pegasus/weechat
1
0
Fork 0
mirror of https://github.com/weechat/weechat.git synced 2026-07-01 15:26:37 +02:00
Code Activity

core: fix code style in function utf8_is_valid()

Browse Source
This commit is contained in:
Sébastien Helleu
2014-07-20 15:50:12 +02:00
parent 1e669e4b1e
commit 45f1b6bfc5
1 changed files with 39 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/core/wee-utf8.c
+39 -19
View File
@@ -79,55 +79,75 @@ utf8_has_8bits (const char *string)
int
utf8_is_valid (const char *string, char **error)
{
int n;
int code_point;
while (string && string[0])
{
/* UTF-8, 2 bytes, should be: 110vvvvv 10vvvvvv and U+0080-07FF */
/*
* UTF-8, 2 bytes, should be: 110vvvvv 10vvvvvv
* and in range: U+0080 - U+07FF
*/
if (((unsigned char)(string[0]) & 0xE0) == 0xC0)
{
if (!string[1] || (((unsigned char)(string[1]) & 0xC0) != 0x80))
goto err;
n = utf8_char_int(string);
if (n < 0x80 || n > 0x7ff)
goto err;
goto invalid;
code_point = utf8_char_int (string);
if ((code_point < 0x0080) || (code_point > 0x07FF))
goto invalid;
string += 2;
}
/* UTF-8, 3 bytes, should be: 1110vvvv 10vvvvvv 10vvvvvv and U+0800-FFFF */
/*
* UTF-8, 3 bytes, should be: 1110vvvv 10vvvvvv 10vvvvvv
* and in range: U+0800 - U+FFFF
* (note: high and low surrogate halves used by UTF-16 (U+D800 through
* U+DFFF) are not legal Unicode values)
*/
else if (((unsigned char)(string[0]) & 0xF0) == 0xE0)
{
if (!string[1] || !string[2]
|| (((unsigned char)(string[1]) & 0xC0) != 0x80)
|| (((unsigned char)(string[2]) & 0xC0) != 0x80))
goto err;
n = utf8_char_int(string);
if (n < 0x800 || n > 0xffff || (n >= 0xd800 && n <= 0xdfff))
goto err;
{
goto invalid;
}
code_point = utf8_char_int (string);
if ((code_point < 0x0800)
|| (code_point > 0xFFFF)
|| ((code_point >= 0xD800) && (code_point <= 0xDFFF)))
{
goto invalid;
}
string += 3;
}
/* UTF-8, 4 bytes, should be: 11110vvv 10vvvvvv 10vvvvvv 10vvvvvv and U+10000-1FFFFF */
/*
* UTF-8, 4 bytes, should be: 11110vvv 10vvvvvv 10vvvvvv 10vvvvvv
* and in range: U+10000 - U+1FFFFF
*/
else if (((unsigned char)(string[0]) & 0xF8) == 0xF0)
{
if (!string[1] || !string[2] || !string[3]
|| (((unsigned char)(string[1]) & 0xC0) != 0x80)
|| (((unsigned char)(string[2]) & 0xC0) != 0x80)
|| (((unsigned char)(string[3]) & 0xC0) != 0x80))
goto err;
n = utf8_char_int(string);
if (n < 0x10000 || n > 0x1fffff)
goto err;
{
goto invalid;
}
code_point = utf8_char_int(string);
if ((code_point < 0x10000) || (code_point > 0x1FFFFF))
goto invalid;
string += 4;
}
/* UTF-8, 1 byte, should be: 0vvvvvvv */
else if ((unsigned char)(string[0]) >= 0x80)
goto err;
goto invalid;
else
string++;
}
if (error)
*error = NULL;
return 1;
err:
invalid:
if (error)
*error = (char *)string;
return 0;