lingua-it-readability 1.0.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: ca7c5b85336a54accf315881255133c101aef7cd
+  data.tar.gz: d1ffbc35b45fa73951cddad360cfc1b696ce8ea2
+SHA512:
+  metadata.gz: ccc18e702fd8487276d79542117377c436cdd5b7b4d46f108e583290430051f1750808d424f40d9217ba6173d3bf0f0d08f31d6ce47833d15435c1e77176d763
+  data.tar.gz: 59d73c1511929d8bb9ce5a9fe38017e717025612e868e8415d0d6ab9c49e0fcae0d5f35d4a61444d034208b03cf045f274b744af978d7b53808024688b8c4444

data/.gitignore

@@ -0,0 +1,9 @@
+/.bundle/
+/.yardoc
+/Gemfile.lock
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/

data/.rspec

@@ -0,0 +1,2 @@
+--format documentation
+--color

data/.travis.yml

@@ -0,0 +1,4 @@
+language: ruby
+rvm:
+  - 2.3.0
+before_install: gem install bundler -v 1.11.2

data/CHANGELOG.md

@@ -0,0 +1,17 @@
+#### 1.0.0 - 2016-02-09
+###### Added
+- Some more tests.
+
+#### 0.6.0 - 2016-02-08
+###### Added
+- Types of text.
+- Some more tests.
+
+#### 0.5.0 - 2016-02-05
+###### Added
+- Initial release.
+- Sentences recognition
+- Italian abbreviations
+- Syllables recongnition
+- Gulpease readability index
+- Italian Flesch readability index

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in lingua-it-readability.gemspec
+gemspec

data/LICENSE.txt

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2016 Andrea Giacomo Baldan
+
+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 +1,44 @@
+[![Build Status](https://travis-ci.org/codepr/lingua.svg?branch=master)](https://travis-ci.org/codepr/lingua)
+
+# Lingua::It::Readability
+
+Inpired by Lingua::EN::Readability and his perl original version Lingua::EN::Fathom, a gem focused on readability of Italian language texts.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'lingua-it-readability'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install lingua-it-readability
+
+## Usage
+
+TODO: Write usage instructions here
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
+
+To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+
+## Changelog
+
+See the [CHANGELOG](CHANGELOG.md) file.
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/codepr/lingua-it-readability.
+
+
+## License
+
+The gem is available as open source under the terms of the [MIT License](http://opensource.org/licenses/MIT).

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 "lingua/it/readability"
+
+# 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

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/lib/lingua/it/paragraph.rb

@@ -0,0 +1,13 @@
+module Lingua
+  module IT
+    module Paragraph
+
+      # Split the sample in paragraph. A paragraph is defined by
+      # a sequence of sentences followed by one or more \n, \r\t
+      # if in Windows env.
+      def self.paragraphs(text)
+        text.dup.split(/(?:\n[\r\t ]*)+/).collect { |p| p.strip }
+      end
+    end
+  end
+end

data/lib/lingua/it/readability/version.rb

@@ -0,0 +1,7 @@
+module Lingua
+  module It
+    module Readability
+      VERSION = "1.0.0"
+    end
+  end
+end

