pragmatic_tokenizer 0.1.2 → 0.1.3
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 +26 -0
- data/lib/pragmatic_tokenizer/tokenizer.rb +15 -3
- data/lib/pragmatic_tokenizer/version.rb +1 -1
- metadata +1 -1
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA1:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 802aa9ef0922e27bb0838c65d661e0918b3f48c7
|
|
4
|
+
data.tar.gz: e4ecd8525874a49fdfbe37494d48aec07fb285ab
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 7999dd167559f7d49c2707dcf6d963ee63269bbb8d118236c59d9d67b1fb009ef54b1b8db872013f1c4ba73b9ddfae2482bff1b49d2227d197b73036695049bc
|
|
7
|
+
data.tar.gz: 7872a5e27d7aeb1332f4a00bffc5e3ea66fb09ece0b34419cc8f10f47c4b504928ded18eedcde9fa022bab9597e2ca8b3ba4ca28c89574425174a8f316d694fc
|
data/README.md
CHANGED
|
@@ -56,6 +56,24 @@ Or install it yourself as:
|
|
|
56
56
|
- `false`
|
|
57
57
|
Leaves contractions as is.
|
|
58
58
|
|
|
59
|
+
<hr>
|
|
60
|
+
|
|
61
|
+
##### `clean`
|
|
62
|
+
**default** = `'false'`
|
|
63
|
+
- `true`
|
|
64
|
+
Removes tokens consisting of only hypens or underscores.
|
|
65
|
+
- `false`
|
|
66
|
+
Leaves tokens as is.
|
|
67
|
+
|
|
68
|
+
<hr>
|
|
69
|
+
|
|
70
|
+
##### `remove_numbers`
|
|
71
|
+
**default** = `'false'`
|
|
72
|
+
- `true`
|
|
73
|
+
Removes any token that contains a number.
|
|
74
|
+
- `false`
|
|
75
|
+
Leaves tokens as is.
|
|
76
|
+
|
|
59
77
|
**Example Usage**
|
|
60
78
|
```ruby
|
|
61
79
|
text = "\"I said, 'what're you? Crazy?'\" said Sandowsky. \"I can't afford to do that.\""
|
|
@@ -84,6 +102,14 @@ PragmaticTokenizer::Tokenizer.new(text,
|
|
|
84
102
|
punctuation: 'none'
|
|
85
103
|
).tokenize
|
|
86
104
|
# => ["crazy", "sandowsky", "afford"]
|
|
105
|
+
|
|
106
|
+
text = "The price is $5.50 and it works for 5 hours."
|
|
107
|
+
PragmaticTokenizer::Tokenizer.new(text, remove_numbers: true).tokenize
|
|
108
|
+
# => ["the", "price", "is", "and", "it", "works", "for", "hours", "."]
|
|
109
|
+
|
|
110
|
+
text = "Hello ______ ."
|
|
111
|
+
PragmaticTokenizer::Tokenizer.new(text, clean: true).tokenize
|
|
112
|
+
# => ["hello", "."]
|
|
87
113
|
```
|
|
88
114
|
|
|
89
115
|
## Development
|
|
@@ -4,8 +4,8 @@ require 'pragmatic_tokenizer/languages'
|
|
|
4
4
|
module PragmaticTokenizer
|
|
5
5
|
class Tokenizer
|
|
6
6
|
|
|
7
|
-
attr_reader :text, :language, :punctuation, :remove_stop_words, :expand_contractions, :language_module
|
|
8
|
-
def initialize(text, language: 'en', punctuation: 'all', remove_stop_words: false, expand_contractions: false)
|
|
7
|
+
attr_reader :text, :language, :punctuation, :remove_stop_words, :expand_contractions, :language_module, :clean, :remove_numbers
|
|
8
|
+
def initialize(text, language: 'en', punctuation: 'all', remove_stop_words: false, expand_contractions: false, clean: false, remove_numbers: false)
|
|
9
9
|
unless punctuation.eql?('all') ||
|
|
10
10
|
punctuation.eql?('semi') ||
|
|
11
11
|
punctuation.eql?('none') ||
|
|
@@ -30,11 +30,13 @@ module PragmaticTokenizer
|
|
|
30
30
|
@punctuation = punctuation
|
|
31
31
|
@remove_stop_words = remove_stop_words
|
|
32
32
|
@expand_contractions = expand_contractions
|
|
33
|
+
@clean = clean
|
|
34
|
+
@remove_numbers = remove_numbers
|
|
33
35
|
end
|
|
34
36
|
|
|
35
37
|
def tokenize
|
|
36
38
|
return [] unless text
|
|
37
|
-
delete_stop_words(find_contractions(remove_punctuation(processor.new(language: language_module).process(text: text))))
|
|
39
|
+
delete_numbers(cleaner(delete_stop_words(find_contractions(remove_punctuation(processor.new(language: language_module).process(text: text))))))
|
|
38
40
|
end
|
|
39
41
|
|
|
40
42
|
private
|
|
@@ -45,6 +47,16 @@ module PragmaticTokenizer
|
|
|
45
47
|
Processor
|
|
46
48
|
end
|
|
47
49
|
|
|
50
|
+
def delete_numbers(tokens)
|
|
51
|
+
return tokens unless remove_numbers
|
|
52
|
+
tokens.delete_if { |t| t =~ /\D*\d+\d*/ }
|
|
53
|
+
end
|
|
54
|
+
|
|
55
|
+
def cleaner(tokens)
|
|
56
|
+
return tokens unless clean
|
|
57
|
+
tokens.delete_if { |t| t =~ /\A_+\z/ || t =~ /\A-+\z/ }
|
|
58
|
+
end
|
|
59
|
+
|
|
48
60
|
def remove_punctuation(tokens)
|
|
49
61
|
case punctuation
|
|
50
62
|
when 'all'
|