amatch 0.1.5 → 0.2.0

data/tests/test_sellers.rb

@@ -0,0 +1,94 @@
+require 'test/unit'
+require 'amatch'
+require 'test_levenshtein'
+
+class TC_Sellers < TC_Levenshtein
+  include Amatch
+
+  D = 0.000001
+
+  def setup
+    @empty = Sellers.new('')
+    @simple = Sellers.new('test')
+  end
+
+  def test_weights
+    assert_in_delta 1, @simple.substitution, D
+    assert_in_delta 1, @simple.insertion, D
+    assert_in_delta 1, @simple.deletion, D
+    @simple.insertion = 1
+    @simple.substitution = @simple.deletion = 1000
+    assert_in_delta 1, @simple.match('tst'), D
+    assert_in_delta 1, @simple.search('bbbtstccc'), D
+    @simple.deletion = 1
+    @simple.substitution = @simple.insertion = 1000
+    assert_in_delta 1, @simple.match('tedst'), D
+    assert_in_delta 1, @simple.search('bbbtedstccc'), D
+    @simple.substitution = 1
+    @simple.deletion = @simple.insertion = 1000
+    assert_in_delta 1, @simple.match('tast'), D
+    assert_in_delta 1, @simple.search('bbbtastccc'), D
+    @simple.insertion = 0.5
+    @simple.substitution = @simple.deletion = 1000
+    assert_in_delta 0.5, @simple.match('tst'), D
+    assert_in_delta 0.5, @simple.search('bbbtstccc'), D
+    @simple.deletion = 0.5
+    @simple.substitution = @simple.insertion = 1000
+    assert_in_delta 0.5, @simple.match('tedst'), D
+    assert_in_delta 0.5, @simple.search('bbbtedstccc'), D
+    @simple.substitution = 0.5
+    @simple.deletion = @simple.insertion = 1000
+    assert_in_delta 0.5, @simple.match('tast'), D
+    assert_in_delta 0.5, @simple.search('bbbtastccc'), D
+    @simple.reset_weights
+    assert_in_delta 1, @simple.substitution, D
+    assert_in_delta 1, @simple.insertion, D
+    assert_in_delta 1, @simple.deletion, D
+  end
+
+  def test_weight_exceptions
+    assert_raises(TypeError) { @simple.substitution = :something }
+    assert_raises(TypeError) { @simple.insertion = :something }
+    assert_raises(TypeError) { @simple.deletion = :something }
+  end
+
+  def test_similar
+    assert_in_delta 0.0, @simple.similar(''), D
+    assert_in_delta 1.0, @simple.similar('test'), D
+    assert_in_delta 0.8, @simple.similar('testa'), D
+    assert_in_delta 0.8, @simple.similar('atest'), D
+    assert_in_delta 0.8, @simple.similar('teast'), D
+    assert_in_delta 0.75, @simple.similar('est'), D
+    assert_in_delta 0.75, @simple.similar('tes'), D
+    assert_in_delta 0.75, @simple.similar('tst'), D
+    assert_in_delta 0.75, @simple.similar('best'), D
+    assert_in_delta 0.75, @simple.similar('tost'), D
+    assert_in_delta 0.75, @simple.similar('tesa'), D
+    assert_in_delta 0.25, @simple.similar('taex'), D
+    assert_in_delta 0.4, @simple.similar('aaatestbbb'), D
+    assert_in_delta 0.75, @simple.pattern.levenshtein_similar('est'), D
+  end
+
+  def test_similar
+    assert_in_delta 1, @empty.similar(''), D
+    assert_in_delta 0, @empty.similar('not empty'), D
+    assert_in_delta 0.0, @simple.similar(''), D
+    assert_in_delta 1.0, @simple.similar('test'), D
+    assert_in_delta 0.8, @simple.similar('testa'), D
+    assert_in_delta 0.8, @simple.similar('atest'), D
+    assert_in_delta 0.8, @simple.similar('teast'), D
+    assert_in_delta 0.75, @simple.similar('est'), D
+    assert_in_delta 0.75, @simple.similar('tes'), D
+    assert_in_delta 0.75, @simple.similar('tst'), D
+    assert_in_delta 0.75, @simple.similar('best'), D
+    assert_in_delta 0.75, @simple.similar('tost'), D
+    assert_in_delta 0.75, @simple.similar('tesa'), D
+    assert_in_delta 0.25, @simple.similar('taex'), D
+    assert_in_delta 0.4, @simple.similar('aaatestbbb'), D
+    assert_in_delta 0.75, @simple.pattern.levenshtein_similar('est'), D
+    @simple.insertion = 1
+    @simple.substitution = @simple.deletion = 2
+    assert_in_delta 0.875, @simple.similar('tst'), D
+  end
+end
+  # vim: set et sw=2 ts=2:

metadata

@@ -3,15 +3,17 @@ rubygems_version: 0.8.10
 specification_version: 1
 name: amatch
 version: !ruby/object:Gem::Version 
-  version: 0.1.5
-date: 2005-05-26
+  version: 0.2.0
+date: 2005-06-01
 summary: Approximate String Matching library
 require_paths: 
-  - lib
+  - ext
 email: flori@ping.de
 homepage: http://amatch.rubyforge.org
 rubyforge_project: amatch
-description: Amatch is a library for approximate string matching and searching using a dynamic programming algorithm to compute the Levenstein distance between strings.
+description: "Amatch is a library for approximate string matching and searching in strings.
+  Several algorithms can be used to do this, and it's also possible to compute a
+  similarity metric number between 0.0 and 1.0 for two given strings."
 autorequire: amatch
 default_executable: agrep.rb
 bindir: bin
@@ -36,15 +38,31 @@ files:
   - ext/MANIFEST
   - ext/amatch.c
   - ext/extconf.rb
+  - ext/amatch.bundle
+  - ext/tags
+  - ext/pair.h
+  - ext/pair.c
   - Rakefile
   - VERSION
-  - amatch.txt.en
   - install.rb
+  - config.save
+  - InstalledFiles
   - tests
-  - tests/test.rb
+  - tests/test_levenshtein.rb
+  - tests/test_hamming.rb
+  - tests/test_pair_distance.rb
+  - tests/runner.rb
+  - tests/test_sellers.rb
+  - tests/test_longest_subsequence.rb
+  - tests/test_longest_substring.rb
 test_files: 
-  - tests/test.rb
-rdoc_options: []
+  - tests/runner.rb
+rdoc_options: 
+  - "--title"
+  - "Amatch -- Approximate Matching"
+  - "--main"
+  - Amatch
+  - "--line-numbers"
 extra_rdoc_files: []
 executables: 
   - agrep.rb

data/amatch.txt.en

@@ -1,117 +0,0 @@
-AMatch
-
-Approximate Matching/Searching/Comparing
-
-SYNOPSIS
-
-    require 'amatch'
-
-    m = Amatch.new("pattern")
-
-    p m.match("pattren")
-    p m.match(["pattren","parent"])
-    p m.matchr("pattren")
-    p m.compare("pattren")
-    p m.comparer("pattren")
-    p m.compare("pattn")
-    p m.comparer("pattn")
-    p m.search("abcpattrendef")
-    p m.searchr("abcpattrendef")
-
-DESCRIPTION
-
-This class enables your programs to do approximate matching, searching and
-comparing of strings. It uses an algorithm that calculates the Levenstein
-distance between those strings to implement those features.
-
-The Levenstein edit distance is defined as the minimal costs involved to
-transform one string into another by using three elementary operations:
-deletion, insertion and substitution of a character. To transform "water" into
-"wine", for instance, you have to substitute ?a -> i?: "witer", ?t -> ?n:
-"winer" and delete ?r: "wine". The edit distance between "water" and "wine" is
-3, because you have to apply three operations. The edit distance between
-"wine" and "wine" is 0, of course: no operation is necessary for the
-transformation -- they're already the same string. It's easy to see that more
-similar strings have smaller edit distances than strings that differ a lot.
-
-You can als use different weights for every operation to prefer special
-operations over others. There are three different kinds of match methods
-defined in this class: "match" computes the Levenstein distance between a
-pattern and some strings, "search" searches in some text for a special pattern
-returning a minimal distance, "compare" calculates a value that can be used to
-define a partial order between strings in relation to a given pattern. It's
-also possible to compute a relative distance. This floating point value is
-computed as absolute distance / length of search pattern.
-
-CONSTRUCTOR
-
-- Amatch#new(pattern)
-
-constructs an Amatch object and initializes it with 'pattern'. If no 'pattern'
-is given it has to be set with Amatch#pattern before matching.
-
-METHODS
-
-- Amatch#pattern    pattern string to match against
-
-- Amatch#subw        weight of one substitution (type Fixnum)
-
-- Amatch#delw        weight of one deletion (type Fixnum)
-
-- Amatch#insw        weight of one insertion (type Fixnum)
-
-- Amatch#resetw        resets all weights to their default values (=1).
-
-The following methods require the parameter 'strings'. This parameter can be
-of type String or Array of Strings. The method executes the matching operation
-and returns a number if a string was given. If an array of strings was given
-it returns an array of numbers.
-
-- Amatch#match(strings)
-
-  calculates the absolute edit distance(s) between 'pattern' and 'strings' =
-  the Levenstein distance in char operations. See also Amatch#pattern.
-
-- Amatch#matchr(strings)
-
-  calculates the relative edit distance as float. This value is defined as the
-  edit distance divided by the length of 'pattern'. See also Amatch#pattern.
-
-- Amatch#search(strings)
-
-  searches 'pattern' in strings and returns the edit distance by greedy
-  trimming prefixes or postfixes of the match.
-
-- Amatch#searchr(strings)
-
-  does the same as Amatch#search but divides the edit distance by the length
-  of 'pattern' and returns the value as float.
-
-- Amatch#compare(strings)
-
-  calculates the same absolute value like Amatch#match. The sign of the result
-  value is negative if the strings are shorter than 'pattern' or positive
-  else.
-
-- Amatch#comparer(strings)
-
-  calculates the same absolute value like Amatch#matchr. The sign of the
-  result value is negative if the strings are shorter than 'pattern' or
-  positive else.
-
-EXAMPLES
-
-An agrep utility will be installed that demonstrates the usage of this
-library.
-
-AUTHOR
-
-Florian Frank <flori@ping.de>
-
-COPYRIGHT
-
-Copyright (c) 2002        Florian Frank <flori@ping.de>
-
-This is free software; you can redistribute it and/or modify it under the
-terms of the GNU General Public License Version 2 as published by the Free
-Software Foundation: http://www.gnu.org/copyleft/gpl.html

