*/
/* DO NOT EDIT THIS FILE IF YOUR EDITOR DOES NOT SUPPORT UTF-8 */
-
+
#if HAVE_CONFIG_H
#include "config.h"
struct icu_termmap *itmp2 = *(struct icu_termmap **) vp2;
int cmp = 0;
-
- cmp = strcmp((const char *)itmp1->sort_key,
+
+ cmp = strcmp((const char *)itmp1->sort_key,
(const char *)itmp2->sort_key);
return cmp;
}
/* perform case mapping */
icu_utf16_casemap(dest16, src16, locale, action, &status);
-
+
/* converting to UTF8 */
icu_utf16_to_utf8(dest8, dest16, &status);
/* determine success */
- if (dest8->utf8
+ if (dest8->utf8
&& (dest8->utf8_len == strlen(chk8cstr))
&& !strcmp(chk8cstr, (const char *) dest8->utf8))
success = 1;
yaz_log(YLOG_WARN, "test_icu_casemap failed");
yaz_log(YLOG_LOG, "Original string: '%s' (%d)",
src8cstr, src8cstr_len);
- yaz_log(YLOG_LOG, "icu_casemap '%s:%c' '%s' (%d)",
+ yaz_log(YLOG_LOG, "icu_casemap '%s:%c' '%s' (%d)",
locale, action, dest8->utf8, dest8->utf8_len);
yaz_log(YLOG_LOG, "expected string: '%s' (%d)",
chk8cstr, chk8cstr_len);
}
-
+
/* clean the buffers */
icu_buf_utf8_destroy(src8);
icu_buf_utf8_destroy(dest8);
icu_buf_utf16_destroy(src16);
icu_buf_utf16_destroy(dest16);
-
+
return success;
}
/* successful tests */
YAZ_CHECK(test_icu_casemap("en", 'l',
- "A ReD fOx hunTS sQUirriLs",
+ "A ReD fOx hunTS sQUirriLs",
"a red fox hunts squirrils"));
-
+
YAZ_CHECK(test_icu_casemap("en", 'u',
- "A ReD fOx hunTS sQUirriLs",
+ "A ReD fOx hunTS sQUirriLs",
"A RED FOX HUNTS SQUIRRILS"));
-
+
YAZ_CHECK(test_icu_casemap("en", 'f',
- "A ReD fOx hunTS sQUirriLs",
+ "A ReD fOx hunTS sQUirriLs",
"a red fox hunts squirrils"));
-
+
YAZ_CHECK(test_icu_casemap("en", 't',
- "A ReD fOx hunTS sQUirriLs",
+ "A ReD fOx hunTS sQUirriLs",
"A Red Fox Hunts Squirrils"));
-
+
/* Locale 'da' */
/* success expected */
YAZ_CHECK(test_icu_casemap("da", 'l',
- "åh ÆbLE, øs fLØde i Åen efter bLåBærGRødeN",
+ "åh ÆbLE, øs fLØde i Åen efter bLåBærGRødeN",
"åh æble, øs fløde i åen efter blåbærgrøden"));
YAZ_CHECK(test_icu_casemap("da", 'u',
- "åh ÆbLE, øs fLØde i Åen efter bLåBærGRødeN",
+ "åh ÆbLE, øs fLØde i Åen efter bLåBærGRødeN",
"ÅH ÆBLE, ØS FLØDE I ÅEN EFTER BLÅBÆRGRØDEN"));
YAZ_CHECK(test_icu_casemap("da", 'f',
- "åh ÆbLE, øs fLØde i Åen efter bLåBærGRødeN",
+ "åh ÆbLE, øs fLØde i Åen efter bLåBærGRødeN",
"åh æble, øs fløde i åen efter blåbærgrøden"));
YAZ_CHECK(test_icu_casemap("da", 't',
- "åh ÆbLE, øs fLØde i Åen efter bLåBærGRødeN",
+ "åh ÆbLE, øs fLØde i Åen efter bLåBærGRødeN",
"Åh Æble, Øs Fløde I Åen Efter Blåbærgrøden"));
/* Locale 'de' */
struct icu_termmap * list[src_list_len];
- UCollator *coll = ucol_open(locale, &status);
+ UCollator *coll = ucol_open(locale, &status);
icu_check_status(status);
if (U_FAILURE(status))
return 0;
/* assigning display terms and sort keys using buf 8 and buf16 */
- for (i = 0; i < src_list_len; i++)
+ for (i = 0; i < src_list_len; i++)
{
list[i] = (struct icu_termmap *) malloc(sizeof(struct icu_termmap));
/* copy display term */
- strcpy(list[i]->disp_term, src_list[i]);
+ strcpy(list[i]->disp_term, src_list[i]);
/* transforming to UTF16 */
icu_utf16_from_utf8_cstr(buf16, list[i]->disp_term, &status);
/* computing sortkeys */
icu_sortkey8_from_utf16(coll, buf8, buf16, &status);
icu_check_status(status);
-
+
/* assigning sortkeys */
