ICU-5580 Update alias table to resolve problem with java canonical names and add test to ICU4J.

X-SVN-Rev: 23716
This commit is contained in:
Michael Ow 2008-03-31 22:13:59 +00:00
parent a8fa35fe9c
commit abd7539f7f
3 changed files with 44 additions and 21 deletions
icu4c/source/data/mappings
icu4j/src/com/ibm/icu
dev/test/charset
impl/data

View File

@ -285,7 +285,7 @@ US-ASCII { MIME* IANA JAVA WINDOWS }
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 { IANA* } ibm-1392 { IBM* } windows-54936 { WINDOWS* } GB18030 { MIME* }
# Table-based interchange codepages
@ -677,12 +677,12 @@ 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 { MIME* IANA } # Needed by iso-2022
KSC_5601 { MIME IANA }
csKSC56011987 { IANA }
korean { IANA }
iso-ir-149 { IANA }
cp1363 { MIME* }
5601
cp1363
ksc
windows-949 # Alternate mapping. Leave untagged. This is the IBM interpretation of a Windows codepage.
ibm-1363_VSUB_VPUA
@ -726,27 +726,27 @@ ibm-437_P100-1995 { UTR22* } ibm-437 { IBM* } IBM437 { IANA* WINDOWS JAVA } c
ibm-720_P100-1997 { UTR22* } ibm-720 { IBM* } windows-720 { WINDOWS* } DOS-720 { WINDOWS } # PC Arabic
ibm-737_P100-1997 { UTR22* } ibm-737 { IBM* } IBM737 { WINDOWS JAVA } cp737 { JAVA* } windows-737 { WINDOWS* } 737 { JAVA } # PC Greek
ibm-775_P100-1996 { UTR22* } ibm-775 { IBM* } IBM775 { IANA* WINDOWS JAVA } cp775 { IANA WINDOWS JAVA* } csPC775Baltic { IANA } windows-775 { WINDOWS* } 775 { JAVA } # PC Baltic
ibm-850_P100-1995 { UTR22* } ibm-850 { IBM* } IBM850 { IANA* WINDOWS JAVA } cp850 { IANA MIME* WINDOWS JAVA* } 850 { IANA JAVA } csPC850Multilingual { IANA JAVA } windows-850 { WINDOWS* } # PC latin1
ibm-850_P100-1995 { UTR22* } ibm-850 { IBM* } IBM850 { IANA* MIME* WINDOWS JAVA } cp850 { IANA MIME WINDOWS JAVA* } 850 { IANA JAVA } csPC850Multilingual { IANA JAVA } windows-850 { WINDOWS* } # PC latin1
ibm-851_P100-1995 { UTR22* } ibm-851 { IBM* } IBM851 { IANA* } cp851 { IANA MIME* } 851 { IANA } csPC851 { IANA } # PC DOS Greek (w/o euro)
ibm-852_P100-1995 { UTR22* } ibm-852 { IBM* } IBM852 { IANA* WINDOWS JAVA } cp852 { IANA WINDOWS JAVA* } 852 { IANA WINDOWS JAVA } csPCp852 { IANA JAVA } windows-852 { WINDOWS* } # PC latin2 (w/o euro update)
ibm-855_P100-1995 { UTR22* } ibm-855 { IBM* } IBM855 { IANA* JAVA } cp855 { IANA JAVA* } 855 { IANA } csIBM855 { IANA } csPCp855 { JAVA } windows-855 { WINDOWS* } # PC cyrillic (w/o euro update)
ibm-856_P100-1995 { UTR22* } ibm-856 { IBM* } IBM856 { JAVA } cp856 { MIME* JAVA* } 856 { JAVA } # PC Hebrew implicit order
ibm-857_P100-1995 { UTR22* } ibm-857 { IBM* } IBM857 { IANA* WINDOWS JAVA } cp857 { IANA MIME* JAVA* } 857 { IANA JAVA } csIBM857 { IANA JAVA } windows-857 { WINDOWS* } # PC Latin 5 (w/o euro update)
ibm-858_P100-1997 { UTR22* } ibm-858 { IBM* } IBM00858 { IANA* JAVA } CCSID00858 { IANA JAVA } CP00858 { IANA JAVA } PC-Multilingual-850+euro { IANA } cp858 { MIME* JAVA* } windows-858 { WINDOWS* } # PC latin1 with Euro
ibm-860_P100-1995 { UTR22* } ibm-860 { IBM* } IBM860 { IANA* JAVA } cp860 { IANA MIME* JAVA* } 860 { IANA JAVA } csIBM860 { IANA JAVA } # PC Portugal
ibm-861_P100-1995 { UTR22* } ibm-861 { IBM* } IBM861 { IANA* WINDOWS JAVA } cp861 { IANA MIME* JAVA* } 861 { IANA JAVA } cp-is { IANA JAVA } csIBM861 { IANA JAVA } windows-861 { WINDOWS* } # PC Iceland
ibm-862_P100-1995 { UTR22* } ibm-862 { IBM* } IBM862 { IANA* JAVA } cp862 { IANA MIME* JAVA* } 862 { IANA JAVA } csPC862LatinHebrew { IANA JAVA } DOS-862 { WINDOWS } windows-862 { WINDOWS* } # PC Hebrew visual order (w/o euro update)
