difflcs 0.6.0
Sign up to get free protection for your applications and to get access to all the features.
- data/CHANGELOG.txt +3 -0
- data/LICENSE.txt +662 -0
- data/README.txt +43 -0
- data/Rakefile +93 -0
- data/install.rb +30 -0
- data/lib/diff_l_c_s.rb +148 -0
- data/lib/diff_l_c_s/counter.rb +120 -0
- data/lib/diff_l_c_s/string.rb +18 -0
- data/lib/diff_l_c_s/version.rb +9 -0
- data/lib/diff_l_c_s/word_split_array.rb +58 -0
- data/lib/difflcs.rb +1 -0
- data/test/counter_test.rb +93 -0
- data/test/diff_l_c_s_test.rb +124 -0
- data/test/test_helper.rb +3 -0
- data/test/word_split_array_test.rb +55 -0
- metadata +77 -0
@@ -0,0 +1,58 @@
|
|
1
|
+
#--#
|
2
|
+
# Copyright: (c) 2006-2008 The LogiLogi Foundation <foundation@logilogi.org>
|
3
|
+
#
|
4
|
+
# License:
|
5
|
+
# This file is part of the DiffLCS library. DiffLCS is Free Software.
|
6
|
+
# You can run/distribute/modify DiffLCS under the terms of the GNU Affero
|
7
|
+
# General Public License version 3. The Affero GPL states that running a
|
8
|
+
# modified version or a derivative work also requires you to make the
|
9
|
+
# sourcecode of that work available to everyone that can interact with it.
|
10
|
+
# We chose the Affero GPL to ensure that DiffLCS remains open and libre
|
11
|
+
# (LICENSE.txt contains the full text of the legally binding license).
|
12
|
+
#++#
|
13
|
+
|
14
|
+
class DiffLCS::WordSplitArray < Array
|
15
|
+
|
16
|
+
### Constants
|
17
|
+
|
18
|
+
# Used as a separator
|
19
|
+
SEPARATOR = "\031" # The Unit Separator character
|
20
|
+
|
21
|
+
### Constructors
|
22
|
+
|
23
|
+
# Splits the words, and treats whitespace correctly.
|
24
|
+
#
|
25
|
+
def initialize(text)
|
26
|
+
old_end = 0
|
27
|
+
# splits for html-tags, for any non-word-characters & for SEPARATORs
|
28
|
+
treated = text.scan(/<\/?\w+>|[^\w<\/>#{SEPARATOR}]+|#{SEPARATOR}/) do |literal|
|
29
|
+
match = $~
|
30
|
+
if match.begin(0) > old_end
|
31
|
+
self.push(text[old_end...match.begin(0)])
|
32
|
+
end
|
33
|
+
self.push(literal)
|
34
|
+
old_end = match.end(0)
|
35
|
+
end
|
36
|
+
if old_end < text.size
|
37
|
+
self.push(text[old_end...text.size])
|
38
|
+
end
|
39
|
+
end
|
40
|
+
|
41
|
+
### Methods
|
42
|
+
|
43
|
+
# Translates word-positions to character-positions.
|
44
|
+
#
|
45
|
+
def translate_to_pos(positions)
|
46
|
+
word_p = 0
|
47
|
+
temp_array = [0]
|
48
|
+
i = 0
|
49
|
+
while i < self.size
|
50
|
+
word_p += self[i].size
|
51
|
+
temp_array.push(word_p)
|
52
|
+
i += 1
|
53
|
+
end
|
54
|
+
return PositionRange::List.new(
|
55
|
+
positions.collect {|position| position.new_dup(
|
56
|
+
temp_array[position.begin], temp_array[position.end])})
|
57
|
+
end
|
58
|
+
end
|
data/lib/difflcs.rb
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require 'diff_l_c_s'
