textation 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: a0fe6300ad5c82008bcfecfc328687b9033f8d2782f6065fe39a1c57d57b25ab
+  data.tar.gz: 87ea79f2420f77ecab5139ac777cc90a6052eb3c1d526c9067559f9bc55cb11d
+SHA512:
+  metadata.gz: c4e62a7aa9b8268c38201d25119cb4d70aa594af8bde739d6ab0e87b5bde6d37bd163a6a4813e2b0711b3ce1de677b1c5604816a00bbd0224e89079ac96ba4c8
+  data.tar.gz: e60d6cfccd32d7e91a679acc6c66728b53f46a7bf52174007e115f75c7c36deb28a30927b9a7cce0d45d2eef7b106fcd96e3854d90bc1d1e4bcf9b32c0970e15

data/.gitignore

@@ -0,0 +1,10 @@
+/.bundle/
+/.yardoc
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+Gemfile.lock
+pkg/*

data/.travis.yml

@@ -0,0 +1,6 @@
+---
+language: ruby
+cache: bundler
+rvm:
+  - 2.7.1
+before_install: gem install bundler -v 2.1.4

data/Gemfile

@@ -0,0 +1,7 @@
+source "https://rubygems.org"
+
+# Specify your gem's dependencies in textation.gemspec
+gemspec
+
+gem "rake", "~> 12.0"
+gem "rspec", "~> 3.2"

data/LICENSE.txt

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2020 iva mudronja
+
+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 +1,91 @@
+# Textation
+
+Simple text analysis with Ruby
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'textation'
+```
+
+And then execute:
+
+    $ bundle install
+
+Or install it yourself as:
+
+    $ gem install textation
+
+## Usage
+
+### Create an instance for usage:
+
+analyzer = Text.new
+
+All methods work for .txt file and for strings
+
+Analyze .txt file || string:
+
+analyzer.analyze('some_text.txt')
+
+will work same as for string👇
+
+analyzer.analyze('I love Ruby! And Ruby loves me!')
+
+{ character_count: 31,
+  character_count_excluding_spaces: 25,
+  letter_count: 23,
+  line_count: 1,
+  word_count: 7,
+  sentence_count: 2,
+  paragraph_count: 1,
+  lines_per_paragraph: "1",
+  syllables_per_line: "9",
+  average_words_per_sentence: 3.5,
+  average_sentences_per_paragraph: 2.0,
+  useful_words:  "love, ruby, loves",
+  percentage_of_useful_words: 42.86,
+  unique_words:  "i, love, ruby, and, loves, me",
+  percentage_of_unique_words: 85.71,
+  occurences_of_words: "ruby: 2, i: 1, love: 1, and: 1, loves: 1, me: 1",
+  percentage_of_words: "ruby: 28.57, i: 14.29, love: 14.29, and: 14.29, loves: 14.29, me: 14.29"
+}
+
+
+Get first 3 top words including stop words (pass .txt file || string):
+
+analyzer.top_words_all('data/test_source_text.txt')
+#=> 'someone, must, have'
+
+You can pass number:
+
+analyzer.top_words_all('data/test_source_text.txt', 1)
+#=> 'someone'
+
+
+Get first 3 top words excluding stop words (pass .txt file || string):
+
+analyzer.top_words_no_stop_words('data/test_source_text.txt')
+#=> 'slandered, josef, morning'
+
+You can pass number:
+
+analyzer.top_words_no_stop_words('data/test_source_text.txt', 4)
+#=> 'slandered, josef, morning, wrong'
+
+
+Get occurence of word (pass .txt file || string):
+
+analyzer.occurence_of_word('data/test_source_text.txt', 'morning')
+#=> 5
+
+Get percentage of word (pass .txt file || string):
+
+analyzer.percentage_of_word('data/test_source_text.txt', 'wrong')
+#=> 5.56
+
+## License
+
+The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).

data/Rakefile

@@ -0,0 +1,2 @@
+require "bundler/gem_tasks"
+task :default => :spec

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "textation"
+
+# 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/data/test_source_text.txt

