hash_comparator 0.0.2 → 0.0.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: d80094bdb97ca8548a489934126643430d81b52d78c32e39f49eb543a8f5094e
-  data.tar.gz: 5edab8fa1f3474079f95f9c7eb62143493262aa79125eb1e37b44ff80149910c
+  metadata.gz: 54c03d1e58cabe164b3df964dac46cee9f437b0071c0e0f5fca0a05f2188d49e
+  data.tar.gz: f9d2999965d9b2588f4ebb90b389596e34c2435f97bb17517300b938caf28209
 SHA512:
-  metadata.gz: 215206512d43dc07b147f8d930539e557709219727c67d04a85ec738cf7b1832dc911a7d1393164f2eff3b9967d32db1f7a019f1d8e13c99ef87b3b1a6cf10aa
-  data.tar.gz: 629862e4672fb94ab7faabee76f7d72e28b5d299341340969be0fcca5f6a6cd3f134d8e1c096f16cc82b5c53c71746e18f51aefc03b54a92c730dc8cde222c6a
+  metadata.gz: 8449d47c0c12cc89e2fbb3827790a6103d81d2b2f5b64b863840a284243f13622f24b69e621153970942289b348a186f12f8578f1d3543aa89773cc9baf2814a
+  data.tar.gz: 7688d1f04f962e17aaea4c6591899627432842dec49e3e62ac47bd652c2a550c37b9b08fa755de973e6a55f4e2001e41b85dcc72b2a352961af3d918b1afedf2

data/lib/hash_comparator/emails/analyzer.rb

@@ -6,23 +6,71 @@ require 'hash_comparator/reverse_matcher'
 module HashComparator
   module Emails
     class Analyzer
-      def self.execute(hash_function:, subject_raw_emails:, target_hashed_emails:, remove_username: false)
-        if remove_username
-          subject_raw_emails = Parser.parse(subject_raw_emails)
+      def self.find_common_human_readable(hash_function:, subject_raw_emails:, target_hashed_emails:, options: {})
+        new(
+          hash_function: hash_function,
+          subject_raw_emails: subject_raw_emails,
+          target_hashed_emails: target_hashed_emails,
+          options: options
+        ).find_common_human_readable
+      end
+
+      def self.find_common_hashes(hash_function:, subject_raw_emails:, target_hashed_emails:, options: {})
+        new(
+          hash_function: hash_function,
+          subject_raw_emails: subject_raw_emails,
+          target_hashed_emails: target_hashed_emails,
+          options: options
+        ).find_common_hashes
+      end
+
+      def initialize(hash_function:, subject_raw_emails:, target_hashed_emails:, options:)
+        @hash_function = hash_function
+        @subject_raw_emails = subject_raw_emails
+        @target_hashed_emails = target_hashed_emails
+        @options = options
+        @subject_hashed_emails = []
+      end
+
+      attr_accessor :hash_function, :subject_raw_emails, :subject_hashed_emails, :target_hashed_emails, :options
+
+      def find_common_human_readable
+        common_hashes = find_common_hashes
+        reverse_match(common_hashes)
+      end
+
+      def find_common_hashes
+        parse
+        hash
+        compare
+      end
+
+      private
+
+      def parse
+        if options[:parsing]
+          @subject_raw_emails = Parser.parse(subject_raw_emails, options[:parsing])
         end
+      end
 
-        subject_hashed_emails = Hasher.hash(
+      def hash
+        @subject_hashed_emails = Hasher.hash(
           hash_function: hash_function,
           human_readable_items: subject_raw_emails
         )
-        hashed_common_emails = SetComparator.calculate_overlap(
+      end
+
+      def compare
+        SetComparator.calculate_overlap(
           subject_items: subject_hashed_emails,
           target_items: target_hashed_emails
         )
+      end
 
+      def reverse_match(common_hashes)
         ReverseMatcher.execute(
           hash_function: hash_function,
-          hashed_items: hashed_common_emails,
+          hashed_items: common_hashes,
           human_readable_items: subject_raw_emails
         )
       end

