bookclean 0.0.2 → 0.0.3
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/lib/bookclean.rb +3 -2
- data/lib/bookclean/version.rb +2 -1
- data/test/test_bookclean.rb +5 -1
- metadata +2 -2
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA1:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: c6c2f8357060a5d60ebeaaae62150af4ccd5a0d2
|
|
4
|
+
data.tar.gz: 28cf7a6fae527d07fff6516cbaa466aa66b131fd
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 8519ec2e61d1eed2748ea20c7319c9ed3a1e846f676c94579ed55be424608a493a3e3e43588454c4653c96d3c63d610bab57949712bed163e96766d84c1b3004
|
|
7
|
+
data.tar.gz: ae05fd382d883d4c76eaef8c49186829b62c8d7e30315ec94b577e5ec8996a52d8ec2ed85fd054e34147a6973c8598bb8069496b240eb319501ce028535a1571
|
data/lib/bookclean.rb
CHANGED
|
@@ -9,9 +9,10 @@ module BookClean
|
|
|
9
9
|
str = UnicodeUtils.downcase(str)
|
|
10
10
|
str.gsub!(/\s+/, ' ')
|
|
11
11
|
str.gsub!(/\s*ltda.?$/, '')
|
|
12
|
-
|
|
12
|
+
str.gsub!(/\slv$/, '')
|
|
13
|
+
str.gsub!(/\ss\.a\.$/, '')
|
|
13
14
|
str.gsub!(/^editora/, '') if !str.match(/^editora\s+..\s+/) #editora da mente should keep editora
|
|
14
|
-
str.gsub!(/editora$/, '')
|
|
15
|
+
str.gsub!(/editora$/, '')
|
|
15
16
|
|
|
16
17
|
|
|
17
18
|
#Split words in tokens
|
data/lib/bookclean/version.rb
CHANGED
data/test/test_bookclean.rb
CHANGED
|
@@ -12,6 +12,10 @@ class BookCleanTest < MiniTest::Unit::TestCase
|
|
|
12
12
|
assert_equal "Gold", BookClean::Publisher.clean("gold editora ltda")
|
|
13
13
|
assert_equal "Gold", BookClean::Publisher.clean("gold editora ltda.")
|
|
14
14
|
assert_equal "Editora da Mente", BookClean::Publisher.clean("editora da mente")
|
|
15
|
-
assert_equal "Civilização", BookClean::Publisher.clean("civilizaÇao editora")
|
|
15
|
+
assert_equal "Civilização", BookClean::Publisher.clean("civilizaÇao editora")
|
|
16
|
+
assert_equal "Contraponto", BookClean::Publisher.clean("contraponto editora")
|
|
17
|
+
assert_equal "Difusão Cultural do Livro", BookClean::Publisher.clean("difusÃo cultural do livro")
|
|
18
|
+
assert_equal "Globo", BookClean::Publisher.clean("globo lv")
|
|
19
|
+
assert_equal "Globo", BookClean::Publisher.clean("globo s.a.")
|
|
16
20
|
end
|
|
17
21
|
end
|
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: 0.0.3
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Samur Araujo
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: bin
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date: 2015-07-
|
|
11
|
+
date: 2015-07-13 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
13
|
- !ruby/object:Gem::Dependency
|
|
14
14
|
name: lisbn
|