tdiff 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- data/.document +3 -0
- data/.rspec +1 -0
- data/.yardopts +1 -0
- data/ChangeLog.md +8 -0
- data/LICENSE.txt +20 -0
- data/README.md +74 -0
- data/Rakefile +35 -0
- data/gemspec.yml +17 -0
- data/lib/tdiff.rb +133 -0
- data/spec/classes/node.rb +15 -0
- data/spec/spec_helper.rb +2 -0
- data/spec/tdiff_spec.rb +111 -0
- data/tdiff.gemspec +10 -0
- metadata +122 -0
data/.document
ADDED
data/.rspec
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
--colour --format documentation
|
data/.yardopts
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
--markup markdown --title "TDiff Documentation" --protected
|
data/ChangeLog.md
ADDED
@@ -0,0 +1,8 @@
|
|
1
|
+
### 0.1.0 / 2010-11-13
|
2
|
+
|
3
|
+
* Initial release:
|
4
|
+
* Provides the {TDiff} mixin.
|
5
|
+
* Allows custom node equality and traversal logic by overriding the
|
6
|
+
{TDiff#tdiff_equal} and {TDiff#tdiff_each_child} methods.
|
7
|
+
* Implements the [Longest Common Subsequence (LCS)](http://en.wikipedia.org/wiki/Longest_common_subsequence_problem).
|
8
|
+
|
data/LICENSE.txt
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
Copyright (c) 2010 Hal Brodigan
|
2
|
+
|
3
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
4
|
+
a copy of this software and associated documentation files (the
|
5
|
+
"Software"), to deal in the Software without restriction, including
|
6
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
7
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
8
|
+
permit persons to whom the Software is furnished to do so, subject to
|
9
|
+
the following conditions:
|
10
|
+
|
11
|
+
The above copyright notice and this permission notice shall be
|
12
|
+
included in all copies or substantial portions of the Software.
|
13
|
+
|
14
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
15
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
16
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
17
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
18
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
19
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
20
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,74 @@
|
|
1
|
+
# TDiff
|
2
|
+
|
3
|
+
* [Source](http://github.com/postmodern/tdiff)
|
4
|
+
* [Issues](http://github.com/postmodern/tdiff/issues)
|
5
|
+
* Postmodern (postmodern.mod3 at gmail.com)
|
6
|
+
|
7
|
+
## Description
|
8
|
+
|
9
|
+
Calculates the differences between two tree-like structures. Similar to
|
10
|
+
Rubys built-in [TSort](http://rubydoc.info/docs/ruby-stdlib/1.9.2/TSort)
|
11
|
+
module.
|
12
|
+
|
13
|
+
## Features
|
14
|
+
|
15
|
+
* Provides the {TDiff} mixin.
|
16
|
+
* Allows custom node equality and traversal logic by overriding the
|
17
|
+
{TDiff#tdiff_equal} and {TDiff#tdiff_each_child} methods.
|
18
|
+
* Implements the [Longest Common Subsequence (LCS)](http://en.wikipedia.org/wiki/Longest_common_subsequence_problem).
|
19
|
+
|
20
|
+
## Examples
|
21
|
+
|
22
|
+
Diff two HTML documents:
|
23
|
+
|
24
|
+
require 'nokogiri'
|
25
|
+
require 'tdiff'
|
26
|
+
|
27
|
+
class Nokogiri::XML::Node
|
28
|
+
|
29
|
+
include TDiff
|
30
|
+
|
31
|
+
def tdiff_each_child(node,&block)
|
32
|
+
node.children.each(&block)
|
33
|
+
end
|
34
|
+
|
35
|
+
def tdiff_equal(node1,node2)
|
36
|
+
if (node1.text? && node2.text?)
