difflcs 0.6.0

data/lib/diff_l_c_s/version.rb

@@ -0,0 +1,9 @@
+module DiffLCS
+  module VERSION #:nodoc:
+    MAJOR = 0
+    MINOR = 6
+    TINY  = 0
+
+    STRING = [MAJOR, MINOR, TINY].join('.')
+  end
+end

data/lib/diff_l_c_s/word_split_array.rb

@@ -0,0 +1,58 @@
+#--#
+# Copyright: (c) 2006-2008 The LogiLogi Foundation <foundation@logilogi.org>
+#
+# License:
+#   This file is part of the DiffLCS library. DiffLCS is Free Software.
+#   You can run/distribute/modify DiffLCS under the terms of the GNU Affero 
+#   General Public License version 3. The Affero GPL states that running a 
+#   modified version or a derivative work also requires you to make the 
+#   sourcecode of that work available to everyone that can interact with it. 
+#   We chose the Affero GPL to ensure that DiffLCS remains open and libre 
+#   (LICENSE.txt contains the full text of the legally binding license).
+#++#
+
+class DiffLCS::WordSplitArray < Array
+
+  ### Constants
+
+  # Used as a separator
+  SEPARATOR = "\031" # The Unit Separator character
+
+  ### Constructors
+
+  # Splits the words, and treats whitespace correctly.
+  #
+  def initialize(text)
+    old_end = 0
+    # splits for html-tags, for any non-word-characters & for SEPARATORs
+    treated = text.scan(/<\/?\w+>|[^\w<\/>#{SEPARATOR}]+|#{SEPARATOR}/) do |literal|
+      match = $~
+      if match.begin(0) > old_end
+        self.push(text[old_end...match.begin(0)])
+      end
+      self.push(literal)
+      old_end = match.end(0)
+    end
+    if old_end < text.size
+      self.push(text[old_end...text.size])
+    end
+  end
+
+  ### Methods
+
+  # Translates word-positions to character-positions.
+  #
+  def translate_to_pos(positions)
+    word_p = 0
+    temp_array = [0]
+    i = 0
+    while i < self.size
+      word_p += self[i].size
+      temp_array.push(word_p)
+      i += 1
+    end
+    return PositionRange::List.new(
+        positions.collect {|position| position.new_dup(
+            temp_array[position.begin], temp_array[position.end])})
+  end
+end

data/lib/difflcs.rb

@@ -0,0 +1 @@
+require 'diff_l_c_s'

data/test/counter_test.rb

@@ -0,0 +1,93 @@
+#--#
+# Copyright: (c) 2006-2008 The LogiLogi Foundation <foundation@logilogi.org>
+#
+# License:
+#   This file is part of the DiffLCS library. DiffLCS is Free Software.