ibm-863_P100-1995 { UTR22* } ibm-863 { IBM* } IBM863 { IANA* JAVA } cp863 { IANA MIME* JAVA* } 863 { IANA JAVA } csIBM863 { IANA JAVA } # PC Canadian French
ibm-864_X110-1999 { UTR22* } ibm-864 { IBM* } IBM864 { IANA* JAVA } cp864 { IANA MIME* JAVA* } csIBM864 { IANA JAVA } # PC Arabic (w/o euro update)
ibm-865_P100-1995 { UTR22* } ibm-865 { IBM* } IBM865 { IANA* JAVA } cp865 { IANA MIME* JAVA* } 865 { IANA JAVA } csIBM865 { IANA JAVA } # PC Nordic
ibm-866_P100-1995 { UTR22* } ibm-866 { IBM* } IBM866 { IANA* JAVA } cp866 { IANA MIME* WINDOWS JAVA* } 866 { IANA JAVA } csIBM866 { IANA JAVA } windows-866 { WINDOWS* } # PC Russian (w/o euro update)
ibm-856_P100-1995 { UTR22* } ibm-856 { IBM* } IBM856 { JAVA } cp856 { JAVA* } 856 { JAVA } # PC Hebrew implicit order
ibm-857_P100-1995 { UTR22* } ibm-857 { IBM* } IBM857 { IANA* MIME* WINDOWS JAVA } cp857 { IANA MIME JAVA* } 857 { IANA JAVA } csIBM857 { IANA JAVA } windows-857 { WINDOWS* } # PC Latin 5 (w/o euro update)
ibm-858_P100-1997 { UTR22* } ibm-858 { IBM* } IBM00858 { IANA* MIME* JAVA } CCSID00858 { IANA JAVA } CP00858 { IANA JAVA } PC-Multilingual-850+euro { IANA } cp858 { MIME JAVA* } windows-858 { WINDOWS* } # PC latin1 with Euro
ibm-860_P100-1995 { UTR22* } ibm-860 { IBM* } IBM860 { IANA* MIME* JAVA } cp860 { IANA MIME JAVA* } 860 { IANA JAVA } csIBM860 { IANA JAVA } # PC Portugal
ibm-861_P100-1995 { UTR22* } ibm-861 { IBM* } IBM861 { IANA* MIME* WINDOWS JAVA } cp861 { IANA MIME JAVA* } 861 { IANA JAVA } cp-is { IANA JAVA } csIBM861 { IANA JAVA } windows-861 { WINDOWS* } # PC Iceland
ibm-862_P100-1995 { UTR22* } ibm-862 { IBM* } IBM862 { IANA* MIME* JAVA } cp862 { IANA MIME JAVA* } 862 { IANA JAVA } csPC862LatinHebrew { IANA JAVA } DOS-862 { WINDOWS } windows-862 { WINDOWS* } # PC Hebrew visual order (w/o euro update)
ibm-863_P100-1995 { UTR22* } ibm-863 { IBM* } IBM863 { IANA* MIME* JAVA } cp863 { IANA MIME JAVA* } 863 { IANA JAVA } csIBM863 { IANA JAVA } # PC Canadian French
ibm-864_X110-1999 { UTR22* } ibm-864 { IBM* } IBM864 { IANA* MIME* JAVA } cp864 { IANA MIME JAVA* } csIBM864 { IANA JAVA } # PC Arabic (w/o euro update)
ibm-865_P100-1995 { UTR22* } ibm-865 { IBM* } IBM865 { IANA* MIME* JAVA } cp865 { IANA MIME JAVA* } 865 { IANA JAVA } csIBM865 { IANA JAVA } # PC Nordic
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* } # PC Hebrew (w/ euro update) Updated version of ibm-862
ibm-868_P100-1995 { UTR22* } ibm-868 { IBM* } IBM868 { IANA* JAVA } CP868 { IANA MIME* JAVA* } 868 { JAVA } csIBM868 { IANA } cp-ar { IANA } # PC Urdu
ibm-869_P100-1995 { UTR22* } ibm-869 { IBM* } IBM869 { IANA* 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)
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)
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 { MIME* JAVA* } 922 { JAVA } # PC Estonian (w/o euro update)
ibm-922_P100-1999 { UTR22* } ibm-922 { IBM* } IBM922 { JAVA } cp922 { JAVA* } 922 { JAVA } # PC Estonian (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
@ -805,7 +805,7 @@ ibm-1133_P100-1997 { UTR22* } ibm-1133 { IBM* }
# ISO_2022 ISO-2022
ISO_2022,locale=ja,version=0 ISO-2022-JP { IANA* MIME* JAVA* } csISO2022JP { IANA JAVA }
ISO_2022,locale=ja,version=1 ISO-2022-JP-1 JIS_Encoding { IANA* } csJISEncoding { IANA } ibm-5054 { IBM* } JIS
ISO_2022,locale=ja,version=1 ISO-2022-JP-1 { MIME* } JIS_Encoding { IANA* } csJISEncoding { IANA } ibm-5054 { IBM* } JIS
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

