html_pretty 0.1.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
data/LICENSE ADDED
@@ -0,0 +1,19 @@
1
+ Copyright (C) 2012 Benjamin Feng
2
+
3
+ Permission is hereby granted, free of charge, to any person obtaining a copy
4
+ of this software and associated documentation files (the "Software"), to deal
5
+ in the Software without restriction, including without limitation the rights
6
+ to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
7
+ copies of the Software, and to permit persons to whom the Software is
8
+ furnished to do so, subject to the following conditions:
9
+
10
+ The above copyright notice and this permission notice shall be included in all
11
+ copies or substantial portions of the Software.
12
+
13
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
14
+ IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
15
+ FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
16
+ AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
17
+ LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
18
+ OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
19
+ SOFTWARE.
data/README.md ADDED
@@ -0,0 +1,2 @@
1
+ html-pretty
2
+ ===========
data/Rakefile ADDED
@@ -0,0 +1,25 @@
1
+ require 'rexml/document'
2
+
3
+
4
+ task :compare do
5
+ dstdir = 'compare'
6
+ srcfile = "#{dstdir}/_orig.html"
7
+ srcstr = IO.read(srcfile)
8
+
9
+ `ruby -Ilib bin/html_pretty #{srcfile} >#{dstdir}/html_pretty.html`
10
+ `htmlbeautifier <#{srcfile} >#{dstdir}/htmlbeautifier.html`
11
+ `tidy -i -q #{srcfile} >#{dstdir}/tidy.html 2>&-`
12
+
13
+ begin
14
+ require 'nokogiri'
15
+ doc = Nokogiri::XML(srcstr, &:noblanks)
16
+ File.open("#{dstdir}/nokogiri.html", 'w'){|f| f.write doc.to_xhtml(:indent => 2)}
17
+ rescue LoadError => e
18
+ $stderr.puts '-- nokogiri not found -- skipping'
19
+ end
20
+
21
+ doc = REXML::Document.new(srcstr)
22
+ File.open("#{dstdir}/rexml.html", 'w'){|f| doc.write f, 2}
23
+ end
24
+
25
+ task :default => :compare
data/bin/html_pretty ADDED
@@ -0,0 +1,10 @@
1
+ #!/usr/bin/env ruby
2
+
3
+
4
+ require 'html_pretty'
5
+
6
+
7
+ input = ARGV[0] ? File.open(ARGV[0]) : $stdin
8
+ output = ARGV[1] ? File.open(ARGV[1], 'w') : $stdout
9
+
10
+ output.write HtmlPretty.run(input.read)
@@ -0,0 +1,3 @@
1
+ module HtmlPretty
2
+ VERSION = '0.1.0'
3
+ end
@@ -0,0 +1,41 @@
1
+ require 'html_pretty/version'
2
+
3
+
4
+ module HtmlPretty
5
+ SPECIAL = /(<!--.*?-->|<script.*?\/script>|<style.*?\/style>)/m
6
+
7
+ # Really bad assumption heavy tidy...
8
+ # Self rolled because other versions have weird errors
9
+ def self.run(html, out='')
10
+ indent = 0
11
+ html.split(SPECIAL).each do |blob|
12
+ if blob.start_with?('<!--!!!-->')
13
+ raise
14
+ elsif blob =~ SPECIAL
15
+ out << " " * indent << blob << "\n"
16
+ else
17
+ blob = blob.gsub(/^[ \t]*\n/, "") # kill blank lines
18
+ blob = blob.gsub(/^[ \t]+/, '') # kill opening whitespace
19
+ blob = blob.gsub(/[ \t]+$/, '') # kill closing whitespace
20
+ blob = blob.gsub(/[ \t]+/, ' ') # collapse all whitespace
21
+ blob = blob.gsub(/<[ \t]+/, '<') # remove whitespace between brackets
22
+ blob = blob.gsub(/[ \t]+>/, '>') # remove whitespace between brackets
23
+ blob.each_line do |line|
24
+ open_tags = line.scan(/<[^\/][^>]*>/).select{|d| d !~ /\/>$/}.size
25
+ close_tags = line.scan(/<\/[^>]*>/).size
26
+ if open_tags > close_tags
27
+ out << " " * indent + line
28
+ indent += open_tags - close_tags
29
+ indent = 0 if indent < 0
30
+ else
31
+ indent += open_tags - close_tags
32
+ indent = 0 if indent < 0
33
+ out << " " * indent + line
34
+ end
35
+ end
36
+ end
37
+ end
38
+
39
+ out
40
+ end
41
+ end
metadata ADDED
@@ -0,0 +1,69 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: html_pretty
3
+ version: !ruby/object:Gem::Version
4
+ version: 0.1.0
5
+ prerelease:
6
+ platform: ruby
7
+ authors:
8
+ - Benjamin Feng
9
+ autorequire:
10
+ bindir: bin
11
+ cert_chain: []
12
+ date: 2013-01-23 00:00:00.000000000 Z
13
+ dependencies:
14
+ - !ruby/object:Gem::Dependency
15
+ name: rspec
16
+ requirement: !ruby/object:Gem::Requirement
17
+ none: false
18
+ requirements:
19
+ - - ! '>='
20
+ - !ruby/object:Gem::Version
21
+ version: 2.0.0
22
+ type: :development
23
+ prerelease: false
24
+ version_requirements: !ruby/object:Gem::Requirement
25
+ none: false
26
+ requirements:
27
+ - - ! '>='
28
+ - !ruby/object:Gem::Version
29
+ version: 2.0.0
30
+ description: html_pretty is yet another HTML prettifier. It purposefully does not
31
+ do parsing or validation.
32
+ email: benjamin.feng@gmail.com
33
+ executables:
34
+ - html_pretty
35
+ extensions: []
36
+ extra_rdoc_files: []
37
+ files:
38
+ - bin/html_pretty
39
+ - lib/html_pretty/version.rb
40
+ - lib/html_pretty.rb
41
+ - LICENSE
42
+ - Rakefile
43
+ - README.md
44
+ homepage: http://github.com/fengb/html_pretty
45
+ licenses: []
46
+ post_install_message:
47
+ rdoc_options: []
48
+ require_paths:
49
+ - lib
50
+ required_ruby_version: !ruby/object:Gem::Requirement
51
+ none: false
52
+ requirements:
53
+ - - ! '>='
54
+ - !ruby/object:Gem::Version
55
+ version: '0'
56
+ required_rubygems_version: !ruby/object:Gem::Requirement
57
+ none: false
58
+ requirements:
59
+ - - ! '>='
60
+ - !ruby/object:Gem::Version
61
+ version: '0'
62
+ requirements: []
63
+ rubyforge_project:
64
+ rubygems_version: 1.8.23
65
+ signing_key:
66
+ specification_version: 3
67
+ summary: Make HTML pretty.
68
+ test_files: []
69
+ has_rdoc: