#include <string.h>
#include <stdlib.h>
-/* DO NOT EDIT THIS FILE IF YOUR EDITOR DOES NOT SUPPORT UTF-8 */
-
-
#define MAX_KEY_SIZE 256
struct icu_termmap
{
};
-
int icu_termmap_cmp(const void *vp1, const void *vp2)
{
struct icu_termmap *itmp1 = *(struct icu_termmap **) vp1;
cmp = strcmp((const char *)itmp1->sort_key,
(const char *)itmp2->sort_key);
return cmp;
-};
-
-
+}
int test_icu_casemap(const char * locale, char action,
/* converting to UTF8 */
icu_utf16_to_utf8(dest8, dest16, &status);
-
-
/* determine success */
if (dest8->utf8
&& (dest8->utf8_len == strlen(chk8cstr))
icu_buf_utf8_destroy(dest8);
icu_buf_utf16_destroy(src16);
icu_buf_utf16_destroy(dest16);
-
-
+
return success;
}
-
-
-/* DO NOT EDIT THIS FILE IF YOUR EDITOR DOES NOT SUPPORT UTF-8 */
-
void test_icu_I18N_casemap(int argc, char **argv)
{
-
/* Locale 'en' */
/* successful tests */
"A ReD fOx hunTS sQUirriLs",
"A Red Fox Hunts Squirrils"));
-
/* Locale 'da' */
/* success expected */
}
-
-/* DO NOT EDIT THIS FILE IF YOUR EDITOR DOES NOT SUPPORT UTF-8 */
-
int test_icu_sortmap(const char * locale, int src_list_len,
const char ** src_list, const char ** chk_list)
{
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));
+ list[i] = (struct icu_termmap *) malloc(sizeof(struct icu_termmap));
- /* copy display term */
- strcpy(list[i]->disp_term, src_list[i]);
+ /* copy display term */
+ strcpy(list[i]->disp_term, src_list[i]);
- /* transforming to UTF16 */
- icu_utf16_from_utf8_cstr(buf16, list[i]->disp_term, &status);
- icu_check_status(status);
+ /* transforming to UTF16 */
+ icu_utf16_from_utf8_cstr(buf16, list[i]->disp_term, &status);
+ icu_check_status(status);
- /* computing sortkeys */
- icu_sortkey8_from_utf16(coll, buf8, buf16, &status);
- icu_check_status(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);
- }
-
+ /* assigning sortkeys */
+ 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);
+ qsort(list, src_list_len, sizeof(struct icu_termmap *), icu_termmap_cmp);
/* checking correct sorting */
- for (i = 0; i < src_list_len; i++){
+ for (i = 0; i < src_list_len; i++)
+ {
if (0 != strcmp(list[i]->disp_term, chk_list[i])){
success = 0;
}
}
- if(!success){
+ if (!success)
+ {
printf("\nERROR\n");
printf("Input str: '%s' : ", locale);
for (i = 0; i < src_list_len; i++) {
printf("\n");
}
-
-
- for( i = 0; i < src_list_len; i++)
+ for (i = 0; i < src_list_len; i++)
free(list[i]);
-
-
+
ucol_close(coll);
icu_buf_utf8_destroy(buf8);
return success;
}
-
-/* DO NOT EDIT THIS FILE IF YOUR EDITOR DOES NOT SUPPORT UTF-8 */
-
void test_icu_I18N_sortmap(int argc, char **argv)
{
-
/* successful tests */
size_t en_1_len = 6;
const char * en_1_src[6] = {"z", "K", "a", "A", "Z", "k"};
}
-
-/* DO NOT EDIT THIS FILE IF YOUR EDITOR DOES NOT SUPPORT UTF-8 */
-
-
-
-
int test_icu_normalizer(const char * rules8cstr,
- const char * src8cstr,
- const char * chk8cstr)
+ const char * src8cstr,
+ const char * chk8cstr)
{
int success = 0;
if(!strcmp((const char *) dest8->utf8,
(const char *) chk8cstr))
success = 1;
- else {
+ else
+ {
success = 0;
printf("Normalization\n");
printf("Rules: '%s'\n", rules8cstr);
printf("Normalized: '%s'\n", dest8->utf8);
printf("Expected: '%s'\n", chk8cstr);
}
-
icu_transform_destroy(transform);
icu_buf_utf16_destroy(src16);
icu_buf_utf8_destroy(dest8);