|
37
|
+
node1.text == node2.text
|
38
|
+
elsif (node1.respond_to?(:root) && node2.respond_to?(:root))
|
39
|
+
tdiff_equal(node1.root,node2.root)
|
40
|
+
elsif (node1.respond_to?(:name) && node2.respond_to?(:name))
|
41
|
+
node1.name == node2.name
|
42
|
+
else
|
43
|
+
false
|
44
|
+
end
|
45
|
+
end
|
46
|
+
|
47
|
+
end
|
48
|
+
|
49
|
+
doc1 = Nokogiri::HTML('<div><p>one</p> <p>three</p></div>')
|
50
|
+
doc2 = Nokogiri::HTML('<div><p>one</p> <p>two</p> <p>three</p></div>')
|
51
|
+
|
52
|
+
doc1.at('div').tdiff(doc2.at('div')) do |change,node|
|
53
|
+
puts "#{change} #{node.to_html}".ljust(30) + node.parent.path
|
54
|
+
end
|
55
|
+
|
56
|
+
### Output
|
57
|
+
|
58
|
+
+ <p>one</p> /html/body/div
|
59
|
+
+ /html/body/div
|
60
|
+
<p>one</p> /html/body/div
|
61
|
+
/html/body/div
|
62
|
+
<p>three</p> /html/body/div
|
63
|
+
- one /html/body/div/p[1]
|
64
|
+
+ two /html/body/div/p[2]
|
65
|
+
three /html/body/div/p[2]
|
66
|
+
|
67
|
+
## Install
|
68
|
+
|
69
|
+
$ gem install tdiff
|
70
|
+
|
71
|
+
## Copyright
|
72
|
+
|
73
|
+
See {file:LICENSE.txt} for details.
|
74
|
+
|
data/Rakefile
ADDED
@@ -0,0 +1,35 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
require 'rake'
|
3
|
+
|
4
|
+
begin
|
5
|
+
gem 'ore-tasks', '~> 0.2.0'
|
6
|
+
require 'ore/tasks'
|
7
|
+
|
8
|
+
Ore::Tasks.new
|
9
|
+
rescue LoadError => e
|
10
|
+
STDERR.puts e.message
|
11
|
+
STDERR.puts "Run `gem install ore-tasks` to install 'ore/tasks'."
|
12
|
+
end
|
13
|
+
|
14
|
+
begin
|
15
|
+
gem 'rspec', '~> 2.1.0'
|
16
|
+
require 'rspec/core/rake_task'
|
17
|
+
|
18
|
+
RSpec::Core::RakeTask.new
|
19
|
+
rescue LoadError => e
|
20
|
+
task :spec do
|
21
|
+
abort "Please run `gem install rspec` to install RSpec."
|
22
|
+
end
|
23
|
+
end
|
24
|
+
task :default => :spec
|
25
|
+
|
26
|
+
begin
|
27
|
+
gem 'yard', '~> 0.6.0'
|
28
|
+
require 'yard'
|
29
|
+
|
30
|
+
YARD::Rake::YardocTask.new
|
31
|
+
rescue LoadError => e
|
32
|
+
task :yard do
|
33
|
+
abort "Please run `gem install yard` to install YARD."
|
34
|
+
end
|
35
|
+
end
|
data/gemspec.yml
ADDED
@@ -0,0 +1,17 @@
|
|
1
|
+
name: tdiff
|
2
|
+
version: 0.1.0
|
3
|
+
summary: Calculates the differences between two tree-like structures.
|
4
|
+
description:
|
5
|
+
Calculates the differences between two tree-like structures. Similar to
|
6
|
+
Rubys built-in TSort module.