+#   You can run/distribute/modify DiffLCS under the terms of the GNU Affero 
+#   General Public License version 3. The Affero GPL states that running a 
+#   modified version or a derivative work also requires you to make the 
+#   sourcecode of that work available to everyone that can interact with it. 
+#   We chose the Affero GPL to ensure that DiffLCS remains open and libre 
+#   (LICENSE.txt contains the full text of the legally binding license).
+#++#
+
+require File.dirname(__FILE__) + '/test_helper.rb'
+
+class CounterTest < Test::Unit::TestCase
+
+  ### Initialization
+
+  def test_initialize
+    c = DiffLCS::Counter.new(1,2)
+    assert_equal 1, c.step_size
+  end
+
+  ### Methods
+
+  def test_step_up_in_old_and_in_new
+    c = DiffLCS::Counter.new(5,80)
+    assert_equal PositionRange.new(5,6), c.in_old
+    assert_equal PositionRange.new(80,81), c.in_new
+
+    c2 = DiffLCS::Counter.new(5,80)
+    c2.step_up
+    c2.step_up
+
+    assert_equal PositionRange.new(5,8), c2.in_old
+    assert_equal PositionRange.new(80,83), c2.in_new
+  end
+
+  def test_size_in_old_and_in_new_assignment
+    c = DiffLCS::Counter.new(5,80)
+    5.times do c.step_up end
+
+    assert_equal 6, c.size
+    c.in_old = PositionRange.new(5,9)
+    assert_equal 4, c.size
+    assert_equal PositionRange.new(80,84), c.in_new
+
+    c2 = DiffLCS::Counter.new(5,80)
+    3.times do c2.step_up end
+
+    assert_equal 4, c2.size
+    c2.in_new = PositionRange.new(80,82)
+    assert_equal 2, c2.size
+    assert_equal PositionRange.new(5,7), c2.in_old
+
+    c3 = DiffLCS::Counter.new(5,80)
+    4.times do c3.step_up end
+
+    assert_equal 5, c3.size
+
+    c3.in_new = PositionRange.new(80,82)
+    assert_equal 2, c3.size
+    assert_equal PositionRange.new(5,7), c3.in_old
+
+    c3.in_old = PositionRange.new(6,7)
+    assert_equal 1, c3.size
+    assert_equal PositionRange.new(81,82), c3.in_new
+  end
+
+  def test_step_size
+    c = DiffLCS::Counter.new(1,5)
+    assert_equal 1, c.step_size
+    c.step_up
+    assert_equal 2, c.step_size
+  end
+
+  def test_comparison
+    c1 = DiffLCS::Counter.new(5,80)
+    c2 = DiffLCS::Counter.new(15,90)
+
+    c1.step_up
+
+    assert c1 > c2
+
+    # cause of no step_ups after in_old => size => comparing
+    c2 = DiffLCS::Counter.new(15,90)
+    c2.step_up
+    c2.step_up
+
+    assert c1 < c2
+  end
+end

