php/archived-php-src
1
0
Fork 0
mirror of https://github.com/php/php-src.git synced 2026-04-29 03:03:26 +02:00
Code Issues Packages Projects Releases Wiki Activity

Add identify filter for ISO-8859-6 (Latin/Arabic)

Browse Source 
Note that some text encoding conversion libraries, such as Solaris iconv
and FreeBSD iconv, map 0x30-0x39 to the Arabic script numerals rather than
the 'regular' Roman numerals. (That is, to Unicode codepoints 0x660-0x669.)

Further, Windows CP28596 adds more mappings to use the unused bytes in
ISO-8859-6.
This commit is contained in:
Alex Dowad
2020-09-19 20:34:13 +02:00
parent 23270d7f9e
commit a6603b60f7
1 changed files with 11 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ext/mbstring/libmbfl/filters/mbfilter_iso8859_6.c
+11 -1
View File
@@ -31,6 +31,8 @@
#include "mbfilter_iso8859_6.h"
#include "unicode_table_iso8859_6.h"
static int mbfl_filt_ident_iso8859_6(int c, mbfl_identify_filter *filter);
static const char *mbfl_encoding_8859_6_aliases[] = {"ISO8859-6", "arabic", NULL};
const mbfl_encoding mbfl_encoding_8859_6 = {
@@ -47,7 +49,7 @@ const mbfl_encoding mbfl_encoding_8859_6 = {
const struct mbfl_identify_vtbl vtbl_identify_8859_6 = {
mbfl_no_encoding_8859_6,
mbfl_filt_ident_common_ctor,
mbfl_filt_ident_true
mbfl_filt_ident_iso8859_6
};
const struct mbfl_convert_vtbl vtbl_8859_6_wchar = {
@@ -132,3 +134,11 @@ int mbfl_filt_conv_wchar_8859_6(int c, mbfl_convert_filter *filter)
return c;
}
static int mbfl_filt_ident_iso8859_6(int c, mbfl_identify_filter *filter)
{
if (c >= 0xA0 && !iso8859_6_ucs_table[c - 0xA0]) {
filter->status = 1;
}
return c;
}