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

icu46/patches/converters.patch

 --- source/data/mappings/ucmlocal.mk    1969-12-31 16:00:00.000000000 -0800
-+++ source/data/mappings/ucmlocal.mk    2009-12-02 13:12:20.156521000 -0800
++++ source/data/mappings/ucmlocal.mk    2010-12-21 15:36:19.030397000 -0800
 @@ -0,0 +1,58 @@
 +# Note: A number of encodings are handled with purely algorithmic converters,
 +# without any mapping tables:
 +# US-ASCII, ISO 8859-1, UTF-7/8/16/32, SCSU
 +
 +# Listed here:
 +
 +# * ISO 8859-2..9,10,13,14,15,16
 +#   - 8859-11 table is not included. It's rather treated as a synonym of
 +#     Windows-874
@@ skipping 39 matching lines @@
 +windows-950-2000.ucm ibm-1375_P100-2007.ucm\
 +ibm-943_P15A-2003.ucm google-euc_jp_mod.ucm\
 +windows-949-2000.ucm\
 +windows-874-2000.ucm ibm-874_P100-1995.ucm\
 +macos-0_2-10.2.ucm macos-7_3-10.2.ucm\
 +ibm-878_P100-1996.ucm ibm-1168_P100-2002.ucm\
 +ibm-864_X110-1999.ucm\
 +noop-cns-11643.ucm\
 +noop-gb2312_gl.ucm\
 +noop-iso-ir-165.ucm
---- source/data/mappings/convrtrs.txt   2009-08-04 10:53:44.000000000 -0700
-+++ source/data/mappings/convrtrs.txt   2009-08-27 09:33:30.822570000 -0700
-@@ -345,7 +345,7 @@
+--- source/data/mappings/convrtrs.txt   2010-09-16 22:04:39.000000000 -0700
++++ source/data/mappings/convrtrs.txt   2010-12-21 15:50:41.804761000 -0800
+@@ -360,7 +360,7 @@
      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
  
-@@ -482,15 +482,16 @@
+@@ -505,15 +505,16 @@
                          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* }
-@@ -588,10 +589,6 @@
+@@ -618,10 +619,6 @@
  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
-@@ -604,14 +601,17 @@
+@@ -637,14 +634,20 @@
  # 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 { UTR22* } # 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 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.
- 
- # Here are various interpretations and extentions of Big5
-@@ -645,33 +645,40 @@
+@@ -695,33 +698,40 @@
  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)
@@ skipping 32 matching lines @@
  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
-@@ -720,13 +727,8 @@
+@@ -774,13 +784,8 @@
  # 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
-@@ -738,16 +740,16 @@
+@@ -793,16 +798,16 @@
  # 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
-@@ -756,27 +758,41 @@
-                         ibm-1363 { IBM* }
+@@ -813,15 +818,30 @@
                          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
+                         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 }
-+                        windows-949 { JAVA* WINDOWS }
-+                        KS_C_5601-1987 { WINDOWS* IANA }
++                        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* }
+@@ -830,18 +850,20 @@
+                         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
- 
-@@ -820,7 +836,16 @@
+                         x-IBM874 { JAVA }
+@@ -891,7 +913,16 @@
  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 } # Windows Arabic (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)
 --- source/data/mappings/windows-932-2000.ucm   1969-12-31 16:00:00.000000000 -0800
-+++ source/data/mappings/windows-932-2000.ucm   2009-08-05 13:21:17.750080000 -0700
++++ source/data/mappings/windows-932-2000.ucm   2010-12-21 15:36:19.154409000 -0800
 @@ -0,0 +1,9932 @@
 +# ***************************************************************************
 +# *
 +# *   Copyright (C) 2001-2002, International Business Machines
 +# *   Corporation and others.  All Rights Reserved.
 +# *
 +# ***************************************************************************
 +#
 +# File created on Dec 03 13:49 Pacific Standard Time 2002
 +#
@@ skipping 9914 matching lines @@
 +<UFFE2> \xEE\xF9 |3
 +<UFFE2> \xFA\x54 |3
 +<UFFE3> \x81\x50 |0
 +<UFFE4> \xFA\x55 |0
 +<UFFE4> \xEE\xFA |3
 +<UFFE5> \x81\x8F |0
 +#
 +END CHARMAP
 +#
 --- source/data/mappings/windows-936-2000.ucm   2007-05-09 23:40:31.000000000 -0700
-+++ source/data/mappings/windows-936-2000.ucm   2009-08-05 13:21:17.768078000 -0700
++++ source/data/mappings/windows-936-2000.ucm   2010-12-21 15:36:19.167404000 -0800
 @@ -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
@@ skipping 23 matching lines @@
  <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
 --- source/data/mappings/windows-949-2000.ucm   2003-12-18 15:16:48.000000000 -0800
-+++ source/data/mappings/windows-949-2000.ucm   2009-08-05 13:21:17.783068000 -0700
++++ source/data/mappings/windows-949-2000.ucm   2010-12-21 15:36:19.178396000 -0800
 @@ -37,7 +37,8 @@
  