@@ -0,0 +1,6 @@
+Someone must have slandered Josef K., for one morning, without having done anything truly wrong, he was arrested.
+Someone must have slandered Josef K., for one morning, without having done anything truly wrong, he was arrested!
+Someone must have slandered Josef K., for one morning, without having done anything truly wrong, he was arrested?
+
+Someone must have slandered Josef K., for one morning, without having done anything truly wrong, he was arrested?!
+Someone must have slandered Josef K., for one morning, without having done anything truly wrong, he was arrested...

data/lib/textation.rb

@@ -0,0 +1,8 @@
+require "textation/version"
+require "textation/text"
+
+module Textation
+  class Error < StandardError; end
+  # Your code goes here...
+end
+

data/lib/textation/text.rb

@@ -0,0 +1,97 @@
+require "textation/version"
+
+STOP_WORDS = ["a", "a's", "able", "about", "above", "according", "accordingly", "across", "actually", "after", "afterwards", "again", "against", "ain't", "all", "allow", "allows", "almost", "alone", "along", "already", "also", "although", "always", "am", "among", "amongst", "an", "and", "another", "any", "anybody", "anyhow", "anyone", "anything", "anyway", "anyways", "anywhere", "apart", "appear", "appreciate", "appropriate", "are", "aren't", "around", "as", "aside", "ask", "asking", "associated", "at", "available", "away", "awfully", "b", "be", "became", "because", "become", "becomes", "becoming", "been", "before", "beforehand", "behind", "being", "believe", "below", "beside", "besides", "best", "better", "between", "beyond", "both", "brief", "but", "by", "c", "c'mon", "c's", "came", "can", "can't", "cannot", "cant", "cause", "causes", "certain", "certainly", "changes", "clearly", "co", "com", "come", "comes", "concerning", "consequently", "consider", "considering", "contain", "containing", "contains", "corresponding", "could", "couldn't", "course", "currently", "d", "definitely", "described", "despite", "did", "didn't", "different", "do", "does", "doesn't", "doing", "don't", "done", "down", "downwards", "during", "e", "each", "edu", "eg", "eight", "either", "else", "elsewhere", "enough", "entirely", "especially", "et", "etc", "even", "ever", "every", "everybody", "everyone", "everything", "everywhere", "ex", "exactly", "example", "except", "f", "far", "few", "fifth", "first", "five", "followed", "following", "follows", "for", "former", "formerly", "forth", "four", "from", "further", "furthermore", "g", "get", "gets", "getting", "given", "gives", "go", "goes", "going", "gone", "got", "gotten", "greetings", "h", "had", "hadn't", "happens", "hardly", "has", "hasn't", "have", "haven't", "having", "he", "he's", "hello", "help", "hence", "her", "here", "here's", "hereafter", "hereby", "herein", "hereupon", "hers", "herself", "hi", "him", "himself", "his", "hither", "hopefully", "how", "howbeit", "however", "i", "i'd", "i'll", "i'm", "i've", "ie", "if", "ignored", "immediate", "in", "inasmuch", "inc", "indeed", "indicate", "indicated", "indicates", "inner", "insofar", "instead", "into", "inward", "is", "isn't", "it", "it'd", "it'll", "it's", "its", "itself", "j", "just", "k", "keep", "keeps", "kept", "know", "knows", "known", "l", "last", "lately", "later", "latter", "latterly", "least", "less", "lest", "let", "let's", "like", "liked", "likely", "little", "look", "looking", "looks", "ltd", "m", "mainly", "many", "may", "maybe", "me", "mean", "meanwhile", "merely", "might", "more", "moreover", "most", "mostly", "much", "must", "my", "myself", "n", "name", "namely", "nd", "near", "nearly", "necessary", "need", "needs", "neither", "never", "nevertheless", "new", "next", "nine", "no", "nobody", "non", "none", "noone", "nor", "normally", "not", "nothing", "novel", "now", "nowhere", "o", "obviously", "of", "off", "often", "oh", "ok", "okay", "old", "on", "once", "one", "ones", "only", "onto", "or", "other", "others", "otherwise", "ought", "our", "ours", "ourselves", "out", "outside", "over", "overall", "own", "p", "particular", "particularly", "per", "perhaps", "placed", "please", "plus", "possible", "presumably", "probably", "provides", "q", "que", "quite", "qv", "r", "rather", "rd", "re", "really", "reasonably", "regarding", "regardless", "regards", "relatively", "respectively", "right", "s", "said", "same", "saw", "say", "saying", "says", "second", "secondly", "see", "seeing", "seem", "seemed", "seeming", "seems", "seen", "self", "selves", "sensible", "sent", "serious", "seriously", "seven", "several", "shall", "she", "should", "shouldn't", "since", "six", "so", "some", "somebody", "somehow", "someone", "something", "sometime", "sometimes", "somewhat", "somewhere", "soon", "sorry", "specified", "specify", "specifying", "still", "sub", "such", "sup", "sure", "t", "t's", "take", "taken", "tell", "tends", "th", "than", "thank", "thanks", "thanx", "that", "that's", "thats", "the", "their", "theirs", "them", "themselves", "then", "thence", "there", "there's", "thereafter", "thereby", "therefore", "therein", "theres", "thereupon", "these", "they", "they'd", "they'll", "they're", "they've", "think", "third", "this", "thorough", "thoroughly", "those", "though", "three", "through", "throughout", "thru", "thus", "to", "together", "too", "took", "toward", "towards", "tried", "tries", "truly", "try", "trying", "twice", "two", "u", "un", "under", "unfortunately", "unless", "unlikely", "until", "unto", "up", "upon", "us", "use", "used", "useful", "uses", "using", "usually", "uucp", "v", "value", "various", "very", "via", "viz", "vs", "w", "want", "wants", "was", "wasn't", "way", "we", "we'd", "we'll", "we're", "we've", "welcome", "well", "went", "were", "weren't", "what", "what's", "whatever", "when", "whence", "whenever", "where", "where's", "whereafter", "whereas", "whereby", "wherein", "whereupon", "wherever", "whether", "which", "while", "whither", "who", "who's", "whoever", "whole", "whom", "whose", "why", "will", "willing", "wish", "with", "within", "without", "won't", "wonder", "would", "wouldn't", "x", "y", "yes", "yet", "you", "you'd", "you'll", "you're", "you've", "your", "yours", "yourself", "yourselves", "z", "zero"]
+
+
+class Text
+  def analyze(text)
+    text = check_input(text)
+    result = {}
+    result[:character_count] = text.length
+    result[:character_count_excluding_spaces] = text.gsub(/\s/, '').length
+    result[:letter_count] = text.gsub(/[^[:alpha:]]/, '').length
+    result[:line_count] = text.split(/\n/).length
+    result[:word_count] = text.split(/\W+/).delete_if(&:empty?).length
+    result[:sentence_count] = text.split(/[^[:alpha:]{1}\.]\.{1,3}\s?\r?\n?|\?+|!+|\?!+|!\?+/).length
+    result[:paragraph_count] = text.split(/\n\n/).length
+    result[:lines_per_paragraph] = text.split(/\n\n/).map { |p| p.split(/\n/).length }.join(', ')
+    result[:syllables_per_line] = syllables_per_line(text).join(', ')
+    result[:average_words_per_sentence] = (result[:word_count].to_f / result[:sentence_count]).round(2)
+    result[:average_sentences_per_paragraph] = (result[:sentence_count].to_f / result[:paragraph_count]).round(2)
+    result[:useful_words] = useful_words(text).join(', ')
+    result[:percentage_of_useful_words] = ((result[:useful_words].split(/\W+/).length.to_f / result[:word_count]) * 100).round(2)
+    result[:occurences_of_words] = occurences_of_words(text).to_a.map {|el| "#{el[0]}: #{el[1]}" }.join(', ')
+    result[:percentage_of_words] = percentage_of_words(text).to_a.map {|el| "#{el[0]}: #{el[1]}" }.join(', ')
+    result[:unique_words] = text.downcase.split(/\W+/).select { |w| w.length >= 1 }.uniq.join(', ') # result[:occurences_of_words].select { |_k, v| v == 1 }.keys
+    result[:percentage_of_unique_words] = ((result[:unique_words].split(/\W+/).length.to_f / result[:word_count]) * 100).round(2)
+    result
+  end
+
+  def useful_words(text)
+    text = check_input(text)
+    text.downcase
+        .split(/\W+/)
+        .delete_if { |w| STOP_WORDS.include?(w) }
+        .select { |w| w.length >= 1 }
+        .uniq
+  end
+
+  def top_words_no_stop_words(text, num = 3)
+    text = useful_words(text)
+    top_words(text, num)
+  end
+
+  def top_words_all(text, num = 3)
+    text = (check_input(text)).downcase.split(/\W+/)
+    top_words(text, num)
+  end
+
+  def top_words(text, num)
+    text.group_by(&:itself)
+        .transform_values(&:count)
+        .sort_by { |_k, v| -v }
+        .first(num)
+        .map(&:first).join(', ')
+  end
+
+  def occurences_of_words(text)
+    text = check_input(text)
+    text.downcase
+        .split(/\W+/)
+        .delete_if(&:empty?)
+        .group_by(&:itself)
+        .transform_values(&:count)
+        .sort_by { |_k, v| -v }
+        .to_h
+  end
+
+  def occurence_of_word(text, word)
+    occurences_of_words(text)[word.downcase]
+  end
+
+  def percentage_of_words(text)
+    occurences = occurences_of_words(text)
+    len = check_input(text).split(/\W+/).length
+    occurences.transform_values { |v| ((v.to_f / len) * 100).round(2) }
+  end
+
+  def percentage_of_word(text, word)
+    percentage_of_words(text)[word.downcase]
+  end
+
+  def syllables_per_line(text)
+    text.downcase.split(/\n/).map do |line|
+      line.split(/\W+/).map do |word|
+        if word.split(/[^aeiouy]+/).delete_if(&:empty?).length > 1
+          word.gsub(/e$|es$|ed$/, "").split(/[^aeiouy]+/).delete_if(&:empty?).length
+        else
+          word.split(/[^aeiouy]+/).delete_if(&:empty?).length
+        end
+      end
+    end.map(&:sum)
+  end
+
+  def check_input(text)
+    text.match?(/.txt$/) ? File.open(text, 'r').read : text
+  end
+end

