shalmaneser 1.2.0.rc1 → 1.2.0.rc2

data/lib/shalmaneser/version.rb

@@ -1,3 +1,3 @@
 module Shalmaneser
-  VERSION = '1.2.0.rc1'
+  VERSION = '1.2.0.rc2'
 end

metadata

@@ -1,83 +1,83 @@
 --- !ruby/object:Gem::Specification
 name: shalmaneser
 version: !ruby/object:Gem::Version
-  version: 1.2.0.rc1
+  version: 1.2.0.rc2
 platform: ruby
 authors:
 - Andrei Beliankou
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-01-03 00:00:00.000000000 Z
+date: 2014-01-06 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: mysql
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ~>
       - !ruby/object:Gem::Version
         version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ~>
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: rdoc
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ~>
       - !ruby/object:Gem::Version
-        version: 3.9.1
+        version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ~>
       - !ruby/object:Gem::Version
-        version: 3.9.1
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ~>
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ~>
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: yard
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ~>
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ~>
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ~>
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ~>
       - !ruby/object:Gem::Version
         version: '0'
 description: |
@@ -98,6 +98,21 @@ extra_rdoc_files:
 - LICENSE.md
 - CHANGELOG.md
 files:
+- .yardopts
+- CHANGELOG.md
+- LICENSE.md
+- README.md
+- bin/fred
+- bin/frprep
+- bin/rosy
+- doc/SB_README
+- doc/exp_files_description.txt
+- doc/fred.pdf
+- doc/index.md
+- doc/salsa_tool.pdf
+- doc/salsatigerxml.pdf
+- doc/shal_doc.pdf
+- doc/shal_lrec.pdf
 - lib/common/AbstractSynInterface.rb
 - lib/common/ConfigData.rb
 - lib/common/Counter.rb
@@ -128,6 +143,8 @@ files:
 - lib/common/headz.rb
 - lib/common/option_parser.rb
 - lib/common/ruby_class_extensions.rb
+- lib/ext/maxent/Classify.class
+- lib/ext/maxent/Train.class
 - lib/fred/Baseline.rb
 - lib/fred/FileZipped.rb
 - lib/fred/FredBOWContext.rb
@@ -201,35 +218,15 @@ files:
 - lib/rosy/opt_parser.rb
 - lib/rosy/rosy.rb
 - lib/shalmaneser/version.rb
-- README.md
-- LICENSE.md
-- CHANGELOG.md
-- .yardopts
-- test/frprep/test_opt_parser.rb
-- test/functional/functional_test_helper.rb
-- test/functional/test_fred.rb
-- test/functional/test_frprep.rb
-- test/functional/test_rosy.rb
-- test/functional/sample_experiment_files/fred_test.salsa.erb
-- test/functional/sample_experiment_files/fred_train.salsa.erb
-- test/functional/sample_experiment_files/prp_test.salsa.erb
-- test/functional/sample_experiment_files/prp_test.salsa.fred.standalone.erb
-- test/functional/sample_experiment_files/prp_test.salsa.rosy.standalone.erb
-- test/functional/sample_experiment_files/prp_train.salsa.erb
-- test/functional/sample_experiment_files/prp_train.salsa.fred.standalone.erb
-- test/functional/sample_experiment_files/prp_train.salsa.rosy.standalone.erb
-- test/functional/sample_experiment_files/rosy_test.salsa.erb
-- test/functional/sample_experiment_files/rosy_train.salsa.erb
-- bin/frprep
-- bin/fred
-- bin/rosy
 homepage: https://github.com/arbox/shalmaneser
 licenses:
 - GPL-2.0
-metadata: {}
+metadata:
+  issue_tracker: https://github.com/arbox/shalmaneser/issues
+  homepage: http://bu.chsta.be/projects/shalmaneser/
 post_install_message: |2+
 
-  Thank you for installing Shalmaneser 1.2.0.rc1!
+  Thank you for installing Shalmaneser 1.2.0.rc2!
 
   This software package has multiple external dependencies:
   - OpenNLP Maximum Entropy Classifier;
@@ -239,8 +236,8 @@ post_install_message: |2+
   - TreeTagger;
   - MySQL Database Server etc.
 