  # build an extension-only (delta) .cnv file
  # requires the base .cnv file at runtime
 -<icu:base>                    "ibm-1363_P11B-1998"
 +# CHROME : we don't want IBM-1363
 +#<icu:base>                    "ibm-1363_P11B-1998"
  
  # The following was the generated state table.
  # This does not account for unassigned characters
 --- source/data/mappings/windows-950-2000.ucm   2003-12-18 15:16:48.000000000 -0800
-+++ source/data/mappings/windows-950-2000.ucm   2009-08-05 13:21:17.799075000 -0700
++++ source/data/mappings/windows-950-2000.ucm   2010-12-21 15:36:19.189398000 -0800
 @@ -37,7 +37,8 @@
  
  # build an extension-only (delta) .cnv file
  # requires the base .cnv file at runtime
 -<icu:base>                    "ibm-1373_P100-2002"
 +# CHROME : we don't want to include ibm-1373
 +#<icu:base>                    "ibm-1373_P100-2002"
  
  # The following was the generated state table.
  # This does not account for unassigned characters
---- source/data/mappings/ucmebcdic.mk   2007-05-09 23:40:31.000000000 -0700
+--- source/data/mappings/ucmebcdic.mk   2010-03-02 01:46:00.000000000 -0800
 +++ source/data/mappings/ucmebcdic.mk   1969-12-31 16:00:00.000000000 -0800
-@@ -1,27 +0,0 @@
--# Copyright (c) 1999-2007, International Business Machines Corporation and
+@@ -1,29 +0,0 @@
+-# Copyright (c) 1999-2010, International Business Machines Corporation and
 -# others. All Rights Reserved.
 -# A list of EBCDIC UCM's to build
 -# ibm-37 and ibm-1047 are already mentioned in makedata.mak and Makefile.in
 -
 -UCM_SOURCE_EBCDIC = ebcdic-xml-us.ucm\
 -ibm-1025_P100-1995.ucm ibm-1026_P100-1995.ucm ibm-1097_P100-1995.ucm\
 -ibm-1112_P100-1995.ucm ibm-1122_P100-1999.ucm ibm-1130_P100-1997.ucm\
 -ibm-1132_P100-1998.ucm ibm-1137_P100-1999.ucm ibm-1364_P110-2007.ucm\
 -ibm-1371_P100-1999.ucm ibm-1388_P103-2001.ucm ibm-1390_P110-2003.ucm\
 -ibm-1399_P110-2003.ucm ibm-870_P100-1995.ucm ibm-875_P100-1995.ucm\
 -ibm-838_P100-1995.ucm ibm-918_P100-1995.ucm ibm-930_P120-1999.ucm\
 -ibm-933_P110-1995.ucm ibm-935_P110-1999.ucm ibm-937_P110-1999.ucm\
 -ibm-939_P120-1999.ucm ibm-1123_P100-1995.ucm ibm-1140_P100-1997.ucm\
 -ibm-1141_P100-1997.ucm ibm-1142_P100-1997.ucm ibm-1143_P100-1997.ucm\
 -ibm-1144_P100-1997.ucm ibm-1145_P100-1997.ucm ibm-1146_P100-1997.ucm\
 -ibm-1147_P100-1997.ucm ibm-1148_P100-1997.ucm ibm-1149_P100-1997.ucm\
 -ibm-1153_P100-1999.ucm ibm-1154_P100-1999.ucm ibm-1155_P100-1999.ucm\
 -ibm-1156_P100-1999.ucm ibm-1157_P100-1999.ucm ibm-1158_P100-1999.ucm\
 -ibm-1160_P100-1999.ucm ibm-1164_P100-1999.ucm ibm-871_P100-1995.ucm\
 -ibm-12712_P100-1998.ucm ibm-16804_X110-1999.ucm ibm-273_P100-1995.ucm\
 -ibm-277_P100-1995.ucm ibm-278_P100-1995.ucm ibm-280_P100-1995.ucm\
 -ibm-284_P100-1995.ucm ibm-285_P100-1995.ucm ibm-290_P100-1995.ucm\
 -ibm-297_P100-1995.ucm ibm-420_X120-1999.ucm ibm-424_P100-1995.ucm\
 -ibm-4517_P100-2005.ucm ibm-4899_P100-1998.ucm ibm-4971_P100-1999.ucm\
 -ibm-500_P100-1995.ucm ibm-5123_P100-1999.ucm ibm-803_P100-1999.ucm\
 -ibm-8482_P100-1999.ucm ibm-9067_X100-2005.ucm ibm-16684_P110-2003.ucm
+-
