cloud_text 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 983b4f884b5029e10005ae1e89c31d2c97f16ace
+  data.tar.gz: 88cea0d72ea1fde97fb59cc552552c3efebb8adf
+SHA512:
+  metadata.gz: 4e9f961744d2d31dd61a075029c53746161c723e588199995a2dbd8a36b9f80abb19c50b3fe0345a0d118310a82c27ccbd8a32662487910cab9c8eec5590ab65
+  data.tar.gz: 064e0468f37ebc8ba528f2f27d6fafcba6b102bfda2b42823ccd17b1bee3020f1899f674e561a0cd46e3d03755517e397617082ff88873b335194df215b77732

data/.gitignore

@@ -0,0 +1,11 @@
+/.bundle/
+/.yardoc
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+
+# rspec failure tracking
+.rspec_status

data/.rspec

@@ -0,0 +1,3 @@
+--format documentation
+--color
+--require spec_helper

data/.travis.yml

@@ -0,0 +1,5 @@
+sudo: false
+language: ruby
+rvm:
+  - 2.3.1
+before_install: gem install bundler -v 1.16.1

data/CODE_OF_CONDUCT.md

@@ -0,0 +1,74 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+In the interest of fostering an open and welcoming environment, we as
+contributors and maintainers pledge to making participation in our project and
+our community a harassment-free experience for everyone, regardless of age, body
+size, disability, ethnicity, gender identity and expression, level of experience,
+nationality, personal appearance, race, religion, or sexual identity and
+orientation.
+
+## Our Standards
+
+Examples of behavior that contributes to creating a positive environment
+include:
+
+* Using welcoming and inclusive language
+* Being respectful of differing viewpoints and experiences
+* Gracefully accepting constructive criticism
+* Focusing on what is best for the community
+* Showing empathy towards other community members
+
+Examples of unacceptable behavior by participants include:
+
+* The use of sexualized language or imagery and unwelcome sexual attention or
+advances
+* Trolling, insulting/derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or electronic
+  address, without explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Our Responsibilities
+
+Project maintainers are responsible for clarifying the standards of acceptable
+behavior and are expected to take appropriate and fair corrective action in
+response to any instances of unacceptable behavior.
+
+Project maintainers have the right and responsibility to remove, edit, or
+reject comments, commits, code, wiki edits, issues, and other contributions
+that are not aligned to this Code of Conduct, or to ban temporarily or
+permanently any contributor for other behaviors that they deem inappropriate,
+threatening, offensive, or harmful.
+
+## Scope
+
+This Code of Conduct applies both within project spaces and in public spaces
+when an individual is representing the project or its community. Examples of
+representing a project or community include using an official project e-mail
+address, posting via an official social media account, or acting as an appointed
+representative at an online or offline event. Representation of a project may be
+further defined and clarified by project maintainers.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported by contacting the project team at recepinancc@gmail.com. All
+complaints will be reviewed and investigated and will result in a response that
+is deemed necessary and appropriate to the circumstances. The project team is
+obligated to maintain confidentiality with regard to the reporter of an incident.
+Further details of specific enforcement policies may be posted separately.
+
+Project maintainers who do not follow or enforce the Code of Conduct in good
+faith may face temporary or permanent repercussions as determined by other
+members of the project's leadership.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
+available at [http://contributor-covenant.org/version/1/4][version]
+
+[homepage]: http://contributor-covenant.org
+[version]: http://contributor-covenant.org/version/1/4/

data/Gemfile

@@ -0,0 +1,9 @@
+source "https://rubygems.org"
+
+git_source(:github) {|repo_name| "https://github.com/#{repo_name}" }
+
+# Specify your gem's dependencies in cloud_text.gemspec
+gemspec
+gem 'unicode_utils'
+gem 'stopwords-filter'
+gem 'ruby-stemmer'

data/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2017 Twentify
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

data/README.md

@@ -0,0 +1,42 @@
+# CloudText
+
+This gem removes punctuation and digits(optional), filters stopwords for the chosen language ('tr', 'en' or 'fr'), does stemming on the words and outputs an array of words with their frequencies.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'cloud_text'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install cloud_text
+
+## Usage
+
+```ruby
+require 'cloud_text'
+
+# Default options
+# remove_digits => false
+# language => "en"
+# stemming => false
+
+options = { remove_digits: false, language: "en", stemming: true }
+cleaner = CloudText.clean_text("Your text to be cleaned, will come here1!1", options)
+# => [["come", 1], ["will", 1], ["clean", 1], ["text", 1]]
+```
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/twentify/cloud_text. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [Contributor Covenant](http://contributor-covenant.org) code of conduct.
+
+## Code of Conduct
+
+Everyone interacting in the CloudText project’s codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/twentify/cloud_text/blob/master/CODE_OF_CONDUCT.md).

data/Rakefile

@@ -0,0 +1,6 @@
+require "bundler/gem_tasks"
+require "rspec/core/rake_task"
+
+RSpec::Core::RakeTask.new(:spec)
+
+task :default => :spec