|
@@ -0,0 +1,93 @@
|
|
1
|
+
#--#
|
2
|
+
# Copyright: (c) 2006-2008 The LogiLogi Foundation <foundation@logilogi.org>
|
3
|
+
#
|
4
|
+
# License:
|
5
|
+
# This file is part of the DiffLCS library. DiffLCS is Free Software.
|
6
|
+
# You can run/distribute/modify DiffLCS under the terms of the GNU Affero
|
7
|
+
# General Public License version 3. The Affero GPL states that running a
|
8
|
+
# modified version or a derivative work also requires you to make the
|
9
|
+
# sourcecode of that work available to everyone that can interact with it.
|
10
|
+
# We chose the Affero GPL to ensure that DiffLCS remains open and libre
|
11
|
+
# (LICENSE.txt contains the full text of the legally binding license).
|
12
|
+
#++#
|
13
|
+
|
14
|
+
require File.dirname(__FILE__) + '/test_helper.rb'
|
15
|
+
|
16
|
+
class CounterTest < Test::Unit::TestCase
|
17
|
+
|
18
|
+
### Initialization
|
19
|
+
|
20
|
+
def test_initialize
|
21
|
+
c = DiffLCS::Counter.new(1,2)
|
22
|
+
assert_equal 1, c.step_size
|
23
|
+
end
|
24
|
+
|
25
|
+
### Methods
|
26
|
+
|
27
|
+
def test_step_up_in_old_and_in_new
|
28
|
+
c = DiffLCS::Counter.new(5,80)
|
29
|
+
assert_equal PositionRange.new(5,6), c.in_old
|
30
|
+
assert_equal PositionRange.new(80,81), c.in_new
|
31
|
+
|
32
|
+
c2 = DiffLCS::Counter.new(5,80)
|
33
|
+
c2.step_up
|
34
|
+
c2.step_up
|
35
|
+
|
36
|
+
assert_equal PositionRange.new(5,8), c2.in_old
|
37
|
+
assert_equal PositionRange.new(80,83), c2.in_new
|
38
|
+
end
|
39
|
+
|
40
|
+
def test_size_in_old_and_in_new_assignment
|
41
|
+
c = DiffLCS::Counter.new(5,80)
|
42
|
+
5.times do c.step_up end
|
43
|
+
|
44
|
+
assert_equal 6, c.size
|
45
|
+
c.in_old = PositionRange.new(5,9)
|
46
|
+
assert_equal 4, c.size
|
47
|
+
assert_equal PositionRange.new(80,84), c.in_new
|
48
|
+
|
49
|
+
c2 = DiffLCS::Counter.new(5,80)
|
50
|
+
3.times do c2.step_up end
|
51
|
+
|
52
|
+
assert_equal 4, c2.size
|
53
|
+
c2.in_new = PositionRange.new(80,82)
|
54
|
+
assert_equal 2, c2.size
|
55
|
+
assert_equal PositionRange.new(5,7), c2.in_old
|
56
|
+
|
57
|
+
c3 = DiffLCS::Counter.new(5,80)
|
58
|
+
4.times do c3.step_up end
|
59
|
+
|
60
|
+
assert_equal 5, c3.size
|
61
|
+
|
62
|
+
c3.in_new = PositionRange.new(80,82)
|
63
|
+
assert_equal 2, c3.size
|
64
|
+
assert_equal PositionRange.new(5,7), c3.in_old
|
65
|
+
|
66
|
+
c3.in_old = PositionRange.new(6,7)
|
67
|
+
assert_equal 1, c3.size
|
68
|
+
assert_equal PositionRange.new(81,82), c3.in_new
|
69
|
+
end
|
70
|
+
|
71
|
+
def test_step_size
|
72
|
+
c = DiffLCS::Counter.new(1,5)
|
73
|
+
assert_equal 1, c.step_size
|
74
|
+
c.step_up
|
75
|
+
assert_equal 2, c.step_size
|
76
|
+
end
|
77
|
+
|
78
|
+
def test_comparison
|
79
|
+
c1 = DiffLCS::Counter.new(5,80)
|
80
|
+
c2 = DiffLCS::Counter.new(15,90)
|
81
|
+
|
82
|
+
c1.step_up
|
83
|
+
|
84
|
+
assert c1 > c2
|
85
|
+
|
86
|
+
# cause of no step_ups after in_old => size => comparing
|
87
|
+
c2 = DiffLCS::Counter.new(15,90)
