rexleparser 0.4.19 → 0.5.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- checksums.yaml.gz.sig +0 -0
- data/lib/rexleparser.rb +91 -113
- data.tar.gz.sig +0 -0
- metadata +2 -2
- metadata.gz.sig +0 -0
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 4fd9dcc1abbf7f2b61bd3d2f86d4e304d14b7356
|
4
|
+
data.tar.gz: ded2e477c2d4f6a634d33fe89a598946366ee9ee
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 5bf24ad6b143d2e89cf8b25b2352b89df9246ed97c59cb48e14b0231348a7750619e9fe3cfc0894220c4f1a980237be3aa5635f704ff84bafb368df102fead72
|
7
|
+
data.tar.gz: 70209b2013bafa24af4667d76647e413caed13b8c66b0fdd8d27ea71d032328ad850e44ac027493bc26029d9602d5a3fdfc2d0082ed3215cdba5e54459281eb5
|
checksums.yaml.gz.sig
CHANGED
Binary file
|
data/lib/rexleparser.rb
CHANGED
@@ -5,154 +5,109 @@
|
|
5
5
|
|
6
6
|
class RexleParser
|
7
7
|
|
8
|
-
attr_reader :instructions, :doctype
|
8
|
+
attr_reader :instructions, :doctype, :to_a
|
9
9
|
|
10
10
|
def initialize(raw_s)
|
11
|
+
|
11
12
|
super()
|
12
13
|
s = raw_s.clone
|
13
14
|
@instructions = s.scan(/<\?([\w-]+) ([^>]+)\?>/)
|
14
15
|
@doctype = s.slice!(/<!DOCTYPE html>\n?/)
|
15
|
-
@a = scan_element(s.strip.gsub(/<\?[^>]+>/,'').split(//))
|
16
|
-
end
|
17
|
-
|
18
|
-
def to_a() @a end
|
19
16
|
|
20
|
-
|
21
|
-
|
22
|
-
|
17
|
+
s2 = s.gsub('<![CDATA[','<!cdata>').gsub(']]>','</!cdata>')
|
18
|
+
@to_a = reverse(parse(s2.strip.gsub(/<\?[^>]+>/,'').reverse))
|
19
|
+
|
23
20
|
end
|
24
21
|
|
22
|
+
|
25
23
|
private
|
26
24
|
|
27
|
-
def scan_a(a)
|
28
|
-
a.inject([]) do |r, x|
|
29
|
-
name, value, attributes, *remaining = x
|
30
|
-
text_remaining = scan_a remaining if remaining
|
31
|
-
r << value.strip << text_remaining if value
|
32
|
-
end
|
33
|
-
end
|
34
|
-
|
35
|
-
def scan_element(a)
|
36
|
-
|
37
|
-
a.shift until a[0] == '<' and a[1] != '/' or a.length < 1
|
38
|
-
|
39
|
-
return unless a.length > 1
|
40
25
|
|
41
|
-
|
26
|
+
def scan_next(r, tagname)
|
42
27
|
|
43
|
-
|
44
|
-
if a[0..1].join == '![' then
|
28
|
+
j = tagname
|
45
29
|
|
46
|
-
|
47
|
-
|
48
|
-
|
49
|
-
|
50
|
-
value << a.shift until a[0..2].join == ']]>' or a.length <= 1
|
51
|
-
a.slice!(0,3)
|
52
|
-
return [name, value, {}]
|
53
|
-
elsif a[0..2].join == '!--' then
|
54
|
-
name = '!-'
|
55
|
-
#<![CDATA[
|
56
|
-
#<!--
|
57
|
-
3.times{ a.shift }
|
58
|
-
value = ''
|
59
|
-
|
60
|
-
value << a.shift until a[0..2].join == '-->' or a.length <= 1
|
61
|
-
a.slice!(0,3)
|
62
|
-
return [name, value, {}]
|
63
|
-
else
|
30
|
+
if (r =~ /^>/) == 0 then
|
31
|
+
|
32
|
+
# end tag match
|
33
|
+
tag = r[/^>[^<]+</]
|
64
34
|
|
65
|
-
|
66
|
-
name << a.shift
|
67
|
-
name << a.shift while a[0] != ' ' and a[0] != '>' and a[0] != '/'
