extract_artist_track 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 2de6a47213e726e3b252c3462a9b460965ad40af
+  data.tar.gz: 8b2ec412d56d01bd71ed8e73ed84080445e48894
+SHA512:
+  metadata.gz: 695b24b0ce207a1a612d3b35f0262ca155f7e45064b5fa929f23ff97050510460b9c8444ff546749243f38b3854ae438ba91ba6382926ad624d2a19a5bf18407
+  data.tar.gz: 91977dc18cffcf2c589313d7ce49108ac6258629e3e3e08040b216ae3ddcfa8bcf82d19bce91267db6d7859f388027549e3c80a5f283918d3ebaed7d7abd75f8

data/.gitignore

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

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 1.12.5

data/Gemfile

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

data/README.md

@@ -0,0 +1,38 @@
+# ExtractArtistTrack [![CircleCI](https://circleci.com/gh/6/extract_artist_track.svg?style=svg)](https://circleci.com/gh/6/extract_artist_track)
+
+Ruby port of [get-artist-title](https://github.com/goto-bus-stop/get-artist-title) for getting the song artist and track from a freeform string, e.g. a YouTube video title.
+
+```ruby
+parser = ExtractArtistTrack::Parser.new(title: "Madeon - The City (Official Video).mp4")
+parser.artist
+=> "Madeon"
+parser.track
+=> "The City"
+
+parser = ExtractArtistTrack::Parser.new(title: "[MV] Perfume「ねぇ」")
+parser.artist
+=> "Perfume"
+parser.track
+=> "ねぇ"
+```
+
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'extract_artist_track'
+```
+
+And then execute:
+
+    $ bundle
+
+
+## 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).
+

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 "extract_artist_track"
+
+# 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/circle.yml

@@ -0,0 +1,3 @@
+machine:
+  ruby:
+    version: 2.3.0

data/extract_artist_track.gemspec

@@ -0,0 +1,26 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'extract_artist_track/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "extract_artist_track"
+  spec.version       = ExtractArtistTrack::VERSION
+  spec.authors       = ["Peter Graham"]
+
+  spec.summary       = %q{Extract artist and track from YouTube video title.}
+  spec.description   = %q{Extract artist and track from a freeform YouTube video title.}
+  spec.homepage      = "https://github.com/6/extract_artist_track"
+
+  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_dependency "mime-types", "3.1"
+  spec.add_development_dependency "bundler", "~> 1.12"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "rspec", "~> 3.0"
+  spec.add_development_dependency "rspec-its", "~> 1.2"
+  spec.add_development_dependency "rspec_junit_formatter", "0.2.3"
+end

data/lib/extract_artist_track.rb

@@ -0,0 +1,38 @@
+require "ostruct"
+require "mime/types/full"
+
+require "extract_artist_track/version"
+require "extract_artist_track/splitter"
+require "extract_artist_track/cleaner"
+require "extract_artist_track/parser"
+
+module ExtractArtistTrack
+  QUOTES = [
+    '“”',
+    '""',
+    "''",
+    '『』',
+    '「」',
+    '【】',
+    '‹›' ,
+    '«»',
+  ]
+
+  SEPARATORS = [
+    ' -- ',
+    '--',
+    ' - ',
+    ' – ',
+    ' — ',
+    ' _ ',
+    '-',
+    '–',
+    '—',
+    ':',
+    '|',
+    '///',
+    ' / ',
+    '_',
+    '/',
+  ]
+end