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "cloud_text"
+
+# You can add fixtures and/or initialization code here to make experimenting
+# with your gem easier. You can also use a different console, if you like.
+
+# (If you use this, don't forget to add pry to your Gemfile!)
+# require "pry"
+# Pry.start
+
+require "irb"
+IRB.start(__FILE__)

data/bin/setup

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+set -euo pipefail
+IFS=$'\n\t'
+set -vx
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/cloud_text.gemspec

@@ -0,0 +1,27 @@
+
+lib = File.expand_path("../lib", __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require "cloud_text/version"
+
+Gem::Specification.new do |spec|
+  spec.name          = "cloud_text"
+  spec.version       = CloudText::VERSION
+  spec.authors       = ["recepinanc"]
+  spec.email         = ["recepinancc@gmail.com"]
+
+  spec.summary       = "Cleans the given text for the given language."
+  spec.description   = "This gem removes punctuation and digits(optional), filters stopwords for the chosen language ('tr', 'en' or 'fr'), does stemming on the words and outputs an array of words with their frequencies."
+  spec.homepage      = "https://github.com/twentify/cloud_text"
+  spec.license       = 'MIT'
+
+  spec.files         = `git ls-files -z`.split("\x0").reject do |f|
+    f.match(%r{^(test|spec|features)/})
+  end
+  spec.bindir        = "exe"
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "bundler", "~> 1.16"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "rspec", "~> 3.0"
+end

data/lib/cloud_text/version.rb

@@ -0,0 +1,3 @@
+module CloudText
+  VERSION = "0.1.0"
+end

data/lib/cloud_text.rb

@@ -0,0 +1,56 @@
+require "cloud_text/version"
+require "unicode_utils"
+require "stopwords"
+require "lingua/stemmer"
+
+module CloudText
+
+  def self.clean_text(input, options = {})
+    @input = input
+    @options = options
+
+    # Remove punctuation and/or digits
+    remove_digits = @options.fetch(:remove_digits, false)
+    if remove_digits
+      @input = input.gsub(/[^A-Za-z0-9^şŞıİçÇöÖüÜĞğ\s]|_|\d/, ' ')
+    else
+      @input = input.gsub(/[^A-Za-z0-9^şŞıİçÇöÖüÜĞğ\s]|_/, ' ')
+    end
+    # Reduce multiple whitespaces into single whitespace
+    @input = @input.gsub(/\s+/, ' ')
+
+    # Lowercase all tokens
+    @language = @options.fetch(:language, "en")
+    @input = UnicodeUtils.downcase(@input, @language.to_sym)
+
+    # Filter stopwords
+    @cutsom_stopwords = @options.fetch(:stopwords, [])
+    if @language == "tr"
+      stopword_filter = Stopwords::Filter.new tr_stopwords
+    else
+      stopword_filter = Stopwords::Snowball::Filter.new @language
+    end
+
+    # Here we intentionally do not downcase custom_stopwords 
+    # since we want to filter only capitalized version of a word
+    stopword_filter.stopwords << @cutsom_stopwords
+    @input = stopword_filter.filter(@input.split)
+    
+    # Stemming
+    stemming_enabled = @options.fetch(:stemming, false)
+    if stemming_enabled
+      stemmer = Lingua::Stemmer.new(language: @language)
+      @input = @input.map do |word|
+        stemmer.stem(word)
+      end
+    end
+
+    # Counting the words, generate array for each element like => [word, frequency]
+    @result = @input.each_with_object(Hash.new(0)) { |token, hash| hash[token] += 1 }.sort_by {|k,v| v}.reverse
+  end
+
+  private
+  def self.tr_stopwords
+    ['a','acaba','altı','altmış','ama','ancak','arada','artık','asla','aslında','aslında','ayrıca','az','bana','bazen','bazı','bazıları','belki','ben','benden','beni','benim','beri','beş','bile','bilhassa','bin','bir','biraz','birçoğu','birçok','biri','birisi','birkaç','birşey','biz','bizden','bize','bizi','bizim','böyle','böylece','bu','buna','bunda','bundan','bunlar','bunları','bunların','bunu','bunun','burada','bütün','çoğu','çoğunu','çok','çünkü','da','daha','dahi','dan','de','defa','değil','diğer','diğeri','diğerleri','diye','doksan','dokuz','dolayı','dolayısıyla','dört','e','edecek','eden','ederek','edilecek','ediliyor','edilmesi','ediyor','eğer','elbette','elli','en','etmesi','etti','ettiği','ettiğini','fakat','falan','filan','gene','gereği','gerek','gibi','göre','hala','halde','halen','hangi','hangisi','hani','hatta','hem','henüz','hep','hepsi','her','herhangi','herkes','herkese','herkesi','herkesin','hiç','hiçbir','hiçbiri','i','ı','için','içinde','iki','ile','ilgili','ise','işte','itibaren','itibariyle','kaç','kadar','karşın','kendi','kendilerine','kendine','kendini','kendisi','kendisine','kendisini','kez','ki','kim','kime','kimi','kimin','kimisi','kimse','kırk','madem','mi','mı','milyar','milyon','mu','mü','nasıl','ne','neden','nedenle','nerde','nerede','nereye','neyse','niçin','nin','nın','niye','nun','nün','o','öbür','olan','olarak','oldu','olduğu','olduğunu','olduklarını','olmadı','olmadığı','olmak','olması','olmayan','olmaz','olsa','olsun','olup','olur','olur','olursa','oluyor','on','ön','ona','önce','ondan','onlar','onlara','onlardan','onları','onların','onu','onun','orada','öte','ötürü','otuz','öyle','oysa','pek','rağmen','sana','sanki','sanki','şayet','şekilde','sekiz','seksen','sen','senden','seni','senin','şey','şeyden','şeye','şeyi','şeyler','şimdi','siz','siz','sizden','sizden','size','sizi','sizi','sizin','sizin','sonra','şöyle','şu','şuna','şunları','şunu','ta','tabii','tam','tamam','tamamen','tarafından','trilyon','tüm','tümü','u','ü','üç','un','ün','üzere','var','vardı','ve','veya','ya','yani','yapacak','yapılan','yapılması','yapıyor','yapmak','yaptı','yaptığı','yaptığını','yaptıkları','ye','yedi','yerine','yetmiş','yi','yı','yine','yirmi','yoksa','yu','yüz','zaten','zira']
+  end
+end

