unicode: make this the API for all unicode things.

basis/alien/libraries/finder/linux/linux.factor

@@ -3,7 +3,7 @@
 USING: alien.libraries.finder arrays assocs
 combinators.short-circuit io io.encodings.utf8 io.files
 io.files.info io.launcher kernel sequences sets splitting system
-unicode.categories ;
+unicode ;
 IN: alien.libraries.finder.linux
 
 <PRIVATE

basis/csv/csv.factor

@@ -2,7 +2,7 @@
 ! See http://factorcode.org/license.txt for BSD license.
 USING: combinators fry io io.files io.streams.string kernel
 make math memoize namespaces sbufs sequences sequences.private
-unicode.categories ;
+unicode ;
 IN: csv
 
 SYMBOL: delimiter

basis/db/postgresql/postgresql-tests.factor

@@ -1,6 +1,6 @@
 USING: accessors alien continuations db db.errors db.queries db.postgresql
 db.private db.tester db.tuples db.types io classes kernel math namespaces
-prettyprint sequences system tools.test unicode.case ;
+prettyprint sequences system tools.test unicode ;
 IN: db.postgresql.tests
 
 : nonexistant-db ( -- db )

basis/db/sqlite/sqlite-tests.factor

@@ -1,6 +1,6 @@
 USING: io io.files io.files.temp io.directories io.launcher
 kernel namespaces prettyprint tools.test db.sqlite db sequences
-continuations db.types db.tuples unicode.case accessors arrays
+continuations db.types db.tuples unicode accessors arrays
 sorting layouts math.parser ;
 IN: db.sqlite.tests
 

basis/documents/elements/elements.factor

@@ -1,7 +1,7 @@
 ! Copyright (C) 2006, 2009 Slava Pestov.
 ! See http://factorcode.org/license.txt for BSD license.
 USING: arrays combinators documents fry kernel math sequences
-accessors unicode.categories unicode.breaks combinators.short-circuit ;
+accessors unicode combinators.short-circuit ;
 IN: documents.elements
 
 GENERIC: prev-elt ( loc document elt -- newloc )

basis/english/english.factor

@@ -1,7 +1,7 @@
 ! Copyright (C) 2015 John Benediktsson
 ! See http://factorcode.org/license.txt for BSD license
 USING: assocs assocs.extras combinators formatting kernel literals
-locals math math.parser sequences splitting unicode.case ;
+locals math math.parser sequences splitting unicode ;
 
 IN: english
 

basis/farkup/farkup.factor

@@ -3,7 +3,7 @@
 USING: sequences kernel splitting lists fry accessors assocs math.order
 math combinators namespaces urls.encoding xml.syntax xmode.code2html
 xml.data arrays strings vectors xml.writer io.streams.string locals
-unicode.categories ;
+unicode ;
 IN: farkup
 
 SYMBOL: relative-link-prefix

basis/formatting/formatting.factor

@@ -4,8 +4,7 @@ USING: accessors arrays assocs calendar combinators
 combinators.smart fry generalizations io io.streams.string
 kernel macros math math.functions math.parser namespaces
 peg.ebnf present prettyprint quotations sequences
-sequences.generalizations strings unicode.case
+sequences.generalizations strings unicode vectors ;
-unicode.categories vectors ;
 FROM: math.parser.private => format-float ;
 IN: formatting
 

basis/ftp/server/server.factor

@@ -8,7 +8,7 @@ io.files io.files.info io.files.types io.pathnames
 io.servers io.sockets io.streams.string io.timeouts
 kernel logging math math.bitwise math.parser namespaces
 sequences simple-tokenizer splitting strings threads
-tools.files unicode.case ;
+tools.files unicode ;
 IN: ftp.server
 
 SYMBOL: server

basis/globs/globs.factor

@@ -3,7 +3,7 @@
 USING: accessors arrays combinators combinators.short-circuit
 io.directories io.files io.files.info io.pathnames kernel locals
 make peg.ebnf regexp regexp.combinators sequences splitting
-strings system unicode.case ;
+strings system unicode ;
 IN: globs
 
 : not-path-separator ( -- sep )

basis/help/apropos/apropos.factor

@@ -3,8 +3,7 @@
 USING: accessors arrays assocs fry help.markup help.topics io
 kernel make math math.parser namespaces sequences sorting
 summary tools.completion vocabs.hierarchy help.vocabs
-vocabs words unicode.case help unicode.categories
+vocabs words unicode help combinators locals ;
-combinators locals ;
 IN: help.apropos
 
 : $completions ( seq -- )

basis/help/lint/checks/checks.factor

@@ -5,8 +5,8 @@ classes.tuple combinators combinators.short-circuit debugger
 definitions effects eval formatting fry grouping help
 help.markup help.topics io io.streams.string kernel macros math
 namespaces sequences sequences.deep sets splitting strings
-summary tools.destructors unicode.categories vocabs
+summary tools.destructors unicode vocabs vocabs.loader words
-vocabs.loader words words.constant words.symbol ;
+words.constant words.symbol ;
 IN: help.lint.checks
 
 ERROR: simple-lint-error message ;

basis/help/search/search.factor

@@ -4,8 +4,8 @@
 USING: arrays assocs combinators combinators.short-circuit fry
 help help.apropos help.markup help.stylesheet help.topics io
 io.streams.string io.styles kernel math memoize namespaces
-sequences sequences.deep sorting splitting strings unicode.case
+sequences sequences.deep sorting splitting strings unicode
-unicode.categories words ;
+words ;
 
 IN: help.search
 

basis/help/tutorial/tutorial.factor

@@ -1,7 +1,6 @@
 USING: help.markup help.syntax ui.commands ui.operations
 editors vocabs.loader kernel sequences prettyprint tools.test
-vocabs.refresh strings unicode.categories unicode.case
+vocabs.refresh strings unicode ui.tools.browser ui.tools.common ;
-ui.tools.browser ui.tools.common ;
 IN: help.tutorial
 
 ARTICLE: "first-program-start" "Creating a vocabulary for your first program"

basis/html/templates/chloe/syntax/syntax.factor

@@ -2,7 +2,7 @@
 ! See http://factorcode.org/license.txt for BSD license.
 USING: accessors sequences combinators kernel namespaces classes.tuple
 assocs splitting words arrays memoize parser lexer io io.files
-io.encodings.utf8 io.streams.string unicode.case mirrors fry math urls
+io.encodings.utf8 io.streams.string unicode mirrors fry math urls
 multiline xml xml.data xml.writer xml.syntax html.components
 html.templates ;
 IN: html.templates.chloe.syntax

basis/http/server/dispatchers/dispatchers.factor

@@ -1,7 +1,7 @@
 ! Copyright (C) 2008 Slava Pestov.
 ! See http://factorcode.org/license.txt for BSD license.
 USING: kernel namespaces sequences assocs accessors splitting
-unicode.case urls http http.server http.server.responses ;
+unicode urls http http.server http.server.responses ;
 IN: http.server.dispatchers
 
 TUPLE: dispatcher default responders ;

basis/http/server/server.factor

@@ -19,7 +19,7 @@ io.servers
 io.timeouts
 io.crlf
 fry logging logging.insomniac calendar urls
-unicode.categories
+unicode
 http
 http.server.requests
 http.server.responses

basis/images/loader/gtk/gtk.factor

@@ -3,7 +3,7 @@
 USING: accessors alien.c-types alien.data alien.syntax arrays assocs
 combinators destructors gdk.pixbuf.ffi glib.ffi gobject.ffi grouping images
 images.loader io kernel locals math sequences system
-specialized-arrays unicode.case ;
+specialized-arrays unicode ;
 IN: images.loader.gtk
 SPECIALIZED-ARRAY: uchar
 

basis/io/directories/search/search.factor

@@ -3,7 +3,7 @@
 USING: accessors arrays assocs continuations deques dlists fry
 io.backend io.directories io.files.info io.pathnames kernel
 kernel.private locals math sequences sequences.extras sorting
-strings system unicode.case vocabs ;
+strings system unicode vocabs ;
 IN: io.directories.search
 
 : qualified-directory-entries ( path -- seq )

basis/io/sockets/secure/openssl/openssl.factor

@@ -7,7 +7,7 @@ io.binary io.buffers io.encodings.8-bit.latin1 io.encodings.utf8
 io.files io.pathnames io.ports io.sockets io.sockets.secure
 io.timeouts kernel libc locals math math.functions math.order
 math.parser memoize namespaces openssl openssl.libcrypto
-openssl.libssl random sequences sets splitting unicode.case ;
+openssl.libssl random sequences sets splitting unicode ;
 IN: io.sockets.secure.openssl
 
