opener-polarity-tagger 2.4.1 → 3.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 6d245663152071934705947dd6288b58efe02df3
-  data.tar.gz: c3345160d77aa52bcf279f181cf4f2e66d49a544
+SHA256:
+  metadata.gz: 1407a3f9dab798e58f92e033a6255151545d225c03a5e056a2f2dbb6878832ed
+  data.tar.gz: 9c79bb5e40a5882effff686d11f180f7d0ababbd5e2c9d11c0a4bab1a835eb22
 SHA512:
-  metadata.gz: d96f2324a4dcf1a4536865bdeeaed29fcb8d0d7437b4c7ccdef19f33d96d1ad4b9e94cd8531ad0ed3eadcbc3efa40e9c956e9da62aeed448d5b7933d5b8b0468
-  data.tar.gz: 4c3862dc9693b72a194c726aa45b45574d53f7845ded89c3f6b15deae9f027a90bfa9f2c0ef53c58a231b49ae9106a622611b185977408faac546286d686ac34
+  metadata.gz: 53b7b5649087d0ab9728df51ccf67dd7c6ff48eeaa0c6f4c3f74a257f07b610f29dc05b0919b1d2c379becb5b31f36c5609bca49583a3eb1d0b085df256ad9e7
+  data.tar.gz: f510909ce50427bb126773dedb60b21f3998fb80f49b9e602254e3adf1de1a658ce5d5a3b8ba7a452a78d764fa3960e455ce89d3d495c82147440e17780237ea

data/LICENSE.txt

@@ -0,0 +1,13 @@
+Copyright 2014 OpeNER Project Consortium
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.

data/README.md

@@ -1,10 +1,13 @@
-Introduction
-------------
+# Introduction
 
-This repository contains the code for the OpeNER polarity tagger. This tool tags words in a KAF file with polarity information, which basically is:
+This repository contains the code for the OpeNER polarity tagger. This tool tags
+words in a KAF file with polarity information, which basically is:
 
-* Polarity information, which represents positive or negative facts in a certain domain. Good, cheap and clean can be positive words in a hotel domain, while bad, expensive and dirty could be negative ones.
-* Sentiment modifiers, which modify the polarity of a surrounding polarity word. For instance very or no are sentiment modifiers
+* Polarity information, which represents positive or negative facts in a certain
+  domain. Good, cheap and clean can be positive words in a hotel domain, while
+  bad, expensive and dirty could be negative ones.
+* Sentiment modifiers, which modify the polarity of a surrounding polarity word.
+  For instance very or no are sentiment modifiers
 
 The polarity tagger supports the following languages:
 
@@ -15,72 +18,82 @@ The polarity tagger supports the following languages:
 * Italian
 * Spanish
 
-##How-to##
-
-The main script of this tool is a python file, which accepts a set of parameters to determine which features
-or options we want to use. The language is read from the KAF file, so it doesn't need to be specified as a parameter
-The program reads a KAF file from the standard input and writes the resulting KAf in the standard output.
-To see the options you can call to the main script with the -h or --help option
-````shell
-$ python core/poltagger-basic-multi.py -h
-usage: poltagger-basic-multi.py [-h] [--no-time] [--ignore-pos]
-                                [--show-lexicons {nl,en,de,es,it,fr}]
-                                [--lexicon LEXICON] [--silent] [--version]
-
-Tags a text with polarities at lemma level
-
-optional arguments:
-  -h, --help            show this help message and exit
-  --no-time             For not including timestamp in header
-  --ignore-pos          Ignore the pos labels
-  --show-lexicons {nl,en,de,es,it,fr}
-                        Show lexicons for the given language and exit
-  --lexicon LEXICON     Lexicon identifier, check with --show-lexicons LANG
-                        for options
-  --lexicon-path LEXICON The path of the lexicons
-  --silent              Turn off debug info
-  --version             show program's version number and exit
-````
-
-The `--ignore-pos` parameter must be used when want to ignore the part-of-speech information assigned to the lemmas, and we want to assign polarities 
-just to the lemmas, not considering the POS tag. This could be useful when the information provided by the pos-tagger is not accurate or the pos-tagging
-has not been processed.
-
-The main options are those concerning with the usage of different lexicons. The lexicons are provided by the
-VU-sentiment-lexicon library (https://github.com/opener-project/VU-sentiment-lexicon), which needs to be installed.
-You can see what the lexicons available for a given language are by calling to the program with the option --show-lexicons LANG,
-for instance:
-````shell
-core/poltagger-basic-multi.py --show-lexicons nl
-
-##############################
-Available lexicons for nl
-  Identifier: "hotel" (Default)
-    Desc: Hotel domain lexicon for Dutch
-     Res: VUA_olery_lexicon_nl_lmf
-    File: /Users/ruben/python_envs/python2.7/lib/python2.7/VUSentimentLexicon/NL-lexicon/Sentiment-Dutch-HotelDomain.xml
-
-  Identifier:"general"
-    Desc: General lexicon for Dutch
-     Res: VUA_olery_lexicon_nl_lmf
-    File: /Users/ruben/python_envs/python2.7/lib/python2.7/VUSentimentLexicon/NL-lexicon/Sentiment-Dutch-general.xml
-
-##############################
-````
-
-Then you can use the lexicon identifiers to select the proper lexicon, with the option --lexicon
-````shell
-cat my_input.nl.kaf | core/poltagger-basic-multi.py --lexicon general
-````
-
-This command will call to the polarity tagger using the general lexicon for Dutch. The lexicon identifiers are unique only per language.
-If the lexicon id is not specified(you skip the --lexicon option), or you provide a wrong identifier, the default lexicon will be loaded.
-If there is no lexicon marked as default in the --show-lexicon options, the first one in the list will be used. Check the VU-sentiment-lexicon
-for further information about how to manage lexicons and add new ones
+## How-To
+
+The main script of this tool is a python file, which accepts a set of parameters
+to determine which features or options we want to use. The language is read from
+the KAF file, so it doesn't need to be specified as a parameter The program
+reads a KAF file from the standard input and writes the resulting KAf in the
+standard output.  To see the options you can call to the main script with the -h
+or `--help` option.
+
+    $ python core/poltagger-basic-multi.py -h
+    usage: poltagger-basic-multi.py [-h] [--no-time] [--ignore-pos]
+                                    [--show-lexicons {nl,en,de,es,it,fr}]
+                                    [--lexicon LEXICON] [--silent] [--version]
+
+    Tags a text with polarities at lemma level
+
+    optional arguments:
+      -h, --help            show this help message and exit
+      --no-time             For not including timestamp in header
+      --ignore-pos          Ignore the pos labels
+      --show-lexicons {nl,en,de,es,it,fr}
+                            Show lexicons for the given language and exit
+      --lexicon LEXICON     Lexicon identifier, check with --show-lexicons LANG
+                            for options
+      --lexicon-path LEXICON The path of the lexicons
+      --silent              Turn off debug info
+      --version             show program's version number and exit
+
+The `--ignore-pos` parameter must be used when want to ignore the part-of-speech
+information assigned to the lemmas, and we want to assign polarities just to the
+lemmas, not considering the POS tag. This could be useful when the information
+provided by the pos-tagger is not accurate or the pos-tagging has not been
+processed.
+
+The main options are those concerning with the usage of different lexicons. The
+lexicons are provided by the VU-sentiment-lexicon library
+(https://github.com/opener-project/VU-sentiment-lexicon), which needs to be
+installed.  You can see what the lexicons available for a given language are by
+calling to the program with the option --show-lexicons LANG, for instance:
+
+    core/poltagger-basic-multi.py --show-lexicons nl
+
+    ##############################
+    Available lexicons for nl
+      Identifier: "hotel" (Default)
+        Desc: Hotel domain lexicon for Dutch
+         Res: VUA_olery_lexicon_nl_lmf
+        File: /Users/ruben/python_envs/python2.7/lib/python2.7/VUSentimentLexicon/NL-lexicon/Sentiment-Dutch-HotelDomain.xml
+
+      Identifier:"general"
+        Desc: General lexicon for Dutch
+         Res: VUA_olery_lexicon_nl_lmf
+        File: /Users/ruben/python_envs/python2.7/lib/python2.7/VUSentimentLexicon/NL-lexicon/Sentiment-Dutch-general.xml
+
+    ##############################
+
+Then you can use the lexicon identifiers to select the proper lexicon, with the
+option --lexicon
+
+    cat my_input.nl.kaf | core/poltagger-basic-multi.py --lexicon general
+
+This command will call to the polarity tagger using the general lexicon for
+Dutch. The lexicon identifiers are unique only per language.  If the lexicon id
+is not specified(you skip the --lexicon option), or you provide a wrong
+identifier, the default lexicon will be loaded.  If there is no lexicon marked
+as default in the --show-lexicon options, the first one in the list will be
+used. Check the VU-sentiment-lexicon for further information about how to manage
+lexicons and add new ones.
 
 ### Confused by some terminology?
 
-This software is part of a larger collection of natural language processing tools known as "the OpeNER project". You can find more information about the project at [the OpeNER portal](http://opener-project.github.io). There you can also find references to terms like KAF (an XML standard to represent linguistic annotations in texts), component, cores, scenario's and pipelines.
+This software is part of a larger collection of natural language processing
+tools known as "the OpeNER project". You can find more information about the
+project at [the OpeNER portal](http://opener-project.github.io). There you can
+also find references to terms like KAF (an XML standard to represent linguistic
+annotations in texts), component, cores, scenario's and pipelines.
 
 Quick Use Example
 -----------------
@@ -89,32 +102,33 @@ Installing the polarity-tagger can be done by executing:
 
     gem install opener-polarity-tagger
 
-The polarity tagger uses python. So it is advised to run a virtualenv before installing the gem.
+The polarity tagger uses python. So it is advised to run a virtualenv before
+installing the gem.
 
-Please bare in mind that all components in OpeNER take KAF as an input and output KAF by default.
+Please bare in mind that all components in OpeNER take KAF as an input and
+output KAF by default.
 
 ### Command line interface
 
-You should now be able to call the polarity tagger as a regular shell command: by its name. Once installed the gem normally sits in your path so you can call it directly from anywhere.
+You should now be able to call the polarity tagger as a regular shell command:
+by its name. Once installed the gem normally sits in your path so you can call
+it directly from anywhere.
 
 This aplication reads a text from standard input in order process it.
 
     cat some_kind_of_kaf_file.kaf | polarity-tagger
 
-
 This will output:
 
-```
-<term lemma="donner" morphofeat="VP3s" pos="V" tid="t119" type="open">
-  <span>
-    <!--donne-->
-    <target id="w119"/>
-  </span>
-  <sentiment polarity="neutral" resource="General domain lexicon for French . Vicomtech_general_lexicon_french"/>
-</term>
-```
+    <term lemma="donner" morphofeat="VP3s" pos="V" tid="t119" type="open">
+      <span>
+        <!--donne-->
+        <target id="w119"/>
+      </span>
+      <sentiment polarity="neutral" resource="General domain lexicon for French . Vicomtech_general_lexicon_french"/>
+    </term>
 
-##Requirements##
+## Requirements
 
 * Python 2.7.0 or newer
 * Ruby 1.9.2 or newer
@@ -127,7 +141,8 @@ You can launch a webservice by executing:
 
     polarity-tagger-server
 
-This will launch a mini webserver with the webservice. It defaults to port 9292, so you can access it at <http://localhost:9292>.
+This will launch a mini webserver with the webservice. It defaults to port 9292,
+so you can access it at <http://localhost:9292>.
 
 To launch it on a different port provide the `-p [port-number]` option like this:
 
@@ -135,20 +150,24 @@ To launch it on a different port provide the `-p [port-number]` option like this
 
 It then launches at <http://localhost:1234>
 
-Documentation on the Webservice is provided by surfing to the urls provided above. For more information on how to launch a webservice run the command with the ```-h``` option.
-
+Documentation on the Webservice is provided by surfing to the urls provided
+above. For more information on how to launch a webservice run the command with
+the `--help` option.
 
 ### Daemon
 
-Last but not least the polarity tagger comes shipped with a daemon that can read jobs (and write) jobs to and from Amazon SQS queues. For more information type:
+Last but not least the polarity tagger comes shipped with a daemon that can read
+jobs (and write) jobs to and from Amazon SQS queues. For more information type:
 
     polarity-tagger-daemon -h
 
-
 Description of dependencies
 ---------------------------
 
-This component runs best if you run it in an environment suited for OpeNER components. You can find an installation guide and helper tools in the [OpeNER installer](https://github.com/opener-project/opener-installer) and an [installation guide on the Opener Website](http://opener-project.github.io/getting-started/how-to/local-installation.html)
+This component runs best if you run it in an environment suited for OpeNER
+components. You can find an installation guide and helper tools in the
+[OpeNER installer](https://github.com/opener-project/opener-installer) and an
+[installation guide on the Opener Website](http://opener-project.github.io/getting-started/how-to/local-installation.html)
 
 At least you need the following system setup:
 
@@ -156,7 +175,10 @@ At least you need the following system setup:
 
 * Ruby 1.9.3 or newer
 * Python 2.6 or newer
-* Lxml installed
+* lxml installed
+* libarchive, on Debian/Ubuntu based systems this can be installed using
+  `sudo apt-get install libarchive-dev`
+* VUKafParserPy, install with sudo pip install 'https://github.com/opener-project/VU-kaf-parser/archive/v1.1.zip#egg=VUKafParserPy'
 
 Domain Adaption
 ---------------
@@ -171,7 +193,8 @@ Language Extension
 The Core
 --------
 
-The component is a fat wrapper around the actual language technology core. You can find the core technolies in the ``\`core/``` folder.
+The component is a wrapper around the actual language technology core. You
+can find the core technolies in the `core/` folder.
 
 Where to go from here
 ---------------------
@@ -182,10 +205,10 @@ Where to go from here
 Report problem/Get help
 -----------------------
 
-If you encounter problems, please email <support@opener-project.eu> or leave an issue in the 
+If you encounter problems, please email <support@opener-project.eu> or leave an
+issue in the
 [issue tracker](https://github.com/opener-project/polarity-tagger/issues).
 
-
 Contributing
 ------------
 
@@ -194,4 +217,3 @@ Contributing
 3. Commit your changes (`git commit -am 'Add some feature'`)
 4. Push to the branch (`git push origin my-new-feature`)
 5. Create new Pull Request
-

data/bin/console

@@ -0,0 +1,13 @@
+#!/usr/bin/env ruby
+
+require 'bundler/setup'
+require_relative '../lib/opener/polarity_tagger'
+
+begin
+  require 'awesome_print'
+  require 'pry'
+  binding.pry
+rescue LoadError
+  require 'irb'
+  IRB.start
+end

data/bin/polarity-tagger

@@ -1,6 +1,12 @@
 #!/usr/bin/env ruby
 
+require 'opener/core'
+
 require_relative '../lib/opener/polarity_tagger'
 
-cli = Opener::PolarityTagger::CLI.new(:args => ARGV)
-cli.run(STDIN.tty? ? nil : STDIN.read)
+switcher = Opener::Core::ResourceSwitcher.new
+cli      = Opener::PolarityTagger::CLI.new
+
+switcher.bind(cli.parser)
+
+cli.run

data/bin/polarity-tagger-daemon

@@ -1,10 +1,14 @@
 #!/usr/bin/env ruby
 
 require 'opener/daemons'
+require 'opener/core'
 
-exec_path = File.expand_path('../../exec/polarity-tagger.rb', __FILE__)
+switcher   = Opener::Core::ResourceSwitcher.new
+controller = Opener::Daemons::Controller.new(
+  :name      => 'opener-polarity-tagger',
+  :exec_path => File.expand_path('../../exec/polarity-tagger.rb', __FILE__)
+)
 
