Fixed some string functions to make them compatible with UTF-8 charset

v2.8-utf8proc
Sebastien Helleu 2007-11-11 13:28:24 +01:00
parent 53328f4138
commit 60428b0d2e
3 changed files with 62 additions and 31 deletions

View File

@ -81,7 +81,7 @@ string_tolower (char *string)
{
if ((string[0] >= 'A') && (string[0] <= 'Z'))
string[0] += ('a' - 'A');
string++;
string = utf8_next_char (string);
}
}
@ -96,7 +96,7 @@ string_toupper (char *string)
{
if ((string[0] >= 'a') && (string[0] <= 'z'))
string[0] -= ('a' - 'A');
string++;
string = utf8_next_char (string);
}
}
@ -107,27 +107,19 @@ string_toupper (char *string)
int
string_strcasecmp (char *string1, char *string2)
{
int c1, c2;
int diff;
if (!string1 || !string2)
return (string1) ? 1 : ((string2) ? -1 : 0);
while (string1[0] && string2[0])
{
c1 = (int)((unsigned char) string1[0]);
c2 = (int)((unsigned char) string2[0]);
if ((c1 >= 'A') && (c1 <= 'Z'))
c1 += ('a' - 'A');
if ((c2 >= 'A') && (c2 <= 'Z'))
c2 += ('a' - 'A');
if ((c1 - c2) != 0)
return c1 - c2;
string1++;
string2++;
diff = utf8_charcasecmp (string1, string2);
if (diff != 0)
return diff;
string1 = utf8_next_char (string1);
string2 = utf8_next_char (string2);
}
return (string1[0]) ? 1 : ((string2[0]) ? -1 : 0);
@ -141,7 +133,7 @@ string_strcasecmp (char *string1, char *string2)
int
string_strncasecmp (char *string1, char *string2, int max)
{
int c1, c2, count;
int count, diff;
if (!string1 || !string2)
return (string1) ? 1 : ((string2) ? -1 : 0);
@ -149,20 +141,12 @@ string_strncasecmp (char *string1, char *string2, int max)
count = 0;
while ((count < max) && string1[0] && string2[0])
{
c1 = (int)((unsigned char) string1[0]);
c2 = (int)((unsigned char) string2[0]);
diff = utf8_charcasecmp (string1, string2);
if (diff != 0)
return diff;
if ((c1 >= 'A') && (c1 <= 'Z'))
c1 += ('a' - 'A');
if ((c2 >= 'A') && (c2 <= 'Z'))
c2 += ('a' - 'A');
if ((c1 - c2) != 0)
return c1 - c2;
string1++;
string2++;
string1 = utf8_next_char (string1);
string2 = utf8_next_char (string2);
count++;
}

View File

@ -315,6 +315,52 @@ utf8_strlen_screen (char *string)
return length;
}
/*
* utf8_charcasecmp: compare two utf8 chars (case is ignored)
*/
int
utf8_charcasecmp (char *string1, char *string2)
{
int length1, length2, i, char1, char2, diff;
if (!string1 || !string2)
return (string1) ? 1 : ((string2) ? -1 : 0);
length1 = utf8_char_size (string1);
length2 = utf8_char_size (string2);
char1 = (int)((unsigned char) string1[0]);
char2 = (int)((unsigned char) string2[0]);
if ((char1 >= 'A') && (char1 <= 'Z'))
char1 += ('a' - 'A');
if ((char2 >= 'A') && (char2 <= 'Z'))
char2 += ('a' - 'A');
diff = char1 - char2;
if (diff != 0)
return diff;
i = 1;
while ((i < length1) && (i < length2))
{
diff = (int)((unsigned char) string1[0]) - (int)((unsigned char) string2[0]);
if (diff != 0)
return diff;
i++;
}
// string1 == string2 ?
if ((i == length1) && (i == length2))
return 0;
// string1 < string2 ?
if (i == length1)
return 1;
// string1 > string2
return -1;
}
/*
* utf8_char_size_screen: return number of chars needed on screen to display
* UTF-8 char

View File

@ -42,6 +42,7 @@ extern int utf8_char_size (char *);
extern int utf8_strlen (char *);
extern int utf8_strnlen (char *, int);
extern int utf8_strlen_screen (char *);
extern int utf8_charcasecmp (char *, char *);
extern int utf8_char_size_screen (char *);
extern char *utf8_add_offset (char *, int);
extern int utf8_real_pos (char *, int);