#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) < 0x80)
-
/*
* Basic UTF-8 routines
*/
for( ; *p ; LDAP_UTF8_INCR(p) ) {
chars++;
- };
+ }
return chars;
}
*
* This function should use a table lookup.
*/
+const char ldap_utf8_lentab[] = {
+ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+ 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
+ 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
+ 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
+ 4, 4, 4, 4, 4, 4, 4, 4, 5, 5, 5, 5, 6, 6, 0, 0 };
+
int ldap_utf8_charlen( const char * p )
{
- unsigned c = * (const unsigned char *) p;
-
- if ((c & 0xfe ) == 0xfc) {
- return 6;
- }
-
- if ((c & 0xfc ) == 0xf8) {
- return 5;
- }
-
- if ((c & 0xf8 ) == 0xf0) {
- return 4;
- }
-
- if ((c & 0xf0 ) == 0xe0) {
- return 3;
- }
-
- if ((c & 0xe0 ) == 0xc0) {
- return 2;
- }
-
- if ((c & 0x80 ) == 0x80) {
- /* INVALID */
- return 0;
- }
+ if (!(*p & 0x80))
+ return 1;
- return 1;
+ return ldap_utf8_lentab[*(unsigned char *)p ^ 0x80];
}
/* conv UTF-8 to UCS-4, useful for comparisons */
-ldap_ucs4_t ldap_utf8_to_ucs4( const char * p )
+ldap_ucs4_t ldap_x_utf8_to_ucs4( const char * p )
{
const unsigned char *c = p;
ldap_ucs4_t ch;
}
/* conv UCS-4 to UTF-8, not used */
-int ldap_ucs4_to_utf8( ldap_ucs4_t c, char *buf )
+int ldap_x_ucs4_to_utf8( ldap_ucs4_t c, char *buf )
{
int len=0;
unsigned char* p = 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 );
return i;
}
+#ifndef UTF8_ALPHA_CTYPE
/*
* UTF-8 ctype routines
* 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_ASCII(c);
}
int ldap_utf8_isdigit( const char * p )
{
unsigned c = * (const unsigned char *) p;
- if(!ISASCII(c)) return 0;
+ if(!LDAP_ASCII(c)) return 0;
- return c >= '0' && c <= '9';
+ return LDAP_DIGIT( c );
}
int ldap_utf8_isxdigit( const char * p )
{
unsigned c = * (const unsigned char *) p;
- if(!ISASCII(c)) return 0;
+ if(!LDAP_ASCII(c)) return 0;
- return ( c >= '0' && c <= '9' )
- || ( c >= 'A' && c <= 'F' )
- || ( c >= 'a' && c <= 'f' );
+ return LDAP_HEX(c);
}
int ldap_utf8_isspace( const char * p )
{
unsigned c = * (const unsigned char *) p;
- if(!ISASCII(c)) return 0;
+ if(!LDAP_ASCII(c)) return 0;
switch(c) {
case ' ':
return 0;
}
-#ifndef UTF8_ALPHA_CTYPE
/*
* These are not needed by the C SDK and are
* not "good enough" for general use.
{
unsigned c = * (const unsigned char *) p;
- if(!ISASCII(c)) return 0;
+ if(!LDAP_ASCII(c)) return 0;
- return ( c >= 'A' && c <= 'Z' )
- || ( c >= 'a' && c <= 'z' );
+ return LDAP_ALPHA(c);
}
int ldap_utf8_isalnum( const char * p )
{
unsigned c = * (const unsigned char *) p;
- if(!ISASCII(c)) return 0;
+ if(!LDAP_ASCII(c)) return 0;
- return ( c >= '0' && c <= '9' )
- || ( c >= 'A' && c <= 'Z' )
- || ( c >= 'a' && c <= 'z' );
+ return LDAP_ALNUM(c);
}
int ldap_utf8_islower( const char * p )
{
unsigned c = * (const unsigned char *) p;
- if(!ISASCII(c)) return 0;
+ if(!LDAP_ASCII(c)) return 0;
- return ( c >= 'a' && c <= 'z' );
+ return LDAP_LOWER(c);
}
int ldap_utf8_isupper( const char * p )
{
unsigned c = * (const unsigned char *) p;
- if(!ISASCII(c)) return 0;
+ if(!LDAP_ASCII(c)) return 0;
- return ( c >= 'A' && c <= 'Z' );
+ return LDAP_UPPER(c);
}
#endif
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;
}
}
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;
}
}
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;
}
}
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;
}
}