consistent_company_ruby 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 2fc44a535ad1632ed8dad8dd11b4341e8c1598c5
+  data.tar.gz: 6a02550a697d5edd52451a04358ee267426ff181
+SHA512:
+  metadata.gz: 088800d076d8456185fd3b4e5e3b267f0369922197af06bc7733ded382cf3719666e041c184fd5ed405b01907905b029120e6bd36c17b7e6207a363ecfd60a93
+  data.tar.gz: 69ae7fdade375d865311a8e92a45c2160bd286761f8466772659c98d836f90b42d09ae5129ce194265c00874f0e023d5999b3093ed1e361b011b8ed01a9c1317

data/lib/consistent_company_ruby.rb

@@ -0,0 +1,7 @@
+require File.expand_path('consistent_company_ruby/instance_methods', File.dirname(__FILE__))
+#
+# String class extension
+#
+class String
+  include ConsistentCompanyRuby::InstanceMethods
+end

data/lib/consistent_company_ruby/instance_methods.rb

@@ -0,0 +1,225 @@
+module ConsistentCompanyRuby
+  module InstanceMethods
+    def namer# company
+      return self if self == ''
+
+      in_string = self.dup
+
+      # while processing we turn & = AND, + = PLUS
+      # and we add space at front and back
+      in_string.gsub('&',' & ')
+      in_string.gsub('+',' + ')
+
+      in_string = in_string.upcase
+      in_string.strip!
+
+      # in_string.gsub(/\(|\)/,' ')
+      num_lefts = 0
+      num_rights = 0
+      left1 = -1
+      right1 = -1
+      left2 = -1
+      right2 = -1
+      len = in_string.size
+
+      (0..len-1).each do |i|
+        if in_string[i] == '('
+          num_lefts += 1
+          if num_lefts == 1
+            left1 = i
+          elsif num_lefts == 2
+            left2 = i
+          end
+        elsif in_string[i] == ')'
+          num_rights += 1
+          if num_rights == 1
+            right1 = i
+          elsif num_rights == 2
+            right2 = i
+          end
+        end
+      end
+
+      if num_lefts == 0 || in_string[0] == '('
+        # Do Nothing
+	    elsif num_lefts == 1
+  	  	if right1 > left1
+          # ..(xx).. -> ....
+          in_string = "#{in_string[0..left1-1]}#{in_string[right1+1..len-1]}"
+        else
+          # ..(xx -> ..
+          in_string = in_string[0..left1-1]
+        end
+      elsif num_lefts == 2
+        if (left1 < right1) && (right1 < left2) && (left2 < right2)
+          # ..(xx)..(xx).. -> ......
+          in_string = "#{in_string[0..left1-1]}#{in_string[right1+1..left2-1]}#{in_string[right2+1..len-1]}"
+        elsif (left1 < left2) && (left2 < right1) && (right1 < right2)
+          # ..(xx(xx)xx).. -> ....
+          in_string = "#{in_string[0..left1-1]}#{in_string[right2+1..len-1]}"
+        elsif (left1 < right1) && (right1 < left2) && (right2 == -1)
+          # ..(xx)..(xx -> ....
+          in_string = "#{in_string[0..left1-1]}#{in_string[right1+1..left2-1]}"
+        elsif (left1 < left2) && (left2 < right1) && (right2 == -1)
+          # ..(xx(xx)xx -> ..
+          in_string = in_string[0..left1-1]
+        elsif (right1 == -1) && (right2 == -1)
+          # ..(xx(xx -> ..
+          in_string = in_string[0..left1-1]
+        end
+      end
+
+      return_string = ''
+      (0..in_string.size-1).each do |i|
+        ch = in_string[i]
+        asc = ch.ord
+
+        if (asc >= 65 && asc <= 90) ||
+            (asc >= 48 && asc <= 57) ||
+            asc > 128 # A-Z, 0-9, and high order chars
+          return_string = "#{return_string}#{ch}"
+        elsif asc == 39 # '
+          # not keeping it
+        elsif asc == 38 && return_string.size > 0 # &
+          if return_string[return_string.size-1] != ' '
+            return_string = "#{return_string} AND "
+          else
+            return_string = "#{return_string}AND "
+          end
+        elsif asc == 43 # +
+          if return_string == 'A' || return_string == 'A '
+            return_string = 'A PLUS '
+          elsif return_string.size > 0
+            if return_string[return_string.size-1] != ' '
+              return_string = "#{return_string} AND "
+            else
+              return_string = "#{return_string}AND "
+            end
+          end
+        elsif return_string.size > 0 &&
+               return_string[return_string.size-1] != ' '
+          return_string = "#{return_string} "
+        end
+        # puts "#{i}#{ch}#{asc}:#{return_string}"
+      end
+
+      return '' if return_string.nil? || return_string == ''
+
+      str_replace return_string, ' AND ', ' & '
+
+      return_string.strip!
