Apply the converter patches for ICU 4.2.1 to ICU 4.6...

icu46/source/data/mappings/convrtrs.txt

 # ******************************************************************************
 # *
 # *   Copyright (C) 1995-2010, International Business Machines
 # *   Corporation and others.  All Rights Reserved.
 # *
 # ******************************************************************************
 
 # If this converter alias table looks very confusing, a much easier to
 # understand view can be found at this demo:
 # http://demo.icu-project.org/icu-bin/convexp
@@ skipping 342 matching lines @@
     us { IANA }
     csASCII { IANA WINDOWS }
     iso-ir-6 { IANA }
     cp367 { IANA WINDOWS }
     ascii7 { JAVA }
     646 { JAVA }
     windows-20127 { WINDOWS* }
     ibm-367 { IBM* } IBM367 { IANA WINDOWS } # This is not truely ibm-367 because it's missing the fallbacks.
 
 # GB 18030 is partly algorithmic, using the MBCS converter
-gb18030 { IANA* }       ibm-1392 { IBM* } windows-54936 { WINDOWS* } GB18030 { MIME* }
+gb18030 { IANA* }       ibm-1392 { IBM* } windows-54936 { WINDOWS* } gb18030 { MIME* }
 
 # Table-based interchange codepages
 
 # Central Europe
 ibm-912_P100-1995 { UTR22* }
                         ibm-912 { IBM* JAVA }
                         ISO-8859-2 { MIME* IANA JAVA* WINDOWS }
                         ISO_8859-2:1987 { IANA* WINDOWS JAVA }
                         latin2 { IANA WINDOWS JAVA }
                         csISOLatin2 { IANA WINDOWS JAVA }
@@ skipping 124 matching lines @@
                         hebrew8 # Reflect HP-UX code page update
 
 # Unfortunately, the Java aliases are split across ibm-916 and ibm-5012
 # Also many platforms are a combination between ibm-916 and ibm-5012 behaviors
 ibm-916_P100-1995 { UTR22* }
                         ibm-916 { IBM* JAVA* }
                         cp916 { JAVA }
                         916 { JAVA }
 
 # Turkish
+# CHROME: ISO-8859-9 and its aliases are moved to windows-1254 per
+# HTML5. 
 ibm-920_P100-1995 { UTR22* }
-                        ibm-920 { IBM* JAVA }
-                        ISO-8859-9 { MIME* IANA WINDOWS JAVA* }
-                        latin5 { IANA WINDOWS JAVA }
-                        csISOLatin5 { IANA JAVA }
-                        iso-ir-148 { IANA WINDOWS JAVA }
-                        ISO_8859-9:1989 { IANA* WINDOWS }
-                        l5 { IANA WINDOWS JAVA }
-                        8859_9 { JAVA }
+                        ibm-920 { IBM* JAVA* }
+                        ISO-8859-9
+                        latin5
+                        csISOLatin5
+                        iso-ir-148 
+                        ISO_8859-9:1989
+                        l5
                         cp920 { JAVA }
                         920 { JAVA }
                         windows-28599 { WINDOWS* }
                         ECMA-128    # IANA doesn't have this alias 6/24/2002
                         turkish8    # Reflect HP-UX codepage update 8/1/2008
                         turkish     # Reflect HP-UX codepage update 8/1/2008
 
