factor/basis/unicode/case/case.factor

121 lines
3.1 KiB
Factor
Raw Normal View History

2008-10-05 19:36:56 -04:00
! Copyright (C) 2008 Daniel Ehrenberg.
! See http://factorcode.org/license.txt for BSD license.
USING: unicode.data sequences sequences.next namespaces make unicode.syntax
unicode.normalize math unicode.categories combinators unicode.syntax
assocs strings splitting kernel accessors unicode.breaks fry ;
2008-01-09 14:44:07 -05:00
IN: unicode.case
2009-01-07 18:59:01 -05:00
<PRIVATE
2008-12-03 09:46:16 -05:00
: at-default ( key assoc -- value/key ) [ at ] [ drop ] 2bi or ;
2008-04-05 08:57:26 -04:00
2008-01-09 14:44:07 -05:00
: ch>lower ( ch -- lower ) simple-lower at-default ;
: ch>upper ( ch -- upper ) simple-upper at-default ;
: ch>title ( ch -- title ) simple-title at-default ;
PRIVATE>
2009-01-07 22:45:33 -05:00
2008-01-09 14:44:07 -05:00
SYMBOL: locale ! Just casing locale, or overall?
2009-01-07 22:45:33 -05:00
2009-01-07 18:59:01 -05:00
<PRIVATE
: split-subseq ( string sep -- strings )
[ dup ] swap '[ _ split1-slice swap ] [ ] produce nip ;
: replace ( old new str -- newstr )
[ split-subseq ] dip join ;
2008-01-09 14:44:07 -05:00
: i-dot? ( -- ? )
locale get { "tr" "az" } member? ;
: lithuanian? ( -- ? ) locale get "lt" = ;
: dot-over ( -- ch ) HEX: 307 ;
2008-01-09 14:44:07 -05:00
: lithuanian>upper ( string -- lower )
"i\u000307" "i" replace
"j\u000307" "j" replace ;
2008-01-09 14:44:07 -05:00
: mark-above? ( ch -- ? )
combining-class 230 = ;
: with-rest ( seq quot: ( seq -- seq ) -- seq )
[ unclip ] dip swap slip prefix ; inline
2008-01-09 14:44:07 -05:00
: add-dots ( seq -- seq )
[ [ "" ] [
dup first mark-above?
[ CHAR: combining-dot-above prefix ] when
] if-empty ] with-rest ;
2008-01-09 14:44:07 -05:00
: lithuanian>lower ( string -- lower )
"i" split add-dots "i" join
"j" split add-dots "i" join ;
2008-01-09 14:44:07 -05:00
: turk>upper ( string -- upper-i )
"i" "I\u000307" replace ;
2008-01-09 14:44:07 -05:00
: turk>lower ( string -- lower-i )
"I\u000307" "i" replace
"I" "\u000131" replace ;
2008-01-09 14:44:07 -05:00
: fix-sigma-end ( string -- string )
[ "" ] [
dup peek CHAR: greek-small-letter-sigma =
[ 1 head* CHAR: greek-small-letter-final-sigma suffix ] when
] if-empty ;
2008-01-09 14:44:07 -05:00
: sigma-map ( string -- string )
{ CHAR: greek-capital-letter-sigma } split [ [
[ { CHAR: greek-small-letter-sigma } ] [
dup first uncased?
CHAR: greek-small-letter-final-sigma
CHAR: greek-small-letter-sigma ? prefix
] if-empty
] map ] with-rest concat fix-sigma-end ;
2008-01-09 14:44:07 -05:00
: final-sigma ( string -- string )
CHAR: greek-capital-letter-sigma
over member? [ sigma-map ] when ;
2008-01-09 14:44:07 -05:00
: map-case ( string string-quot char-quot -- case )
[
2008-08-23 23:35:29 -04:00
[
[ dup special-casing at ] 2dip
[ [ % ] compose ] [ [ , ] compose ] bi* ?if
] 2curry each
2008-02-01 19:36:20 -05:00
] "" make ; inline
2009-01-08 00:54:19 -05:00
PRIVATE>
: >lower ( string -- lower )
i-dot? [ turk>lower ] when final-sigma
2009-01-08 00:54:19 -05:00
[ lower>> ] [ ch>lower ] map-case ;
: >upper ( string -- upper )
i-dot? [ turk>upper ] when
[ upper>> ] [ ch>upper ] map-case ;
<PRIVATE
2009-01-08 00:54:19 -05:00
: (>title) ( string -- title )
i-dot? [ turk>upper ] when
2009-01-08 00:54:19 -05:00
[ title>> ] [ ch>title ] map-case ;
: title-word ( string -- title )
unclip 1string [ >lower ] [ (>title) ] bi* prepend ;
2009-01-08 00:54:19 -05:00
2009-01-07 18:59:01 -05:00
PRIVATE>
2009-01-08 00:54:19 -05:00
2008-01-09 14:44:07 -05:00
: >title ( string -- title )
2009-01-08 00:54:19 -05:00
final-sigma >words [ title-word ] map concat ;
2008-01-09 14:44:07 -05:00
: >case-fold ( string -- fold )
>upper >lower ;
: lower? ( string -- ? ) dup >lower = ;
: upper? ( string -- ? ) dup >upper = ;
: title? ( string -- ? ) dup >title = ;
: case-fold? ( string -- ? ) dup >case-fold = ;