 GENERIC: ssl-method ( symbol -- method )

basis/io/standard-paths/windows/windows.factor

@@ -2,7 +2,7 @@
 ! See http://factorcode.org/license.txt for BSD license.
 USING: environment fry io.directories.search.windows io.files
 io.pathnames io.standard-paths kernel sequences splitting
-system unicode.case ;
+system unicode ;
 IN: io.standard-paths.windows
 
 M: windows find-in-applications

basis/math/statistics/statistics-docs.factor

@@ -105,7 +105,7 @@ HELP: histogram-by
 { $description "Returns a hashtable where the keys are the elements of the sequence binned by being passed through " { $snippet "quot" } ", and the values are the number of times members of each bin appeared in that sequence." }
 { $examples
     { $unchecked-example "! Count the number of times letters and non-letters appear in a sequence."
-               "USING: prettyprint math.statistics unicode.categories ;"
+               "USING: prettyprint math.statistics unicode ;"
                "\"aaa123bc\" [ letter? ] histogram-by ."
                "H{ { t 5 } { f 3 } }"
     }

basis/models/search/search.factor

@@ -1,6 +1,6 @@
 ! Copyright (C) 2008, 2009 Slava Pestov
 ! See http://factorcode.org/license.txt for BSD license.
-USING: fry kernel models.arrow.smart sequences unicode.case ;
+USING: fry kernel models.arrow.smart sequences unicode ;
 IN: models.search
 
 : <search> ( values search quot -- model )

basis/peg/ebnf/ebnf-tests.factor

@@ -3,7 +3,7 @@
 !
 USING: kernel tools.test peg peg.ebnf peg.ebnf.private words
 math math.parser sequences accessors peg.parsers parser
-namespaces arrays strings eval unicode.data multiline ;
+namespaces arrays strings eval unicode multiline ;
 IN: peg.ebnf.tests
 
 { T{ ebnf-non-terminal f "abc" } } [

basis/peg/ebnf/ebnf.factor

@@ -3,7 +3,7 @@
 USING: accessors assocs combinators combinators.short-circuit
 effects kernel make math math.parser multiline namespaces parser
 peg peg.parsers quotations sequences sequences.deep splitting
-stack-checker strings strings.parser summary unicode.categories
+stack-checker strings strings.parser summary unicode
 vocabs.parser words ;
 FROM: vocabs.parser => search ;
 FROM: peg.search => replace ;

basis/peg/parsers/parsers-docs.factor

@@ -1,7 +1,7 @@
 ! Copyright (C) 2008 Chris Double, Doug Coleman.
 ! See http://factorcode.org/license.txt for BSD license.
 USING: help.markup help.syntax kernel math sequences
-unicode.categories strings ;
+unicode strings ;
 IN: peg.parsers
 
 HELP: 1token

basis/peg/parsers/parsers.factor

@@ -1,8 +1,7 @@
 ! Copyright (C) 2007, 2008 Chris Double, Doug Coleman.
 ! See http://factorcode.org/license.txt for BSD license.
-USING: kernel sequences strings namespaces make math assocs
+USING: accessors kernel make math math.parser math.ranges peg
-vectors arrays math.parser accessors unicode.categories
+peg.private peg.search sequences strings unicode vectors ;
-sequences.deep peg peg.private peg.search math.ranges words ;
 IN: peg.parsers
 
 TUPLE: just-parser p1 ;

basis/peg/peg.factor

@@ -3,8 +3,7 @@
 USING: accessors arrays assocs classes combinators
 combinators.short-circuit compiler.units effects.parser fry
 generalizations kernel locals make math math.order namespaces
-quotations sequences sets splitting unicode.categories vectors
+quotations sequences sets splitting unicode vectors words ;
-words ;
 IN: peg
 
 TUPLE: parse-result remaining ast ;

basis/regexp/classes/classes.factor

@@ -1,9 +1,8 @@
 ! Copyright (C) 2008, 2009 Doug Coleman, Daniel Ehrenberg.
 ! See http://factorcode.org/license.txt for BSD license.
-USING: accessors kernel math math.order words combinators
+USING: accessors arrays assocs classes combinators
-combinators.smart combinators.short-circuit locals
+combinators.short-circuit combinators.smart fry kernel locals
-unicode.categories sequences fry macros arrays assocs sets
+math math.order sequences sets unicode unicode.data ;
-classes unicode.script unicode.data ;
 FROM: ascii => ascii? ;
 IN: regexp.classes
 

basis/regexp/compiler/compiler.factor

@@ -1,10 +1,9 @@
 ! Copyright (C) 2009 Daniel Ehrenberg.
 ! See http://factorcode.org/license.txt for BSD license.
-USING: regexp.classes kernel sequences regexp.negation
+USING: accessors assocs combinators combinators.short-circuit
-quotations assocs fry math locals combinators sets
+fry kernel kernel.private locals math namespaces regexp.classes
-accessors words compiler.units kernel.private strings
+regexp.transition-tables sequences sequences.private sets
-sequences.private arrays namespaces unicode.breaks
+strings unicode words ;
-regexp.transition-tables combinators.short-circuit ;
 IN: regexp.compiler
 
 GENERIC: question>quot ( question -- quot )

basis/regexp/dfa/dfa.factor

@@ -1,8 +1,7 @@
 ! Copyright (C) 2008, 2009 Doug Coleman, Daniel Ehrenberg.
 ! See http://factorcode.org/license.txt for BSD license.
-USING: accessors arrays assocs combinators fry kernel locals
+USING: accessors arrays assocs fry kernel locals regexp.ast
-math math.order regexp.nfa regexp.transition-tables sequences
+regexp.classes regexp.transition-tables sequences sets vectors ;
-sets sorting vectors regexp.ast regexp.classes ;
 IN: regexp.dfa
 
 : find-delta ( states transition nfa -- new-states )

basis/regexp/disambiguate/disambiguate.factor

@@ -1,8 +1,8 @@
 ! Copyright (C) 2009 Daniel Ehrenberg.
 ! See http://factorcode.org/license.txt for BSD license.
-USING: kernel accessors regexp.classes math.bits assocs sequences
+USING: accessors arrays assocs fry kernel locals math math.bits
-arrays sets regexp.dfa math fry regexp.minimize regexp.ast
+regexp.ast regexp.classes regexp.transition-tables sequences
-locals regexp.transition-tables ;
+sets ;
 IN: regexp.disambiguate
 
 TUPLE: parts in out ;

basis/regexp/minimize/minimize.factor

@@ -1,8 +1,8 @@
 ! Copyright (C) 2009 Daniel Ehrenberg
 ! See http://factorcode.org/license.txt for BSD license.
-USING: kernel sequences regexp.transition-tables fry assocs
+USING: accessors arrays assocs combinators.short-circuit fry
-accessors locals math sorting arrays sets hashtables regexp.dfa
+hashtables kernel locals math regexp.classes
-combinators.short-circuit regexp.classes ;
+regexp.transition-tables sequences sets sorting ;
 IN: regexp.minimize
 
 : table>state-numbers ( table -- assoc )

basis/regexp/negation/negation.factor

@@ -1,9 +1,9 @@
 ! Copyright (C) 2009 Daniel Ehrenberg.
 ! See http://factorcode.org/license.txt for BSD license.
-USING: regexp.nfa regexp.disambiguate kernel sequences
+USING: accessors assocs fry hashtables kernel namespaces
-assocs regexp.classes hashtables accessors fry vectors
+regexp.ast regexp.classes regexp.dfa regexp.disambiguate
-regexp.ast regexp.transition-tables regexp.minimize
+regexp.minimize regexp.nfa regexp.transition-tables sequences
-regexp.dfa namespaces sets ;
+sets vectors ;
 IN: regexp.negation
 
 CONSTANT: fail-state -1

basis/regexp/nfa/nfa.factor

@@ -1,13 +1,11 @@
 ! Copyright (C) 2008, 2009 Doug Coleman, Daniel Ehrenberg.
 ! See http://factorcode.org/license.txt for BSD license.
-USING: accessors arrays assocs grouping kernel locals math namespaces
+USING: accessors arrays assocs combinators.short-circuit fry
-sequences fry quotations math.order math.ranges vectors
+kernel locals math memoize namespaces regexp.ast regexp.classes
-unicode.categories regexp.transition-tables words sets hashtables
+regexp.transition-tables sequences sets unicode vectors ;
-combinators.short-circuit unicode.data regexp.ast
-regexp.classes memoize ;
 IN: regexp.nfa
 
