ICU-1575 port updated rules

X-SVN-Rev: 7266
This commit is contained in:
Alan Liu 2001-12-03 18:30:30 +00:00
parent 96173a5d60
commit 35b031a971
4 changed files with 524 additions and 518 deletions

View File

@ -6,7 +6,7 @@
// THIS IS A MACHINE-GENERATED FILE
// Tool: dumpicurules.bat
// Source: ../../text/resources/Transliterator_Fullwidth_Halfwidth.txt
// Date: Fri Nov 30 13:01:41 2001
// Date: Mon Dec 3 10:28:46 2001
//--------------------------------------------------------------------
// Fullwidth_Halfwidth
@ -23,6 +23,8 @@ translit_Fullwidth_Halfwidth {
// Fullwidth-Halfwidth
// Mechanically generated from Unicode Character Database
// IDEOGRAPHIC SPACE then added, and
// FULLWIDTH MACRON changed to map to MACRON, not SPACE + COMBINING MACRON
// multicharacter
@ -269,7 +271,7 @@ translit_Fullwidth_Halfwidth {
"¢<>'¢';" // from FULLWIDTH CENT SIGN
"£<>'£';" // from FULLWIDTH POUND SIGN
"¬<>'¬';" // from FULLWIDTH NOT SIGN
" ̄<>' '̄;" // from FULLWIDTH MACRON
" ̄<>'¯';" // from FULLWIDTH MACRON
"' '<>' ';" // ideographic space (place this after MACRON)
"¦<>'¦';" // from FULLWIDTH BROKEN BAR
"¥<>'¥';" // from FULLWIDTH YEN SIGN
@ -283,5 +285,6 @@ translit_Fullwidth_Halfwidth {
"○<>○;" // to HALFWIDTH WHITE CIRCLE
// eof
}
}

View File

@ -4,9 +4,9 @@
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// THIS IS A MACHINE-GENERATED FILE
// Tool: dumpICUrules.bat
// Tool: dumpicurules.bat
// Source: ../../text/resources/Transliterator_Latin_Katakana.txt
// Date: Fri Nov 30 19:39:31 2001
// Date: Mon Dec 3 10:28:39 2001
//--------------------------------------------------------------------
// Latin_Katakana
@ -18,8 +18,8 @@ translit_Latin_Katakana {
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// $Source: /xsrl/Nsvn/icu/icu/data/Attic/translit_Latin_Katakana.txt,v $
// $Date: 2001/12/01 04:30:28 $
// $Revision: 1.6 $
// $Date: 2001/12/03 18:30:30 $
// $Revision: 1.7 $
//--------------------------------------------------------------------
// note: a global filter is more efficient, but MUST include all source chars
@ -28,7 +28,7 @@ translit_Latin_Katakana {
//## WARNING -- must add width filter, both here and below!!! ###
":: [[\u1100-\u1112\u111A\u1121\u1160-\u1175\u11AA\u11AC-\u11AD\u11B0-\u11B5\u2190-\u2193\u2502\u25A0\u25CB\u3000-\u3002\u300C-\u300D\u3099-\u309A\u30A1-\u30ED\u30EF\u30F2-\u30F4\u30F7\u30FA-\u30FC\uFF01-\uFF5E\uFFE0-\uFFE6][',.A-Za-z~\u00C0-\u00D6\u00D8-\u00F6\u00F8-\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-\u01ED\u01F0\u01F4-\u01F5\u01F8-\u021B\u021E-\u021F\u0226-\u0233\u0304\u04E2-\u04E3\u04EE-\u04EF\u1E00-\u1E99\u1EA0-\u1EF9\u1FB1\u1FB9\u1FD1\u1FD9\u1FE1\u1FE9\u212A-\u212B]] ;"
":: fullwidth-halfwidth ();"
":: [:Latin:] fullwidth-halfwidth ();"
":: NFD (NFC);"
":: Lower ();" // whenever transliterating from cased to uncased script, include this
// :: NFD () ; # this would catch the odd cases where a lowercase is not in NFD, but none are important for Japanese
@ -504,7 +504,7 @@ translit_Latin_Katakana {
// [\u02BE[:Nonspacing Mark:]-[\u3099-\u309C]] > ; # delete any non-spacing marks that we didn't use
":: NFC (NFD) ;"
":: (halfwidth-fullwidth);"
":: ([:Katakana:] halfwidth-fullwidth);"
// note: a global filter is more efficient, but MUST include all source chars!!
//:: ([\\u0000-\u007E \u3001\u3002 \u3099-\u309C \u30A1-\u30FC \uFF61-\uFF9F [:Latin:][:Katakana:] [:nonspacing mark:]]);

