Remove duplicate implementation of CP932 from mbstring

Sigh. Double sigh. After fruitlessly searching the Internet for information on this mysterious text encoding called "SJIS-open", I wrote a script to try converting every Unicode codepoint from 0-0xFFFF and compare the results from different variants of Shift-JIS, to see which one "SJIS-open" would be most similar to. The result? It's just CP932. There is no difference at all. So why do we have two implementations of CP932 in mbstring? In case somebody, somewhere is using "SJIS-open" (or its aliases "SJIS-win" or "SJIS-ms"), add these as aliases to CP932 so existing code will continue to work.
php · Jun 17, 2021 · e245985 · e245985
1 parent 7502c86
commit e245985
Show file tree

Hide file tree

Showing 9 changed files with 4 additions and 360 deletions.
diff --git a/ext/mbstring/config.m4 b/ext/mbstring/config.m4
@@ -117,7 +117,6 @@ AC_DEFUN([PHP_MBSTRING_SETUP_LIBMBFL], [
     libmbfl/filters/mbfilter_qprint.c
     libmbfl/filters/mbfilter_singlebyte.c
     libmbfl/filters/mbfilter_sjis.c
-    libmbfl/filters/mbfilter_sjis_open.c
     libmbfl/filters/mbfilter_sjis_mobile.c
     libmbfl/filters/mbfilter_sjis_mac.c
     libmbfl/filters/mbfilter_sjis_2004.c

diff --git a/ext/mbstring/config.w32 b/ext/mbstring/config.w32
@@ -26,7 +26,7 @@ if (PHP_MBSTRING != "no") {
 			mbfilter_ucs4.c mbfilter_uhc.c mbfilter_utf16.c mbfilter_utf32.c \
 			mbfilter_utf7.c mbfilter_utf7imap.c mbfilter_utf8.c \
 			mbfilter_utf8_mobile.c mbfilter_euc_jp_2004.c mbfilter_uuencode.c \
-			mbfilter_cp5022x.c mbfilter_sjis_open.c mbfilter_sjis_mobile.c \
+			mbfilter_cp5022x.c mbfilter_sjis_mobile.c \
 			mbfilter_sjis_mac.c mbfilter_iso2022jp_2004.c \
 			mbfilter_iso2022jp_mobile.c mbfilter_singlebyte.c \
 			mbfilter_tl_jisx0201_jisx0208.c", "mbstring");

diff --git a/ext/mbstring/libmbfl/filters/mbfilter_cp932.c b/ext/mbstring/libmbfl/filters/mbfilter_cp932.c
@@ -54,7 +54,7 @@ static const unsigned char mblen_table_sjis[] = { /* 0x80-0x9f,0xE0-0xFF */
   2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2
 };
 
-static const char *mbfl_encoding_cp932_aliases[] = {"MS932", "Windows-31J", "MS_Kanji", NULL};
+static const char *mbfl_encoding_cp932_aliases[] = {"MS932", "Windows-31J", "MS_Kanji", "SJIS-win", "SJIS-ms", "SJIS-open", NULL};
 
 const mbfl_encoding mbfl_encoding_cp932 = {
 	mbfl_no_encoding_cp932,

diff --git a/ext/mbstring/libmbfl/filters/mbfilter_sjis_open.c b/ext/mbstring/libmbfl/filters/mbfilter_sjis_open.c
diff --git a/ext/mbstring/libmbfl/filters/mbfilter_sjis_open.h b/ext/mbstring/libmbfl/filters/mbfilter_sjis_open.h
diff --git a/ext/mbstring/libmbfl/mbfl/mbfl_convert.c b/ext/mbstring/libmbfl/mbfl/mbfl_convert.c
@@ -44,7 +44,6 @@
 #include "filters/mbfilter_euc_kr.h"
 #include "filters/mbfilter_iso2022_kr.h"
 #include "filters/mbfilter_sjis.h"
-#include "filters/mbfilter_sjis_open.h"
 #include "filters/mbfilter_sjis_2004.h"
 #include "filters/mbfilter_sjis_mobile.h"
 #include "filters/mbfilter_sjis_mac.h"