Turn on UCONFIG_NO_NON_HTML5_CONVERTER to save 100kB

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 38 matching lines @@
 +#<icu:base>                    "ibm-1373_P100-2002"
  
 -# The following was the generated state table.
 -# This does not account for unassigned characters
 -#<icu:state>                  0-80, 81-fe:1, ff
 -#<icu:state>                  40-7e, a1-fe
 -#
  CHARMAP
  <U0000> \x00 |0
  <U0001> \x01 |0
-Index: source/data/mappings/windows-936-2000.ucm
-===================================================================
---- source/data/mappings/windows-936-2000.ucm   (revision 259715)
-+++ source/data/mappings/windows-936-2000.ucm   (working copy)
-@@ -37,7 +37,8 @@
- 
- # build an extension-only (delta) .cnv file
- # requires the base .cnv file at runtime
--<icu:base>                    "ibm-1386_P100-2001"
-+# CHROME : we don't want ibm-1386
-+#<icu:base>                    "ibm-1386_P100-2001"
- 
- # The following was the generated state table.
- # This does not account for unassigned characters
-@@ -259,6 +260,7 @@
- <U01DA> \xA8\xB7 |0
- <U01DB> \xA8\xB8 |1
- <U01DC> \xA8\xB8 |0
-+<U01F9> \xA8\xBF |1
- <U0251> \xA8\xBB |0
- <U0261> \xA8\xC0 |0
- <U02C7> \xA1\xA6 |0
-@@ -380,6 +382,7 @@
- <U044E> \xA7\xF0 |0
- <U044F> \xA7\xF1 |0
- <U0451> \xA7\xD7 |0
-+<U1E3F> \xA8\xBC |1
- <U2010> \xA9\x5C |0
- <U2013> \xA8\x43 |0
- <U2014> \xA1\xAA |0
-@@ -472,6 +475,7 @@
- <U2299> \xA1\xD1 |0
- <U22A5> \xA1\xCD |0
- <U22BF> \xA8\x53 |0
-+<U22EF> \xA1\xAD |1
- <U2312> \xA1\xD0 |0
- <U2460> \xA2\xD9 |0
- <U2461> \xA2\xDA |0
-@@ -696,6 +700,7 @@
- <U3015> \xA1\xB3 |0
- <U3016> \xA1\xBC |0
- <U3017> \xA1\xBD |0
-+<U301C> \xA1\xAB |1
- <U301D> \xA8\x94 |0
- <U301E> \xA8\x95 |0
- <U3021> \xA9\x40 |0
 Index: source/data/mappings/convrtrs.txt
 ===================================================================
 --- source/data/mappings/convrtrs.txt   (revision 259715)
 +++ source/data/mappings/convrtrs.txt   (working copy)
 @@ -292,44 +292,8 @@
  # End of Java-specific, non-Unicode-standard UTF variants.
  
