arabic_normalizer 0.1.0 → 0.1.1
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 +3 -3
- data/lib/arabic_normalizer.rb +11 -13
- data/lib/arabic_normalizer/version.rb +1 -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: 595779d3887e6b4c0785c2ccd35e2d428809d118
|
|
4
|
+
data.tar.gz: 08b6b15c78cc24ff59d41c0bb9015b81e04901a5
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 2db268cf7d49a480126bbe1e56d8c517c98fbe22b38270511537f43fb40be1eda15e1b9bc27db3a7c4f19a93c83d64b6d18297adb1b0759b17a95d87b13d6e14
|
|
7
|
+
data.tar.gz: c31c17c2e523ab80d53cbbfc41135875a752e030bb63f7e6db513696127b5febd3d9b6eb6cfe2730f5cd2c145d09bc6d9184d2dd6ef58daaea2346a4588c94c4
|
data/README.md
CHANGED
|
@@ -7,7 +7,7 @@ ArabicNormalizer is pure Ruby port of Arabic Normalizer from Lucene.
|
|
|
7
7
|
Add this line to your application's Gemfile:
|
|
8
8
|
|
|
9
9
|
```ruby
|
|
10
|
-
gem '
|
|
10
|
+
gem 'arabic_normalizer'
|
|
11
11
|
```
|
|
12
12
|
|
|
13
13
|
And then execute:
|
|
@@ -16,11 +16,11 @@ And then execute:
|
|
|
16
16
|
|
|
17
17
|
Or install it yourself as:
|
|
18
18
|
|
|
19
|
-
$ gem install
|
|
19
|
+
$ gem install arabic_normalizer
|
|
20
20
|
|
|
21
21
|
## Usage
|
|
22
22
|
```
|
|
23
|
-
require '
|
|
23
|
+
require 'arabic_normalizer'
|
|
24
24
|
|
|
25
25
|
ArabicNormalizer::normalize("مكتبٌ")
|
|
26
26
|
=> "مكتب"
|
data/lib/arabic_normalizer.rb
CHANGED
|
@@ -27,19 +27,17 @@ module ArabicNormalizer
|
|
|
27
27
|
SHADDA = "\u0651"
|
|
28
28
|
SUKUN = "\u0652"
|
|
29
29
|
|
|
30
|
+
NORMALIZATION_RULES = {
|
|
31
|
+
ALEF_MADDA => ALEF, ALEF_HAMZA_ABOVE => ALEF, ALEF_HAMZA_BELOW => ALEF,
|
|
32
|
+
YEH_HAMZA => YEH, DOTLESS_YEH => YEH,
|
|
33
|
+
TEH_MARBOUTA => HEH,
|
|
34
|
+
WAW_HAMZA => WAW,
|
|
35
|
+
TATWEEL => '', FATHATAN => '', DAMMATAN => '', KASRATAN => '', FATHA => '', DAMMA => '', KASRA => '', SHADDA => '', SUKUN => ''
|
|
36
|
+
}
|
|
37
|
+
|
|
38
|
+
NORMALIZATION_REGEX = /[#{NORMALIZATION_RULES.keys.join}]/.freeze
|
|
39
|
+
|
|
30
40
|
def self.normalize(string)
|
|
31
|
-
string.gsub(
|
|
32
|
-
#{ALEF_MADDA}#{ALEF_HAMZA_ABOVE}#{ALEF_HAMZA_BELOW}
|
|
33
|
-
#{YEH_HAMZA}#{DOTLESS_YEH}
|
|
34
|
-
#{TEH_MARBOUTA}
|
|
35
|
-
#{WAW_HAMZA}
|
|
36
|
-
#{TATWEEL}#{FATHATAN}#{DAMMATAN}#{KASRATAN}#{FATHA}#{DAMMA}#{KASRA}#{SHADDA}#{SUKUN}
|
|
37
|
-
]/x,
|
|
38
|
-
ALEF_MADDA => ALEF, ALEF_HAMZA_ABOVE => ALEF, ALEF_HAMZA_BELOW => ALEF,
|
|
39
|
-
YEH_HAMZA => YEH, DOTLESS_YEH => YEH,
|
|
40
|
-
TEH_MARBOUTA => HEH,
|
|
41
|
-
WAW_HAMZA => WAW,
|
|
42
|
-
TATWEEL => '', FATHATAN => '', DAMMATAN => '', KASRATAN => '', FATHA => '', DAMMA => '', KASRA => '', SHADDA => '', SUKUN => ''
|
|
43
|
-
)
|
|
41
|
+
string.gsub(NORMALIZATION_REGEX, NORMALIZATION_RULES)
|
|
44
42
|
end
|
|
45
43
|
end
|
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: arabic_normalizer
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.1.
|
|
4
|
+
version: 0.1.1
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Jean Debs
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: exe
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date: 2016-03-
|
|
11
|
+
date: 2016-03-29 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
13
|
- !ruby/object:Gem::Dependency
|
|
14
14
|
name: bundler
|