data/tests/test.rb

@@ -1,94 +0,0 @@
-require 'test/unit'
-require 'amatch'
-
-class TC_AmatchTest < Test::Unit::TestCase
-
-    def setup
-        @matcher = Amatch.new('test')
-    end
-
-    def test_match
-        assert(@matcher.match('') == 4)
-        assert(@matcher.match('test') == 0)
-        assert(@matcher.match('test') == 0)
-        assert(@matcher.match('testa') == 1)
-        assert(@matcher.match('atest') == 1)
-        assert(@matcher.match('teast') == 1)
-        assert(@matcher.match('est') == 1)
-        assert(@matcher.match('tes') == 1)
-        assert(@matcher.match('tst') == 1)
-        assert(@matcher.match('best') == 1)
-        assert(@matcher.match('tost') == 1)
-        assert(@matcher.match('tesa') == 1)
-        assert(@matcher.match('taex') == 3)
-        assert(@matcher.matchr('') == 1.0)
-        assert(@matcher.matchr('tesa') == 0.25)
-        assert(@matcher.match('aaatestbbb') == 6)
-    end
-
-    def test_search
-        assert(@matcher.search('') == 4)
-        assert(@matcher.searchr('') == 1.0)
-        assert(@matcher.search('aaatestbbb') == 0)
-        assert(@matcher.search('aaataexbbb') == 3)
-        assert(@matcher.searchr('aaataexbbb') == 0.75)
-        assert(@matcher.search('aaaaaaaaa') == 4)
-        assert(@matcher.searchr('aaaaaaaaa') == 1.0)
-    end
-
-    def test_compare
-        assert(@matcher.compare('') == -4)
-        assert(@matcher.comparer('') == -1.0)
-        assert(@matcher.compare('taex') == 3)
-        assert(@matcher.comparer('tesa') == 0.25)
-        assert(@matcher.compare('aaatestbbb') == 6)
-        assert(@matcher.compare('test') == 0)
-        assert(@matcher.compare('tex') == -2)
-        assert(@matcher.comparer('tsa') == -0.5)
-        assert(@matcher.compare('wxyz') == 4)
-        assert(@matcher.comparer('wxyz') == 1.0)
-        assert_raises(TypeError) { @matcher.match(:foo) }
-    end
-
-    def test_array_result
-        assert(@matcher.match([]) == []);
-        assert(@matcher.match(["tets", "test"]) == [2, 0]);
-        assert(@matcher.matchr(["tets", "test"]) == [0.5, 0]);
-        assert(@matcher.compare(["tets", "test"]) == [2, 0]);
-        assert(@matcher.comparer(["tets", "test"]) == [0.5, 0]);
-        assert(@matcher.search(["tetsaaa", "testaaa"]) == [1, 0]);
-        assert(@matcher.searchr(["tetsaaa", "testaaa"]) == [0.25, 0]);
-        assert_raises(TypeError) { @matcher.match([:foo, "bar"]) }
-    end
-
-    def test_weights
-        assert(@matcher.subw == 1)
-        assert(@matcher.insw == 1)
-        assert(@matcher.delw == 1)
-        @matcher.subw = 2
-        assert(@matcher.subw == 2)
-        assert(@matcher.match('tast') == 2)
-        @matcher.subw = 1
-        assert(@matcher.match('tast') == 1)
-        @matcher.delw = 2
-        assert(@matcher.delw == 2)
-        assert(@matcher.match('teist') == 2)
-        @matcher.insw = 2
-        assert(@matcher.insw == 2)
-        assert(@matcher.match('tst') == 2)
-        @matcher.resetw    
-        assert(@matcher.subw == 1)
-        assert(@matcher.insw == 1)
-        assert(@matcher.delw == 1)
-        @matcher.subw = :something
-        assert_raises(TypeError) { @matcher.match('anything') }
-        @matcher.subw = 1
-        @matcher.insw = :something
-        assert_raises(TypeError) { @matcher.match('anything') }
-        @matcher.insw = 1
-        @matcher.delw = :something
-        assert_raises(TypeError) { @matcher.match('anything') }
-    end
-
-end
-    # vim: set noet sw=4 ts=4: