ots 0.5.0 → 0.5.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- data/CHANGELOG +22 -0
- data/README.md +4 -0
- data/ext/ots.c +8 -4
- data/ext/version.h +1 -1
- metadata +4 -3
data/CHANGELOG
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
1
|
+
=== 0.5.1 (2012-01-11)
|
|
2
|
+
|
|
3
|
+
* GC bugfix: hang on to encoding index rather than rb_encoding pointer.
|
|
4
|
+
|
|
5
|
+
=== 0.5.0 (2012-01-10)
|
|
6
|
+
|
|
7
|
+
api rewrite and some dictionary parser fixes
|
|
8
|
+
|
|
9
|
+
renamed:
|
|
10
|
+
|
|
11
|
+
* OTS.dictionaries => OTS.languages
|
|
12
|
+
|
|
13
|
+
api changes:
|
|
14
|
+
|
|
15
|
+
* OTS.parse, takes an options hash now with language or dictionary options
|
|
16
|
+
* removed OTS::Article#title
|
|
17
|
+
* added OTS::Article#topics, returns the most important keywords
|
|
18
|
+
* renamed the lines option in OTS::Article#summarize to sentences
|
|
19
|
+
|
|
20
|
+
xml parser fixes:
|
|
21
|
+
|
|
22
|
+
* uses xmlReadFile instead of xmlParseFile
|
data/README.md
CHANGED
|
@@ -76,6 +76,10 @@ ots is an interface to libots - The [open text summarizer](http://libots.sourcef
|
|
|
76
76
|
OTS.languages #=> list of supported languages dictionaries baked-in to libots
|
|
77
77
|
```
|
|
78
78
|
|
|
79
|
+
## See Also
|
|
80
|
+
|
|
81
|
+
[https://github.com/ssoper/summarize](https://github.com/ssoper/summarize)
|
|
82
|
+
|
|
79
83
|
## License
|
|
80
84
|
|
|
81
85
|
[Creative Commons Attribution - CC BY](http://creativecommons.org/licenses/by/3.0)
|
data/ext/ots.c
CHANGED
|
@@ -10,6 +10,10 @@ static void article_free(OtsArticle *article) {
|
|
|
10
10
|
ots_free_article(article);
|
|
11
11
|
}
|
|
12
12
|
|
|
13
|
+
rb_encoding* article_encoding(VALUE self) {
|
|
14
|
+
return rb_enc_from_index((int)rb_iv_get(self, "@encoding"));
|
|
15
|
+
}
|
|
16
|
+
|
|
13
17
|
VALUE article_allocate(VALUE klass) {
|
|
14
18
|
OtsArticle *article = ots_new_article();
|
|
15
19
|
return Data_Wrap_Struct(klass, 0, article_free, article);
|
|
@@ -56,7 +60,7 @@ VALUE article_initialize(int argc, VALUE *argv, VALUE self) {
|
|
|
56
60
|
ots_parse_stream(RSTRING_PTR(text), RSTRING_LEN(text), article);
|
|
57
61
|
ots_grade_doc(article);
|
|
58
62
|
|
|
59
|
-
rb_iv_set(self, "@encoding", (VALUE)
|
|
63
|
+
rb_iv_set(self, "@encoding", (VALUE)rb_enc_get_index(text));
|
|
60
64
|
|
|
61
65
|
return self;
|
|
62
66
|
}
|
|
@@ -108,7 +112,7 @@ VALUE article_summarize(VALUE self, VALUE options) {
|
|
|
108
112
|
else
|
|
109
113
|
ots_highlight_doc(article, NUM2INT(percent));
|
|
110
114
|
|
|
111
|
-
return article_summary(article, (
|
|
115
|
+
return article_summary(article, article_encoding(self));
|
|
112
116
|
}
|
|
113
117
|
|
|
114
118
|
VALUE article_topics(VALUE self) {
|
|
@@ -116,7 +120,7 @@ VALUE article_topics(VALUE self) {
|
|
|
116
120
|
|
|
117
121
|
return
|
|
118
122
|
article->title ?
|
|
119
|
-
rb_str_split(rb_enc_str_new2(article->title, (
|
|
123
|
+
rb_str_split(rb_enc_str_new2(article->title, article_encoding(self)), ",") :
|
|
120
124
|
Qnil;
|
|
121
125
|
}
|
|
122
126
|
|
|
@@ -129,7 +133,7 @@ typedef struct {
|
|
|
129
133
|
|
|
130
134
|
VALUE article_keywords(VALUE self) {
|
|
131
135
|
OtsArticle *article = article_handle(self);
|
|
132
|
-
rb_encoding *encoding = (
|
|
136
|
+
rb_encoding *encoding = article_encoding(self);
|
|
133
137
|
|
|
134
138
|
VALUE words = rb_ary_new();
|
|
135
139
|
GList* word_ptr = article->ImpWords;
|
data/ext/version.h
CHANGED
|
@@ -1,2 +1,2 @@
|
|
|
1
1
|
#pragma once
|
|
2
|
-
#define RUBY_OTS_VERSION "0.5.
|
|
2
|
+
#define RUBY_OTS_VERSION "0.5.1"
|
metadata
CHANGED
|
@@ -5,8 +5,8 @@ version: !ruby/object:Gem::Version
|
|
|
5
5
|
segments:
|
|
6
6
|
- 0
|
|
7
7
|
- 5
|
|
8
|
-
-
|
|
9
|
-
version: 0.5.
|
|
8
|
+
- 1
|
|
9
|
+
version: 0.5.1
|
|
10
10
|
platform: ruby
|
|
11
11
|
authors:
|
|
12
12
|
- Bharanee Rathna
|
|
@@ -14,7 +14,7 @@ autorequire:
|
|
|
14
14
|
bindir: bin
|
|
15
15
|
cert_chain: []
|
|
16
16
|
|
|
17
|
-
date: 2012-01-
|
|
17
|
+
date: 2012-01-11 00:00:00 +11:00
|
|
18
18
|
default_executable:
|
|
19
19
|
dependencies:
|
|
20
20
|
- !ruby/object:Gem::Dependency
|
|
@@ -75,6 +75,7 @@ files:
|
|
|
75
75
|
- test/test_ots.rb
|
|
76
76
|
- test/helper.rb
|
|
77
77
|
- README.md
|
|
78
|
+
- CHANGELOG
|
|
78
79
|
- dictionaries/cy.xml
|
|
79
80
|
- dictionaries/tr.xml
|
|
80
81
|
- dictionaries/fr.xml
|