 # Nordic languages
 iso-8859_10-1998 { UTR22* } ISO-8859-10 { MIME* IANA* }
                         iso-ir-157 { IANA }
@@ skipping 84 matching lines @@
                         ibm-943 { IBM* JAVA }
                         Shift_JIS # Leave untagged because this isn't the default
                         cp943 { JAVA* }    # This is slightly different, but the backslash mapping is the same.
                         943 { JAVA }
                         ibm-943_VASCII_VSUB_VPUA
                         x-IBM943 { JAVA }
                         # japanese. Unicode name is \u30b7\u30d5\u30c8\u7b26\u53f7\u5316\u8868\u73fe
 ibm-33722_P12A_P12A-2004_U2 { UTR22* }
                         ibm-33722   # Leave untagged because this isn't the default
                         ibm-5050    # Leave untagged because this isn't the default, and yes this alias is correct
-                        EUC-JP { IANA MIME* WINDOWS }
-                        Extended_UNIX_Code_Packed_Format_for_Japanese { IANA* WINDOWS }
-                        csEUCPkdFmtJapanese { IANA WINDOWS }
-                        X-EUC-JP { WINDOWS }   # Japan EUC. x-euc-jp is a MIME name
                         windows-51932 { WINDOWS* }
                         ibm-33722_VPUA
                         IBM-eucJP
 ibm-33722_P120-1999 { UTR22* }  # Japan EUC with \ <-> Yen mapping
                         ibm-33722 { IBM* JAVA }
                         ibm-5050 { IBM }    # Yes this is correct
                         cp33722 { JAVA* }
                         33722 { JAVA }
                         ibm-33722_VASCII_VPUA
                         x-IBM33722 { JAVA }
                         x-IBM33722A { JAVA }
                         x-IBM33722C { JAVA }
 # ibm-954 seems to be almost a superset of ibm-33722 and ibm-1350
 # ibm-1350 seems to be almost a superset of ibm-33722
 # ibm-954 contains more PUA characters than the others.
+# CHROME : Instead of ibm-33722_P*, we use our own EUC-JP converter
+# to match IE7 and Mozilla more closely.
+# google_euc_jp_mod is a modified version of EUC-JP that prefers 2-byte code
+# points when converting from Unicode while recognizing both 2-byte and
+# 3-byte code points when converting to Unicode.
+google-euc_jp_mod { UTR22* }
+                        EUC-JP { MIME* IANA JAVA* WINDOWS* }
+                        Extended_UNIX_Code_Packed_Format_for_Japanese { IANA* JAVA WINDOWS }
+                        csEUCPkdFmtJapanese { IANA JAVA WINDOWS }
+                        X-EUC-JP { MIME JAVA WINDOWS }   # Japan EUC. x-euc-jp is a MIME name
+                        eucjis {JAVA}
+                        ujis # Linux sometimes uses this name. This is an unfortunate generic and rarely used name. Its use is discouraged.
 ibm-954_P101-2007 { UTR22* }
                         ibm-954 { IBM* }
-                        EUC-JP { JAVA* } # Matches more closely with ibm-1350
-                        Extended_UNIX_Code_Packed_Format_for_Japanese { JAVA }
-                        csEUCPkdFmtJapanese { JAVA }
-                        X-EUC-JP { JAVA }   # Japan EUC. x-euc-jp is a MIME name
-                        eucjis { JAVA }
-                        ujis # Linux sometimes uses this name. This is an unfortunate generic and rarely used name. Its use is discouraged.
                         x-IBM954 { JAVA }
                         x-IBM954C { JAVA }
                         # eucJP # This is closest to Solaris EUC-JP.
                         
 aix-IBM_udcJP-4.3.6 { UTR22* }
                         x-IBM-udcJP { JAVA }
 
 java-euc_jp_linux-1.6_P { UTR22* }
                         euc-jp-linux
                         x-EUC_JP_LINUX { JAVA }
@@ skipping 30 matching lines @@
                         x-MS950-HKSCS { JAVA }
                         # windows-950 # Windows-950 can be w/ or w/o HKSCS extensions. By default it's not.
                         # windows-950_hkscs
 solaris-zh_TW_big5-2.7 { UTR22* }
                         Big5_Solaris { JAVA }
                         x-Big5-Solaris { JAVA }
 # GBK
 ibm-1386_P100-2001  { UTR22* }
                         ibm-1386 { IBM* }
                         cp1386
-                        windows-936 # Alternate mapping. Leave untagged. This is the IBM interpretation of a Windows codepage.
+                        #windows-936 # Alternate mapping. Leave untagged. This is the IBM interpretation of a Windows codepage.
                         ibm-1386_VSUB_VPUA
+# CHROME: Added 4 GB2312 aliases and EUC-CN to Windows-936 to reflect the
+#         reality of the web (GB2312 is treated synonymously with its
+#         superset, Windows-936/GBK)
+#         All the aliases listed for this converter (windows-936-2000)
+#         are removed from the list of aliases for other simplified Chinese
+#         converters above.
 windows-936-2000 { UTR22* }
-                        GBK { IANA* WINDOWS JAVA* }
+                        GB2312 { IANA* MIME* }
+                        windows-936 { IANA WINDOWS* JAVA }
+                        GBK { WINDOWS JAVA* }
                         CP936 { IANA JAVA }
                         MS936 { IANA }  # In JDK 1.5, this goes to x-mswin-936. This is an IANA name split.
-                        windows-936 { IANA WINDOWS* JAVA }
+                        chinese { IANA }
+                        iso-ir-58 { IANA }
+                        gb2312-1980
+                        EUC-CN
+                        csGB2312 { IANA }
+                        GB_2312-80 { IANA }
 
