lib/nlp/nitnlp.nit

   1 # This file is part of NIT ( http://www.nitlanguage.org ).
   2 #
   3 # Licensed under the Apache License, Version 2.0 (the "License");
   4 # you may not use this file except in compliance with the License.
   5 # You may obtain a copy of the License at
   6 #
   7 #     http://www.apache.org/licenses/LICENSE-2.0
   8 #
   9 # Unless required by applicable law or agreed to in writing, software
  10 # distributed under the License is distributed on an "AS IS" BASIS,
  11 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  12 # See the License for the specific language governing permissions and
  13 # limitations under the License.
  14
  15 # Natural Language Processor based on the StanfordNLP core.
  16 #
  17 # This tool provides a document comparison service from command line based on
  18 # StanfordNLP and NLPVector consine similarity.
  19 #
  20 # See http://nlp.stanford.edu/software/corenlp.shtml.
  21 module nitnlp
  22
  23 import opts
  24 import nlp
  25
  26 # Option management
  27 var opt_java_cp = new OptionString("Java classpath for StanfordNLP jars", "--cp")
  28 var options = new OptionContext
  29 options.add_option(opt_java_cp)
  30 options.parse(args)
  31 var arguments = options.rest
  32
  33 # Processor initialization
  34 var java_cp = opt_java_cp.value
  35 if java_cp == null then java_cp = "*"
  36 var proc = new NLPProcessor(java_cp)
  37
  38 if arguments.length != 2 then
  39         print "Usage: nitnlp text1 text2\n"
  40         options.usage
  41         sys.exit 1
  42 end
  43
  44 var doc1 = proc.process(arguments.first)
  45 print doc1.vector.join(":", ",")
  46 var doc2 = proc.process(arguments.last)
  47 print doc2.vector.join(":", ",")
  48
  49 print doc1.vector.cosine_similarity(doc2.vector)