moriyoshi Sat Oct 25 23:41:19 2003 EDT
Modified files: (Branch: PHP_4_3)
/php-src/ext/mbstring mbstring.c mbstring.h
/php-src/ext/mbstring/tests mb_convert_encoding.phpt
mb_convert_variables.phpt
mb_detect_encoding.phpt
mb_detect_order.phpt
Log:
Backport some patch already in HEAD to assure backwards compatibility
Index: php-src/ext/mbstring/mbstring.c
diff -u php-src/ext/mbstring/mbstring.c:1.142.2.30
php-src/ext/mbstring/mbstring.c:1.142.2.31
--- php-src/ext/mbstring/mbstring.c:1.142.2.30 Sat Oct 25 07:58:39 2003
+++ php-src/ext/mbstring/mbstring.c Sat Oct 25 23:41:18 2003
@@ -17,7 +17,7 @@
+----------------------------------------------------------------------+
*/
-/* $Id: mbstring.c,v 1.142.2.30 2003/10/25 11:58:39 hirokawa Exp $ */
+/* $Id: mbstring.c,v 1.142.2.31 2003/10/26 03:41:18 moriyoshi Exp $ */
/*
* PHP4 Multibyte String module "mbstring"
@@ -84,62 +84,65 @@
MUTEX_T mbregex_locale_mutex = NULL;
#endif
-/* {{{ php_mbstr_default_identify_list[] */
-#if defined(HAVE_MBSTR_JA)
-static const enum mbfl_no_encoding php_mbstr_default_identify_list[] = {
+/* {{{ php_mb_default_identify_list */
+typedef struct _php_mb_nls_ident_list {
+ enum mbfl_no_language lang;
+ enum mbfl_no_encoding* list;
+ int list_size;
+} php_mb_nls_ident_list;
+
+static const enum mbfl_no_encoding php_mb_default_identify_list_ja[] = {
mbfl_no_encoding_ascii,
mbfl_no_encoding_jis,
mbfl_no_encoding_utf8,
mbfl_no_encoding_euc_jp,
mbfl_no_encoding_sjis
};
-#endif
-#if defined(HAVE_MBSTR_CN) & !defined(HAVE_MBSTR_JA)
-static const enum mbfl_no_encoding php_mbstr_default_identify_list[] = {
+static const enum mbfl_no_encoding php_mb_default_identify_list_cn[] = {
mbfl_no_encoding_ascii,
mbfl_no_encoding_utf8,
mbfl_no_encoding_euc_cn,
mbfl_no_encoding_cp936
};
-#endif
-#if defined(HAVE_MBSTR_TW) & !defined(HAVE_MBSTR_CN) & !defined(HAVE_MBSTR_JA)
-static const enum mbfl_no_encoding php_mbstr_default_identify_list[] = {
+static const enum mbfl_no_encoding php_mb_default_identify_list_tw_hk[] = {
mbfl_no_encoding_ascii,
mbfl_no_encoding_utf8,
mbfl_no_encoding_euc_tw,
mbfl_no_encoding_big5
};
-#endif
-#if defined(HAVE_MBSTR_KR) & !defined(HAVE_MBSTR_TW) & !defined(HAVE_MBSTR_CN) &
!defined(HAVE_MBSTR_JA)
-static const enum mbfl_no_encoding php_mbstr_default_identify_list[] = {
+static const enum mbfl_no_encoding php_mb_default_identify_list_kr[] = {
mbfl_no_encoding_ascii,
mbfl_no_encoding_utf8,
mbfl_no_encoding_euc_kr,
mbfl_no_encoding_uhc
};
-#endif
-#if defined(HAVE_MBSTR_RU) & !defined(HAVE_MBSTR_KR) & !defined(HAVE_MBSTR_TW) &
!defined(HAVE_MBSTR_CN) & !defined(HAVE_MBSTR_JA)
-static const enum mbfl_no_encoding php_mbstr_default_identify_list[] = {
+static const enum mbfl_no_encoding php_mb_default_identify_list_ru[] = {
mbfl_no_encoding_ascii,
mbfl_no_encoding_utf8,
mbfl_no_encoding_koi8r,
mbfl_no_encoding_cp1251,
mbfl_no_encoding_cp866
};
-#endif
-#if !defined(HAVE_MBSTR_RU) & !defined(HAVE_MBSTR_KR) & !defined(HAVE_MBSTR_TW) &
!defined(HAVE_MBSTR_CN) & !defined(HAVE_MBSTR_JA)
-static const enum mbfl_no_encoding php_mbstr_default_identify_list[] = {
+static const enum mbfl_no_encoding php_mb_default_identify_list_neut[] = {
mbfl_no_encoding_ascii,
mbfl_no_encoding_utf8
};
-#endif
-static const int php_mbstr_default_identify_list_size =
sizeof(php_mbstr_default_identify_list)/sizeof(enum mbfl_no_encoding);
+
+php_mb_nls_ident_list php_mb_default_identify_list[] = {
+ { mbfl_no_language_japanese, php_mb_default_identify_list_ja,
sizeof(php_mb_default_identify_list_ja) / sizeof(php_mb_default_identify_list_ja[0]) },
+ { mbfl_no_language_korean, php_mb_default_identify_list_kr,
sizeof(php_mb_default_identify_list_kr) / sizeof(php_mb_default_identify_list_kr[0]) },
+ { mbfl_no_language_traditional_chinese, php_mb_default_identify_list_tw_hk,
sizeof(php_mb_default_identify_list_tw_hk) /
sizeof(php_mb_default_identify_list_tw_hk[0]) },
+ { mbfl_no_language_simplified_chinese, php_mb_default_identify_list_cn,
sizeof(php_mb_default_identify_list_cn) / sizeof(php_mb_default_identify_list_cn[0]) },
+ { mbfl_no_language_russian, php_mb_default_identify_list_ru,
sizeof(php_mb_default_identify_list_ru) / sizeof(php_mb_default_identify_list_ru[0]) },
+ { mbfl_no_language_neutral, php_mb_default_identify_list_neut,
sizeof(php_mb_default_identify_list_neut) /
sizeof(php_mb_default_identify_list_neut[0]) }
+};
+
/* }}} */
static const unsigned char third_and_rest_force_ref[] = { 3, BYREF_NONE, BYREF_NONE,
BYREF_FORCE_REST };
@@ -358,12 +361,19 @@
* Even if any illegal encoding is detected the result may contain a list
* of parsed encodings.
*/
+
+/* {{{ static int php_mb_parse_encoding_list()
+ * Return 0 if input contains any illegal encoding, otherwise 1.
+ * Even if any illegal encoding is detected the result may contain a list
+ * of parsed encodings.
+ */
static int
-php_mb_parse_encoding_list(const char *value, int value_length, int **return_list,
int *return_size, int persistent TSRMLS_DC)
+php_mb_parse_encoding_list(const char *value, int value_length, enum mbfl_no_encoding
**return_list, int *return_size, int persistent TSRMLS_DC)
{
- int n, l, size, bauto, *src, *list, *entry, ret = 1;
+ int n, l, size, bauto, ret = 1;
char *p, *p1, *p2, *endp, *tmpstr;
enum mbfl_no_encoding no_encoding;
+ enum mbfl_no_encoding *src, *entry, *list;
list = NULL;
if (value == NULL || value_length <= 0) {
@@ -375,6 +385,12 @@
}
return 0;
} else {
+ enum mbfl_no_encoding *identify_list;
+ int identify_list_size;
+
+ identify_list = MBSTRG(default_detect_order_list);
+ identify_list_size = MBSTRG(default_detect_order_list_size);
+
/* copy the value string for work */
if (value[0]=='"' && value[value_length-1]=='"' && value_length>2) {
tmpstr = (char *)estrndup(value+1, value_length-2);
@@ -393,7 +409,7 @@
p1 = p2 + 1;
n++;
}
- size = n + php_mbstr_default_identify_list_size;
+ size = n + identify_list_size;
/* make list */
list = (int *)pecalloc(size, sizeof(int), persistent);
if (list != NULL) {
@@ -417,23 +433,25 @@
p--;
}
/* convert to the encoding number and check encoding */
- no_encoding = mbfl_name2no_encoding(p1);
- if (no_encoding == mbfl_no_encoding_auto) {
+ if (strcasecmp(p1, "auto") == 0) {
if (!bauto) {
bauto = 1;
- l =
php_mbstr_default_identify_list_size;
- src =
(int*)php_mbstr_default_identify_list;
+ l = identify_list_size;
+ src = identify_list;
while (l > 0) {
*entry++ = *src++;
l--;
n++;
}
}
- } else if (no_encoding != mbfl_no_encoding_invalid) {
- *entry++ = no_encoding;
- n++;
} else {
- ret = 0;
+ no_encoding = mbfl_name2no_encoding(p1);
+ if (no_encoding != mbfl_no_encoding_invalid) {
+ *entry++ = no_encoding;
+ n++;
+ } else {
+ ret = 0;
+ }
}
p1 = p2 + 1;
} while (n < size && p2 != NULL);
@@ -481,19 +499,26 @@
* of parsed encodings.
