Commit initial

.gitignore

@@ -0,0 +1,8 @@
+/.bundle/
+/.yardoc
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/

Gemfile

@@ -0,0 +1,5 @@
+source 'https://rubygems.org'
+
+git_source(:github) { |repo_name| "https://github.com/#{repo_name}" }
+
+gemspec

Rakefile

@@ -0,0 +1,2 @@
+require 'bundler/gem_tasks'
+task default: :spec

bin/console

@@ -0,0 +1,7 @@
+#!/usr/bin/env ruby
+
+require 'bundler/setup'
+require 'crawler/movie'
+
+require 'irb'
+IRB.start(__FILE__)

bin/setup

@@ -0,0 +1,6 @@
+#!/usr/bin/env bash
+set -euo pipefail
+IFS=$'\n\t'
+set -vx
+
+bundle install

crawler-core.gemspec

@@ -0,0 +1,33 @@
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'crawler/core/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = 'crawler-core'
+  spec.version       = Crawler::Core::VERSION
+  spec.authors       = ['Jonathan PHILIPPE']
+  spec.email         = ['jonathan@cinema.paris']
+
+  spec.summary       = %q{}
+  spec.description   = %q{}
+  spec.homepage      = 'https://crawler.cinema.paris'
+  spec.license       = 'CC-BY-SA-4.0'
+
+  if spec.respond_to?(:metadata)
+    spec.metadata['homepage_uri'] = spec.homepage
+    spec.metadata['source_code_uri'] = 'https://github.com/cinema-paris/crawler-core'
+    spec.metadata['changelog_uri'] = 'https://github.com/cinema-paris/crawler-core/CHANGELOG.md'
+  end
+
+  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 'bundler', '~> 1.17'
+  spec.add_development_dependency 'rake', '~> 10.0'
+  spec.add_runtime_dependency 'activesupport', '>= 3.0'
+  spec.add_runtime_dependency 'levenshtein-ffi', '>= 1.0'
+end

lib/crawler/base.rb

@@ -0,0 +1,40 @@
+require 'active_support/concern'
+require 'active_support/inflector'
+require 'levenshtein-ffi'
+
+module Crawler
+  module Base
+    extend ActiveSupport::Concern
+
+    class_methods do
+      def add_provider(provider_name, options = {})
+        raise NotImplementedError
+      end
+
+      def configure
+        yield self
+      end
+
+      def transliterate(string)
+        ActiveSupport::Inflector.transliterate(string.gsub(/[:\-.,!?]/, ' ').strip.gsub(/\s+/, ' '), nil).downcase
+      end
+
+      def levenshtein_score(string_1, string_2)
+        string_1_transliterated = transliterate(string_1)
+        string_2_transliterated = transliterate(string_2)
+        levenshtein_distance = Levenshtein.distance(string_1_transliterated, string_2_transliterated)
+        max_size = [string_1_transliterated.size, string_2_transliterated.size].max.to_f
+
+        (max_size - levenshtein_distance) / max_size
+      end
+
+      def search(*args)
+        raise NotImplementedError
+      end
+
+      def best(*args)
+        raise NotImplementedError
+      end
+    end
+  end
+end

lib/crawler/core/version.rb

@@ -0,0 +1,5 @@
+module Crawler
+  module Core
+    VERSION = '0.1.0'
+  end
+end