nokogiri 1.4.4 → 1.4.5

Sign up to get free protection for your applications and to get access to all the features.

Potentially problematic release.

This version of nokogiri might be problematic. Click here for more details.

Files changed (54) hide show
  1. data/.gemtest +0 -0
  2. data/CHANGELOG.ja.rdoc +16 -0
  3. data/CHANGELOG.rdoc +23 -1
  4. data/Manifest.txt +4 -3
  5. data/Rakefile +41 -37
  6. data/ext/nokogiri/xml_document.c +9 -0
  7. data/ext/nokogiri/xml_io.c +32 -7
  8. data/ext/nokogiri/xml_node.c +14 -13
  9. data/ext/nokogiri/xml_sax_parser.c +4 -2
  10. data/ext/nokogiri/xslt_stylesheet.c +9 -3
  11. data/lib/nokogiri/css.rb +6 -3
  12. data/lib/nokogiri/css/parser.rb +665 -70
  13. data/lib/nokogiri/css/parser.y +3 -1
  14. data/lib/nokogiri/css/parser_extras.rb +91 -0
  15. data/lib/nokogiri/css/tokenizer.rb +148 -3
  16. data/lib/nokogiri/css/tokenizer.rex +1 -1
  17. data/lib/nokogiri/ffi/structs/xml_attr.rb +2 -1
  18. data/lib/nokogiri/ffi/structs/xml_node_set.rb +1 -1
  19. data/lib/nokogiri/ffi/weak_bucket.rb +10 -10
  20. data/lib/nokogiri/ffi/xml/document.rb +8 -0
  21. data/lib/nokogiri/ffi/xml/node_set.rb +1 -0
  22. data/lib/nokogiri/ffi/xml/sax/parser.rb +9 -1
  23. data/lib/nokogiri/ffi/xslt/stylesheet.rb +4 -0
  24. data/lib/nokogiri/html/document.rb +134 -15
  25. data/lib/nokogiri/html/sax/parser.rb +6 -2
  26. data/lib/nokogiri/version.rb +6 -1
  27. data/lib/nokogiri/xml/node.rb +8 -23
  28. data/lib/nokogiri/xml/node/save_options.rb +10 -0
  29. data/lib/nokogiri/xml/node_set.rb +1 -1
  30. data/lib/nokogiri/xml/parse_options.rb +8 -0
  31. data/lib/nokogiri/xml/reader.rb +6 -6
  32. data/lib/nokogiri/xml/sax/document.rb +2 -2
  33. data/lib/nokogiri/xml/schema.rb +7 -1
  34. data/tasks/cross_compile.rb +8 -15
  35. data/test/css/test_tokenizer.rb +8 -0
  36. data/test/files/encoding.html +82 -0
  37. data/test/files/encoding.xhtml +84 -0
  38. data/test/helper.rb +2 -0
  39. data/test/html/sax/test_parser.rb +45 -0
  40. data/test/html/test_document.rb +55 -0
  41. data/test/html/test_document_encoding.rb +46 -0
  42. data/test/html/test_element_description.rb +1 -1
  43. data/test/test_memory_leak.rb +20 -0
  44. data/test/test_reader.rb +13 -0
  45. data/test/test_xslt_transforms.rb +6 -2
  46. data/test/xml/sax/test_parser.rb +16 -0
  47. data/test/xml/test_document.rb +3 -1
  48. data/test/xml/test_node.rb +13 -1
  49. data/test/xml/test_node_set.rb +10 -0
  50. data/test/xml/test_schema.rb +5 -0
  51. metadata +94 -109
  52. data/deps.rip +0 -5
  53. data/lib/nokogiri/css/generated_parser.rb +0 -676
  54. data/lib/nokogiri/css/generated_tokenizer.rb +0 -145
data/lib/nokogiri/css/generated_tokenizer.rb DELETED
@@ -1,145 +0,0 @@
1
- #--
2
- # DO NOT MODIFY!!!!
3
- # This file is automatically generated by rex 1.0.4
4
- # from lexical definition file "lib/nokogiri/css/tokenizer.rex".
5
- #++
6
-
7
- module Nokogiri
8
- module CSS
9
- class GeneratedTokenizer < GeneratedParser
10
- require 'strscan'
11
-
12
- class ScanError < StandardError ; end
13
-
14
- attr_reader :lineno
15
- attr_reader :filename
16
- attr_accessor :state
17
-
18
- def scan_setup(str)
19
- @ss = StringScanner.new(str)
20
- @lineno = 1
21
- @state = nil
22
- end
23
-
24
- def action(&block)
25
- yield
26
- end
27
-
28
- def scan_str(str)
29
- scan_setup(str)
30
- do_parse
31
- end
32
-
33