*/
static int
-php_mb_parse_encoding_array(zval *array, int **return_list, int *return_size, int
persistent)
+php_mb_parse_encoding_array(zval *array, enum mbfl_no_encoding **return_list, int
*return_size, int persistent TSRMLS_DC)
{
zval **hash_entry;
HashTable *target_hash;
- int i, n, l, size, bauto, *list, *entry, *src, ret = 1;
+ int i, n, l, size, bauto,ret = 1;
enum mbfl_no_encoding no_encoding;
+ enum mbfl_no_encoding *src, *list, *entry;
list = NULL;
if (Z_TYPE_P(array) == IS_ARRAY) {
+ enum mbfl_no_encoding *identify_list;
+ int identify_list_size;
+
+ identify_list = MBSTRG(default_detect_order_list);
+ identify_list_size = MBSTRG(default_detect_order_list_size);
+
target_hash = Z_ARRVAL_P(array);
zend_hash_internal_pointer_reset(target_hash);
i = zend_hash_num_elements(target_hash);
- size = i + php_mbstr_default_identify_list_size;
+ size = i + identify_list_size;
list = (int *)pecalloc(size, sizeof(int), persistent);
if (list != NULL) {
entry = list;
@@ -504,23 +529,25 @@
break;
}
convert_to_string_ex(hash_entry);
- no_encoding =
mbfl_name2no_encoding(Z_STRVAL_PP(hash_entry));
- if (no_encoding == mbfl_no_encoding_auto) {
+ if (strcasecmp(Z_STRVAL_PP(hash_entry), "auto") == 0) {
if (!bauto) {
bauto = 1;
- l =
php_mbstr_default_identify_list_size;
- src =
(int*)php_mbstr_default_identify_list;
+ l = identify_list_size;
+ src = identify_list;
while (l > 0) {
*entry++ = *src++;
l--;
n++;
}
}
- } else if (no_encoding != mbfl_no_encoding_invalid) {
- *entry++ = no_encoding;
- n++;
} else {
- ret = 0;;
+ no_encoding =
mbfl_name2no_encoding(Z_STRVAL_PP(hash_entry));
+ if (no_encoding != mbfl_no_encoding_invalid) {
+ *entry++ = no_encoding;
+ n++;
+ } else {
+ ret = 0;
+ }
}
zend_hash_move_forward(target_hash);
i--;
@@ -556,6 +583,25 @@
}
/* }}} */
+/* {{{ php_mb_nls_get_default_detect_order_list */
+static int php_mb_nls_get_default_detect_order_list(enum mbfl_no_language lang, enum
mbfl_no_encoding **plist, int* plist_size)
+{
+ size_t i;
+
+ *plist = (enum mbfl_no_encoding *) php_mb_default_identify_list_neut;
+ *plist_size = sizeof(php_mb_default_identify_list_neut) /
sizeof(php_mb_default_identify_list_neut[0]);
+
+ for (i = 0; i < sizeof(php_mb_default_identify_list) /
sizeof(php_mb_default_identify_list[0]); i++) {
+ if (php_mb_default_identify_list[i].lang == lang) {
+ *plist = php_mb_default_identify_list[i].list;
+ *plist_size = php_mb_default_identify_list[i].list_size;
+ return 1;
+ }
+ }
+ return 0;
+}
+/* }}} */
+
#if HAVE_MBREGEX
/* {{{ static void php_mbregex_free_cache() */
static void
@@ -576,6 +622,7 @@
return FAILURE;
}
MBSTRG(language) = no_language;
+ php_mb_nls_get_default_detect_order_list(no_language,
