1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
|
# a markdown translator
#
# The differences between this and original markdown:
# - markdown in inline tags are not processed
# - every line-break in non-tag parts is translated into <br/>
# - nested list elements are not supported
require "rsec"
class LittleMarkdown
include Rsec::Helper
def initialize
@markdown_line_translator = make_markdown_line_translator
@parser = (make_xml_tag_parser | make_char_parser).star.eof
end
def translate src
@stack = []
@charsbuf = ''
@out = ''
@parser.parse! src
flush_chars
@out
end
def flush_chars
@out.<< translate_markdown @charsbuf
@charsbuf = ''
end
def make_char_parser
# care stringscanner's bug, see issues
(/./.r | /\n/).fail('char'){|c| @charsbuf << c}
end
# make a single-line markdown parser
def make_markdown_line_translator
line_text = lazy{line}.map{|tokens|
tokens.empty? ? Rsec::INVALID : tokens.join # filter out empty
}
title = /"[^"]*"|'[^']*'/.r._?{|(s)|
s ? "title=#{s}" : ''
}
img = seq('!['.r >> /[^\]]+/ << '](', /[^\)"']+/, title, ')'){|(txt, path, title)|
"<img src='#{path}' #{title}>#{txt}</img>"
}
link = seq(('['.r >> /[^\]]+/ << ']('), /[^\)"']+/, title, ')'){|(txt, path, title)|
"<a href='#{path}' #{title}>#{txt}</a>"
}
# NOTE strong should be left of em
strong = ('**'.r >> line_text << '**').map{|s|
"<strong>#{s}</strong>"
}
em = ('*'.r >> line_text << '*').map{|s|
"<em>#{s}</em>"
}
code = ('`'.r >> /[^`]+/ << '`').map{|s|
"<code>#{s}</code>"
}
escape = '<'.r{'<'} | '&'.r{'&'} | /\\[\!\`\*\[\]]/.r{|s|s[1]}
text = /[^\!\`\*\[\]]+/
id = seq_(('['.r >> /[^\]]+/ << ']:'), text){|(id, text)|
"<span id='#{id}'>#{text}</span>"
}
line = (img | link | strong | em | code | escape | id | text).star
line.eof.map &:join
end
# pseudo xml tag parser, except <br> and <hr> and <script>
def make_xml_tag_parser
name = /[\w-]+/ # greedy, no need to worry space between first attr
value = /"[^"]*"|'[^']*'/
attr = seq_(name, seq_('=', value)._?)
attrs = /\s*/.r.join(attr)
# use a stack to ensure tag matching
tag_start = seq('<', name, attrs){|res|
@stack.push res[1].downcase
res
}
tag_empty_end = '/>'.r{|res|
@stack.pop
res
}
tag_non_empty_end = seq('>', lazy{content}, '</', name, /\s*\>/){|res|
if @stack.pop == res[3].downcase
res
else
Rsec::INVALID
end
}
special_tag = /\<[bh]r\s*\>/i.r | seq_('<script', attrs, /\>.*?\<\/script\>/)
tag = special_tag | seq(tag_start, (tag_empty_end | tag_non_empty_end))
# xml content
comment = /<!--([^-]|-[^-])*-->/
cdata = /<!\[CDATA\[.*?\]\]>/x
entity = /&(nbsp|lt|gt|amp|cent|pound|yen|euro|sect|copy|reg|trade|#[a-f0-9]{2,4});/i
text = /[^<&]+/
content = (cdata.r | comment | entity | tag | text).star
tag.fail('tag'){|res|
if @charsbuf.end_with? "\n"
flush_chars
@out << res.join
else
@charsbuf << res.join # inline tags
end
}
end
# translate markdown
def translate_markdown str
lines = str.split("\n").chunk{|line|
line[/^(\ {4}|\#{1,6}\ |[\+\-\>]\ |)/]
}.map{|(leading, lines)|
case leading
when ' ' # code
"<pre><code>#{lines.join "\n"}</code></pre>"
when /\#{1,6}/ # headings
hn = "h#{leading.strip.size}"
lines.map! do |line|
line = line.sub(/\#{1,6}/, '')
"<#{hn}>#{@markdown_line_translator.parse! line}</#{hn}>"
end
lines.join
when '> ' # block quote
# TODO nested
lines.map! do |line|
@markdown_line_translator.parse! line[2..-1]
end
"<blockquote>#{lines.join '<br/>'}</blockquote>"
when '+ ' # numbered list
# TODO nested
lines.map! do |line|
"<li>#{@markdown_line_translator.parse! line[2..-1]}</li>"
end
"<ol>#{lines.join}</ol>"
when '- ' # unordered list
# TODO nested
lines.map! do |line|
"<li>#{@markdown_line_translator.parse! line[2..-1]}</li>"
end
"<ul>#{lines.join}</ul>"
else
lines.map! do |line|
@markdown_line_translator.parse! line
end
lines.join "<br/>"
end
}
# add trailing '\n' s
lines.join('<br/>') << ('<br/>' * str[/\n*\Z/].size)
end
end
if __FILE__ == $PROGRAM_NAME
lm = LittleMarkdown.new
puts lm.translate <<-MD
## *a *
<pre a="3">123afd</pre>
** b **
MD
end
|
