mirror of
https://github.com/unicode-org/icu.git
synced 2025-04-07 22:44:49 +00:00
ICU-1575 fixed normalizing transliterator to get closer to the end in incremental mode; latin-katakana & fullwidth/halfwidth now pass incremental tests. UnicodeSet has some package-private utilities added -- they should be made public next release.
X-SVN-Rev: 7280
This commit is contained in:
parent
e1777df34b
commit
3eccfcc26d
7 changed files with 539 additions and 23 deletions
|
@ -9,11 +9,21 @@
|
|||
*/
|
||||
|
||||
#include "unicode/utypes.h"
|
||||
#include "unicode/uniset.h"
|
||||
#include "nortrans.h"
|
||||
#include "unormimp.h"
|
||||
#include "mutex.h"
|
||||
#include "ucln_in.h"
|
||||
|
||||
U_NAMESPACE_BEGIN
|
||||
|
||||
/**
|
||||
* Generated in unicodetools, NFSkippable
|
||||
*/
|
||||
static UnicodeSet* SKIPPABLES = NULL;
|
||||
|
||||
static const int32_t D = 0, C = 1, KD= 2, KC = 3;
|
||||
|
||||
U_CDECL_BEGIN
|
||||
|
||||
/*
|
||||
|
@ -145,6 +155,22 @@ NormalizationTransliterator::NormalizationTransliterator(
|
|||
Transliterator(id, 0) {
|
||||
fMode = mode;
|
||||
options = opt;
|
||||
skippable = NULL;
|
||||
initStatics();
|
||||
switch(mode) {
|
||||
case UNORM_NFD:
|
||||
skippable = &SKIPPABLES[D];
|
||||
break;
|
||||
case UNORM_NFC:
|
||||
skippable = &SKIPPABLES[C];
|
||||
break;
|
||||
case UNORM_NFKD:
|
||||
skippable = &SKIPPABLES[KD];
|
||||
break;
|
||||
case UNORM_NFKC:
|
||||
skippable = &SKIPPABLES[KC];
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
|
@ -160,6 +186,7 @@ NormalizationTransliterator::NormalizationTransliterator(const NormalizationTran
|
|||
Transliterator(o) {
|
||||
fMode = o.fMode;
|
||||
options = o.options;
|
||||
skippable = o.skippable;
|
||||
}
|
||||
|
||||
/**
|
||||
|
@ -169,6 +196,7 @@ NormalizationTransliterator& NormalizationTransliterator::operator=(const Normal
|
|||
Transliterator::operator=(o);
|
||||
fMode = o.fMode;
|
||||
options = o.options;
|
||||
skippable = o.skippable;
|
||||
return *this;
|
||||
}
|
||||
|
||||
|
@ -267,7 +295,12 @@ void NormalizationTransliterator::handleTransliterate(Replaceable& text, UTransP
|
|||
// stop in incremental mode when we reach the input limit
|
||||
// in case there are additional characters that could change the
|
||||
// normalization result
|
||||
break;
|
||||
|
||||
// UNLESS all characters in the result of the normalization of
|
||||
// the last run are in the skippable set
|
||||
if (!skippable->containsAll(output)) {
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
// replace the input chunk with its normalized form
|
||||
|
@ -283,4 +316,342 @@ void NormalizationTransliterator::handleTransliterate(Replaceable& text, UTransP
|
|||
offsets.start = start;
|
||||
}
|
||||
|
||||
void NormalizationTransliterator::initStatics() {
|
||||
if (SKIPPABLES == NULL) {
|
||||
Mutex lock;
|
||||
if (SKIPPABLES == NULL) {
|
||||
SKIPPABLES = new UnicodeSet[4];
|
||||
UErrorCode ec = U_ZERO_ERROR;
|
||||
|
||||
SKIPPABLES[D].applyPattern(
|
||||
"[^\\u00C0-\\u00C5\\u00C7-\\u00CF\\u00D1-\\u00D6\\u00D9-\\u00DD\\u00E0-"
|
||||
"\\u00E5\\u00E7-\\u00EF\\u00F1-\\u00F6\\u00F9-\\u00FD\\u00FF-\\u010F\\u0112"
|
||||
"-\\u0125\\u0128-\\u0130\\u0134-\\u0137\\u0139-\\u013E\\u0143-\\u0148"
|
||||
"\\u014C-\\u0151\\u0154-\\u0165\\u0168-\\u017E\\u01A0-\\u01A1\\u01AF-"
|
||||
"\\u01B0\\u01CD-\\u01DC\\u01DE-\\u01E3\\u01E6-\\u01F0\\u01F4-\\u01F5\\u01F8"
|
||||
"-\\u021B\\u021E-\\u021F\\u0226-\\u0233\\u0300-\\u034E\\u0360-\\u0362"
|
||||
"\\u0374\\u037E\\u0385-\\u038A\\u038C\\u038E-\\u0390\\u03AA-\\u03B0\\u03CA-"
|
||||
"\\u03CE\\u03D3-\\u03D4\\u0400-\\u0401\\u0403\\u0407\\u040C-\\u040E\\u0419"
|
||||
"\\u0439\\u0450-\\u0451\\u0453\\u0457\\u045C-\\u045E\\u0476-\\u0477\\u0483-"
|
||||
"\\u0486\\u04C1-\\u04C2\\u04D0-\\u04D3\\u04D6-\\u04D7\\u04DA-\\u04DF\\u04E2"
|
||||
"-\\u04E7\\u04EA-\\u04F5\\u04F8-\\u04F9\\u0591-\\u05A1\\u05A3-\\u05B9"
|
||||
"\\u05BB-\\u05BD\\u05BF\\u05C1-\\u05C2\\u05C4\\u0622-\\u0626\\u064B-\\u0655"
|
||||
"\\u0670\\u06C0\\u06C2\\u06D3\\u06D6-\\u06DC\\u06DF-\\u06E4\\u06E7-\\u06E8"
|
||||
"\\u06EA-\\u06ED\\u0711\\u0730-\\u074A\\u0929\\u0931\\u0934\\u093C\\u094D"
|
||||
"\\u0951-\\u0954\\u0958-\\u095F\\u09BC\\u09CB-\\u09CD\\u09DC-\\u09DD\\u09DF"
|
||||
"\\u0A33\\u0A36\\u0A3C\\u0A4D\\u0A59-\\u0A5B\\u0A5E\\u0ABC\\u0ACD\\u0B3C"
|
||||
"\\u0B48\\u0B4B-\\u0B4D\\u0B5C-\\u0B5D\\u0B94\\u0BCA-\\u0BCD\\u0C48\\u0C4D"
|
||||
"\\u0C55-\\u0C56\\u0CC0\\u0CC7-\\u0CC8\\u0CCA-\\u0CCB\\u0CCD\\u0D4A-\\u0D4D"
|
||||
"\\u0DCA\\u0DDA\\u0DDC-\\u0DDE\\u0E38-\\u0E3A\\u0E48-\\u0E4B\\u0EB8-\\u0EB9"
|
||||
"\\u0EC8-\\u0ECB\\u0F18-\\u0F19\\u0F35\\u0F37\\u0F39\\u0F43\\u0F4D\\u0F52"
|
||||
"\\u0F57\\u0F5C\\u0F69\\u0F71-\\u0F76\\u0F78\\u0F7A-\\u0F7D\\u0F80-\\u0F84"
|
||||
