AuroraMiddleware/scuffed-code
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

ICU-306 eliminate ambiguities (1 alias->n converters) from alias table

Browse Source 
X-SVN-Rev: 1958
This commit is contained in:
Alan Liu 2000-07-19 23:07:13 +00:00
parent 1ab1e529c5
commit deb8e9224e
2 changed files with 42 additions and 38 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

40
icu4c/data/convrtrs.txt
View File

@ -34,7 +34,9 @@
# Currently, the IANA list is at
# http://www.isi.edu/in-notes/iana/assignments/character-sets
# Name matching is case-insensitive.
# Name matching is case-insensitive. The characters '-' and '_'
# (dash and underscore) are ignored. Space (' ') is also ignored,
# but no names in this file can contain spaces.
# However, the names in the left column are directly file names
# or names of algorithmic converters, and their case must not
# be changed - or else code and/or file names must also be changed.
@ -45,7 +47,7 @@ UTF16_BigEndian utf-16be
UTF16_LittleEndian utf-16le
UTF16_PlatformEndian iso-10646-ucs-2 csUnicode utf16 utf-16 ibm-1200 ibm1200 cp1200 ucs-2
UTF16_OppositeEndian
LATIN_1 iso-8859-1 iso_8859-1 ibm-819 ibm819 cp819 latin1 latin-1 8859-1 csisolatin1 iso-ir-100 iso_8859-1:1978 cp367 ibm367 iso-8859-1:1987 l1 iso_8859_1 ansi_x3.110-1983 iso8859-1 #!!!!! There's whole lot of names for this
LATIN_1 iso-8859-1 iso_8859-1 ibm-819 ibm819 cp819 latin1 latin-1 8859-1 csisolatin1 iso-ir-100 iso_8859-1:1978 iso-8859-1:1987 l1 iso_8859_1 ansi_x3.110-1983 iso8859-1 #!!!!! There's whole lot of names for this
ISO_2022 iso-2022 2022 cp2022 iso2022 iso_2022
LMBCS-1 lmbcs
LMBCS-2
@ -62,7 +64,7 @@ LMBCS-19
# Table-based
ibm-367 usascii ascii ascii-7 us-ascii usascii ansi_x3.4-1968 ansi_x3.4-1986 iso_646.irv:1991 iso646-us us csASCII 646
ibm-367 usascii ascii ascii-7 us-ascii usascii ansi_x3.4-1968 ansi_x3.4-1986 iso_646.irv:1991 iso646-us us csASCII 646 cp367
# Special mapping for S/390 new line characters
ebcdic-xml-us
@ -73,14 +75,15 @@ ibm-913 iso-8859-3 iso_8859-3 iso8859-3 latin3 cp913 ibm913 8859
ibm-914 iso-8859-4 iso_8859-4 iso8859-4 latin4 cp914 ibm914 8859-4 csisolatin4 iso-ir-110 iso_8859-4:1988 l4 # Baltic
ibm-915 iso-8859-5 iso_8859-5 iso8859-5 cyrillic cp915 ibm915 8859-5 csisolatincyrillic iso-ir-144 iso_8859-5:1988 # Cyrillic
ibm-1089 iso-8859-6 iso_8859-6 iso8859-6 arabic cp1089 ibm1089 8859-6 csisolatinarabic iso-ir-127 iso_8859-6:1987 ecma-114 asmo-708 # Arabic
ibm-4909 cp813 iso-8859-7 iso_8859-7 iso8859-7 ibm813 cp813 greek greek8 elot_928 ecma-118 8859-7 csisolatingreek iso-ir-126 iso_8859-7:1987 # ISO Greek (w/ euro update)
ibm-813 # same as 4909 (w/o euro update)
ibm-4909 iso-8859-7 iso_8859-7 iso8859-7 greek greek8 elot_928 ecma-118 8859-7 csisolatingreek iso-ir-126 iso_8859-7:1987 # ISO Greek (w/ euro update)
ibm-813 cp813 ibm813 # same as 4909 (w/o euro update)
ibm-916 iso-8859-8 iso_8859-8 iso8859-8 hebrew cp916 ibm916 8859-8 csisolatinhebrew iso-ir-138 iso_8859-8:1988 # hebrew iso-8859-8i - typo?
