clones/php-src
1
0
Fork 0
mirror of https://github.com/php/php-src.git synced 2024-09-21 18:07:23 +00:00
Code Issues Packages Projects Releases Wiki Activity

Restore backwards-compatible mappings of U+005C and U+007E to SJIS-2004

Browse Source 
In 0d0029d729 and 315d48b434, I changed the mappings used for Unicode
to Shift-JIS-2004, in an attempt to follow the JISC specification
more closely. However, feedback from Japanese PHP users indicates
that most users of SJIS-2004 expect 0x5C and 0x7E to be treated as
equivalent to the same ASCII bytes. This is due to a long history of
non-complying implementations which then became a de-facto standard.

Therefore, restore the earlier mappings for U+005C and U+007E.

Thanks to the GitHub user 'youkidearitai' for reporting this issue.

Fixes GH-9528.
This commit is contained in:
Alex Dowad 2022-10-04 15:44:34 +09:00
parent 5877b84056
commit dd00e2f1e3
3 changed files with 11 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
ext/mbstring/libmbfl/filters/mbfilter_sjis_2004.c
View File

@ -24,9 +24,15 @@
/*
* The source code included in this files was separated from mbfilter_sjis.c
* by rui hirokawa <hirokawa@php.net> on 15 aug 2011.
*
*/
/* Although the specification for Shift-JIS-2004 indicates that 0x5C and
* 0x7E should (respectively) represent a Yen sign and an overbar, feedback
* from Japanese PHP users indicates that they prefer 0x5C and 0x7E to be
* treated as equivalent to U+005C and U+007E. This is the historical
* behavior of mbstring, and promotes compatibility with other software
* which handles Shift-JIS and Shift-JIS-2004 text in this way. */
#include "mbfilter.h"
#include "mbfilter_sjis_2004.h"
@ -489,13 +495,6 @@ retry:
}
}
if (s1 <= 0 && (filter->to->no_encoding == mbfl_no_encoding_2022jp_2004 || filter->to->no_encoding == mbfl_no_encoding_eucjp2004) && (c == 0x5C || c == 0x7E)) {
/* ISO-2022-JP-2004 can represent ASCII characters directly, so there is no need
* to use the JIS X 0208 REVERSE SOLIDUS for ASCII backslash, or WAVE DASH for tilde
* Likewise for EUC-JP-2004 */
s1 = c;
}
/* check for major japanese chars: U+4E00 - U+9FFF */
if (s1 <= 0) {
for (k = 0; k < uni2jis_tbl_len; k++) {

4
ext/mbstring/libmbfl/filters/unicode_table_jis2004.h
View File

@ -1608,11 +1608,11 @@ static const unsigned short ucs_a1_jisx0213_table[] = { // 0x0000 - 0x045f
0x0040,0x0041,0x0042,0x0043,0x0044,0x0045,0x0046,0x0047,
0x0048,0x0049,0x004A,0x004B,0x004C,0x004D,0x004E,0x004F,
0x0050,0x0051,0x0052,0x0053,0x0054,0x0055,0x0056,0x0057,
0x0058,0x0059,0x005A,0x005B,0x2140,0x005D,0x005E,0x005F,
0x0058,0x0059,0x005A,0x005B,0x005C,0x005D,0x005E,0x005F,
0x0060,0x0061,0x0062,0x0063,0x0064,0x0065,0x0066,0x0067,
0x0068,0x0069,0x006A,0x006B,0x006C,0x006D,0x006E,0x006F,
0x0070,0x0071,0x0072,0x0073,0x0074,0x0075,0x0076,0x0077,
0x0078,0x0079,0x007A,0x007B,0x007C,0x007D,0x2141,0x007F,
0x0078,0x0079,0x007A,0x007B,0x007C,0x007D,0x007E,0x007F,
0x0000,0x0000,0x0000,0x0000,0x0000,0x0000,0x0000,0x0000,
0x0000,0x0000,0x0000,0x0000,0x0000,0x0000,0x0000,0x0000,
0x0000,0x0000,0x0000,0x0000,0x0000,0x0000,0x0000,0x0000,

8
ext/mbstring/tests/sjis2004_encoding.phpt
View File

@ -38,12 +38,8 @@ while ($line = fgets($fp, 256)) {
}
}
/* U+007E is TILDE, Shift-JIS 0x8160 is WAVE DASH */
$fromUnicode["\x00\x7E"] = "\x81\x60";
/* U+005C is backslash, Shift-JIS 0x815F is REVERSE SOLIDUS
* (ie. a fancy way to say "backslash") */
$fromUnicode["\x00\x5C"] = "\x81\x5F";
$fromUnicode["\x00\x7E"] = "\x7E";
$fromUnicode["\x00\x5C"] = "\x5C";
testAllValidChars($validChars, 'SJIS-2004', 'UTF-32BE');
echo "SJIS-2004 verification and conversion works for all valid characters\n";