+      return_string = transform_company return_string
+      return_string.strip!
+      return_string.gsub!(' ','')
+      return_string
+    end
+
+    def transform_company res
+      res = " #{res} "
+      str_replace res,  " THE ", " "
+      str_replace res,  " ONE ", " 1 "
+      str_replace res,  " TWO ", " 2 "
+      str_replace res,  " TO ", " 2 "
+      str_replace res,  " THREE ", " 3 "
+      str_replace res,  " FOUR ", " 4 "
+      str_replace res,  " FOR ", " 4 "
+      str_replace res,  " FIVE ", " 5 "
+      str_replace res,  " SIX ", " 6 "
+      str_replace res,  " SEVEN ", " 7 "
+      str_replace res,  " EIGHT ", " 8 "
+      str_replace res,  " NINE ", " 9 "
+      str_replace res,  " TEN ", " 10 "
+      str_replace res,  " ELEVEN ", " 11 "
+
+      str_replace res,  " FIRST ", " 1ST "
+      str_replace res,  " SECOND ", " 2ND "
+      str_replace res,  " THIRD ", " 3RD "
+      str_replace res,  " FOURTH ", " 4TH "
+      str_replace res,  " FIFTH ", " 5TH "
+      str_replace res,  " SIXTH ", " 6TH "
+      str_replace res,  " SEVENTH ", " 7TH "
+      str_replace res,  " EIGHTH ", " 8TH "
+      str_replace res,  " NINTH ", " 9TH "
+      str_replace res,  " TENTH ", " 10TH "
+      str_replace res,  " CENTRE ", " CTR "
+      str_replace res,  " CENTER ", " CTR "
+      str_replace res,  " CNTR ", " CTR "
+      str_replace res,  " CENT ", " CTR "
+      str_replace res,  " CENTR ", " CTR "
+      str_replace res,  " AUTOMOTIVE ", " AUTO "
+      str_replace res,  " AUTOMOBILE ", " AUTO "
+      str_replace res,  " AUTOS ", " AUTO "
+      str_replace res,  " AVENUE ", " AVE "
+      str_replace res,  " DRIVE ", " DR "
+      str_replace res,  " PHOTOGRAPHY ", " PHOTO "
+      str_replace res,  " BROTHERS ", " BROS "
+      str_replace res,  " TECHNOLOGY ", " TEC "
+      str_replace res,  " TECH ", " TEC "
+      str_replace res,  " TELEVISION ", " TV "
+      str_replace res,  " INFORMATION ", " INFO "
+      str_replace res,  " SOCIETY ", " SOC "
+      str_replace res,  " DEPARTMENT ", " DEPT "
+      str_replace res,  " REGIONAL ", " REG "
+      str_replace res,  " REGION ", " REG "
+      str_replace res,  " AUTHORITY ", " AUTH "
+      str_replace res,  " NATIONAL ", " NATL "
+      str_replace res,  " INTERNATIONAL ", " INT "
+      str_replace res,  " INTERNATION ", " INT "
+      str_replace res,  " INTL ", " INT "
+      str_replace res,  " MARKETING ", " MKT "
+      str_replace res,  " MKTG ", " MKT "
+      str_replace res,  " MANAGEMENT ", " MGT "
+      str_replace res,  " MGMT ", " MGT "
+
+      res.strip!
+      space_loc = res.index ' '
+
+      if space_loc && res.size > 3
+
+        # Check for "A" as the first word, and
+        # make sure that second word is not an initital or the word "PLUS"
+        # For example: "A C & R" do not remove "A"; "A TOUCH OF CLASS" remove the "A"
+        if res.start_with?('A ') &&
+            !res[2..res.size].start_with?('&') &&
+            !res[3..res.size].start_with?(' ') &&
+            !res[2..res.size].start_with?('PLUS')
+         res.gsub! 'A ', ''
+        end
+
+        # Remove last word if it is a company word or &
+        space_loc = res.index ' '
+        if space_loc
+          res_array = res.split(' ')
+          if is_company_word(res_array.last)
+            res_array.pop
+            if is_company_word(res_array.last) # Look at the new last word
+              res_array.pop
+            end
+            res = res_array.join(' ')
+          end
+
+          res = res[0..res.size-2] if res.end_with? '&'
+        end
+      end
+
+      res
+    end
+
+    def is_company_word(in_word)
+      if ["ADV","ADVERTISING","AGCY","AGENCY","AGY","ASC","ASS","ASSN","ASSOC","ASSOCIAT","ASSOCIATES","ASSOCIATION","ATTORNEY","ATTRNY","ATTY","ATY","AUTO","CO","COMP","COMPANIES","COMPANY","CORP","CORPORATION","CT","CONTRA","DEPARTMENT","DEPT","DIR","DIRECT","DIV","DIVISION","GROUP","HOLDINGS","INC","INCORPORATED","INT","LIMITED","LLC","LLP","LOCAL","LTD","PC","PLC","PROD","PRODS","PRODUCT","PRODUCTIONS","PRODUCTS","TR","TRADE"].include?(in_word)
+        true
+      else
+        false
+      end
+    end
+
+    # It's more than a gsub
+    def str_replace(orig, rep, with)
+      s = orig
+      while s.include?(rep)
+        s.sub! rep, with
+      end
+      orig
+    end
+  end
+end