data/test/diff_l_c_s_test.rb

@@ -0,0 +1,124 @@
+#--#
+# Copyright: (c) 2006-2008 The LogiLogi Foundation <foundation@logilogi.org>
+#
+# License:
+#   This file is part of the DiffLCS library. DiffLCS is Free Software.
+#   You can run/distribute/modify DiffLCS under the terms of the GNU Affero 
+#   General Public License version 3. The Affero GPL states that running a 
+#   modified version or a derivative work also requires you to make the 
+#   sourcecode of that work available to everyone that can interact with it. 
+#   We chose the Affero GPL to ensure that DiffLCS remains open and libre 
+#   (LICENSE.txt contains the full text of the legally binding license).
+#++#
+
+require File.dirname(__FILE__) + '/test_helper.rb'
+
+require 'diff_l_c_s/string'
+
+class DiffLCSTest < Test::Unit::TestCase
+  ### Class methods
+
+  def test_diff
+    similar = ['This is the first small diff test. Isn\'t it nice ? ']
+    old_chunk_arr = similar.dup
+    new_chunk_arr = [similar[0], 'Yes it is! Look! It works.']
+    do_diff_test(similar, old_chunk_arr, new_chunk_arr)
+
+    similar = [
+        'We are now really into testing ',
+        ' of hand-written - or is it typed ? - texts ',
+        ' diffing (finding differences between two rows) ']
+    old_chunk_arr = [similar[0], 'the sound process of', similar[2],
+        'beauties of wizzardly', similar[1], '~']
+    new_chunk_arr = [similar[0], 'all of it. We are happy with our world',
+        similar[1], '&', similar[2], '=']
+    do_diff_test(similar, old_chunk_arr, new_chunk_arr)
+  end
+
+  def test_word_diff
+    similar = ['This is the first small diff test. Isn\'t it nice ? ']
+    old_chunk_arr = similar.dup
+    new_chunk_arr = [similar[0], 'Yes it is! Look! It works.']
+    do_word_diff_test(similar, old_chunk_arr, new_chunk_arr)
+
+    similar = [
+        'We are now really into testing ',
+        ' of hand-written - or is it typed ? - texts ',
+        ' diffing (finding differences between two rows) ']
+    old_chunk_arr = [similar[0], 'the sound process of', similar[2],
+        'beauties of wizzardly', similar[1]]
+    new_chunk_arr = [similar[0], 'all of it. We are happy with our world',
+        similar[1], 'Und', similar[2]]
+    do_word_diff_test(similar, old_chunk_arr, new_chunk_arr)
+  end
+
+  def test_longest_common_sub_strings
+    old_arr = 'abcde'.split('')
+    new_arr = 'acdbe'.split('')
+
+    diff_hash = DiffLCS.longest_common_sub_strings(old_arr,new_arr)
+
+    assert_equal PositionRange.new(2,4),
+        diff_hash[:matched_old].first
+    assert_equal PositionRange.new(1,3),
+        diff_hash[:matched_new].first
+
+    old_arr = 'aaaaablabbbbbbccccc'.split('')
+    new_arr = 'aaaaakbbbbbbk'.split('')
+
+    assert_equal({:matched_old => PositionRange::List.from_s('8,14:0,5'),
+            :matched_new => PositionRange::List.from_s('6,12:0,5')},
+        DiffLCS.longest_common_sub_strings(old_arr,new_arr))
+  end
+
+  def test_string
+    assert_equal({:matched_old => PositionRange::List.from_s('0,2:5,9:2,4'),
+            :matched_new => PositionRange::List.from_s('0,2:3,7:7,9')},
+        '123456789'.diff('120678934'))
+  end
+
+  ### Test helpers
+
+  def do_diff_test(similar_chunk_arr, old_chunk_arr, new_chunk_arr)
+    old = old_chunk_arr.join
+    new = new_chunk_arr.join
+    old_arr = old.split('')
+    new_arr = new.split('')
+    target_matched_old =
+        self.get_position_range_list_for_ranges_of_in(
+            similar_chunk_arr, old)
+    target_matched_new =
+        self.get_position_range_list_for_ranges_of_in(
+            new_chunk_arr - (new_chunk_arr - similar_chunk_arr), new)
+    assert_equal({:matched_old => target_matched_old,
+            :matched_new => target_matched_new},
+        DiffLCS.diff(old_arr, new_arr, :minimum_lcs_size => 15))
+  end
+
+  def do_word_diff_test(similar_chunk_arr, old_chunk_arr, new_chunk_arr)
+    old = old_chunk_arr.join
+    new = new_chunk_arr.join
+    target_matched_old =
+        self.get_position_range_list_for_ranges_of_in(
+            similar_chunk_arr, old)
+    target_matched_new =
+        self.get_position_range_list_for_ranges_of_in(
+            new_chunk_arr - (new_chunk_arr - similar_chunk_arr), new)
+    assert_equal({:matched_old => target_matched_old,
+            :matched_new => target_matched_new},
+        DiffLCS.word_diff(old, new, :minimum_lcs_size => 3))
+  end
+
+  def get_position_range_list_for_ranges_of_in(substrings, string)
+    p_r_l = PositionRange::List.new
+    substrings.each {|substring|
+      pos = string.index(substring)
+      if pos
+        p_r_l.push(PositionRange.new(pos, pos + substring.size))
+      else
+        raise StandardError, ' Substring not found'
+      end
+    }
+    return p_r_l
+  end
+end

data/test/test_helper.rb

@@ -0,0 +1,3 @@
+require 'stringio'
+require 'test/unit'
+require File.dirname(__FILE__) + '/../lib/diff_l_c_s'