data/lib/textation/version.rb

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

data/textation.gemspec

@@ -0,0 +1,30 @@
+require_relative 'lib/textation/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "textation"
+  spec.version       = Textation::VERSION
+  spec.authors       = ["iva"]
+  spec.email         = ["iva.pilizota@gmail.com"]
+
+  spec.summary       = "Simple text analysis with Ruby" #%q{TODO: Write a short summary, because RubyGems requires one.}
+ # spec.description   = %q{TODO: Write a longer description or delete this line.}
+  spec.homepage      = "https://github.com/ivaMm/textation" #{}"TODO: Put your gem's website or public repo URL here."
+  spec.license       = "MIT"
+  spec.required_ruby_version = Gem::Requirement.new(">= 2.3.0")
+
+  #spec.metadata["allowed_push_host"] = "TODO: Set to 'http://mygemserver.com'"
+
+  spec.metadata["homepage_uri"] = spec.homepage
+  spec.metadata["source_code_uri"] = "https://github.com/ivaMm/textation" # "TODO: Put your gem's public repo URL here."
+  # spec.metadata["changelog_uri"] = "TODO: Put your gem's CHANGELOG.md URL here."
+
+  # Specify which files should be added to the gem when it is released.
+  # The `git ls-files -z` loads the files in the RubyGem that have been added into git.
+  spec.files         = Dir.chdir(File.expand_path('..', __FILE__)) do
+    `git ls-files -z`.split("\x0").reject { |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 "rspec", "~> 3.2"
+end

metadata

@@ -0,0 +1,73 @@
+--- !ruby/object:Gem::Specification
+name: textation
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- iva
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2020-12-08 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.2'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.2'
+description: 
+email:
+- iva.pilizota@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".travis.yml"
+- Gemfile
+- Gemfile.lock
+- LICENSE.txt
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- data/test_source_text.txt
+- lib/textation.rb
+- lib/textation/text.rb
+- lib/textation/version.rb
+- textation.gemspec
+homepage: https://github.com/ivaMm/textation
+licenses:
+- MIT
+metadata:
+  homepage_uri: https://github.com/ivaMm/textation
+  source_code_uri: https://github.com/ivaMm/textation
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 2.3.0
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.1.2
+signing_key: 
+specification_version: 4
+summary: Simple text analysis with Ruby
+test_files: []