loose_tight_dictionary 1.0.4 → 1.0.5

data/README.rdoc

@@ -1,5 +1,9 @@
 = loose_tight_dictionary
 
+DEPRECATED: use [fuzzy_match](https://github.com/seamusabshere/fuzzy_match) instead. All further development will happen there.
+
+FuzzyMatch 1.0.5 is identical to LooseTightDictionary 1.0.5 (except for the name).
+
 Find a needle in a haystack based on string similarity (using the Pair Distance algorithm and Levenshtein distance) and regular expressions.
 
 == Quickstart

data/lib/loose_tight_dictionary.rb

@@ -22,9 +22,9 @@ class LooseTightDictionary
   attr_reader :identities
   attr_reader :tighteners
   attr_reader :stop_words
-  attr_reader :first_blocking_decides
-  attr_reader :must_match_blocking
-  attr_reader :must_match_at_least_one_word
+  attr_reader :default_first_blocking_decides
+  attr_reader :default_must_match_blocking
+  attr_reader :default_must_match_at_least_one_word
 
   # haystack - a bunch of records
   # options
@@ -35,9 +35,9 @@ class LooseTightDictionary
   # * read: how to interpret each entry in the 'haystack', either a Proc or a symbol
   def initialize(records, options = {})
     options = options.symbolize_keys
-    @first_blocking_decides = options.fetch :first_blocking_decides, false
-    @must_match_blocking = options.fetch :must_match_blocking, false
-    @must_match_at_least_one_word = options.fetch :must_match_at_least_one_word, false
+    @default_first_blocking_decides = options[:first_blocking_decides]
+    @default_must_match_blocking = options[:must_match_blocking]
+    @default_must_match_at_least_one_word = options[:must_match_at_least_one_word]
     @blockings = options.fetch(:blockings, []).map { |regexp_or_str| Blocking.new regexp_or_str }
     @identities = options.fetch(:identities, []).map { |regexp_or_str| Identity.new regexp_or_str }
     @tighteners = options.fetch(:tighteners, []).map { |regexp_or_str| Tightener.new regexp_or_str }
@@ -61,6 +61,9 @@ class LooseTightDictionary
     options = options.symbolize_keys
     gather_last_result = options.fetch(:gather_last_result, false)
     is_find_all = options.fetch(:find_all, false)
+    first_blocking_decides = options.fetch(:first_blocking_decides, default_first_blocking_decides)
+    must_match_blocking = options.fetch(:must_match_blocking, default_must_match_blocking)
+    must_match_at_least_one_word = options.fetch(:must_match_at_least_one_word, default_must_match_at_least_one_word)
     
     if gather_last_result
       free_last_result
@@ -112,10 +115,18 @@ class LooseTightDictionary
       [ candidates.dup, [] ]
     end
     
-    # special case: the needle didn't fit anywhere, but must_match_blocking is false, so we'll try it against everything
     if joint.none?
-      joint = disjoint
-      disjoint = []
+      if must_match_blocking
+        if is_find_all
+          return []
+        else
+          return nil
+        end
+      else
+        # special case: the needle didn't fit anywhere, but must_match_blocking is false, so we'll try it against everything
+        joint = disjoint
+        disjoint = []
+      end
     end
     
     if gather_last_result
@@ -163,8 +174,8 @@ class LooseTightDictionary
   #
   #     d = LooseTightDictionary.new ['737', '747', '757' ]
   #     d.explain 'boeing 737-100'
-  def explain(needle)
-    record = find needle, :gather_last_result => true
+  def explain(needle, options = {})
+    record = find needle, options.merge(:gather_last_result => true)
     log "#" * 150
     log "# Match #{needle.inspect} => #{record.inspect}"
     log "#" * 150

data/lib/loose_tight_dictionary/score.rb

@@ -27,9 +27,7 @@ class LooseTightDictionary
     end
         
     def utf8?
-      return @utf8_query[0] if @utf8_query.is_a?(::Array)
-      @utf8_query = [ (defined?(::Encoding) ? str1.encoding.to_s : $KCODE).downcase.start_with?('u') ]
-      @utf8_query[0]
+      (defined?(::Encoding) ? str1.encoding.to_s : $KCODE).downcase.start_with?('u')
     end
     
     if defined?(::Amatch)
@@ -118,5 +116,10 @@ class LooseTightDictionary
       end
       
     end
+    
+    extend ::ActiveSupport::Memoizable
+    memoize :dices_coefficient
+    memoize :levenshtein
+    memoize :utf8?
   end
 end

data/lib/loose_tight_dictionary/version.rb

@@ -1,3 +1,3 @@
 class LooseTightDictionary
-  VERSION = '1.0.4'
+  VERSION = '1.0.5'
 end

data/loose_tight_dictionary.gemspec

@@ -9,8 +9,8 @@ Gem::Specification.new do |s|
   s.authors     = ["Seamus Abshere"]
   s.email       = ["seamus@abshere.net"]
   s.homepage    = "https://github.com/seamusabshere/loose_tight_dictionary"
-  s.summary     = %Q{Allows iterative development of dictionaries for big data sets.}
-  s.description = %Q{Create dictionaries that link rows between two tables using loose matching (string similarity) by default and tight matching (regexp) by request.}
+  s.summary     = %Q{DEPRECATED: use fuzzy_match instead. Find a needle in a haystack using string similarity and (optionally) regexp rules.}
+  s.description = %Q{DEPRECATED: use fuzzy_match instead. Find a needle in a haystack using string similarity and (optionally) regexp rules.}
 