data/test/word_split_array_test.rb

@@ -0,0 +1,55 @@
+#--#
+# Copyright: (c) 2006-2008 The LogiLogi Foundation <foundation@logilogi.org>
+#
+# License:
+#   This file is part of the DiffLCS library. DiffLCS is Free Software.
+#   You can run/distribute/modify DiffLCS under the terms of the GNU Affero 
+#   General Public License version 3. The Affero GPL states that running a 
+#   modified version or a derivative work also requires you to make the 
+#   sourcecode of that work available to everyone that can interact with it. 
+#   We chose the Affero GPL to ensure that DiffLCS remains open and libre 
+#   (LICENSE.txt contains the full text of the legally binding license).
+#++#
+
+require File.dirname(__FILE__) + '/test_helper.rb'
+
+class WordSplitArrayTest < Test::Unit::TestCase
+  ### Initialization
+
+  def test_initialize
+    assert_equal ['boo',' ','ba',' ','bol'], DiffLCS::WordSplitArray.new('boo ba bol')
+    assert_equal ['boo',' ','ba','   ','bol'], DiffLCS::WordSplitArray.new('boo ba   bol')
+    assert_equal ['boo','. ','ba',' ','bol'], DiffLCS::WordSplitArray.new('boo. ba bol')
+    assert_equal [' ','boo','. ','ba',' ','bol'], DiffLCS::WordSplitArray.new(' boo. ba bol')
+    assert_equal ['boo','. ','ba',' ','bol',' '], DiffLCS::WordSplitArray.new('boo. ba bol ')
+    assert_equal [' ','boo','. ','ba',' ','bol',' '], DiffLCS::WordSplitArray.new(' boo. ba bol ')
+    assert_equal [' ','boo','. ','<ba>',' ','</bol>',' '], DiffLCS::WordSplitArray.new(' boo. <ba> </bol> ')
+    assert_equal [' ','boo','. ','<ba>','moma','</bol>',' '], DiffLCS::WordSplitArray.new(' boo. <ba>moma</bol> ')
+    assert_equal ['boo',' ',DiffLCS::WordSplitArray::SEPARATOR,' ','ba',' ','bol'],
+        DiffLCS::WordSplitArray.new('boo ' + DiffLCS::WordSplitArray::SEPARATOR + ' ba bol')
+  end
+
+  ### Methods
+
+  def test_translate_to_pos
+    # normal
+    assert_equal PositionRange::List.from_s('0,3:3,4:4,6:6,9:9,12'),
+        DiffLCS::WordSplitArray.new('boo ba   bol').translate_to_pos(
+            PositionRange::List.from_s('0,1:1,2:2,3:3,4:4,5'))
+
+    # scrambled
+    assert_equal PositionRange::List.from_s('3,4:0,3'),
+        DiffLCS::WordSplitArray.new('boo ').translate_to_pos(
+            PositionRange::List.from_s('1,2:0,1'))
+
+    # ends with space
+    assert_equal PositionRange::List.from_s('0,3:3,4:4,7:7,8'),
+        DiffLCS::WordSplitArray.new('boo baa ').translate_to_pos(
+            PositionRange::List.from_s('0,1:1,2:2,3:3,4'))
+
+    # starts with space
+    assert_equal PositionRange::List.from_s('0,1:1,4:4,5:5,8'),
+        DiffLCS::WordSplitArray.new(' boo baa').translate_to_pos(
+            PositionRange::List.from_s('0,1:1,2:2,3:3,4'))
+  end
+end

metadata

@@ -0,0 +1,77 @@
+--- !ruby/object:Gem::Specification 
+name: difflcs
+version: !ruby/object:Gem::Version 
+  version: 0.6.0
+platform: ruby
+authors: 
+- Wybo Wiersma
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2008-12-30 00:00:00 +01:00
+default_executable: 
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: positionrange
+  type: :runtime
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 0.6.0
+    version: 
+description: A diff algoritm using longest common substrings that can also find text that has moved.
+email: wybo@logilogi.org
+executables: []
+
+extensions: []
+
+extra_rdoc_files: []
+
+files: 
+- Rakefile
+- install.rb
+- README.txt
+- CHANGELOG.txt
+- LICENSE.txt
+- lib/diff_l_c_s
+- lib/diff_l_c_s/counter.rb
+- lib/diff_l_c_s/word_split_array.rb
+- lib/diff_l_c_s/string.rb
+- lib/diff_l_c_s/version.rb
+- lib/difflcs.rb
+- lib/diff_l_c_s.rb
+- test/counter_test.rb
+- test/diff_l_c_s_test.rb
+- test/test_helper.rb
+- test/word_split_array_test.rb
+has_rdoc: true
+homepage: http://difflcs.rubyforge.org
+post_install_message: 
+rdoc_options: []
+
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+requirements: 
+- none
+rubyforge_project: difflcs
+rubygems_version: 1.3.1
+signing_key: 
+specification_version: 2
+summary: Diffing that sniffs out moved text.
+test_files: []
+