data/lib/tr_stopwords.txt

@@ -0,0 +1 @@
+['a','acaba','altı','altmış','ama','ancak','arada','artık','asla','aslında','aslında','ayrıca','az','bana','bazen','bazı','bazıları','belki','ben','benden','beni','benim','beri','beş','bile','bilhassa','bin','bir','biraz','birçoğu','birçok','biri','birisi','birkaç','birşey','biz','bizden','bize','bizi','bizim','böyle','böylece','bu','buna','bunda','bundan','bunlar','bunları','bunların','bunu','bunun','burada','bütün','çoğu','çoğunu','çok','çünkü','da','daha','dahi','dan','de','defa','değil','diğer','diğeri','diğerleri','diye','doksan','dokuz','dolayı','dolayısıyla','dört','e','edecek','eden','ederek','edilecek','ediliyor','edilmesi','ediyor','eğer','elbette','elli','en','etmesi','etti','ettiği','ettiğini','fakat','falan','filan','gene','gereği','gerek','gibi','göre','hala','halde','halen','hangi','hangisi','hani','hatta','hem','henüz','hep','hepsi','her','herhangi','herkes','herkese','herkesi','herkesin','hiç','hiçbir','hiçbiri','i','ı','için','içinde','iki','ile','ise','işte','itibaren','itibariyle','kaç','kadar','karşın','kendi','kendilerine','kendine','kendini','kendisi','kendisine','kendisini','kez','ki','kim','kime','kimi','kimin','kimisi','kimse','kırk','madem','mi','mı','milyar','milyon','mu','mü','nasıl','ne','neden','nedenle','nerde','nerede','nereye','neyse','niçin','nin','nın','niye','nun','nün','o','öbür','olan','olarak','oldu','olduğu','olduğunu','olduklarını','olmadı','olmadığı','olmak','olması','olmayan','olmaz','olsa','olsun','olup','olur','olur','olursa','oluyor','on','ön','ona','önce','ondan','onlar','onlara','onlardan','onları','onların','onu','onun','orada','öte','ötürü','otuz','öyle','oysa','pek','rağmen','sana','sanki','sanki','şayet','şekilde','sekiz','seksen','sen','senden','seni','senin','şey','şeyden','şeye','şeyi','şeyler','şimdi','siz','siz','sizden','sizden','size','sizi','sizi','sizin','sizin','sonra','şöyle','şu','şuna','şunları','şunu','ta','tabii','tam','tamam','tamamen','tarafından','trilyon','tüm','tümü','u','ü','üç','un','ün','üzere','var','vardı','ve','veya','ya','yani','yapacak','yapılan','yapılması','yapıyor','yapmak','yaptı','yaptığı','yaptığını','yaptıkları','ye','yedi','yerine','yetmiş','yi','yı','yine','yirmi','yoksa','yu','yüz','zaten',zira]

metadata

@@ -0,0 +1,102 @@
+--- !ruby/object:Gem::Specification
+name: cloud_text
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- recepinanc
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2017-12-30 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.16'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.16'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+description: This gem removes punctuation and digits(optional), filters stopwords
+  for the chosen language ('tr', 'en' or 'fr'), does stemming on the words and outputs
+  an array of words with their frequencies.
+email:
+- recepinancc@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- ".travis.yml"
+- CODE_OF_CONDUCT.md
+- Gemfile
+- LICENSE
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- cloud_text.gemspec
+- lib/cloud_text.rb
+- lib/cloud_text/version.rb
+- lib/tr_stopwords.txt
+homepage: https://github.com/twentify/cloud_text
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.6.8
+signing_key: 
+specification_version: 4
+summary: Cleans the given text for the given language.
+test_files: []