logstash-filter-stanford-nlp 0.0.1-java → 0.0.2-java

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: ff7cc127d889fca197a10767b6090798e15c26f3
-  data.tar.gz: 43502d6e32406d82ed13487239bc99054102c733
+  metadata.gz: 79376297953b669cb0332e0ab559264f84a58b29
+  data.tar.gz: ec4311f18f4d29e394bccc88e6e499de7bb18067
 SHA512:
-  metadata.gz: 297bb707f2876d2c3f6a38a31725ec814e9dd3d45833cfb1584d73e39d9ea85e7aa8dec59f8f0bf3d5c7fe8931b1137e7dc00ba5275cabae3043914244e25e10
-  data.tar.gz: ce2d3fa01e89d595c89b1f760c66d4e435fe16afd7f78b32cc4973a116102c76208b6a5e13853786def230ad2356aa66471355c04b7c7984d4db958ea7467c7c
+  metadata.gz: 536309fe7c3a8ba1a92842e2713312251c97e3109058c09af03fb7ca17799d1a938b17ba992e09bca06f4b86f3d3d85f13a1a88e6be1911dac9244a5f7734161
+  data.tar.gz: 5cd67e45fc0e5ac30be45dcade26f1afae7b66a925dd4bca29c2f775a1923063aade2ba441ab1f4eb296e8e0aec44cee0c3498ace9bd19f4cadcaedf1e98dde6

data/README.md

@@ -5,6 +5,55 @@ the Logstash with the [Stanford NLP library](http://nlp.stanford.edu/software)
 
 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.
 
+```sh
+▶ bin/logstash -p lib -e '
+input { stdin { } }
+filter { ner {}}
+output {
+  stdout { codec => rubydebug }
+}
+'
+ner plugin doesn't have a version. This plugin isn't well
+ supported by the community and likely has no maintainer. {:level=>:warn}
+Settings: Default pipeline workers: 8
+Pipeline main started
+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
+Reading POS tagger model from edu/stanford/nlp/models/pos-tagger/english-left3words/english-left3words-distsim.tagger ... done [0.8 sec].
+Loading classifier from edu/stanford/nlp/models/ner/english.all.3class.distsim.crf.ser.gz ... done [1.4 sec].
+Loading classifier from edu/stanford/nlp/models/ner/english.muc.7class.distsim.crf.ser.gz ... done [0.8 sec].
+Loading classifier from edu/stanford/nlp/models/ner/english.conll.4class.distsim.crf.ser.gz ... done [0.9 sec].
+[[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.
+Reading TokensRegex rules from edu/stanford/nlp/models/sutime/defs.sutime.txt
+May 10, 2016 9:45:39 AM edu.stanford.nlp.ling.tokensregex.CoreMapExpressionExtractor appendRules
+INFO: Read 83 rules
+Reading TokensRegex rules from edu/stanford/nlp/models/sutime/english.sutime.txt
+May 10, 2016 9:45:39 AM edu.stanford.nlp.ling.tokensregex.CoreMapExpressionExtractor appendRules
+INFO: Read 267 rules
+Reading TokensRegex rules from edu/stanford/nlp/models/sutime/english.holidays.sutime.txt
+May 10, 2016 9:45:39 AM edu.stanford.nlp.ling.tokensregex.CoreMapExpressionExtractor appendRules
+INFO: Read 25 rules
+{
+            "ner.dates" => [
+        [0] "04/04/2016",
+        [1] "9428"
+    ],
+           "@timestamp" => 2016-05-10T15:45:33.852Z,
+             "@version" => "1",
+                 "host" => "administorsmbp2.corp.verisys.com",
+            "ner.names" => [
+        [0] "Jeffrey Alan Mott",
+        [1] "Michelle Mott",
+        [2] "Sanger"
+    ],
+        "ner.locations" => [
+        [0] "Brea"
+    ],
+              "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",
+    "ner.organizations" => [
+        [0] "Aldan , Inc."
+    ]
+}
+```
 ## Developing
 
 ### 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
 - Install dependencies
 ```sh
 bundle install
+
+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
 ```
 
 #### Test

data/logstash-filter-stanford-nlp.gemspec

@@ -1,6 +1,6 @@
 Gem::Specification.new do |s|
   s.name = 'logstash-filter-stanford-nlp'
-  s.version         = '0.0.1'
+  s.version         = '0.0.2'
   s.licenses = ['Apache License (2.0)']
   s.summary = "This filter extracts named entities from the message and adds them as attributes to the message."
   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|
   s.homepage = "http://www.github.com/rahtanoj/logstash-filter-stanford-nlp"
   s.require_paths = ["lib"]
   s.platform = 'java'
+  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"
 
   # Files
   s.files =  `git ls-files -z`.split("\x0")

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: logstash-filter-stanford-nlp
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 0.0.2
 platform: java
 authors:
 - Jonathan Randall
@@ -91,7 +91,9 @@ licenses:
 metadata:
   logstash_plugin: 'true'
   logstash_group: filter
-post_install_message:
+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'
 rdoc_options: []
 require_paths:
 - lib