  
 -# On UTF-7:
 -# RFC 2152 (http://www.imc.org/rfc2152) allows to encode some US-ASCII
@@ skipping 124 matching lines @@
 -                        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)
 -# - 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* }
++shift_jis-html
                          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 
 -ibm-943_P130-1999 { UTR22* }
@@ skipping 29 matching lines @@
 -                        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). All the
 +# 3-byte seqeunces in the normative EUC-JP are now decode-only.
-+euc-jp-html5 { UTR22* }
++euc-jp-html
 +                        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* }
@@ skipping 14 matching lines @@
                          csBig5 { IANA WINDOWS }
 @@ -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 }
++# Chrome: HTML5 has big5-hkscs as an alias for big5
++#         TODO(jshin): Decide if Chrome should follow spec. crbug.com/277040
  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 +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 }
@@ skipping 217 matching lines @@
 -ibm-866_P100-1995 { UTR22* }    ibm-866 { IBM* } IBM866 { IANA* MIME* JAVA } cp866 { IANA MIME WINDOWS JAVA* } 866 { IANA JAVA } csIBM866 { IANA JAVA } windows-866 { WINDOWS* } # PC Russian (w/o euro update)
 -ibm-867_P100-1998 { UTR22* }    ibm-867 { IBM* } x-IBM867 { JAVA* } # PC Hebrew (w/ euro update) Updated version of ibm-862
 -ibm-868_P100-1995 { UTR22* }    ibm-868 { IBM* } IBM868 { IANA* MIME* JAVA } CP868 { IANA MIME JAVA* } 868 { JAVA } csIBM868 { IANA } cp-ar { IANA }          # PC Urdu
 -ibm-869_P100-1995 { UTR22* }    ibm-869 { IBM* } IBM869 { IANA* MIME* WINDOWS JAVA } cp869 { IANA MIME JAVA* } 869 { IANA JAVA } cp-gr { IANA JAVA } csIBM869 { IANA JAVA } windows-869 { WINDOWS* } # PC Greek (w/o euro update)
 +# Chrome: only keep ibm-878 for KOI8-R, ibm-1168 for KOI8-RU and ibm-866
  ibm-878_P100-1996 { UTR22* }    ibm-878 { IBM* } KOI8-R { IANA* MIME* WINDOWS JAVA* } koi8 { WINDOWS JAVA } csKOI8R { IANA WINDOWS JAVA } windows-20866 { WINDOWS* } cp878   # Russian internet
 -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)
++ibm866-html   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 +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)
@@ skipping 51 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 +672,25 @@
+@@ -943,322 +672,21 @@
  # 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.
++# Chrome: The encoding standard only supports ISO-2022-JP.
++# Remove ISO-2022-{KR,CN,CN-Ext} and HZ-GB from the alias table.
++# See crbug.com/277037 and https://www.w3.org/Bugs/Public/show_bug.cgi?id=25339
++# about HZ-GB.
  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 }
 -ISO_2022,locale=ja,version=3    JIS7
 -ISO_2022,locale=ja,version=4    JIS8
- ISO_2022,locale=ko,version=0    ISO-2022-KR { IANA* MIME* JAVA* } csISO2022KR { IANA JAVA } # This uses ibm-949
+-ISO_2022,locale=ko,version=0    ISO-2022-KR { IANA* MIME* JAVA* } csISO2022KR { IANA JAVA } # This uses ibm-949
 -ISO_2022,locale=ko,version=1    ibm-25546 { IBM* }
- ISO_2022,locale=zh,version=0    ISO-2022-CN { IANA* JAVA* } csISO2022CN { JAVA } x-ISO-2022-CN-GB { JAVA }
- ISO_2022,locale=zh,version=1    ISO-2022-CN-EXT { IANA* }
+-ISO_2022,locale=zh,version=0    ISO-2022-CN { IANA* JAVA* } csISO2022CN { JAVA } x-ISO-2022-CN-GB { JAVA }
+-ISO_2022,locale=zh,version=1    ISO-2022-CN-EXT { IANA* }
 -ISO_2022,locale=zh,version=2    ISO-2022-CN-CNS x-ISO-2022-CN-CNS { JAVA* }
- HZ                              HZ-GB-2312 { IANA* }
+-HZ                              HZ-GB-2312 { IANA* }
 -x11-compound-text               COMPOUND_TEXT x-compound-text { JAVA* }
  
 -ISCII,version=0         x-ISCII91 { JAVA* } x-iscii-de { WINDOWS } windows-57002 { WINDOWS* } iscii-dev ibm-4902 { IBM* } # ibm-806 contains non-standard box drawing symbols.
 -ISCII,version=1         x-iscii-be { WINDOWS } windows-57003 { WINDOWS* } iscii-bng windows-57006 { WINDOWS } x-iscii-as { WINDOWS } # be is different from as on Windows.
 -ISCII,version=2         x-iscii-pa { WINDOWS } windows-57011 { WINDOWS* } iscii-gur
 -ISCII,version=3         x-iscii-gu { WINDOWS } windows-57010 { WINDOWS* } iscii-guj
 -ISCII,version=4         x-iscii-or { WINDOWS } windows-57007 { WINDOWS* } iscii-ori
 -ISCII,version=5         x-iscii-ta { WINDOWS } windows-57004 { WINDOWS* } iscii-tml
 -ISCII,version=6         x-iscii-te { WINDOWS } windows-57005 { WINDOWS* } iscii-tlg
 -ISCII,version=7         x-iscii-ka { WINDOWS } windows-57008 { WINDOWS* } iscii-knd
@@ skipping 292 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)