   s.rubyforge_project = "loose_tight_dictionary"
 

data/test/test_loose_tight_dictionary.rb

@@ -62,6 +62,10 @@ class TestLooseTightDictionary < Test::Unit::TestCase
     d = LooseTightDictionary.new [ 'X' ], :blockings => [ /X/, /Y/ ], :must_match_blocking => true
     assert_equal 'X', d.find('X')
     assert_equal nil, d.find('A')
+    
+    d = LooseTightDictionary.new [ 'X' ], :blockings => [ /X/, /Y/ ]
+    assert_equal 'X', d.find('X', :must_match_blocking => true)
+    assert_equal nil, d.find('A', :must_match_blocking => true)
   end
     
   def test_011_free
@@ -153,6 +157,9 @@ class TestLooseTightDictionary < Test::Unit::TestCase
   end
   
   def test_020_stop_words
+    d = LooseTightDictionary.new [ 'A HOTEL', 'B HTL' ]
+    assert_equal 'B HTL', d.find('A HTL', :must_match_at_least_one_word => true)
+    
     d = LooseTightDictionary.new [ 'A HOTEL', 'B HTL' ], :must_match_at_least_one_word => true
     assert_equal 'B HTL', d.find('A HTL')
     

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: loose_tight_dictionary
 version: !ruby/object:Gem::Version
-  version: 1.0.4
+  version: 1.0.5
   prerelease: 
 platform: ruby
 authors:
@@ -9,11 +9,11 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2011-12-06 00:00:00.000000000Z
+date: 2012-01-13 00:00:00.000000000Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: shoulda
-  requirement: &2177777000 !ruby/object:Gem::Requirement
+  requirement: &2155673120 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -21,10 +21,10 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *2177777000
+  version_requirements: *2155673120
 - !ruby/object:Gem::Dependency
   name: remote_table
-  requirement: &2177776540 !ruby/object:Gem::Requirement
+  requirement: &2155672640 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -32,10 +32,10 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *2177776540
+  version_requirements: *2155672640
 - !ruby/object:Gem::Dependency
   name: activerecord
-  requirement: &2177776000 !ruby/object:Gem::Requirement
+  requirement: &2155671900 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -43,10 +43,10 @@ dependencies:
         version: '3'
   type: :development
   prerelease: false
-  version_requirements: *2177776000
+  version_requirements: *2155671900
 - !ruby/object:Gem::Dependency
   name: mysql
-  requirement: &2177775560 !ruby/object:Gem::Requirement
+  requirement: &2155671300 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -54,10 +54,10 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *2177775560
+  version_requirements: *2155671300
 - !ruby/object:Gem::Dependency
   name: cohort_scope
-  requirement: &2177775060 !ruby/object:Gem::Requirement
+  requirement: &2155670520 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -65,10 +65,10 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *2177775060
+  version_requirements: *2155670520
 - !ruby/object:Gem::Dependency
   name: weighted_average
-  requirement: &2177774620 !ruby/object:Gem::Requirement
+  requirement: &2155670100 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -76,10 +76,10 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *2177774620
+  version_requirements: *2155670100
 - !ruby/object:Gem::Dependency
   name: rake
-  requirement: &2177774160 !ruby/object:Gem::Requirement
+  requirement: &2155669660 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -87,10 +87,10 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *2177774160
+  version_requirements: *2155669660
 - !ruby/object:Gem::Dependency
   name: activesupport
-  requirement: &2177773620 !ruby/object:Gem::Requirement
+  requirement: &2155668940 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -98,10 +98,10 @@ dependencies:
         version: '3'
   type: :runtime
   prerelease: false
-  version_requirements: *2177773620
+  version_requirements: *2155668940
 - !ruby/object:Gem::Dependency
   name: to_regexp
-  requirement: &2177773100 !ruby/object:Gem::Requirement
+  requirement: &2155668060 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -109,9 +109,9 @@ dependencies:
         version: 0.0.3
   type: :runtime
   prerelease: false
-  version_requirements: *2177773100
-description: Create dictionaries that link rows between two tables using loose matching
-  (string similarity) by default and tight matching (regexp) by request.
+  version_requirements: *2155668060
+description: ! 'DEPRECATED: use fuzzy_match instead. Find a needle in a haystack using
+  string similarity and (optionally) regexp rules.'
 email:
 - seamus@abshere.net
 executables: []
@@ -185,7 +185,8 @@ rubyforge_project: loose_tight_dictionary
 rubygems_version: 1.8.10
 signing_key: 
 specification_version: 3
-summary: Allows iterative development of dictionaries for big data sets.
+summary: ! 'DEPRECATED: use fuzzy_match instead. Find a needle in a haystack using
+  string similarity and (optionally) regexp rules.'
 test_files:
 - test/helper.rb
 - test/test_blocking.rb