-# Java has two different tables for ibm-1383 and gb2312. We pick closest set for tagging.
+# Java has two different tables for ibm-1383 and gb2312. We pick closest set for tagging. 
 ibm-1383_P110-1999 { UTR22* }       # China EUC.
                         ibm-1383 { IBM* JAVA }
-                        GB2312 { IANA* MIME* }
-                        csGB2312 { IANA }
                         cp1383 { JAVA* }
                         1383 { JAVA }
-                        EUC-CN  # According to other platforms, windows-20936 looks more like euc-cn. x-euc-cn is also a MIME name
+                        #EUC-CN  # According to other platforms, windows-20936 looks more like euc-cn. x-euc-cn is also a MIME name
                         ibm-eucCN
                         hp15CN  # From HP-UX?
                         ibm-1383_VPUA
                         # gb          # This is not an IANA name. gb in IANA means Great Britain.
 
 ibm-5478_P100-1995 { UTR22* } ibm-5478 { IBM* } # This gb_2312_80 DBCS mapping is needed by iso-2022.
-                        GB_2312-80 { IANA* }    # Windows maps this alias incorrectly
-                        chinese { IANA }
-                        iso-ir-58 { IANA }
-                        csISO58GB231280 { IANA }
-                        gb2312-1980
+                        csISO58GB231280 { IANA* }
                         GB2312.1980-0   # From X11R6
 
 ibm-964_P110-1999 { UTR22* }                # Taiwan EUC. x-euc-tw is a MIME name
                         ibm-964 { IBM* JAVA }
                         EUC-TW
                         ibm-eucTW
                         cns11643 
                         cp964 { JAVA* }
                         964 { JAVA }
                         ibm-964_VPUA
@@ skipping 32 matching lines @@
 # </quote>
 #
 # The following aliases tries to mirror the poor state of alias recognition
 # on these platforms.
 #
 # ibm-970 is almost a subset of ibm-1363.
 # Java, Solaris and AIX use euc-kr to also mean ksc5601.
 # Java has both ibm-970 and EUC-KR as separate converters.
 ibm-970_P110_P110-2006_U2 { UTR22* }
                         ibm-970 { IBM* JAVA }
-                        EUC-KR { IANA* MIME* WINDOWS JAVA }
-                        KS_C_5601-1987 { JAVA }
                         windows-51949 { WINDOWS* }
-                        csEUCKR { IANA WINDOWS }  # x-euc-kr is also a MIME name
                         ibm-eucKR { JAVA }
-                        KSC_5601 { JAVA } # Needed by iso-2022
-                        5601 { JAVA }
                         cp970 { JAVA* }
                         970 { JAVA }
                         ibm-970_VPUA
                         x-IBM970 { JAVA }
 
 # ibm-971 is almost the set of DBCS mappings of ibm-970
 ibm-971_P100-1995       ibm-971 { IBM* } ibm-971_VPUA x-IBM971 { JAVA }
 
 # Java, Solaris and AIX use euc-kr to also mean ksc5601, and _sometimes_ for Windows too.
 # ibm-1363 is almost a superset of ibm-970.
 ibm-1363_P11B-1998 { UTR22* }
                         ibm-1363 # Leave untagged because this isn't the default
-                        KS_C_5601-1987 { IANA* }
-                        KS_C_5601-1989 { IANA }
-                        KSC_5601 { IANA }
-                        csKSC56011987 { IANA }
-                        korean { IANA }
-                        iso-ir-149 { IANA }
+                        #KS_C_5601-1987 { IANA* }
+                        #KS_C_5601-1989 { IANA }
+                        #KSC_5601 { IANA }
+                        #csKSC56011987 { IANA }
+                        #korean { IANA }
+                        #iso-ir-149 { IANA }
                         cp1363 { MIME* }
-                        5601
-                        ksc
-                        windows-949 # Alternate mapping. Leave untagged. This is the IBM interpretation of a Windows codepage.
+                        #5601
+                        #ksc
+                        #windows-949 # Alternate mapping. Leave untagged. This is the IBM interpretation of a Windows codepage.
                         ibm-1363_VSUB_VPUA
                         x-IBM1363C { JAVA }
                         # ks_x_1001:1992
                         # ksc5601-1992
 
 ibm-1363_P110-1997 { UTR22* } # Korean KSC MBCS with \ <-> Won mapping
                         ibm-1363 { IBM* }
                         ibm-1363_VASCII_VSUB_VPUA
                         x-IBM1363 { JAVA }
 
