open-nlp 0.1.1 → 0.1.2
Sign up to get free protection for your applications and to get access to all the features.
- data/README.md +3 -3
- data/bin/en-chunker.bin +0 -0
- data/bin/en-detokenizer.xml +107 -0
- data/bin/en-ner-date.bin +0 -0
- data/bin/en-ner-location.bin +0 -0
- data/bin/en-ner-money.bin +0 -0
- data/bin/en-ner-organization.bin +0 -0
- data/bin/en-ner-percentage.bin +0 -0
- data/bin/en-ner-person.bin +0 -0
- data/bin/en-ner-time.bin +0 -0
- data/bin/en-parser-chunking.bin +0 -0
- data/bin/en-pos-maxent.bin +0 -0
- data/bin/en-pos-perceptron.bin +0 -0
- data/bin/en-sent.bin +0 -0
- data/bin/en-token.bin +0 -0
- data/lib/open-nlp.rb +1 -1
- data/lib/open-nlp/config.rb +19 -3
- data/spec/english_spec.rb +2 -2
- metadata +20 -6
data/README.md
CHANGED
@@ -2,12 +2,10 @@
|
|
2
2
|
|
3
3
|
###About
|
4
4
|
|
5
|
-
This library provides high-level Ruby bindings to the Open NLP package, a Java machine learning toolkit for natural language processing (NLP).
|
5
|
+
This library provides high-level Ruby bindings to the Open NLP package, a Java machine learning toolkit for natural language processing (NLP). This gem is compatible with Ruby 1.9.2 and 1.9.3 as well as JRuby 1.7.1. It is tested on both Java 6 and Java 7.
|
6
6
|
|
7
7
|
###Installing
|
8
8
|
|
9
|
-
__Note: If you are running on MRI, this gem will use the Ruby-Java Bridge (Rjb), which currently does not support Java 7. Therefore, if you have installed Java 7, you should set your JAVA_HOME to point to your old Java 6 install before installing Rjb; for example, `export "JAVA_HOME=/usr/lib/jvm/java-6-openjdk/"`.__
|
10
|
-
|
11
9
|
First, install the gem: `gem install open-nlp`. Then, individually download the appropriate models from the [open-nlp website](http://opennlp.sourceforge.net/models-1.5/) or just get [all English language models](louismullie.com/treat/open-nlp-english.zip) in one package (80 MB).
|
12
10
|
|
13
11
|
Place the contents of the extracted archive inside the /bin/ folder of the open-nlp gem (e.g. [...]/gems/open-nlp-0.x.x/bin/).
|
@@ -39,6 +37,8 @@ OpenNLP.jvm_args = ['-option1', '-option2']
|
|
39
37
|
# Redirect VM output to log.txt
|
40
38
|
OpenNLP.log_file = 'log.txt'
|
41
39
|
|
40
|
+
# Set default models for a language.
|
41
|
+
OpenNLP.use :language
|
42
42
|
```
|
43
43
|
|
44
44
|
###Examples
|
data/bin/en-chunker.bin
ADDED
Binary file
|
@@ -0,0 +1,107 @@
|
|
1
|
+
<?xml version="1.0" encoding="UTF-8"?>
|
2
|
+
|
3
|
+
<!--
|
4
|
+
Licensed to the Apache Software Foundation (ASF) under one
|
5
|
+
or more contributor license agreements. See the NOTICE file
|
6
|
+
distributed with this work for additional information
|
7
|
+
regarding copyright ownership. The ASF licenses this file
|
8
|
+
to you under the Apache License, Version 2.0 (the
|
9
|
+
"License"); you may not use this file except in compliance
|
10
|
+
with the License. You may obtain a copy of the License at
|
11
|
+
|
12
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
13
|
+
|
14
|
+
Unless required by applicable law or agreed to in writing,
|
15
|
+
software distributed under the License is distributed on an
|
16
|
+
"AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
|
17
|
+
KIND, either express or implied. See the License for the
|
18
|
+
specific language governing permissions and limitations
|
19
|
+
under the License.