"\\u0F86-\\u0F87\\u0F93\\u0F9D\\u0FA2\\u0FA7\\u0FAC\\u0FB9\\u0FC6\\u1026"
|
||||
"\\u1037\\u1039\\u17D2\\u18A9\\u1E00-\\u1E99\\u1E9B\\u1EA0-\\u1EF9\\u1F00-"
|
||||
"\\u1F15\\u1F18-\\u1F1D\\u1F20-\\u1F45\\u1F48-\\u1F4D\\u1F50-\\u1F57\\u1F59"
|
||||
"\\u1F5B\\u1F5D\\u1F5F-\\u1F7D\\u1F80-\\u1FB4\\u1FB6-\\u1FBC\\u1FBE\\u1FC1-"
|
||||
"\\u1FC4\\u1FC6-\\u1FD3\\u1FD6-\\u1FDB\\u1FDD-\\u1FEF\\u1FF2-\\u1FF4\\u1FF6"
|
||||
"-\\u1FFD\\u2000-\\u2001\\u20D0-\\u20DC\\u20E1\\u2126\\u212A-\\u212B\\u219A"
|
||||
"-\\u219B\\u21AE\\u21CD-\\u21CF\\u2204\\u2209\\u220C\\u2224\\u2226\\u2241"
|
||||
"\\u2244\\u2247\\u2249\\u2260\\u2262\\u226D-\\u2271\\u2274-\\u2275\\u2278-"
|
||||
"\\u2279\\u2280-\\u2281\\u2284-\\u2285\\u2288-\\u2289\\u22AC-\\u22AF\\u22E0"
|
||||
"-\\u22E3\\u22EA-\\u22ED\\u2329-\\u232A\\u302A-\\u302F\\u304C\\u304E\\u3050"
|
||||
"\\u3052\\u3054\\u3056\\u3058\\u305A\\u305C\\u305E\\u3060\\u3062\\u3065"
|
||||
"\\u3067\\u3069\\u3070-\\u3071\\u3073-\\u3074\\u3076-\\u3077\\u3079-\\u307A"
|
||||
"\\u307C-\\u307D\\u3094\\u3099-\\u309A\\u309E\\u30AC\\u30AE\\u30B0\\u30B2"
|
||||
"\\u30B4\\u30B6\\u30B8\\u30BA\\u30BC\\u30BE\\u30C0\\u30C2\\u30C5\\u30C7"
|
||||
"\\u30C9\\u30D0-\\u30D1\\u30D3-\\u30D4\\u30D6-\\u30D7\\u30D9-\\u30DA\\u30DC"
|
||||
"-\\u30DD\\u30F4\\u30F7-\\u30FA\\u30FE\\uAC00-\\uD7A3\\uF900-\\uFA0D\\uFA10"
|
||||
"\\uFA12\\uFA15-\\uFA1E\\uFA20\\uFA22\\uFA25-\\uFA26\\uFA2A-\\uFA2D\\uFB1D-"
|
||||
"\\uFB1F\\uFB2A-\\uFB36\\uFB38-\\uFB3C\\uFB3E\\uFB40-\\uFB41\\uFB43-\\uFB44"
|
||||
"\\uFB46-\\uFB4E\\uFE20-\\uFE23\\U0001D15E-\\U0001D169\\U0001D16D-\\U0001"
|
||||
"D172\\U0001D17B-\\U0001D182\\U0001D185-\\U0001D18B\\U0001D1AA-\\U0001D"
|
||||
"1AD\\U0001D1BB-\\U0001D1C0\\U0002F800-\\U0002FA1D]", ec);
|
||||
|
||||
SKIPPABLES[C].applyPattern(
|
||||
"[^<->A-PR-Za-pr-z\\u00A8\\u00C0-\\u00CF\\u00D1-\\u00D6\\u00D8-\\u00DD"
|
||||
"\\u00E0-\\u00EF\\u00F1-\\u00F6\\u00F8-\\u00FD\\u00FF-\\u0103\\u0106-"
|
||||
"\\u010F\\u0112-\\u0117\\u011A-\\u0121\\u0124-\\u0125\\u0128-\\u012D\\u0130"
|
||||
"\\u0139-\\u013A\\u013D-\\u013E\\u0143-\\u0144\\u0147-\\u0148\\u014C-"
|
||||
"\\u0151\\u0154-\\u0155\\u0158-\\u015D\\u0160-\\u0161\\u0164-\\u0165\\u0168"
|
||||
"-\\u0171\\u0174-\\u017F\\u01A0-\\u01A1\\u01AF-\\u01B0\\u01B7\\u01CD-"
|
||||
"\\u01DC\\u01DE-\\u01E1\\u01E6-\\u01EB\\u01F4-\\u01F5\\u01F8-\\u01FB\\u0200"
|
||||
"-\\u021B\\u021E-\\u021F\\u0226-\\u0233\\u0292\\u0300-\\u034E\\u0360-"
|
||||
"\\u0362\\u0374\\u037E\\u0387\\u0391\\u0395\\u0397\\u0399\\u039F\\u03A1"
|
||||
"\\u03A5\\u03A9\\u03AC\\u03AE\\u03B1\\u03B5\\u03B7\\u03B9\\u03BF\\u03C1"
|
||||
"\\u03C5\\u03C9-\\u03CB\\u03CE\\u03D2\\u0406\\u0410\\u0413\\u0415-\\u0418"
|
||||
"\\u041A\\u041E\\u0423\\u0427\\u042B\\u042D\\u0430\\u0433\\u0435-\\u0438"
|
||||
"\\u043A\\u043E\\u0443\\u0447\\u044B\\u044D\\u0456\\u0474-\\u0475\\u0483-"
|
||||
"\\u0486\\u04D8-\\u04D9\\u04E8-\\u04E9\\u0591-\\u05A1\\u05A3-\\u05B9\\u05BB"
|
||||
"-\\u05BD\\u05BF\\u05C1-\\u05C2\\u05C4\\u0622-\\u0623\\u0627\\u0648\\u064A-"
|
||||
"\\u0655\\u0670\\u06C1\\u06D2\\u06D5-\\u06DC\\u06DF-\\u06E4\\u06E7-\\u06E8"
|
||||
"\\u06EA-\\u06ED\\u0711\\u0730-\\u074A\\u0928\\u0930\\u0933\\u093C\\u094D"
|
||||
"\\u0951-\\u0954\\u0958-\\u095F\\u09BC\\u09BE\\u09C7\\u09CD\\u09D7\\u09DC-"
|
||||
"\\u09DD\\u09DF\\u0A33\\u0A36\\u0A3C\\u0A4D\\u0A59-\\u0A5B\\u0A5E\\u0ABC"
|
||||
"\\u0ACD\\u0B3C\\u0B3E\\u0B47\\u0B4D\\u0B56-\\u0B57\\u0B5C-\\u0B5D\\u0B92"
|
||||
"\\u0BBE\\u0BC6-\\u0BC7\\u0BCD\\u0BD7\\u0C46\\u0C4D\\u0C55-\\u0C56\\u0CBF"
|
||||
"\\u0CC2\\u0CC6\\u0CCA\\u0CCD\\u0CD5-\\u0CD6\\u0D3E\\u0D46-\\u0D47\\u0D4D"
|
||||
"\\u0D57\\u0DCA\\u0DCF\\u0DD9\\u0DDC\\u0DDF\\u0E38-\\u0E3A\\u0E48-\\u0E4B"
|
||||
"\\u0EB8-\\u0EB9\\u0EC8-\\u0ECB\\u0F18-\\u0F19\\u0F35\\u0F37\\u0F39\\u0F43"
|
||||
"\\u0F4D\\u0F52\\u0F57\\u0F5C\\u0F69\\u0F71-\\u0F76\\u0F78\\u0F7A-\\u0F7D"
|
||||
"\\u0F80-\\u0F84\\u0F86-\\u0F87\\u0F93\\u0F9D\\u0FA2\\u0FA7\\u0FAC\\u0FB9"
|
||||
"\\u0FC6\\u1025\\u102E\\u1037\\u1039\\u1100-\\u1112\\u1161-\\u1175\\u11A8-"
|
||||
"\\u11C2\\u17D2\\u18A9\\u1E00-\\u1E03\\u1E0A-\\u1E0F\\u1E12-\\u1E1B\\u1E20-"
|
||||
"\\u1E27\\u1E2A-\\u1E41\\u1E44-\\u1E53\\u1E58-\\u1E7D\\u1E80-\\u1E87\\u1E8E"
|
||||
"-\\u1E91\\u1E96-\\u1E99\\u1EA0-\\u1EF3\\u1EF6-\\u1EF9\\u1F00-\\u1F11"
|
||||
"\\u1F18-\\u1F19\\u1F20-\\u1F31\\u1F38-\\u1F39\\u1F40-\\u1F41\\u1F48-"
|
||||
"\\u1F49\\u1F50-\\u1F51\\u1F59\\u1F60-\\u1F71\\u1F73-\\u1F75\\u1F77\\u1F79"
|
||||
"\\u1F7B-\\u1F7D\\u1F80-\\u1F81\\u1F88-\\u1F89\\u1F90-\\u1F91\\u1F98-"
|
||||
"\\u1F99\\u1FA0-\\u1FA1\\u1FA8-\\u1FA9\\u1FB3\\u1FB6\\u1FBB-\\u1FBC\\u1FBE-"
|
||||
"\\u1FBF\\u1FC3\\u1FC6\\u1FC9\\u1FCB-\\u1FCC\\u1FD3\\u1FDB\\u1FE3\\u1FEB"
|
||||
"\\u1FEE-\\u1FEF\\u1FF3\\u1FF6\\u1FF9\\u1FFB-\\u1FFE\\u2000-\\u2001\\u20D0-"
|
||||
"\\u20DC\\u20E1\\u2126\\u212A-\\u212B\\u2190\\u2192\\u2194\\u21D0\\u21D2"
