corenlp 0.0.4 → 0.0.5

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: a88d19d7dc8eae9e7df59d4fe9b1e0c492aa194f
-  data.tar.gz: 5c6a32994f6720210b7a909c5b839503530793b3
+  metadata.gz: 13fb6d3e676a78f59359715c392e857d4836198e
+  data.tar.gz: ee58cbc6af1c899a1ef7cb070e2bad0c939c3765
 SHA512:
-  metadata.gz: b5f185cda3feb604e97e5682440a01f763773e80631bf5a68aa19a1a35e2874999770dd8707af2d74cb9baf630491219fdba498284f37a784813510d48c6549f
-  data.tar.gz: 99cfc0054a47e92c517b6ba9025e063d6fb316a2788acf9255079ab828a7f046ff82057fee9b2b1a154127f7825ce6abcef0eae52a08e59175c0d94bcb58233b
+  metadata.gz: 649e14c7fc8936da85e307bde80eaf1b3615c87faa61b2137a8a673aafd8dfea18b8ca300851fb6107b55519edb7dd42782213272e9585553d77878a5674f53b
+  data.tar.gz: c0fc54d340e2d2c03067066989d9a9b70e866c49f5f5250c1512735ab2b8bc742d0d894b8c7edc3504edd4f00d7b947135e0e9f5e8998a19e21e1b63df81278e

data/README.md

@@ -38,11 +38,12 @@ The following code will build up a treebank structure for the raw text "Put the
 
 ## Options
 
-The Treebank object can be initialize with various options.
+The Treebank object can be initialized with various options.
 
  * `java_max_memory` - set to 3GB by default. This can be customized via the Treebank initializer to be `-Xmx2g`, which would use a max of 2GB of memory, for example.
  * `threads_to_use` - number of threads Stanford CoreNLP uses to parse text. This is set to 4 by default. This option is passed to the Java executable.
  * `output_directory` - by default this is `./tmp/language_processing`, which already exists. This is where Stanford CoreNLP XML files are placed. These XML files represented the structured parser output.
+ * `deps_dir` - the directory where the Stanford CoreNLP dependencies files are. By default this is './lib/ext`.
 
 ## Tests
 

data/lib/corenlp.rb

@@ -4,7 +4,7 @@ Bundler.require
 
 module Corenlp
   class Treebank
-    attr_accessor :raw_text, :filenames, :output_directory, :summary_file, :threads_to_use, :java_max_memory, :sentences
+    attr_accessor :raw_text, :filenames, :output_directory, :summary_file, :threads_to_use, :java_max_memory, :sentences, :deps_dir
 
     def initialize(attrs = {})
       self.raw_text = attrs[:raw_text] || ""
@@ -15,6 +15,7 @@ module Corenlp
       self.threads_to_use = attrs[:threads_to_use] || 4
       self.java_max_memory = attrs[:java_max_memory] || "-Xmx3g"
       self.sentences = []
+      self.deps_dir = attrs[:deps_dir] || "./lib/ext"
     end
 
     def write_output_file_and_summary_file
@@ -25,8 +26,7 @@ module Corenlp
     end
 
     def process_files_with_stanford_corenlp
-      deps = "./lib/ext" # dependencies directory: JARs, model files, taggers, etc.
-      classpath = "#{deps}/stanford-corenlp-3.4.jar:#{deps}/stanford-corenlp-3.4-models.jar:#{deps}/xom.jar:#{deps}/joda-time.jar:#{deps}/jollyday.jar:#{deps}/ejml-0.23.jar"
+      classpath = "#{deps_dir}/stanford-corenlp-3.4.jar:#{deps_dir}/stanford-corenlp-3.4-models.jar:#{deps_dir}/xom.jar:#{deps_dir}/joda-time.jar:#{deps_dir}/jollyday.jar:#{deps_dir}/ejml-0.23.jar"
       stanford_bin = "edu.stanford.nlp.pipeline.StanfordCoreNLP"
       annotators = "tokenize,ssplit,pos,lemma,parse,ner"
 

data/lib/corenlp/version.rb

@@ -1,3 +1,3 @@
 module Corenlp
-  VERSION = "0.0.4"
+  VERSION = "0.0.5"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: corenlp
 version: !ruby/object:Gem::Version
-  version: 0.0.4
+  version: 0.0.5
 platform: ruby
 authors:
 - Lengio Corporation