|
7
|
+
|
8
|
+
license: MIT
|
9
|
+
authors: Postmodern
|
10
|
+
email: postmodern.mod3@gmail.com
|
11
|
+
homepage: http://github.com/postmodern/tdiff
|
12
|
+
has_yard: true
|
13
|
+
|
14
|
+
development_dependencies:
|
15
|
+
ore-tasks: ~> 0.2.0
|
16
|
+
rspec: ~> 2.1.0
|
17
|
+
yard: ~> 0.6.0
|
data/lib/tdiff.rb
ADDED
@@ -0,0 +1,133 @@
|
|
1
|
+
#
|
2
|
+
# {TDiff} adds the ability to calculate the differences between two tree-like
|
3
|
+
# objects. Simply include {TDiff} into the class which represents the tree
|
4
|
+
# nodes and define the {#tdiff_each_child} and {#tdiff_equal} methods.
|
5
|
+
#
|
6
|
+
module TDiff
|
7
|
+
#
|
8
|
+
# Default method which will enumerate over every child of a parent node.
|
9
|
+
#
|
10
|
+
# @param [Object] node
|
11
|
+
# The parent node.
|
12
|
+
#
|
13
|
+
# @yield [child]
|
14
|
+
# The given block will be passed each child of the parent node.
|
15
|
+
#
|
16
|
+
def tdiff_each_child(node,&block)
|
17
|
+
node.each(&block) if node.kind_of?(Enumerable)
|
18
|
+
end
|
19
|
+
|
20
|
+
#
|
21
|
+
# Default method which compares two nodes.
|
22
|
+
#
|
23
|
+
# @param [Object] original_node
|
24
|
+
# A node from the original tree.
|
25
|
+
#
|
26
|
+
# @param [Object] new_node
|
27
|
+
# A node from the new tree.
|
28
|
+
#
|
29
|
+
# @return [Boolean]
|
30
|
+
# Specifies whether the two nodes are equal.
|
31
|
+
#
|
32
|
+
def tdiff_equal(original_node,new_node)
|
33
|
+
original_node == new_node
|
34
|
+
end
|
35
|
+
|
36
|
+
#
|
37
|
+
# Finds the differences between `self` and another tree.
|
38
|
+
#
|
39
|
+
# @param [#tdiff_each_child] tree
|
40
|
+
# The other tree.
|
41
|
+
#
|
42
|
+
# @yield [change, node]
|
43
|
+
# The given block will be passed the added or removed nodes.
|
44
|
+
#
|
45
|
+
# @yieldparam [' ', '+', '-'] change
|
46
|
+
# The state-change of the node.
|
47
|
+
#
|
48
|
+
# @yieldparam [Object] node
|
49
|
+
# A node from one of the two trees.
|
50
|
+
#
|
51
|
+
# @return [Enumerator]
|
52
|
+
# If no block is given, an Enumerator object will be returned.
|
53
|
+
#
|
54
|
+
def tdiff(tree,&block)
|
55
|
+
return enum_for(:tdiff,tree) unless block
|
56
|
+
|
57
|
+
# check if the nodes differ
|
58
|
+
unless tdiff_equal(self,tree)
|
59
|
+
yield '-', self
|
60
|
+
yield '+', tree
|
61
|
+
return self
|
62
|
+
end
|
63
|
+
|
64
|
+
c = Hash.new { |hash,key| hash[key] = Hash.new(0) }
|
65
|
+
x = enum_for(:tdiff_each_child,self)
|
66
|
+
y = enum_for(:tdiff_each_child,tree)
|
67
|
+
|
68
|
+
x.each_with_index do |xi,i|
|
69
|
+
y.each_with_index do |yi,j|
|
70
|
+
c[i][j] = if tdiff_equal(xi,yi)
|
71
|
+
c[i-1][j-1] + 1
|
72
|
+
else
|
73
|
+
if c[i][j-1] > c[i-1][j]
|
74
|
+
c[i][j-1]
|
75
|
+
else
