hirokawa Sun Jul 13 03:34:28 2003 EDT
Modified files: (Branch: PHP_4_3)
/php-src/ext/mbstring mbfilter.c mbfilter.h mbstring.c
Log:
added strict detection mode in mb_detect_encoding to detect corrupted byte sequence.
Index: php-src/ext/mbstring/mbfilter.c
diff -u php-src/ext/mbstring/mbfilter.c:1.52.2.4
php-src/ext/mbstring/mbfilter.c:1.52.2.5
--- php-src/ext/mbstring/mbfilter.c:1.52.2.4 Fri May 30 09:20:17 2003
+++ php-src/ext/mbstring/mbfilter.c Sun Jul 13 03:34:27 2003
@@ -80,7 +80,7 @@
*
*/
-/* $Id: mbfilter.c,v 1.52.2.4 2003/05/30 13:20:17 iliaa Exp $ */
+/* $Id: mbfilter.c,v 1.52.2.5 2003/07/13 07:34:27 hirokawa Exp $ */
#ifdef HAVE_CONFIG_H
@@ -7473,7 +7473,7 @@
* identify encoding
*/
const mbfl_encoding *
-mbfl_identify_encoding(mbfl_string *string, enum mbfl_no_encoding *elist, int eliztsz
TSRMLS_DC)
+mbfl_identify_encoding(mbfl_string *string, enum mbfl_no_encoding *elist, int
eliztsz, int strict TSRMLS_DC)
{
int i, n, num, bad;
unsigned char *p;
@@ -7517,7 +7517,7 @@
}
i++;
}
- if ((num - 1) <= bad) {
+ if ((num - 1) <= bad && !strict) {
break;
}
p++;
@@ -7556,11 +7556,11 @@
}
const char*
-mbfl_identify_encoding_name(mbfl_string *string, enum mbfl_no_encoding *elist, int
eliztsz TSRMLS_DC)
+mbfl_identify_encoding_name(mbfl_string *string, enum mbfl_no_encoding *elist, int
eliztsz, int strict TSRMLS_DC)
{
const mbfl_encoding *encoding;
- encoding = mbfl_identify_encoding(string, elist, eliztsz TSRMLS_CC);
+ encoding = mbfl_identify_encoding(string, elist, eliztsz, strict TSRMLS_CC);
if (encoding != NULL &&
encoding->no_encoding > mbfl_no_encoding_charset_min &&
encoding->no_encoding < mbfl_no_encoding_charset_max) {
@@ -7575,7 +7575,7 @@
{
const mbfl_encoding *encoding;
- encoding = mbfl_identify_encoding(string, elist, eliztsz TSRMLS_CC);
+ encoding = mbfl_identify_encoding(string, elist, eliztsz, 0 TSRMLS_CC);
if (encoding != NULL &&
encoding->no_encoding > mbfl_no_encoding_charset_min &&
encoding->no_encoding < mbfl_no_encoding_charset_max) {
Index: php-src/ext/mbstring/mbfilter.h
diff -u php-src/ext/mbstring/mbfilter.h:1.17 php-src/ext/mbstring/mbfilter.h:1.17.2.1
--- php-src/ext/mbstring/mbfilter.h:1.17 Tue Nov 12 14:24:45 2002
+++ php-src/ext/mbstring/mbfilter.h Sun Jul 13 03:34:28 2003
@@ -86,7 +86,7 @@
*
*/
-/* $Id: mbfilter.h,v 1.17 2002/11/12 19:24:45 moriyoshi Exp $ */
+/* $Id: mbfilter.h,v 1.17.2.1 2003/07/13 07:34:28 hirokawa Exp $ */
#ifndef MBFL_MBFILTER_H
@@ -460,10 +460,10 @@
* identify encoding
*/
const mbfl_encoding *
-mbfl_identify_encoding(mbfl_string *string, enum mbfl_no_encoding *elist, int eliztsz
TSRMLS_DC);
+mbfl_identify_encoding(mbfl_string *string, enum mbfl_no_encoding *elist, int
