mislav-remark 0.1.0 → 0.2.0
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/README.markdown +18 -6
- data/Rakefile +2 -2
- data/lib/remark.rb +18 -3
- data/spec/remark_spec.rb +26 -0
- data/spec/sample.html +8 -0
- metadata +2 -2
data/README.markdown
CHANGED
|
@@ -1,17 +1,29 @@
|
|
|
1
|
-
Remark
|
|
2
|
-
|
|
1
|
+
Remark — HTML→Markdown tool
|
|
2
|
+
===========================
|
|
3
3
|
|
|
4
|
-
|
|
4
|
+
<i>Remark</i> parses HTML and delivers proper Markdown.
|
|
5
5
|
|
|
6
6
|
Usage
|
|
7
7
|
-----
|
|
8
8
|
|
|
9
9
|
From command-line:
|
|
10
10
|
|
|
11
|
-
|
|
11
|
+
remark path/to/file.html
|
|
12
|
+
|
|
13
|
+
or by STDIN:
|
|
14
|
+
|
|
15
|
+
echo "..." | remark
|
|
16
|
+
|
|
17
|
+
You can try feeding it a document from the web:
|
|
18
|
+
|
|
19
|
+
curl -s daringfireball.net/projects/markdown/basics | remark > result.markdown
|
|
12
20
|
|
|
13
|
-
|
|
21
|
+
See how it does.
|
|
22
|
+
|
|
23
|
+
If you've cloned the repository, invoke the binary like this:
|
|
24
|
+
|
|
25
|
+
ruby -Ilib -rubygems bin/remark spec/sample.html
|
|
14
26
|
|
|
15
|
-
|
|
27
|
+
And this is how you use it from Ruby code:
|
|
16
28
|
|
|
17
29
|
Remark.new('<h1>My document</h1><p>Some content</p>').to_markdown
|
data/Rakefile
CHANGED
|
@@ -8,8 +8,8 @@ task :gemspec do
|
|
|
8
8
|
gem.authors = ["Mislav Marohnić"]
|
|
9
9
|
gem.has_rdoc = false
|
|
10
10
|
|
|
11
|
-
gem.version = '0.
|
|
12
|
-
gem.files = FileList['Rakefile', '{bin,lib,rails,spec}/**/*', 'README*', 'LICENSE*']
|
|
11
|
+
gem.version = '0.2.0'
|
|
12
|
+
gem.files = FileList['Rakefile', '{bin,lib,rails,spec}/**/*', 'README*', 'LICENSE*'] & `git ls-files`.split("\n")
|
|
13
13
|
gem.executables = Dir['bin/*'].map { |f| File.basename(f) }
|
|
14
14
|
end
|
|
15
15
|
|
data/lib/remark.rb
CHANGED
|
@@ -6,7 +6,20 @@ class Remark
|
|
|
6
6
|
end
|
|
7
7
|
|
|
8
8
|
def to_markdown
|
|
9
|
-
remark_children(
|
|
9
|
+
remark_children(scope).join("\n\n")
|
|
10
|
+
end
|
|
11
|
+
|
|
12
|
+
def scope
|
|
13
|
+
if body = @doc.at('/html/body')
|
|
14
|
+
candidates = (body / 'p').inject(Hash.new(0)) do |memo, para|
|
|
15
|
+
memo[para.parent] += 1
|
|
16
|
+
memo
|
|
17
|
+
end.invert
|
|
18
|
+
|
|
19
|
+
candidates[candidates.keys.max]
|
|
20
|
+
else
|
|
21
|
+
@doc
|
|
22
|
+
end
|
|
10
23
|
end
|
|
11
24
|
|
|
12
25
|
IGNORE = %w(script head style)
|
|
@@ -35,7 +48,7 @@ class Remark
|
|
|
35
48
|
|
|
36
49
|
def remark_item(item)
|
|
37
50
|
if item.text?
|
|
38
|
-
item.to_s.gsub(/\n+/, ' ') unless item.to_s =~
|
|
51
|
+
item.to_s.gsub(/\n+/, ' ') unless item.to_s =~ /\A\s*\Z/
|
|
39
52
|
elsif item.elem?
