fuzzy_match 2.0.3 → 2.0.4

data/CHANGELOG

@@ -1,3 +1,9 @@
+2.0.4 / 2013-09-19
+
+* Bug fixes
+
+  * Restore 1.8 compatibility per @zhaocai in #6
+
 2.0.3 / 2013-08-11
 
 * Enhancements

data/Gemfile

@@ -4,8 +4,8 @@ gemspec
 
 # bin/fuzzy_match development
 gem 'activesupport'
-# gem 'remote_table'
+gem 'remote_table'
 gem 'thor'
 gem 'to_regexp'
-# gem 'perftools.rb'
+gem 'perftools.rb'
 gem 'pry'

data/README.markdown

@@ -1,4 +1,12 @@
-# fuzzy_match
+## Top 3 reasons you should use FuzzyMatch
+
+1. *intelligent defaults*: it uses a combination of Pair Distance (2-gram) and Levenshtein Edit Distance to effectively match many examples with no configuration
+2. *all-vs-all*: it takes care of finding the optimal match by comparing everything against everything else (when that's necessary)
+3. *refinable*: you might get to 90% with no configuration, but if you need to go beyond you can use regexps, grouping, and stop words
+
+It solves many mid-range matching problems — if your haystack is ~10k records — if you can winnow down the initial possibilities at the database level and only bring good contenders into app memory — why not give it a shot?
+
+# FuzzyMatch
 
 Find a needle in a haystack based on string similarity and regular expression rules.
 
@@ -12,7 +20,7 @@ Warning! `normalizers` are gone in version 2 and above! See the CHANGELOG and ch
 
     >> require 'fuzzy_match'
     => true
-    >> FuzzyMatch.new(['seamus', 'andy', 'ben']).find('Shamus)
+    >> FuzzyMatch.new(['seamus', 'andy', 'ben']).find('Shamus')
     => "seamus"
 
 See also the blog post [Fuzzy match in Ruby](http://numbers.brighterplanet.com/2012/01/18/fuzzy-match-in-ruby/).

data/bin/fuzzy_match

@@ -18,15 +18,15 @@ require 'to_regexp'
 class FuzzyMatch
   class Cli < ::Thor
     desc :match, "Print out matches between A and B, where A is haystack and B is a bunch of needles."
-    method_option :csv, default: false, type: :boolean, desc: "CSV output"
-    method_option :a_col, default: 0, type: :string, desc: "Column name in A. Defaults to first column."
-    method_option :b_col, default: 0, type: :string, desc: "Column name in B. Defaults to first column."
-    method_option :downcase, default: true, type: :boolean, desc: "Whether to downcase everything (except regexes, where you have to do /foo/i)"
-    method_option :groupings, default: nil, type: :string, desc: "Spreadsheet with groupings - no headers, multi-part groupings on the same row"
-    method_option :rules, default: nil, type: :string, desc: "Spreadsheet with headers: stop_words, identities, find_options. Listing a find_option like must_match_grouping makes it true."
-    method_option :explain, default: false, type: :boolean
-    method_option :grep, default: nil, type: :string
-    method_option :limit, default: 1.0/0, type: :numeric
+    method_option :csv, :default => false, :type => :boolean, :desc => "CSV output"
+    method_option :a_col, :default => 0, :type => :string, :desc => "Column name in A. Defaults to first column."
+    method_option :b_col, :default => 0, :type => :string, :desc => "Column name in B. Defaults to first column."
+    method_option :downcase, :default => true, :type => :boolean, :desc => "Whether to downcase everything (except regexes, where you have to do /foo/i)"
+    method_option :groupings, :default => nil, :type => :string, :desc => "Spreadsheet with groupings - no headers, multi-part groupings on the same row"
+    method_option :rules, :default => nil, :type => :string, :desc => "Spreadsheet with headers: stop_words, identities, find_options. Listing a find_option like must_match_grouping makes it true."
+    method_option :explain, :default => false, :type => :boolean
+    method_option :grep, :default => nil, :type => :string
+    method_option :limit, :default => 1.0/0, :type => :numeric
     def match(a_url, b_url)
       puts "Checking matches using fuzzy_match version #{FuzzyMatch::VERSION}..."
       fz = mkfz a_url
@@ -84,12 +84,12 @@ class FuzzyMatch
     def fz_options
       memo = {}
       if options.groupings
-        memo[:groupings] = RemoteTable.new(options.groupings, headers: false).map do |row|
+        memo[:groupings] = RemoteTable.new(options.groupings, :headers => false).map do |row|
           row.to_a.select(&:present?).map { |v| v.to_regexp(detect: true) }
         end
       end
       if options.rules
-        t = RemoteTable.new(options.rules, headers: :first_row)
+        t = RemoteTable.new(options.rules, :headers => :first_row)
         find_options = t.rows.map { |row| row['find_options'] }
         memo.merge!(
           identities: t.rows.map { |row| row['identities'] }.select(&:present?).map { |v| v.to_regexp(detect: true) },

data/lib/fuzzy_match.rb

@@ -140,7 +140,7 @@ class FuzzyMatch
     when String
       Record.new needle
     else
-      Record.new needle, read: read
+      Record.new needle, :read => read
     end
     
     if gather_last_result

data/lib/fuzzy_match/version.rb

@@ -1,3 +1,3 @@
 class FuzzyMatch
-  VERSION = '2.0.3'
+  VERSION = '2.0.4'
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: fuzzy_match
 version: !ruby/object:Gem::Version
-  version: 2.0.3
+  version: 2.0.4
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-08-12 00:00:00.000000000 Z
+date: 2013-09-19 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: active_record_inline_schema