ibm-920 iso-8859-9 iso_8859-9 iso8859-9 ECMA-128 latin5 cp920 ibm920 8859-9 csisolatin5 iso-ir-148 l5 # Turkish
ibm-923 iso-8859-15 iso_8859-15 iso8859-15 latin9 cp923 ibm923 8859-15 latin0 csisolatin0 csisolatin9 # Latin 9
ibm-1252 windows-1252 cp1252 ibm-1004 cp1004 # Windows Latin 1 We don't have an ibm-5348, so this is a best possible match
ibm-1252 windows-1252 cp1252 # Windows Latin 1 We don't have an ibm-5348, so this is a best possible match
ibm-1004 cp1004 # Previously an alias of 1252
ibm-943 shift_jis csWindows31J sjis shiftjis shift-jis ibm943 cp943 cp932 ms_kanji csshiftjis windows-31j x-sjis # japanese. Unicode name is \u30b7\u30d5\u30c8\u7b26\u53f7\u5316\u8868\u73fe Iana says that Windows-31J is an extension to csshiftjis ibm-932 removed
ibm-949 KS_C_5601-1987 iso-ir-149 KS_C_5601-1989 csKSC56011987 korean ibm949 ksc-5601 ksc_5601 johab ks_x_1001:1992 # KSC-5601-1992, korean
ibm-949 KS_C_5601-1987 iso-ir-149 KS_C_5601-1989 csKSC56011987 korean ibm949 ksc-5601 ksc_5601 johab ks_x_1001:1992 ksc # KSC-5601-1992, korean
ibm-1370 Big5 csBig5 big-5 x-big5 cp950 # Taiwan Big-5 (w/ euro update)
ibm-950 # Taiwan Big-5
ibm-1386 gb_2312-80 iso-ir-58 csISO58GB231280 gb2312-80 gbk chinese gb ibm1386 gb2312 gb2312-1980 cp936 zh_cn # Chinese GBK removed
@ -100,27 +103,27 @@ ibm-437 ibm437 cp437 csPC8CodePage437 437 # PC US
ibm-850 IBM850 cp850 850 csPC850Multilingual # PC latin1
ibm-851 IBM851 cp851 851 csPC851 # PC DOS Greek (no euro)
ibm-858 ibm858 cp858 # PC latin1 with Euro cp850 removed
ibm-9044 IBM852 852 csPCp852 cp852 # PC latin2 (w/ euro update) #where should the names go here or below - inconsistency!!!
ibm-852 # PC latin2 (w/o euro update)
ibm-872 IBM855 855 csIBM855 cp855 # PC cyrillic (w/ euro update) #where should the names go here or below - inconsistency!!!
ibm-855 # PC cyrillic (w/o euro update)
ibm-9044 # PC latin2 (w/ euro update) #where should the names go here or below - inconsistency!!!
ibm-852 IBM852 852 csPCp852 cp852 # PC latin2 (w/o euro update)
ibm-872 # PC cyrillic (w/ euro update) #where should the names go here or below - inconsistency!!!
ibm-855 IBM855 855 csIBM855 cp855 # PC cyrillic (w/o euro update)
ibm-856 ibm856 cp856 # PC Hebrew (old)
ibm-9049 IBM857 857 csIBM857 cp857 # PC Latin 5 (Turkish) (w/ euro update) #where should the names go here or below - inconsistency!!!
ibm-857 # PC Latin 5 (w/o euro update)
ibm-9049 # PC Latin 5 (Turkish) (w/ euro update) #where should the names go here or below - inconsistency!!!
ibm-857 IBM857 857 csIBM857 cp857 # PC Latin 5 (w/o euro update)
ibm-859 ibm859 cp859 # PC Latin 9 (w/ euro update)
ibm-860 ibm860 cp860 860 csIBM860 # PC Portugal
ibm-861 ibm861 cp861 861 cp-is csIBM861 # PC Iceland
ibm-867 ibm867 cp867 862 cp862 cspc862latinhebrew # PC Hebrew (w/ euro update) #where should the names go here or below - inconsistency!!!
ibm-862 IBM862 # PC Hebrew (w/o euro update)
ibm-863 ibm863 cp863 863 csIBM863 # PC Canadian French
ibm-17248 IBM864 cp864 csIBM864 # PC Arabic (w/ euro update) #where should the names go here or below - inconsistency!!!
ibm-864 # PC Arabic (w/o euro update)
ibm-17248 # PC Arabic (w/ euro update) #where should the names go here or below - inconsistency!!!