&MBSTRG(default_detect_order_list), &MBSTRG(default_detect_order_list_size));
return SUCCESS;
}
/* }}} */
@@ -783,6 +830,8 @@
MBSTRG(detect_order_list_size) = 0;
MBSTRG(current_detect_order_list) = NULL;
MBSTRG(current_detect_order_list_size) = 0;
+ MBSTRG(default_detect_order_list) = (enum mbfl_no_encoding *)
php_mb_default_identify_list_neut;
+ MBSTRG(default_detect_order_list_size) =
sizeof(php_mb_default_identify_list_neut) /
sizeof(php_mb_default_identify_list_neut[0]);
MBSTRG(filter_illegal_mode) = MBFL_OUTPUTFILTER_ILLEGAL_MODE_CHAR;
MBSTRG(filter_illegal_substchar) = 0x3f; /* '?' */
MBSTRG(current_filter_illegal_mode) = MBFL_OUTPUTFILTER_ILLEGAL_MODE_CHAR;
@@ -950,17 +999,15 @@
n = MBSTRG(detect_order_list_size);
}
if (n <= 0) {
- list = (int*)php_mbstr_default_identify_list;
- n = php_mbstr_default_identify_list_size;
+ list = MBSTRG(default_detect_order_list);
+ n = MBSTRG(default_detect_order_list_size);
}
entry = (int *)safe_emalloc(n, sizeof(int), 0);
- if (entry != NULL) {
- MBSTRG(current_detect_order_list) = entry;
- MBSTRG(current_detect_order_list_size) = n;
- while (n > 0) {
- *entry++ = *list++;
- n--;
- }
+ MBSTRG(current_detect_order_list) = entry;
+ MBSTRG(current_detect_order_list_size) = n;
+ while (n > 0) {
+ *entry++ = *list++;
+ n--;
}
/* override original function. */
@@ -1120,6 +1167,7 @@
php_error_docref(NULL TSRMLS_CC, E_WARNING, "Unknown language
\"%s\"", Z_STRVAL_PP(arg1));
RETURN_FALSE;
} else {
+ php_mb_nls_get_default_detect_order_list(no_language,
&MBSTRG(default_detect_order_list), &MBSTRG(default_detect_order_list_size));
MBSTRG(current_language) = no_language;
RETURN_TRUE;
}
@@ -3786,16 +3834,16 @@
elist = MBSTRG(current_detect_order_list);
size = MBSTRG(current_detect_order_list_size);
if (size <= 0){
- elist = (int*)php_mbstr_default_identify_list;
- size = php_mbstr_default_identify_list_size;
+ elist = MBSTRG(default_detect_order_list);
+ size = MBSTRG(default_detect_order_list_size);
}
}
} else {
elist = MBSTRG(current_detect_order_list);
size = MBSTRG(current_detect_order_list_size);
if (size <= 0){
- elist = (int*)php_mbstr_default_identify_list;
- size = php_mbstr_default_identify_list_size;
+ elist = MBSTRG(default_detect_order_list);
+ size = MBSTRG(default_detect_order_list_size);
}
}
Index: php-src/ext/mbstring/mbstring.h
diff -u php-src/ext/mbstring/mbstring.h:1.40.2.9
php-src/ext/mbstring/mbstring.h:1.40.2.10
--- php-src/ext/mbstring/mbstring.h:1.40.2.9 Sat Oct 25 07:58:39 2003
+++ php-src/ext/mbstring/mbstring.h Sat Oct 25 23:41:18 2003
@@ -16,7 +16,7 @@
+----------------------------------------------------------------------+
*/
-/* $Id: mbstring.h,v 1.40.2.9 2003/10/25 11:58:39 hirokawa Exp $ */
