wp2txt 0.9.1 → 0.9.2
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 +5 -5
- data/bin/wp2txt +4 -4
- data/lib/wp2txt/version.rb +1 -1
- data/lib/wp2txt.rb +1 -0
- data/wp2txt.gemspec +1 -1
- metadata +7 -8
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
|
-
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
2
|
+
SHA256:
|
3
|
+
metadata.gz: 3ed3d7e29a8f1c6b5f97ca0da646ddfb53ae88add38f647eae0bdc03e626269e
|
4
|
+
data.tar.gz: '009188addebcd908f449f2ce4cf39036406f3816cafeeb61beba097fe036e890'
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: d91531685df204222ab7bae9b3153653d61ccd36270e36f14575cabc3c2b1d6009bfa15f9033cb8eeb837f7c1a97fdb6303611166ec62ca96b9e4c8fc1e1ec15
|
7
|
+
data.tar.gz: 19183feee7eb8f7c03d3f7bf60eebb7e75ffeb6c6eec6967a8c3e480f82f2b48b6e171d2aa22c7aa44a9336b981ad51dfd37ab423c3db2fe1a0d854860c37231
|
data/bin/wp2txt
CHANGED
@@ -11,11 +11,11 @@ DOCDIR = File.join(File.dirname(__FILE__), '..', 'doc')
|
|
11
11
|
require 'wp2txt'
|
12
12
|
require 'wp2txt/utils'
|
13
13
|
require 'wp2txt/version'
|
14
|
-
require '
|
14
|
+
require 'optimist'
|
15
15
|
|
16
16
|
include Wp2txt
|
17
17
|
|
18
|
-
opts =
|
18
|
+
opts = Optimist::options do
|
19
19
|
version Wp2txt::VERSION
|
20
20
|
banner <<-EOS
|
21
21
|
WP2TXT extracts plain text data from Wikipedia dump file (encoded in XML/compressed with Bzip2) stripping all the MediaWiki markups and other metadata.
|
@@ -40,8 +40,8 @@ EOS
|
|
40
40
|
opt :file_size, "Approximate size (in MB) of each output file", :default => 10
|
41
41
|
opt :num_threads, "Number of threads to be spawned (capped to the number of CPU cores; set 99 to spawn max num of threads)", :default => 4
|
42
42
|
end
|
43
|
-
|
44
|
-
|
43
|
+
Optimist::die :size, "must be larger than 0" unless opts[:file_size] >= 0
|
44
|
+
Optimist::die :output_dir, "must exist" unless File.exist?(opts[:output_dir])
|
45
45
|
|
46
46
|
input_file = ARGV[0]
|
47
47
|
output_dir = opts[:output_dir]
|
data/lib/wp2txt/version.rb
CHANGED
data/lib/wp2txt.rb
CHANGED
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: 0.9.
|
4
|
+
version: 0.9.2
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Yoichiro Hasebe
|
8
|
-
autorequire:
|
8
|
+
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date:
|
11
|
+
date: 2022-07-25 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: nokogiri
|
@@ -53,7 +53,7 @@ dependencies:
|
|
53
53
|
- !ruby/object:Gem::Version
|
54
54
|
version: '0'
|
55
55
|
- !ruby/object:Gem::Dependency
|
56
|
-
name:
|
56
|
+
name: optimist
|
57
57
|
requirement: !ruby/object:Gem::Requirement
|
58
58
|
requirements:
|
59
59
|
- - ">="
|
@@ -99,7 +99,7 @@ files:
|
|
99
99
|
homepage: http://github.com/yohasebe/wp2txt
|
100
100
|
licenses: []
|
101
101
|
metadata: {}
|
102
|
-
post_install_message:
|
102
|
+
post_install_message:
|
103
103
|
rdoc_options: []
|
104
104
|
require_paths:
|
105
105
|
- lib
|
@@ -114,9 +114,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
114
114
|
- !ruby/object:Gem::Version
|
115
115
|
version: '0'
|
116
116
|
requirements: []
|
117
|
-
|
118
|
-
|
119
|
-
signing_key:
|
117
|
+
rubygems_version: 3.3.3
|
118
|
+
signing_key:
|
120
119
|
specification_version: 4
|
121
120
|
summary: Wikipedia dump to text converter
|
122
121
|
test_files:
|