ibm-864 IBM864 cp864 csIBM864 # PC Arabic (w/o euro update)
ibm-865 ibm865 cp865 865 csIBM865 # PC Nordic
ibm-808 cp866 866 csIBM866 # PC Russian (w/ euro update) #where should the names go here or below - inconsistency!!! put IBM866 cp866 866 csIBM866 down
ibm-866 IBM866 # PC Russian (w/o euro update) added IBM866 cp866 866 csIBM866
ibm-868 ibm868 cp868 cp-ar csIBM868 # PC Urdu
ibm-9061 IBM869 869 cp-gr csIBM869 cp869 # PC Greek (w/ euro update)
ibm-869 # PC Greek (w/o euro update)
ibm-9061 cp-gr # PC Greek (w/ euro update)
ibm-869 IBM869 869 csIBM869 cp869 # PC Greek (w/o euro update)
ibm-878 koi8-r ibm878 cp878 koi8 cskoi8r # Russian internet
ibm-901 cp921 # PC Baltic (w/ euro update) moved cp921 down
ibm-921 # PC Baltic (w/o euro update) from above
@ -163,7 +166,7 @@ ibm-5104 cp1008 # 8-bit Arabic (w/ euro update)
ibm-9238 cp1046 # PC Arabic Extended (w/ euro update)
#ibm-1161 cp9066 # PC Thailand (IBM "version) (w/ euro update)
ibm-1362 cp1362 # Korean Windows DBCS (w/ euro update)
ibm-1363 cp1363 cp949 ksc korean # Korean KSC Korean Windows MBCS (w/ euro update)
ibm-1363 cp1363 cp949 # Korean KSC Korean Windows MBCS (w/ euro update)
ibm-5210 cp1114 # PC SBCS Big-5 (w/ euro update)
ibm-21427 cp947 # PC DBCS Big-5 (w/ euro update)
@ -223,7 +226,6 @@ ibm-1364 cp1364 # Korean Host Mixed
ibm-8482 # host SBCS (Katakana)
ibm-4899 cpibm4899 # Old EBCDIC Hebrew
ibm-4971 cp875 cpibm4971 # EBCDIC Greek
ibm-1159 cp28709 # SBCS T-Ch Host
ibm-9027 # DBCS T-Ch Host
ibm-5123 cp1027 # Host Roman Jis
ibm-12712 cpibm12712 ibm12712 ebcdic-he # EBCDIC Hebrew (new sheqel, control charaters update)

40
icu4c/source/data/mappings/convrtrs.txt
View File

@ -34,7 +34,9 @@
# Currently, the IANA list is at
# http://www.isi.edu/in-notes/iana/assignments/character-sets
# Name matching is case-insensitive.
# Name matching is case-insensitive. The characters '-' and '_'
# (dash and underscore) are ignored. Space (' ') is also ignored,
# but no names in this file can contain spaces.
# However, the names in the left column are directly file names
# or names of algorithmic converters, and their case must not
# be changed - or else code and/or file names must also be changed.
@ -45,7 +47,7 @@ UTF16_BigEndian utf-16be
UTF16_LittleEndian utf-16le
UTF16_PlatformEndian iso-10646-ucs-2 csUnicode utf16 utf-16 ibm-1200 ibm1200 cp1200 ucs-2
UTF16_OppositeEndian
LATIN_1 iso-8859-1 iso_8859-1 ibm-819 ibm819 cp819 latin1 latin-1 8859-1 csisolatin1 iso-ir-100 iso_8859-1:1978 cp367 ibm367 iso-8859-1:1987 l1 iso_8859_1 ansi_x3.110-1983 iso8859-1 #!!!!! There's whole lot of names for this
LATIN_1 iso-8859-1 iso_8859-1 ibm-819 ibm819 cp819 latin1 latin-1 8859-1 csisolatin1 iso-ir-100 iso_8859-1:1978 iso-8859-1:1987 l1 iso_8859_1 ansi_x3.110-1983 iso8859-1 #!!!!! There's whole lot of names for this
ISO_2022 iso-2022 2022 cp2022 iso2022 iso_2022
LMBCS-1 lmbcs
LMBCS-2
@ -62,7 +64,7 @@ LMBCS-19