+#CHROME: Windows-949 is NOT EUC-KR, but a superset of EUC-KR with 8,822
+#        additional Hangul syllables. However, the reality of the web
+#        dictates that we make a compromise and make EUC-KR a synonym of
+#        windows-949.
+#        All the aliases listed for this converter (windows-949-2000)
+#        are removed from the list of aliases for other Korean converters
+#        above.
 windows-949-2000 { UTR22* }
                         windows-949 { JAVA* WINDOWS* }
                         KS_C_5601-1987 { WINDOWS }
                         KS_C_5601-1989 { WINDOWS }
                         KSC_5601 { MIME WINDOWS } # Needed by iso-2022
+                        EUC-KR { IANA* MIME* WINDOWS }
+                        KS_C_5601-1987 { WINDOWS IANA }
+                        KS_C_5601-1989 { WINDOWS IANA }
+                        KSC_5601 { IANA WINDOWS } # Needed by iso-2022
                         csKSC56011987 { WINDOWS }
-                        korean { WINDOWS }
-                        iso-ir-149 { WINDOWS }
+                        korean { IANA WINDOWS }
+                        iso-ir-149 { IANA WINDOWS }
                         ms949 { JAVA }
+                        csEUCKR { IANA WINDOWS }
+                        5601
+                        x-windows-949 # Mozilla
+                        x-UHC   # Mozilla (Unified Hangul Code)
                         x-KSC5601 { JAVA }
 
 windows-1361-2000 { UTR22* }
                         ksc5601_1992
                         ms1361
                         johab
                         x-Johab { JAVA }
 
+#CHROME: TIS-620, ISO-8859-11 and Windows-874 are slightly different from
+# each other, but they're used as if they're identical on the web.
 windows-874-2000 { UTR22* }   # Thai (w/ euro update)
-                        TIS-620 { WINDOWS }
-                        windows-874 { JAVA* WINDOWS* }
+                        TIS-620 { IANA* WINDOWS MIME* }
+                        windows-874 { JAVA* WINDOWS* MIME }
                         MS874 { JAVA }
                         x-windows-874 { JAVA }
-                        # iso-8859-11 { WINDOWS } # iso-8859-11 is similar to TIS-620. ibm-13162 is a closer match.
+                        iso-8859-11 { IANA WINDOWS MIME } # iso-8859-11 is similar to TIS-620. ibm-13162 is a closer match.
 
 ibm-874_P100-1995 { UTR22* }    # Thai PC (w/o euro update).
                         ibm-874 { IBM* JAVA }
                         ibm-9066 { IBM }    # Yes ibm-874 == ibm-9066. ibm-1161 has the euro update.
                         cp874 { JAVA* }
-                        TIS-620 { IANA* JAVA }  # This is actually separate from ibm-874, which is similar to this table
+                        #TIS-620 { IANA* JAVA }  # This is actually separate from ibm-874, which is similar to this table
                         tis620.2533 { JAVA }    # This is actually separate from ibm-874, which is similar to this table
                         eucTH               # eucTH is an unusual alias from Solaris.  eucTH has fewer mappings than TIS620
                         x-IBM874 { JAVA }
 
 ibm-1162_P100-1999 { UTR22* }   # Thai (w/ euro update)
                         ibm-1162 { IBM* }
 
 windows-864-2000 { UTR22* }
                         ibm-864s
                         cp864s
@@ skipping 29 matching lines @@
 ibm-1168_P100-2002 { UTR22* }   ibm-1168 { IBM* } KOI8-U { IANA* WINDOWS } windows-21866 { WINDOWS* } # Ukrainian KOI8. koi8-ru != KOI8-U and Microsoft is wrong for aliasing them as the same.
 ibm-4909_P100-1999 { UTR22* }   ibm-4909 { IBM* } # ISO Greek (w/ euro update), update of ibm-813
 