|
35
|
+
if tag[/^>.*[^\/]<$/] then
|
68
36
|
|
69
|
-
|
37
|
+
# is it the end tag to match the start tag?
|
38
|
+
tag = r.slice!(/^>[^<]+</)
|
39
|
+
end_tag = tag[/^>[^>]*#{j}<$/]
|
70
40
|
|
71
|
-
|
72
|
-
|
73
|
-
|
41
|
+
if end_tag then
|
42
|
+
|
43
|
+
j = nil
|
44
|
+
return [:end_tag, end_tag]
|
45
|
+
|
46
|
+
elsif tag[/^>[^>]*\w+<$/] then
|
47
|
+
|
48
|
+
# broken tag found
|
49
|
+
broken_tag = tag
|
50
|
+
return [:child, [nil, [], broken_tag]] if broken_tag
|
51
|
+
else
|
74
52
|
|
75
|
-
|
76
|
-
|
53
|
+
text, tag = tag.sub('>',';tg&').split(/>/,2)
|
54
|
+
r.prepend '>' + tag
|
55
|
+
return [:child, text]
|
56
|
+
end
|
77
57
|
|
78
|
-
|
79
|
-
a.shift(2)
|
58
|
+
else
|
80
59
|
|
81
|
-
|
82
|
-
|
83
|
-
#a.shift until a[0] == '<' or a.length < 1
|
84
|
-
raw_values.strip!
|
60
|
+
# it's a start tag?
|
61
|
+
return [:newnode] if tag[/^>.*[\w!]+\/<$/]
|
85
62
|
|
86
|
-
|
87
|
-
element = [name, nil, attributes]
|
63
|
+
end # end of tag match
|
88
64
|
|
89
|
-
|
90
|
-
return [element, after_text.join]
|
65
|
+
else
|
91
66
|
|
92
|
-
|
67
|
+
# it's a text value
|
68
|
+
text = r.slice!(/[^>]+/)
|
69
|
+
return [:child, text] if text
|
70
|
+
end
|
71
|
+
end
|
93
72
|
|
94
|
-
|
73
|
+
def parse(r, j=nil)
|
95
74
|
|
96
|
-
|
97
|
-
value, attributes = get_value_and_attribs(raw_values)
|
98
|
-
end
|
75
|
+
tag = r.slice!(/^>[^<]+</) if (r =~ /^>[^<]+</) == 0
|
99
76
|
|
100
|
-
|
101
|
-
tag = a[0, name.length + 3].join
|
102
|
-
|
103
|
-
return unless a.length > 0
|
104
|
-
|
105
|
-
children = tag == ("</%s>" % name) ? false : true
|
106
|
-
|
107
|
-
if children == true then
|
77
|
+
if tag[0,3] == '>--' then
|
108
78
|
|
109
|
-
|
110
|
-
|
79
|
+
i = r =~ /<--/
|
80
|
+
tag += r.slice!(0,i+5)
|
81
|
+
# it's a comment tag
|
82
|
+
tagname = '-!'
|
83
|
+
return [">#{tagname}<", [tag[/>--(.*)--!</,1]], ">#{tagname}/<"]
|
84
|
+
end
|
85
|
+
|
86
|
+
tagname = tag[/([\w!]+)\/?<$/,1]
