From d952205f32c2d15d5a59336396e84cc26a5db9f2 Mon Sep 17 00:00:00 2001 From: George Rhoten Date: Sat, 15 Nov 2003 03:40:13 +0000 Subject: [PATCH] ICU-3346 Fix some aliases based on the last update X-SVN-Rev: 13738 --- icu4c/source/data/mappings/convrtrs.txt | 41 ++++++++++++++----------- 1 file changed, 23 insertions(+), 18 deletions(-) diff --git a/icu4c/source/data/mappings/convrtrs.txt b/icu4c/source/data/mappings/convrtrs.txt index 3c9c1cdb1ec..a539de7294b 100644 --- a/icu4c/source/data/mappings/convrtrs.txt +++ b/icu4c/source/data/mappings/convrtrs.txt @@ -14,6 +14,9 @@ # Please be friendly to the rest of us that edit this table by # keeping this table free of tabs. +# If this table looks very confusing, a much easier to understand view can +# be found at this demo: http://oss.software.ibm.com/cgi-bin/icu/convexp + # This is an alias file used by the character set converter. # # Format: @@ -88,7 +91,7 @@ JAVA # Source: Sun JDK. Alias name case is ignored, but dashes are not ignored. # GLIBC # AIX - # DB2 + # DB2 # SOLARIS # APPLE # HPUX @@ -549,11 +552,14 @@ ibm-949_P11A-1999 { UTR22* } # ibm-970 is almost a subset of ibm-1363. # Java, Solaris and AIX use euc-kr to also mean ksc5601. ibm-970_P110-1995 { UTR22* } - ibm-970 { IBM* } + ibm-970 { IBM* JAVA } EUC-KR { IANA* MIME* WINDOWS JAVA* } + KS_C_5601-1987 { JAVA } windows-51949 { WINDOWS* } - ibm-eucKR { JAVA } csEUCKR { IANA WINDOWS } # x-euc-kr is also a MIME name + ibm-eucKR { JAVA } + KSC_5601 { JAVA } # Needed by iso-2022 + 5601 { JAVA } ibm-970_VPUA # ibm-971 is almost the set of DBCS mappings of ibm-970 @@ -576,38 +582,37 @@ ibm-1363_P11B-1998 { UTR22* } # 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 + windows-949-2000 { UTR22* } windows-949 { JAVA* WINDOWS* } - KS_C_5601-1987 { WINDOWS JAVA } + KS_C_5601-1987 { WINDOWS } KS_C_5601-1989 { WINDOWS } KSC_5601 { WINDOWS } # Needed by iso-2022 csKSC56011987 { WINDOWS } korean { WINDOWS } iso-ir-149 { WINDOWS } - 5601 { JAVA } - # TODO re-check Java aliases here - -ibm-1363_P110-1997 { UTR22* } # Korean KSC MBCS with \ <-> Won mapping - ibm-1363 { IBM* } - ibm-1363_VASCII_VSUB_VPUA + ms949 { JAVA } ibm-1162_P100-1999 { UTR22* } # Thai (w/ euro update) ibm-1162 { IBM* } - TIS-620 { IANA* } - # tis620.2533 { JAVA } -- TODO check on this one - eucTH # eucTH is an unusual alias from Solaris. eucTH has fewer mappings than TIS620 - # iso-8859-11 { WINDOWS } # 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* } + ibm-874 { IBM* JAVA } ibm-9066 { IBM } # Yes ibm-874 == ibm-9066. ibm-1161 has the euro update. - 874 { JAVA } cp874 { JAVA* } + TIS-620 { IANA* JAVA } # This actually separate from ibm-874, which is similar to this table + tis620.2533 { JAVA } # This 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 cp9066 windows-874-2000 { UTR22* } # Thai (w/ euro update) TIS-620 { WINDOWS } windows-874 { JAVA* WINDOWS* } + MS874 { JAVA } + # iso-8859-11 { WINDOWS } # iso-8859-11 is similar to TIS-620. ibm-13162 is a closer match. # Platform codepages ibm-437_P100-1995 { UTR22* } ibm-437 { IBM* } IBM437 { IANA* WINDOWS JAVA } cp437 { IANA WINDOWS JAVA* } 437 { IANA WINDOWS JAVA } csPC8CodePage437 { IANA JAVA } windows-437 { WINDOWS* } # PC US @@ -733,7 +738,7 @@ ibm-939_P120-1999 { UTR22* } # EBCDIC_STATEFUL Latin-Kanji Host Mixed. ibm-1025_P100-1995 { UTR22* } ibm-1025 { IBM* JAVA } cp1025 { JAVA* } 1025 { JAVA } # EBCDIC Cyrillic ibm-1026_P100-1995 { UTR22* } ibm-1026 { IBM* JAVA } IBM1026 { IANA* } CP1026 { IANA JAVA* } csIBM1026 { IANA } 1026 { JAVA } # EBCDIC Turkey ibm-1047_P100-1995 { UTR22* } ibm-1047 { IBM* } IBM1047 { IANA* } cpibm1047 # EBCDIC Open systems Latin1 -ibm-1097_P100-1995 { UTR22* } ibm-1097 { IBM* JAVA } cp1097 { JAVA* } 1097 { JAVA } ibm-1097_VPUA # EBCDIC Farsi +ibm-1097_P100-1995 { UTR22* } ibm-1097 { IBM* JAVA } cp1097 { JAVA* } 1097 { JAVA } # EBCDIC Farsi ibm-1112_P100-1995 { UTR22* } ibm-1112 { IBM* JAVA } cp1112 { JAVA* } 1112 { JAVA } # EBCDIC Baltic ibm-1122_P100-1999 { UTR22* } ibm-1122 { IBM* JAVA } cp1122 { JAVA* } 1122 { JAVA } # EBCDIC Estonia ibm-1123_P100-1995 { UTR22* } ibm-1123 { IBM* JAVA } cp1123 { JAVA* } 1123 { JAVA } cpibm1123 # EBCDIC Cyrillic Ukraine @@ -764,6 +769,7 @@ ibm-1371_P100-1999 { UTR22* } ibm-1371 { IBM* } cpibm1371 # Taiwan ibm-1388_P103-2001 { UTR22* } ibm-1388 { IBM* } ibm-9580 { IBM } # S-Ch DBCS-Host Data GBK EBCDIC_STATEFUL. Yes ibm-9580 is an alias. ibm-1390_P110-2003 { UTR22* } ibm-1390 { IBM* } cpibm1390 # Japan EBCDIC MIXED (JIS X 0213) ibm-1399_P110-2003 { UTR22* } ibm-1399 { IBM* } # Host MBCS (Latin-Kanji) (JIS X 0213) +ibm-16684_P110-2003 { UTR22* } ibm-16684 { IBM* } # DBCS Jis + Roman Jis Host. This is the DBCS portion of ibm-1390 and ibm-1399 (JIS X 0213) ibm-4899_P100-1998 { UTR22* } ibm-4899 { IBM* } cpibm4899 # Old EBCDIC Hebrew ibm-4971_P100-1999 { UTR22* } ibm-4971 { IBM* } cpibm4971 # EBCDIC Greek ibm-12712_P100-1998 { UTR22* } ibm-12712 { IBM* } cpibm12712 ebcdic-he # EBCDIC Hebrew (new sheqel, control charaters update) @@ -774,7 +780,6 @@ ibm-16804_X110-1999 { UTR22* } ibm-16804 { IBM* } cpibm16804 ebcdic-ar # EBCDIC ibm-1137_P100-1999 { UTR22* } ibm-1137 { IBM* } # Devanagari EBCDIC (based on Unicode character set) ibm-5123_P100-1999 { UTR22* } ibm-5123 { IBM* } # Host Roman Jis. Euro update of ibm-1027 ibm-8482_P100-1999 { UTR22* } ibm-8482 { IBM* } # host SBCS (Katakana). Euro update of ibm-290 -ibm-16684_P110-2003 { UTR22* } ibm-16684 { IBM* } # DBCS Jis + Roman Jis Host. This is the DBCS portion of ibm-1390 and ibm-1399 (JIS X 0213) # EBCDIC codepages for S/390, with LF and NL codes swapped