ots 0.5.0 → 0.5.1

data/CHANGELOG

@@ -0,0 +1,22 @@
+=== 0.5.1 (2012-01-11)
+
+* GC bugfix: hang on to encoding index rather than rb_encoding pointer.
+
+=== 0.5.0 (2012-01-10)
+
+api rewrite and some dictionary parser fixes
+
+renamed:
+
+* OTS.dictionaries => OTS.languages
+
+api changes:
+
+* OTS.parse, takes an options hash now with language or dictionary options
+* removed OTS::Article#title
+* added OTS::Article#topics, returns the most important keywords
+* renamed the lines option in OTS::Article#summarize to sentences
+
+xml parser fixes:
+
+* uses xmlReadFile instead of xmlParseFile

data/README.md

@@ -76,6 +76,10 @@ ots is an interface to libots - The [open text summarizer](http://libots.sourcef
   OTS.languages #=> list of supported languages dictionaries baked-in to libots
 ```
 
+## See Also
+
+[https://github.com/ssoper/summarize](https://github.com/ssoper/summarize)
+
 ## License
 
 [Creative Commons Attribution - CC BY](http://creativecommons.org/licenses/by/3.0)

data/ext/ots.c

@@ -10,6 +10,10 @@ static void article_free(OtsArticle *article) {
       ots_free_article(article);
 }
 
+rb_encoding* article_encoding(VALUE self) {
+    return rb_enc_from_index((int)rb_iv_get(self, "@encoding"));
+}
+
 VALUE article_allocate(VALUE klass) {
     OtsArticle *article = ots_new_article();
     return Data_Wrap_Struct(klass, 0, article_free, article);
@@ -56,7 +60,7 @@ VALUE article_initialize(int argc, VALUE *argv, VALUE self) {
     ots_parse_stream(RSTRING_PTR(text), RSTRING_LEN(text), article);
     ots_grade_doc(article);
 
-    rb_iv_set(self, "@encoding", (VALUE)rb_enc_get(text));
+    rb_iv_set(self, "@encoding", (VALUE)rb_enc_get_index(text));
 
     return self;
 }
@@ -108,7 +112,7 @@ VALUE article_summarize(VALUE self, VALUE options) {
     else
         ots_highlight_doc(article, NUM2INT(percent));
 
-    return article_summary(article, (rb_encoding *)rb_iv_get(self, "@encoding"));
+    return article_summary(article, article_encoding(self));
 }
 
 VALUE article_topics(VALUE self) {
@@ -116,7 +120,7 @@ VALUE article_topics(VALUE self) {
 
     return
         article->title ?
-            rb_str_split(rb_enc_str_new2(article->title, (rb_encoding*)rb_iv_get(self, "@encoding")), ",") :
+            rb_str_split(rb_enc_str_new2(article->title, article_encoding(self)), ",") :
             Qnil;
 }
 
@@ -129,7 +133,7 @@ typedef struct {
 
 VALUE article_keywords(VALUE self) {
     OtsArticle *article = article_handle(self);
-    rb_encoding *encoding = (rb_encoding*)rb_iv_get(self, "@encoding");
+    rb_encoding *encoding = article_encoding(self);
 
     VALUE words     = rb_ary_new();
     GList* word_ptr = article->ImpWords;

data/ext/version.h

@@ -1,2 +1,2 @@
 #pragma once
-#define RUBY_OTS_VERSION            "0.5.0"
+#define RUBY_OTS_VERSION            "0.5.1"

metadata

@@ -5,8 +5,8 @@ version: !ruby/object:Gem::Version
   segments: 
   - 0
   - 5
-  - 0
-  version: 0.5.0
+  - 1
+  version: 0.5.1
 platform: ruby
 authors: 
 - Bharanee Rathna
@@ -14,7 +14,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2012-01-10 00:00:00 +11:00
+date: 2012-01-11 00:00:00 +11:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -75,6 +75,7 @@ files:
 - test/test_ots.rb
 - test/helper.rb
 - README.md
+- CHANGELOG
 - dictionaries/cy.xml
 - dictionaries/tr.xml
 - dictionaries/fr.xml