-! This uses unicode.data for ch>upper and ch>lower
+! This uses unicode for ch>upper and ch>lower
 ! but case-insensitive matching should be done by case-folding everything
 ! before processing starts
 

basis/regexp/parser/parser.factor

@@ -1,10 +1,9 @@
 ! Copyright (C) 2008, 2009 Doug Coleman, Daniel Ehrenberg.
 ! See http://factorcode.org/license.txt for BSD license.
-USING: peg.ebnf kernel math.parser sequences assocs arrays fry math
+USING: accessors arrays assocs combinators
-combinators regexp.classes strings splitting peg locals accessors
+combinators.short-circuit interval-maps kernel locals
-regexp.ast unicode.case unicode.script.private unicode.categories
+math.parser memoize peg.ebnf regexp.ast regexp.classes sequences
-memoize interval-maps sets unicode.data combinators.short-circuit
+sets splitting strings unicode unicode.data unicode.script ;
-namespaces ;
 IN: regexp.parser
 
 : allowed-char? ( ch -- ? )

basis/regexp/transition-tables/transition-tables.factor

@@ -1,7 +1,7 @@
 ! Copyright (C) 2008 Doug Coleman.
 ! See http://factorcode.org/license.txt for BSD license.
-USING: accessors arrays assocs fry hashtables kernel sequences
+USING: accessors arrays assocs fry hashtables kernel locals
-vectors locals regexp.classes sets ;
+regexp.classes sequences sets vectors ;
 IN: regexp.transition-tables
 
 TUPLE: transition-table transitions start-state final-states ;

basis/roman/roman.factor

@@ -4,7 +4,7 @@ USING: accessors arrays assocs combinators.smart effects
 effects.parser fry generalizations grouping kernel lexer macros
 math math.order math.vectors namespaces parser quotations
 sequences sequences.private splitting.monotonic stack-checker
-strings unicode.case words ;
+strings unicode words ;
 IN: roman
 
 <PRIVATE

basis/sequences/parser/parser-tests.factor

@@ -1,5 +1,4 @@
-USING: tools.test sequences.parser unicode.categories kernel
+USING: tools.test sequences.parser unicode kernel accessors ;
-accessors ;
 IN: sequences.parser.tests
 
 { "hello" }

basis/sequences/parser/parser.factor

@@ -2,7 +2,7 @@
 ! See http://factorcode.org/license.txt for BSD license.
 USING: accessors circular combinators.short-circuit fry io
 kernel locals math math.order sequences sorting.functor
-sorting.slots unicode.categories sequences.private ;
+sorting.slots unicode sequences.private ;
 IN: sequences.parser
 
 TUPLE: sequence-parser sequence n ;

basis/sorting/human/human.factor

@@ -1,8 +1,7 @@
 ! Copyright (C) 2008, 2010 Doug Coleman, Slava Pestov.
 ! See http://factorcode.org/license.txt for BSD license.
 USING: accessors fry kernel make math math.order math.parser
-sequences sorting.functor strings unicode.case
+sequences sorting.functor strings unicode ;
-unicode.categories unicode.collation ;
 IN: sorting.human
 
 : cut-find ( sequence pred -- before after )

basis/sorting/title/title.factor

@@ -1,7 +1,7 @@
 ! Copyright (C) 2009 Doug Coleman.
 ! See http://factorcode.org/license.txt for BSD license.
 USING: sorting.functor regexp kernel accessors sequences
-unicode.case ;
+unicode ;
 IN: sorting.title
 
 << "title" [

basis/tools/completion/completion.factor

@@ -4,8 +4,8 @@ USING: accessors arrays assocs colors.constants combinators
 combinators.short-circuit fry io.directories io.files
 io.files.info io.pathnames kernel locals make math math.order
 sequences sequences.private sorting splitting
-splitting.monotonic unicode.categories unicode.data vectors
+splitting.monotonic unicode unicode.data vectors vocabs
-vocabs vocabs.hierarchy ;
+vocabs.hierarchy ;
 IN: tools.completion
 
 <PRIVATE

basis/tools/files/unix/unix.factor

@@ -1,6 +1,6 @@
 ! Copyright (C) 2008 Doug Coleman.
 ! See http://factorcode.org/license.txt for BSD license.
-USING: accessors combinators kernel system unicode.case io.files
+USING: accessors combinators kernel system unicode io.files
 io.files.info io.files.info.unix generalizations
 strings arrays sequences math.parser unix.groups unix.users
 tools.files.private unix.stat math fry macros combinators.smart

basis/tools/scaffold/scaffold-tests.factor

@@ -1,7 +1,7 @@
 ! Copyright (C) 2009 Doug Coleman.
 ! See http://factorcode.org/license.txt for BSD license.
 USING: help.markup io.streams.string kernel sequences
-tools.scaffold tools.scaffold.private tools.test unicode.case ;
+tools.scaffold tools.scaffold.private tools.test unicode ;
 IN: tools.scaffold.tests
 
 : undocumented-word ( obj1 obj2 -- obj3 obj4 )

basis/tools/scaffold/scaffold.factor

@@ -5,7 +5,7 @@ classes combinators combinators.short-circuit fry hashtables
 help.markup interpolate io io.directories io.encodings.utf8
 io.files io.pathnames io.streams.string kernel math math.parser
 namespaces prettyprint quotations sequences sets sorting
-splitting strings system timers unicode.categories urls vocabs
+splitting strings system timers unicode urls vocabs
 vocabs.loader vocabs.metadata words words.symbol ;
 IN: tools.scaffold
 

basis/tools/test/test.factor

@@ -5,7 +5,7 @@ compiler.units continuations debugger effects fry
 generalizations io kernel lexer locals macros namespaces parser
 prettyprint quotations sequences sequences.generalizations
 source-files source-files.errors source-files.errors.debugger
-splitting stack-checker summary tools.errors unicode.case vocabs
+splitting stack-checker summary tools.errors unicode vocabs
 vocabs.files vocabs.metadata vocabs.parser words ;
 FROM: vocabs.hierarchy => load ;
 IN: tools.test

basis/ui/backend/cocoa/views/views.factor

@@ -7,7 +7,7 @@ cocoa.views combinators core-foundation.strings core-graphics
 core-graphics.types core-text io.encodings.utf8 kernel literals
 locals math math.rectangles namespaces opengl sequences threads
 ui.gadgets ui.gadgets.private ui.gadgets.worlds ui.gestures
-ui.private unicode.case ;
+ui.private unicode ;
 IN: ui.backend.cocoa.views
 
 : send-mouse-moved ( view event -- )

basis/ui/commands/commands.factor

@@ -1,8 +1,7 @@
 ! Copyright (C) 2006, 2008 Slava Pestov.
 ! See http://factorcode.org/license.txt for BSD license.
 USING: accessors assocs fry help.markup kernel make quotations
-sequences splitting tr ui.gestures unicode.case unicode.categories
+sequences splitting tr ui.gestures unicode words ;
-words ;
 IN: ui.commands
 
 SYMBOL: +nullary+

basis/ui/gadgets/editors/editors.factor

@@ -9,7 +9,7 @@ sorting splitting timers ui.baseline-alignment ui.clipboards
 ui.commands ui.gadgets ui.gadgets.borders
 ui.gadgets.line-support ui.gadgets.menus ui.gadgets.scrollers
 ui.gadgets.theme ui.gestures ui.pens.solid ui.render ui.text
-unicode.categories ;
+unicode ;
 EXCLUDE: fonts => selection ;
 IN: ui.gadgets.editors
 

basis/unicode/breaks/breaks-docs.factor

@@ -1,4 +1,4 @@
-USING: help.syntax help.markup strings ;
+USING: help.syntax help.markup strings unicode ;
 IN: unicode.breaks
 
