X-Git-Url: https://git.sur5r.net/?a=blobdiff_plain;f=libraries%2Flibldap%2Futf-8.c;h=6b2ac969e1046d0f8be70daa30daa521fde189eb;hb=2b0819c4a9209784f762ec154ce4721038522a8a;hp=2c0cf19082c92cfc2835a1d5b1c3306f9efeabe5;hpb=42cc5e5333c36b1bd7ab250dac3a1a54ec3c439a;p=openldap

diff --git a/libraries/libldap/utf-8.c b/libraries/libldap/utf-8.c
index 2c0cf19082..6b2ac969e1 100644
--- a/libraries/libldap/utf-8.c
+++ b/libraries/libldap/utf-8.c
@@ -25,13 +25,13 @@
 #include <ac/string.h>
 #include <ac/time.h>
 
+#include "ldap_utf8.h"
+
 #include "ldap-int.h"
 #include "ldap_defaults.h"
 
-#undef ISASCII
-#define ISASCII(uc)	((uc) < 0x100)
-#undef UCS4_INVALID
-#define UCS4_INVALID	0x80000000U
+#undef LDAP_IS_ASCII
+#define LDAP_IS_ASCII(uc)	((uc) < 0x80)
 
 /*
  * Basic UTF-8 routines
@@ -39,16 +39,14 @@
 
 /*
  * return the number of bytes required to hold the
- * NULL-terminated UTF-8 string INCLUDING the
+ * NULL-terminated UTF-8 string NOT INCLUDING the
  * termination.
  */
 ber_len_t ldap_utf8_bytes( const char * p )
 {
-	ber_len_t bytes = 0;
-
-	if( p == NULL ) return bytes;
+	ber_len_t bytes;
 
-	while( p[bytes++] ) {
+	for( bytes=0; p[bytes]; bytes++ ) {
 		/* EMPTY */ ;
 	}
 
@@ -111,23 +109,23 @@ int ldap_utf8_charlen( const char * p )
 }
 
 /* conv UTF-8 to UCS-4, useful for comparisons */
-ber_int_t ldap_utf8_to_ucs4( const char * p )
+ldap_ucs4_t ldap_x_utf8_to_ucs4( const char * p )
 {
     const unsigned char *c = p;
-    ber_int_t ch;
+    ldap_ucs4_t ch;
 	int len, i;
 	static unsigned char mask[] = {
 		0, 0x7f, 0x1f, 0x0f, 0x07, 0x03, 0x01 };
 
 	len = LDAP_UTF8_CHARLEN(p);
 
-	if( len == 0 ) return UCS4_INVALID;
+	if( len == 0 ) return LDAP_UCS4_INVALID;
 
 	ch = c[0] & mask[len];
 
 	for(i=1; i < len; i++) {
 		if ((c[i] & 0xc0) != 0x80) {
-			return UCS4_INVALID;
+			return LDAP_UCS4_INVALID;
 		}
 
 		ch <<= 6;
@@ -138,7 +136,7 @@ ber_int_t ldap_utf8_to_ucs4( const char * p )
 }
 
 /* conv UCS-4 to UTF-8, not used */
-int ldap_ucs4_to_utf8( ber_int_t c, char *buf )
+int ldap_x_ucs4_to_utf8( ldap_ucs4_t c, char *buf )
 {
 	int len=0;
 	unsigned char* p = buf;
@@ -165,7 +163,7 @@ int ldap_ucs4_to_utf8( ber_int_t c, char *buf )
 		p[len++] = 0x80 | ( (c >> 6) & 0x3f );
 		p[len++] = 0x80 | ( c & 0x3f );
 
-	} else if( c < 0x400000 ) {
+	} else if( c < 0x4000000 ) {
 		p[len++] = 0xf8 | ( c >> 24 );
 		p[len++] = 0x80 | ( (c >> 18) & 0x3f );
 		p[len++] = 0x80 | ( (c >> 12) & 0x3f );
@@ -204,7 +202,7 @@ char* ldap_utf8_next( const char * p )
 	}
 
 	for( i=1; i<6; i++ ) {
-		if ( u[i] & 0xc0 != 0x80 ) {
+		if ( ( u[i] & 0xc0 ) != 0x80 ) {
 			return (char *) &p[i];
 		}
 	}
@@ -227,7 +225,7 @@ char* ldap_utf8_prev( const char * p )
 	const unsigned char *u = p;
 
 	for( i=-1; i>-6 ; i-- ) {
-		if ( u[i] & 0xc0 != 0x80 ) {
+		if ( ( u[i] & 0xc0 ) != 0x80 ) {
 			return (char *) &p[i];
 		}
 	}
@@ -257,7 +255,7 @@ int ldap_utf8_copy( char* dst, const char *src )
 	}
 
 	for( i=1; i<6; i++ ) {
-		if ( u[i] & 0xc0 != 0x80 ) {
+		if ( ( u[i] & 0xc0 ) != 0x80 ) {
 			return i; 
 		}
 		dst[i] = src[i];
@@ -268,20 +266,20 @@ int ldap_utf8_copy( char* dst, const char *src )
 