- memcpy(list[i]->sort_key, buf8->utf8, buf8->utf8_len);
- }
+ memcpy(list[i]->sort_key, buf8->utf8, buf8->utf8_len);
+ }
/* do the sorting */
qsort(list, src_list_len, sizeof(struct icu_termmap *), icu_termmap_cmp);
if (!success)
{
- yaz_log(YLOG_LOG, "ERROR");
- yaz_log(YLOG_LOG, "Input str:'%s':", locale);
+ yaz_log(YLOG_LOG, "ERROR");
+ yaz_log(YLOG_LOG, "Input str:'%s':", locale);
for (i = 0; i < src_list_len; i++) {
- yaz_log(YLOG_LOG, " '%s'", list[i]->disp_term);
+ yaz_log(YLOG_LOG, " '%s'", list[i]->disp_term);
}
- yaz_log(YLOG_LOG, "ICU sort: '%s':", locale);
+ yaz_log(YLOG_LOG, "ICU sort: '%s':", locale);
for (i = 0; i < src_list_len; i++) {
- yaz_log(YLOG_LOG, " '%s'", list[i]->disp_term);
+ yaz_log(YLOG_LOG, " '%s'", list[i]->disp_term);
}
- yaz_log(YLOG_LOG, "Expected: '%s':", locale);
+ yaz_log(YLOG_LOG, "Expected: '%s':", locale);
for (i = 0; i < src_list_len; i++) {
- yaz_log(YLOG_LOG, " '%s'", chk_list[i]);
+ yaz_log(YLOG_LOG, " '%s'", chk_list[i]);
}
}
-
+
for (i = 0; i < src_list_len; i++)
free(list[i]);
-
+
ucol_close(coll);
icu_buf_utf8_destroy(buf8);
icu_buf_utf16_destroy(buf16);
- return success;
+ return success;
}
static void check_icu_sortmap(void)
YAZ_CHECK(test_icu_sortmap("en_CA", en_1_len, en_1_src, en_1_cck));
YAZ_CHECK(test_icu_sortmap("en_GB", en_1_len, en_1_src, en_1_cck));
YAZ_CHECK(test_icu_sortmap("en_US", en_1_len, en_1_src, en_1_cck));
-
+
/* successful tests */
{
size_t da_1_len = 6;
const char * chk8cstr)
{
int success = 0;
-
+
UErrorCode status = U_ZERO_ERROR;
struct icu_buf_utf16 * src16 = icu_buf_utf16_create(0);
struct icu_transform * transform
= icu_transform_create(rules8cstr, 'f', 0, &status);
icu_check_status(status);
-
+
icu_utf16_from_utf8_cstr(src16, src8cstr, &status);
icu_check_status(status);
icu_check_status(status);
- if (!strcmp((const char *) dest8->utf8,
+ if (!strcmp((const char *) dest8->utf8,
(const char *) chk8cstr))
success = 1;
else
YAZ_CHECK(test_icu_normalizer("[:Punctuation:] Any-Remove",
"Don't shoot!",
"Dont shoot"));
-
+
YAZ_CHECK(test_icu_normalizer("[:Control:] Any-Remove",
"Don't\n shoot!",
"Don't shoot!"));
YAZ_CHECK(test_icu_normalizer("Lower; [:^Letter:] Remove",
"Don't shoot!",
"dontshoot"));
-
+
YAZ_CHECK(test_icu_normalizer("[:^Number:] Remove",
"Monday 15th of April",
"15"));
YAZ_CHECK(tokenizer);
/* attach text buffer to tokenizer */
- icu_tokenizer_attach(tokenizer, src16, &status);
+ icu_tokenizer_attach(tokenizer, src16, &status);
icu_check_status(status);
/* perform work on tokens */
icu_buf_utf16_destroy(src16);
icu_buf_utf16_destroy(tkn16);
icu_buf_utf8_destroy(tkn8);
-
+
return success;
}
static void check_icu_tokenizer(void)
{
- const char * en_str
+ const char * en_str
= "O Romeo, Romeo! wherefore art thou Romeo?";
-
+
YAZ_CHECK(test_icu_tokenizer("en", 's', en_str, 2));
YAZ_CHECK(test_icu_tokenizer("en", 'l', en_str, 7));
YAZ_CHECK(test_icu_tokenizer("en", 'w', en_str, 16));
YAZ_CHECK(test_icu_tokenizer("en", 'c', en_str, 41));
{
- const char * da_str
+ const char * da_str
= "Blåbærtærte. Denne kage stammer fra Finland. "
"Den er med blåbær, men alle sommerens forskellige bær kan bruges.";
-
+
YAZ_CHECK(test_icu_tokenizer("da", 's', da_str, 3));
YAZ_CHECK(test_icu_tokenizer("dar", 'l', da_str, 17));
YAZ_CHECK(test_icu_tokenizer("da", 'w', da_str, 37));