|
20
|
+
-->
|
21
|
+
|
22
|
+
<dictionary>
|
23
|
+
<entry operation="RIGHT_LEFT_MATCHING">
|
24
|
+
<token>"</token>
|
25
|
+
</entry>
|
26
|
+
<entry operation="RIGHT_LEFT_MATCHING">
|
27
|
+
<token>'</token>
|
28
|
+
</entry>
|
29
|
+
<entry operation="MOVE_LEFT">
|
30
|
+
<token>.</token>
|
31
|
+
</entry>
|
32
|
+
<entry operation="MOVE_LEFT">
|
33
|
+
<token>?</token>
|
34
|
+
</entry>
|
35
|
+
<entry operation="MOVE_LEFT">
|
36
|
+
<token>!</token>
|
37
|
+
</entry>
|
38
|
+
<entry operation="MOVE_LEFT">
|
39
|
+
<token>,</token>
|
40
|
+
</entry>
|
41
|
+
<entry operation="MOVE_LEFT">
|
42
|
+
<token>;</token>
|
43
|
+
</entry>
|
44
|
+
<entry operation="MOVE_LEFT">
|
45
|
+
<token>:</token>
|
46
|
+
</entry>
|
47
|
+
<entry operation="MOVE_RIGHT">
|
48
|
+
<token>(</token>
|
49
|
+
</entry>
|
50
|
+
<entry operation="MOVE_LEFT">
|
51
|
+
<token>)</token>
|
52
|
+
</entry>
|
53
|
+
<entry operation="MOVE_LEFT">
|
54
|
+
<token>}</token>
|
55
|
+
</entry>
|
56
|
+
<entry operation="MOVE_RIGHT">
|
57
|
+
<token>{</token>
|
58
|
+
</entry>
|
59
|
+
<entry operation="MOVE_LEFT">
|
60
|
+
<token>]</token>
|
61
|
+
</entry>
|
62
|
+
<entry operation="MOVE_RIGHT">
|
63
|
+
<token>[</token>
|
64
|
+
</entry>
|
65
|
+
<entry operation="MOVE_RIGHT">
|
66
|
+
<token>``</token>
|
67
|
+
</entry>
|
68
|
+
<entry operation="MOVE_LEFT">
|
69
|
+
<token>''</token>
|
70
|
+
</entry>
|
71
|
+
<entry operation="MOVE_LEFT">
|
72
|
+
<token>%</token>
|
73
|
+
</entry>
|
74
|
+
<entry operation="MOVE_LEFT">
|
75
|
+
<token>n't</token>
|
76
|
+
</entry>
|
77
|
+
<entry operation="MOVE_LEFT">
|
78
|
+
<token>'ve</token>
|
79
|
+
</entry>
|
80
|
+
<entry operation="MOVE_LEFT">
|
81
|
+
<token>'d</token>
|
82
|
+
</entry>
|
83
|
+
<entry operation="MOVE_LEFT">
|
84
|
+
<token>'ll</token>
|
85
|
+
</entry>
|
86
|
+
<entry operation="MOVE_LEFT">
|
87
|
+
<token>'s</token>
|
88
|
+
</entry>
|
89
|
+
<entry operation="MOVE_LEFT">
|
90
|
+
<token>'re</token>
|
91
|
+
</entry>
|
92
|
+
<entry operation="MOVE_LEFT">
|
93
|
+
<token>'m</token>
|
94
|
+
</entry>
|
95
|
+
<entry operation="MOVE_LEFT">
|
96
|
+
<token>.org</token>
|
97
|
+
</entry>
|
98
|
+
<entry operation="MOVE_LEFT">
|
99
|
+
<token>.com</token>
|
100
|
+
</entry>
|
101
|
+
<entry operation="MOVE_LEFT">
|
102
|
+
<token>.net</token>
|
103
|
+
</entry>
|
104
|
+
<entry operation="MOVE_RIGHT">
|
105
|
+
<token>#</token>
|
106
|
+
</entry>
|
107
|
+
</dictionary>
|
data/bin/en-ner-date.bin
ADDED
Binary file
|
Binary file
|
Binary file
|
Binary file
|
Binary file
|
Binary file
|
data/bin/en-ner-time.bin
ADDED
Binary file
|
Binary file
|
Binary file
|
Binary file
|
data/bin/en-sent.bin
ADDED
Binary file
|
data/bin/en-token.bin
ADDED
Binary file
|
data/lib/open-nlp.rb
CHANGED
data/lib/open-nlp/config.rb
CHANGED
@@ -30,18 +30,34 @@ module OpenNLP::Config
|
|
30
30
|
english: 'en-detokenizer.xml'