 /*
  * UTF-8 ctype routines
- * Only deals with characters < 0x100 (ie: US-ASCII)
+ * Only deals with characters < 0x80 (ie: US-ASCII)
  */
 
 int ldap_utf8_isascii( const char * p )
 {
 	unsigned c = * (const unsigned char *) p;
-	return ISASCII(c);
+	return LDAP_IS_ASCII(c);
 }
 
 int ldap_utf8_isdigit( const char * p )
 {
 	unsigned c = * (const unsigned char *) p;
 
-	if(!ISASCII(c)) return 0;
+	if(!LDAP_IS_ASCII(c)) return 0;
 
 	return c >= '0' && c <= '9';
 }
@@ -290,7 +288,7 @@ int ldap_utf8_isxdigit( const char * p )
 {
 	unsigned c = * (const unsigned char *) p;
 
-	if(!ISASCII(c)) return 0;
+	if(!LDAP_IS_ASCII(c)) return 0;
 
 	return ( c >= '0' && c <= '9' )
 		|| ( c >= 'A' && c <= 'F' )
@@ -301,7 +299,7 @@ int ldap_utf8_isspace( const char * p )
 {
 	unsigned c = * (const unsigned char *) p;
 
-	if(!ISASCII(c)) return 0;
+	if(!LDAP_IS_ASCII(c)) return 0;
 
 	switch(c) {
 	case ' ':
@@ -325,7 +323,7 @@ int ldap_utf8_isalpha( const char * p )
 {
 	unsigned c = * (const unsigned char *) p;
 
-	if(!ISASCII(c)) return 0;
+	if(!LDAP_IS_ASCII(c)) return 0;
 
 	return ( c >= 'A' && c <= 'Z' )
 		|| ( c >= 'a' && c <= 'z' );
@@ -335,7 +333,7 @@ int ldap_utf8_isalnum( const char * p )
 {
 	unsigned c = * (const unsigned char *) p;
 
-	if(!ISASCII(c)) return 0;
+	if(!LDAP_IS_ASCII(c)) return 0;
 
 	return ( c >= '0' && c <= '9' )
 		|| ( c >= 'A' && c <= 'Z' )
@@ -346,7 +344,7 @@ int ldap_utf8_islower( const char * p )
 {
 	unsigned c = * (const unsigned char *) p;
 
-	if(!ISASCII(c)) return 0;
+	if(!LDAP_IS_ASCII(c)) return 0;
 
 	return ( c >= 'a' && c <= 'z' );
 }
@@ -355,7 +353,7 @@ int ldap_utf8_isupper( const char * p )
 {
 	unsigned c = * (const unsigned char *) p;
 
-	if(!ISASCII(c)) return 0;
+	if(!LDAP_IS_ASCII(c)) return 0;
 
 	return ( c >= 'A' && c <= 'Z' );
 }
@@ -370,7 +368,7 @@ int ldap_utf8_isupper( const char * p )
 char * (ldap_utf8_strchr)( const char *str, const char *chr )
 {
 	for( ; *str != '\0'; LDAP_UTF8_INCR(str) ) {
-		if( ldap_utf8_to_ucs4( str ) == ldap_utf8_to_ucs4( chr ) ) {
+		if( ldap_x_utf8_to_ucs4( str ) == ldap_x_utf8_to_ucs4( chr ) ) {
 			return (char *) str;
 		} 
 	}
@@ -386,7 +384,7 @@ ber_len_t (ldap_utf8_strcspn)( const char *str, const char *set )
 
 	for( cstr = str; *cstr != '\0'; LDAP_UTF8_INCR(cstr) ) {
 		for( cset = set; *cset != '\0'; LDAP_UTF8_INCR(cset) ) {
-			if( ldap_utf8_to_ucs4( cstr ) == ldap_utf8_to_ucs4( cset ) ) {
+			if( ldap_x_utf8_to_ucs4( cstr ) == ldap_x_utf8_to_ucs4( cset ) ) {
 				return cstr - str;
 			} 
 		}
@@ -402,13 +400,12 @@ ber_len_t (ldap_utf8_strspn)( const char *str, const char *set )
 	const char *cset;
 
 	for( cstr = str; *cstr != '\0'; LDAP_UTF8_INCR(cstr) ) {
-
 		for( cset = set; ; LDAP_UTF8_INCR(cset) ) {
 			if( *cset == '\0' ) {
 				return cstr - str;
 			}
 
-			if( ldap_utf8_to_ucs4( cstr ) == ldap_utf8_to_ucs4( cset ) ) {
+			if( ldap_x_utf8_to_ucs4( cstr ) == ldap_x_utf8_to_ucs4( cset ) ) {
 				break;
 			} 
 		}
@@ -420,13 +417,11 @@ ber_len_t (ldap_utf8_strspn)( const char *str, const char *set )
 /* like strpbrk(), replaces strchr() as well */
 char *(ldap_utf8_strpbrk)( const char *str, const char *set )
 {
-	int len;
-
 	for( ; *str != '\0'; LDAP_UTF8_INCR(str) ) {
 		const char *cset;
 
 		for( cset = set; *cset != '\0'; LDAP_UTF8_INCR(cset) ) {
-			if( ldap_utf8_to_ucs4( str ) == ldap_utf8_to_ucs4( cset ) ) {
+			if( ldap_x_utf8_to_ucs4( str ) == ldap_x_utf8_to_ucs4( cset ) ) {
 				return (char *) str;
 			} 
 		}