|
|
40
53
|
if IGNORE.include?(item.name)
|
|
41
54
|
nil
|
|
@@ -71,6 +84,8 @@ class Remark
|
|
|
71
84
|
'!' + remark_link(elem.attributes['alt'], elem.attributes['src'], elem.attributes['title'])
|
|
72
85
|
when 'blockquote'
|
|
73
86
|
remark_children(elem).join("\n\n").gsub(/^/, '> ')
|
|
87
|
+
when 'br'
|
|
88
|
+
' ' + elem.inner_html
|
|
74
89
|
else
|
|
75
90
|
elem
|
|
76
91
|
end
|
|
@@ -82,7 +97,7 @@ class Remark
|
|
|
82
97
|
end
|
|
83
98
|
|
|
84
99
|
def remark_inline(elem)
|
|
85
|
-
remark_children(elem).join('')
|
|
100
|
+
remark_children(elem).join('').gsub(/\s{2,}/, ' ')
|
|
86
101
|
end
|
|
87
102
|
|
|
88
103
|
def remark_list(list)
|
data/spec/remark_spec.rb
CHANGED
|
@@ -92,5 +92,31 @@ describe Remark do
|
|
|
92
92
|
remark("<img src='moo.jpg' alt='cow'>").should == ''
|
|
93
93
|
remark("<img src='moo.jpg' alt='cow' width='16'>").should == '<img src="moo.jpg" alt="cow" width="16" />'
|
|
94
94
|
end
|
|
95
|
+
|
|
96
|
+
it "should not have BR ruin all the fun" do
|
|
97
|
+
remark("<p>Foo<br>bar</p>").should == 'Foo bar'
|
|
98
|
+
remark("<p>Foo<br>\nbar <code>baz</code></p>").should == 'Foo bar `baz`'
|
|
99
|
+
end
|
|
100
|
+
|
|
101
|
+
it "should scope to the most likely element that holds content" do
|
|
102
|
+
remark(<<-HTML).should == "Wow, 3 paragraphs\n\nThis must be where the content is\n\nI'm sure"
|
|
103
|
+
<html>
|
|
104
|
+
<body>
|
|
105
|
+
<div id="div1">
|
|
106
|
+
<p>Only 1 paragraph</p>
|
|
107
|
+
</div>
|
|
108
|
+
<div id="div3">
|
|
109
|
+
<p>Wow, 3 paragraphs</p>
|
|
110
|
+
<p>This must be where the content is</p>
|
|
111
|
+
<p>I'm sure</p>
|
|
112
|
+
</div>
|
|
113
|
+
<div id="div2">
|
|
114
|
+
<p>Only 2 paragraphs</p>
|
|
115
|
+
<p>How disappointing</p>
|
|
116
|
+
</div>
|
|
117
|
+
</body>
|
|
118
|
+
</html>
|
|
119
|
+
HTML
|
|
120
|
+
end
|
|
95
121
|
end
|
|
96
122
|
|
data/spec/sample.html
CHANGED
|
@@ -29,6 +29,14 @@ Markdown doesn't have a syntax for them.</p>
|
|
|
29
29
|
<pre><code>And who would forget
|
|
30
30
|
Preformatted code blocks :)</code></pre>
|
|
31
31
|
|
|
32
|
+
<p>Notice how it handles <img src="moo.jpg" alt="images" title="Awesum img"> in a nice way.</p>
|
|
33
|
+
|
|
34
|
+
<blockquote>
|
|
35
|
+
<p>I think</p>
|
|
36
|
+
|
|
37
|
+
<p>therefore I am</p>
|
|
38
|
+
</blockquote>
|
|
39
|
+
|
|
32
40
|
<h2>TODO</h2>
|
|
33
41
|
|
|
34
42
|
<p>Remark should probably support BR elements in paragraphs,<br>
|
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: mislav-remark
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.
|
|
4
|
+
version: 0.2.0
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- "Mislav Marohni\xC4\x87"
|
|
@@ -9,7 +9,7 @@ autorequire:
|
|
|
9
9
|
bindir: bin
|
|
10
10
|
cert_chain: []
|
|
11
11
|
|
|
12
|
-
date: 2009-06-
|
|
12
|
+
date: 2009-06-24 00:00:00 -07:00
|
|
13
13
|
default_executable: remark
|
|
14
14
|
dependencies: []
|
|
15
15
|
|