|
88
|
+
c2.step_up
|
89
|
+
c2.step_up
|
90
|
+
|
91
|
+
assert c1 < c2
|
92
|
+
end
|
93
|
+
end
|
@@ -0,0 +1,124 @@
|
|
1
|
+
#--#
|
2
|
+
# Copyright: (c) 2006-2008 The LogiLogi Foundation <foundation@logilogi.org>
|
3
|
+
#
|
4
|
+
# License:
|
5
|
+
# This file is part of the DiffLCS library. DiffLCS is Free Software.
|
6
|
+
# You can run/distribute/modify DiffLCS under the terms of the GNU Affero
|
7
|
+
# General Public License version 3. The Affero GPL states that running a
|
8
|
+
# modified version or a derivative work also requires you to make the
|
9
|
+
# sourcecode of that work available to everyone that can interact with it.
|
10
|
+
# We chose the Affero GPL to ensure that DiffLCS remains open and libre
|
11
|
+
# (LICENSE.txt contains the full text of the legally binding license).
|
12
|
+
#++#
|
13
|
+
|
14
|
+
require File.dirname(__FILE__) + '/test_helper.rb'
|
15
|
+
|
16
|
+
require 'diff_l_c_s/string'
|
17
|
+
|
18
|
+
class DiffLCSTest < Test::Unit::TestCase
|
19
|
+
### Class methods
|
20
|
+
|
21
|
+
def test_diff
|
22
|
+
similar = ['This is the first small diff test. Isn\'t it nice ? ']
|
23
|
+
old_chunk_arr = similar.dup
|
24
|
+
new_chunk_arr = [similar[0], 'Yes it is! Look! It works.']
|
25
|
+
do_diff_test(similar, old_chunk_arr, new_chunk_arr)
|
26
|
+
|
27
|
+
similar = [
|
28
|
+
'We are now really into testing ',
|
29
|
+
' of hand-written - or is it typed ? - texts ',
|
30
|
+
' diffing (finding differences between two rows) ']
|
31
|
+
old_chunk_arr = [similar[0], 'the sound process of', similar[2],
|
32
|
+
'beauties of wizzardly', similar[1], '~']
|
33
|
+
new_chunk_arr = [similar[0], 'all of it. We are happy with our world',
|
34
|
+
similar[1], '&', similar[2], '=']
|
35
|
+
do_diff_test(similar, old_chunk_arr, new_chunk_arr)
|
36
|
+
end
|
37
|
+
|
38
|
+
def test_word_diff
|
39
|
+
similar = ['This is the first small diff test. Isn\'t it nice ? ']
|
40
|
+
old_chunk_arr = similar.dup
|
41
|
+
new_chunk_arr = [similar[0], 'Yes it is! Look! It works.']
|
42
|
+
do_word_diff_test(similar, old_chunk_arr, new_chunk_arr)
|
43
|
+
|
44
|
+
similar = [
|
45
|
+
'We are now really into testing ',
|
46
|
+
' of hand-written - or is it typed ? - texts ',
|
47
|
+
' diffing (finding differences between two rows) ']
|
48
|
+
old_chunk_arr = [similar[0], 'the sound process of', similar[2],
|
49
|
+
'beauties of wizzardly', similar[1]]
|
50
|
+
new_chunk_arr = [similar[0], 'all of it. We are happy with our world',
|
51
|
+
similar[1], 'Und', similar[2]]
|
52
|
+
do_word_diff_test(similar, old_chunk_arr, new_chunk_arr)
|
53
|
+
end
|
54
|
+
|
55
|
+
def test_longest_common_sub_strings
|
56
|
+
old_arr = 'abcde'.split('')
|
57
|
+
new_arr = 'acdbe'.split('')
|
58
|
+
|
59
|
+
diff_hash = DiffLCS.longest_common_sub_strings(old_arr,new_arr)
|
60
|
+
|
61
|
+
assert_equal PositionRange.new(2,4),
|
62
|
+
diff_hash[:matched_old].first
|
63
|
+
assert_equal PositionRange.new(1,3),
|
64
|
+
diff_hash[:matched_new].first
|
65
|
+
|
66
|
+
old_arr = 'aaaaablabbbbbbccccc'.split('')
|
67
|
+
new_arr = 'aaaaakbbbbbbk'.split('')
|
68
|
+
|
69
|
+
assert_equal({:matched_old => PositionRange::List.from_s('8,14:0,5'),
|
70
|
+
:matched_new => PositionRange::List.from_s('6,12:0,5')},
|
71
|
+
DiffLCS.longest_common_sub_strings(old_arr,new_arr))
|
72
|
+
end
|
73
|
+
|
74
|
+
def test_string
|
75
|
+
assert_equal({:matched_old => PositionRange::List.from_s('0,2:5,9:2,4'),
|
76
|
+