|
31
31
|
},
|
32
32
|
# Intentionally left empty.
|
33
|
+
# Available for English, Spanish, Dutch.
|
33
34
|
name_finder: {},
|
34
35
|
parser: {
|
35
36
|
english: 'en-parser-chunking.bin'
|
36
37
|
},
|
37
38
|
pos_tagger: {
|
38
|
-
english: 'en-pos-maxent.bin'
|
39
|
+
english: 'en-pos-maxent.bin',
|
40
|
+
danish: 'da-pos-maxent.bin',
|
41
|
+
german: 'de-pos-maxent.bin',
|
42
|
+
dutch: 'nl-pos-maxent.bin',
|
43
|
+
portuguese: 'pt-pos-maxent.bin',
|
44
|
+
swedish: 'se-pos-maxent.bin'
|
39
45
|
},
|
40
46
|
sentence_detector: {
|
41
|
-
english: 'en-sent.bin'
|
47
|
+
english: 'en-sent.bin',
|
48
|
+
german: 'de-sent.bin',
|
49
|
+
danish: 'da-sent.bin',
|
50
|
+
dutch: 'nl-sent.bin',
|
51
|
+
portuguese: 'pt-sent.bin',
|
52
|
+
swedish: 'se-sent.bin'
|
42
53
|
},
|
43
54
|
tokenizer: {
|
44
|
-
english: 'en-token.bin'
|
55
|
+
english: 'en-token.bin',
|
56
|
+
danish: 'da-token.bin',
|
57
|
+
german: 'de-token.bin',
|
58
|
+
dutch: 'nl-token.bin',
|
59
|
+
portuguese: 'pt-token.bin',
|
60
|
+
swedish: 'se-token.bin'
|
45
61
|
}
|
46
62
|
}
|
47
63
|
|
data/spec/english_spec.rb
CHANGED
@@ -29,8 +29,8 @@ describe OpenNLP do
|
|
29
29
|
|
30
30
|
OpenNLP.models[:pos_tagger].get_pos_model.to_s
|
31
31
|
.index('opennlp.perceptron.PerceptronModel').should_not be_nil
|
32
|
-
|
33
|
-
tags.should eql ["DT", "NN", "IN", "DT", "NN", "VBD", "VBN", "IN", "PRP$", "NNS", "."]
|
32
|
+
|
33
|
+
tags.to_a.should eql ["DT", "NN", "IN", "DT", "NN", "VBD", "VBN", "IN", "PRP$", "NNS", "."]
|
34
34
|
|
35
35
|
end
|
36
36
|
end
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: open-nlp
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.1.
|
4
|
+
version: 0.1.2
|
5
5
|
prerelease:
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
@@ -9,24 +9,24 @@ authors:
|
|
9
9
|
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
date: 2012-12-
|
12
|
+
date: 2012-12-26 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: bind-it
|
16
16
|
requirement: !ruby/object:Gem::Requirement
|
17
17
|
none: false
|
18
18
|
requirements:
|
19
|
-
- -
|
19
|
+
- - ~>
|
20
20
|
- !ruby/object:Gem::Version
|
21
|
-
version:
|
21
|
+
version: 0.2.5
|
22
22
|
type: :runtime
|
23
23
|
prerelease: false
|
24
24
|
version_requirements: !ruby/object:Gem::Requirement
|
25
25
|
none: false
|
26
26
|
requirements:
|
27
|
-
- -
|
27
|
+
- - ~>
|
28
28
|
- !ruby/object:Gem::Version
|
29
|
-
version:
|
29
|
+
version: 0.2.5
|
30
30
|
- !ruby/object:Gem::Dependency
|
31
31
|
name: rspec
|
32
32
|
requirement: !ruby/object:Gem::Requirement
|
@@ -51,6 +51,20 @@ executables: []
|
|
51
51
|
extensions: []
|
52
52
|
extra_rdoc_files: []
|
53
53
|
files:
|
54
|
+
- bin/en-chunker.bin
|
55
|
+
- bin/en-detokenizer.xml
|
56
|
+
- bin/en-ner-date.bin
|
57
|
+
- bin/en-ner-location.bin
|
58
|
+
- bin/en-ner-money.bin
|
59
|
+
- bin/en-ner-organization.bin
|
60
|
+
- bin/en-ner-percentage.bin
|
61
|
+
- bin/en-ner-person.bin
|
62
|
+
- bin/en-ner-time.bin
|
63
|
+
- bin/en-parser-chunking.bin
|
64
|
+
- bin/en-pos-maxent.bin
|
65
|
+
- bin/en-pos-perceptron.bin
|
66
|
+
- bin/en-sent.bin
|
67
|
+
- bin/en-token.bin
|
54
68
|
- bin/jwnl-1.3.3.jar
|
55
69
|
- bin/opennlp-maxent-3.0.2-incubating.jar
|
56
70
|
- bin/opennlp-tools-1.5.2-incubating.jar
|