Update tz data to 2014f and add SJIS for the encoding spec

patches/converters.patch

 Index: source/data/mappings/windows-949-2000.ucm
 ===================================================================
 --- source/data/mappings/windows-949-2000.ucm   (revision 259715)
 +++ source/data/mappings/windows-949-2000.ucm   (working copy)
 @@ -32,18 +32,17 @@
  # Suggested ICU specific alias information
  #<icu:alias>                  "windows-949_VPUA"
  
 -<icu:state>                   0-80, 81-fe:1, ff
 -<icu:state>                   40-7e, 80-fe
@@ skipping 106 matching lines @@
 -# but are not allowed in, e.g., email headers.
 -# By default, the ICU UTF-7 converter encodes set O directly.
 -# By choosing the option "version=1", set O will be escaped instead.
 -# For example:
 -#     utf7Converter=ucnv_open("UTF-7,version=1");
 -#
 -# For details about email headers see RFC 2047.
 -UTF-7 { IANA* MIME* WINDOWS }   windows-65000 { WINDOWS* }
 -                                unicode-1-1-utf-7
 -                                unicode-2-0-utf-7
-+# Chrome : Remove all the entries for UTF-7, SCSU, BOCU, CESU-8.
++# Chrome: Remove all the entries for UTF-7, SCSU, BOCU, CESU-8.
  
 -# UTF-EBCDIC doesn't exist in ICU, but the aliases are here for reference.
 -#UTF-EBCDIC ibm-1210 { IBM* } ibm-1211 { IBM }
 -
 -# IMAP-mailbox-name is an ICU-specific name for the encoding of IMAP mailbox names.
 -# It is a substantially modified UTF-7 encoding. See the specification in:
 -#
 -# RFC 2060: INTERNET MESSAGE ACCESS PROTOCOL - VERSION 4rev1
 -# (http://www.ietf.org/rfc/rfc2060.txt)
 -# Section 5.1.3.  Mailbox International Naming Convention
@@ skipping 78 matching lines @@
 -                        8859_9 { JAVA }
 +                        ISO-8859-9
 +                        latin5
 +                        csISOLatin5
 +                        iso-ir-148 
 +                        ISO_8859-9:1989
 +                        l5
                          cp920 { JAVA }
                          920 { JAVA }
                          windows-28599 { WINDOWS* }
-@@ -567,17 +513,6 @@
+@@ -567,22 +513,11 @@
  
  # CJK encodings
  
 -ibm-942_P12A-1999 { UTR22* }    # ibm-942_P120 is a rarely used alternate mapping (sjis78 is already old)
 -                        ibm-942 { IBM* }
 -                        ibm-932 { IBM }
 -                        cp932
 -                        shift_jis78
 -                        sjis78
 -                        ibm-942_VSUB_VPUA
 -                        ibm-932_VSUB_VPUA
 -                        x-IBM942 { JAVA* }
 -                        x-IBM942C { JAVA }
 -                        # Is this "JIS_C6226-1978"?
++# Chrome: Instead of ibm-943_P15A-2003, we use what's specified in the WHATWG
++# encoding standard (HTML5) for Shift_JIS. Keep all the aliases (even though
++not all of them not required by the encoding spec) for now.
  
- # ibm-943_P15A-2003 differs from windows-932-2000 only in a few roundtrip mappings:
- # - the usual IBM PC control code rotation (1A-1C-7F)
-@@ -603,62 +538,20 @@
+-# ibm-943_P15A-2003 differs from windows-932-2000 only in a few roundtrip mappings:
+-# - the usual IBM PC control code rotation (1A-1C-7F)
+-# - the Windows table has roundtrips for bytes 80, A0, and FD-FF to U+0080 and PUA
+-ibm-943_P15A-2003 { UTR22* }
++shift_jis-html5 { UTR22* }
+                         ibm-943 # Leave untagged because this isn't the default
+                         Shift_JIS { IANA* MIME* WINDOWS JAVA }
+                         MS_Kanji { IANA WINDOWS JAVA }
+@@ -601,64 +536,20 @@
+                         ibm-943_VSUB_VPUA
+                         x-MS932_0213 { JAVA }
                          x-JISAutoDetect { JAVA }
-                         # cp943 # This isn't Windows, and no one else uses it.
-                         # IANA says that Windows-31J is an extension to csshiftjis ibm-932 
+-                        # cp943 # This isn't Windows, and no one else uses it.
+-                        # IANA says that Windows-31J is an extension to csshiftjis ibm-932 
 -ibm-943_P130-1999 { UTR22* }
 -                        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-2009_U2 { UTR22* }
 -                        ibm-33722   # Leave untagged because this isn't the default
@@ skipping 18 matching lines @@
 -# ibm-954 contains more PUA characters than the others.
 -ibm-954_P101-2007 { UTR22* }
 -                        ibm-954 { IBM* }
 -                        x-IBM954 { JAVA* }
 -                        x-IBM954C { JAVA }
 -                        # eucJP # This is closest to Solaris EUC-JP.
 -euc-jp-2007 { UTR22* }
 -                        EUC-JP { MIME* IANA JAVA* WINDOWS* }
 +
 +# Chrome: Instead of ibm-33722_P*, we use what's specified in the WHATWG
-+# encoding standard (HTML5) with 30+ additional decode-only mappings. All the
++# encoding standard (HTML5). All the
 +# 3-byte seqeunces in the normative EUC-JP are now decode-only.
 +euc-jp-html5 { UTR22* }
 +                        EUC-JP { MIME* IANA JAVA* WINDOWS*}
                          Extended_UNIX_Code_Packed_Format_for_Japanese { IANA* JAVA WINDOWS }
                          csEUCPkdFmtJapanese { IANA JAVA WINDOWS }
 +                        windows-51932 { 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.
  
 -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* }
 -
 -java-sjis_0213-1.6_P { UTR22* }
 -                        x-SJIS_0213 { JAVA* }
 -
 -# Here are various interpretations and extentions of Big5
 -ibm-1373_P100-2002 { UTR22* } # IBM's interpretation of Windows' Taiwan Big-5 without HKSCS extensions
 -                        ibm-1373 { IBM* }
 -                        windows-950 # Alternate mapping. Leave untagged. This is the IBM interpretation of a Windows codepage.
  windows-950-2000 { UTR22* }
                          Big5 { IANA* MIME* JAVA* WINDOWS }
                          csBig5 { IANA WINDOWS }
-@@ -666,16 +559,14 @@
+@@ -666,16 +557,14 @@
                          x-windows-950 { JAVA }
                          x-big5
                          ms950
 -ibm-950_P110-1999 { UTR22* }                # Taiwan Big-5 (w/o euro update)
 -                        ibm-950 { IBM* JAVA }
 -                        cp950 { JAVA* }
 -                        950 { JAVA }
 -                        x-IBM950 { JAVA }
  ibm-1375_P100-2007 { UTR22* }   # Big5-HKSCS-2004 with Unicode 3.1 mappings. This uses supplementary characters.
                          ibm-1375 { IBM* }
                          Big5-HKSCS { IANA* JAVA* }
                          big5hk { JAVA }
                          HKSCS-BIG5  # From http://www.openi18n.org/localenameguide/
 +
 +# Chrome: HTML5 has big5-hkscs as an alias for big5
 +#         TODO(jshin): Decide if Chrome should follow spec. crbug.com/277040
  ibm-5471_P100-2006 { UTR22* }   # Big5-HKSCS-2001 with Unicode 3.0 mappings. This uses many PUA characters.
                          ibm-5471 { IBM* }
                          Big5-HKSCS
-@@ -685,201 +576,68 @@
+@@ -685,201 +574,68 @@
                          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
@@ skipping 219 matching lines @@
 -ibm-901_P100-1999 { UTR22* }    ibm-901 { IBM* } # PC Baltic (w/ euro update), update of ibm-921
 -ibm-902_P100-1999 { UTR22* }    ibm-902 { IBM* } # PC Estonian (w/ euro update), update of ibm-922
 -ibm-922_P100-1999 { UTR22* }    ibm-922 { IBM* } IBM922 { JAVA } cp922 { JAVA* } 922 { JAVA } x-IBM922 { JAVA } # PC Estonian (w/o euro update)
 +# Chrome: Use the table from the WHATWG encoding standard (HTML5).
 +ibm-866_html5-2012 { UTR22* }    ibm-866 { IBM* } IBM866 { IANA* MIME* JAVA } cp866 { IANA MIME WINDOWS JAVA* } 866 { IANA JAVA } csIBM866 { IANA JAVA } # PC Russian (w/o euro update)
  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.
-@@ -888,53 +646,26 @@
+@@ -888,53 +644,26 @@
  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 }
@@ skipping 45 matching lines @@
 -ibm-1124_P100-1996 { UTR22* }   ibm-1124 { IBM* JAVA } cp1124 { JAVA* } 1124 { JAVA } x-IBM1124 { JAVA }  # ISO Cyrillic Ukraine
 -ibm-1125_P100-1997 { UTR22* }   ibm-1125 { IBM* } cp1125                                # Cyrillic Ukraine PC
 -ibm-1129_P100-1997 { UTR22* }   ibm-1129 { IBM* }                                       # ISO Vietnamese
 -ibm-1131_P100-1997 { UTR22* }   ibm-1131 { IBM* } cp1131                                # Cyrillic Belarus PC
 -ibm-1133_P100-1997 { UTR22* }   ibm-1133 { IBM* }                                       # ISO Lao
 -
 -
  # Partially algorithmic converters
  
  # [U_ENABLE_GENERIC_ISO_2022]
-@@ -943,322 +674,25 @@
+@@ -943,322 +672,25 @@
  # Language-specific variants of ISO-2022 continue to be available as listed below.
  # ISO_2022                         ISO-2022
  
 +# Chrome: The encoding standard only supports ISO-2022-JP and HZ-GB. 
 +# Keep ISO-2022-{KR,CN,CN-Ext} until we're sure what to do about
 +# replacement encodings. See crbug.com/277037
 +# TODO(jshin): Remove them when the bug is resolved.
  ISO_2022,locale=ja,version=0    ISO-2022-JP { IANA* MIME* JAVA* } csISO2022JP { IANA JAVA } x-windows-iso2022jp { JAVA } x-windows-50220 { JAVA }
 -ISO_2022,locale=ja,version=1    ISO-2022-JP-1 { MIME* } JIS_Encoding { IANA* } csJISEncoding { IANA } ibm-5054 { IBM* } JIS x-windows-50221 { JAVA* }
 -ISO_2022,locale=ja,version=2    ISO-2022-JP-2 { IANA* MIME* } csISO2022JP2 { IANA }
@@ skipping 310 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)