discourse-diff 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +8 -0
- data/.travis.yml +5 -0
- data/CODE_OF_CONDUCT.md +74 -0
- data/Gemfile +8 -0
- data/Gemfile.lock +38 -0
- data/LICENSE.txt +21 -0
- data/README.md +43 -0
- data/Rakefile +10 -0
- data/bin/console +14 -0
- data/bin/setup +8 -0
- data/discourse-diff.gemspec +21 -0
- data/lib/discourse/diff.rb +275 -0
- data/lib/discourse/onpdiff.rb +153 -0
- metadata +101 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: c4cb06363e0625bb3f299bafa5a129a87e1e38db
|
4
|
+
data.tar.gz: 21805df17067b7bf27874310c954ad5ebd7e0878
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: bb46193929e2bd974daea80e492e53061ca821920285a800442b5add7e52877016793be8472396bf7200c0b5bcf090cb8a76923a6dc934421646cce7ef2bd0d7
|
7
|
+
data.tar.gz: 1db2a9d41c5d4642f1c36fc08b45579308296405e4eec72064886b93123a5792b79ba86cbc618d6a5e724c03ff2165a365148fb8c5bc26ce4daab72e725e2cee
|
data/.gitignore
ADDED
data/.travis.yml
ADDED
data/CODE_OF_CONDUCT.md
ADDED
@@ -0,0 +1,74 @@
|
|
1
|
+
# Contributor Covenant Code of Conduct
|
2
|
+
|
3
|
+
## Our Pledge
|
4
|
+
|
5
|
+
In the interest of fostering an open and welcoming environment, we as
|
6
|
+
contributors and maintainers pledge to making participation in our project and
|
7
|
+
our community a harassment-free experience for everyone, regardless of age, body
|
8
|
+
size, disability, ethnicity, gender identity and expression, level of experience,
|
9
|
+
nationality, personal appearance, race, religion, or sexual identity and
|
10
|
+
orientation.
|
11
|
+
|
12
|
+
## Our Standards
|
13
|
+
|
14
|
+
Examples of behavior that contributes to creating a positive environment
|
15
|
+
include:
|
16
|
+
|
17
|
+
* Using welcoming and inclusive language
|
18
|
+
* Being respectful of differing viewpoints and experiences
|
19
|
+
* Gracefully accepting constructive criticism
|
20
|
+
* Focusing on what is best for the community
|
21
|
+
* Showing empathy towards other community members
|
22
|
+
|
23
|
+
Examples of unacceptable behavior by participants include:
|
24
|
+
|
25
|
+
* The use of sexualized language or imagery and unwelcome sexual attention or
|
26
|
+
advances
|
27
|
+
* Trolling, insulting/derogatory comments, and personal or political attacks
|
28
|
+
* Public or private harassment
|
29
|
+
* Publishing others' private information, such as a physical or electronic
|
30
|
+
address, without explicit permission
|
31
|
+
* Other conduct which could reasonably be considered inappropriate in a
|
32
|
+
professional setting
|
33
|
+
|
34
|
+
## Our Responsibilities
|
35
|
+
|
36
|
+
Project maintainers are responsible for clarifying the standards of acceptable
|
37
|
+
behavior and are expected to take appropriate and fair corrective action in
|
38
|
+
response to any instances of unacceptable behavior.
|
39
|
+
|
40
|
+
Project maintainers have the right and responsibility to remove, edit, or
|
41
|
+
reject comments, commits, code, wiki edits, issues, and other contributions
|
42
|
+
that are not aligned to this Code of Conduct, or to ban temporarily or
|
43
|
+
permanently any contributor for other behaviors that they deem inappropriate,
|
44
|
+
threatening, offensive, or harmful.
|
45
|
+
|
46
|
+
## Scope
|
47
|
+
|
48
|
+
This Code of Conduct applies both within project spaces and in public spaces
|
49
|
+
when an individual is representing the project or its community. Examples of
|
50
|
+
representing a project or community include using an official project e-mail
|
51
|
+
address, posting via an official social media account, or acting as an appointed
|
52
|
+
representative at an online or offline event. Representation of a project may be
|
53
|
+
further defined and clarified by project maintainers.