 # The cp aliases in this section aren't really windows aliases, but it was used by ICU for Windows.
 # cp is usually used to denote IBM in Java, and that is why we don't do that anymore.
 # The windows-* aliases mean windows codepages.
 ibm-5346_P100-1998 { UTR22* }   ibm-5346 { IBM* } windows-1250 { IANA* JAVA* WINDOWS* } cp1250 { WINDOWS JAVA } # Windows Latin2 (w/ euro update)
 ibm-5347_P100-1998 { UTR22* }   ibm-5347 { IBM* } windows-1251 { IANA* JAVA* WINDOWS* } cp1251 { WINDOWS JAVA } ANSI1251 # Windows Cyrillic (w/ euro update). ANSI1251 is from Solaris
 ibm-5348_P100-1997 { UTR22* }   ibm-5348 { IBM* } windows-1252 { IANA* JAVA* WINDOWS* } cp1252 { JAVA }         # Windows Latin1 (w/ euro update)
 ibm-5349_P100-1998 { UTR22* }   ibm-5349 { IBM* } windows-1253 { IANA* JAVA* WINDOWS* } cp1253 { JAVA }         # Windows Greek (w/ euro update)
-ibm-5350_P100-1998 { UTR22* }   ibm-5350 { IBM* } windows-1254 { IANA* JAVA* WINDOWS* } cp1254 { JAVA }         # Windows Turkish (w/ euro update)
+#CHROME : Make ISO-8859-9 an alias to windows-1254 per HTML5. Move
+#other IANA aliases for ISO-8859-9 as well.
+ibm-5350_P100-1998 { UTR22* }   ibm-5350 { IBM* } windows-1254 { MIME* IANA* JAVA* WINDOWS* } cp1254 { JAVA }         # Windows Turkish (w/ euro update)
+                        ISO-8859-9 { MIME }
+                        latin5 { IANA }
+                        csISOLatin5 { IANA }
+                        iso-ir-148 { IANA }
+                        ISO_8859-9:1989 { IANA }
+                        l5 { IANA }
+                        8859_9 { JAVA }
 ibm-9447_P100-2002 { UTR22* }   ibm-9447 { IBM* } windows-1255 { IANA* JAVA* WINDOWS* } cp1255 { JAVA }         # Windows Hebrew (w/ euro update)
 ibm-9448_X100-2005 { UTR22* }   ibm-9448 { IBM* } windows-1256 { IANA* JAVA* WINDOWS* } cp1256 { WINDOWS JAVA } x-windows-1256S { JAVA } # Windows Arabic (w/ euro update)
 ibm-9449_P100-2002 { UTR22* }   ibm-9449 { IBM* } windows-1257 { IANA* JAVA* WINDOWS* } cp1257 { JAVA }         # Windows Baltic (w/ euro update)
 ibm-5354_P100-1998 { UTR22* }   ibm-5354 { IBM* } windows-1258 { IANA* JAVA* WINDOWS* } cp1258 { JAVA }         # Windows Vietnamese (w/ euro update)
 
 # These tables are out of date, and most don't have the Euro
 # Leave the windows- variants untagged. They are alternate tables of the newer ones above.
 ibm-1250_P100-1995 { UTR22* }   ibm-1250 { IBM* } windows-1250  # Old Windows Latin2 (w/o euro update)
 ibm-1251_P100-1995 { UTR22* }   ibm-1251 { IBM* } windows-1251  # Old Windows Cyrillic (w/o euro update)
 ibm-1252_P100-2000 { UTR22* }   ibm-1252 { IBM* } windows-1252  # Old Windows Latin 1 without Euro
@@ skipping 352 matching lines @@
 ibm-952_P110-1997 { UTR22* }    ibm-952 { IBM* } x-JIS0208 # Pure DBCS, Japanese EUC, G1 - JIS X208-1990
 ibm-953_P100-2000 { UTR22* }    ibm-953 { IBM* } JIS_X0212-1990 { IANA* } # Pure DBCS, Japanese EUC, G3 - JIS X 0212-1990
 ibm-955_P110-1997 { UTR22* }    ibm-955 { IBM* } # Pure DBCS, Japanese EUC, G0 - JIS X208-1978
 ibm-9577_P100-2001 { UTR22* }   ibm-9577 { IBM* } ibm-1385 { IBM } x-IBM1385 { JAVA } # ibm-9577 and ibm-1385 are identical DBCS tables.
 iso-8859_16-2001 { UTR22* }     ISO-8859-16 { IANA* } iso-ir-226 { IANA } ISO_8859-16:2001 { IANA } latin10 { IANA } l10 { IANA }
 
 # To be considered for listing at a later date for the data library customization tool
 #ibm-1159_P100-1999 { UTR22* }   ibm-1159 { IBM* } # SBCS T-Ch Host. Euro update of ibm-28709. This is used in combination with another CCSID mapping.
 #ibm-960_P100-2000 { UTR22* }    ibm-960 { IBM* } # Pure DBCS, CNS11643 plane 1
 #ibm-963_P100-1995 { UTR22* }    ibm-963 { IBM* } # Pure DBCS, CNS11643 plane 2 Traditional Chinese (DBCS subset of ibm-965)