data/lib/lingua/it/readability.rb

@@ -0,0 +1,140 @@
+# coding: utf-8
+prefix = File.dirname(__FILE__) + "/"
+$LOAD_PATH.unshift prefix
+
+Dir.glob(prefix + "**/*.rb").each do |f|
+  require File.expand_path(f)
+end
+
+module Lingua
+  module IT
+    class Readability
+      attr_reader :text
+      attr_reader :type
+      attr_reader :paragraphs
+      attr_reader :sentences
+      attr_reader :words
+      attr_reader :frequencies
+
+      # Initialize the sample with +text+
+      def initialize(text, type = 'standard')
+        @text                = text.dup
+        @type                = type
+        @paragraphs          = Lingua::IT::Paragraph.paragraphs(self.text)
+        @sentences           = Lingua::IT::Sentence.sentences(self.text, self.type)
+        @words               = []
+        @frequencies         = {}
+        @frequencies.default = 0
+        @syllables           = Lingua::IT::Syllable.syllables(self.text)
+        count_words
+      end
+
+      # The number of paragraphs in the sample. A paragraph is defined as a
+      # newline followed by one or more empty or whitespace-only lines.
+      def num_paragraphs
+        paragraphs.length
+      end
+
+      # The number of sentences in the sample. The meaning of a "sentence" is
+      # defined by Lingua::IT::Sentence.
+      def num_sentences
+        @sentences.length
+      end
+
+      # The number of characeters in the sample. A character is defined as a
+      # single letter, not taking account of punctuation and spaces
+      def num_chars
+        @text.dup.gsub(/[[:punct:]][[:space:]]/, '').scan(/[a-zA-Z0-9_Èàòèéìù\(\)\[\]\{\}]/i).length
+      end
+      alias :num_characters :num_chars
+
+      # The number of words in the sample. A word is defined as a sequence of
+      # characters, not taking account of punctuation and spaces, see private
+      # method +count_words+ for additional info about a word definition
+      def num_words
+        words.length
+      end
+
+      # The total number of syllables in the text sample. Syllables are defined
+      # in Lingua::IT::Syllable.
+      def num_syllables
+        @syllables.length
+      end
+
+      # The number of different unique words used in the text sample.
+      def num_unique_words
+        @frequencies.keys.length
+      end
+
+      # An array containing each unique word used in the text sample.
+      def unique_words
+        @frequencies.keys
+      end
+
+      # The number of occurences of the word +word+ in the text sample.
+      def occurrences(word)
+        @frequencies[word]
+      end
+
+      # The average number of words per sentence.
+      def words_per_sentence
+        ((words.length.to_f / sentences.length.to_f) * 100).round / 100.0
+      end
+
+      # The average number of syllables per word. The syllable count is
+      # performed by Lingua::IT::Syllable, and so may not be completely
+      # accurate
+      def syllables_per_word
+        ((@syllables.length.to_f / words.length.to_f) * 100).round / 100.0
+      end
+
+      # Gulpease index of readability expressly calibrated to suit italian
+      # text samples.
+      # An index < 40 means a low readable sample, between 40 and 60 it
+      # represents a medium readable sample, over 60 a well written sample
+      # easily readable by an under 16 person.
+      def gulpease
+        89 + (((300 * num_sentences) - (10 * num_chars)) / num_words)
+      end
+
+      # Flesch index of readability expressly calibrated to suit italian
+      # text samples, derived from U.S. Flesch index.
+      # An index < 40 means a low readable sample, between 40 and 60 it
+      # represents a medium readable sample, over 60 a well written sample
+      # easily readable by an under 16 person.
+      def flesch
+        ((206.0 - (65.0 * (num_syllables.to_f / num_words.to_f)) -
+          ((num_words.to_f / num_sentences.to_f))) * 100).round / 100.0
+      end
+
+      # A nicely formatted report on the sample, showing most the useful
+      # stats
+      def report
+        sprintf "Number of paragraphs           %d \n" <<
+                "Number of sentences            %d \n" <<
+                "Number of words                %d \n" <<
+                "Number of characters           %d \n\n" <<
+                "Average words per sentence     %.2f \n" <<
+                "Average syllables per word     %.2f \n\n" <<
+                "Gulpease score                 %2.2f \n" <<
+                "Flesch score                   %2.2f \n",
+                num_paragraphs, num_sentences, num_words, num_characters,
+                words_per_sentence, syllables_per_word, gulpease,
+                flesch
+      end
+
+      private
+
+      # Nnumber of words in the sample. A words is represented by a sequence
+      # of single characters exlucding punctuation, except for all kind of
+      # parenthesis like () [] and {}. Being calibrated for italian language
+      # it takes in account even accented characters.
+      def count_words
+        @words = @text.dup.gsub(/[^\wÈèòàù\(\)\[\]\{\}]/i, ' ').strip.split(/\s+/)
+        @words.each do |word|
+          @frequencies[word] += 1
+        end
+      end
+    end
+  end
+end

data/lib/lingua/it/sentence.rb

@@ -0,0 +1,64 @@
+module Lingua
+  module IT
+    class Sentence
+
+      # Takes Italian text and split it into sentences, respecting
+      # generale abbreviations. It grant permission of adding more
+      # abbreviations to take in account during the process.
+      class << self
+        attr_reader :abbreviations
+        attr_reader :abbr_regex
+      end
+
+      # Common abbreviations
+      TITLES = %w(sig sigg dott preg prof mr jr amn avv co stim dr egr geom ing mons on rag rev soc spett card ill gent cav) unless defined?(TITLES)
+      MISC   = %w(p v femm dim ecc etc corr cc bcc all es fatt g gg id int lett ogg pag pagg cap pp tel ind v n num min sec ms abbr agg art aus) unless defined?(MISC)
+      MONTHS = %w(gen feb mar apr mag giu lug ago set sett ott nov dic) unless defined?(MONTHS)
+      DAYS   = %w(lun mar mer gio ven sab dom) unless defined?(DAYS)
+
+      # Text types
+      TYPES = {
+        'standard'   => /["']?[A-Z][^.?!]+((?![.?!]['"]?\s["']?[A-Z][^.?!]).)+[.?!'"]+/,
+        'scientific' => /["']?[A-Z][^.;:?!]+((?![.;:?!]['"]?\s["']?[A-Z][^.;:?!]).)+[.;:?!'"]+/
+      }
+      TYPES.default_proc = proc { |hash, key| hash[key] = /["']?[A-Z][^.?!]+((?![.?!]['"]?\s["']?[A-Z][^.?!]).)+[.?!'"]+/ }
+
+      # Split up in sentences, use 0002 as a temporary end mark for
+      # the abbreviations found, even if the regex should be enough
+      # to recognize real stop point from abbreviations ones.
+      # A sentences should definetly end marked only by a . or a ?
+      # or a !
+      def self.sentences(text, type = 'standard')
+        txt = text.dup
+        txt.gsub!(/\b(#{@abbr_regex})(\.)\B/i, '\10002')
+        txt.gsub!(/#{TYPES[type]}/, '\2\001')
+        txt.gsub!(/\b(#{@abbr_regex})(0002)/i, '\1.')
+        txt.split(/01/).map { |sentence| sentence.strip }
+      end
+
+      # Add customized abbreviations to standard set
+      def self.abbreviation(*abbreviations)
+        @abbreviations += abbreviations
+        @abbreviations.uniq!
+        set_abbr_regex!
+        @abbreviations
+      end
+
+      private
+      # Utility method, chain up all abbreviations constants arrays
+      def self.initialize_abbreviations!
+        @abbreviations = TITLES + MISC + MONTHS + DAYS
+        set_abbr_regex!
+      end
+
+      # Utility method, join all elements of the abbreviations arrays
+      # using | as separator, making suitable for a regex.
+      def self.set_abbr_regex!
+        @abbr_regex = "#{@abbreviations.join('|')}"
+      end
+
+      initialize_abbreviations!
+
+    end
+  end
+end

