More features in the unicode.breaks API, with documentation

diff --git a/basis/unicode/breaks/breaks-docs.factor b/basis/unicode/breaks/breaks-docs.factor
index 552883a299331185bbdeb730c71ef755ca03e79e..9c57aab9f69f30d3e621a1146c60c75857c7f152 100644 (file)
--- a/basis/unicode/breaks/breaks-docs.factor
+++ b/basis/unicode/breaks/breaks-docs.factor
@@ -7,11 +7,16 @@ ARTICLE: "unicode.breaks" "Word and grapheme breaks"
 "The " { $vocab-link "unicode.breaks" "unicode.breaks" } " vocabulary partially implements Unicode Standard Annex #29. This provides for segmentation of a string along grapheme and word boundaries. In Unicode, a grapheme, or a basic unit of display in text, may be more than one code point. For example, in the string \"e\\u000301\" (where U+0301 is a combining acute accent), there is only one grapheme, as the acute accent goes above the e, forming a single grapheme. Word breaks, in general, are more complicated than simply splitting by whitespace, and the Unicode algorithm provides for that."
 $nl "Operations for graphemes:"
 { $subsection first-grapheme }
+{ $subsection first-grapheme-from }
 { $subsection last-grapheme }
+{ $subsection last-grapheme-from }
 { $subsection >graphemes }
 { $subsection string-reverse }
 "Operations on words:"
 { $subsection first-word }
+{ $subsection first-word-from }
+{ $subsection last-word }
+{ $subsection last-word-from }
 { $subsection >words } ;
 
 HELP: first-grapheme
@@ -22,6 +27,14 @@ HELP: last-grapheme
 { $values { "str" string } { "i" "an index" } }
 { $description "Finds the index of the start of the last grapheme of the string. This can be used to traverse the graphemes of a string backwards." } ;
 
+HELP: first-grapheme-from
+{ $values { "start" "an index" } { "str" string } { "i" "an index" } }
+{ $description "Finds the length of the first grapheme of the string, starting from the given index. This can be used repeatedly to efficiently traverse the graphemes of the string, using slices." } ;
+
+HELP: last-grapheme-from
+{ $values { "end" "an index" } { "str" string } { "i" "an index" } }
+{ $description "Finds the index of the start of the last grapheme of the string, starting from the given index. This can be used to traverse the graphemes of a string backwards." } ;
+
 HELP: >graphemes
 { $values { "str" string } { "graphemes" "an array of strings" } }
 { $description "Divides a string into a sequence of individual graphemes." } ;
@@ -32,7 +45,19 @@ HELP: string-reverse
 
 HELP: first-word
 { $values { "str" string } { "i" "index" } }
-{ $description "Finds the length of the first word in the string." } ;
+{ $description "Finds the index of the end of the first word in the string." } ;
+
+HELP: last-word
+{ $values { "str" string } { "i" "index" } }
+{ $description "Finds the index of the beginning of the last word in the string." } ;
+
+HELP: first-word-from
+{ $values { "start" "index" } { "str" string } { "i" "index" } }
+{ $description "Finds the index of the end of the first word in the string, starting from the given index." } ;
+
+HELP: last-word-from
+{ $values { "end" "index" } { "str" string } { "i" "index" } }
+{ $description "Finds the index of the start of the word that the index is contained in." } ;
 
 HELP: >words
 { $values { "str" string } { "words" "an array of strings" } }

diff --git a/basis/unicode/breaks/breaks-tests.factor b/basis/unicode/breaks/breaks-tests.factor
index 6d6d4233f572f043101fa48417ae80e62b6cb036..bbce857681bd17540a928ce624a8eff2ffae4fd5 100644 (file)
--- a/basis/unicode/breaks/breaks-tests.factor
+++ b/basis/unicode/breaks/breaks-tests.factor
@@ -12,6 +12,11 @@ IN: unicode.breaks.tests
 [ 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 )
     "vocab:unicode/breaks/GraphemeBreakTest.txt" ;
 

diff --git a/basis/unicode/breaks/breaks.factor b/basis/unicode/breaks/breaks.factor
index 6d6b5cc0cfd7a858f15b1715510656a75602324d..ed96842c41ad0f58d1c2e900c8b31ed451ff55c4 100644 (file)
--- a/basis/unicode/breaks/breaks.factor
+++ b/basis/unicode/breaks/breaks.factor
@@ -247,3 +247,12 @@ PRIVATE>
             word-break-next nip
         ]
     } 2|| ;
+
+: first-word-from ( start str -- i )
+    over tail-slice first-word + ;
+
+: last-word ( str -- i )
+    [ length ] keep '[ _ word-break-at? ] find-last drop 0 or ;
+
+: last-word-from ( end str -- i )
+    swap head-slice last-word ;