data/test/test_consistent_company_ruby.rb

@@ -0,0 +1,62 @@
+require 'minitest/autorun'
+require 'consistent_company_ruby'
+
+class ConsistentCompanyRubyTest < Minitest::Test
+  def test_namer
+    # don't change the calling string
+    str = ' my test '
+    _company = str.namer
+    assert_equal(' my test ', str)
+
+    # empty name
+    assert_equal("", "".namer)
+    assert_equal("", " ".namer)
+    assert_equal("", "___".namer)
+    # remove leading and trailing space
+    assert_equal('TEST', " test ".namer)
+    # remove embedded space
+    assert_equal('TEST', " te st ".namer)
+    # remove Company
+    assert_equal("MYTEST", "My Test Company".namer)
+    assert_equal("MYCOMPANYTEST", ("MY COMPANY TEST").namer)
+    assert_equal("MYTEST", ("MY TEST COMPANY COMP").namer)
+    # remove leading The
+    assert_equal("AAA", "The AAA Company".namer)
+    # remove punctuation
+    assert_equal("TESTERS", %q{The, ?%^* tester's company!}.namer)
+    # a very long name
+    assert_equal("A"*1000+"NAMEISHERE", (" A"*1000 + 'NAME IS HERE ').namer)
+    # parenthesis matching
+    assert_equal("BBEE", ("BB(xx)EE").namer)
+    assert_equal("BE", ("B(xx)E").namer)
+    assert_equal("XX", ("(xx)").namer)
+    assert_equal("BB", ("BB(xx").namer)
+    assert_equal("XX", ("(xx").namer)
+    assert_equal("BBMMEE", ("BB(xx)MM(xx)EE").namer)
+    assert_equal("BBEE", ("BB(xx(xx)xx)EE").namer)
+    assert_equal("BBMM", ("BB(xx)MM(xx").namer)
+    assert_equal("BB", ("BB(xx(xx)xx").namer)
+    assert_equal("BB", ("BB(xx(xx").namer)
+
+    # handle and &
+    assert_equal("PRE&POST", ("pre and post").namer)
+    assert_equal("PRE&POST", ("pre & post").namer)
+    assert_equal("PRE&POST", ("&pre and post&").namer)
+    assert_equal("PRE&POST", ("& pre and post &").namer)
+    assert_equal("ANDPRE&POSTAND", ("and pre and post and").namer)
+
+    # leading A
+    assert_equal("ABTEST", ("A B TEST").namer)
+    assert_equal("BTEST", ("A BTEST").namer)
+    assert_equal("APLUSTEST", ("A PLUS TEST").namer)
+    assert_equal("APLUSTEST", ("A + TEST").namer)
+    assert_equal("APLUSTEST", ("A+ TEST").namer)
+
+    # common name shortening
+    assert_equal("TESTCTRCTRCTR", ("Test Center Center Center").namer)
+    assert_equal("My Test Advertising Co".namer, "MY TEST ADV COMPANY".namer)
+
+    # rigorous checking
+    assert_equal "ABA123&&MCCDAFDS&&B", "aba 123 ~!@\#$%^& *()_+ <>? ,./ {} [] ;' : 'mccdafd s & and b".namer
+  end
+end

metadata

@@ -0,0 +1,47 @@
+--- !ruby/object:Gem::Specification
+name: consistent_company_ruby
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Gene Wu
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2016-08-19 00:00:00.000000000 Z
+dependencies: []
+description: Written in Ruby. To normalize a company name.
+email: genehk@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/consistent_company_ruby.rb
+- lib/consistent_company_ruby/instance_methods.rb
+- test/test_consistent_company_ruby.rb
+homepage: http://github.com/gwu1/consistent_company_ruby
+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: 2.5.1
+signing_key: 
+specification_version: 4
+summary: Normalize company name
+test_files:
+- test/test_consistent_company_ruby.rb