 ABOUT: "unicode.breaks"

basis/unicode/breaks/breaks.factor

@@ -1,11 +1,8 @@
 ! Copyright (C) 2008 Daniel Ehrenberg.
 ! See http://factorcode.org/license.txt for BSD license.
-USING: accessors alien.syntax arrays assocs combinators
+USING: accessors arrays assocs combinators fry interval-maps
-combinators.short-circuit compiler.units fry interval-maps io
+kernel literals locals math namespaces parser sequences
-io.encodings.ascii io.files kernel literals locals make math
+simple-flat-file unicode.categories unicode.data
-math.parser math.ranges memoize namespaces parser sequences
-sets simple-flat-file splitting unicode.categories
-unicode.categories.syntax unicode.data unicode.normalize
 unicode.normalize.private words words.constant ;
 IN: unicode.breaks
 
@@ -105,38 +102,6 @@ define-constant
 : grapheme-break? ( class1 class2 -- ? )
     grapheme-table nth nth not ;
 
-PRIVATE>
-
-: first-grapheme ( str -- i )
-    unclip-slice grapheme-class over
-    [ grapheme-class [ nip ] [ grapheme-break? ] 2bi ] find drop
-    nip swap length or 1 + ;
-
-: first-grapheme-from ( start str -- i )
-    over tail-slice first-grapheme + ;
-
-: last-grapheme ( str -- i )
-    unclip-last-slice grapheme-class swap
-    [ grapheme-class dup rot grapheme-break? ] find-last drop ?1+ nip ;
-
-: last-grapheme-from ( end str -- i )
-    swap head-slice last-grapheme ;
-
-<PRIVATE
-
-: >pieces ( str quot: ( str -- i ) -- graphemes )
-    [ dup empty? not ] swap '[ dup @ cut-slice swap ] produce nip ; inline
-
-PRIVATE>
-
-: >graphemes ( str -- graphemes )
-    [ first-grapheme ] >pieces ;
-
-: string-reverse ( str -- rts )
-    >graphemes reverse! concat ;
-
-<PRIVATE
-
 ! Word breaks
 <<
 CONSTANT: wOther 0
@@ -253,37 +218,3 @@ define-constant
     ] if ;
 
 PRIVATE>
-
- : first-word ( str -- i )
-    [ [ length ] [ first word-break-prop ] bi ] keep
-    1 swap dup '[ _ word-break-next ] find-index-from
-    drop nip swap or ;
-
-: >words ( str -- words )
-    [ first-word ] >pieces ;
-
-<PRIVATE
-
-: nth-next ( i str -- str[i-1] str[i] )
-    [ [ 1 - ] keep ] dip '[ _ nth ] bi@ ;
-
-PRIVATE>
-
-: word-break-at? ( i str -- ? )
-    {
-        [ drop zero? ]
-        [ length = ]
-        [
-            [ nth-next [ word-break-prop ] dip ] 2keep
-            word-break-next nip
-        ]
-    } 2|| ;
-
-: first-word-from ( start str -- i )
-    over tail-slice first-word + ;
-
-: last-word ( str -- i )
-    [ length iota ] keep '[ _ word-break-at? ] find-last drop 0 or ;
-
-: last-word-from ( end str -- i )
-    swap head-slice last-word ;

basis/unicode/case/case-docs.factor

@@ -1,4 +1,4 @@
-USING: help.syntax help.markup kernel strings ;
+USING: help.syntax help.markup kernel strings unicode ;
 IN: unicode.case
 
 ABOUT: "unicode.case"

basis/unicode/case/case.factor

@@ -1,9 +1,7 @@
 ! Copyright (C) 2008, 2009 Daniel Ehrenberg.
 ! See http://factorcode.org/license.txt for BSD license.
-USING: unicode.data sequences namespaces
+USING: combinators.short-circuit kernel locals namespaces sbufs
-sbufs make unicode.normalize math hints
+sequences splitting unicode.categories unicode.data ;
-unicode.categories combinators assocs combinators.short-circuit
-strings splitting kernel accessors unicode.breaks fry locals ;
 QUALIFIED: ascii
 IN: unicode.case
 
@@ -52,10 +50,13 @@ SYMBOL: locale ! Just casing locale, or overall?
         [ 1 head* CHAR: greek-small-letter-final-sigma suffix ] when
     ] if-empty ; inline
 
+! this duplicate unicode to prevent dependencies
+CATEGORY-NOT: (uncased) Lu Ll Lt Lm Mn Me ;
+
 : sigma-map ( string -- string )
     { CHAR: greek-capital-letter-sigma } split [ [
         [ { CHAR: greek-small-letter-sigma } ] [
-            dup first uncased?
+            dup first (uncased)?
             CHAR: greek-small-letter-final-sigma
             CHAR: greek-small-letter-sigma ? prefix
         ] if-empty
@@ -85,43 +86,3 @@ SYMBOL: locale ! Just casing locale, or overall?
     [ lithuanian? [ lithuanian>upper ] when ] bi ;
 
 PRIVATE>
-
-: >lower ( string -- lower )
-    locale>lower final-sigma
-    [ lower>> ] [ ch>lower ] map-case ;
-
-HINTS: >lower string ;
-
-: >upper ( string -- upper )
-    locale>upper
-    [ upper>> ] [ ch>upper ] map-case ;
-
-HINTS: >upper string ;
-
-<PRIVATE
-
-: (>title) ( string -- title )
-    locale>upper
-    [ title>> ] [ ch>title ] map-case ; inline
-
-PRIVATE>
-
-: capitalize ( string -- title )
-    unclip-slice 1string [ >lower ] [ (>title) ] bi*
-    "" prepend-as ; inline
-
-: >title ( string -- title )
-    final-sigma >words [ capitalize ] map! concat ;
-
-HINTS: >title string ;
-
-: >case-fold ( string -- fold )
-    >upper >lower ;
-
-: lower? ( string -- ? ) dup >lower = ;
-
-: upper? ( string -- ? ) dup >upper = ;
-
-: title? ( string -- ? ) dup >title = ;
-
-: case-fold? ( string -- ? ) dup >case-fold = ;

basis/unicode/categories/categories-docs.factor

@@ -1,66 +1,21 @@
-! Copyright (C) 2009 Daniel Ehrenberg
+! Copyright (C) 2008 Daniel Ehrenberg.
 ! See http://factorcode.org/license.txt for BSD license.
-USING: help.markup help.syntax kernel ;
+USING: help.syntax help.markup ;
 IN: unicode.categories
 
-HELP: LETTER
+ABOUT: "unicode.categories"
-{ $class-description "The class of upper cased letters." } ;
 
-HELP: Letter
+ARTICLE: "unicode.categories" "Unicode category syntax"
-{ $class-description "The class of letters." } ;
+"There is special syntax sugar for making predicate classes which are unions of Unicode general categories, plus some other code."
-
-HELP: alpha
-{ $class-description "The class of alphanumeric characters." } ;
-
-HELP: math
-{ $class-description "The class of Unicode math characters." } ;
-
-HELP: blank
-{ $class-description "The class of whitespace characters." } ;
-
-HELP: character
-{ $class-description "The class of pre-defined Unicode code points." } ;
-
-HELP: control
-{ $class-description "The class of control characters." } ;
-
-HELP: digit
-{ $class-description "The class of digits." } ;
-
-HELP: letter
-{ $class-description "The class of lower-cased letters." } ;
-
-HELP: printable
-{ $class-description "The class of characters which are printable, as opposed to being control or formatting characters." } ;
-
-HELP: uncased
-{ $class-description "The class of letters which don't have a case." } ;
-
-ARTICLE: "unicode.categories" "Character classes"
-"The " { $vocab-link "unicode.categories" } " vocabulary implements predicates for determining if a code point has a particular property, for example being a lower cased letter. These should be used in preference to the " { $vocab-link "ascii" } " equivalents in most cases. Each character class has an associated predicate word."
 { $subsections
-    blank
+    POSTPONE: CATEGORY:
-    blank?
+    POSTPONE: CATEGORY-NOT:
-    letter
-    letter?
-    LETTER
-    LETTER?
-    Letter
-    Letter?
-    digit
-    digit?
-    printable
-    printable?
-    alpha
-    alpha?
-    control
-    control?
-    uncased
-    uncased?
-    character
-    character?
-    math
-    math?
 } ;
 