|
||||
"\\u21D4\\u2203\\u2208\\u220B\\u2223\\u2225\\u223C\\u2243\\u2245\\u2248"
|
||||
"\\u224D\\u2261\\u2264-\\u2265\\u2272-\\u2273\\u2276-\\u2277\\u227A-\\u227D"
|
||||
"\\u2282-\\u2283\\u2286-\\u2287\\u2291-\\u2292\\u22A2\\u22A8-\\u22A9\\u22AB"
|
||||
"\\u22B2-\\u22B5\\u2329-\\u232A\\u302A-\\u302F\\u3046\\u304B\\u304D\\u304F"
|
||||
"\\u3051\\u3053\\u3055\\u3057\\u3059\\u305B\\u305D\\u305F\\u3061\\u3064"
|
||||
"\\u3066\\u3068\\u306F\\u3072\\u3075\\u3078\\u307B\\u3099-\\u309A\\u309D"
|
||||
"\\u30A6\\u30AB\\u30AD\\u30AF\\u30B1\\u30B3\\u30B5\\u30B7\\u30B9\\u30BB"
|
||||
"\\u30BD\\u30BF\\u30C1\\u30C4\\u30C6\\u30C8\\u30CF\\u30D2\\u30D5\\u30D8"
|
||||
"\\u30DB\\u30EF-\\u30F2\\u30FD\\uAC00\\uAC1C\\uAC38\\uAC54\\uAC70\\uAC8C"
|
||||
"\\uACA8\\uACC4\\uACE0\\uACFC\\uAD18\\uAD34\\uAD50\\uAD6C\\uAD88\\uADA4"
|
||||
"\\uADC0\\uADDC\\uADF8\\uAE14\\uAE30\\uAE4C\\uAE68\\uAE84\\uAEA0\\uAEBC"
|
||||
"\\uAED8\\uAEF4\\uAF10\\uAF2C\\uAF48\\uAF64\\uAF80\\uAF9C\\uAFB8\\uAFD4"
|
||||
"\\uAFF0\\uB00C\\uB028\\uB044\\uB060\\uB07C\\uB098\\uB0B4\\uB0D0\\uB0EC"
|
||||
"\\uB108\\uB124\\uB140\\uB15C\\uB178\\uB194\\uB1B0\\uB1CC\\uB1E8\\uB204"
|
||||
"\\uB220\\uB23C\\uB258\\uB274\\uB290\\uB2AC\\uB2C8\\uB2E4\\uB300\\uB31C"
|
||||
"\\uB338\\uB354\\uB370\\uB38C\\uB3A8\\uB3C4\\uB3E0\\uB3FC\\uB418\\uB434"
|
||||
"\\uB450\\uB46C\\uB488\\uB4A4\\uB4C0\\uB4DC\\uB4F8\\uB514\\uB530\\uB54C"
|
||||
"\\uB568\\uB584\\uB5A0\\uB5BC\\uB5D8\\uB5F4\\uB610\\uB62C\\uB648\\uB664"
|
||||
"\\uB680\\uB69C\\uB6B8\\uB6D4\\uB6F0\\uB70C\\uB728\\uB744\\uB760\\uB77C"
|
||||
"\\uB798\\uB7B4\\uB7D0\\uB7EC\\uB808\\uB824\\uB840\\uB85C\\uB878\\uB894"
|
||||
"\\uB8B0\\uB8CC\\uB8E8\\uB904\\uB920\\uB93C\\uB958\\uB974\\uB990\\uB9AC"
|
||||
"\\uB9C8\\uB9E4\\uBA00\\uBA1C\\uBA38\\uBA54\\uBA70\\uBA8C\\uBAA8\\uBAC4"
|
||||
"\\uBAE0\\uBAFC\\uBB18\\uBB34\\uBB50\\uBB6C\\uBB88\\uBBA4\\uBBC0\\uBBDC"
|
||||
"\\uBBF8\\uBC14\\uBC30\\uBC4C\\uBC68\\uBC84\\uBCA0\\uBCBC\\uBCD8\\uBCF4"
|
||||
"\\uBD10\\uBD2C\\uBD48\\uBD64\\uBD80\\uBD9C\\uBDB8\\uBDD4\\uBDF0\\uBE0C"
|
||||
"\\uBE28\\uBE44\\uBE60\\uBE7C\\uBE98\\uBEB4\\uBED0\\uBEEC\\uBF08\\uBF24"
|
||||
"\\uBF40\\uBF5C\\uBF78\\uBF94\\uBFB0\\uBFCC\\uBFE8\\uC004\\uC020\\uC03C"
|
||||
"\\uC058\\uC074\\uC090\\uC0AC\\uC0C8\\uC0E4\\uC100\\uC11C\\uC138\\uC154"
|
||||
"\\uC170\\uC18C\\uC1A8\\uC1C4\\uC1E0\\uC1FC\\uC218\\uC234\\uC250\\uC26C"
|
||||
"\\uC288\\uC2A4\\uC2C0\\uC2DC\\uC2F8\\uC314\\uC330\\uC34C\\uC368\\uC384"
|
||||
"\\uC3A0\\uC3BC\\uC3D8\\uC3F4\\uC410\\uC42C\\uC448\\uC464\\uC480\\uC49C"
|
||||
"\\uC4B8\\uC4D4\\uC4F0\\uC50C\\uC528\\uC544\\uC560\\uC57C\\uC598\\uC5B4"
|
||||
"\\uC5D0\\uC5EC\\uC608\\uC624\\uC640\\uC65C\\uC678\\uC694\\uC6B0\\uC6CC"
|
||||
"\\uC6E8\\uC704\\uC720\\uC73C\\uC758\\uC774\\uC790\\uC7AC\\uC7C8\\uC7E4"
|
||||
"\\uC800\\uC81C\\uC838\\uC854\\uC870\\uC88C\\uC8A8\\uC8C4\\uC8E0\\uC8FC"
|
||||
"\\uC918\\uC934\\uC950\\uC96C\\uC988\\uC9A4\\uC9C0\\uC9DC\\uC9F8\\uCA14"
|
||||
"\\uCA30\\uCA4C\\uCA68\\uCA84\\uCAA0\\uCABC\\uCAD8\\uCAF4\\uCB10\\uCB2C"
|
||||
"\\uCB48\\uCB64\\uCB80\\uCB9C\\uCBB8\\uCBD4\\uCBF0\\uCC0C\\uCC28\\uCC44"
|
||||
"\\uCC60\\uCC7C\\uCC98\\uCCB4\\uCCD0\\uCCEC\\uCD08\\uCD24\\uCD40\\uCD5C"
|
||||
"\\uCD78\\uCD94\\uCDB0\\uCDCC\\uCDE8\\uCE04\\uCE20\\uCE3C\\uCE58\\uCE74"
|
||||
"\\uCE90\\uCEAC\\uCEC8\\uCEE4\\uCF00\\uCF1C\\uCF38\\uCF54\\uCF70\\uCF8C"
|
||||
"\\uCFA8\\uCFC4\\uCFE0\\uCFFC\\uD018\\uD034\\uD050\\uD06C\\uD088\\uD0A4"
|
||||
"\\uD0C0\\uD0DC\\uD0F8\\uD114\\uD130\\uD14C\\uD168\\uD184\\uD1A0\\uD1BC"
|
||||
"\\uD1D8\\uD1F4\\uD210\\uD22C\\uD248\\uD264\\uD280\\uD29C\\uD2B8\\uD2D4"
|
||||
"\\uD2F0\\uD30C\\uD328\\uD344\\uD360\\uD37C\\uD398\\uD3B4\\uD3D0\\uD3EC"
|
||||
"\\uD408\\uD424\\uD440\\uD45C\\uD478\\uD494\\uD4B0\\uD4CC\\uD4E8\\uD504"
|
||||
"\\uD520\\uD53C\\uD558\\uD574\\uD590\\uD5AC\\uD5C8\\uD5E4\\uD600\\uD61C"
|
||||
"\\uD638\\uD654\\uD670\\uD68C\\uD6A8\\uD6C4\\uD6E0\\uD6FC\\uD718\\uD734"
|
||||
"\\uD750\\uD76C\\uD788\\uF900-\\uFA0D\\uFA10\\uFA12\\uFA15-\\uFA1E\\uFA20"
|
||||
"\\uFA22\\uFA25-\\uFA26\\uFA2A-\\uFA2D\\uFB1D-\\uFB1F\\uFB2A-\\uFB36\\uFB38"
|
||||
"-\\uFB3C\\uFB3E\\uFB40-\\uFB41\\uFB43-\\uFB44\\uFB46-\\uFB4E\\uFE20-"
|
||||
"\\uFE23\\U0001D15E-\\U0001D169\\U0001D16D-\\U0001D172\\U0001D17B-"
|
||||
"\\U0001D182\\U0001D185-\\U0001D18B\\U0001D1AA-\\U0001D1AD\\U0001D1BB-"
|
||||
"\\U0001D1C0\\U0002F800-\\U0002FA1D]", ec);
|
||||
|
||||
SKIPPABLES[KD].applyPattern(
|
||||
"[^\\u00A0\\u00A8\\u00AA\\u00AF\\u00B2-\\u00B5\\u00B8-\\u00BA\\u00BC-"
|
||||
"\\u00BE\\u00C0-\\u00C5\\u00C7-\\u00CF\\u00D1-\\u00D6\\u00D9-\\u00DD\\u00E0"
|
||||
"-\\u00E5\\u00E7-\\u00EF\\u00F1-\\u00F6\\u00F9-\\u00FD\\u00FF-\\u010F"
|
||||
"\\u0112-\\u0125\\u0128-\\u0130\\u0132-\\u0137\\u0139-\\u0140\\u0143-"
|
||||
"\\u0149\\u014C-\\u0151\\u0154-\\u0165\\u0168-\\u017F\\u01A0-\\u01A1\\u01AF"
