jruby-boilerpipe 0.0.3 → 0.0.4
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/lib/boilerpipe/document/document.rb +6 -0
- data/lib/boilerpipe/filters/filters.rb +28 -0
- data/lib/boilerpipe/version.rb +1 -1
- data/lib/boilerpipe.rb +2 -0
- metadata +4 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: e5f4a7aa89527c4a4ff728af27d20fbb3a70a63b1dfa143edfc176c1aa22f701
|
4
|
+
data.tar.gz: b70726c8ee26c021ea0bb65ef7f8835398b3017f1829d97697e39b449acb66e1
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 56e28d6ec541be25cb7b2c3895388cf5884808ec3fc0efdf777a9aa39efcd98eca7515d535868c9c4d815247ccaf0e40a09c3bce071a59294d67235d698dc29f
|
7
|
+
data.tar.gz: 3c0126c84617f75027f770bf48a424a1c3f308d289c2ce5e1e1eea1e06bebd7e7206e15053904bc2b7aed8eed47430ea5b9551da61795a06504aa201489b8547
|
@@ -0,0 +1,28 @@
|
|
1
|
+
module Boilerpipe
|
2
|
+
module Filters
|
3
|
+
java_import 'com.kohlschutter.boilerpipe.filters.english.IgnoreBlocksAfterContentFilter'
|
4
|
+
java_import 'com.kohlschutter.boilerpipe.filters.english.TerminatingBlocksFinder'
|
5
|
+
java_import 'com.kohlschutter.boilerpipe.filters.english.NumWordsRulesClassifier'
|
6
|
+
java_import 'com.kohlschutter.boilerpipe.filters.english.HeuristicFilterBase'
|
7
|
+
java_import 'com.kohlschutter.boilerpipe.filters.heuristics.DocumentTitleMatchClassifier'
|
8
|
+
|
9
|
+
class IgnoreBlocksAfterContentFilter
|
10
|
+
def self.process(doc)
|
11
|
+
DEFAULT_INSTANCE.process(doc)
|
12
|
+
end
|
13
|
+
end
|
14
|
+
|
15
|
+
class TerminatingBlocksFinder
|
16
|
+
def self.process(doc)
|
17
|
+
new.process(doc)
|
18
|
+
end
|
19
|
+
end
|
20
|
+
|
21
|
+
class NumWordsRulesClassifier
|
22
|
+
def self.process(doc)
|
23
|
+
new.process(doc)
|
24
|
+
end
|
25
|
+
end
|
26
|
+
|
27
|
+
end
|
28
|
+
end
|
data/lib/boilerpipe/version.rb
CHANGED
data/lib/boilerpipe.rb
CHANGED
@@ -1,4 +1,6 @@
|
|
1
1
|
require_relative 'boilerpipe-common-2.0-SNAPSHOT-jar-with-dependencies.jar'
|
2
2
|
require 'boilerpipe/version'
|
3
3
|
require 'boilerpipe/sax/boilerpipe_html_parser'
|
4
|
+
require 'boilerpipe/document/document'
|
4
5
|
require 'boilerpipe/extractors/article_extractor'
|
6
|
+
require 'boilerpipe/filters/filters'
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: jruby-boilerpipe
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0.
|
4
|
+
version: 0.0.4
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Gregory Ostermayr
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2017-09-
|
11
|
+
date: 2017-09-04 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
requirement: !ruby/object:Gem::Requirement
|
@@ -69,7 +69,9 @@ files:
|
|
69
69
|
- jruby-boilerpipe.gemspec
|
70
70
|
- lib/boilerpipe-common-2.0-SNAPSHOT-jar-with-dependencies.jar
|
71
71
|
- lib/boilerpipe.rb
|
72
|
+
- lib/boilerpipe/document/document.rb
|
72
73
|
- lib/boilerpipe/extractors/article_extractor.rb
|
74
|
+
- lib/boilerpipe/filters/filters.rb
|
73
75
|
- lib/boilerpipe/sax/boilerpipe_html_parser.rb
|
74
76
|
- lib/boilerpipe/version.rb
|
75
77
|
homepage: https://github.com/gregors/jruby-boilerpipe
|