# Table-based
ibm-367 usascii ascii ascii-7 us-ascii usascii ansi_x3.4-1968 ansi_x3.4-1986 iso_646.irv:1991 iso646-us us csASCII 646
ibm-367 usascii ascii ascii-7 us-ascii usascii ansi_x3.4-1968 ansi_x3.4-1986 iso_646.irv:1991 iso646-us us csASCII 646 cp367
# Special mapping for S/390 new line characters
ebcdic-xml-us
@ -73,14 +75,15 @@ ibm-913 iso-8859-3 iso_8859-3 iso8859-3 latin3 cp913 ibm913 8859
ibm-914 iso-8859-4 iso_8859-4 iso8859-4 latin4 cp914 ibm914 8859-4 csisolatin4 iso-ir-110 iso_8859-4:1988 l4 # Baltic
ibm-915 iso-8859-5 iso_8859-5 iso8859-5 cyrillic cp915 ibm915 8859-5 csisolatincyrillic iso-ir-144 iso_8859-5:1988 # Cyrillic
ibm-1089 iso-8859-6 iso_8859-6 iso8859-6 arabic cp1089 ibm1089 8859-6 csisolatinarabic iso-ir-127 iso_8859-6:1987 ecma-114 asmo-708 # Arabic
ibm-4909 cp813 iso-8859-7 iso_8859-7 iso8859-7 ibm813 cp813 greek greek8 elot_928 ecma-118 8859-7 csisolatingreek iso-ir-126 iso_8859-7:1987 # ISO Greek (w/ euro update)
ibm-813 # same as 4909 (w/o euro update)
ibm-4909 iso-8859-7 iso_8859-7 iso8859-7 greek greek8 elot_928 ecma-118 8859-7 csisolatingreek iso-ir-126 iso_8859-7:1987 # ISO Greek (w/ euro update)
ibm-813 cp813 ibm813 # same as 4909 (w/o euro update)
ibm-916 iso-8859-8 iso_8859-8 iso8859-8 hebrew cp916 ibm916 8859-8 csisolatinhebrew iso-ir-138 iso_8859-8:1988 # hebrew iso-8859-8i - typo?
ibm-920 iso-8859-9 iso_8859-9 iso8859-9 ECMA-128 latin5 cp920 ibm920 8859-9 csisolatin5 iso-ir-148 l5 # Turkish
ibm-923 iso-8859-15 iso_8859-15 iso8859-15 latin9 cp923 ibm923 8859-15 latin0 csisolatin0 csisolatin9 # Latin 9
ibm-1252 windows-1252 cp1252 ibm-1004 cp1004 # Windows Latin 1 We don't have an ibm-5348, so this is a best possible match
ibm-1252 windows-1252 cp1252 # Windows Latin 1 We don't have an ibm-5348, so this is a best possible match
ibm-1004 cp1004 # Previously an alias of 1252
ibm-943 shift_jis csWindows31J sjis shiftjis shift-jis ibm943 cp943 cp932 ms_kanji csshiftjis windows-31j x-sjis # japanese. Unicode name is \u30b7\u30d5\u30c8\u7b26\u53f7\u5316\u8868\u73fe Iana says that Windows-31J is an extension to csshiftjis ibm-932 removed
ibm-949 KS_C_5601-1987 iso-ir-149 KS_C_5601-1989 csKSC56011987 korean ibm949 ksc-5601 ksc_5601 johab ks_x_1001:1992 # KSC-5601-1992, korean
ibm-949 KS_C_5601-1987 iso-ir-149 KS_C_5601-1989 csKSC56011987 korean ibm949 ksc-5601 ksc_5601 johab ks_x_1001:1992 ksc # KSC-5601-1992, korean
ibm-1370 Big5 csBig5 big-5 x-big5 cp950 # Taiwan Big-5 (w/ euro update)
ibm-950 # Taiwan Big-5
ibm-1386 gb_2312-80 iso-ir-58 csISO58GB231280 gb2312-80 gbk chinese gb ibm1386 gb2312 gb2312-1980 cp936 zh_cn # Chinese GBK removed
@ -100,27 +103,27 @@ ibm-437 ibm437 cp437 csPC8CodePage437 437 # PC US
ibm-850 IBM850 cp850 850 csPC850Multilingual # PC latin1
ibm-851 IBM851 cp851 851 csPC851 # PC DOS Greek (no euro)
ibm-858 ibm858 cp858 # PC latin1 with Euro cp850 removed
ibm-9044 IBM852 852 csPCp852 cp852 # PC latin2 (w/ euro update) #where should the names go here or below - inconsistency!!!