return success;
-};
-
-
-/* DO NOT EDIT THIS FILE IF YOUR EDITOR DOES NOT SUPPORT UTF-8 */
+}
void test_icu_I18N_normalizer(int argc, char **argv)
{
-
YAZ_CHECK(test_icu_normalizer("[:Punctuation:] Any-Remove",
"Don't shoot!",
"Dont shoot"));
" word4you? ",
"word4you"));
-
YAZ_CHECK(test_icu_normalizer("NFD; [:Nonspacing Mark:] Remove; NFC",
"à côté de l'alcôve ovoïde",
"a cote de l'alcove ovoide"));
-
}
-
-/* DO NOT EDIT THIS FILE IF YOUR EDITOR DOES NOT SUPPORT UTF-8 */
-
int test_icu_tokenizer(const char * locale, char action,
- const char * src8cstr, int count)
+ const char * src8cstr, int count)
{
int success = 1;
return success;
}
-
-/* DO NOT EDIT THIS FILE IF YOUR EDITOR DOES NOT SUPPORT UTF-8 */
-
void test_icu_I18N_tokenizer(int argc, char **argv)
{
-
-
const char * en_str
= "O Romeo, Romeo! wherefore art thou Romeo?";
YAZ_CHECK(test_icu_tokenizer("en", 'w', en_str, 16));
YAZ_CHECK(test_icu_tokenizer("en", 'c', en_str, 41));
-
-
{
const char * da_str
= "Blåbærtærte. Denne kage stammer fra Finland. "
YAZ_CHECK(test_icu_tokenizer("da", 'w', da_str, 37));
YAZ_CHECK(test_icu_tokenizer("da", 'c', da_str, 110));
}
-
}
-
void test_icu_I18N_chain(int argc, char **argv)
{
const char * en_str
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\"/>"
YAZ_CHECK(icu_chain_assign_cstr(chain, en_str, &status));
- while (icu_chain_next_token(chain, &status)){
+ while (icu_chain_next_token(chain, &status))
+ {
;
/* printf("%d '%s' '%s'\n",
- icu_chain_token_number(chain),
- icu_chain_token_norm(chain),
- icu_chain_token_display(chain)); */
+ icu_chain_token_number(chain),
+ icu_chain_token_norm(chain),
+ icu_chain_token_display(chain)); */
}
YAZ_CHECK_EQ(icu_chain_token_number(chain), 7);
YAZ_CHECK(icu_chain_assign_cstr(chain, "what is this?", &status));
- while (icu_chain_next_token(chain, &status)){
+ while (icu_chain_next_token(chain, &status))
+ {
;
/* printf("%d '%s' '%s'\n",
- icu_chain_token_number(chain),
- icu_chain_token_norm(chain),
- icu_chain_token_display(chain)); */
+ icu_chain_token_number(chain),
+ icu_chain_token_norm(chain),
+ icu_chain_token_display(chain)); */
}
chain, "O Romeo, Romeo! wherefore art thou\t Romeo?",
&status));
- while (icu_chain_next_token(chain, &status)){
+ while (icu_chain_next_token(chain, &status))
+ {
;
/* printf("%d '%s' '%s'\n",
- icu_chain_token_number(chain),
- icu_chain_token_norm(chain),
- icu_chain_token_display(chain)); */
-
+ icu_chain_token_number(chain),
+ icu_chain_token_norm(chain),
+ icu_chain_token_display(chain)); */
}
YAZ_CHECK(icu_chain_assign_cstr(chain, "what is this?", &status));
- while (icu_chain_next_token(chain, &status)){
- ;
- /* printf("%d '%s' '%s'\n",
- icu_chain_token_number(chain),
- icu_chain_token_norm(chain),
- icu_chain_token_display(chain)); */
+ while (icu_chain_next_token(chain, &status))
+ {
+ ;
+ /* printf("%d '%s' '%s'\n",
+ icu_chain_token_number(chain),
+ icu_chain_token_norm(chain),
+ icu_chain_token_display(chain)); */
}
/* we expect 'what' 'is' 'this', i.e. 3 tokens */
}
-
void test_chain_empty_token(void)
{
UErrorCode status = U_ZERO_ERROR;
chain, "a string with 15 tokenss and 8 displays",
&status));
- while (icu_chain_next_token(chain, &status)){
+ while (icu_chain_next_token(chain, &status))
+ {
;
/* printf("%d '%s' '%s'\n",
- icu_chain_token_number(chain),