data/lib/lingua/it/syllable.rb

@@ -0,0 +1,46 @@
+# coding: utf-8
+module Lingua
+  module IT
+    module Syllable
+
+      # This module is inspired by the Perl Lingua::IT::Hyphenation module.
+      # However, it uses a different (though not larger) set of patterns to
+      # compensate for the 'special cases' which arise out of Italian's
+      # irregular orthography. A number of extra patterns (particularly for
+      # derived word forms) means that this module is somewhat more accurate
+      # than the Perl original.
+
+      V = "[aeiouàèéìòù]"
+      C = "[b-df-hj-np-tv-z]"
+      S = "iut"
+      X = "fi|aci"
+      Y = "#{C}e"
+      Z = "i[aeo]"
+
+      def self.syllables(text)
+        words = text.dup.split(/[^a-zA-Zàèéìòù'0-9]+/)
+        hyphenation = ""
+        words.each do |word|
+          word.gsub!(/(#{V})(#{S})/i, '\1=iu=t')
+          word.gsub!(/(#{V})(#{Z})/i, '\1=\2')
+          word.gsub!(/(#{X})(#{V})/i, '\1=\2')
+          word.gsub!(/(#{Y})(#{V})/i, '\1=\2')
+          word.gsub!(/(#{V})([bcfgptv][lr])/i, '\1=\2')
+          word.gsub!(/(#{V})([cg]h)/i, '\1=\2')
+          word.gsub!(/(#{V})(gn)/i, '\1=\2')
+          word.gsub!(/(#{C})\1/i, '\1=\1')
+          word.gsub!(/(s#{C})/i, '=\1')
+          1 while word.gsub!(/(#{V}*#{C}+#{V}+)(#{C}#{V})/i, '\1=\2')
+          1 while word.gsub!(/(#{V}*#{C}+#{V}+#{C})(#{C})/i, '\1=\2')
+          word.gsub!(/^(#{V}+#{C})(#{C})/i, '\1=\2')
+          word.gsub!(/^(#{V}+)(#{C}#{V})/i, '\1=\2')
+          word.sub!(/^=/, '')
+          word.sub!(/=$/, '')
+          word.gsub!(/=+/,'=');
+          hyphenation += "#{word}="
+        end
+        hyphenation.split('=')
+      end
+    end
+  end
+end

data/lingua-it-readability.gemspec

@@ -0,0 +1,25 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'lingua/it/readability/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "lingua-it-readability"
+  spec.version       = Lingua::It::Readability::VERSION
+  spec.authors       = ["Andrea Giacomo Baldan"]
+  spec.email         = ["a.g.baldan@gmail.com"]
+
+  spec.summary       = %q{Text readability indexes and stats calibrated on Italian language.}
+  spec.description   = %q{Text readability indexes and stats calibrated on Italian language. Inspired by Lingua::EN::Readability and the original perl module Lingua::EN::Fathom. Gulpease and Flesch for italian text is calculated.}
+  spec.homepage      = "https://github.com/codepr/lingua-it-readability"
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
+  spec.bindir        = "exe"
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "bundler", "~> 1.11"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "rspec", "~> 3.0"
+end

metadata

@@ -0,0 +1,104 @@
+--- !ruby/object:Gem::Specification
+name: lingua-it-readability
+version: !ruby/object:Gem::Version
+  version: 1.0.0
+platform: ruby
+authors:
+- Andrea Giacomo Baldan
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2016-02-08 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.11'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.11'
+- !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: Text readability indexes and stats calibrated on Italian language. Inspired
+  by Lingua::EN::Readability and the original perl module Lingua::EN::Fathom. Gulpease
+  and Flesch for italian text is calculated.
+email:
+- a.g.baldan@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- ".travis.yml"
+- CHANGELOG.md
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- lib/lingua/it/paragraph.rb
+- lib/lingua/it/readability.rb
+- lib/lingua/it/readability/version.rb
+- lib/lingua/it/sentence.rb
+- lib/lingua/it/syllable.rb
+- lingua-it-readability.gemspec
+homepage: https://github.com/codepr/lingua-it-readability
+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: 2.5.2
+signing_key: 
+specification_version: 4
+summary: Text readability indexes and stats calibrated on Italian language.
+test_files: []