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
|
#
# xml parser
#
class XHTMLParser
rule
target : /* none */
| xml_doc
xml_doc : xml_header extra xml_body
| xml_header xml_body
| xml_body
xml_header : xtag_in element attributes xtag_out
xml_body : tag_from contents tag_to
tag_from : tag_in element attributes tag_out
tag_empty : tag_in element attributes etag_out
tag_to : etag_in element tag_out
attributes : /* none */
| attributes attribute
attribute : attr equal quoted
quoted : quote1 value quote1
| quote2 value quote2
contents : /* none */
| contents content
content : text
| extra
| tag_from contents tag_to
| tag_empty
extra : tag_in ext extra_texts tag_out
extra_texts : /* none */
| extra_texts rem_in remtexts rem_out
| extra_texts exttext
remtexts : remtext
| remtexts remtext
end
---- header ----
#
# generated by racc
#
require 'xhtmlparser.rex'
---- inner ----
---- footer ----
exit if ARGV.size == 0
filename = ARGV.shift
htmlparser = XHTMLParser.new
htmlparser.scan_file filename
|