- icu_chain_token_norm(chain),
- icu_chain_token_display(chain)); */
+ icu_chain_token_number(chain),
+ icu_chain_token_norm(chain),
+ icu_chain_token_display(chain)); */
}
YAZ_CHECK_EQ(icu_chain_token_number(chain), 15);
chain, src8,
&status));
- while (icu_chain_next_token(chain, &status)){
+ while (icu_chain_next_token(chain, &status))
+ {
;
/* printf("%d '%s' '%s'\n",
- icu_chain_token_number(chain),
- icu_chain_token_norm(chain),
- icu_chain_token_display(chain)); */
+ icu_chain_token_number(chain),
+ icu_chain_token_norm(chain),
+ icu_chain_token_display(chain)); */
}
YAZ_CHECK_EQ(icu_chain_token_number(chain), 1);
dest8 = (char *) icu_chain_token_norm(chain);
YAZ_CHECK_EQ(strcmp(src8, dest8), 0);
+ icu_chain_destroy(chain);
+}
+
+void test_icu_iter1(void)
+{
+ UErrorCode status = U_ZERO_ERROR;
+ struct icu_chain * chain = 0;
+ xmlNode *xml_node;
+ struct icu_iter *iter;
+ struct icu_buf_utf8 *token;
+
+ const char * xml_str = "<icu locale=\"en\">"
+ "<tokenize rule=\"w\"/>"
+ "<transform rule=\"[[:WhiteSpace:][:Punctuation:]] Remove\"/>"
+ "</icu>";
+
+ xmlDoc *doc = xmlParseMemory(xml_str, strlen(xml_str));
+ YAZ_CHECK(doc);
+ if (!doc)
+ return;
+ xml_node = xmlDocGetRootElement(doc);
+ YAZ_CHECK(xml_node);
+ if (!xml_node)
+ return ;
+ chain = icu_chain_xml_config(xml_node, 0, &status);
+
+ xmlFreeDoc(doc);
+ YAZ_CHECK(chain);
+
+ iter = icu_iter_create(chain, "a string with 15 tokens and 8 displays");
+ YAZ_CHECK(iter);
+ if (!iter)
+ return;
+#if 1
+ token = icu_buf_utf8_create(0);
+ while (icu_iter_next(iter, token))
+ {
+ printf("[%.*s]", (int) token->utf8_len, token->utf8);
+ }
+ icu_buf_utf8_destroy(token);
+#endif
+
+ icu_iter_destroy(iter);
icu_chain_destroy(chain);
}
-#endif /* YAZ_HAVE_ICU */
-/* DO NOT EDIT THIS FILE IF YOUR EDITOR DOES NOT SUPPORT UTF-8 */
+void test_icu_iter2(void)
+{
+ UErrorCode status = U_ZERO_ERROR;
+ struct icu_chain * chain = 0;
+ xmlNode *xml_node;
+ struct icu_iter *iter;
+ struct icu_buf_utf8 *token;
+
+ const char * xml_str = "<icu locale=\"en\">"
+ "<transform rule=\"[:Control:] Any-Remove\"/>"
+ "<tokenize rule=\"l\"/>"
+ "<tokenize rule=\"w\"/>"
+ "<transform rule=\"[[:WhiteSpace:][:Punctuation:]] Remove\"/>"
+ "<display/>"
+ "<casemap rule=\"l\"/>"
+ "</icu>";
+
+ xmlDoc *doc = xmlParseMemory(xml_str, strlen(xml_str));
+ YAZ_CHECK(doc);
+ if (!doc)
+ return;
+ xml_node = xmlDocGetRootElement(doc);
+ YAZ_CHECK(xml_node);
+ if (!xml_node)
+ return ;
+
+ chain = icu_chain_xml_config(xml_node, 0, &status);
+
+ xmlFreeDoc(doc);
+ YAZ_CHECK(chain);
+
+ iter = icu_iter_create(chain, "Adobe Acrobat Reader, 1991-1999.");
+ YAZ_CHECK(iter);
+ if (!iter)
+ return;
+ token = icu_buf_utf8_create(0);
+ while (icu_iter_next(iter, token))
+ {
+ printf("[%.*s]", (int) token->utf8_len, token->utf8);
+ }
+ icu_buf_utf8_destroy(token);
+
+ icu_iter_destroy(iter);
+ icu_chain_destroy(chain);
+}
+
+#endif /* YAZ_HAVE_ICU */
int main(int argc, char **argv)
{
-
YAZ_CHECK_INIT(argc, argv);
YAZ_CHECK_LOG();
test_icu_I18N_chain(argc, argv);
test_chain_empty_token();
test_chain_empty_chain();
+ test_icu_iter1();
+ test_icu_iter2();
+
test_bug_1140();
#else /* YAZ_HAVE_ICU */
YAZ_CHECK_TERM;
}
-
-/* DO NOT EDIT THIS FILE IF YOUR EDITOR DOES NOT SUPPORT UTF-8 */
-
-
-
/*
* Local variables:
* c-basic-offset: 4