data/lib/extract_artist_track/cleaner.rb

@@ -0,0 +1,73 @@
+module ExtractArtistTrack
+  class Cleaner
+    def self.clean_title(title)
+      return if !title.is_a?(String)
+      title = clean_file_extension(title)
+      clean_fluff(title)
+    end
+
+    def self.clean_artist(artist)
+      artist = clean_fluff(artist.strip)
+        .gsub(/\s*[0-1][0-9][0-1][0-9][0-3][0-9]\s*/, '') # date formats ex. 130624
+        .gsub(/^[\/\s,:;~\-–_\s"]+/, '') # trim starting white chars and dash
+        .gsub(/[\/\s,:;~\-–_\s"]+$/, '') # trim trailing white chars and dash
+      clean_quotes(artist)
+    end
+
+    def self.clean_track(track)
+      track = clean_fluff(track.strip)
+        .gsub(/\s*\*+\s?\S+\s?\*+$/, '') # **NEW**
+        .gsub(/\s*video\s*clip/i, '') # video clip
+        .gsub(/\s+\(?live\)?$/i, '') # live
+        .gsub(/\(\s*\)/, '') # Leftovers after e.g. (official video)
+        .gsub(/\[\s*\]/, '') # Leftovers after e.g. [1080p]
+        .gsub(/【\s*】/, '') # Leftovers after e.g. 【MV】
+        .gsub(/^(|.*\s)"(.*)"(\s.*|)$/, '\2') # Artist - The new "Track title" featuring someone
+        .gsub(/^(|.*\s)'(.*)'(\s.*|)$/, '\2') # 'Track title'
+        .gsub(/^[\/\s,:;~\-–_\s"]+/, '') # trim starting white chars and dash
+        .gsub(/[\/\s,:;~\-–_\s"]+$/, '') # trim trailing white chars and dash
+      clean_quotes(track)
+    end
+
+  private
+
+    def self.clean_file_extension(string)
+      file_extensions = MIME::Types[/^(audio|video)/].map {|mime| mime.extensions }.flatten.uniq
+      file_extensions_regex = %r{\.(#{file_extensions.join("|")})$}i
+      string.gsub(file_extensions_regex, '')
+    end
+
+    # Remove various versions of "MV" and "PV" markers
+    def self.clean_mvpv(string)
+      string
+        .gsub(/\s*\[\s*([PM]\/?V)\s*\]/, '') # [MV] or [M/V]
+        .gsub(/\s*\(\s*([PM]\/?V)\s*\)/, '') # (MV) or (M/V)
+        .gsub(/\s*【\s*([PM]\/?V)\s*】/, '') # 【MV】 or 【M/V】
+        .gsub(/[\s\-–_]+([PM]\/?V)\s*/, '') # MV or M/V at the end
+        .gsub(/([PM]\/?V)[\s\-–_]+/, '') # MV or M/V at the start
+    end
+
+    def self.clean_fluff(string)
+      clean_mvpv(string)
+        .gsub(/\s*\[[^\]]+\]$/, '') # [whatever] at the end
+        .gsub(/^\s*\[[^\]]+\]\s*/, '') # [whatever] at the start
+        .gsub(/\s*\([^\)]*\bver(\.|sion)?\s*\)$/i, '') # (whatever version)
+        .gsub(/\s*[a-z]*\s*\bver(\.|sion)?$/i, '') # ver. and 1 word before (no parens)
+        .gsub(/\s*(of+icial\s*)?(music\s*)?video/i, '') # (official)? (music)? video
+        .gsub(/\s*(ALBUM TRACK\s*)?(album track\s*)/i, '') # (ALBUM TRACK)
+        .gsub(/\s*\(\s*of+icial\s*\)/i, '') # (official)
+        .gsub(/\s*\(\s*[0-9]{4}\s*\)/i, '') # (1999)
+        .gsub(/\s+\(\s*(HD|HQ)\s*\)$/, '') # HD (HQ)
+        .gsub(/[\s\-–_]+(HD|HQ)\s*$/, '') # HD (HQ)
+        .gsub(/(\s*[-~_\/]\s*)?\b(with\s+)?lyrics\s*/i, '')
+        .gsub(/\(\s*(with\s+)?lyrics\s*\)\s*/i, '')
+    end
+
+    def self.clean_quotes(string)
+      regexes = QUOTES.map { |set| %r{^#{set[0]}(.*?)#{set[1]}\s*} }
+      regexes.reduce(string) do |str, regex|
+        str.gsub(regex, '\1 ')
+      end.strip
+    end
+  end
+end

data/lib/extract_artist_track/parser.rb

@@ -0,0 +1,29 @@
+module ExtractArtistTrack
+  class Parser
+    def initialize(title:)
+      @title = Cleaner.clean_title(title)
+    end
+
+    def artist
+      return @artist if defined?(@artist)
+      return @artist = nil if invalid? || splitter.artist.nil?
+      @artist = Cleaner.clean_artist(splitter.artist)
+    end
+
+    def track
+      return @track if defined?(@track)
+      return @track = nil if invalid? || splitter.track.nil?
+      @track = Cleaner.clean_track(splitter.track)
+    end
+
+  private
+
+    def invalid?
+      @title.nil? || @title.empty?
+    end
+
+    def splitter
+      @splitter ||= Splitter.new(title: @title)
+    end
+  end
+end

data/lib/extract_artist_track/splitter.rb

@@ -0,0 +1,41 @@
+module ExtractArtistTrack
+  class Splitter
+    attr_reader :title, :artist, :track
+    def initialize(title:)
+      @title = title
+      return if title.nil? || title.empty?
+      split = split_by_separator
+      split ||= split_by_quotes
+      @artist = split&.artist
+      @track = split&.track
+    end
+
+    def split_by_separator
+      SEPARATORS.each do |separator|
+        index = title.index(separator)
+        if index
+          return OpenStruct.new({
+            artist: title[0..index-1],
+            track: title[index..-1],
+          })
+        end
+      end
+      nil
+    end
+
+    def split_by_quotes
+      regexes = QUOTES.map { |set| %r{#{set[0]}(.*?)#{set[1]}} }
+      regexes.each do |regex|
+        str = title.gsub(regex) { |match| " #{match} " }
+        index = regex =~ str
+        if index
+          return OpenStruct.new({
+            artist: str[0..index-1],
+            track: str[index..-1],
+          })
+        end
+      end
+      nil
+    end
+  end
+end

data/lib/extract_artist_track/version.rb

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

metadata

@@ -0,0 +1,141 @@
+--- !ruby/object:Gem::Specification
+name: extract_artist_track
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Peter Graham
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2016-09-30 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: mime-types
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '='
+      - !ruby/object:Gem::Version
+        version: '3.1'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '='
+      - !ruby/object:Gem::Version
+        version: '3.1'
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.12'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.12'
+- !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'
+- !ruby/object:Gem::Dependency
+  name: rspec-its
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.2'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.2'
+- !ruby/object:Gem::Dependency
+  name: rspec_junit_formatter
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '='
+      - !ruby/object:Gem::Version
+        version: 0.2.3
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '='
+      - !ruby/object:Gem::Version
+        version: 0.2.3
+description: Extract artist and track from a freeform YouTube video title.
+email: 
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- ".travis.yml"
+- Gemfile
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- circle.yml
+- extract_artist_track.gemspec
+- lib/extract_artist_track.rb
+- lib/extract_artist_track/cleaner.rb
+- lib/extract_artist_track/parser.rb
+- lib/extract_artist_track/splitter.rb
+- lib/extract_artist_track/version.rb
+homepage: https://github.com/6/extract_artist_track
+licenses: []
+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: 2.5.1
+signing_key: 
+specification_version: 4
+summary: Extract artist and track from YouTube video title.
+test_files: []