data/lib/hash_comparator/emails/parser.rb

@@ -1,11 +1,156 @@
 module HashComparator
   module Emails
     class Parser
-      def self.parse(emails)
-        emails.map do |email|
+      def self.parse(emails, options = {})
+        new(emails, options).parse
+      end
+
+      def initialize(emails, options)
+        @emails = emails
+        @options = options
+      end
+
+      attr_accessor :emails, :options
+
+      def parse
+        remove_usernames if options[:remove_usernames]
+        remove_generic_domains if options[:remove_generic_domains]
+
+        emails
+      end
+
+      private
+
+      def remove_usernames
+        @emails = emails.map do |email|
           email.strip.split('@')[1]
         end
       end
+
+      def remove_generic_domains
+        @emails = emails.each_with_object([]) do |email, list|
+          domain = email.split('@')[-1]
+          list << email unless GENERIC_EMAIL_DOMAINS.include?(domain)
+        end
+      end
     end
+
+    # Email Domains
+    # Adapted from https://github.com/mailcheck/mailcheck/wiki/List-of-Popular-Domains
+    GENERIC_EMAIL_DOMAINS = %w[
+      aol.com
+      att.net
+      comcast.net
+      facebook.com
+      gmail.com
+      gmx.com
+      googlemail.com
+      google.com
+      hotmail.com
+      hotmail.co.uk
+      mac.com
+      me.com
+      mail.com
+      msn.com
+      live.com
+      sbcglobal.net
+      verizon.net
+      yahoo.com
+      yahoo.co.uk
+      email.com
+      games.com
+      gmx.net
+      hush.com
+      hushmail.com
+      icloud.com
+      inbox.com
+      lavabit.com
+      love.com
+      outlook.com
+      pobox.com
+      rocketmail.com
+      safe-mail.net
+      wow.com
+      ygm.com
+      ymail.com
+      zoho.com
+      fastmail.fm
+      bellsouth.net
+      charter.net
+      comcast.net
+      cox.net
+      earthlink.net
+      juno.com
+      btinternet.com
+      virginmedia.com
+      blueyonder.co.uk
+      freeserve.co.uk
+      live.co.uk
+      ntlworld.com
+      o2.co.uk
+      orange.net
+      sky.com
+      talktalk.co.uk
+      tiscali.co.uk
+      virgin.net
+      wanadoo.co.uk
+      bt.com
+      sina.com
+      qq.com
+      naver.com
+      hanmail.net
+      daum.net
+      nate.com
+      yahoo.co.jp
+      yahoo.co.kr
+      yahoo.co.id
+      yahoo.co.in
+      yahoo.com.sg
+      yahoo.com.ph
+      hotmail.fr
+      live.fr
+      laposte.net
+      yahoo.fr
+      wanadoo.fr
+      orange.fr
+      gmx.fr
+      sfr.fr
+      neuf.fr
+      free.fr
+      gmx.de
+      hotmail.de
+      live.de
+      online.de
+      t-online.de
+      web.de
+      yahoo.de
+      mail.ru
+      rambler.ru
+      yandex.ru
+      ya.ru
+      list.ru
+      hotmail.be
+      live.be
+      skynet.be
+      voo.be
+      tvcablenet.be
+      telenet.be
+      hotmail.com.ar
+      live.com.ar
+      yahoo.com.ar
+      fibertel.com.ar
+      speedy.com.ar
+      arnet.com.ar
+      hotmail.com
+      gmail.com
+      yahoo.com.mx
+      live.com.mx
+      yahoo.com
+      hotmail.es
+      live.com
+      hotmail.com.mx
+      prodigy.net.mx
+      msn.com
+    ].freeze
   end
 end

data/lib/hash_comparator/hasher.rb

@@ -2,7 +2,12 @@ require 'digest'
 
 module HashComparator
   class Hasher
-    SUPPORTED_HASH_FUNCTIONS = { md5: Digest::MD5 }.freeze
+    SUPPORTED_HASH_FUNCTIONS = {
+      md5: Digest::MD5,
+      sha1: Digest::SHA1,
+      sha256: Digest::SHA2,
+      sha512: Digest::SHA512
+    }.freeze
 
     def self.hash(hash_function:, human_readable_items:)
       new(hash_function: hash_function, human_readable_items: human_readable_items).hash

data/lib/hash_comparator/reverse_matcher.rb

@@ -24,10 +24,11 @@ module HashComparator
         hash_function: hash_function,
         human_readable_items: human_readable_items
       )
-      matches = human_readable_items.each_with_index.map do |item, i|
-        item if hashed_items.include?(subject_hashed_items[i])
-      end.compact
 
+      matches = human_readable_items.each_with_index.each_with_object([]) do |(item, i), list|
+        list << item if hashed_items.include?(subject_hashed_items[i])
+      end
+      
       matches.uniq.sort
     end
   end

data/lib/hash_comparator/version.rb

@@ -1,3 +1,3 @@
 module HashComparator
-  VERSION = '0.0.2'
+  VERSION = '0.0.3'
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: hash_comparator
 version: !ruby/object:Gem::Version
-  version: 0.0.2
+  version: 0.0.3
 platform: ruby
 authors:
 - Tanner Johnson
@@ -14,16 +14,16 @@ dependencies:
   name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.9.2
+        version: '13.0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.9.2
+        version: '13.0'
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
@@ -52,10 +52,13 @@ files:
 - lib/hash_comparator/reverse_matcher.rb
 - lib/hash_comparator/set_comparator.rb
 - lib/hash_comparator/version.rb
-homepage: https://rubygems.org/gems/hash_comparator
+homepage: https://github.com/tannerljohnson/hash_comparator
 licenses:
 - MIT
-metadata: {}
+metadata:
+  homepage_uri: https://github.com/tannerljohnson/hash_comparator
+  source_code_uri: https://github.com/tannerljohnson/hash_comparator
+  changelog_uri: https://github.com/tannerljohnson/hash_comparator
 post_install_message:
 rdoc_options: []
 require_paths: