[ 3 ] [ "\u001112\u001161\u0011abA\u000300a"
dup last-grapheme head last-grapheme ] unit-test
+[ 3 ] [ 2 "hello" first-grapheme-from ] unit-test
+[ 1 ] [ 2 "hello" last-grapheme-from ] unit-test
+
+[ 4 ] [ 2 "what am I saying" first-word-from ] unit-test
+[ 0 ] [ 2 "what am I saying" last-word-from ] unit-test
+[ 16 ] [ 11 "what am I saying" first-word-from ] unit-test
+[ 10 ] [ 11 "what am I saying" last-word-from ] unit-test
+
: grapheme-break-test ( -- filename )
- "resource:basis/unicode/breaks/GraphemeBreakTest.txt" ;
+ "vocab:unicode/breaks/GraphemeBreakTest.txt" ;
: word-break-test ( -- filename )
- "resource:basis/unicode/breaks/WordBreakTest.txt" ;
+ "vocab:unicode/breaks/WordBreakTest.txt" ;
: parse-test-file ( file-name -- tests )
utf8 file-lines
[ "#" split1 drop ] map harvest [
"÷" split
- [ "×" split [ [ blank? ] trim hex> ] map harvest >string ] map
+ [
+ "×" split
+ [ [ blank? ] trim hex> ] map
+ [ { f 0 } member? ] reject
+ >string
+ ] map
harvest
] map ;
[ concat [ quot call [ "" like ] map ] curry ] bi unit-test
] each ;
-: grapheme-test ( tests quot -- )
+: grapheme-test ( tests -- )
[
[ 1quotation ]
[ concat [ >graphemes [ "" like ] map ] curry ] bi unit-test
] each ;
grapheme-break-test parse-test-file [ >graphemes ] test
-! word-break-test parse-test-file [ >words ] test
+word-break-test parse-test-file [ >words ] test
+
+[ { t f t t f t } ] [ 6 iota [ "as df" word-break-at? ] map ] unit-test