mirror of
https://github.com/unicode-org/icu.git
synced 2025-04-17 18:56:53 +00:00
ICU-1427 Fixed casing problems in roundtrip
X-SVN-Rev: 6585
This commit is contained in:
parent
a39ab6337c
commit
4f6767b06b
3 changed files with 43 additions and 19 deletions
|
@ -3,8 +3,8 @@
|
|||
# Corporation and others. All Rights Reserved.
|
||||
#--------------------------------------------------------------------
|
||||
# $Source: /xsrl/Nsvn/icu/icu4j/src/com/ibm/icu/impl/data/Attic/Transliterator_Cyrillic_Latin.txt,v $
|
||||
# $Date: 2001/10/20 01:33:44 $
|
||||
# $Revision: 1.3 $
|
||||
# $Date: 2001/11/02 19:07:05 $
|
||||
# $Revision: 1.4 $
|
||||
#--------------------------------------------------------------------
|
||||
# TODO: add remaining characters
|
||||
# Should add variants for Russian-English, Russian-German
|
||||
|
@ -23,6 +23,7 @@ $breve = \u0306 ;
|
|||
$dot = \u0307 ;
|
||||
$caron = \u030C ;
|
||||
$comma = \u0326 ;
|
||||
$under = \u0331 ;
|
||||
|
||||
# move up so not masked
|
||||
|
||||
|
@ -202,12 +203,14 @@ $comma = \u0326 ;