:matched_new => PositionRange::List.from_s('0,2:3,7:7,9')},
|
77
|
+
'123456789'.diff('120678934'))
|
78
|
+
end
|
79
|
+
|
80
|
+
### Test helpers
|
81
|
+
|
82
|
+
def do_diff_test(similar_chunk_arr, old_chunk_arr, new_chunk_arr)
|
83
|
+
old = old_chunk_arr.join
|
84
|
+
new = new_chunk_arr.join
|
85
|
+
old_arr = old.split('')
|
86
|
+
new_arr = new.split('')
|
87
|
+
target_matched_old =
|
88
|
+
self.get_position_range_list_for_ranges_of_in(
|
89
|
+
similar_chunk_arr, old)
|
90
|
+
target_matched_new =
|
91
|
+
self.get_position_range_list_for_ranges_of_in(
|
92
|
+
new_chunk_arr - (new_chunk_arr - similar_chunk_arr), new)
|
93
|
+
assert_equal({:matched_old => target_matched_old,
|
94
|
+
:matched_new => target_matched_new},
|
95
|
+
DiffLCS.diff(old_arr, new_arr, :minimum_lcs_size => 15))
|
96
|
+
end
|
97
|
+
|
98
|
+
def do_word_diff_test(similar_chunk_arr, old_chunk_arr, new_chunk_arr)
|
99
|
+
old = old_chunk_arr.join
|
100
|
+
new = new_chunk_arr.join
|
101
|
+
target_matched_old =
|
102
|
+
self.get_position_range_list_for_ranges_of_in(
|
103
|
+
similar_chunk_arr, old)
|
104
|
+
target_matched_new =
|
105
|
+
self.get_position_range_list_for_ranges_of_in(
|
106
|
+
new_chunk_arr - (new_chunk_arr - similar_chunk_arr), new)
|
107
|
+
assert_equal({:matched_old => target_matched_old,
|
108
|
+
:matched_new => target_matched_new},
|
109
|
+
DiffLCS.word_diff(old, new, :minimum_lcs_size => 3))
|
110
|
+
end
|
111
|
+
|
112
|
+
def get_position_range_list_for_ranges_of_in(substrings, string)
|
113
|
+
p_r_l = PositionRange::List.new
|
114
|
+
substrings.each {|substring|
|
115
|
+
pos = string.index(substring)
|
116
|
+
if pos
|
117
|
+
p_r_l.push(PositionRange.new(pos, pos + substring.size))
|
118
|
+
else
|
119
|
+
raise StandardError, ' Substring not found'
|
120
|
+
end
|
121
|
+
}
|
122
|
+
return p_r_l
|
123
|
+
end
|
124
|
+
end
|
data/test/test_helper.rb
ADDED
@@ -0,0 +1,55 @@
|
|
1
|
+
#--#
|
2
|
+
# Copyright: (c) 2006-2008 The LogiLogi Foundation <foundation@logilogi.org>
|
3
|
+
#
|
4
|
+
# License:
|
5
|
+
# This file is part of the DiffLCS library. DiffLCS is Free Software.
|
6
|
+
# You can run/distribute/modify DiffLCS under the terms of the GNU Affero
|
7
|
+
# General Public License version 3. The Affero GPL states that running a
|
8
|
+
# modified version or a derivative work also requires you to make the
|
9
|
+
# sourcecode of that work available to everyone that can interact with it.
|
10
|
+
# We chose the Affero GPL to ensure that DiffLCS remains open and libre
|
11
|
+
# (LICENSE.txt contains the full text of the legally binding license).
|
12
|
+
#++#
|
13
|
+
|
14
|
+
require File.dirname(__FILE__) + '/test_helper.rb'
|
15
|
+
|
16
|
+
class WordSplitArrayTest < Test::Unit::TestCase
|
17
|
+
### Initialization
|
18
|
+
|
19
|
+
def test_initialize
|
20
|
+
assert_equal ['boo',' ','ba',' ','bol'], DiffLCS::WordSplitArray.new('boo ba bol')
|
21
|
+
assert_equal ['boo',' ','ba',' ','bol'], DiffLCS::WordSplitArray.new('boo ba bol')
|
22
|
+
assert_equal ['boo','. ','ba',' ','bol'], DiffLCS::WordSplitArray.new('boo. ba bol')
|
23
|
+
assert_equal [' ','boo','. ','ba',' ','bol'], DiffLCS::WordSplitArray.new(' boo. ba bol')
|
24
|
+
assert_equal ['boo','. ','ba',' ','bol',' '], DiffLCS::WordSplitArray.new('boo. ba bol ')
|
25
|
+
assert_equal [' ','boo','. ','ba',' ','bol',' '], DiffLCS::WordSplitArray.new(' boo. ba bol ')
|
26
|
+
assert_equal [' ','boo','. ','<ba>',' ','</bol>',' '], DiffLCS::WordSplitArray.new(' boo. <ba> </bol> ')