-  Please proceede to installation instructions on our wiki:
-  https://github.com/arbox/shalmaneser/wiki/Installation
+  Please proceede to installation instructions:
+  https://github.com/arbox/shalmaneser/blob/1.2/doc/index.md
 
   If you find any bugs or have questions consider opeing a ticket:
   https://github.com/arbox/shalmaneser/issues
@@ -260,16 +257,12 @@ required_rubygems_version: !ruby/object:Gem::Requirement
   - - '>'
     - !ruby/object:Gem::Version
       version: 1.3.1
-requirements: []
+requirements:
+- mysql-server
 rubyforge_project: 
-rubygems_version: 2.0.14
+rubygems_version: 2.2.0
 signing_key: 
 specification_version: 4
 summary: SHALMANESER - SHALlow seMANtic parSER
-test_files:
-- test/frprep/test_opt_parser.rb
-- test/functional/functional_test_helper.rb
-- test/functional/test_fred.rb
-- test/functional/test_frprep.rb
-- test/functional/test_rosy.rb
+test_files: []
 has_rdoc: 

data/test/frprep/test_opt_parser.rb

@@ -1,94 +0,0 @@
-# -*- coding: utf-8 -*-
-
-require 'test/unit'
-require 'stringio' # for helper methods
-require 'frprep/opt_parser'
-
-include FrPrep
-
-class TestOptParser < Test::Unit::TestCase
-
-  def setup
-    @exp_file = 'test/frprep/data/prp_test.salsa'
-    @valid_opts = ['--expfile', @exp_file,
-                   '--help'
-                  ]
-  end
-
-  def test_public_methods
-    assert_respond_to(OptParser, :parse)
-  end
-
-  # It should return a FrPrepConfigData object.
-  def test_parse_method
-    input = ['-e', @exp_file]
-    return_value = OptParser.parse(input)
-    assert(return_value.instance_of?(FrPrepConfigData))
-  end
-
-  # It should reject the empty input and exit.
-  def test_empty_input
-    out, err = intercept_output do
-      assert_raises(SystemExit) { OptParser.parse([]) }
-    end
-    assert_match(/You have to provide some options./, err)
-  end
-
-  # It should accept correct options.
-  # Invalid options is the matter of OptionParser itself,
-  # do not test it here.
-  # We test only, that OP exits and does not raise an exception.
-  def test_accept_correct_options
-    # this options we should treat separately
-    @valid_opts.delete('--help')
-    assert_nothing_raised { OptParser.parse(@valid_opts) }
-
-    stdout, stderr = intercept_output do 
-      assert_raises(SystemExit) { OptParser.parse(['--invalid-option']) }
-    end
-
-    assert_match(/You have provided an invalid option:/, stderr)
-  end
-
-  # It should successfully exit with some options.
-  def test_successful_exit
-    quietly do
-      success_args = ['-h', '--help']
-      success_args.each do |arg|
-        assert_raises(SystemExit) { OptParser.parse(arg.split) }
-      end
-    end
-  end
-
-end
-################################################################################
-# It is a helper method, many testable units provide some verbose output
-# to stderr and/or stdout. It is usefull to suppress any kind of verbosity.
-def quietly(&b)
-  begin
-    orig_stderr = $stderr.clone
-    orig_stdout = $stdout.clone
-    $stderr.reopen(File.new('/dev/null', 'w'))
-    $stdout.reopen(File.new('/dev/null', 'w'))
-    b.call
-  ensure
-    $stderr.reopen(orig_stderr)
-    $stdout.reopen(orig_stdout)
-  end
-end
-
-# It is a helper method for handling stdout and stderr as strings.
-def intercept_output
-  orig_stdout = $stdout
-  orig_stderr = $stderr
-  $stdout = StringIO.new
-  $stderr = StringIO.new
-  
-  yield
-  
-  return $stdout.string, $stderr.string
-ensure
-  $stdout = orig_stdout
-  $stderr = orig_stderr
-end
-

data/test/functional/functional_test_helper.rb

@@ -1,40 +0,0 @@
-require 'erb'
-
-module FunctionalTestHelper
-  PREF = 'test/functional/sample_experiment_files'
-
-  PRP_TEST_FILE   = 'test/functional/sample_experiment_files/prp_test.salsa'
-  PRP_TEST_FILE_FRED_STD = "#{PREF}/prp_test.salsa.fred.standalone"
-  PRP_TEST_FILE_ROSY_STD = "#{PREF}/prp_test.salsa.rosy.standalone"
-  PRP_TRAIN_FILE  = 'test/functional/sample_experiment_files/prp_train.salsa'
-  PRP_TRAIN_FILE_FRED_STD  = "#{PREF}/prp_train.salsa.fred.standalone"
-  PRP_TRAIN_FILE_ROSY_STD  = "#{PREF}/prp_train.salsa.rosy.standalone"
-
-  FRED_TEST_FILE  = 'test/functional/sample_experiment_files/fred_test.salsa'
-  FRED_TRAIN_FILE = 'test/functional/sample_experiment_files/fred_train.salsa'
-  ROSY_TEST_FILE  = 'test/functional/sample_experiment_files/rosy_test.salsa'
-  ROSY_TRAIN_FILE = 'test/functional/sample_experiment_files/rosy_train.salsa'
-
-  # Run an external process for functional testing and check the return code.
-  # <system> returns <true> if the external code exposes no errors.
-  # <@msg> is defined for every test object.
-  def execute(cmd)
-    status = system(cmd)
-    assert(status, @msg)
-  end
-  
-  # Create a temporary exp file only for this test.
-  # Shalmaneser needs absolute paths, we provide them in exp files
-  # using templating.
-  def create_exp_file(file)
-    template = File.read("#{file}.erb")
-    text = ERB.new(template).result
-    File.open(file, 'w') do |f|
-      f.write(text)
-    end
-  end
-
-  def remove_exp_file(file)
-    File.delete(file)
-  end
-end