-ABOUT: "unicode.categories"
+HELP: CATEGORY:
+{ $syntax "CATEGORY: foo Nl Pd Lu | \"Diacritic\" property? ;" }
+{ $description "This defines a predicate class which is a subset of code points. In this example, " { $snippet "foo" } " is the class of characters which are in the general category Nl or Pd or Lu, or which have the Diacritic property." } ;
+
+HELP: CATEGORY-NOT:
+{ $syntax "CATEGORY-NOT: foo Nl Pd Lu | \"Diacritic\" property? ;" }
+{ $description "This defines a predicate class which is a subset of code points, the complement of what " { $link POSTPONE: CATEGORY: } " would define. In this example, " { $snippet "foo" } " is the class of characters which are neither in the general category Nl or Pd or Lu, nor have the Diacritic property." } ;

basis/unicode/categories/categories-tests.factor

@@ -1,19 +1,2 @@
-! Copyright (C) 2008 Daniel Ehrenberg.
+! Copyright (C) 2009 Daniel Ehrenberg.
 ! See http://factorcode.org/license.txt for BSD license.
-USING: tools.test kernel unicode.categories words sequences unicode.data ;
-IN: unicode.categories.tests
-
-{ { f f t t f t t f f t } } [ CHAR: A {
-    blank? letter? LETTER? Letter? digit?
-    printable? alpha? control? uncased? character?
-} [ execute ] with map ] unit-test
-{ "Nd" } [ CHAR: 3 category ] unit-test
-{ "Lo" } [ 0x3400 category ] unit-test
-{ "Lo" } [ 0x3450 category ] unit-test
-{ "Lo" } [ 0x4DB5 category ] unit-test
-{ "Cs" } [ 0xDD00 category ] unit-test
-{ t } [ CHAR: \t blank? ] unit-test
-{ t } [ CHAR: \s blank? ] unit-test
-{ t } [ CHAR: \r blank? ] unit-test
-{ t } [ CHAR: \n blank? ] unit-test
-{ f } [ CHAR: a blank? ] unit-test

basis/unicode/categories/categories.factor

@@ -1,16 +1,34 @@
 ! Copyright (C) 2008 Daniel Ehrenberg.
 ! See http://factorcode.org/license.txt for BSD license.
-USING: unicode.categories.syntax sequences unicode.data ;
+USING: accessors assocs classes.parser classes.predicate fry
+kernel math parser sequences splitting unicode.data
+unicode.data.private ;
 IN: unicode.categories
 
-CATEGORY: blank Zs Zl Zp | "\r\n\t" member? ;
+! For use in CATEGORY:
-CATEGORY: letter Ll | "Other_Lowercase" property? ;
+SYMBOLS: Cn Lu Ll Lt Lm Lo Mn Mc Me Nd Nl No Pc Pd Ps Pe Pi Pf Po Sm Sc Sk So Zs Zl Zp Cc Cf Cs Co | ;
-CATEGORY: LETTER Lu | "Other_Uppercase" property? ;
+
-CATEGORY: Letter Lu Ll Lt Lm Lo Nl ;
+<PRIVATE
-CATEGORY: digit Nd Nl No ;
+
-CATEGORY-NOT: printable Cc Cf Cs Co Cn ;
+: [category] ( categories code -- quot )
-CATEGORY: alpha Lu Ll Lt Lm Lo Nd Nl No | "Other_Alphabetic" property? ;
+    '[ integer>fixnum-strict dup category# _ member? [ drop t ] _ if ] ;
-CATEGORY: control Cc ;
+
-CATEGORY-NOT: uncased Lu Ll Lt Lm Mn Me ;
+: integer-predicate-class ( word predicate -- )
-CATEGORY-NOT: character Cn ;
+    integer swap define-predicate-class ;
-CATEGORY: math Sm | "Other_Math" property? ;
+
+: define-category ( word categories code -- )
+    [category] integer-predicate-class ;
+
+: define-not-category ( word categories code -- )
+    [category] [ not ] compose integer-predicate-class ;
+
+: parse-category ( -- word tokens quot )
+    scan-new-class \ ; parse-until { | } split1
+    [ [ name>> categories-map at ] B{ } map-as ]
+    [ [ [ ] like ] [ [ drop f ] ] if* ] bi* ;
+
+PRIVATE>
+
+SYNTAX: CATEGORY: parse-category define-category ;
+
+SYNTAX: CATEGORY-NOT: parse-category define-not-category ;

basis/unicode/categories/summary.txt

@@ -1 +1 @@
-Unicode character categories
+Parsing words used by Unicode implementation

basis/unicode/categories/syntax/authors.txt

@@ -1 +0,0 @@
-Daniel Ehrenberg

basis/unicode/categories/syntax/summary.txt

@@ -1 +0,0 @@
-Parsing words used by Unicode implementation

basis/unicode/categories/syntax/syntax-docs.factor

@@ -1,21 +0,0 @@
-! Copyright (C) 2008 Daniel Ehrenberg.
-! See http://factorcode.org/license.txt for BSD license.
-USING: help.syntax help.markup ;
-IN: unicode.categories.syntax
-
-ABOUT: "unicode.categories.syntax"
-
-ARTICLE: "unicode.categories.syntax" "Unicode category syntax"
-"There is special syntax sugar for making predicate classes which are unions of Unicode general categories, plus some other code."
-{ $subsections
-    POSTPONE: CATEGORY:
-    POSTPONE: CATEGORY-NOT:
-} ;
-
-HELP: CATEGORY:
-{ $syntax "CATEGORY: foo Nl Pd Lu | \"Diacritic\" property? ;" }
-{ $description "This defines a predicate class which is a subset of code points. In this example, " { $snippet "foo" } " is the class of characters which are in the general category Nl or Pd or Lu, or which have the Diacritic property." } ;
-
-HELP: CATEGORY-NOT:
-{ $syntax "CATEGORY-NOT: foo Nl Pd Lu | \"Diacritic\" property? ;" }
-{ $description "This defines a predicate class which is a subset of code points, the complement of what " { $link POSTPONE: CATEGORY: } " would define. In this example, " { $snippet "foo" } " is the class of characters which are neither in the general category Nl or Pd or Lu, nor have the Diacritic property." } ;

basis/unicode/categories/syntax/syntax-tests.factor

@@ -1,2 +0,0 @@
-! Copyright (C) 2009 Daniel Ehrenberg.
-! See http://factorcode.org/license.txt for BSD license.

basis/unicode/categories/syntax/syntax.factor

@@ -1,34 +0,0 @@
-! Copyright (C) 2008, 2009 Daniel Ehrenberg.
-! See http://factorcode.org/license.txt for BSD license.
-USING: unicode.data kernel math sequences parser unicode.data.private
-bit-arrays namespaces sequences.private arrays classes.parser
-assocs classes.predicate sets fry splitting accessors ;
-IN: unicode.categories.syntax
-
-! For use in CATEGORY:
-SYMBOLS: Cn Lu Ll Lt Lm Lo Mn Mc Me Nd Nl No Pc Pd Ps Pe Pi Pf Po Sm Sc Sk So Zs Zl Zp Cc Cf Cs Co | ;
-
-<PRIVATE
-
-: [category] ( categories code -- quot )
-    '[ integer>fixnum-strict dup category# _ member? [ drop t ] _ if ] ;
-
-: integer-predicate-class ( word predicate -- )
-    integer swap define-predicate-class ;
-
-: define-category ( word categories code -- )
-    [category] integer-predicate-class ;
-
-: define-not-category ( word categories code -- )
-    [category] [ not ] compose integer-predicate-class ;
-
-: parse-category ( -- word tokens quot )
-    scan-new-class \ ; parse-until { | } split1
-    [ [ name>> categories-map at ] B{ } map-as ]
-    [ [ [ ] like ] [ [ drop f ] ] if* ] bi* ;
-
-PRIVATE>
-
-SYNTAX: CATEGORY: parse-category define-category ;
-
-SYNTAX: CATEGORY-NOT: parse-category define-not-category ;

basis/unicode/categories/syntax/tags.txt

@@ -1 +0,0 @@
-text

basis/unicode/collation/collation-docs.factor

@@ -1,5 +1,5 @@
 USING: byte-arrays help.syntax help.markup kernel math.order
-strings ;
+strings unicode ;
 IN: unicode.collation
 