|
54
|
+
|
55
|
+
## Enforcement
|
56
|
+
|
57
|
+
Instances of abusive, harassing, or otherwise unacceptable behavior may be
|
58
|
+
reported by contacting the project team at james.kiesel@gmail.com. All
|
59
|
+
complaints will be reviewed and investigated and will result in a response that
|
60
|
+
is deemed necessary and appropriate to the circumstances. The project team is
|
61
|
+
obligated to maintain confidentiality with regard to the reporter of an incident.
|
62
|
+
Further details of specific enforcement policies may be posted separately.
|
63
|
+
|
64
|
+
Project maintainers who do not follow or enforce the Code of Conduct in good
|
65
|
+
faith may face temporary or permanent repercussions as determined by other
|
66
|
+
members of the project's leadership.
|
67
|
+
|
68
|
+
## Attribution
|
69
|
+
|
70
|
+
This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
|
71
|
+
available at [http://contributor-covenant.org/version/1/4][version]
|
72
|
+
|
73
|
+
[homepage]: http://contributor-covenant.org
|
74
|
+
[version]: http://contributor-covenant.org/version/1/4/
|
data/Gemfile
ADDED
data/Gemfile.lock
ADDED
@@ -0,0 +1,38 @@
|
|
1
|
+
PATH
|
2
|
+
remote: .
|
3
|
+
specs:
|
4
|
+
discourse-diff (0.1.0)
|
5
|
+
|
6
|
+
GEM
|
7
|
+
remote: https://rubygems.org/
|
8
|
+
specs:
|
9
|
+
diff-lcs (1.3)
|
10
|
+
mini_portile2 (2.3.0)
|
11
|
+
nokogiri (1.8.2)
|
12
|
+
mini_portile2 (~> 2.3.0)
|
13
|
+
rake (10.5.0)
|
14
|
+
rspec (3.0.0)
|
15
|
+
rspec-core (~> 3.0.0)
|
16
|
+
rspec-expectations (~> 3.0.0)
|
17
|
+
rspec-mocks (~> 3.0.0)
|
18
|
+
rspec-core (3.0.4)
|
19
|
+
rspec-support (~> 3.0.0)
|
20
|
+
rspec-expectations (3.0.4)
|
21
|
+
diff-lcs (>= 1.2.0, < 2.0)
|
22
|
+
rspec-support (~> 3.0.0)
|
23
|
+
rspec-mocks (3.0.4)
|
24
|
+
rspec-support (~> 3.0.0)
|
25
|
+
rspec-support (3.0.4)
|
26
|
+
|
27
|
+
PLATFORMS
|
28
|
+
ruby
|
29
|
+
|
30
|
+
DEPENDENCIES
|
31
|
+
bundler (~> 1.16)
|
32
|
+
discourse-diff!
|
33
|
+
nokogiri
|
34
|
+
rake (~> 10.0)
|
35
|
+
rspec (~> 3.0.0)
|
36
|
+
|
37
|
+
BUNDLED WITH
|
38
|
+
1.16.0
|
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2018 James Kiesel
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
6
|
+
of this software and associated documentation files (the "Software"), to deal
|
7
|
+
in the Software without restriction, including without limitation the rights
|
8
|
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
9
|
+
copies of the Software, and to permit persons to whom the Software is
|
10
|
+
furnished to do so, subject to the following conditions:
|
11
|
+
|
12
|
+
The above copyright notice and this permission notice shall be included in
|
13
|
+
all copies or substantial portions of the Software.
|
14
|
+
|
15
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
16
|
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
17
|
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
18
|
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
19
|
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
20
|
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
21
|
+
THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,43 @@
|
|
1
|
+
# Discourse::Diff
|
2
|
+
|
3
|
+
Welcome to your new gem! In this directory, you'll find the files you need to be able to package up your Ruby library into a gem. Put your Ruby code in the file `lib/discourse/diff`. To experiment with that code, run `bin/console` for an interactive prompt.
|
4
|
+
|
5
|
+
TODO: Delete this and the text above, and describe your gem
|
6
|
+
|
7
|
+
## Installation
|
8
|
+
|
9
|
+
Add this line to your application's Gemfile:
|
10
|
+
|
11
|
+
```ruby
|
12
|
+
gem 'discourse-diff'
|
13
|
+
```
|
14
|
+
|
15
|
+
And then execute:
|
16
|
+
|
17
|
+
$ bundle
|
18
|
+
|
19
|
+
Or install it yourself as:
|
20
|
+
|
21
|
+
$ gem install discourse-diff
|
22
|
+
|
23
|
+
## Usage
|
24
|
+
|
25
|
+
TODO: Write usage instructions here
|
26
|
+
|
27
|
+
## Development
|
28
|
+
|
29
|
+
After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake test` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
|
30
|
+
|
31
|
+
To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
|
32
|
+
|
33
|
+
## Contributing
|
34
|
+
|
35
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/discourse-diff. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [Contributor Covenant](http://contributor-covenant.org) code of conduct.