+-#UCM_SOURCE_EBCDIC_IGNORE_SISO =
+\ No newline at end of file
 --- source/data/mappings/google-euc_jp_mod.ucm  1969-12-31 16:00:00.000000000 -0800
-+++ source/data/mappings/google-euc_jp_mod.ucm  2009-08-05 13:21:17.850068000 -0700
++++ source/data/mappings/google-euc_jp_mod.ucm  2010-12-21 15:36:37.148907000 -0800
 @@ -0,0 +1,13699 @@
 +# ***************************************************************************
 +# *
 +# *   Copyright (C) 1995-2008, International Business Machines
 +# *   Corporation and others.  All Rights Reserved.
 +# *
 +# ***************************************************************************
 +#
 +# File created by combining Mozilla's EUC-JP, IE7's codepage 51932 and ibm-954
 +#
@@ skipping 13681 matching lines @@
 +<UFF9F> \x8E\xDF |0
 +<UFFE0> \xA1\xF1 |0
 +<UFFE1> \xA1\xF2 |0
 +<UFFE2> \xA2\xCC |0
 +<UFFE2> \xFC\xFB |3
 +<UFFE3> \xA1\xB1 |0
 +<UFFE4> \xFC\xFC |0
 +<UFFE5> \xA1\xEF |0
 +END CHARMAP
 --- source/data/mappings/iso-8859_16-2001.ucm   1969-12-31 16:00:00.000000000 -0800
-+++ source/data/mappings/iso-8859_16-2001.ucm   2009-08-05 13:21:17.854067000 -0700
++++ source/data/mappings/iso-8859_16-2001.ucm   2010-12-21 15:36:37.150883000 -0800
 @@ -0,0 +1,301 @@
 +#
 +#      Name:             ISO/IEC 8859-16:2001 to Unicode
 +#      Unicode version:  3.0
 +#      Table version:    1.0
 +#      Table format:     Format A
 +#      Date:             2001 July 26
 +#      Authors:          Markus Kuhn <http://www.cl.cam.ac.uk/~mgk25/>
 +#
 +#      Copyright (c) 1999-2001 Unicode, Inc.  All Rights reserved.
@@ skipping 282 matching lines @@
 +<U017D> \xB4 |0
 +<U017E> \xB8 |0
 +<U0218> \xAA |0
 +<U0219> \xBA |0
 +<U021A> \xDE |0
 +<U021B> \xFE |0
 +<U201D> \xB5 |0
 +<U201E> \xA5 |0
 +<U20AC> \xA4 |0
 +END CHARMAP
---- source/common/ucnv2022.c    2009-08-07 12:29:02.000000000 -0700
-+++ source/common/ucnv2022.c    2009-12-02 13:24:21.544681000 -0800
+--- source/common/ucnv2022.c    2010-09-08 16:18:15.000000000 -0700
++++ source/common/ucnv2022.c    2010-12-21 15:36:37.178900000 -0800
 @@ -491,7 +491,7 @@
              }
              if(jpCharsetMasks[version]&CSM(GB2312)) {
                  myConverterData->myConverterArray[GB2312] =
 -                    ucnv_loadSharedData("ibm-5478", &stackPieces, &stackArgs, errorCode);   /* gb_2312_80-1 */
 +                    ucnv_loadSharedData("noop-gb2312_gl", &stackPieces, &stackArgs, errorCode);   /* gb_2312_80-1 */
              }
              if(jpCharsetMasks[version]&CSM(KSC5601)) {
                  myConverterData->myConverterArray[KSC5601] =
 @@ -514,7 +514,7 @@
@@ skipping 16 matching lines @@
 -                    ucnv_loadSharedData("iso-ir-165", &stackPieces, &stackArgs, errorCode);
 +                    ucnv_loadSharedData("noop-iso-ir-165", &stackPieces, &stackArgs, errorCode);
              }
              myConverterData->myConverterArray[CNS_11643] =
 -                ucnv_loadSharedData("cns-11643-1992", &stackPieces, &stackArgs, errorCode);
 +                ucnv_loadSharedData("noop-cns-11643", &stackPieces, &stackArgs, errorCode);
  