-Opener::Daemons::Controller.new(
-  :name      => 'polarity-tagger',
-  :exec_path => exec_path
-)
+switcher.bind(controller.parser.parser)
+
+controller.run

data/bin/polarity-tagger-server

@@ -1,54 +1,14 @@
 #!/usr/bin/env ruby
 
-require 'puma/cli'
-require 'optparse'
+require 'opener/webservice'
 require 'opener/core'
 
-rack_config   = File.expand_path('../../config.ru', __FILE__)
-switcher      = Opener::Core::ResourceSwitcher.new
-puma_args     = [rack_config]
-switcher_opts = {}
+switcher = Opener::Core::ResourceSwitcher.new
+parser   = Opener::Webservice::OptionParser.new(
+  'opener-polarity-tagger',
+  File.expand_path('../../config.ru', __FILE__)
+)
 
-option_parser = OptionParser.new do |opts|
-  opts.banner = "Usage: #{File.basename($0)} [OPTIONS]"
+switcher.bind(parser.parser)
 
-  opts.separator "\nOptions:\n\n"
-
-  opts.on('-h', '--help', 'Shows this help message') do
-    abort option_parser.to_s
-  end
-
-  opts.on('-S', '--state PATH', 'Where to store the state details') do |val|
-    puma_args += ['--state', val]
-  end
-
-  opts.on('-b', '--bind URI', 'URI to bind to (tcp://, unix://, ssl://)') do |val|
-    puma_args += ['--bind', val]
-  end
-
-  opts.on('--pidfile PATH', 'Use PATH as a pidfile') do |val|
-    puma_args += ['--pidfile', val]
-  end
-
-  opts.on('--daemon', 'Daemonize the server into the background') do |val|
-    puma_args << '--daemon'
-  end
-
-  opts.on('-e', '--environment ENVIRONMENT', 'The environment to use') do |val|
-    puma_args += ['--environment', val]
-  end
-
-  opts.separator "\nResource Options:\n\n"
-
-  switcher.bind(opts, switcher_opts)
-end
-
-option_parser.parse!(ARGV)
-
-switcher.install(switcher_opts)
-
-# Puma on JRuby does some weird stuff with forking/exec. As a result of this we
-# *have to* update ARGV as otherwise running Puma as a daemon does not work.
-ARGV.replace(puma_args)
-
-Puma::CLI.new(ARGV).run
+parser.run

data/core/LexiconMod.py

@@ -61,7 +61,6 @@ def show_lexicons(language, path=None):
     print '#'*30
     print
 
-
 class LexiconSent:
 
     def __init__(self,language='nl',lexicon_id=None, path=None):
@@ -79,10 +78,8 @@ class LexiconSent:
 
         self.load_resources(language,lexicon_id, path)
 
-
         self.__load_lexicon_xml()
 
-
     def load_resources(self,language,my_id=None, path=None):
         if path is None:
           path = os.path.dirname(__file__)
@@ -100,14 +97,9 @@ class LexiconSent:
         self.filename = os.path.join(this_folder,folder_per_lang[language],lexicons[id_to_load][0])
         self.resource = lexicons[id_to_load][1]+" . "+lexicons[id_to_load][2]
 
-
-
-
-
     def getResource(self):
         return self.resource
 
-
     def convert_pos_to_kaf(self,pos):
         my_map = {}
         my_map['adj'] = 'G'
@@ -119,7 +111,6 @@ class LexiconSent:
         my_map['verb']= 'V'
         return my_map.get(pos.lower(),'O')
 
-
     def __load_lexicon_xml(self):
         logging.debug('Loading lexicon from the file'+self.filename)
         from collections import defaultdict
@@ -160,16 +151,12 @@ class LexiconSent:
         logging.debug('Loaded: '+str(len(self.intensifiers))+' intensifiers')
         logging.debug('Loaded: '+str(len(self.sentLex))+' elements with polarity')
 
-
-
     def isIntensifier(self,lemma):
         return lemma in self.intensifiers
 
-
     def isNegator(self,lemma):
       return lemma in self.negators
 
-
     def getPolarity(self,lemma,pos):
       if pos:
           return self.sentLex.get((lemma,pos),'unknown'),pos