|
||||
"-\\u01B0\\u01C4-\\u01DC\\u01DE-\\u01E3\\u01E6-\\u01F5\\u01F8-\\u021B"
|
||||
"\\u021E-\\u021F\\u0226-\\u0233\\u02B0-\\u02B8\\u02D8-\\u02DD\\u02E0-"
|
||||
"\\u02E4\\u0300-\\u034E\\u0360-\\u0362\\u0374\\u037A\\u037E\\u0384-\\u038A"
|
||||
"\\u038C\\u038E-\\u0390\\u03AA-\\u03B0\\u03CA-\\u03CE\\u03D0-\\u03D6\\u03F0"
|
||||
"-\\u03F2\\u03F4-\\u03F5\\u0400-\\u0401\\u0403\\u0407\\u040C-\\u040E\\u0419"
|
||||
"\\u0439\\u0450-\\u0451\\u0453\\u0457\\u045C-\\u045E\\u0476-\\u0477\\u0483-"
|
||||
"\\u0486\\u04C1-\\u04C2\\u04D0-\\u04D3\\u04D6-\\u04D7\\u04DA-\\u04DF\\u04E2"
|
||||
"-\\u04E7\\u04EA-\\u04F5\\u04F8-\\u04F9\\u0587\\u0591-\\u05A1\\u05A3-"
|
||||
"\\u05B9\\u05BB-\\u05BD\\u05BF\\u05C1-\\u05C2\\u05C4\\u0622-\\u0626\\u064B-"
|
||||
"\\u0655\\u0670\\u0675-\\u0678\\u06C0\\u06C2\\u06D3\\u06D6-\\u06DC\\u06DF-"
|
||||
"\\u06E4\\u06E7-\\u06E8\\u06EA-\\u06ED\\u0711\\u0730-\\u074A\\u0929\\u0931"
|
||||
"\\u0934\\u093C\\u094D\\u0951-\\u0954\\u0958-\\u095F\\u09BC\\u09CB-\\u09CD"
|
||||
"\\u09DC-\\u09DD\\u09DF\\u0A33\\u0A36\\u0A3C\\u0A4D\\u0A59-\\u0A5B\\u0A5E"
|
||||
"\\u0ABC\\u0ACD\\u0B3C\\u0B48\\u0B4B-\\u0B4D\\u0B5C-\\u0B5D\\u0B94\\u0BCA-"
|
||||
"\\u0BCD\\u0C48\\u0C4D\\u0C55-\\u0C56\\u0CC0\\u0CC7-\\u0CC8\\u0CCA-\\u0CCB"
|
||||
"\\u0CCD\\u0D4A-\\u0D4D\\u0DCA\\u0DDA\\u0DDC-\\u0DDE\\u0E33\\u0E38-\\u0E3A"
|
||||
"\\u0E48-\\u0E4B\\u0EB3\\u0EB8-\\u0EB9\\u0EC8-\\u0ECB\\u0EDC-\\u0EDD\\u0F0C"
|
||||
"\\u0F18-\\u0F19\\u0F35\\u0F37\\u0F39\\u0F43\\u0F4D\\u0F52\\u0F57\\u0F5C"
|
||||
"\\u0F69\\u0F71-\\u0F7D\\u0F80-\\u0F84\\u0F86-\\u0F87\\u0F93\\u0F9D\\u0FA2"
|
||||
"\\u0FA7\\u0FAC\\u0FB9\\u0FC6\\u1026\\u1037\\u1039\\u17D2\\u18A9\\u1E00-"
|
||||
"\\u1E9B\\u1EA0-\\u1EF9\\u1F00-\\u1F15\\u1F18-\\u1F1D\\u1F20-\\u1F45\\u1F48"
|
||||
"-\\u1F4D\\u1F50-\\u1F57\\u1F59\\u1F5B\\u1F5D\\u1F5F-\\u1F7D\\u1F80-\\u1FB4"
|
||||
"\\u1FB6-\\u1FC4\\u1FC6-\\u1FD3\\u1FD6-\\u1FDB\\u1FDD-\\u1FEF\\u1FF2-"
|
||||
"\\u1FF4\\u1FF6-\\u1FFE\\u2000-\\u200A\\u2011\\u2017\\u2024-\\u2026\\u202F"
|
||||
"\\u2033-\\u2034\\u2036-\\u2037\\u203C\\u203E\\u2048-\\u2049\\u2070\\u2074-"
|
||||
"\\u208E\\u20A8\\u20D0-\\u20DC\\u20E1\\u2100-\\u2103\\u2105-\\u2107\\u2109-"
|
||||
"\\u2113\\u2115-\\u2116\\u2119-\\u211D\\u2120-\\u2122\\u2124\\u2126\\u2128"
|
||||
"\\u212A-\\u212D\\u212F-\\u2131\\u2133-\\u2139\\u2153-\\u217F\\u219A-"
|
||||
"\\u219B\\u21AE\\u21CD-\\u21CF\\u2204\\u2209\\u220C\\u2224\\u2226\\u222C-"
|
||||
"\\u222D\\u222F-\\u2230\\u2241\\u2244\\u2247\\u2249\\u2260\\u2262\\u226D-"
|
||||
"\\u2271\\u2274-\\u2275\\u2278-\\u2279\\u2280-\\u2281\\u2284-\\u2285\\u2288"
|
||||
"-\\u2289\\u22AC-\\u22AF\\u22E0-\\u22E3\\u22EA-\\u22ED\\u2329-\\u232A"
|
||||
"\\u2460-\\u24EA\\u2E9F\\u2EF3\\u2F00-\\u2FD5\\u3000\\u302A-\\u302F\\u3036"
|
||||
"\\u3038-\\u303A\\u304C\\u304E\\u3050\\u3052\\u3054\\u3056\\u3058\\u305A"
|
||||
"\\u305C\\u305E\\u3060\\u3062\\u3065\\u3067\\u3069\\u3070-\\u3071\\u3073-"
|
||||
"\\u3074\\u3076-\\u3077\\u3079-\\u307A\\u307C-\\u307D\\u3094\\u3099-\\u309C"
|
||||
"\\u309E\\u30AC\\u30AE\\u30B0\\u30B2\\u30B4\\u30B6\\u30B8\\u30BA\\u30BC"
|
||||
"\\u30BE\\u30C0\\u30C2\\u30C5\\u30C7\\u30C9\\u30D0-\\u30D1\\u30D3-\\u30D4"
|
||||
"\\u30D6-\\u30D7\\u30D9-\\u30DA\\u30DC-\\u30DD\\u30F4\\u30F7-\\u30FA\\u30FE"
|
||||
"\\u3131-\\u318E\\u3192-\\u319F\\u3200-\\u321C\\u3220-\\u3243\\u3260-"
|
||||
"\\u327B\\u3280-\\u32B0\\u32C0-\\u32CB\\u32D0-\\u32FE\\u3300-\\u3376\\u337B"
|
||||
"-\\u33DD\\u33E0-\\u33FE\\uAC00-\\uD7A3\\uF900-\\uFA0D\\uFA10\\uFA12\\uFA15"
|
||||
"-\\uFA1E\\uFA20\\uFA22\\uFA25-\\uFA26\\uFA2A-\\uFA2D\\uFB00-\\uFB06\\uFB13"
|
||||
"-\\uFB17\\uFB1D-\\uFB36\\uFB38-\\uFB3C\\uFB3E\\uFB40-\\uFB41\\uFB43-"
|
||||
"\\uFB44\\uFB46-\\uFBB1\\uFBD3-\\uFD3D\\uFD50-\\uFD8F\\uFD92-\\uFDC7\\uFDF0"
|
||||
"-\\uFDFB\\uFE20-\\uFE23\\uFE30-\\uFE44\\uFE49-\\uFE52\\uFE54-\\uFE66"
|
||||
"\\uFE68-\\uFE6B\\uFE70-\\uFE72\\uFE74\\uFE76-\\uFEFC\\uFF01-\\uFF5E\\uFF61"
|
||||
"-\\uFFBE\\uFFC2-\\uFFC7\\uFFCA-\\uFFCF\\uFFD2-\\uFFD7\\uFFDA-\\uFFDC"
|
||||
"\\uFFE0-\\uFFE6\\uFFE8-\\uFFEE\\U0001D15E-\\U0001D169\\U0001D16D-\\U0001"
|
||||
"D172\\U0001D17B-\\U0001D182\\U0001D185-\\U0001D18B\\U0001D1AA-\\U0001D"
|
||||
"1AD\\U0001D1BB-\\U0001D1C0\\U0001D400-\\U0001D454\\U0001D456-\\U0001D4"
|
||||
"9C\\U0001D49E-\\U0001D49F\\U0001D4A2\\U0001D4A5-\\U0001D4A6\\U0001D4A9"
|
||||
"-\\U0001D4AC\\U0001D4AE-\\U0001D4B9\\U0001D4BB\\U0001D4BD-\\U0001D4C0"
|
||||
"\\U0001D4C2-\\U0001D4C3\\U0001D4C5-\\U0001D505\\U0001D507-\\U0001D50A"
|
||||
"\\U0001D50D-\\U0001D514\\U0001D516-\\U0001D51C\\U0001D51E-\\U0001D539"
|
||||
"\\U0001D53B-\\U0001D53E\\U0001D540-\\U0001D544\\U0001D546\\U0001D54A-"
|
||||
"\\U0001D550\\U0001D552-\\U0001D6A3\\U0001D6A8-\\U0001D7C9\\U0001D7CE-"
|
||||
"\\U0001D7FF\\U0002F800-\\U0002FA1D]", ec);
|
||||
|
||||
SKIPPABLES[KC].applyPattern(