|
36
|
+
|
37
|
+
## License
|
38
|
+
|
39
|
+
The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
|
40
|
+
|
41
|
+
## Code of Conduct
|
42
|
+
|
43
|
+
Everyone interacting in the Discourse::Diff project’s codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/[USERNAME]/discourse-diff/blob/master/CODE_OF_CONDUCT.md).
|
data/Rakefile
ADDED
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "discourse/diff"
|
5
|
+
|
6
|
+
# You can add fixtures and/or initialization code here to make experimenting
|
7
|
+
# with your gem easier. You can also use a different console, if you like.
|
8
|
+
|
9
|
+
# (If you use this, don't forget to add pry to your Gemfile!)
|
10
|
+
# require "pry"
|
11
|
+
# Pry.start
|
12
|
+
|
13
|
+
require "irb"
|
14
|
+
IRB.start(__FILE__)
|
data/bin/setup
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
lib = File.expand_path("../lib", __FILE__)
|
2
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
3
|
+
require "discourse/diff"
|
4
|
+
|
5
|
+
Gem::Specification.new do |spec|
|
6
|
+
spec.name = "discourse-diff"
|
7
|
+
spec.version = "0.1.0"
|
8
|
+
spec.authors = ["Discourse", "James Kiesel"]
|
9
|
+
spec.email = ["contact@discourse.org", "james.kiesel@gmail.com"]
|
10
|
+
|
11
|
+
spec.summary = %q{Discourse Diff provides inline html diffing for markdown blobs}
|
12
|
+
spec.description = %q{This library has been extracted from [Discourse core](https://www.github.com/discourse/discourse)}
|
13
|
+
spec.license = "MIT"
|
14
|
+
|
15
|
+
spec.files = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(spec)/}) }
|
16
|
+
spec.require_paths = ["lib"]
|
17
|
+
|
18
|
+
spec.add_development_dependency "bundler", "~> 1.16"
|
19
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
20
|
+
spec.add_development_dependency "rspec", ">= 3.0.0"
|
21
|
+
end
|
@@ -0,0 +1,275 @@
|
|
1
|
+
require "discourse/onpdiff"
|
2
|
+
require "nokogiri"
|
3
|
+
|
4
|
+
module Discourse
|
5
|
+
class Diff
|
6
|
+
MAX_DIFFERENCE = 200
|
7
|
+
|
8
|
+
def initialize(before, after)
|
9
|
+
@before = before
|
10
|
+
@after = after
|
11
|
+
before_html = tokenize_html_blocks(@before)
|
12
|
+
after_html = tokenize_html_blocks(@after)
|
13
|
+
before_markdown = tokenize_line(CGI::escapeHTML(@before))
|
14
|
+
after_markdown = tokenize_line(CGI::escapeHTML(@after))
|
15
|
+
|
16
|
+
@block_by_block_diff = ONPDiff.new(before_html, after_html).diff
|
17
|
+
@line_by_line_diff = ONPDiff.new(before_markdown, after_markdown).short_diff
|
18
|
+
end
|
19
|
+
|
20
|
+
def inline_html
|
21
|
+
i = 0
|
22
|
+
inline = []
|
23
|
+
while i < @block_by_block_diff.length
|
24
|
+
op_code = @block_by_block_diff[i][1]
|
25
|
+
if op_code == :common then inline << @block_by_block_diff[i][0]
|
26
|
+
else
|
27
|
+
if op_code == :delete
|
28
|
+
opposite_op_code = :add
|
29
|
+
klass = "del"
|
30
|
+
first = i
|
31
|
+
second = i + 1
|
32
|
+
else
|
33
|
+
opposite_op_code = :delete
|
34
|
+
klass = "ins"
|
35
|
+
first = i + 1
|
36
|