 ARTICLE: "unicode.collation" "Collation and weak comparison"

basis/unicode/collation/collation.factor

@@ -1,13 +1,13 @@
 ! Copyright (C) 2008 Daniel Ehrenberg.
 ! See http://factorcode.org/license.txt for BSD license.
-USING: sequences io.files io.encodings.ascii kernel splitting
+USING: accessors arrays assocs combinators
-accessors math.parser ascii io assocs strings math namespaces make
+combinators.short-circuit kernel locals make math math.order
-sorting combinators math.order arrays unicode.normalize unicode.data
+math.parser namespaces sequences simple-flat-file splitting
-locals macros sequences.deep words unicode.breaks quotations
+strings unicode.data ;
-combinators.short-circuit simple-flat-file ;
 IN: unicode.collation
 
 <PRIVATE
+
 SYMBOL: ducet
 
 TUPLE: weight primary secondary tertiary ignorable? ;
@@ -112,6 +112,7 @@ ducet get-global insert-helpers
             [ [ variable-weight ] each ]
         } cleave
     ] { } make ;
+
 PRIVATE>
 
 : completely-ignorable? ( weight -- ? )
@@ -124,36 +125,3 @@ PRIVATE>
         [ swap ignorable?>> or ]
         [ swap completely-ignorable? or not ] 2bi
     ] filter nip ;
-
-: collation-key ( string -- key )
-    nfd string>graphemes graphemes>weights
-    filter-ignorable weights>bytes ;
-
-<PRIVATE
-: insensitive= ( str1 str2 levels-removed -- ? )
-    [
-        [ collation-key ] dip
-        [ [ 0 = not ] trim-tail but-last ] times
-    ] curry same? ;
-PRIVATE>
-
-: primary= ( str1 str2 -- ? )
-    3 insensitive= ;
-
-: secondary= ( str1 str2 -- ? )
-    2 insensitive= ;
-
-: tertiary= ( str1 str2 -- ? )
-    1 insensitive= ;
-
-: quaternary= ( str1 str2 -- ? )
-    0 insensitive= ;
-
-: w/collation-key ( str -- {str,key} )
-    [ collation-key ] keep 2array ;
-
-: sort-strings ( strings -- sorted )
-    [ w/collation-key ] map natural-sort values ;
-
-: string<=> ( str1 str2 -- <=> )
-    [ w/collation-key ] compare ;

basis/unicode/data/data-docs.factor

@@ -1,6 +1,6 @@
 ! Copyright (C) 2009 Daniel Ehrenberg
 ! See http://factorcode.org/license.txt for BSD license.
-USING: help.syntax help.markup kernel math strings ;
+USING: help.syntax help.markup kernel math strings unicode ;
 IN: unicode.data
 
 ABOUT: "unicode.data"

basis/unicode/data/data.factor

@@ -28,17 +28,12 @@ PRIVATE>
 CONSTANT: name-map H{ }
 
 : canonical-entry ( char -- seq ) canonical-map at ; inline
-: combine-chars ( a b -- char/f ) >2ch combine-map at ; inline
 : compatibility-entry ( char -- seq ) compatibility-map at ; inline
+: combine-chars ( a b -- char/f ) >2ch combine-map at ; inline
 : combining-class ( char -- n ) class-map at ; inline
 : non-starter? ( char -- ? ) combining-class { 0 f } member? not ; inline
-: name>char ( name -- char ) name-map at ; inline
-: char>name ( char -- name ) name-map value-at ; inline
 : property ( property -- interval-map ) properties at ; foldable
 : property? ( char property -- ? ) property interval-sets:in? ; inline
-: ch>lower ( ch -- lower ) simple-lower ?at drop ; inline
-: ch>upper ( ch -- upper ) simple-upper ?at drop ; inline
-: ch>title ( ch -- title ) simple-title ?at drop ; inline
 : special-case ( ch -- casing-tuple ) special-casing at ; inline
 
 ! For non-existent characters, use Cn
@@ -143,7 +138,7 @@ PRIVATE>
     name-map sort-values keys
     [ { [ "first>" tail? ] [ "last>" tail? ] } 1|| ] filter
     2 group [
-        [ name>char ] bi@ [ [a,b] ] [ table ?nth ] bi
+        [ name-map at ] bi@ [ [a,b] ] [ table ?nth ] bi
         [ swap table ?set-nth ] curry each
     ] assoc-each table ;
 
@@ -208,14 +203,15 @@ load-data {
 } cleave
 
 combine-map keys [ 2ch> nip ] map
-[ combining-class ] reject
+[ class-map at ] reject
 [ 0 swap class-map set-at ] each
 
 load-special-casing special-casing swap assoc-union! drop
 
 load-properties properties swap assoc-union! drop
 
-[ name>char [ "Invalid character" throw ] unless* ]
-name>char-hook set-global
-
 PRIVATE>
+
+[
+    name-map at [ "Invalid character" throw ] unless*
+] name>char-hook set-global

basis/unicode/normalize/normalize-docs.factor

@@ -1,4 +1,4 @@
-USING: help.syntax help.markup strings ;
+USING: help.syntax help.markup strings unicode ;
 IN: unicode.normalize
 
 ABOUT: "unicode.normalize"

basis/unicode/normalize/normalize.factor

@@ -89,23 +89,6 @@ HINTS: (nfd) string ;
 
 HINTS: (nfkd) string ;
 
-PRIVATE>
-
-: nfd ( string -- nfd )
-    [ (nfd) ] with-string ;
-
-: nfkd ( string -- nfkd )
-    [ (nfkd) ] with-string ;
-
-: string-append ( s1 s2 -- string )
-    [ append ] keep
-    0 over ?nth non-starter?
-    [ length dupd reorder-back ] [ drop ] if ;
-
-HINTS: string-append string string ;
-
-<PRIVATE
-
 ! Normalization -- Composition
 
 : initial-medial? ( str i -- ? )
@@ -189,9 +172,3 @@ DEFER: compose-iter
 HINTS: combine string ;
 
 PRIVATE>
-
-: nfc ( string -- nfc )
-    [ (nfd) combine ] with-string ;
-
-: nfkc ( string -- nfkc )
-    [ (nfkd) combine ] with-string ;

basis/unicode/script/script-docs.factor

@@ -1,6 +1,6 @@
 ! Copyright (C) 2009 Daniel Ehrenberg
 ! See http://factorcode.org/license.txt for BSD license.
-USING: help.syntax help.markup strings ;
+USING: help.syntax help.markup strings unicode ;
 IN: unicode.script
 
 ABOUT: "unicode.script"

basis/unicode/script/script.factor

@@ -4,15 +4,8 @@ USING: interval-maps namespaces parser simple-flat-file
 words.constant ;
 IN: unicode.script
 
-<PRIVATE
-
 <<
 "script-table" create-word-in
 "vocab:unicode/script/Scripts.txt" load-interval-file
 define-constant
 >>
-
-PRIVATE>
-
-: script-of ( char -- script )
-    script-table interval-at ;

basis/unicode/unicode-docs.factor

@@ -15,7 +15,7 @@ $nl
 { $vocab-subsection "Word and grapheme breaks" "unicode.breaks" }
 { $vocab-subsection "Unicode normalization" "unicode.normalize" }
 "The following are mostly for internal use:"
-{ $vocab-subsection "Unicode category syntax" "unicode.categories.syntax" }
+{ $vocab-subsection "Unicode category syntax" "unicode.categories" }
 { $vocab-subsection "Unicode data tables" "unicode.data" }
 { $see-also "ascii" "io.encodings" } ;
 