- def load_file( filename )
34
- @filename = filename
35
- open(filename, "r") do |f|
36
- scan_setup(f.read)
37
- end
38
- end
39
-
40
- def scan_file( filename )
41
- load_file(filename)
42
- do_parse
43
- end
44
-
45
-
46
- def next_token
47
- return if @ss.eos?
48
-
49
- text = @ss.peek(1)
50
- @lineno += 1 if text == "\n"
51
- token = case @state
52
- when nil
53
- case
54
- when (text = @ss.scan(/has\([\s]*/))
55
- action { [:HAS, text] }
56
-
57
- when (text = @ss.scan(/[-@]?([_A-Za-z]|[^\0-\177]|\\[0-9A-Fa-f]{1,6}(\r\n|[\s])?|\\[^\n\r\f0-9A-Fa-f])([_A-Za-z0-9-]|[^\0-\177]|\\[0-9A-Fa-f]{1,6}(\r\n|[\s])?|\\[^\n\r\f0-9A-Fa-f])*\([\s]*/))
58
- action { [:FUNCTION, text] }
59
-
60
- when (text = @ss.scan(/[-@]?([_A-Za-z]|[^\0-\177]|\\[0-9A-Fa-f]{1,6}(\r\n|[\s])?|\\[^\n\r\f0-9A-Fa-f])([_A-Za-z0-9-]|[^\0-\177]|\\[0-9A-Fa-f]{1,6}(\r\n|[\s])?|\\[^\n\r\f0-9A-Fa-f])*/))
61
- action { [:IDENT, text] }
62
-
63
- when (text = @ss.scan(/\#([_A-Za-z0-9-]|[^\0-\177]|\\[0-9A-Fa-f]{1,6}(\r\n|[\s])?|\\[^\n\r\f0-9A-Fa-f])+/))
64
- action { [:HASH, text] }
65
-
66
- when (text = @ss.scan(/[\s]*~=[\s]*/))
67
- action { [:INCLUDES, text] }
68
-
69
- when (text = @ss.scan(/[\s]*\|=[\s]*/))
70
- action { [:DASHMATCH, text] }
71
-
72
- when (text = @ss.scan(/[\s]*\^=[\s]*/))
73
- action { [:PREFIXMATCH, text] }
74
-
75
- when (text = @ss.scan(/[\s]*\$=[\s]*/))
76
- action { [:SUFFIXMATCH, text] }
77
-
78
- when (text = @ss.scan(/[\s]*\*=[\s]*/))
79
- action { [:SUBSTRINGMATCH, text] }
80
-
81
- when (text = @ss.scan(/[\s]*!=[\s]*/))
82
- action { [:NOT_EQUAL, text] }
83
-
84
- when (text = @ss.scan(/[\s]*=[\s]*/))
85
- action { [:EQUAL, text] }
86
-
87
- when (text = @ss.scan(/[\s]*\)/))
88
- action { [:RPAREN, text] }
89
-
90
- when (text = @ss.scan(/[\s]*\[[\s]*/))
91
- action { [:LSQUARE, text] }
92
-
93
- when (text = @ss.scan(/[\s]*\]/))
94
- action { [:RSQUARE, text] }
95
-
96
- when (text = @ss.scan(/[\s]*\+[\s]*/))
97
- action { [:PLUS, text] }
98
-
99
- when (text = @ss.scan(/[\s]*>[\s]*/))
100
- action { [:GREATER, text] }
101
-
102
- when (text = @ss.scan(/[\s]*,[\s]*/))
103
- action { [:COMMA, text] }
104
-
105
- when (text = @ss.scan(/[\s]*~[\s]*/))
106
- action { [:TILDE, text] }
107
-
108
- when (text = @ss.scan(/\:not\([\s]*/))
109
- action { [:NOT, text] }
110
-
111
- when (text = @ss.scan(/-?([0-9]+|[0-9]*\.[0-9]+)/))
112
- action { [:NUMBER, text] }
113
-
114
- when (text = @ss.scan(/[\s]*\/\/[\s]*/))
115
- action { [:DOUBLESLASH, text] }
116
-
117
- when (text = @ss.scan(/[\s]*\/[\s]*/))
118
- action { [:SLASH, text] }
119
-
120
- when (text = @ss.scan(/U\+[0-9a-f?]{1,6}(-[0-9a-f]{1,6})?/))
121
- action {[:UNICODE_RANGE, text] }
122
-
123
- when (text = @ss.scan(/[\s]+/))
124
- action { [:S, text] }
125
-
126
- when (text = @ss.scan(/"([^\n\r\f"]|\n|\r\n|\r|\f|[^\0-\177]|\\[0-9A-Fa-f]{1,6}(\r\n|[\s])?|\\[^\n\r\f0-9A-Fa-f])*"|'([^\n\r\f']|\n|\r\n|\r|\f|[^\0-\177]|\\[0-9A-Fa-f]{1,6}(\r\n|[\s])?|\\[^\n\r\f0-9A-Fa-f])*'/))
127
- action { [:STRING, text] }
128
-
129
- when (text = @ss.scan(/./))
130
- action { [text, text] }
131
-
132
- else
133
- text = @ss.string[@ss.pos .. -1]
134
- raise ScanError, "can not match: '" + text + "'"
135
- end # if
136
-
137
- else
138
- raise ScanError, "undefined state: '" + state.to_s + "'"
139
- end # case state
140
- token
141
- end # def next_token
142
-
143
- end # class
144
- end
145
- end