+
second = i
|
37
|
+
end
|
38
|
+
|
39
|
+
if i + 1 < @block_by_block_diff.length && @block_by_block_diff[i + 1][1] == opposite_op_code
|
40
|
+
diff = ONPDiff.new(tokenize_html(@block_by_block_diff[first][0]), tokenize_html(@block_by_block_diff[second][0])).diff
|
41
|
+
inline << generate_inline_html(diff)
|
42
|
+
i += 1
|
43
|
+
else
|
44
|
+
inline << add_class_or_wrap_in_tags(@block_by_block_diff[i][0], klass)
|
45
|
+
end
|
46
|
+
end
|
47
|
+
i += 1
|
48
|
+
end
|
49
|
+
|
50
|
+
"<div class=\"inline-diff\">#{inline.join}</div>"
|
51
|
+
end
|
52
|
+
|
53
|
+
def side_by_side_html
|
54
|
+
i = 0
|
55
|
+
left, right = [], []
|
56
|
+
while i < @block_by_block_diff.length
|
57
|
+
op_code = @block_by_block_diff[i][1]
|
58
|
+
if op_code == :common
|
59
|
+
left << @block_by_block_diff[i][0]
|
60
|
+
right << @block_by_block_diff[i][0]
|
61
|
+
else
|
62
|
+
if op_code == :delete
|
63
|
+
opposite_op_code = :add
|
64
|
+
side = left
|
65
|
+
klass = "del"
|
66
|
+
first = i
|
67
|
+
second = i + 1
|
68
|
+
else
|
69
|
+
opposite_op_code = :delete
|
70
|
+
side = right
|
71
|
+
klass = "ins"
|
72
|
+
first = i + 1
|
73
|
+
second = i
|
74
|
+
end
|
75
|
+
|
76
|
+
if i + 1 < @block_by_block_diff.length && @block_by_block_diff[i + 1][1] == opposite_op_code
|
77
|
+
diff = ONPDiff.new(tokenize_html(@block_by_block_diff[first][0]), tokenize_html(@block_by_block_diff[second][0])).diff
|
78
|
+
deleted, inserted = generate_side_by_side_html(diff)
|
79
|
+
left << deleted
|
80
|
+
right << inserted
|
81
|
+
i += 1
|
82
|
+
else
|
83
|
+
side << add_class_or_wrap_in_tags(@block_by_block_diff[i][0], klass)
|
84
|
+
end
|
85
|
+
end
|
86
|
+
i += 1
|
87
|
+
end
|
88
|
+
|
89
|
+
"<div class=\"revision-content\">#{left.join}</div><div class=\"revision-content\">#{right.join}</div>"
|
90
|
+
end
|
91
|
+
|
92
|
+
def side_by_side_markdown
|
93
|
+
i = 0
|
94
|
+
table = ["<table class=\"markdown\">"]
|
95
|
+
while i < @line_by_line_diff.length
|
96
|
+
table << "<tr>"
|
97
|
+
op_code = @line_by_line_diff[i][1]
|
98
|
+
if op_code == :common
|
99
|
+
table << "<td>#{@line_by_line_diff[i][0]}</td>"
|
100
|
+
table << "<td>#{@line_by_line_diff[i][0]}</td>"
|
101
|
+
else
|
102
|
+
if op_code == :delete
|
103
|
+
opposite_op_code = :add
|
104
|
+
first = i
|
105
|
+
second = i + 1
|
106
|
+
else
|
107
|
+
opposite_op_code = :delete
|
108
|
+
first = i + 1
|
109
|
+
second = i
|
110
|
+
end
|
111
|
+
|
112
|
+
if i + 1 < @line_by_line_diff.length && @line_by_line_diff[i + 1][1] == opposite_op_code
|
113
|
+
before_tokens, after_tokens = tokenize_markdown(@line_by_line_diff[first][0]), tokenize_markdown(@line_by_line_diff[second][0])
|
114
|
+
if (before_tokens.length - after_tokens.length).abs > MAX_DIFFERENCE
|
115
|
+
before_tokens, after_tokens = tokenize_line(@line_by_line_diff[first][0]), tokenize_line(@line_by_line_diff[second][0])
|
116
|
+
end
|
117
|
+
diff = ONPDiff.new(before_tokens, after_tokens).short_diff
|
118
|
+