|
76
|
+
c[i-1][j]
|
77
|
+
end
|
78
|
+
end
|
79
|
+
end
|
80
|
+
end
|
81
|
+
|
82
|
+
unchanged = []
|
83
|
+
changes = []
|
84
|
+
|
85
|
+
x_backtrack = x.each_with_index.reverse_each
|
86
|
+
y_backtrack = y.each_with_index.reverse_each
|
87
|
+
|
88
|
+
next_child = lambda { |children|
|
89
|
+
begin
|
90
|
+
children.next
|
91
|
+
rescue StopIteration
|
92
|
+
# end of iteration, return a -1 index
|
93
|
+
[nil, -1]
|
94
|
+
end
|
95
|
+
}
|
96
|
+
|
97
|
+
xi, i = next_child[x_backtrack]
|
98
|
+
yi, j = next_child[y_backtrack]
|
99
|
+
|
100
|
+
until (i == -1 && j == -1)
|
101
|
+
if (i != -1 && j != -1 && tdiff_equal(xi,yi))
|
102
|
+
changes.unshift [' ', xi]
|
103
|
+
unchanged.unshift [xi, yi]
|
104
|
+
|
105
|
+
xi, i = next_child[x_backtrack]
|
106
|
+
yi, j = next_child[y_backtrack]
|
107
|
+
else
|
108
|
+
if (j >= 0 && (i == -1 || c[i][j-1] >= c[i-1][j]))
|
109
|
+
changes.unshift ['+', yi]
|
110
|
+
|
111
|
+
yi, j = next_child[y_backtrack]
|
112
|
+
elsif (i >= 0 && (j == -1 || c[i][j-1] < c[i-1][j]))
|
113
|
+
changes.unshift ['-', xi]
|
114
|
+
|
115
|
+
xi, i = next_child[x_backtrack]
|
116
|
+
end
|
117
|
+
end
|
118
|
+
end
|
119
|
+
|
120
|
+
# explicitly discard the c matrix
|
121
|
+
c = nil
|
122
|
+
|
123
|
+
# sequentially iterate over the changed nodes
|
124
|
+
changes.each(&block)
|
125
|
+
changes = nil
|
126
|
+
|
127
|
+
# recurse down through unchanged nodes
|
128
|
+
unchanged.each { |x,y| x.tdiff(y,&block) }
|
129
|
+
unchanged = nil
|
130
|
+
|
131
|
+
return self
|
132
|
+
end
|
133
|
+
end
|
data/spec/spec_helper.rb
ADDED
data/spec/tdiff_spec.rb
ADDED
@@ -0,0 +1,111 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
require 'classes/node'
|
3
|
+
require 'tdiff'
|
4
|
+
|
5
|
+
describe TDiff do
|
6
|
+
before(:all) do
|
7
|
+
@tree = Node.new('root', [
|
8
|
+
Node.new('leaf1', [
|
9
|
+
Node.new('subleaf1', []),
|
10
|
+
Node.new('subleaf2', [])
|
11
|
+
]),
|
12
|
+
|
13
|
+
Node.new('leaf2', [
|
14
|
+
Node.new('subleaf1', []),
|
15
|
+
Node.new('subleaf2', [])
|
16
|
+
])
|
17
|
+
])
|
18
|
+
|
19
|
+
@different_root = Node.new('wrong', [])
|
20
|
+
|
21
|
+
@added = Node.new('root', [
|
22
|
+
Node.new('leaf1', [
|
23
|
+
Node.new('subleaf1', []),
|
24
|
+
Node.new('subleaf3', []),
|
25
|
+
Node.new('subleaf2', [])
|
26
|
+
]),
|
27
|
+
|
28
|
+
Node.new('leaf2', [
|
29
|
+
Node.new('subleaf1', []),
|
30
|
+
Node.new('subleaf2', [])
|
31
|
+
])
|
32
|
+
])
|
33
|
+
|
34
|
+
@removed = Node.new('root', [
|
35
|
+
Node.new('leaf1', [
|
36
|
+
Node.new('subleaf1', [])
|
37
|
+
]),
|
38
|
+
|
39
|
+
Node.new('leaf2', [
|
40
|
+
Node.new('subleaf1', []),
|
41
|
+
Node.new('subleaf2', [])
|
42
|
+
])
|
43
|
+
])
|
44
|
+
|
45
|
+
@changed_order = Node.new('root', [
|
46
|
+
Node.new('leaf2', [
|
47
|
+
Node.new('subleaf1', []),
|
48
|
+
Node.new('subleaf2', [])
|
49
|
+
]),
|
50
|
+
|
51
|
+
Node.new('leaf1', [
|
52
|
+
Node.new('subleaf1', []),
|
53
|
+
Node.new('subleaf2', [])
|
54
|
+
])
|
55
|
+
])
|
56
|
+
end
|
57
|
+
|
58
|
+
it "should tell if two trees are identical" do
|
59
|
+
@tree.tdiff(@tree).all? { |change,node|
|
60
|
+
change == ' '
|
61
|
+
}.should == true
|
62
|
+
end
|
63
|
+
|
64
|
+
it "should stop if the root nodes have changed" do
|
65
|
+
changes = @tree.tdiff(@different_root).to_a
|
66
|
+
|
67
|
+
changes.length.should == 2
|
68
|
+
|
69
|
+
changes[0][0].should == '-'
|
70
|
+
changes[0][1].should == @tree
|
71
|
+
|
72
|
+
changes[1][0].should == '+'
|
73
|
+
changes[1][1].should == @different_root
|
74
|
+
end
|
75
|
+
|
76
|
+
it "should tell when sub-nodes are added" do
|
77
|
+
changes = @tree.tdiff(@added).select { |change,node| change == '+' }
|
78
|
+
|
79
|
+
changes.length.should == 1
|
80
|
+
changes[0][0].should == '+'
|
81
|
+
changes[0][1].should == @added.children[0].children[1]
|
82
|
+
end
|
83
|
+
|
84
|
+
it "should tell when sub-nodes are removed" do
|
85
|
+
changes = @tree.tdiff(@removed).select { |change,node| change == '-' }
|
86
|
+
|
87
|
+
changes.length.should == 1
|
88
|
+
changes[0][0].should == '-'
|
89
|
+
changes[0][1].should == @tree.children[0].children[1]
|
90
|
+
end
|
91
|
+
|
92
|
+
it "should detect when the order of children has changed" do
|
93
|
+
changes = @tree.tdiff(@changed_order).to_a
|
94
|
+
|
95
|
+
changes.length.should == 5
|
96
|
+
changes[0][0].should == '-'
|
97
|
+
changes[0][1].should == @tree.children[0]
|
98
|
+
|
99
|
+
changes[1][0].should == ' '
|
100
|
+
changes[1][1].should == @tree.children[1]
|
101
|
+
|
102
|
+
changes[2][0].should == '+'
|
103
|
+
changes[2][1].should == @changed_order.children[1]
|
104
|
+
|
105
|
+
changes[3][0].should == ' '
|
106
|
+
changes[3][1].should == @tree.children[1].children[0]
|
107
|
+
|
108
|
+
changes[4][0].should == ' '
|
109
|
+
changes[4][1].should == @tree.children[1].children[1]
|
110
|
+
end
|
111
|
+
end
|
data/tdiff.gemspec
ADDED
metadata
ADDED
@@ -0,0 +1,122 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: tdiff
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
prerelease: false
|
5
|
+
segments:
|
6
|
+
- 0
|
7
|
+
- 1
|
8
|
+
- 0
|
9
|
+
version: 0.1.0
|
10
|
+
platform: ruby
|
11
|
+
authors:
|
12
|
+
- Postmodern
|
13
|
+
autorequire:
|
14
|
+
bindir: bin
|
15
|
+
cert_chain: []
|
16
|
+
|
17
|
+
date: 2010-11-13 00:00:00 -08:00
|
18
|
+
default_executable:
|
19
|
+
dependencies:
|
20
|
+
- !ruby/object:Gem::Dependency
|
21
|
+
name: ore-tasks