View File

@ -6,7 +6,7 @@
// THIS IS A MACHINE-GENERATED FILE
// Tool: dumpicurules.bat
// Source: ../../text/resources/Transliterator_Fullwidth_Halfwidth.txt
// Date: Fri Nov 30 13:01:41 2001
// Date: Mon Dec 3 10:28:46 2001
//--------------------------------------------------------------------
// Fullwidth_Halfwidth
@ -23,6 +23,8 @@ translit_Fullwidth_Halfwidth {
// Fullwidth-Halfwidth
// Mechanically generated from Unicode Character Database
// IDEOGRAPHIC SPACE then added, and
// FULLWIDTH MACRON changed to map to MACRON, not SPACE + COMBINING MACRON
// multicharacter
@ -269,7 +271,7 @@ translit_Fullwidth_Halfwidth {
"¢<>'¢';" // from FULLWIDTH CENT SIGN
"£<>'£';" // from FULLWIDTH POUND SIGN
"¬<>'¬';" // from FULLWIDTH NOT SIGN
" ̄<>' '̄;" // from FULLWIDTH MACRON
" ̄<>'¯';" // from FULLWIDTH MACRON
"' '<>' ';" // ideographic space (place this after MACRON)
"¦<>'¦';" // from FULLWIDTH BROKEN BAR
"¥<>'¥';" // from FULLWIDTH YEN SIGN
@ -283,5 +285,6 @@ translit_Fullwidth_Halfwidth {
"○<>○;" // to HALFWIDTH WHITE CIRCLE
// eof
}
}

View File

@ -4,9 +4,9 @@
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// THIS IS A MACHINE-GENERATED FILE
// Tool: dumpICUrules.bat
// Tool: dumpicurules.bat
// Source: ../../text/resources/Transliterator_Latin_Katakana.txt
// Date: Fri Nov 30 19:39:31 2001
// Date: Mon Dec 3 10:28:39 2001
//--------------------------------------------------------------------
// Latin_Katakana
@ -18,8 +18,8 @@ translit_Latin_Katakana {
// Corporation and others. All Rights Reserved.
//--------------------------------------------------------------------
// $Source: /xsrl/Nsvn/icu/icu/source/data/translit/Attic/t_Latn_Kana.txt,v $
// $Date: 2001/12/01 04:30:28 $
// $Revision: 1.6 $
// $Date: 2001/12/03 18:30:30 $
// $Revision: 1.7 $
//--------------------------------------------------------------------
// note: a global filter is more efficient, but MUST include all source chars
@ -28,7 +28,7 @@ translit_Latin_Katakana {
//## WARNING -- must add width filter, both here and below!!! ###
":: [[\u1100-\u1112\u111A\u1121\u1160-\u1175\u11AA\u11AC-\u11AD\u11B0-\u11B5\u2190-\u2193\u2502\u25A0\u25CB\u3000-\u3002\u300C-\u300D\u3099-\u309A\u30A1-\u30ED\u30EF\u30F2-\u30F4\u30F7\u30FA-\u30FC\uFF01-\uFF5E\uFFE0-\uFFE6][',.A-Za-z~\u00C0-\u00D6\u00D8-\u00F6\u00F8-\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-\u01ED\u01F0\u01F4-\u01F5\u01F8-\u021B\u021E-\u021F\u0226-\u0233\u0304\u04E2-\u04E3\u04EE-\u04EF\u1E00-\u1E99\u1EA0-\u1EF9\u1FB1\u1FB9\u1FD1\u1FD9\u1FE1\u1FE9\u212A-\u212B]] ;"
":: fullwidth-halfwidth ();"
":: [:Latin:] fullwidth-halfwidth ();"
":: NFD (NFC);"
":: Lower ();" // whenever transliterating from cased to uncased script, include this
// :: NFD () ; # this would catch the odd cases where a lowercase is not in NFD, but none are important for Japanese
@ -504,7 +504,7 @@ translit_Latin_Katakana {
// [\u02BE[:Nonspacing Mark:]-[\u3099-\u309C]] > ; # delete any non-spacing marks that we didn't use
":: NFC (NFD) ;"
":: (halfwidth-fullwidth);"
":: ([:Katakana:] halfwidth-fullwidth);"
// note: a global filter is more efficient, but MUST include all source chars!!
//:: ([\\u0000-\u007E \u3001\u3002 \u3099-\u309C \u30A1-\u30FC \uFF61-\uFF9F [:Latin:][:Katakana:] [:nonspacing mark:]]);