deleted, inserted = generate_side_by_side_markdown(diff)
|
119
|
+
table << "<td class=\"diff-del\">#{deleted.join}</td>"
|
120
|
+
table << "<td class=\"diff-ins\">#{inserted.join}</td>"
|
121
|
+
i += 1
|
122
|
+
else
|
123
|
+
if op_code == :delete
|
124
|
+
table << "<td class=\"diff-del\">#{@line_by_line_diff[i][0]}</td>"
|
125
|
+
table << "<td></td>"
|
126
|
+
else
|
127
|
+
table << "<td></td>"
|
128
|
+
table << "<td class=\"diff-ins\">#{@line_by_line_diff[i][0]}</td>"
|
129
|
+
end
|
130
|
+
end
|
131
|
+
end
|
132
|
+
table << "</tr>"
|
133
|
+
i += 1
|
134
|
+
end
|
135
|
+
table << "</table>"
|
136
|
+
|
137
|
+
table.join
|
138
|
+
end
|
139
|
+
|
140
|
+
private
|
141
|
+
|
142
|
+
def tokenize_line(text)
|
143
|
+
text.scan(/[^\r\n]+[\r\n]*/)
|
144
|
+
end
|
145
|
+
|
146
|
+
def tokenize_markdown(text)
|
147
|
+
t, tokens = [], []
|
148
|
+
i = 0
|
149
|
+
while i < text.length
|
150
|
+
if text[i] =~ /\w/
|
151
|
+
t << text[i]
|
152
|
+
elsif text[i] =~ /[ \t]/ && t.join =~ /^\w+$/
|
153
|
+
begin
|
154
|
+
t << text[i]
|
155
|
+
i += 1
|
156
|
+
end while i < text.length && text[i] =~ /[ \t]/
|
157
|
+
i -= 1
|
158
|
+
tokens << t.join
|
159
|
+
t = []
|
160
|
+
else
|
161
|
+
tokens << t.join if t.length > 0
|
162
|
+
tokens << text[i]
|
163
|
+
t = []
|
164
|
+
end
|
165
|
+
i += 1
|
166
|
+
end
|
167
|
+
tokens << t.join if t.length > 0
|
168
|
+
tokens
|
169
|
+
end
|
170
|
+
|
171
|
+
def tokenize_html_blocks(html)
|
172
|
+
Nokogiri::HTML.fragment(html).search("./*").map(&:to_html)
|
173
|
+
end
|
174
|
+
|
175
|
+
def tokenize_html(html)
|
176
|
+
HtmlTokenizer.tokenize(html)
|
177
|
+
end
|
178
|
+
|
179
|
+
def add_class_or_wrap_in_tags(html_or_text, klass)
|
180
|
+
index_of_next_chevron = html_or_text.index(">")
|
181
|
+
if html_or_text.length > 0 && html_or_text[0] == '<' && index_of_next_chevron
|
182
|
+
index_of_class = html_or_text.index("class=")
|
183
|
+
if index_of_class.nil? || index_of_class > index_of_next_chevron
|
184
|
+
# we do not have a class for the current tag
|
185
|
+
# add it right before the ">"
|
186
|
+
html_or_text.insert(index_of_next_chevron, " class=\"diff-#{klass}\"")
|
187
|
+
else
|
188
|
+
# we have a class, insert it at the beginning if not already present
|
189
|
+
classes = html_or_text[/class=(["'])([^\1]*)\1/, 2]
|
190
|
+
if classes.include?("diff-#{klass}")
|
191
|
+
html_or_text
|
192
|
+
else
|
193
|
+
html_or_text.insert(index_of_class + "class=".length + 1, "diff-#{klass} ")
|
194
|
+
end
|
195
|
+
end
|
196
|
+
else
|
197
|
+
"<#{klass}>#{html_or_text}</#{klass}>"
|
198
|
+
end
|
199
|
+
end
|
200
|
+
|
201
|
+
def generate_inline_html(diff)
|
202
|
+
inline = []
|
203
|
+
diff.each do |d|
|
204
|
+
case d[1]
|
205
|
+
when :common then inline << d[0]
|
206
|
+
when :delete then inline << add_class_or_wrap_in_tags(d[0], "del")
|
207
|
+
when :add then inline << add_class_or_wrap_in_tags(d[0], "ins")
|
208
|
+
end
|
209
|
+
end
|
210
|
+
inline
|
211
|
+
end
|
212