  
              /* set the function pointers to appropriate funtions */
 --- source/data/mappings/noop-cns-11643.ucm     1969-12-31 16:00:00.000000000 -0800
-+++ source/data/mappings/noop-cns-11643.ucm     2009-12-02 15:38:15.114703000 -0800
++++ source/data/mappings/noop-cns-11643.ucm     2010-12-21 15:36:37.182878000 -0800
 @@ -0,0 +1,31 @@
 +# *******************************************************************************
 +# *
 +# *   Copyright (C) 2009, International Business Machines
 +# *   Corporation and others.  All Rights Reserved.
 +# *
 +# *******************************************************************************
 +#
 +# File created on   Dec 2, 2009
 +#
@@ skipping 13 matching lines @@
 +# (state 0) lead byte, selects the CNS plane (0x80 + plane number)
 +<icu:state>           81-90:1
 +
 +# (1..2) middle and trail bytes for valid but unassigned sequences
 +<icu:state>           21-7e:2
 +<icu:state>           21-7e.u
 +
 +CHARMAP
 +END CHARMAP
 --- source/data/mappings/noop-gb2312_gl.ucm     1969-12-31 16:00:00.000000000 -0800
-+++ source/data/mappings/noop-gb2312_gl.ucm     2009-12-02 15:38:36.641528000 -0800
++++ source/data/mappings/noop-gb2312_gl.ucm     2010-12-21 15:36:37.183880000 -0800
 @@ -0,0 +1,32 @@
 +#________________________________________________________________________
 +#
 +# (C) COPYRIGHT International Business Machines Corp. 2009
 +#     All Rights Reserved
 +#
 +#________________________________________________________________________
 +#
 +#       Name:    "Fake" Unicode to ISO-IR-165 table
 +#       Date:    December 2, 2009
@@ skipping 14 matching lines @@
 +<icu:charsetFamily>           "ASCII"
 +<icu:alias>                   "ibm-5478_STD"
 +
 +<icu:state>                   0-20:2, 21-7e:1, 7f-ff:2
 +<icu:state>                   21-7e.u
 +<icu:state>
 +
 +CHARMAP
 +END CHARMAP
 --- source/data/mappings/noop-iso-ir-165.ucm    1969-12-31 16:00:00.000000000 -0800
-+++ source/data/mappings/noop-iso-ir-165.ucm    2009-12-02 15:38:06.317529000 -0800
++++ source/data/mappings/noop-iso-ir-165.ucm    2010-12-21 15:36:37.185880000 -0800
 @@ -0,0 +1,29 @@
 +#________________________________________________________________________
 +#
 +# (C) COPYRIGHT International Business Machines Corp. 2009
 +#     All Rights Reserved
 +#
 +#________________________________________________________________________
 +#
 +#       Name:    "Fake" Unicode to ISO-IR-165 table
 +#       Date:    December 2, 2009
@@ skipping 10 matching lines @@
 +<mb_cur_max>            2
 +<mb_cur_min>            2
 +<uconv_class>           "MBCS"
 +<subchar>               \x7e\x7e
 +<icu:state>             0-20:2, 21-7e:1, 7f-ff:2
 +<icu:state>             21-7e.u
 +<icu:state>
 +#
 +CHARMAP
 +END CHARMAP