|
22
|
+
prerelease: false
|
23
|
+
requirement: &id001 !ruby/object:Gem::Requirement
|
24
|
+
none: false
|
25
|
+
requirements:
|
26
|
+
- - ~>
|
27
|
+
- !ruby/object:Gem::Version
|
28
|
+
segments:
|
29
|
+
- 0
|
30
|
+
- 2
|
31
|
+
- 0
|
32
|
+
version: 0.2.0
|
33
|
+
type: :development
|
34
|
+
version_requirements: *id001
|
35
|
+
- !ruby/object:Gem::Dependency
|
36
|
+
name: rspec
|
37
|
+
prerelease: false
|
38
|
+
requirement: &id002 !ruby/object:Gem::Requirement
|
39
|
+
none: false
|
40
|
+
requirements:
|
41
|
+
- - ~>
|
42
|
+
- !ruby/object:Gem::Version
|
43
|
+
segments:
|
44
|
+
- 2
|
45
|
+
- 1
|
46
|
+
- 0
|
47
|
+
version: 2.1.0
|
48
|
+
type: :development
|
49
|
+
version_requirements: *id002
|
50
|
+
- !ruby/object:Gem::Dependency
|
51
|
+
name: yard
|
52
|
+
prerelease: false
|
53
|
+
requirement: &id003 !ruby/object:Gem::Requirement
|
54
|
+
none: false
|
55
|
+
requirements:
|
56
|
+
- - ~>
|
57
|
+
- !ruby/object:Gem::Version
|
58
|
+
segments:
|
59
|
+
- 0
|
60
|
+
- 6
|
61
|
+
- 0
|
62
|
+
version: 0.6.0
|
63
|
+
type: :development
|
64
|
+
version_requirements: *id003
|
65
|
+
description: Calculates the differences between two tree-like structures. Similar to Rubys built-in TSort module.
|
66
|
+
email: postmodern.mod3@gmail.com
|
67
|
+
executables: []
|
68
|
+
|
69
|
+
extensions: []
|
70
|
+
|
71
|
+
extra_rdoc_files:
|
72
|
+
- README.md
|
73
|
+
- ChangeLog.md
|
74
|
+
- LICENSE.txt
|
75
|
+
files:
|
76
|
+
- .document
|
77
|
+
- .rspec
|
78
|
+
- .yardopts
|
79
|
+
- ChangeLog.md
|
80
|
+
- LICENSE.txt
|
81
|
+
- README.md
|
82
|
+
- Rakefile
|
83
|
+
- gemspec.yml
|
84
|
+
- lib/tdiff.rb
|
85
|
+
- spec/classes/node.rb
|
86
|
+
- spec/spec_helper.rb
|
87
|
+
- spec/tdiff_spec.rb
|
88
|
+
- tdiff.gemspec
|
89
|
+
has_rdoc: yard
|
90
|
+
homepage: http://github.com/postmodern/tdiff
|
91
|
+
licenses:
|
92
|
+
- MIT
|
93
|
+
post_install_message:
|
94
|
+
rdoc_options: []
|
95
|
+
|
96
|
+
require_paths:
|
97
|
+
- lib
|
98
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
99
|
+
none: false
|
100
|
+
requirements:
|
101
|
+
- - ">="
|
102
|
+
- !ruby/object:Gem::Version
|
103
|
+
segments:
|
104
|
+
- 0
|
105
|
+
version: "0"
|
106
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
107
|
+
none: false
|
108
|
+
requirements:
|
109
|
+
- - ">="
|
110
|
+
- !ruby/object:Gem::Version
|
111
|
+
segments:
|
112
|
+
- 0
|
113
|
+
version: "0"
|
114
|
+
requirements: []
|
115
|
+
|
116
|
+
rubyforge_project: tdiff
|
117
|
+
rubygems_version: 1.3.7
|
118
|
+
signing_key:
|
119
|
+
specification_version: 3
|
120
|
+
summary: Calculates the differences between two tree-like structures.
|
121
|
+
test_files:
|
122
|
+
- spec/tdiff_spec.rb
|