|
+
|
213
|
+
def generate_side_by_side_html(diff)
|
214
|
+
deleted, inserted = [], []
|
215
|
+
diff.each do |d|
|
216
|
+
case d[1]
|
217
|
+
when :common
|
218
|
+
deleted << d[0]
|
219
|
+
inserted << d[0]
|
220
|
+
when :delete then deleted << add_class_or_wrap_in_tags(d[0], "del")
|
221
|
+
when :add then inserted << add_class_or_wrap_in_tags(d[0], "ins")
|
222
|
+
end
|
223
|
+
end
|
224
|
+
[deleted, inserted]
|
225
|
+
end
|
226
|
+
|
227
|
+
def generate_side_by_side_markdown(diff)
|
228
|
+
deleted, inserted = [], []
|
229
|
+
diff.each do |d|
|
230
|
+
case d[1]
|
231
|
+
when :common
|
232
|
+
deleted << d[0]
|
233
|
+
inserted << d[0]
|
234
|
+
when :delete then deleted << "<del>#{d[0]}</del>"
|
235
|
+
when :add then inserted << "<ins>#{d[0]}</ins>"
|
236
|
+
end
|
237
|
+
end
|
238
|
+
[deleted, inserted]
|
239
|
+
end
|
240
|
+
|
241
|
+
class HtmlTokenizer < Nokogiri::XML::SAX::Document
|
242
|
+
|
243
|
+
attr_accessor :tokens
|
244
|
+
|
245
|
+
def initialize
|
246
|
+
@tokens = []
|
247
|
+
end
|
248
|
+
|
249
|
+
def self.tokenize(html)
|
250
|
+
me = new
|
251
|
+
parser = Nokogiri::HTML::SAX::Parser.new(me)
|
252
|
+
parser.parse("<html><body>#{html}</body></html>")
|
253
|
+
me.tokens
|
254
|
+
end
|
255
|
+
|
256
|
+
USELESS_TAGS = %w{html body}
|
257
|
+
def start_element(name, attributes = [])
|
258
|
+
return if USELESS_TAGS.include?(name)
|
259
|
+
attrs = attributes.map { |a| " #{a[0]}=\"#{a[1]}\"" }.join
|
260
|
+
@tokens << "<#{name}#{attrs}>"
|
261
|
+
end
|
262
|
+
|
263
|
+
AUTOCLOSING_TAGS = %w{area base br col embed hr img input meta}
|
264
|
+
def end_element(name)
|
265
|
+
return if USELESS_TAGS.include?(name) || AUTOCLOSING_TAGS.include?(name)
|
266
|
+
@tokens << "</#{name}>"
|
267
|
+
end
|
268
|
+
|
269
|
+
def characters(string)
|
270
|
+
@tokens.concat string.scan(/\W|\w+[ \t]*/).map { |x| CGI::escapeHTML(x) }
|
271
|
+
end
|
272
|
+
|
273
|
+
end
|
274
|
+
end
|
275
|
+
end
|
@@ -0,0 +1,153 @@
|
|
1
|
+
# Use "An O(NP) Sequence Comparison Algorithm" as described by Sun Wu, Udi Manber and Gene Myers
|
2
|
+
# in http://www.itu.dk/stud/speciale/bepjea/xwebtex/litt/an-onp-sequence-comparison-algorithm.pdf
|
3
|
+
class ONPDiff
|
4
|
+
|
5
|
+
def initialize(a, b)
|
6
|
+
@a, @b = a, b
|
7
|
+
@m, @n = a.length, b.length
|
8
|
+
@backtrack = []
|
9
|
+
if @reverse = @m > @n
|
10
|
+
@a, @b = @b, @a
|
11
|
+
@m, @n = @n, @m
|
12
|
+
end
|
13
|
+
@offset = @m + 1
|
14
|
+
@delta = @n - @m
|
15
|
+
end
|
16
|
+
|
17
|
+
def diff
|
18
|
+
@diff ||= build_edit_script(compose)
|
19
|
+
end
|
20
|
+
|
21
|
+
def short_diff
|
22
|
+
@short_diff ||= build_short_edit_script(compose)
|
23
|
+
end
|
24
|
+
|
25
|
+
private
|
26
|
+
|
27
|
+
def compose
|
28
|
+
return @shortest_path if @shortest_path
|
29
|
+
|
30
|
+
size = @m + @n + 3
|
31
|
+
fp = Array.new(size) { |i| -1 }
|
32
|
+
@path = Array.new(size) { |i| -1 }
|
33
|
+
p = -1
|
34
|
+
|
35
|
+
begin
|
36
|
+
p += 1
|
37
|
+
|
38
|
+
k = -p