ibm-852 # PC latin2 (w/o euro update)
ibm-872 IBM855 855 csIBM855 cp855 # PC cyrillic (w/ euro update) #where should the names go here or below - inconsistency!!!
ibm-855 # PC cyrillic (w/o euro update)
ibm-9044 # PC latin2 (w/ euro update) #where should the names go here or below - inconsistency!!!
ibm-852 IBM852 852 csPCp852 cp852 # PC latin2 (w/o euro update)
ibm-872 # PC cyrillic (w/ euro update) #where should the names go here or below - inconsistency!!!
ibm-855 IBM855 855 csIBM855 cp855 # PC cyrillic (w/o euro update)
ibm-856 ibm856 cp856 # PC Hebrew (old)
ibm-9049 IBM857 857 csIBM857 cp857 # PC Latin 5 (Turkish) (w/ euro update) #where should the names go here or below - inconsistency!!!
ibm-857 # PC Latin 5 (w/o euro update)
ibm-9049 # PC Latin 5 (Turkish) (w/ euro update) #where should the names go here or below - inconsistency!!!
ibm-857 IBM857 857 csIBM857 cp857 # PC Latin 5 (w/o euro update)
ibm-859 ibm859 cp859 # PC Latin 9 (w/ euro update)
ibm-860 ibm860 cp860 860 csIBM860 # PC Portugal
ibm-861 ibm861 cp861 861 cp-is csIBM861 # PC Iceland
ibm-867 ibm867 cp867 862 cp862 cspc862latinhebrew # PC Hebrew (w/ euro update) #where should the names go here or below - inconsistency!!!
ibm-862 IBM862 # PC Hebrew (w/o euro update)
ibm-863 ibm863 cp863 863 csIBM863 # PC Canadian French
ibm-17248 IBM864 cp864 csIBM864 # PC Arabic (w/ euro update) #where should the names go here or below - inconsistency!!!
ibm-864 # PC Arabic (w/o euro update)
ibm-17248 # PC Arabic (w/ euro update) #where should the names go here or below - inconsistency!!!
ibm-864 IBM864 cp864 csIBM864 # PC Arabic (w/o euro update)
ibm-865 ibm865 cp865 865 csIBM865 # PC Nordic
ibm-808 cp866 866 csIBM866 # PC Russian (w/ euro update) #where should the names go here or below - inconsistency!!! put IBM866 cp866 866 csIBM866 down
ibm-866 IBM866 # PC Russian (w/o euro update) added IBM866 cp866 866 csIBM866
ibm-868 ibm868 cp868 cp-ar csIBM868 # PC Urdu
ibm-9061 IBM869 869 cp-gr csIBM869 cp869 # PC Greek (w/ euro update)
ibm-869 # PC Greek (w/o euro update)
ibm-9061 cp-gr # PC Greek (w/ euro update)
ibm-869 IBM869 869 csIBM869 cp869 # PC Greek (w/o euro update)
ibm-878 koi8-r ibm878 cp878 koi8 cskoi8r # Russian internet
ibm-901 cp921 # PC Baltic (w/ euro update) moved cp921 down
ibm-921 # PC Baltic (w/o euro update) from above
@ -163,7 +166,7 @@ ibm-5104 cp1008 # 8-bit Arabic (w/ euro update)
ibm-9238 cp1046 # PC Arabic Extended (w/ euro update)
#ibm-1161 cp9066 # PC Thailand (IBM "version) (w/ euro update)
ibm-1362 cp1362 # Korean Windows DBCS (w/ euro update)
ibm-1363 cp1363 cp949 ksc korean # Korean KSC Korean Windows MBCS (w/ euro update)
ibm-1363 cp1363 cp949 # Korean KSC Korean Windows MBCS (w/ euro update)
ibm-5210 cp1114 # PC SBCS Big-5 (w/ euro update)
ibm-21427 cp947 # PC DBCS Big-5 (w/ euro update)
@ -223,7 +226,6 @@ ibm-1364 cp1364 # Korean Host Mixed
ibm-8482 # host SBCS (Katakana)
ibm-4899 cpibm4899 # Old EBCDIC Hebrew
ibm-4971 cp875 cpibm4971 # EBCDIC Greek
ibm-1159 cp28709 # SBCS T-Ch Host
ibm-9027 # DBCS T-Ch Host
ibm-5123 cp1027 # Host Roman Jis
ibm-12712 cpibm12712 ibm12712 ebcdic-he # EBCDIC Hebrew (new sheqel, control charaters update)