|
||||
"[^<->A-PR-Za-pr-z\\u00A0\\u00A8\\u00AA\\u00AF\\u00B2-\\u00B5\\u00B8-"
|
||||
"\\u00BA\\u00BC-\\u00BE\\u00C0-\\u00CF\\u00D1-\\u00D6\\u00D8-\\u00DD\\u00E0"
|
||||
"-\\u00EF\\u00F1-\\u00F6\\u00F8-\\u00FD\\u00FF-\\u0103\\u0106-\\u010F"
|
||||
"\\u0112-\\u0117\\u011A-\\u0121\\u0124-\\u0125\\u0128-\\u012D\\u0130\\u0132"
|
||||
"-\\u0133\\u0139-\\u013A\\u013D-\\u0140\\u0143-\\u0144\\u0147-\\u0149"
|
||||
"\\u014C-\\u0151\\u0154-\\u0155\\u0158-\\u015D\\u0160-\\u0161\\u0164-"
|
||||
"\\u0165\\u0168-\\u0171\\u0174-\\u017F\\u01A0-\\u01A1\\u01AF-\\u01B0\\u01B7"
|
||||
"\\u01C4-\\u01DC\\u01DE-\\u01E1\\u01E6-\\u01EB\\u01F1-\\u01F5\\u01F8-"
|
||||
"\\u01FB\\u0200-\\u021B\\u021E-\\u021F\\u0226-\\u0233\\u0292\\u02B0-\\u02B8"
|
||||
"\\u02D8-\\u02DD\\u02E0-\\u02E4\\u0300-\\u034E\\u0360-\\u0362\\u0374\\u037A"
|
||||
"\\u037E\\u0384-\\u0385\\u0387\\u0391\\u0395\\u0397\\u0399\\u039F\\u03A1"
|
||||
"\\u03A5\\u03A9\\u03AC\\u03AE\\u03B1\\u03B5\\u03B7\\u03B9\\u03BF\\u03C1"
|
||||
"\\u03C5\\u03C9-\\u03CB\\u03CE\\u03D0-\\u03D6\\u03F0-\\u03F2\\u03F4-\\u03F5"
|
||||
"\\u0406\\u0410\\u0413\\u0415-\\u0418\\u041A\\u041E\\u0423\\u0427\\u042B"
|
||||
"\\u042D\\u0430\\u0433\\u0435-\\u0438\\u043A\\u043E\\u0443\\u0447\\u044B"
|
||||
"\\u044D\\u0456\\u0474-\\u0475\\u0483-\\u0486\\u04D8-\\u04D9\\u04E8-\\u04E9"
|
||||
"\\u0587\\u0591-\\u05A1\\u05A3-\\u05B9\\u05BB-\\u05BD\\u05BF\\u05C1-\\u05C2"
|
||||
"\\u05C4\\u0622-\\u0623\\u0627\\u0648\\u064A-\\u0655\\u0670\\u0675-\\u0678"
|
||||
"\\u06C1\\u06D2\\u06D5-\\u06DC\\u06DF-\\u06E4\\u06E7-\\u06E8\\u06EA-\\u06ED"
|
||||
"\\u0711\\u0730-\\u074A\\u0928\\u0930\\u0933\\u093C\\u094D\\u0951-\\u0954"
|
||||
"\\u0958-\\u095F\\u09BC\\u09BE\\u09C7\\u09CD\\u09D7\\u09DC-\\u09DD\\u09DF"
|
||||
"\\u0A33\\u0A36\\u0A3C\\u0A4D\\u0A59-\\u0A5B\\u0A5E\\u0ABC\\u0ACD\\u0B3C"
|
||||
"\\u0B3E\\u0B47\\u0B4D\\u0B56-\\u0B57\\u0B5C-\\u0B5D\\u0B92\\u0BBE\\u0BC6-"
|
||||
"\\u0BC7\\u0BCD\\u0BD7\\u0C46\\u0C4D\\u0C55-\\u0C56\\u0CBF\\u0CC2\\u0CC6"
|
||||
"\\u0CCA\\u0CCD\\u0CD5-\\u0CD6\\u0D3E\\u0D46-\\u0D47\\u0D4D\\u0D57\\u0DCA"
|
||||
"\\u0DCF\\u0DD9\\u0DDC\\u0DDF\\u0E33\\u0E38-\\u0E3A\\u0E48-\\u0E4B\\u0EB3"
|
||||
"\\u0EB8-\\u0EB9\\u0EC8-\\u0ECB\\u0EDC-\\u0EDD\\u0F0C\\u0F18-\\u0F19\\u0F35"
|
||||
"\\u0F37\\u0F39\\u0F43\\u0F4D\\u0F52\\u0F57\\u0F5C\\u0F69\\u0F71-\\u0F7D"
|
||||
"\\u0F80-\\u0F84\\u0F86-\\u0F87\\u0F93\\u0F9D\\u0FA2\\u0FA7\\u0FAC\\u0FB9"
|
||||
"\\u0FC6\\u1025\\u102E\\u1037\\u1039\\u1100-\\u1112\\u1161-\\u1175\\u11A8-"
|
||||
"\\u11C2\\u17D2\\u18A9\\u1E00-\\u1E03\\u1E0A-\\u1E0F\\u1E12-\\u1E1B\\u1E20-"
|
||||
"\\u1E27\\u1E2A-\\u1E41\\u1E44-\\u1E53\\u1E58-\\u1E7D\\u1E80-\\u1E87\\u1E8E"
|
||||
"-\\u1E91\\u1E96-\\u1E9B\\u1EA0-\\u1EF3\\u1EF6-\\u1EF9\\u1F00-\\u1F11"
|
||||
"\\u1F18-\\u1F19\\u1F20-\\u1F31\\u1F38-\\u1F39\\u1F40-\\u1F41\\u1F48-"
|
||||
"\\u1F49\\u1F50-\\u1F51\\u1F59\\u1F60-\\u1F71\\u1F73-\\u1F75\\u1F77\\u1F79"
|
||||
"\\u1F7B-\\u1F7D\\u1F80-\\u1F81\\u1F88-\\u1F89\\u1F90-\\u1F91\\u1F98-"
|
||||
"\\u1F99\\u1FA0-\\u1FA1\\u1FA8-\\u1FA9\\u1FB3\\u1FB6\\u1FBB-\\u1FC1\\u1FC3"
|
||||
"\\u1FC6\\u1FC9\\u1FCB-\\u1FCF\\u1FD3\\u1FDB\\u1FDD-\\u1FDF\\u1FE3\\u1FEB"
|
||||
"\\u1FED-\\u1FEF\\u1FF3\\u1FF6\\u1FF9\\u1FFB-\\u1FFE\\u2000-\\u200A\\u2011"
|
||||
"\\u2017\\u2024-\\u2026\\u202F\\u2033-\\u2034\\u2036-\\u2037\\u203C\\u203E"
|
||||
"\\u2048-\\u2049\\u2070\\u2074-\\u208E\\u20A8\\u20D0-\\u20DC\\u20E1\\u2100-"
|
||||
"\\u2103\\u2105-\\u2107\\u2109-\\u2113\\u2115-\\u2116\\u2119-\\u211D\\u2120"
|
||||
"-\\u2122\\u2124\\u2126\\u2128\\u212A-\\u212D\\u212F-\\u2131\\u2133-\\u2139"
|
||||
"\\u2153-\\u217F\\u2190\\u2192\\u2194\\u21D0\\u21D2\\u21D4\\u2203\\u2208"
|
||||
"\\u220B\\u2223\\u2225\\u222C-\\u222D\\u222F-\\u2230\\u223C\\u2243\\u2245"
|
||||
"\\u2248\\u224D\\u2261\\u2264-\\u2265\\u2272-\\u2273\\u2276-\\u2277\\u227A-"
|
||||
"\\u227D\\u2282-\\u2283\\u2286-\\u2287\\u2291-\\u2292\\u22A2\\u22A8-\\u22A9"
|
||||
"\\u22AB\\u22B2-\\u22B5\\u2329-\\u232A\\u2460-\\u24EA\\u2E9F\\u2EF3\\u2F00-"
|
||||
"\\u2FD5\\u3000\\u302A-\\u302F\\u3036\\u3038-\\u303A\\u3046\\u304B\\u304D"
|
||||
"\\u304F\\u3051\\u3053\\u3055\\u3057\\u3059\\u305B\\u305D\\u305F\\u3061"
|
||||
"\\u3064\\u3066\\u3068\\u306F\\u3072\\u3075\\u3078\\u307B\\u3099-\\u309D"
|
||||
"\\u30A6\\u30AB\\u30AD\\u30AF\\u30B1\\u30B3\\u30B5\\u30B7\\u30B9\\u30BB"
|
||||
"\\u30BD\\u30BF\\u30C1\\u30C4\\u30C6\\u30C8\\u30CF\\u30D2\\u30D5\\u30D8"
|
||||
"\\u30DB\\u30EF-\\u30F2\\u30FD\\u3131-\\u318E\\u3192-\\u319F\\u3200-\\u321C"
|
||||
"\\u3220-\\u3243\\u3260-\\u327B\\u3280-\\u32B0\\u32C0-\\u32CB\\u32D0-"
|
||||
"\\u32FE\\u3300-\\u3376\\u337B-\\u33DD\\u33E0-\\u33FE\\uAC00\\uAC1C\\uAC38"
|
||||
"\\uAC54\\uAC70\\uAC8C\\uACA8\\uACC4\\uACE0\\uACFC\\uAD18\\uAD34\\uAD50"
|
||||
"\\uAD6C\\uAD88\\uADA4\\uADC0\\uADDC\\uADF8\\uAE14\\uAE30\\uAE4C\\uAE68"