|
39
|
+
while k <= @delta - 1
|
40
|
+
fp[k + @offset] = snake(k, fp[k - 1 + @offset] + 1, fp[k + 1 + @offset])
|
41
|
+
k += 1
|
42
|
+
end
|
43
|
+
|
44
|
+
k = @delta + p
|
45
|
+
while k >= @delta + 1
|
46
|
+
fp[k + @offset] = snake(k, fp[k - 1 + @offset] + 1, fp[k + 1 + @offset])
|
47
|
+
k -= 1
|
48
|
+
end
|
49
|
+
|
50
|
+
fp[@delta + @offset] = snake(@delta, fp[@delta - 1 + @offset] + 1, fp[@delta + 1 + @offset])
|
51
|
+
|
52
|
+
end until fp[@delta + @offset] == @n
|
53
|
+
|
54
|
+
r = @path[@delta + @offset]
|
55
|
+
|
56
|
+
@shortest_path = []
|
57
|
+
while r != -1
|
58
|
+
@shortest_path << [@backtrack[r][0], @backtrack[r][1]]
|
59
|
+
r = @backtrack[r][2]
|
60
|
+
end
|
61
|
+
|
62
|
+
@shortest_path
|
63
|
+
end
|
64
|
+
|
65
|
+
def snake(k, p, pp)
|
66
|
+
r = p > pp ? @path[k - 1 + @offset] : @path[k + 1 + @offset]
|
67
|
+
y = [p, pp].max
|
68
|
+
x = y - k
|
69
|
+
|
70
|
+
while x < @m && y < @n && @a[x] == @b[y]
|
71
|
+
x += 1
|
72
|
+
y += 1
|
73
|
+
end
|
74
|
+
|
75
|
+
@path[k + @offset] = @backtrack.length
|
76
|
+
@backtrack << [x, y, r]
|
77
|
+
|
78
|
+
y
|
79
|
+
end
|
80
|
+
|
81
|
+
def build_edit_script(shortest_path)
|
82
|
+
ses = []
|
83
|
+
x, y = 1, 1
|
84
|
+
px, py = 0, 0
|
85
|
+
i = shortest_path.length - 1
|
86
|
+
while i >= 0
|
87
|
+
while px < shortest_path[i][0] || py < shortest_path[i][1]
|
88
|
+
if shortest_path[i][1] - shortest_path[i][0] > py - px
|
89
|
+
t = @reverse ? :delete : :add
|
90
|
+
ses << [@b[py], t]
|
91
|
+
y += 1
|
92
|
+
py += 1
|
93
|
+
elsif shortest_path[i][1] - shortest_path[i][0] < py - px
|
94
|
+
t = @reverse ? :add : :delete
|
95
|
+
ses << [@a[px], t]
|
96
|
+
x += 1
|
97
|
+
px += 1
|
98
|
+
else
|
99
|
+
ses << [@a[px], :common]
|
100
|
+
x += 1
|
101
|
+
y += 1
|
102
|
+
px += 1
|
103
|
+
py += 1
|
104
|
+
end
|
105
|
+
end
|
106
|
+
i -= 1
|
107
|
+
end
|
108
|
+
ses
|
109
|
+
end
|
110
|
+
|
111
|
+
def build_short_edit_script(shortest_path)
|
112
|
+
ses = []
|
113
|
+
x, y = 1, 1
|
114
|
+
px, py = 0, 0
|
115
|
+
i = shortest_path.length - 1
|
116
|
+
while i >= 0
|
117
|
+
while px < shortest_path[i][0] || py < shortest_path[i][1]
|
118
|
+
if shortest_path[i][1] - shortest_path[i][0] > py - px
|
119
|
+
t = @reverse ? :delete : :add
|
120
|
+
if ses.length > 0 && ses[-1][1] == t
|
121
|
+
ses[-1][0] << @b[py]
|
122
|
+
else
|
123
|
+
ses << [@b[py], t]
|
124
|
+
end
|
125
|
+
y += 1
|
126
|
+
py += 1
|
127
|
+
elsif shortest_path[i][1] - shortest_path[i][0] < py - px
|
128
|
+
t = @reverse ? :add : :delete
|
129
|
+
if ses.length > 0 && ses[-1][1] == t
|
130
|
+
ses[-1][0] << @a[px]
|
131
|
+
else
|
132
|
+
ses << [@a[px], t]
|
133
|
+
end
|
134
|
+
x += 1
|
135
|
+
px += 1
|
136
|
+
else
|
137
|
+
if ses.length > 0 && ses[-1][1] == :common
|
138
|
+
ses[-1][0] << @a[px]
|
139
|
+
else
|
140
|
+
ses << [@a[px], :common]
|
141
|
+
end
|
142
|
+
x += 1
|
143
|
+
y += 1
|
144
|
+
px += 1
|
145
|
+
py += 1
|
146
|
+
end
|
147
|
+
end
|
148
