wp2txt 1.1.0 → 1.1.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/README.md +12 -3
- data/bin/wp2txt +0 -2
- data/lib/wp2txt/version.rb +1 -1
- data/lib/wp2txt.rb +16 -10
- metadata +3 -3
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 5e8cda1ff32863bb95b4b314782e46007eabcd784938b4fe33f6660445a37d31
|
4
|
+
data.tar.gz: 805bd29ba8b660e705156bf7a4cc1d006b2f43a2c81c24e86ef210ef1fd1ef16
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: fe798d5ab55cefd55f776e4d0f975cb510a7c9c65af348ba216365827266d808b65f9125d9bc50c21cb05349ae71d07a46a80998ffd000bbcaac71b2eed15e45
|
7
|
+
data.tar.gz: 94f8df87a935b52d19f05adca27a01f64787dfa35fed067dc68cc1204b4b0022411f6cb6db1d2c9175987d27113e506f84d1761e4661c7d4f65f934c6ee1647e
|
data/README.md
CHANGED
@@ -8,6 +8,15 @@ WP2TXT extracts text and category data from Wikipedia dump files (encoded in XML
|
|
8
8
|
|
9
9
|
## Changelog
|
10
10
|
|
11
|
+
**April 2023**
|
12
|
+
|
13
|
+
- File split/delete issues fixed
|
14
|
+
|
15
|
+
**January 2023**
|
16
|
+
|
17
|
+
- Bug related to command line arguments fixed
|
18
|
+
- Code cleanup introducing Rubocop
|
19
|
+
|
11
20
|
**December 2022**
|
12
21
|
|
13
22
|
- Docker images available via Docker Hub
|
@@ -93,7 +102,7 @@ Download the latest Wikipedia dump file for the desired language at a URL such a
|
|
93
102
|
|
94
103
|
https://dumps.wikimedia.org/enwiki/latest/enwiki-latest-pages-articles.xml.bz2
|
95
104
|
|
96
|
-
Here, `enwiki` refers to the English Wikipedia. To get the Japanese Wikipedia dump file, for instance, change this to jawiki (Japanese). In doing so, note that there are two instances of `enwiki` in the URL above.
|
105
|
+
Here, `enwiki` refers to the English Wikipedia. To get the Japanese Wikipedia dump file, for instance, change this to `jawiki` (Japanese). In doing so, note that there are two instances of `enwiki` in the URL above.
|
97
106
|
|
98
107
|
Alternatively, you can also select Wikipedia dump files created on a specific date from [here](http://dumps.wikimedia.org/backup-index.html). Make sure to download a file named in the following format:
|
99
108
|
|
@@ -213,11 +222,11 @@ The author will appreciate your mentioning one of these in your research.
|
|
213
222
|
Or use this BibTeX entry:
|
214
223
|
|
215
224
|
```
|
216
|
-
@misc{
|
225
|
+
@misc{wp2txt_2023,
|
217
226
|
author = {Yoichiro Hasebe},
|
218
227
|
title = {WP2TXT: A command-line toolkit to extract text content and category data from Wikipedia dump files},
|
219
228
|
url = {https://github.com/yohasebe/wp2txt},
|
220
|
-
year = {
|
229
|
+
year = {2023}
|
221
230
|
}
|
222
231
|
```
|
223
232
|
|
data/bin/wp2txt
CHANGED
data/lib/wp2txt/version.rb
CHANGED
data/lib/wp2txt.rb
CHANGED
@@ -48,14 +48,19 @@ module Wp2txt
|
|
48
48
|
basename = File.basename(command)
|
49
49
|
path = +""
|
50
50
|
print "Checking #{basename}: "
|
51
|
-
|
52
|
-
|
53
|
-
|
54
|
-
|
55
|
-
|
56
|
-
|
57
|
-
|
58
|
-
|
51
|
+
begin
|
52
|
+
if open("| which #{command} 2>/dev/null") { |f| path = f.gets.strip }
|
53
|
+
puts "detected [#{path}]"
|
54
|
+
path.strip
|
55
|
+
elsif open("| which #{basename} 2>/dev/null") { |f| path = f.gets.strip }
|
56
|
+
puts "detected [#{path}]"
|
57
|
+
path.strip
|
58
|
+
else
|
59
|
+
puts "#{basename} not found"
|
60
|
+
false
|
61
|
+
end
|
62
|
+
rescue StandardError
|
63
|
+
puts "#{basename} not found"
|
59
64
|
false
|
60
65
|
end
|
61
66
|
end
|
@@ -69,7 +74,7 @@ module Wp2txt
|
|
69
74
|
if /.bz2$/ =~ @input_file
|
70
75
|
if @bz2_gem
|
71
76
|
file = Bzip2::Reader.new File.open(@input_file, "r:UTF-8")
|
72
|
-
elsif
|
77
|
+
elsif Gem.win_platform?
|
73
78
|
file = IO.popen("bunzip2.exe -c #{@input_file}")
|
74
79
|
elsif (bzpath = command_exist?("lbzip2") || command_exist?("pbzip2") || command_exist?("bzip2"))
|
75
80
|
file = IO.popen("#{bzpath} -c -d #{@input_file}")
|
@@ -155,7 +160,7 @@ module Wp2txt
|
|
155
160
|
@fp.puts(output_text) if output_text != ""
|
156
161
|
@fp.close
|
157
162
|
|
158
|
-
if File.size(outfilename).zero?
|
163
|
+
if outfilename && File.size(outfilename).zero?
|
159
164
|
File.delete(outfilename)
|
160
165
|
@outfiles.delete(outfilename)
|
161
166
|
end
|
@@ -292,6 +297,7 @@ module Wp2txt
|
|
292
297
|
@fp.puts(output_text)
|
293
298
|
@fp.close
|
294
299
|
end
|
300
|
+
@file_pointer.close
|
295
301
|
File.delete(@input_file) if @del_interfile
|
296
302
|
output_text = +""
|
297
303
|
end
|
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: 1.1.
|
4
|
+
version: 1.1.2
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Yoichiro Hasebe
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2023-
|
11
|
+
date: 2023-04-15 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: bundler
|
@@ -208,7 +208,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
208
208
|
- !ruby/object:Gem::Version
|
209
209
|
version: '0'
|
210
210
|
requirements: []
|
211
|
-
rubygems_version: 3.
|
211
|
+
rubygems_version: 3.3.3
|
212
212
|
signing_key:
|
213
213
|
specification_version: 4
|
214
214
|
summary: A command-line toolkit to extract text content and category data from Wikipedia
|