logstash-filter-stanford-nlp 0.0.1-java → 0.0.2-java
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 +51 -0
- data/logstash-filter-stanford-nlp.gemspec +2 -1
- metadata +4 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 79376297953b669cb0332e0ab559264f84a58b29
|
4
|
+
data.tar.gz: ec4311f18f4d29e394bccc88e6e499de7bb18067
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 536309fe7c3a8ba1a92842e2713312251c97e3109058c09af03fb7ca17799d1a938b17ba992e09bca06f4b86f3d3d85f13a1a88e6be1911dac9244a5f7734161
|
7
|
+
data.tar.gz: 5cd67e45fc0e5ac30be45dcade26f1afae7b66a925dd4bca29c2f775a1923063aade2ba441ab1f4eb296e8e0aec44cee0c3498ace9bd19f4cadcaedf1e98dde6
|
data/README.md
CHANGED
@@ -5,6 +5,55 @@ the Logstash with the [Stanford NLP library](http://nlp.stanford.edu/software)
|
|
5
5
|
|
6
6
|
It is fully free and fully open source. The license is Apache 2.0, meaning you are pretty much free to use it however you want in whatever way.
|
7
7
|
|
8
|
+
```sh
|
9
|
+
▶ bin/logstash -p lib -e '
|
10
|
+
input { stdin { } }
|
11
|
+
filter { ner {}}
|
12
|
+
output {
|
13
|
+
stdout { codec => rubydebug }
|
14
|
+
}
|
15
|
+
'
|
16
|
+
ner plugin doesn't have a version. This plugin isn't well
|
17
|
+
supported by the community and likely has no maintainer. {:level=>:warn}
|
18
|
+
Settings: Default pipeline workers: 8
|
19
|
+
Pipeline main started
|
20
|
+
Jeffrey Alan Mott and Michelle Mott, individuals Dda Integrity Landscape 3756 Independence Avenue Sanger, CA 93637 CSLB#774222 Decision 04/04/2016. Aldan, Inc. P.O. Box 9428, Brea, CA 92822 CSLB #949229 Decision
|
21
|
+
Reading POS tagger model from edu/stanford/nlp/models/pos-tagger/english-left3words/english-left3words-distsim.tagger ... done [0.8 sec].
|
22
|
+
Loading classifier from edu/stanford/nlp/models/ner/english.all.3class.distsim.crf.ser.gz ... done [1.4 sec].
|
23
|
+
Loading classifier from edu/stanford/nlp/models/ner/english.muc.7class.distsim.crf.ser.gz ... done [0.8 sec].
|
24
|
+
Loading classifier from edu/stanford/nlp/models/ner/english.conll.4class.distsim.crf.ser.gz ... done [0.9 sec].
|
25
|
+
[[main]>worker1] INFO edu.stanford.nlp.time.JollyDayHolidays - Initializing JollyDayHoliday for SUTime from classpath edu/stanford/nlp/models/sutime/jollyday/Holidays_sutime.xml as sutime.binder.1.
|
26
|
+
Reading TokensRegex rules from edu/stanford/nlp/models/sutime/defs.sutime.txt
|
27
|
+
May 10, 2016 9:45:39 AM edu.stanford.nlp.ling.tokensregex.CoreMapExpressionExtractor appendRules
|
28
|
+
INFO: Read 83 rules
|
29
|
+
Reading TokensRegex rules from edu/stanford/nlp/models/sutime/english.sutime.txt
|
30
|
+
May 10, 2016 9:45:39 AM edu.stanford.nlp.ling.tokensregex.CoreMapExpressionExtractor appendRules
|
31
|
+
INFO: Read 267 rules
|
32
|
+
Reading TokensRegex rules from edu/stanford/nlp/models/sutime/english.holidays.sutime.txt
|
33
|
+
May 10, 2016 9:45:39 AM edu.stanford.nlp.ling.tokensregex.CoreMapExpressionExtractor appendRules
|
34
|
+
INFO: Read 25 rules
|
35
|
+
{
|
36
|
+
"ner.dates" => [
|
37
|
+
[0] "04/04/2016",
|
38
|
+
[1] "9428"
|
39
|
+
],
|
40
|
+
"@timestamp" => 2016-05-10T15:45:33.852Z,
|
41
|
+
"@version" => "1",
|
42
|
+
"host" => "administorsmbp2.corp.verisys.com",
|
43
|
+
"ner.names" => [
|
44
|
+
[0] "Jeffrey Alan Mott",
|
45
|
+
[1] "Michelle Mott",
|
46
|
+
[2] "Sanger"
|
47
|
+
],
|
48
|
+
"ner.locations" => [
|
49
|
+
[0] "Brea"
|
50
|
+
],
|
51
|
+
"message" => "Jeffrey Alan Mott and Michelle Mott, individuals Dda Integrity Landscape 3756 Independence Avenue Sanger, CA 93637 CSLB#774222 Decision 04/04/2016. Aldan, Inc. P.O. Box 9428, Brea, CA 92822 CSLB #949229 Decision",
|
52
|
+
"ner.organizations" => [
|
53
|
+
[0] "Aldan , Inc."
|
54
|
+
]
|
55
|
+
}
|
56
|
+
```
|
8
57
|
## Developing
|
9
58
|
|
10
59
|
### 1. Plugin Developement and Testing
|
@@ -17,6 +66,8 @@ It is fully free and fully open source. The license is Apache 2.0, meaning you a
|
|
17
66
|
- Install dependencies
|
18
67
|
```sh
|
19
68
|
bundle install
|
69
|
+
|
70
|
+
curl http://nlp.stanford.edu/software/stanford-english-corenlp-2016-01-10-models.jar -o lib/edu/stanford/nlp/stanford-corenlp/3.6.0/stanford-corenlp-3.6.0-models.jar
|
20
71
|
```
|
21
72
|
|
22
73
|
#### Test
|
@@ -1,6 +1,6 @@
|
|
1
1
|
Gem::Specification.new do |s|
|
2
2
|
s.name = 'logstash-filter-stanford-nlp'
|
3
|
-
s.version = '0.0.
|
3
|
+
s.version = '0.0.2'
|
4
4
|
s.licenses = ['Apache License (2.0)']
|
5
5
|
s.summary = "This filter extracts named entities from the message and adds them as attributes to the message."
|
6
6
|
s.description = "This gem is a Logstash plugin required to be installed on top of the Logstash core pipeline using $LS_HOME/bin/logstash-plugin install gemname. This gem is not a stand-alone program"
|
@@ -9,6 +9,7 @@ Gem::Specification.new do |s|
|
|
9
9
|
s.homepage = "http://www.github.com/rahtanoj/logstash-filter-stanford-nlp"
|
10
10
|
s.require_paths = ["lib"]
|
11
11
|
s.platform = 'java'
|
12
|
+
s.post_install_message = "ATTENTION: You now need to execute - mkdir -p lib/edu/stanford/nlp/stanford-corenlp/3.6.0/ && curl http://nlp.stanford.edu/software/stanford-english-corenlp-2016-01-10-models.jar -o lib/edu/stanford/nlp/stanford-corenlp/3.6.0/stanford-corenlp-3.6.0-models.jar"
|
12
13
|
|
13
14
|
# Files
|
14
15
|
s.files = `git ls-files -z`.split("\x0")
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: logstash-filter-stanford-nlp
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0.
|
4
|
+
version: 0.0.2
|
5
5
|
platform: java
|
6
6
|
authors:
|
7
7
|
- Jonathan Randall
|
@@ -91,7 +91,9 @@ licenses:
|
|
91
91
|
metadata:
|
92
92
|
logstash_plugin: 'true'
|
93
93
|
logstash_group: filter
|
94
|
-
post_install_message:
|
94
|
+
post_install_message: 'ATTENTION: You now need to execute - mkdir -p lib/edu/stanford/nlp/stanford-corenlp/3.6.0/
|
95
|
+
&& curl http://nlp.stanford.edu/software/stanford-english-corenlp-2016-01-10-models.jar
|
96
|
+
-o lib/edu/stanford/nlp/stanford-corenlp/3.6.0/stanford-corenlp-3.6.0-models.jar'
|
95
97
|
rdoc_options: []
|
96
98
|
require_paths:
|
97
99
|
- lib
|