basis/unicode/unicode.factor

@@ -1 +1,200 @@
+
+USING: accessors arrays assocs combinators.short-circuit fry
+hints interval-maps kernel math math.order sequences sorting
+strings unicode.breaks.private unicode.case.private
+unicode.categories unicode.collation unicode.collation.private
+unicode.data unicode.data.private unicode.normalize.private
+unicode.script ;
+
 IN: unicode
+
+CATEGORY: blank Zs Zl Zp | "\r\n\t" member? ;
+
+CATEGORY: letter Ll | "Other_Lowercase" property? ;
+
+CATEGORY: LETTER Lu | "Other_Uppercase" property? ;
+
+CATEGORY: Letter Lu Ll Lt Lm Lo Nl ;
+
+CATEGORY: digit Nd Nl No ;
+
+CATEGORY-NOT: printable Cc Cf Cs Co Cn ;
+
+CATEGORY: alpha Lu Ll Lt Lm Lo Nd Nl No | "Other_Alphabetic" property? ;
+
+CATEGORY: control Cc ;
+
+CATEGORY-NOT: uncased Lu Ll Lt Lm Mn Me ;
+
+CATEGORY-NOT: character Cn ;
+
+CATEGORY: math Sm | "Other_Math" property? ;
+
+: script-of ( char -- script )
+    script-table interval-at ;
+
+: name>char ( name -- char ) name-map at ; inline
+
+: char>name ( char -- name ) name-map value-at ; inline
+
+: ch>lower ( ch -- lower ) simple-lower ?at drop ; inline
+
+: ch>upper ( ch -- upper ) simple-upper ?at drop ; inline
+
+: ch>title ( ch -- title ) simple-title ?at drop ; inline
+
+: first-grapheme ( str -- i )
+    unclip-slice grapheme-class over
+    [ grapheme-class [ nip ] [ grapheme-break? ] 2bi ] find drop
+    nip swap length or 1 + ;
+
+: first-grapheme-from ( start str -- i )
+    over tail-slice first-grapheme + ;
+
+: last-grapheme ( str -- i )
+    unclip-last-slice grapheme-class swap
+    [ grapheme-class dup rot grapheme-break? ] find-last drop ?1+ nip ;
+
+: last-grapheme-from ( end str -- i )
+    swap head-slice last-grapheme ;
+
+<PRIVATE
+
+: >pieces ( str quot: ( str -- i ) -- graphemes )
+    [ dup empty? not ] swap '[ dup @ cut-slice swap ] produce nip ; inline
+
+PRIVATE>
+
+: >graphemes ( str -- graphemes )
+    [ first-grapheme ] >pieces ;
+
+: string-reverse ( str -- rts )
+    >graphemes reverse! concat ;
+
+: first-word ( str -- i )
+    [ [ length ] [ first word-break-prop ] bi ] keep
+    1 swap dup '[ _ word-break-next ] find-index-from
+    drop nip swap or ;
+
+: >words ( str -- words )
+    [ first-word ] >pieces ;
+
+<PRIVATE
+
+: nth-next ( i str -- str[i-1] str[i] )
+    [ [ 1 - ] keep ] dip '[ _ nth ] bi@ ;
+
+PRIVATE>
+
+: word-break-at? ( i str -- ? )
+    {
+        [ drop zero? ]
+        [ length = ]
+        [
+            [ nth-next [ word-break-prop ] dip ] 2keep
+            word-break-next nip
+        ]
+    } 2|| ;
+
+: first-word-from ( start str -- i )
+    over tail-slice first-word + ;
+
+: last-word ( str -- i )
+    [ length iota ] keep '[ _ word-break-at? ] find-last drop 0 or ;
+
+: last-word-from ( end str -- i )
+    swap head-slice last-word ;
+
+: >lower ( string -- lower )
+    locale>lower final-sigma
+    [ lower>> ] [ ch>lower ] map-case ;
+
+HINTS: >lower string ;
+
+: >upper ( string -- upper )
+    locale>upper
+    [ upper>> ] [ ch>upper ] map-case ;
+
+HINTS: >upper string ;
+
+<PRIVATE
+
+: (>title) ( string -- title )
+    locale>upper
+    [ title>> ] [ ch>title ] map-case ; inline
+
+PRIVATE>
+
+: capitalize ( string -- title )
+    unclip-slice 1string [ >lower ] [ (>title) ] bi*
+    "" prepend-as ; inline
+
+: >title ( string -- title )
+    final-sigma >words [ capitalize ] map! concat ;
+
+HINTS: >title string ;
+
+: >case-fold ( string -- fold )
+    >upper >lower ;
+
+: lower? ( string -- ? ) dup >lower = ;
+
+: upper? ( string -- ? ) dup >upper = ;
+
+: title? ( string -- ? ) dup >title = ;
+
+: case-fold? ( string -- ? ) dup >case-fold = ;
+
+: nfd ( string -- nfd )
+    [ (nfd) ] with-string ;
+
+: nfkd ( string -- nfkd )
+    [ (nfkd) ] with-string ;
+
+: string-append ( s1 s2 -- string )
+    [ append ] keep
+    0 over ?nth non-starter?
+    [ length dupd reorder-back ] [ drop ] if ;
+
+HINTS: string-append string string ;
+
+: nfc ( string -- nfc )
+    [ (nfd) combine ] with-string ;
+
+: nfkc ( string -- nfkc )
+    [ (nfkd) combine ] with-string ;
+
+: collation-key ( string -- key )
+    nfd string>graphemes graphemes>weights
+    filter-ignorable weights>bytes ;
+
+<PRIVATE
+
+: insensitive= ( str1 str2 levels-removed -- ? )
+    [
+        [ collation-key ] dip
+        [ [ 0 = not ] trim-tail but-last ] times
+    ] curry same? ;
+
+PRIVATE>
+
+: primary= ( str1 str2 -- ? )
+    3 insensitive= ;
+
+: secondary= ( str1 str2 -- ? )
+    2 insensitive= ;
+
+: tertiary= ( str1 str2 -- ? )
+    1 insensitive= ;
+
+: quaternary= ( str1 str2 -- ? )
+    0 insensitive= ;
+
+: w/collation-key ( str -- {str,key} )
+    [ collation-key ] keep 2array ;
+
+: sort-strings ( strings -- sorted )
+    [ w/collation-key ] map natural-sort values ;
+
+: string<=> ( str1 str2 -- <=> )
+    [ w/collation-key ] compare ;

basis/uuid/uuid.factor

@@ -2,7 +2,7 @@
 ! See http://factorcode.org/license.txt for BSD license
 USING: byte-arrays calendar checksums checksums.md5
 checksums.sha io.binary kernel math math.parser math.ranges
-random sequences strings system unicode.case ;
+random sequences strings system unicode ;
 IN: uuid
 
 <PRIVATE

basis/validators/validators.factor

@@ -2,8 +2,7 @@
 ! See http://factorcode.org/license.txt for BSD license.
 USING: arrays assocs classes continuations hashtables kernel
 make math math.functions math.parser math.ranges namespaces
-quotations regexp sequences sets unicode.case unicode.categories
+quotations regexp sequences sets unicode words xmode.catalog ;
-words xmode.catalog ;
 IN: validators
 
 : v-checkbox ( str -- ? )

basis/windows/errors/errors.factor

@@ -1,5 +1,5 @@
 USING: alien.data kernel locals math math.bitwise
-windows.kernel32 sequences byte-arrays unicode.categories
+windows.kernel32 sequences byte-arrays unicode
 io.encodings.string alien.strings arrays literals
 windows.types specialized-arrays math.parser ;
 SPECIALIZED-ARRAY: TCHAR

basis/xml/char-classes/char-classes.factor

@@ -1,6 +1,6 @@
 ! Copyright (C) 2005, 2009 Daniel Ehrenberg
 ! See http://factorcode.org/license.txt for BSD license.
-USING: kernel sequences unicode.categories.syntax math math.order
+USING: kernel sequences unicode.categories math math.order
 combinators hints combinators.short-circuit ;
 IN: xml.char-classes
 

basis/xml/elements/elements.factor

@@ -3,7 +3,7 @@
 USING: kernel namespaces xml.tokenize xml.state xml.name
 xml.data accessors arrays make xml.char-classes fry assocs sequences
 math xml.errors sets combinators io.encodings io.encodings.iana
-unicode.case xml.dtd strings xml.entities unicode.categories ;
+unicode xml.dtd strings xml.entities ;
 IN: xml.elements
 
 : take-interpolated ( quot -- interpolated )

basis/xml/syntax/inverse/inverse.factor

@@ -3,7 +3,7 @@
 USING: accessors arrays assocs combinators
 combinators.short-circuit fry generalizations inverse kernel
 namespaces sequences sequences.generalizations sorting strings
-unicode.categories xml.data xml.syntax xml.syntax.private ;
+unicode xml.data xml.syntax xml.syntax.private ;
 IN: xml.syntax.inverse
 
 : remove-blanks ( seq -- newseq )

basis/xml/syntax/syntax.factor

@@ -5,7 +5,7 @@ effects.parser sequences summary lexer splitting combinators
 locals memoize sequences.deep xml.data xml.state xml namespaces
 present arrays generalizations sequences.generalizations strings
 make math macros multiline combinators.short-circuit sorting fry
-unicode.categories effects ;
+unicode effects ;
 IN: xml.syntax
 
