wiktionary 0.1.0 → 0.1.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.gitignore +1 -0
- data/Readme.md +64 -0
- data/lib/wiktionary/noun.rb +17 -3
- data/spec/noun.rb +2 -0
- data/wiktionary.gemspec +25 -0
- metadata +20 -3
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
!binary "U0hBMQ==":
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 091eb3a349dd479feed4637a5beaef0900cea651
|
4
|
+
data.tar.gz: ca129fad7fefe18ee4d823d8ae0d94f5e5258536
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 7d38ae673dcef87169985be6d6f2a189ae588f7d7a27df4e8a8e6944ec8d74394f6969797bd14100cdd230ac624ef164204067f00c6ae9a9544228ffb03111fe
|
7
|
+
data.tar.gz: a93e59d7997fc418488a6deddb22223bd021a287fa5c387b8588ff0f1a6908800256aba7fd77da236260021aa98a0ee58048edd98b0a00918def7dcbe2d3ccbd
|
data/.gitignore
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
*.gem
|
data/Readme.md
ADDED
@@ -0,0 +1,64 @@
|
|
1
|
+
# Word conversion rules from Wiktionary
|
2
|
+
|
3
|
+
The aim of the project is providing ruls for converting English words and basic
|
4
|
+
informations about the words morphology. The project is based on the English
|
5
|
+
Wiktionary thus the descriptions are pretty accurate and include most of the
|
6
|
+
exceptions (e.g. ox -> oxen).
|
7
|
+
|
8
|
+
## Basic usage
|
9
|
+
|
10
|
+
Installation:
|
11
|
+
|
12
|
+
```
|
13
|
+
$ gem install wiktionary
|
14
|
+
```
|
15
|
+
|
16
|
+
So far only nouns are supported.
|
17
|
+
|
18
|
+
```ruby
|
19
|
+
require 'wiktionary/noun'
|
20
|
+
|
21
|
+
nouns = Wiktionary::Noun.new
|
22
|
+
nouns.singularize("dogs") #=> ["dog"]
|
23
|
+
nouns.singularize("oxen") #=> ["ox"]
|
24
|
+
nouns.singularize("feet") #=> ["foot"]
|
25
|
+
|
26
|
+
nouns.singular?("dog") #=> true
|
27
|
+
nouns.singular?("dogs") #=> false
|
28
|
+
|
29
|
+
|
30
|
+
nouns.plural?("dog") #=> false
|
31
|
+
nouns.plural?("dogs") #=> true
|
32
|
+
```
|
33
|
+
|
34
|
+
The `singularize` method returns an array since there might be more than one
|
35
|
+
base form of a given plural word.
|
36
|
+
|
37
|
+
## Data
|
38
|
+
|
39
|
+
The `data` directory - contains lists and mappings of noun forms (plural,
|
40
|
+
singular, countable, etc.). They are used to identify plural forms and
|
41
|
+
transform plural to singular. Generated from Wiktionary dump using
|
42
|
+
https://github.com/djstrong/nouns-with-plurals.
|
43
|
+
|
44
|
+
The following files are available:
|
45
|
+
* `noun.csv` - countable nouns
|
46
|
+
* `noun_countable_and_uncountable.csv` - e.g. http://en.wiktionary.org/wiki/beers
|
47
|
+
* `noun_uncountable.csv` - nouns that cannot be used freely with numbers or
|
48
|
+
the indefinite article, and which therefore takes no plural form, e.g.
|
49
|
+
http://en.wiktionary.org/wiki/lycra
|
50
|
+
* `noun_usually_uncountable.csv` - e.g. http://en.wiktionary.org/wiki/information
|
51
|
+
* `noun_unknown.csv` - nouns with unknown or uncertain plural
|
52
|
+
* `noun_pluralia_tantum.csv` - nouns that do not have singular forms, e.g. http://en.wiktionary.org/wiki/scissors
|
53
|
+
* `noun_not_attested.csv` - nouns with plural not attested
|
54
|
+
|
55
|
+
The following files contain two columns (singular and
|
56
|
+
plural form):
|
57
|
+
* `noun.csv`
|
58
|
+
* `noun_countable_and_uncountable.csv`
|
59
|
+
* `noun_usually_uncountable.csv`
|
60
|
+
|
61
|
+
## Credits
|
62
|
+
|
63
|
+
Krzysztof Wróbel (djstrong)
|
64
|
+
Aleksander Smywiński-Pohl (apohllo)
|
data/lib/wiktionary/noun.rb
CHANGED
@@ -1,4 +1,6 @@
|
|
1
|
+
# encoding: utf-8
|
1
2
|
require 'csv'
|
3
|
+
require 'unicode_utils'
|
2
4
|
|
3
5
|
module Wiktionary
|
4
6
|
class Noun
|
@@ -39,7 +41,16 @@ module Wiktionary
|
|
39
41
|
|
40
42
|
# Returns list of possible singular forms of noun.
|
41
43
|
def singularize(noun)
|
42
|
-
|
44
|
+
first_capital = false
|
45
|
+
if noun =~ /^\p{Lu}/
|
46
|
+
noun = UnicodeUtils.downcase(noun[0]) + noun[1..-1]
|
47
|
+
first_capital = true
|
48
|
+
end
|
49
|
+
result = @plural_to_singulars[noun]
|
50
|
+
if first_capital
|
51
|
+
result.map!{|word| UnicodeUtils.upcase(word[0]) + word[1..-1] }
|
52
|
+
end
|
53
|
+
result
|
43
54
|
end
|
44
55
|
|
45
56
|
private
|
@@ -70,13 +81,16 @@ module Wiktionary
|
|
70
81
|
end
|
71
82
|
|
72
83
|
def add(singular,plurals)
|
84
|
+
singular = UnicodeUtils.downcase(singular)
|
85
|
+
plurals = plurals.map{|pl| UnicodeUtils.downcase(pl) }
|
73
86
|
plurals.each do |plural|
|
74
|
-
@plural_to_singulars[plural] << singular
|
75
|
-
@singular_to_plurals[singular] << plural
|
87
|
+
@plural_to_singulars[plural] << singular unless @plural_to_singulars[plural].include?(singular)
|
88
|
+
@singular_to_plurals[singular] << plural unless @singular_to_plurals[singular].include?(plural)
|
76
89
|
end
|
77
90
|
end
|
78
91
|
|
79
92
|
def add_uncountable(singular)
|
93
|
+
singular = UnicodeUtils.downcase(singular)
|
80
94
|
@singular_to_plurals[singular] ||= []
|
81
95
|
end
|
82
96
|
end
|
data/spec/noun.rb
CHANGED
@@ -25,5 +25,7 @@ RSpec.describe Wiktionary::Noun do
|
|
25
25
|
expect(@nouns.singularize("politics")).to include "politics"
|
26
26
|
expect(@nouns.singularize("oxen")).to include "ox"
|
27
27
|
expect(@nouns.singularize("feet")).to include "foot"
|
28
|
+
expect(@nouns.singularize("Dogs")).to include "Dog"
|
29
|
+
expect(@nouns.singularize("Γ rays")).to include "Γ ray"
|
28
30
|
end
|
29
31
|
end
|
data/wiktionary.gemspec
ADDED
@@ -0,0 +1,25 @@
|
|
1
|
+
Gem::Specification.new do |s|
|
2
|
+
s.name = "wiktionary"
|
3
|
+
s.version = "0.1.1"
|
4
|
+
s.date = "#{Time.now.strftime("%Y-%m-%d")}"
|
5
|
+
s.required_ruby_version = '>= 2.0.0'
|
6
|
+
s.authors = ['Krzysztof Wróbel','Aleksander Smywiński-Pohl']
|
7
|
+
s.email = ["djstrong@gmail.com","apohllo@o2.pl"]
|
8
|
+
s.homepage = "http://github.com/cycloped-io/wiktionary"
|
9
|
+
s.summary = "Word morphology and conversion based on Wiktionary"
|
10
|
+
s.description = "English words morphological description and basic conversion rules based on the English Wiktionary."
|
11
|
+
s.license = "http://opensource.org/licenses/MIT"
|
12
|
+
|
13
|
+
s.rubyforge_project = "wiktionary"
|
14
|
+
s.rdoc_options = ["--main", "Readme.md"]
|
15
|
+
|
16
|
+
s.files = `git ls-files`.split("\n")
|
17
|
+
s.test_files = `git ls-files -- {test,spec,features}/*`.split("\n")
|
18
|
+
s.require_path = "lib"
|
19
|
+
|
20
|
+
s.add_dependency("unicode_utils")
|
21
|
+
|
22
|
+
s.add_development_dependency("rspec", [">= 3.2.0","< 4.0.0"])
|
23
|
+
s.add_development_dependency("rake", [">= 10.4.0","< 11.0.0"])
|
24
|
+
end
|
25
|
+
|
metadata
CHANGED
@@ -1,16 +1,30 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: wiktionary
|
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
|
+
- Krzysztof Wróbel
|
8
8
|
- Aleksander Smywiński-Pohl
|
9
9
|
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
date: 2015-08-
|
12
|
+
date: 2015-08-22 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: unicode_utils
|
16
|
+
requirement: !ruby/object:Gem::Requirement
|
17
|
+
requirements:
|
18
|
+
- - ! '>='
|
19
|
+
- !ruby/object:Gem::Version
|
20
|
+
version: '0'
|
21
|
+
type: :runtime
|
22
|
+
prerelease: false
|
23
|
+
version_requirements: !ruby/object:Gem::Requirement
|
24
|
+
requirements:
|
25
|
+
- - ! '>='
|
26
|
+
- !ruby/object:Gem::Version
|
27
|
+
version: '0'
|
14
28
|
- !ruby/object:Gem::Dependency
|
15
29
|
name: rspec
|
16
30
|
requirement: !ruby/object:Gem::Requirement
|
@@ -60,7 +74,9 @@ executables: []
|
|
60
74
|
extensions: []
|
61
75
|
extra_rdoc_files: []
|
62
76
|
files:
|
77
|
+
- .gitignore
|
63
78
|
- .rspec
|
79
|
+
- Readme.md
|
64
80
|
- data/noun.csv
|
65
81
|
- data/noun_countable_and_uncountable.csv
|
66
82
|
- data/noun_non_attested.csv
|
@@ -72,6 +88,7 @@ files:
|
|
72
88
|
- lib/wiktionary/noun.rb
|
73
89
|
- spec/noun.rb
|
74
90
|
- spec/spec_helper.rb
|
91
|
+
- wiktionary.gemspec
|
75
92
|
homepage: http://github.com/cycloped-io/wiktionary
|
76
93
|
licenses:
|
77
94
|
- http://opensource.org/licenses/MIT
|