|
||||
"\\uAE84\\uAEA0\\uAEBC\\uAED8\\uAEF4\\uAF10\\uAF2C\\uAF48\\uAF64\\uAF80"
|
||||
"\\uAF9C\\uAFB8\\uAFD4\\uAFF0\\uB00C\\uB028\\uB044\\uB060\\uB07C\\uB098"
|
||||
"\\uB0B4\\uB0D0\\uB0EC\\uB108\\uB124\\uB140\\uB15C\\uB178\\uB194\\uB1B0"
|
||||
"\\uB1CC\\uB1E8\\uB204\\uB220\\uB23C\\uB258\\uB274\\uB290\\uB2AC\\uB2C8"
|
||||
"\\uB2E4\\uB300\\uB31C\\uB338\\uB354\\uB370\\uB38C\\uB3A8\\uB3C4\\uB3E0"
|
||||
"\\uB3FC\\uB418\\uB434\\uB450\\uB46C\\uB488\\uB4A4\\uB4C0\\uB4DC\\uB4F8"
|
||||
"\\uB514\\uB530\\uB54C\\uB568\\uB584\\uB5A0\\uB5BC\\uB5D8\\uB5F4\\uB610"
|
||||
"\\uB62C\\uB648\\uB664\\uB680\\uB69C\\uB6B8\\uB6D4\\uB6F0\\uB70C\\uB728"
|
||||
"\\uB744\\uB760\\uB77C\\uB798\\uB7B4\\uB7D0\\uB7EC\\uB808\\uB824\\uB840"
|
||||
"\\uB85C\\uB878\\uB894\\uB8B0\\uB8CC\\uB8E8\\uB904\\uB920\\uB93C\\uB958"
|
||||
"\\uB974\\uB990\\uB9AC\\uB9C8\\uB9E4\\uBA00\\uBA1C\\uBA38\\uBA54\\uBA70"
|
||||
"\\uBA8C\\uBAA8\\uBAC4\\uBAE0\\uBAFC\\uBB18\\uBB34\\uBB50\\uBB6C\\uBB88"
|
||||
"\\uBBA4\\uBBC0\\uBBDC\\uBBF8\\uBC14\\uBC30\\uBC4C\\uBC68\\uBC84\\uBCA0"
|
||||
"\\uBCBC\\uBCD8\\uBCF4\\uBD10\\uBD2C\\uBD48\\uBD64\\uBD80\\uBD9C\\uBDB8"
|
||||
"\\uBDD4\\uBDF0\\uBE0C\\uBE28\\uBE44\\uBE60\\uBE7C\\uBE98\\uBEB4\\uBED0"
|
||||
"\\uBEEC\\uBF08\\uBF24\\uBF40\\uBF5C\\uBF78\\uBF94\\uBFB0\\uBFCC\\uBFE8"
|
||||
"\\uC004\\uC020\\uC03C\\uC058\\uC074\\uC090\\uC0AC\\uC0C8\\uC0E4\\uC100"
|
||||
"\\uC11C\\uC138\\uC154\\uC170\\uC18C\\uC1A8\\uC1C4\\uC1E0\\uC1FC\\uC218"
|
||||
"\\uC234\\uC250\\uC26C\\uC288\\uC2A4\\uC2C0\\uC2DC\\uC2F8\\uC314\\uC330"
|
||||
"\\uC34C\\uC368\\uC384\\uC3A0\\uC3BC\\uC3D8\\uC3F4\\uC410\\uC42C\\uC448"
|
||||
"\\uC464\\uC480\\uC49C\\uC4B8\\uC4D4\\uC4F0\\uC50C\\uC528\\uC544\\uC560"
|
||||
"\\uC57C\\uC598\\uC5B4\\uC5D0\\uC5EC\\uC608\\uC624\\uC640\\uC65C\\uC678"
|
||||
"\\uC694\\uC6B0\\uC6CC\\uC6E8\\uC704\\uC720\\uC73C\\uC758\\uC774\\uC790"
|
||||
"\\uC7AC\\uC7C8\\uC7E4\\uC800\\uC81C\\uC838\\uC854\\uC870\\uC88C\\uC8A8"
|
||||
"\\uC8C4\\uC8E0\\uC8FC\\uC918\\uC934\\uC950\\uC96C\\uC988\\uC9A4\\uC9C0"
|
||||
"\\uC9DC\\uC9F8\\uCA14\\uCA30\\uCA4C\\uCA68\\uCA84\\uCAA0\\uCABC\\uCAD8"
|
||||
"\\uCAF4\\uCB10\\uCB2C\\uCB48\\uCB64\\uCB80\\uCB9C\\uCBB8\\uCBD4\\uCBF0"
|
||||
"\\uCC0C\\uCC28\\uCC44\\uCC60\\uCC7C\\uCC98\\uCCB4\\uCCD0\\uCCEC\\uCD08"
|
||||
"\\uCD24\\uCD40\\uCD5C\\uCD78\\uCD94\\uCDB0\\uCDCC\\uCDE8\\uCE04\\uCE20"
|
||||
"\\uCE3C\\uCE58\\uCE74\\uCE90\\uCEAC\\uCEC8\\uCEE4\\uCF00\\uCF1C\\uCF38"
|
||||
"\\uCF54\\uCF70\\uCF8C\\uCFA8\\uCFC4\\uCFE0\\uCFFC\\uD018\\uD034\\uD050"
|
||||
"\\uD06C\\uD088\\uD0A4\\uD0C0\\uD0DC\\uD0F8\\uD114\\uD130\\uD14C\\uD168"
|
||||
"\\uD184\\uD1A0\\uD1BC\\uD1D8\\uD1F4\\uD210\\uD22C\\uD248\\uD264\\uD280"
|
||||
"\\uD29C\\uD2B8\\uD2D4\\uD2F0\\uD30C\\uD328\\uD344\\uD360\\uD37C\\uD398"
|
||||
"\\uD3B4\\uD3D0\\uD3EC\\uD408\\uD424\\uD440\\uD45C\\uD478\\uD494\\uD4B0"
|
||||
"\\uD4CC\\uD4E8\\uD504\\uD520\\uD53C\\uD558\\uD574\\uD590\\uD5AC\\uD5C8"
|
||||
"\\uD5E4\\uD600\\uD61C\\uD638\\uD654\\uD670\\uD68C\\uD6A8\\uD6C4\\uD6E0"
|
||||
"\\uD6FC\\uD718\\uD734\\uD750\\uD76C\\uD788\\uF900-\\uFA0D\\uFA10\\uFA12"
|
||||
"\\uFA15-\\uFA1E\\uFA20\\uFA22\\uFA25-\\uFA26\\uFA2A-\\uFA2D\\uFB00-\\uFB06"
|
||||
"\\uFB13-\\uFB17\\uFB1D-\\uFB36\\uFB38-\\uFB3C\\uFB3E\\uFB40-\\uFB41\\uFB43"
|
||||
"-\\uFB44\\uFB46-\\uFBB1\\uFBD3-\\uFD3D\\uFD50-\\uFD8F\\uFD92-\\uFDC7"
|
||||
"\\uFDF0-\\uFDFB\\uFE20-\\uFE23\\uFE30-\\uFE44\\uFE49-\\uFE52\\uFE54-"
|
||||
"\\uFE66\\uFE68-\\uFE6B\\uFE70-\\uFE72\\uFE74\\uFE76-\\uFEFC\\uFF01-\\uFF5E"
|
||||
"\\uFF61-\\uFFBE\\uFFC2-\\uFFC7\\uFFCA-\\uFFCF\\uFFD2-\\uFFD7\\uFFDA-"
|
||||
"\\uFFDC\\uFFE0-\\uFFE6\\uFFE8-\\uFFEE\\U0001D15E-\\U0001D169\\U0001D16D-"
|
||||
"\\U0001D172\\U0001D17B-\\U0001D182\\U0001D185-\\U0001D18B\\U0001D1AA-"
|
||||
"\\U0001D1AD\\U0001D1BB-\\U0001D1C0\\U0001D400-\\U0001D454\\U0001D456-"
|
||||
"\\U0001D49C\\U0001D49E-\\U0001D49F\\U0001D4A2\\U0001D4A5-\\U0001D4A6"
|
||||
"\\U0001D4A9-\\U0001D4AC\\U0001D4AE-\\U0001D4B9\\U0001D4BB\\U0001D4BD-"
|
||||
"\\U0001D4C0\\U0001D4C2-\\U0001D4C3\\U0001D4C5-\\U0001D505\\U0001D507-"
|
||||
"\\U0001D50A\\U0001D50D-\\U0001D514\\U0001D516-\\U0001D51C\\U0001D51E-"
|
||||
"\\U0001D539\\U0001D53B-\\U0001D53E\\U0001D540-\\U0001D544\\U0001D546"
|
||||
"\\U0001D54A-\\U0001D550\\U0001D552-\\U0001D6A3\\U0001D6A8-\\U0001D7C9"
|
||||
"\\U0001D7CE-\\U0001D7FF\\U0002F800-\\U0002FA1D]", ec);
|
||||
|
||||
ucln_i18n_registerCleanup();
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Static memory cleanup function.
|
||||
*/
|
||||
void NormalizationTransliterator::cleanup() {
|
||||
if (SKIPPABLES != NULL) {
|
||||
delete[] SKIPPABLES;
|
||||
SKIPPABLES = NULL;
|
||||
}
|
||||
}
|
||||
|
||||
U_NAMESPACE_END
|
||||
|
|
|
@ -19,7 +19,7 @@ U_NAMESPACE_BEGIN
|
|||
/**
|
||||
* A transliterator that performs normalization.
|
||||
* @author Alan Liu
|
||||
* @version $RCSfile: nortrans.h,v $ $Revision: 1.1 $ $Date: 2001/11/16 23:51:15 $
|
||||
* @version $RCSfile: nortrans.h,v $ $Revision: 1.2 $ $Date: 2001/12/03 20:50:11 $
|
||||
*/
|
||||
class U_I18N_API NormalizationTransliterator : public Transliterator {
|
||||
|
||||
|
@ -33,6 +33,11 @@ class U_I18N_API NormalizationTransliterator : public Transliterator {
|
|||
*/
|
||||
int32_t options;
|
||||
|
||||
/**
|
||||
* Alias to skippables set. NOT OWNED.
|
||||
*/
|
||||
UnicodeSet* skippable;
|
||||
|
||||
public:
|
||||
|
||||
/**
|
||||
|
@ -69,6 +74,11 @@ class U_I18N_API NormalizationTransliterator : public Transliterator {
|
|||
*/
|
||||
static void registerIDs();
|
||||
|
||||
/**
|
||||
* Static memory cleanup function.
|
||||
*/
|
||||
static void cleanup();
|
||||
|
||||
private:
|
||||
|
||||
// Transliterator::Factory methods
|
||||
|
@ -81,6 +91,8 @@ class U_I18N_API NormalizationTransliterator : public Transliterator {
|
|||
*/
|
||||
NormalizationTransliterator(const UnicodeString& id,
|
||||
UNormalizationMode mode, int32_t opt);
|
||||
|
||||
static void initStatics();
|
||||
};
|
||||
|
||||
U_NAMESPACE_END
|
||||
|
|
|
@ -1854,6 +1854,7 @@ U_NAMESPACE_END
|
|||
*/
|
||||
U_CFUNC UBool transliterator_cleanup(void) {
|
||||
TitlecaseTransliterator::cleanup();
|
||||
NormalizationTransliterator::cleanup();
|
||||
if (registry) {
|
||||
delete registry;
|
||||
registry = NULL;
|
||||
|
|
|
@ -540,6 +540,16 @@ public:
|
|||
*/
|
||||
virtual UBool containsAll(const UnicodeSet& c) const;
|
||||
|
||||
private:
|
||||
friend class NormalizationTransliterator;
|
||||
// TODO: Make this public
|
||||
/**
|
||||
* Return TRUE if every character in s is in this set.
|
||||
*/
|
||||
UBool containsAll(const UnicodeString& s) const;
|
||||
|
||||
public:
|
||||
|
||||
/**
|
||||
* Adds all of the elements in the specified set to this set if
|
||||
* they're not already present. This operation effectively
|
||||
|
|
|
@ -746,6 +746,18 @@ UBool UnicodeSet::containsAll(const UnicodeSet& c) const {
|
|||
return TRUE;
|
||||
}
|
||||
|
||||
/**
|
||||
* Return TRUE if every character in s is in this set.
|
||||
*/
|
||||
UBool UnicodeSet::containsAll(const UnicodeString& s) const {
|
||||
UChar32 cp;
|
||||
for (int32_t i = 0; i < s.length(); i += UTF_CHAR_LENGTH(cp)) {
|
||||
cp = s.char32At(i);
|
||||
if (!contains(cp)) return FALSE;
|
||||
}
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
/**
|
||||
* Adds all of the elements in the specified set to this set if
|
||||
* they're not already present. This operation effectively
|
||||
|
|
|
@ -11,6 +11,7 @@
|
|||
#include "unicode/cpdtrans.h"
|
||||
#include "unicode/dtfmtsym.h"
|
||||
#include "unicode/hextouni.h"
|
||||
#include "unicode/normlzr.h"
|
||||
#include "unicode/nultrans.h"
|
||||
#include "unicode/rbt.h"
|
||||
#include "unicode/translit.h"
|
||||
|
@ -2978,14 +2979,18 @@ void TransliteratorTest::TestSpecialCases(void) {
|
|||
"Any-Dev2", "XY > Z",
|
||||
"Greek-Latin/FAKE",
|
||||
CharsToUnicodeString
|
||||
("[^[:L:][:M:]] { \\u03bc\\u03c0 > b ; \\u03bc\\u03c0 } [^[:L:][:M:]] > b ; [^[:L:][:M:]] { [\\u039c\\u03bc][\\u03a0\\u03c0] > B ; [\\u039c\\u03bc][\\u03a0\\u03c0] } [^[:L:][:M:]] > B ;")
|
||||
("[^[:L:][:M:]] { \\u03bc\\u03c0 > b ; \\u03bc\\u03c0 } [^[:L:][:M:]] > b ; [^[:L:][:M:]] { [\\u039c\\u03bc][\\u03a0\\u03c0] > B ; [\\u039c\\u03bc][\\u03a0\\u03c0] } [^[:L:][:M:]] > B ;"),
|
||||
"" // END MARKER
|
||||
};
|
||||
|
||||
const UnicodeString testCases[] = {
|
||||
// NORMALIZATION, not in C
|
||||
"NFC", CharsToUnicodeString("a\\u0300"), CharsToUnicodeString("\\u00E0"),
|
||||
"NFD", CharsToUnicodeString("\\u00E0"), CharsToUnicodeString("a\\u0300"),
|
||||
|
||||
static const UnicodeString testCases[] = {
|
||||
// NORMALIZATION
|
||||
// should add more test cases
|
||||
"NFD" , CharsToUnicodeString("a\\u0300 \\u00E0 \\u1100\\u1161 \\uFF76\\uFF9E\\u03D3"), "",
|
||||
"NFC" , CharsToUnicodeString("a\\u0300 \\u00E0 \\u1100\\u1161 \\uFF76\\uFF9E\\u03D3"), "",
|
||||
"NFKD", CharsToUnicodeString("a\\u0300 \\u00E0 \\u1100\\u1161 \\uFF76\\uFF9E\\u03D3"), "",
|
||||
"NFKC", CharsToUnicodeString("a\\u0300 \\u00E0 \\u1100\\u1161 \\uFF76\\uFF9E\\u03D3"), "",
|
||||
|
||||
// mp -> b BUG
|
||||
"Greek-Latin/UNGEGN", CharsToUnicodeString("(\\u03BC\\u03C0)"), "(b)",
|
||||
"Greek-Latin/FAKE", CharsToUnicodeString("(\\u03BC\\u03C0)"), "(b)",
|
||||
|
@ -3007,6 +3012,9 @@ void TransliteratorTest::TestSpecialCases(void) {
|
|||
"Lower", CharsToUnicodeString("ab'cD \\uFB00i\\u0131I\\u0130 \\u01C7\\u01C8\\u01C9 ") + DESERET_dee + DESERET_DEE,
|
||||
CharsToUnicodeString("ab'cd \\uFB00i\\u0131ii \\u01C9\\u01C9\\u01C9 ") + DESERET_dee + DESERET_dee,
|
||||
|
||||
"Upper", CharsToUnicodeString("ab'cD \\uFB00i\\u0131I\\u0130 \\u01C7\\u01C8\\u01C9 ") + DESERET_dee + DESERET_DEE, "",
|
||||
"Lower", CharsToUnicodeString("ab'cD \\uFB00i\\u0131I\\u0130 \\u01C7\\u01C8\\u01C9 ") + DESERET_dee + DESERET_DEE, "",
|
||||
|
||||
// FORMS OF S
|
||||
"Greek-Latin/UNGEGN", CharsToUnicodeString("\\u03C3 \\u03C3\\u03C2 \\u03C2\\u03C3"),
|
||||
CharsToUnicodeString("s ss s\\u0331s\\u0331") ,
|
||||
|
@ -3015,12 +3023,13 @@ void TransliteratorTest::TestSpecialCases(void) {
|
|||
"Greek-Latin", CharsToUnicodeString("\\u03C3 \\u03C3\\u03C2 \\u03C2\\u03C3"),
|
||||
CharsToUnicodeString("s ss s\\u0331s\\u0331") ,
|
||||
"Latin-Greek", CharsToUnicodeString("s ss s\\u0331s\\u0331"),
|
||||
CharsToUnicodeString("\\u03C3 \\u03C3\\u03C2 \\u03C2\\u03C3")
|
||||
CharsToUnicodeString("\\u03C3 \\u03C3\\u03C2 \\u03C2\\u03C3"),
|
||||
"" // END MARKER
|
||||
};
|
||||
|
||||
UParseError pos;
|
||||
int32_t i;
|
||||
for (i = 0; i < 6 /*registerRules.length*/; i+=2) {
|
||||
for (i = 0; registerRules[i].length()!=0; i+=2) {
|
||||
UErrorCode status = U_ZERO_ERROR;
|
||||
|
||||
Transliterator *t = Transliterator::createFromRules(registerRules[0+i],
|
||||
|
@ -3031,12 +3040,50 @@ void TransliteratorTest::TestSpecialCases(void) {
|
|||
Transliterator::registerInstance(t);
|
||||
}
|
||||
}
|
||||
for (i = 0; i < 36 /*testCases.length*/; i+=3) {
|
||||
UErrorCode status = U_ZERO_ERROR;
|
||||
Transliterator *t = Transliterator::createInstance(testCases[i+0], UTRANS_FORWARD, pos, status);
|
||||
expect(*t, testCases[i+1], testCases[i+2], 0);
|
||||
for (i = 0; testCases[i].length()!=0; i+=3) {
|
||||
UErrorCode ec = U_ZERO_ERROR;
|
||||
UParseError pe;
|
||||
const UnicodeString& name = testCases[i];
|
||||
Transliterator *t = Transliterator::createInstance(name, UTRANS_FORWARD, pe, ec);
|
||||
if (U_FAILURE(ec)) {
|
||||
errln((UnicodeString)"FAIL: Couldn't create " + name);
|
||||
delete t;
|
||||
continue;
|
||||
}
|
||||
const UnicodeString& id = t->getID();
|
||||
const UnicodeString& source = testCases[i+1];
|
||||
UnicodeString target;
|
||||
|
||||
// Automatic generation of targets, to make it simpler to add test cases (and more fail-safe)
|
||||
|
||||
if (testCases[i+2].length() > 0) {
|
||||
target = testCases[i+2];
|
||||
} else if (0==id.caseCompare("NFD", U_FOLD_CASE_DEFAULT)) {
|
||||
Normalizer::normalize(source, UNORM_NFD, 0, target, ec);
|
||||
} else if (0==id.caseCompare("NFC", U_FOLD_CASE_DEFAULT)) {
|
||||
Normalizer::normalize(source, UNORM_NFC, 0, target, ec);
|
||||
} else if (0==id.caseCompare("NFKD", U_FOLD_CASE_DEFAULT)) {
|
||||
Normalizer::normalize(source, UNORM_NFKD, 0, target, ec);
|
||||
} else if (0==id.caseCompare("NFKC", U_FOLD_CASE_DEFAULT)) {
|
||||
Normalizer::normalize(source, UNORM_NFKC, 0, target, ec);
|
||||
} else if (0==id.caseCompare("Lower", U_FOLD_CASE_DEFAULT)) {
|
||||
target = source;
|
||||
target.toLower(Locale::US);
|
||||
} else if (0==id.caseCompare("Upper", U_FOLD_CASE_DEFAULT)) {
|
||||
target = source;
|
||||
target.toUpper(Locale::US);
|
||||
}
|
||||
if (U_FAILURE(ec)) {
|
||||
errln((UnicodeString)"FAIL: Internal error normalizing " + source);
|
||||
continue;
|
||||
}
|
||||
|
||||
expect(*t, source, target);
|
||||
delete t;
|
||||
}
|
||||
for (i = 0; registerRules[i].length()!=0; i+=2) {
|
||||
Transliterator::unregister(registerRules[i]);
|
||||
}
|
||||
}
|
||||
|
||||
char* Char32ToEscapedChars(UChar32 ch, char* buffer) {
|
||||
|
@ -3080,16 +3127,66 @@ void TransliteratorTest::TestSurrogateCasing (void) {
|
|||
}
|
||||
}
|
||||
|
||||
static void _trans(Transliterator& t, const UnicodeString& src,
|
||||
UnicodeString& result) {
|
||||
result = src;
|
||||
t.transliterate(result);
|
||||
}
|
||||
|
||||
static void _trans(const UnicodeString& id, const UnicodeString& src,
|
||||
UnicodeString& result, UErrorCode ec) {
|
||||
UParseError pe;
|
||||
Transliterator *t = Transliterator::createInstance(id, UTRANS_FORWARD, pe, ec);
|
||||
if (U_SUCCESS(ec)) {
|
||||
_trans(*t, src, result);
|
||||
}
|
||||
delete t;
|
||||
}
|
||||
|
||||
static const UnicodeString& _findMatch(const UnicodeString& source,
|
||||
const UnicodeString* pairs) {
|
||||
static const UnicodeString empty;
|
||||
for (int32_t i=0; pairs[i].length() > 0; i+=2) {
|
||||
if (0==source.caseCompare(pairs[i], U_FOLD_CASE_DEFAULT)) {
|
||||
return pairs[i+1];
|
||||
}
|
||||
}
|
||||
return empty;
|
||||
}
|
||||
|
||||
// Check to see that incremental gets at least part way through a reasonable string.
|
||||
|
||||
void TransliteratorTest::TestIncrementalProgress(void) {
|
||||
UErrorCode ec = U_ZERO_ERROR;
|
||||
UnicodeString latinTest = "The Quick Brown Fox.";
|
||||
UnicodeString devaTest;
|
||||
_trans("Latin-Devanagari", latinTest, devaTest, ec);
|
||||
UnicodeString kataTest;
|
||||
_trans("Latin-Katakana", latinTest, kataTest, ec);
|
||||
if (U_FAILURE(ec)) {
|
||||
errln("FAIL: Internal error");
|
||||
return;
|
||||
}
|
||||
static const UnicodeString tests[] = {
|
||||
"Any", latinTest,
|
||||
"Latin", latinTest,
|
||||
"Halfwidth", latinTest,
|
||||
"Devanagari", devaTest,
|
||||
"Katakana", kataTest,
|
||||
"" // END MARKER
|
||||
};
|
||||
|
||||
UnicodeString test("The Quick Brown Fox Jumped Over The Lazy Dog.");
|
||||
int32_t i = 0, j=0, k=0;
|
||||
int32_t sources = Transliterator::countAvailableSources();
|
||||
for (i = 0; i < sources; i++) {
|
||||
UnicodeString source;
|
||||
Transliterator::getAvailableSource(i, source);
|
||||
if (source != UnicodeString("Latin")) continue;
|
||||
UnicodeString test = _findMatch(source, tests);
|
||||
if (test.length() == 0) {
|
||||
logln((UnicodeString)"Skipping " + source + "-X");
|
||||
continue;
|
||||
}
|
||||
int32_t targets = Transliterator::countAvailableTargets(source);
|
||||
for (j = 0; j < targets; j++) {
|
||||
UnicodeString target;
|
||||
|
@ -3105,12 +3202,23 @@ void TransliteratorTest::TestIncrementalProgress(void) {
|
|||
|
||||
Transliterator *t = Transliterator::createInstance(id, UTRANS_FORWARD, err, status);
|
||||
if (U_FAILURE(status)) {
|
||||
errln("FAIL: Not able to create transliterator from the composed ID.");
|
||||
errln((UnicodeString)"FAIL: Could not create " + id);
|
||||
delete t;
|
||||
continue;
|
||||
}
|
||||
status = U_ZERO_ERROR;
|
||||
UnicodeString result = CheckIncrementalAux(t, test);
|
||||
CheckIncrementalAux(t, test);
|
||||
|
||||
UnicodeString rev;
|
||||
_trans(*t, test, rev);
|
||||
Transliterator *inv = t->createInverse(status);
|
||||
CheckIncrementalAux(inv, result);
|
||||
if (U_FAILURE(status)) {
|
||||
errln((UnicodeString)"FAIL: Could not create inverse of " + id);
|
||||
delete t;
|
||||
delete inv;
|
||||
continue;
|
||||
}
|
||||
CheckIncrementalAux(inv, rev);
|
||||
delete t;
|
||||
delete inv;
|
||||
}
|
||||
|
@ -3118,7 +3226,7 @@ void TransliteratorTest::TestIncrementalProgress(void) {
|
|||
}
|
||||
}
|
||||
|
||||
UnicodeString TransliteratorTest::CheckIncrementalAux(const Transliterator* t,
|
||||
void TransliteratorTest::CheckIncrementalAux(const Transliterator* t,
|
||||
const UnicodeString& input) {
|
||||
UErrorCode ec = U_ZERO_ERROR;
|
||||
UTransPosition pos;
|
||||
|
@ -3132,10 +3240,13 @@ UnicodeString TransliteratorTest::CheckIncrementalAux(const Transliterator* t,
|
|||
t->transliterate(test, pos, ec);
|
||||
if (U_FAILURE(ec)) {
|
||||
errln((UnicodeString)"FAIL: transliterate() error " + u_errorName(ec));
|
||||
return test;
|
||||
return;
|
||||
}
|
||||
UBool gotError = FALSE;
|
||||
if (pos.start == 0) {
|
||||
|
||||
// we have a few special cases. Any-Remove (pos.start = 0, but also = limit) and U+XXXXX?X?
|
||||
|
||||
if (pos.start == 0 && pos.limit != 0 && t->getID() != "Hex-Any/Unicode") {
|
||||
errln((UnicodeString)"No Progress, " +
|
||||
t->getID() + ": " + formatInput(test, input, pos));
|
||||
gotError = TRUE;
|
||||
|
@ -3149,7 +3260,6 @@ UnicodeString TransliteratorTest::CheckIncrementalAux(const Transliterator* t,
|
|||
t->getID() + ": " + formatInput(test, input, pos));
|
||||
gotError = TRUE;
|
||||
}
|
||||
return test;
|
||||
}
|
||||
//======================================================================
|
||||
// Support methods
|
||||
|
|
|
@ -347,7 +347,7 @@ class TransliteratorTest : public IntlTest {
|
|||
|
||||
void checkRules(const UnicodeString& label, Transliterator& t2,
|
||||
const UnicodeString& testRulesForward);
|
||||
UnicodeString CheckIncrementalAux(const Transliterator* t,
|
||||
void CheckIncrementalAux(const Transliterator* t,
|
||||
const UnicodeString& input);
|
||||
|
||||
};
|
||||
|
|
Loading…
Add table
Reference in a new issue