eliztsz, int strict TSRMLS_DC);
const char *
-mbfl_identify_encoding_name(mbfl_string *string, enum mbfl_no_encoding *elist, int
eliztsz TSRMLS_DC);
+mbfl_identify_encoding_name(mbfl_string *string, enum mbfl_no_encoding *elist, int
eliztsz, int strict TSRMLS_DC);
const enum mbfl_no_encoding
mbfl_identify_encoding_no(mbfl_string *string, enum mbfl_no_encoding *elist, int
eliztsz TSRMLS_DC);
Index: php-src/ext/mbstring/mbstring.c
diff -u php-src/ext/mbstring/mbstring.c:1.142.2.19
php-src/ext/mbstring/mbstring.c:1.142.2.20
--- php-src/ext/mbstring/mbstring.c:1.142.2.19 Sat Jun 28 07:00:37 2003
+++ php-src/ext/mbstring/mbstring.c Sun Jul 13 03:34:28 2003
@@ -17,7 +17,7 @@
+----------------------------------------------------------------------+
*/
-/* $Id: mbstring.c,v 1.142.2.19 2003/06/28 11:00:37 hirokawa Exp $ */
+/* $Id: mbstring.c,v 1.142.2.20 2003/07/13 07:34:28 hirokawa Exp $ */
/*
* PHP4 Multibyte String module "mbstring"
@@ -2694,15 +2694,15 @@
}
/* }}} */
-/* {{{ proto string mb_detect_encoding(string str [, mixed encoding_list])
+/* {{{ proto string mb_detect_encoding(string str [, mixed encoding_list [, bool
strict]])
Encodings of the given string is returned (as a string) */
PHP_FUNCTION(mb_detect_encoding)
{
- pval **arg_str, **arg_list;
+ pval **arg_str, **arg_list, **arg_strict;
mbfl_string string;
const char *ret;
enum mbfl_no_encoding *elist;
- int size, *list;
+ int size, *list, strict = 0;
if (ZEND_NUM_ARGS() == 1) {
if (zend_get_parameters_ex(1, &arg_str) == FAILURE) {
@@ -2712,6 +2712,10 @@
if (zend_get_parameters_ex(2, &arg_str, &arg_list) == FAILURE) {
WRONG_PARAM_COUNT;
}
+ } else if (ZEND_NUM_ARGS() == 3) {
+ if (zend_get_parameters_ex(3, &arg_str, &arg_list, &arg_strict) ==
FAILURE) {
+ WRONG_PARAM_COUNT;
+ }
} else {
WRONG_PARAM_COUNT;
}
@@ -2719,7 +2723,7 @@
/* make encoding list */
list = NULL;
size = 0;
- if (ZEND_NUM_ARGS() >= 2) {
+ if (ZEND_NUM_ARGS() >= 2 && Z_STRVAL_PP(arg_list)) {
switch (Z_TYPE_PP(arg_list)) {
case IS_ARRAY:
if (!php_mb_parse_encoding_array(*arg_list, &list, &size, 0)) {
@@ -2744,6 +2748,11 @@
}
}
+ if (ZEND_NUM_ARGS() == 3) {
+ convert_to_long_ex(arg_strict);
+ strict = Z_LVAL_PP(arg_strict);
+ }
+
if (size > 0 && list != NULL) {
elist = list;
} else {
@@ -2756,7 +2765,7 @@
string.no_language = MBSTRG(current_language);
string.val = (unsigned char *)Z_STRVAL_PP(arg_str);
string.len = Z_STRLEN_PP(arg_str);
- ret = mbfl_identify_encoding_name(&string, elist, size TSRMLS_CC);
+ ret = mbfl_identify_encoding_name(&string, elist, size, strict TSRMLS_CC);
if (list != NULL) {
efree((void *)list);
}
--
PHP CVS Mailing List (http://www.php.net/)
To unsubscribe, visit: http://www.php.net/unsub.php