 <PRIVATE

basis/xml/writer/writer.factor

@@ -2,7 +2,7 @@
 ! See http://factorcode.org/license.txt for BSD license.
 USING: hashtables kernel math namespaces sequences strings
 assocs combinators io io.streams.string accessors
-xml.data wrap.strings xml.entities unicode.categories fry ;
+xml.data wrap.strings xml.entities unicode fry ;
 IN: xml.writer
 
 SYMBOL: sensitive-tags

basis/xmode/catalog/catalog.factor

@@ -1,6 +1,6 @@
 USING: accessors assocs globs io.pathnames kernel memoize
 namespaces regexp sequences sorting splitting strings
-unicode.case xml xml.data xml.syntax xml.traversal xmode.loader
+unicode xml xml.data xml.syntax xml.traversal xmode.loader
 xmode.rules xmode.utilities ;
 IN: xmode.catalog
 

basis/xmode/keyword-map/keyword-map.factor

@@ -1,7 +1,7 @@
 ! Copyright (C) 2007, 2008 Slava Pestov.
 ! See http://factorcode.org/license.txt for BSD license.
 USING: accessors kernel strings assocs sequences hashtables
-sorting unicode.case unicode.categories sets ;
+sorting unicode sets ;
 IN: xmode.keyword-map
 
 ! Based on org.gjt.sp.jedit.syntax.KeywordMap

basis/xmode/rules/rules.factor

@@ -1,7 +1,7 @@
 ! Copyright (C) 2008 Slava Pestov.
 ! See http://factorcode.org/license.txt for BSD license.
 USING: accessors xmode.tokens xmode.keyword-map kernel
-sequences vectors assocs strings memoize unicode.case
+sequences vectors assocs strings memoize unicode
 regexp ;
 IN: xmode.rules
 

extra/benchmark/unicode/unicode.factor

@@ -1,6 +1,6 @@
 ! Copyright (C) 2012 John Benediktsson
 ! See http://factorcode.org/license.txt for BSD license.
-USING: kernel math random sequences strings unicode.case ;
+USING: kernel math random sequences strings unicode ;
 IN: benchmark.unicode
 
 : crazy-unicode-string ( -- string )

extra/c/lexer/lexer.factor

@@ -3,7 +3,7 @@
 USING: accessors combinators combinators.short-circuit
 generalizations kernel locals math.order math.ranges
 sequences.parser sequences sequences.generalizations
-sorting.functor sorting.slots unicode.categories ;
+sorting.functor sorting.slots unicode ;
 IN: c.lexer
 
 : take-c-comment ( sequence-parser -- seq/f )

extra/c/preprocessor/preprocessor.factor

@@ -3,8 +3,8 @@
 USING: sequences.parser io io.encodings.utf8 io.files
 io.streams.string kernel combinators accessors io.pathnames
 fry sequences arrays locals namespaces io.directories
-assocs math splitting make unicode.categories
+assocs math splitting make unicode combinators.short-circuit
-combinators.short-circuit c.lexer ;
+c.lexer ;
 IN: c.preprocessor
 
 : initial-library-paths ( -- seq )

extra/cgi/cgi.factor

@@ -3,7 +3,7 @@
 
 USING: arrays assocs combinators environment io kernel
 linked-assocs math.parser regexp sequences splitting strings
-unicode.case urls.encoding ;
+unicode urls.encoding ;
 
 IN: cgi
 

extra/codebook/codebook.factor

@@ -5,7 +5,7 @@ io.directories io.directories.hierarchy io.encodings.binary
 io.encodings.detect io.encodings.utf8 io.files io.files.info
 io.files.temp io.files.types io.files.unique io.launcher
 io.pathnames kernel locals math math.parser namespaces sequences
-sorting strings system unicode.categories xml.syntax xml.writer
+sorting strings system unicode xml.syntax xml.writer
 xmode.catalog xmode.marker xmode.tokens ;
 IN: codebook
 

extra/game/models/loader/loader.factor

@@ -3,7 +3,7 @@
 USING: accessors assocs byte-arrays combinators game.models
 io.encodings.ascii io.files io.pathnames io.streams.byte-array
 kernel namespaces sequences splitting
-strings unicode.case arrays io.encodings ;
+strings unicode arrays io.encodings ;
 IN: game.models.loader
 
 ERROR: unknown-models-extension extension ;

extra/geobytes/geobytes.factor

@@ -1,7 +1,7 @@
 ! Copyright (C) 2009 Doug Coleman.
 ! See http://factorcode.org/license.txt for BSD license.
 USING: combinators combinators.smart csv io.encodings.8-bit
-math.parser memoize sequences kernel unicode.categories money
+math.parser memoize sequences kernel unicode money
 io.encodings.8-bit.latin1 ;
 IN: geobytes
 

extra/gml/ui/ui.factor

@@ -5,7 +5,7 @@ io.pathnames io.streams.string kernel locals models namespaces
 sequences ui ui.gadgets ui.gadgets.buttons ui.gadgets.editors
 ui.gadgets.frames ui.gadgets.grids ui.gadgets.labels
 ui.gadgets.packs ui.gadgets.scrollers ui.gadgets.worlds
-ui.gadgets.tables ui.gadgets.labeled unicode.case ;
+ui.gadgets.tables ui.gadgets.labeled unicode ;
 FROM: gml => gml ;
 IN: gml.ui
 

extra/graphviz/render/render.factor

@@ -5,7 +5,7 @@ graphviz.dot images.viewer io.backend io.directories
 io.encodings.8-bit.latin1 io.encodings.utf8 io.files
 io.files.temp io.files.unique io.launcher io.standard-paths
 kernel locals make namespaces sequences summary system threads
-unicode.case vocabs webbrowser words ;
+unicode vocabs webbrowser words ;
 IN: graphviz.render
 
 <PRIVATE

extra/html/parser/analyzer/analyzer.factor

@@ -2,8 +2,7 @@
 ! See http://factorcode.org/license.txt for BSD license.
 USING: accessors assocs combinators combinators.short-circuit
 fry html.parser http.client io kernel locals math math.statistics
-sequences sets splitting unicode.case unicode.categories urls
+sequences sets splitting unicode urls urls.encoding shuffle ;
-urls.encoding shuffle ;
 IN: html.parser.analyzer
 
 : scrape-html ( url -- response vector )

extra/html/parser/parser.factor

@@ -2,8 +2,7 @@
 ! See http://factorcode.org/license.txt for BSD license.
 USING: accessors arrays hashtables sequences.parser
 html.parser.utils kernel namespaces sequences make math
-unicode.case unicode.categories combinators.short-circuit
+unicode combinators.short-circuit quoting fry ;
-quoting fry ;
 IN: html.parser
 
 TUPLE: tag name attributes text closing? ;

extra/html/parser/printer/printer.factor

@@ -1,6 +1,6 @@
 USING: accessors assocs combinators html.parser
 html.parser.utils io io.streams.string kernel math math.order
-namespaces sequences strings unicode.categories ;
+namespaces sequences strings unicode ;
 IN: html.parser.printer
 
 TUPLE: html-printer ;

extra/id3/id3.factor

@@ -2,10 +2,10 @@
 ! See http://factorcode.org/license.txt for BSD license.
 USING: sequences io io.encodings.binary io.files io.pathnames
 strings kernel math io.mmap accessors combinators math.ranges
-unicode.categories byte-arrays io.encodings.string
+unicode byte-arrays io.encodings.string
 io.encodings.utf16 assocs math.parser combinators.short-circuit
 fry namespaces combinators.smart splitting io.encodings.ascii
-arrays io.files.info unicode.case io.directories.search literals
+arrays io.files.info io.directories.search literals
 math.functions continuations ;
 FROM: alien.c-types => uchar ;
 IN: id3

extra/managed-server/chat/chat.factor

@@ -3,7 +3,7 @@
 USING: accessors assocs calendar calendar.format
 combinators.smart io io.crlf io.encodings.utf8 kernel locals
 managed-server namespaces sequences sorting splitting
-unicode.case ;
+unicode ;
 IN: managed-server.chat
 
 TUPLE: chat-server < managed-server ;

extra/parser-combinators/parser-combinators-tests.factor

@@ -1,7 +1,7 @@
 ! Copyright (C) 2005 Chris Double.
 ! See http://factorcode.org/license.txt for BSD license.
 USING: kernel lists lists.lazy tools.test strings math
-sequences parser-combinators arrays math.parser unicode.categories ;
+sequences parser-combinators arrays math.parser unicode ;
 IN: parser-combinators.tests
 
 ! Testing <&>