|
27
|
+
assert_equal [' ','boo','. ','<ba>','moma','</bol>',' '], DiffLCS::WordSplitArray.new(' boo. <ba>moma</bol> ')
|
28
|
+
assert_equal ['boo',' ',DiffLCS::WordSplitArray::SEPARATOR,' ','ba',' ','bol'],
|
29
|
+
DiffLCS::WordSplitArray.new('boo ' + DiffLCS::WordSplitArray::SEPARATOR + ' ba bol')
|
30
|
+
end
|
31
|
+
|
32
|
+
### Methods
|
33
|
+
|
34
|
+
def test_translate_to_pos
|
35
|
+
# normal
|
36
|
+
assert_equal PositionRange::List.from_s('0,3:3,4:4,6:6,9:9,12'),
|
37
|
+
DiffLCS::WordSplitArray.new('boo ba bol').translate_to_pos(
|
38
|
+
PositionRange::List.from_s('0,1:1,2:2,3:3,4:4,5'))
|
39
|
+
|
40
|
+
# scrambled
|
41
|
+
assert_equal PositionRange::List.from_s('3,4:0,3'),
|
42
|
+
DiffLCS::WordSplitArray.new('boo ').translate_to_pos(
|
43
|
+
PositionRange::List.from_s('1,2:0,1'))
|
44
|
+
|
45
|
+
# ends with space
|
46
|
+
assert_equal PositionRange::List.from_s('0,3:3,4:4,7:7,8'),
|
47
|
+
DiffLCS::WordSplitArray.new('boo baa ').translate_to_pos(
|
48
|
+
PositionRange::List.from_s('0,1:1,2:2,3:3,4'))
|
49
|
+
|
50
|
+
# starts with space
|
51
|
+
assert_equal PositionRange::List.from_s('0,1:1,4:4,5:5,8'),
|
52
|
+
DiffLCS::WordSplitArray.new(' boo baa').translate_to_pos(
|
53
|
+
PositionRange::List.from_s('0,1:1,2:2,3:3,4'))
|
54
|
+
end
|
55
|
+
end
|
metadata
ADDED
@@ -0,0 +1,77 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: difflcs
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.6.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Wybo Wiersma
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
|
12
|
+
date: 2008-12-30 00:00:00 +01:00
|
13
|
+
default_executable:
|
14
|
+
dependencies:
|
15
|
+
- !ruby/object:Gem::Dependency
|
16
|
+
name: positionrange
|
17
|
+
type: :runtime
|
18
|
+
version_requirement:
|
19
|
+
version_requirements: !ruby/object:Gem::Requirement
|
20
|
+
requirements:
|
21
|
+
- - ">="
|
22
|
+
- !ruby/object:Gem::Version
|
23
|
+
version: 0.6.0
|
24
|
+
version:
|
25
|
+
description: A diff algoritm using longest common substrings that can also find text that has moved.
|
26
|
+
email: wybo@logilogi.org
|
27
|
+
executables: []
|
28
|
+
|
29
|
+
extensions: []
|
30
|
+
|
31
|
+
extra_rdoc_files: []
|
32
|
+
|
33
|
+
files:
|
34
|
+
- Rakefile
|
35
|
+
- install.rb
|
36
|
+
- README.txt
|
37
|
+
- CHANGELOG.txt
|
38
|
+
- LICENSE.txt
|
39
|
+
- lib/diff_l_c_s
|
40
|
+
- lib/diff_l_c_s/counter.rb
|
41
|
+
- lib/diff_l_c_s/word_split_array.rb
|
42
|
+
- lib/diff_l_c_s/string.rb
|
43
|
+
- lib/diff_l_c_s/version.rb
|
44
|
+
- lib/difflcs.rb
|
45
|
+
- lib/diff_l_c_s.rb
|
46
|
+
- test/counter_test.rb
|
47
|
+
- test/diff_l_c_s_test.rb
|
48
|
+
- test/test_helper.rb
|
49
|
+
- test/word_split_array_test.rb
|
50
|
+
has_rdoc: true
|
51
|
+
homepage: http://difflcs.rubyforge.org
|
52
|
+
post_install_message:
|
53
|
+
rdoc_options: []
|
54
|
+
|
55
|
+
require_paths:
|
56
|
+
- lib
|
57
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - ">="
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: "0"
|
62
|
+
version:
|
63
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
64
|
+
requirements:
|
65
|
+
- - ">="
|
66
|
+
- !ruby/object:Gem::Version
|
67
|
+
version: "0"
|
68
|
+
version:
|
69
|
+
requirements:
|
70
|
+
- none
|
71
|
+
rubyforge_project: difflcs
|
72
|
+
rubygems_version: 1.3.1
|
73
|
+
signing_key:
|
74
|
+
specification_version: 2
|
75
|
+
summary: Diffing that sniffs out moved text.
|
76
|
+
test_files: []
|
77
|
+
|