+/* $Id: mbstring.h,v 1.40.2.10 2003/10/26 03:41:18 moriyoshi Exp $ */
/*
* PHP4 Multibyte String module "mbstring" (currently only for Japanese)
@@ -168,6 +168,8 @@
int detect_order_list_size;
enum mbfl_no_encoding *current_detect_order_list;
int current_detect_order_list_size;
+ enum mbfl_no_encoding *default_detect_order_list;
+ int default_detect_order_list_size;
int filter_illegal_mode;
int filter_illegal_substchar;
int current_filter_illegal_mode;
Index: php-src/ext/mbstring/tests/mb_convert_encoding.phpt
diff -u php-src/ext/mbstring/tests/mb_convert_encoding.phpt:1.3
php-src/ext/mbstring/tests/mb_convert_encoding.phpt:1.3.2.1
--- php-src/ext/mbstring/tests/mb_convert_encoding.phpt:1.3 Sun Nov 3 03:37:59
2002
+++ php-src/ext/mbstring/tests/mb_convert_encoding.phpt Sat Oct 25 23:41:19 2003
@@ -4,6 +4,7 @@
<?php extension_loaded('mbstring') or die('skip mbstring not available'); ?>
--INI--
output_handler=
+mbstring.language=Japanese
--FILE--
<?php
// TODO: Add more tests
Index: php-src/ext/mbstring/tests/mb_convert_variables.phpt
diff -u php-src/ext/mbstring/tests/mb_convert_variables.phpt:1.3
php-src/ext/mbstring/tests/mb_convert_variables.phpt:1.3.2.1
--- php-src/ext/mbstring/tests/mb_convert_variables.phpt:1.3 Sun Nov 3 03:37:59
2002
+++ php-src/ext/mbstring/tests/mb_convert_variables.phpt Sat Oct 25 23:41:19
2003
@@ -4,6 +4,7 @@
<?php extension_loaded('mbstring') or die('skip mbstring not available'); ?>
--INI--
output_handler=
+mbstring.language=Japanese
--FILE--
<?php
// TODO: Add more tests
Index: php-src/ext/mbstring/tests/mb_detect_encoding.phpt
diff -u php-src/ext/mbstring/tests/mb_detect_encoding.phpt:1.2
php-src/ext/mbstring/tests/mb_detect_encoding.phpt:1.2.2.1
--- php-src/ext/mbstring/tests/mb_detect_encoding.phpt:1.2 Wed Oct 30 03:06:52
2002
+++ php-src/ext/mbstring/tests/mb_detect_encoding.phpt Sat Oct 25 23:41:19 2003
@@ -2,6 +2,8 @@
mb_detect_encoding()
--SKIPIF--
<?php extension_loaded('mbstring') or die('skip mbstring not available'); ?>
+--INI--
+mbstring.language=Japanese
--FILE--
<?php
// TODO: Add more tests
Index: php-src/ext/mbstring/tests/mb_detect_order.phpt
diff -u php-src/ext/mbstring/tests/mb_detect_order.phpt:1.2
php-src/ext/mbstring/tests/mb_detect_order.phpt:1.2.2.1
--- php-src/ext/mbstring/tests/mb_detect_order.phpt:1.2 Wed Oct 30 03:06:52 2002
+++ php-src/ext/mbstring/tests/mb_detect_order.phpt Sat Oct 25 23:41:19 2003
@@ -2,6 +2,8 @@
mb_detect_order()
--SKIPIF--
<?php extension_loaded('mbstring') or die('skip mbstring not available'); ?>
+--INI--
+mbstring.language=Japanese
--FILE--
<?php
//$debug = true;
--
PHP CVS Mailing List (http://www.php.net/)
To unsubscribe, visit: http://www.php.net/unsub.php