->utf16, &(src16->utf16_len),
375 0, &(src16->utf16_len), &status);
377 icu_utf16_to_utf8(dest8, src16, &status);
378 icu_check_status(status);
380 printf("Transliterator:\n%s\n", dest8->utf8);
383 utrans_close (trans);
384 icu_buf_utf16_destroy(rules16);
385 icu_buf_utf16_destroy(src16);
386 icu_buf_utf16_destroy(dest16);
387 icu_buf_utf8_destroy(dest8);
392 icu_check_status(status);
395 int32_t ustr16_lim = *ustr16_len;
396 /* Transliterate a segment of a UChar* string */
398 utrans_transUChars (trans, ustr16, &*ustr16_len,
400 0, &ustr16_lim, &status);
402 utrans_close (trans);
404 printf("\n\nUnicode Set Patterns:\n"
405 " Pattern Description\n"
406 " Ranges [a-z] The lower case letters a through z\n"
407 " Named Chars [abc123] The six characters a,b,c,1,2 and 3\n"
408 " String [abc{def}] chars a, b and c, and string 'def'\n"
409 " Categories [\\p{Letter}] Perl General Category 'Letter'.\n"
410 " Categories [:Letter:] Posix General Category 'Letter'.\n"
412 " Combination Example\n"
413 " Union [[:Greek:] [:letter:]]\n"
414 " Intersection [[:Greek:] & [:letter:]]\n"
415 " Set Complement [[:Greek:] - [:letter:]]\n"
416 " Complement [^[:Greek:] [:letter:]]\n"
418 "see: http://icu.sourceforge.net/userguide/unicodeSet.html\n"
421 " [:Punctuation:] Any-Remove\n"
422 " [:Cased-Letter:] Any-Upper\n"
423 " [:Control:] Any-Remove\n"
424 " [:Decimal_Number:] Any-Remove\n"
425 " [:Final_Punctuation:] Any-Remove\n"
426 " [:Georgian:] Any-Upper\n"
427 " [:Katakana:] Any-Remove\n"
428 " [:Arabic:] Any-Remove\n"
429 " [:Punctuation:] Remove\n"
430 " [[:Punctuation:]-[.,]] Remove\n"
431 " [:Line_Separator:] Any-Remove\n"
432 " [:Math_Symbol:] Any-Remove\n"
433 " Lower; [:^Letter:] Remove (word tokenization)\n"
434 " [:^Number:] Remove (numeric tokenization)\n"
435 " [:^Katagana:] Remove (remove everything except Katagana)\n"
436 " Lower;[[:WhiteSpace:][:Punctuation:]] Remove (word tokenization)\n"
437 " NFD; [:Nonspacing Mark:] Remove; NFC (removes accents from characters)\n"
438 " [A-Za-z]; Lower(); Latin-Katakana; Katakana-Hiragana (transforms latin and katagana to hiragana)\n"
439 " [[:separator:][:start punctuation:][:initial punctuation:]] Remove \n"
441 "see http://icu.sourceforge.net/userguide/Transform.html\n"
442 " http://www.unicode.org/Public/UNIDATA/UCD.html\n"
443 " http://icu.sourceforge.net/userguide/Transform.html\n"
444 " http://icu.sourceforge.net/userguide/TransformRule.html\n"
450 // DO NOT EDIT THIS FILE IF YOUR EDITOR DOES NOT SUPPORT UTF-8
452 int test_icu_tokenizer(const char * locale, char action,
453 const char * src8cstr, int count)
457 UErrorCode status = U_ZERO_ERROR;
458 struct icu_buf_utf16 * src16 = icu_buf_utf16_create(0);
459 struct icu_buf_utf16 * tkn16 = icu_buf_utf16_create(0);
460 struct icu_buf_utf8 * tkn8 = icu_buf_utf8_create(0);
462 //printf("Input: '%s'\n", src8cstr);
464 // transforming to UTF16
465 icu_utf16_from_utf8_cstr(src16, src8cstr, &status);
466 icu_check_status(status);
469 struct icu_tokenizer * tokenizer
470 = icu_tokenizer_create(locale, action, &status);
471 icu_check_status(status);
472 YAZ_CHECK(tokenizer);
474 // attach text buffer to tokenizer
475 icu_tokenizer_attach(tokenizer, src16, &status);
476 icu_check_status(status);
477 YAZ_CHECK(tokenizer->bi);
479 // perform work on tokens
480 //printf("Tokens: ");
481 while(icu_tokenizer_next_token(tokenizer, tkn16, &status)){
482 icu_check_status(status);
484 // converting to UTF8
485 icu_utf16_to_utf8(tkn8, tkn16, &status);
487 //printf("(%d)'%s' ", icu_tokenizer_token_id(tokenizer), tkn8->utf8);
489 //printf("token %d %d %d %d '%s'\n",
491 // icu_tokenizer_token_start(tokenizer),
492 // icu_tokenizer_token_end(tokenizer),
493 // icu_tokenizer_token_length(tokenizer),
496 //printf("\nTokens: %d\n", icu_tokenizer_token_count(tokenizer));
499 if (count != icu_tokenizer_token_count(tokenizer)){
501 printf("\nTokenizer '%s:%c' Error: \n", locale, action);
502 printf("Input: '%s'\n", src8cstr);
503 printf("Tokens: %d", icu_tokenizer_token_count(tokenizer));
504 printf(", expected: %d\n", count);
507 icu_tokenizer_destroy(tokenizer);
508 icu_buf_utf16_destroy(src16);
509 icu_buf_utf16_destroy(tkn16);
510 icu_buf_utf8_destroy(tkn8);
516 // DO NOT EDIT THIS FILE IF YOUR EDITOR DOES NOT SUPPORT UTF-8
518 void test_icu_I18N_tokenizer(int argc, char **argv)
523 = "O Romeo, Romeo! wherefore art thou Romeo?";
525 YAZ_CHECK(test_icu_tokenizer("en", 's', en_str, 2));
526 YAZ_CHECK(test_icu_tokenizer("en", 'l', en_str, 7));
527 YAZ_CHECK(test_icu_tokenizer("en", 'w', en_str, 16));
528 YAZ_CHECK(test_icu_tokenizer("en", 'c', en_str, 41));
533 = "Blåbærtærte. Denne kage stammer fra Finland. "
534 "Den er med blåbær, men alle sommerens forskellige bær kan bruges.";
536 YAZ_CHECK(test_icu_tokenizer("da", 's', da_str, 3));
537 YAZ_CHECK(test_icu_tokenizer("dar", 'l', da_str, 17));
538 YAZ_CHECK(test_icu_tokenizer("da", 'w', da_str, 37));
539 YAZ_CHECK(test_icu_tokenizer("da", 'c', da_str, 110));
549 // DO NOT EDIT THIS FILE IF YOUR EDITOR DOES NOT SUPPORT UTF-8
551 int main(int argc, char **argv)
554 YAZ_CHECK_INIT(argc, argv);
559 //test_icu_I18N_casemap_failures(argc, argv);
560 test_icu_I18N_casemap(argc, argv);
561 test_icu_I18N_sortmap(argc, argv);
562 test_icu_I18N_transliterator(argc, argv);
563 test_icu_I18N_tokenizer(argc, argv);
567 printf("ICU unit tests omitted.\n"
568 "Please install libicu36-dev and icu-doc or similar\n");
577 // DO NOT EDIT THIS FILE IF YOUR EDITOR DOES NOT SUPPORT UTF-8
584 * indent-tabs-mode: nil
586 * vim: shiftwidth=4 tabstop=8 expandtab