factor: trim some using lists

[factor.git] / basis / unicode / data / data.factor

diff --git a/basis/unicode/data/data.factor b/basis/unicode/data/data.factor
index bc744a747db21a116f950d5f697a457b8c0ef898..459c3b017b927c49be95045b2167f5844d93c9c0 100644 (file)
--- a/basis/unicode/data/data.factor
+++ b/basis/unicode/data/data.factor
@@ -2,8 +2,8 @@
 ! See http://factorcode.org/license.txt for BSD license.
 USING: arrays ascii assocs byte-arrays combinators
 combinators.short-circuit grouping hashtables interval-sets
-io.encodings.utf8 io.files kernel locals make math math.bitwise
-math.order math.parser math.ranges memoize namespaces sequences
+io.encodings.utf8 io.files kernel make math math.bitwise
+math.order math.parser ranges namespaces sequences
 sets simple-flat-file sorting splitting strings.parser ;
 IN: unicode.data
 
@@ -33,7 +33,7 @@ CONSTANT: name-map H{ }
 : combining-class ( char -- n ) class-map at ; inline
 : non-starter? ( char -- ? ) combining-class { 0 f } member? not ; inline
 : property ( property -- interval-map ) properties at ; foldable
-: property? ( char property -- ? ) property interval-sets:in? ; inline
+: property? ( char property -- ? ) property interval-in? ; inline
 : special-case ( ch -- casing-tuple ) special-casing at ; inline
 
 ! For non-existent characters, use Cn
@@ -53,7 +53,7 @@ CONSTANT: categories {
 MEMO: categories-map ( -- hashtable )
     categories H{ } zip-index-as ;
 
-CONSTANT: num-chars 0x2FA1E
+CONSTANT: NUM-CHARS 0x2FA1E
 
 PRIVATE>
 
@@ -76,7 +76,7 @@ PRIVATE>
 
 ! Loading data from UnicodeData.txt
 
-: load-data ( -- data )
+: load-unicode-data ( -- data )
     "vocab:unicode/UCD/UnicodeData.txt" load-data-file ;
 
 : (process-data) ( index data -- newdata )
@@ -100,15 +100,15 @@ PRIVATE>
 
 : (process-decomposed) ( data -- alist )
     5 swap (process-data)
-    [ " " split [ hex> ] map ] assoc-map ;
+    [ split-words [ hex> ] map ] assoc-map ;
 
 : exclusions-file ( -- filename )
     "vocab:unicode/UCD/CompositionExclusions.txt" ;
 
 : exclusions ( -- set )
     exclusions-file utf8 file-lines
-    [ "#" split1 drop [ blank? ] trim-tail hex> ] map
-    [ 0 = ] reject ;
+    [ "#" split1 drop [ ascii:blank? ] trim-tail hex> ] map
+    0 swap remove ;
 
 : unique ( seq -- assoc )
     [ dup ] H{ } map>assoc ;
@@ -141,12 +141,12 @@ PRIVATE>
     name-map sort-values keys
     [ { [ "first>" tail? ] [ "last>" tail? ] } 1|| ] filter
     2 group [
-        [ name-map at ] bi@ [ [a,b] ] [ table ?nth ] bi
+        [ name-map at ] bi@ [ [a..b] ] [ table ?nth ] bi
         [ swap table ?set-nth ] curry each
     ] assoc-each table ;
 
 :: process-category ( data -- category-listing )
-    num-chars <byte-array> :> table
+    NUM-CHARS <byte-array> :> table
     2 data (process-data) [| char cat |
         cat categories-map at char table ?set-nth
     ] assoc-each table fill-ranges ;
@@ -157,7 +157,7 @@ PRIVATE>
     ] H{ } assoc-map-as ;
 
 : multihex ( hexstring -- string )
-    " " split [ hex> ] map sift ;
+    split-words [ hex> ] map sift ;
 
 PRIVATE>
 
@@ -194,7 +194,7 @@ C: <code-point> code-point
     [ length 5 = ] filter
     [ [ set-code-point ] each ] H{ } make ;
 
-load-data {
+load-unicode-data {
     [ process-names name-map swap assoc-union! drop ]
     [ 13 swap process-data simple-lower swap assoc-union! drop ]
     [ 12 swap process-data simple-upper swap assoc-union! drop ]
@@ -215,6 +215,8 @@ load-properties properties swap assoc-union! drop
 
 PRIVATE>
 
+ERROR: invalid-unicode-character name ;
+
 [
-    name-map at [ "Invalid character" throw ] unless*
+    name-map ?at [ invalid-unicode-character ] unless
 ] name>char-hook set-global