static void check_icu_chain(void)
{
- const char * en_str
+ const char * en_str
= "O Romeo, Romeo! wherefore art thou\t Romeo?";
UErrorCode status = U_ZERO_ERROR;
struct icu_chain * chain = 0;
-
+
const char * xml_str = "<icu locale=\"en\">"
"<transform rule=\"[:Control:] Any-Remove\"/>"
"<tokenize rule=\"l\"/>"
"<casemap rule=\"l\"/>"
"</icu>";
-
+
xmlDoc *doc = xmlParseMemory(xml_str, strlen(xml_str));
xmlNode *xml_node = xmlDocGetRootElement(doc);
YAZ_CHECK(xml_node);
{
UErrorCode status = U_ZERO_ERROR;
struct icu_chain * chain = 0;
-
+
const char * xml_str = "<icu locale=\"en\">"
/* if the first rule is normalize instead. Then it works */
"<casemap rule=\"l\"/>"
"</icu>";
-
+
xmlDoc *doc = xmlParseMemory(xml_str, strlen(xml_str));
xmlNode *xml_node = xmlDocGetRootElement(doc);
YAZ_CHECK(xml_node);
YAZ_CHECK(chain);
if (!chain)
return;
-
+
YAZ_CHECK(icu_chain_assign_cstr(
chain, "O Romeo, Romeo! wherefore art thou\t Romeo?",
&status));
icu_chain_token_norm(chain),
icu_chain_token_display(chain)); */
}
-
+
YAZ_CHECK_EQ(icu_chain_token_number(chain), 7);
"<tokenize rule=\"w\"/>"
"<transform rule=\"[[:WhiteSpace:][:Punctuation:]] Remove\"/>"
"</icu>";
-
+
xmlDoc *doc = xmlParseMemory(xml_str, strlen(xml_str));
xmlNode *xml_node = xmlDocGetRootElement(doc);
YAZ_CHECK(xml_node);
xmlFreeDoc(doc);
YAZ_CHECK(chain);
-
+
YAZ_CHECK(icu_chain_assign_cstr(
chain, "a string with 15 tokenss and 8 displays",
&status));
const char * xml_str = "<icu locale=\"en\">"
"</icu>";
-
+
const char * src8 = "some 5487 weired !¤%&(/& sTuFf";
char * dest8 = 0;
xmlFreeDoc(doc);
YAZ_CHECK(chain);
-
+
YAZ_CHECK(icu_chain_assign_cstr(
chain, src8,
&status));
dest8 = (char *) icu_chain_token_norm(chain);
YAZ_CHECK_EQ(strcmp(src8, dest8), 0);
-
+
icu_chain_destroy(chain);
}
"<tokenize rule=\"w\"/>"
"<transform rule=\"[[:WhiteSpace:][:Punctuation:]] Remove\"/>"
"</icu>";
-
+
xmlDoc *doc = xmlParseMemory(xml_str, strlen(xml_str));
YAZ_CHECK(doc);
if (!doc)
xmlFreeDoc(doc);
YAZ_CHECK(chain);
-
+
iter = icu_iter_create(chain);
icu_iter_first(iter, "a string with 15 tokens and 8 displays");
YAZ_CHECK(iter);
{
struct icu_chain *chain = (struct icu_chain *) p;
int i;
-
+
for (i = 0; i < 1000; i++)
{
YAZ_CHECK(test_iter(chain, "Adobe Acrobat Reader, 1991-1999.",
YAZ_CHECK(chain);
if (!chain)
return;
-
+
YAZ_CHECK(test_iter(chain, "Adobe Acrobat Reader, 1991-1999.",
"[adobe][acrobat][reader][1991][][1999][]"));
struct icu_chain * chain = 0;
xmlNode *xml_node;
- const char * xml_str =
+ const char * xml_str =
"<icu_chain id=\"sort\" locale=\"el\">\n"
"<transform rule=\"[:Control:] Any-Remove\"/>\n"
"<transform rule=\"[[:Control:][:WhiteSpace:][:Punctuation:]] Remove\"/>\n"
YAZ_CHECK(chain);
if (!chain)
return;
-
+
YAZ_CHECK(test_iter(chain, "Adobe Acrobat Reader, 1991-1999.",
"[adobeacrobatreader19911999]"));
int main(int argc, char **argv)
{
- YAZ_CHECK_INIT(argc, argv);
+ YAZ_CHECK_INIT(argc, argv);
YAZ_CHECK_LOG();
#if YAZ_HAVE_ICU
check_icu_chain();
check_chain_empty_token();
check_chain_empty_chain();
- check_icu_iter1();
+ check_icu_iter1();
check_icu_iter2();
check_icu_iter3();
-
+
check_bug_1140();
u_cleanup();
YAZ_CHECK(0 == 0);
#endif /* YAZ_HAVE_ICU */
-
+
YAZ_CHECK_TERM;
}
projects / yaz-moved-to-github.git / blobdiff