|
111
87
|
|
112
|
-
|
113
|
-
|
114
|
-
|
115
|
-
|
116
|
-
|
117
|
-
return after_text.length >= 1 ? [element, after_text.join] : element
|
88
|
+
# self closing tag?
|
89
|
+
if tag[/^>\/.*#{tagname}<$/] then
|
90
|
+
return [">/#{tagname}<", [], "#{tag.sub(/>\//,'>')}"]
|
91
|
+
end
|
118
92
|
|
119
|
-
|
93
|
+
start_tag, children, end_tag = tag, [], nil
|
120
94
|
|
121
|
-
|
122
|
-
a.slice!(0, name.length + 3) if a[0, name.length + 3].join \
|
123
|
-
== "</%s>" % name
|
124
|
-
after_text = []
|
125
|
-
after_text << a.shift until a[0] == '<' or a.length <= 1
|
95
|
+
until end_tag do
|
126
96
|
|
127
|
-
|
97
|
+
key, res = scan_next r, tagname
|
128
98
|
|
129
|
-
|
99
|
+
case key
|
100
|
+
when :end_tag
|
101
|
+
end_tag = res
|
102
|
+
return [start_tag, children, end_tag]
|
103
|
+
when :child
|
104
|
+
children << res
|
105
|
+
when :newnode
|
106
|
+
children << parse(r, tagname)
|
130
107
|
end
|
131
108
|
end
|
132
109
|
|
133
|
-
|
134
|
-
|
135
|
-
def scan_elements(a, element)
|
136
|
-
r = scan_element(a)
|
137
|
-
|
138
|
-
if r and r[0].is_a?(Array) then
|
139
|
-
element = r.inject(element) {|r,x| r << x} if r
|
140
|
-
elsif r
|
141
|
-
element << r
|
142
|
-
end
|
143
|
-
return a
|
144
|
-
end
|
145
|
-
|
146
|
-
def get_value_and_attribs(raw_values)
|
147
|
-
|
148
|
-
match_found = raw_values.match(/([^>]*)>(.*)/m)
|
149
|
-
|
150
|
-
if match_found then
|
151
|
-
raw_attributes, value = match_found.captures
|
152
|
-
attributes = get_attributes(raw_attributes)
|
153
|
-
end
|
154
|
-
|
155
|
-
[value.gsub('>','>').gsub('<','<'), attributes]
|
110
|
+
[start_tag, children, end_tag]
|
156
111
|
end
|
157
112
|
|
158
113
|
def get_attributes(raw_attributes)
|
@@ -169,4 +124,27 @@ class RexleParser
|
|
169
124
|
|
170
125
|
return r
|
171
126
|
end
|
127
|
+
|
128
|
+
def reverse(raw_obj)
|
129
|
+
|
130
|
+
obj = raw_obj.clone
|
131
|
+
return obj.reverse! if obj.is_a? String
|
132
|
+
|
133
|
+
tag = obj.pop.reverse.sub('!cdata','!-')
|
134
|
+
|
135
|
+
children = obj[-1]
|
136
|
+
|
137
|
+
if children.last.is_a?(String) then
|
138
|
+
ltext ||= ''
|
139
|
+
ltext << children.pop.reverse
|
140
|
+
end
|
141
|
+
|
142
|
+
ltext << children.pop.reverse if children.last.is_a?(String)
|
143
|
+
|
144
|
+
r = children.reverse.map do |x|
|
145
|
+
reverse(x)
|
146
|
+
end
|
147
|
+
|
148
|
+
return [tag[/[!\-\w\[]+/], ltext, get_attributes(tag), *r]
|
149
|
+
end
|
172
150
|
end
|
data.tar.gz.sig
CHANGED
Binary file
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: rexleparser
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.5.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- James Robertson
|
@@ -31,7 +31,7 @@ cert_chain:
|
|
31
31
|
CkjTMLaPwIQI6dsbG4bVJ7/XzL7c8niqJSF7M0yr1+2kUrWFUZMBMrUUxgZxSkjL
|
32
32
|
Cgd76bp2zjiyCw==
|
33
33
|
-----END CERTIFICATE-----
|
34
|
-
date:
|
34
|
+
date: 2015-01-25 00:00:00.000000000 Z
|
35
35
|
dependencies: []
|
36
36
|
description:
|
37
37
|
email: james@r0bertson.co.uk
|
metadata.gz.sig
CHANGED
Binary file
|