[PHP-CVS] com php-src: fix for bug#18556 - use simple tolower() function for internal things: Zend/zend_operators.c ext/standard/string.c

2012-07-14 Thread Stanislav Malyshev
Commit:582514d4c7b216dbdc7a8429962cf3e5776206f0
Author:Stanislav Malyshev s...@php.net Tue, 10 Jul 2012 18:12:13 
-0700
Parents:   d2beb0fc050baa752a93ae07585a4488e3dcf053
Branches:  master

Link:   
http://git.php.net/?p=php-src.git;a=commitdiff;h=582514d4c7b216dbdc7a8429962cf3e5776206f0

Log:
fix for bug#18556 - use simple tolower() function for internal things

Bugs:
https://bugs.php.net/18556

Changed paths:
  M  Zend/zend_operators.c
  M  ext/standard/string.c


Diff:
diff --git a/Zend/zend_operators.c b/Zend/zend_operators.c
index f968625..8805eb2 100644
--- a/Zend/zend_operators.c
+++ b/Zend/zend_operators.c
@@ -42,6 +42,43 @@ static _locale_t current_locale = NULL;
 
 #define TYPE_PAIR(t1,t2) (((t1)  4) | (t2))
 
+static unsigned char tolower_map[256] = {
+0x00,0x01,0x02,0x03,0x04,0x05,0x06,0x07,0x08,0x09,0x0a,0x0b,0x0c,0x0d,0x0e,0x0f,
+0x10,0x11,0x12,0x13,0x14,0x15,0x16,0x17,0x18,0x19,0x1a,0x1b,0x1c,0x1d,0x1e,0x1f,
+0x20,0x21,0x22,0x23,0x24,0x25,0x26,0x27,0x28,0x29,0x2a,0x2b,0x2c,0x2d,0x2e,0x2f,
+0x30,0x31,0x32,0x33,0x34,0x35,0x36,0x37,0x38,0x39,0x3a,0x3b,0x3c,0x3d,0x3e,0x3f,
+0x40,0x61,0x62,0x63,0x64,0x65,0x66,0x67,0x68,0x69,0x6a,0x6b,0x6c,0x6d,0x6e,0x6f,
+0x70,0x71,0x72,0x73,0x74,0x75,0x76,0x77,0x78,0x79,0x7a,0x5b,0x5c,0x5d,0x5e,0x5f,
+0x60,0x61,0x62,0x63,0x64,0x65,0x66,0x67,0x68,0x69,0x6a,0x6b,0x6c,0x6d,0x6e,0x6f,
+0x70,0x71,0x72,0x73,0x74,0x75,0x76,0x77,0x78,0x79,0x7a,0x7b,0x7c,0x7d,0x7e,0x7f,
+0x80,0x81,0x82,0x83,0x84,0x85,0x86,0x87,0x88,0x89,0x8a,0x8b,0x8c,0x8d,0x8e,0x8f,
+0x90,0x91,0x92,0x93,0x94,0x95,0x96,0x97,0x98,0x99,0x9a,0x9b,0x9c,0x9d,0x9e,0x9f,
+0xa0,0xa1,0xa2,0xa3,0xa4,0xa5,0xa6,0xa7,0xa8,0xa9,0xaa,0xab,0xac,0xad,0xae,0xaf,
+0xb0,0xb1,0xb2,0xb3,0xb4,0xb5,0xb6,0xb7,0xb8,0xb9,0xba,0xbb,0xbc,0xbd,0xbe,0xbf,
+0xc0,0xc1,0xc2,0xc3,0xc4,0xc5,0xc6,0xc7,0xc8,0xc9,0xca,0xcb,0xcc,0xcd,0xce,0xcf,
+0xd0,0xd1,0xd2,0xd3,0xd4,0xd5,0xd6,0xd7,0xd8,0xd9,0xda,0xdb,0xdc,0xdd,0xde,0xdf,
+0xe0,0xe1,0xe2,0xe3,0xe4,0xe5,0xe6,0xe7,0xe8,0xe9,0xea,0xeb,0xec,0xed,0xee,0xef,
+0xf0,0xf1,0xf2,0xf3,0xf4,0xf5,0xf6,0xf7,0xf8,0xf9,0xfa,0xfb,0xfc,0xfd,0xfe,0xff
+};
+
+#define zend_tolower_ascii(c) (tolower_map[(c)])
+
+/**
+ * Functions using locale lowercase:
+   zend_binary_strncasecmp_l
+   zend_binary_strcasecmp_l
+   zend_binary_zval_strcasecmp
+   zend_binary_zval_strncasecmp
+   string_compare_function_ex
+   string_case_compare_function
+ * Functions using ascii lowercase:
+   zend_str_tolower_copy
+   zend_str_tolower_dup
+   zend_str_tolower
+   zend_binary_strcasecmp
+   zend_binary_strncasecmp
+ */
+
 ZEND_API int zend_atoi(const char *str, int str_len) /* {{{ */
 {
int retval;
@@ -1908,7 +1945,7 @@ ZEND_API char *zend_str_tolower_copy(char *dest, const 
char *source, unsigned in
register unsigned char *end = str + length;
 
while (str  end) {
-   *result++ = zend_tolower((int)*str++);
+   *result++ = zend_tolower_ascii((int)*str++);
}
*result = '\0';
 
@@ -1928,7 +1965,7 @@ ZEND_API void zend_str_tolower(char *str, unsigned int 
length) /* {{{ */
register unsigned char *end = p + length;
 
while (p  end) {
-   *p = zend_tolower((int)*p);
+   *p = zend_tolower_ascii((int)*p);
p++;
}
 }
@@ -1977,6 +2014,49 @@ ZEND_API int zend_binary_strcasecmp(const char *s1, uint 
len1, const char *s2, u
 
len = MIN(len1, len2);
while (len--) {
+   c1 = zend_tolower_ascii((int)*(unsigned char *)s1++);
+   c2 = zend_tolower_ascii((int)*(unsigned char *)s2++);
+   if (c1 != c2) {
+   return c1 - c2;
+   }
+   }
+
+   return len1 - len2;
+}
+/* }}} */
+
+ZEND_API int zend_binary_strncasecmp(const char *s1, uint len1, const char 
*s2, uint len2, uint length) /* {{{ */
+{
+   int len;
+   int c1, c2;
+
+   if (s1 == s2) {
+   return 0;
+   }
+   len = MIN(length, MIN(len1, len2));
+   while (len--) {
+   c1 = zend_tolower_ascii((int)*(unsigned char *)s1++);
+   c2 = zend_tolower_ascii((int)*(unsigned char *)s2++);
+   if (c1 != c2) {
+   return c1 - c2;
+   }
+   }
+
+   return MIN(length, len1) - MIN(length, len2);
+}
+/* }}} */
+
+ZEND_API int zend_binary_strcasecmp_l(const char *s1, uint len1, const char 
*s2, uint len2) /* {{{ */
+{
+   int len;
+   int c1, c2;
+
+   if (s1 == s2) {
+   return 0;
+   }
+
+   len = MIN(len1, len2);
+   while (len--) {
c1 = zend_tolower((int)*(unsigned char *)s1++);
c2 = zend_tolower((int)*(unsigned char *)s2++);
if (c1 != c2) {
@@ -1988,7 +2068,7 @@ ZEND_API int zend_binary_strcasecmp(const char *s1, uint 
len1, const char *s2, u
 }
 

Re: [PHP-CVS] com php-src: fix for bug#18556 - use simple tolower() function for internal things: Zend/zend_operators.c ext/standard/string.c

2012-07-14 Thread Nuno Lopes

Hi,

Just a few minor nitpicks:


+static unsigned char tolower_map[256] = {


This should be const.



+#define zend_tolower_ascii(c) (tolower_map[(c)])


I suggest casting to unsigned char to prevent overflows and negative chars 
problems (128-255):

#define zend_tolower_ascii(c) (tolower_map[(unsigned char)(c)])



+ *result++ = zend_tolower_ascii((int)*str++);


The cast to int is not necessary. Same comment applies for most other calls.

And thanks for fixing this ancient bug :)

Nuno 



--
PHP CVS Mailing List (http://www.php.net/)
To unsubscribe, visit: http://www.php.net/unsub.php