|
+
i -= 1
|
149
|
+
end
|
150
|
+
ses
|
151
|
+
end
|
152
|
+
|
153
|
+
end
|
metadata
ADDED
@@ -0,0 +1,101 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: discourse-diff
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Discourse
|
8
|
+
- James Kiesel
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2018-05-09 00:00:00.000000000 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: bundler
|
16
|
+
requirement: !ruby/object:Gem::Requirement
|
17
|
+
requirements:
|
18
|
+
- - "~>"
|
19
|
+
- !ruby/object:Gem::Version
|
20
|
+
version: '1.16'
|
21
|
+
type: :development
|
22
|
+
prerelease: false
|
23
|
+
version_requirements: !ruby/object:Gem::Requirement
|
24
|
+
requirements:
|
25
|
+
- - "~>"
|
26
|
+
- !ruby/object:Gem::Version
|
27
|
+
version: '1.16'
|
28
|
+
- !ruby/object:Gem::Dependency
|
29
|
+
name: rake
|
30
|
+
requirement: !ruby/object:Gem::Requirement
|
31
|
+
requirements:
|
32
|
+
- - "~>"
|
33
|
+
- !ruby/object:Gem::Version
|
34
|
+
version: '10.0'
|
35
|
+
type: :development
|
36
|
+
prerelease: false
|
37
|
+
version_requirements: !ruby/object:Gem::Requirement
|
38
|
+
requirements:
|
39
|
+
- - "~>"
|
40
|
+
- !ruby/object:Gem::Version
|
41
|
+
version: '10.0'
|
42
|
+
- !ruby/object:Gem::Dependency
|
43
|
+
name: rspec
|
44
|
+
requirement: !ruby/object:Gem::Requirement
|
45
|
+
requirements:
|
46
|
+
- - ">="
|
47
|
+
- !ruby/object:Gem::Version
|
48
|
+
version: 3.0.0
|
49
|
+
type: :development
|
50
|
+
prerelease: false
|
51
|
+
version_requirements: !ruby/object:Gem::Requirement
|
52
|
+
requirements:
|
53
|
+
- - ">="
|
54
|
+
- !ruby/object:Gem::Version
|
55
|
+
version: 3.0.0
|
56
|
+
description: This library has been extracted from [Discourse core](https://www.github.com/discourse/discourse)
|
57
|
+
email:
|
58
|
+
- contact@discourse.org
|
59
|
+
- james.kiesel@gmail.com
|
60
|
+
executables: []
|
61
|
+
extensions: []
|
62
|
+
extra_rdoc_files: []
|
63
|
+
files:
|
64
|
+
- ".gitignore"
|
65
|
+
- ".travis.yml"
|
66
|
+
- CODE_OF_CONDUCT.md
|
67
|
+
- Gemfile
|
68
|
+
- Gemfile.lock
|
69
|
+
- LICENSE.txt
|
70
|
+
- README.md
|
71
|
+
- Rakefile
|
72
|
+
- bin/console
|
73
|
+
- bin/setup
|
74
|
+
- discourse-diff.gemspec
|
75
|
+
- lib/discourse/diff.rb
|
76
|
+
- lib/discourse/onpdiff.rb
|
77
|
+
homepage:
|
78
|
+
licenses:
|
79
|
+
- MIT
|
80
|
+
metadata: {}
|
81
|
+
post_install_message:
|
82
|
+
rdoc_options: []
|
83
|
+
require_paths:
|
84
|
+
- lib
|
85
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - ">="
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '0'
|
90
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
91
|
+
requirements:
|
92
|
+
- - ">="
|
93
|
+
- !ruby/object:Gem::Version
|
94
|
+
version: '0'
|
95
|
+
requirements: []
|
96
|
+
rubyforge_project:
|
97
|
+
rubygems_version: 2.5.1
|
98
|
+
signing_key:
|
99
|
+
specification_version: 4
|
100
|
+
summary: Discourse Diff provides inline html diffing for markdown blobs
|
101
|
+
test_files: []
|