View File

@ -1576,7 +1576,30 @@ public class TestCharset extends TestFmwk {
+ " JDK: " + mapSize);
}
logln("Total Number of chasets = " + map.size());
}
}
/* ticket 5580 */
public void TestJavaCanonicalNameOnAvailableCharsets() {
CharsetProviderICU provider = new CharsetProviderICU();
Iterator allCharsets = provider.charsets();
String errorMessage = null;
while (allCharsets.hasNext()) {
Charset _chset = (Charset)allCharsets.next();
Charset chset = Charset.forName(_chset.name());
if (!chset.name().equals(_chset.name())) {
if (errorMessage == null) {
errorMessage = new String("Error: Charset.forName( " + _chset.name() + " ) returned " + chset + " instead of " + _chset);
} else {
errorMessage = errorMessage + "\nError: Charset.forName( " + _chset.name() + " ) returned " + chset + " instead of " + _chset;
}
}
}
if (errorMessage != null) {
errln(errorMessage);
}
}
public void TestWindows936(){
CharsetProviderICU icu = new CharsetProviderICU();

View File

@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d22c018a069cfff20a406ecad95bbf4ac087b324c1905efa104465c2559ca6f0
size 5487794
oid sha256:ed7c7aef0520ae3182b6c7b9ab01ecc3c40e2af9ed46f68943abbec87ce85300
size 5412788