bookclean 0.0.4 → 0.0.6
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/.gitignore +1 -0
- data/lib/bookclean.rb +16 -3
- data/lib/bookclean/version.rb +1 -1
- metadata +3 -3
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA1:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 7b1fc97d4ac692c2a9756fe7129d9f76f9938d23
|
|
4
|
+
data.tar.gz: a93182ebbe1c5b3109142b8034687218cfb78ff1
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 677f93449aed56fd4f24aa12a0e1de57cbd7f717d732baf67107dff3fd785218a137d8d087ca9bff26bcd9a65d1bf774d45d48bda38ee99328ac7429eb1b8a44
|
|
7
|
+
data.tar.gz: 288f27319f4b1a9ff6ae01be9dfd92ef2b1c1040649c211734d175aade1423a0970829493c62ab123d92cf8dfaed500d1db751af7e707d41bd2792052dd79b8f
|
data/.gitignore
CHANGED
data/lib/bookclean.rb
CHANGED
|
@@ -11,10 +11,23 @@ module BookClean
|
|
|
11
11
|
str.gsub!(/\s*ltda.?$/, '')
|
|
12
12
|
str.gsub!(/\slv$/, '')
|
|
13
13
|
str.gsub!(/\ss\.a\.$/, '')
|
|
14
|
+
str.gsub!(/\ss\.a$/, '')
|
|
15
|
+
str.gsub!(/\ssa\.$/, '')
|
|
16
|
+
str.gsub!(/\ss\.\sa\.$/, '')
|
|
17
|
+
str.gsub!(/\ss\.\sa$/, '')
|
|
14
18
|
str.gsub!(/^editora/, '') if !str.match(/^editora\s+..\s+/) #editora da mente should keep editora
|
|
15
|
-
str.gsub!(/editora$/, '')
|
|
16
|
-
|
|
17
|
-
|
|
19
|
+
str.gsub!(/editora$/, '')
|
|
20
|
+
str.gsub!('&', ' & ')
|
|
21
|
+
str.gsub!(/\s+/, ' ')
|
|
22
|
+
str.gsub!('Ã?', 'á')
|
|
23
|
+
str.gsub!('ã?', 'á')
|
|
24
|
+
str.gsub!(' ed.', '')
|
|
25
|
+
str.gsub!(/\sed$/, '')
|
|
26
|
+
str.gsub!(/\s-$/, '')
|
|
27
|
+
|
|
28
|
+
|
|
29
|
+
|
|
30
|
+
|
|
18
31
|
#Split words in tokens
|
|
19
32
|
#Match each token to dictionary of accented words.
|
|
20
33
|
#Join words by space
|
data/lib/bookclean/version.rb
CHANGED
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: bookclean
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.0.
|
|
4
|
+
version: 0.0.6
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Samur Araujo
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: bin
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date:
|
|
11
|
+
date: 2017-08-09 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
13
|
- !ruby/object:Gem::Dependency
|
|
14
14
|
name: lisbn
|
|
@@ -131,7 +131,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
|
131
131
|
version: '0'
|
|
132
132
|
requirements: []
|
|
133
133
|
rubyforge_project:
|
|
134
|
-
rubygems_version: 2.
|
|
134
|
+
rubygems_version: 2.4.8
|
|
135
135
|
signing_key:
|
|
136
136
|
specification_version: 4
|
|
137
137
|
summary: Clean book metadata.
|