|
|||
# Ҿ <> XXX ; # CYRILLIC CAPITAL LETTER ABKHASIAN CHE WITH DESCENDER
|
||||
|
||||
|
||||
ъ <> [:Ll:] { $modprime2 ; # CYRILLIC SMALL LETTER HARD SIGN
|
||||
Ъ <> $modprime2 ; # CYRILLIC CAPITAL LETTER HARD SIGN
|
||||
Ъ <> $modprime2 $under ; # CYRILLIC CAPITAL LETTER HARD SIGN
|
||||
ъ <> $modprime2 ; # CYRILLIC SMALL LETTER HARD SIGN
|
||||
Ь <> $modprime $under ; # CYRILLIC CAPITAL LETTER SOFT SIGN
|
||||
ь <> $modprime ; # CYRILLIC SMALL LETTER SOFT SIGN
|
||||
|
||||
ы <> y ; # CYRILLIC SMALL LETTER YERU
|
||||
Ы <> Y ; # CYRILLIC CAPITAL LETTER YERU
|
||||
ь <> [:Ll:] { $modprime ; # CYRILLIC SMALL LETTER SOFT SIGN
|
||||
Ь <> $modprime ; # CYRILLIC CAPITAL LETTER SOFT SIGN
|
||||
|
||||
# ҍ <> XXX ; # CYRILLIC SMALL LETTER SEMISOFT SIGN
|
||||
# Ҍ <> XXX ; # CYRILLIC CAPITAL LETTER SEMISOFT SIGN
|
||||
# ѣ <> XXX ; # CYRILLIC SMALL LETTER YAT
|
||||
|
|
|
@ -3,8 +3,8 @@
|
|||
# Corporation and others. All Rights Reserved.
|
||||
#--------------------------------------------------------------------
|
||||
# $Source: /xsrl/Nsvn/icu/icu4j/src/com/ibm/text/resources/Attic/Transliterator_Cyrillic_Latin.txt,v $
|
||||
# $Date: 2001/10/20 01:33:44 $
|
||||
# $Revision: 1.3 $
|
||||
# $Date: 2001/11/02 19:07:05 $
|
||||
# $Revision: 1.4 $
|
||||
#--------------------------------------------------------------------
|
||||
# TODO: add remaining characters
|
||||
# Should add variants for Russian-English, Russian-German
|
||||
|
@ -23,6 +23,7 @@ $breve = \u0306 ;
|
|||
$dot = \u0307 ;
|
||||
$caron = \u030C ;
|
||||
$comma = \u0326 ;
|
||||
$under = \u0331 ;
|
||||
|
||||
# move up so not masked
|
||||
|
||||
|
@ -202,12 +203,14 @@ $comma = \u0326 ;
|
|||
# Ҿ <> XXX ; # CYRILLIC CAPITAL LETTER ABKHASIAN CHE WITH DESCENDER
|
||||
|
||||
|
||||
ъ <> [:Ll:] { $modprime2 ; # CYRILLIC SMALL LETTER HARD SIGN
|
||||
Ъ <> $modprime2 ; # CYRILLIC CAPITAL LETTER HARD SIGN
|
||||
Ъ <> $modprime2 $under ; # CYRILLIC CAPITAL LETTER HARD SIGN
|
||||
ъ <> $modprime2 ; # CYRILLIC SMALL LETTER HARD SIGN
|
||||
Ь <> $modprime $under ; # CYRILLIC CAPITAL LETTER SOFT SIGN
|
||||
ь <> $modprime ; # CYRILLIC SMALL LETTER SOFT SIGN
|
||||
|
||||
ы <> y ; # CYRILLIC SMALL LETTER YERU
|
||||
Ы <> Y ; # CYRILLIC CAPITAL LETTER YERU
|
||||
ь <> [:Ll:] { $modprime ; # CYRILLIC SMALL LETTER SOFT SIGN
|
||||
Ь <> $modprime ; # CYRILLIC CAPITAL LETTER SOFT SIGN
|
||||
|
||||
# ҍ <> XXX ; # CYRILLIC SMALL LETTER SEMISOFT SIGN
|
||||
# Ҍ <> XXX ; # CYRILLIC CAPITAL LETTER SEMISOFT SIGN
|
||||
# ѣ <> XXX ; # CYRILLIC SMALL LETTER YAT
|
||||
|
|
|
@ -3,8 +3,8 @@
|
|||
# Corporation and others. All Rights Reserved.
|
||||
#--------------------------------------------------------------------
|
||||
# $Source: /xsrl/Nsvn/icu/icu4j/src/com/ibm/text/resources/Attic/Transliterator_el_Latin.txt,v $
|
||||
# $Date: 2001/11/01 00:39:31 $
|
||||
# $Revision: 1.1 $
|
||||
# $Date: 2001/11/02 19:07:06 $
|
||||
# $Revision: 1.2 $
|
||||
#--------------------------------------------------------------------
|
||||
|
||||
# Rules are predicated on running NFD first, and NFC afterwards
|
||||
|
@ -41,6 +41,12 @@ $softener = [βΒγΓδΔζΖλΛμΜνΝρΡ$gvowel] ;
|
|||
|
||||
$under = \u0331;
|
||||
|
||||
$caron = \u030C;
|
||||
|
||||
$afterLetter = [:^L:] [\'[:M:]]* ;
|
||||
$beforeLetter = [\'[:M:]]* [:^L:] ;
|
||||
|
||||
|
||||
# Fix punctuation
|
||||
|
||||
\; <> \? ;
|
||||
|
@ -143,11 +149,23 @@ $vowel { Υ <> U $under ;
|
|||
ρ <> r ;
|
||||
Ρ <> R ;
|
||||
|
||||
[Pp] {ς > \'s ;
|
||||
[Pp] {σ > \'s ;
|
||||
σ < [:^L:] [:M:]* { s } [:^L:] ;
|
||||
ς <> s } [:^L:] ;
|
||||
σ <> s ;
|
||||
[Pp] { } ς > \' ;
|
||||
[Pp] { } σ > \' ;
|
||||
|
||||
# Caron means exception
|
||||
|
||||
# before a letter, initial
|
||||
ς } $beforeLetter <> s $caron } $beforeLetter;
|
||||
σ } $beforeLetter <> s } $beforeLetter;
|
||||
|
||||
# otherwise, after a letter = final
|
||||
$afterLetter { σ <> $afterLetter { s $caron;
|
||||
$afterLetter { ς <> $afterLetter { s ;
|
||||
|
||||
# otherwise (isolated) = initial
|
||||
ς <> s $caron;
|
||||
σ <> s ;
|
||||
|
||||
[Pp] { Σ <> \'S ;
|
||||
Σ <> S ;
|
||||
|
||||
|
|
Loading…
Add table
Reference in a new issue