data/test/functional/sample_experiment_files/fred_test.salsa.erb

@@ -1,122 +0,0 @@
-experiment_ID = fred_test
-
-apply_to_all_known_targets = true
-
-enduser_mode = false
-
-verbose = true
-
-
-############################
-# Paths
-# - fred_directory: directory where Fred puts its internal data
-# - directory_output: 
-#   redirect system output of disambiguated text (in SalsaTigerXML)
-#   to another directory. 
-#   If you do not set anything here, output is to
-#   <fred_directory>/<experiment_ID>/output/stxml
-# - classifier_dir:
-#   Write trained classifiers to this directory.
-#   If you do not set this parameter, classifiers are written to
-#   <fred_directory>/<experiment_ID>/classifiers
-
-fred_directory = <%= File.expand_path('test/functional/output') %>
-classifier_dir = <%= File.expand_path('test/functional/input/fred/cls') %>
-# - preproc_descr_file_train / ...test
-#   where the experiment file for frprep is located
-#   (preprocessing for Fred and Rosy)
-#   for the preprocessing of the data used in this experiment
-#
-#   give one preprocessing file name for the training data
-#   and one for the test data
-#   (If you only ever use test data in this experiment, you only
-#   need to give preproc_descr_file_test, and vice versa for training data.)
-
-preproc_descr_file_test = <%= File.expand_path('test/functional/sample_experiment_files/prp_test.salsa.fred.standalone') %>
-
-#####################
-# noncontiguous input?
-# if so, set 'noncontiguous_input' to 'true' (default is 'false')
-# Also give the larger corpus from which the input sentences are:
-# - directory
-# - format: same possibilities as for frprep format
-# - encoding: same possibilities as for frprep encoding
-
-noncontiguous_input = false
-#larger_corpus_dir = 
-larger_corpus_format = SalsaTigerXML
-#larger_corpus_encoding = iso
-
-
-#################
-# Features
-
-# bag-of-words context, with given context size,
-# for example:
- feature = context 50
- feature = context 2
-#
-# (you can give more than one context feature line!)
-#
-# other possible features:
-# feature = syntax
-# feature = synsem
-#
-# syntax: grammatical functions
-# synsem: grammatical functions plus headwords
-
-#feature = context % %contextsize%
-feature = syntax
-
-# How to handle training data that is labeled
-# with multiple sense labels?
-# - binarize (default): This works only with binary classifiers. 
-#   When featurizing for the binary classifiers, consider an item 
-#   positive if its set of assigned labels includes the 
-#   label for this binary classifier.
-# - repeat: Repeat the instance, once for each
-#   sense label that has been assigned. (Basically, treat it
-#   as N instances with equal features but different labels.)
-# - join: join all the assigned senses into one combined sense
-#   and treat that as a separate sense to train on.
-# - keep: keep as multiple sense labels. (Note that this
-#   makes sense only for classifiers that can deal with
-#   multiple labels.)
-
-#handle_multilabel = binarize
-handle_multilabel = repeat
-
-# What to do with numerical features?
-# - keep: just leave as is
-# - repeat: for a feature with max. numerical value N,
-#   use N binary features
-# - bin: use a fixed number of bins, e.g. 5, then
-#   if feature value > 20: set all bins to 1,
-#   if feature value > 10: set the first four bins to 1, 
-#   etc.
-#   default: bin.
-#numerical_features = bin
-numerical_features = keep
-
-# Binary classifiers, or n-ary classifiers?
-# if binary classifiers, set 'binary_classifiers = true'
-# default is 'false'.
-binary_classifiers = false
-
-#################
-# Fred internal settings
-
-# what kind of classifier to use?
-#
-# format:
-# <classifier type> <path> <optionally another path>
-#
-# for maxent, give first the path where maxent resides, 
-# then <where_shalmaneser_resides>/program/tools/maxent
-classifier = maxent <%= File.expand_path('tools/maxent/maxent-2.4.0') %>
-
-
-# for binary classifiers, you can set the pseudolabel
-# on the 'negative' sense.
-# Default is 'NONE'      
-negsense = NONE