wp2txt 0.8.0 → 0.9.1
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.
- checksums.yaml +4 -4
- data/README.md +11 -6
- data/bin/benchmark.rb +5 -4
- data/bin/wp2txt +24 -27
- data/data/output_samples/testdata_en.txt +49076 -0
- data/data/output_samples/testdata_ja.txt +9382 -0
- data/data/testdata_en.bz2 +0 -0
- data/data/{testdata.bz2 → testdata_ja.bz2} +0 -0
- data/lib/wp2txt.rb +66 -42
- data/lib/wp2txt/article.rb +33 -3
- data/lib/wp2txt/utils.rb +44 -49
- data/lib/wp2txt/version.rb +1 -1
- data/spec/utils_spec.rb +28 -16
- data/wp2txt.gemspec +1 -0
- metadata +21 -4
data/wp2txt.gemspec
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: wp2txt
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.9.1
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Yoichiro Hasebe
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date:
|
11
|
+
date: 2018-01-10 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: nokogiri
|
@@ -24,6 +24,20 @@ dependencies:
|
|
24
24
|
- - ">="
|
25
25
|
- !ruby/object:Gem::Version
|
26
26
|
version: '0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: parallel
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ">="
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
type: :runtime
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - ">="
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0'
|
27
41
|
- !ruby/object:Gem::Dependency
|
28
42
|
name: htmlentities
|
29
43
|
requirement: !ruby/object:Gem::Requirement
|
@@ -69,7 +83,10 @@ files:
|
|
69
83
|
- Rakefile
|
70
84
|
- bin/benchmark.rb
|
71
85
|
- bin/wp2txt
|
72
|
-
- data/
|
86
|
+
- data/output_samples/testdata_en.txt
|
87
|
+
- data/output_samples/testdata_ja.txt
|
88
|
+
- data/testdata_en.bz2
|
89
|
+
- data/testdata_ja.bz2
|
73
90
|
- lib/wp2txt.rb
|
74
91
|
- lib/wp2txt/article.rb
|
75
92
|
- lib/wp2txt/mw_api.rb
|
@@ -98,7 +115,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
98
115
|
version: '0'
|
99
116
|
requirements: []
|
100
117
|
rubyforge_project: wp2txt
|
101
|
-
rubygems_version: 2.
|
118
|
+
rubygems_version: 2.6.13
|
102
119
|
signing_key:
|
103
120
|
specification_version: 4
|
104
121
|
summary: Wikipedia dump to text converter
|