rubysl-rexml 1.0.0

Sign up to get free protection for your applications and to get access to all the features.
Files changed (179) hide show
  1. checksums.yaml +7 -0
  2. data/.gitignore +17 -0
  3. data/.travis.yml +8 -0
  4. data/Gemfile +4 -0
  5. data/LICENSE +25 -0
  6. data/README.md +29 -0
  7. data/Rakefile +1 -0
  8. data/lib/rexml/attlistdecl.rb +62 -0
  9. data/lib/rexml/attribute.rb +185 -0
  10. data/lib/rexml/cdata.rb +67 -0
  11. data/lib/rexml/child.rb +96 -0
  12. data/lib/rexml/comment.rb +80 -0
  13. data/lib/rexml/doctype.rb +271 -0
  14. data/lib/rexml/document.rb +230 -0
  15. data/lib/rexml/dtd/attlistdecl.rb +10 -0
  16. data/lib/rexml/dtd/dtd.rb +51 -0
  17. data/lib/rexml/dtd/elementdecl.rb +17 -0
  18. data/lib/rexml/dtd/entitydecl.rb +56 -0
  19. data/lib/rexml/dtd/notationdecl.rb +39 -0
  20. data/lib/rexml/element.rb +1227 -0
  21. data/lib/rexml/encoding.rb +71 -0
  22. data/lib/rexml/encodings/CP-1252.rb +103 -0
  23. data/lib/rexml/encodings/EUC-JP.rb +35 -0
  24. data/lib/rexml/encodings/ICONV.rb +22 -0
  25. data/lib/rexml/encodings/ISO-8859-1.rb +7 -0
  26. data/lib/rexml/encodings/ISO-8859-15.rb +72 -0
  27. data/lib/rexml/encodings/SHIFT-JIS.rb +37 -0
  28. data/lib/rexml/encodings/SHIFT_JIS.rb +1 -0
  29. data/lib/rexml/encodings/UNILE.rb +34 -0
  30. data/lib/rexml/encodings/US-ASCII.rb +30 -0
  31. data/lib/rexml/encodings/UTF-16.rb +35 -0
  32. data/lib/rexml/encodings/UTF-8.rb +18 -0
  33. data/lib/rexml/entity.rb +166 -0
  34. data/lib/rexml/formatters/default.rb +109 -0
  35. data/lib/rexml/formatters/pretty.rb +138 -0
  36. data/lib/rexml/formatters/transitive.rb +56 -0
  37. data/lib/rexml/functions.rb +382 -0
  38. data/lib/rexml/instruction.rb +70 -0
  39. data/lib/rexml/light/node.rb +196 -0
  40. data/lib/rexml/namespace.rb +47 -0
  41. data/lib/rexml/node.rb +75 -0
  42. data/lib/rexml/output.rb +24 -0
  43. data/lib/rexml/parent.rb +166 -0
  44. data/lib/rexml/parseexception.rb +51 -0
  45. data/lib/rexml/parsers/baseparser.rb +503 -0
  46. data/lib/rexml/parsers/lightparser.rb +60 -0
  47. data/lib/rexml/parsers/pullparser.rb +196 -0
  48. data/lib/rexml/parsers/sax2parser.rb +238 -0
  49. data/lib/rexml/parsers/streamparser.rb +46 -0
  50. data/lib/rexml/parsers/treeparser.rb +97 -0
  51. data/lib/rexml/parsers/ultralightparser.rb +56 -0
  52. data/lib/rexml/parsers/xpathparser.rb +698 -0
  53. data/lib/rexml/quickpath.rb +266 -0
  54. data/lib/rexml/rexml.rb +32 -0
  55. data/lib/rexml/sax2listener.rb +97 -0
  56. data/lib/rexml/source.rb +251 -0
  57. data/lib/rexml/streamlistener.rb +92 -0
  58. data/lib/rexml/syncenumerator.rb +33 -0
  59. data/lib/rexml/text.rb +344 -0
  60. data/lib/rexml/undefinednamespaceexception.rb +8 -0
  61. data/lib/rexml/validation/relaxng.rb +559 -0
  62. data/lib/rexml/validation/validation.rb +155 -0
  63. data/lib/rexml/validation/validationexception.rb +9 -0
  64. data/lib/rexml/xmldecl.rb +119 -0
  65. data/lib/rexml/xmltokens.rb +18 -0
  66. data/lib/rexml/xpath.rb +66 -0
  67. data/lib/rexml/xpath_parser.rb +792 -0
  68. data/lib/rubysl/rexml.rb +1 -0
  69. data/lib/rubysl/rexml/version.rb +5 -0
  70. data/rubysl-rexml.gemspec +23 -0
  71. data/spec/attribute/clone_spec.rb +10 -0
  72. data/spec/attribute/element_spec.rb +22 -0
  73. data/spec/attribute/equal_value_spec.rb +17 -0
  74. data/spec/attribute/hash_spec.rb +12 -0
  75. data/spec/attribute/initialize_spec.rb +28 -0
  76. data/spec/attribute/inspect_spec.rb +19 -0
  77. data/spec/attribute/namespace_spec.rb +23 -0
  78. data/spec/attribute/node_type_spec.rb +9 -0
  79. data/spec/attribute/prefix_spec.rb +17 -0
  80. data/spec/attribute/remove_spec.rb +19 -0
  81. data/spec/attribute/to_s_spec.rb +13 -0
  82. data/spec/attribute/to_string_spec.rb +14 -0
  83. data/spec/attribute/value_spec.rb +14 -0
  84. data/spec/attribute/write_spec.rb +22 -0
  85. data/spec/attribute/xpath_spec.rb +19 -0
  86. data/spec/attributes/add_spec.rb +6 -0
  87. data/spec/attributes/append_spec.rb +6 -0
  88. data/spec/attributes/delete_all_spec.rb +30 -0
  89. data/spec/attributes/delete_spec.rb +26 -0
  90. data/spec/attributes/each_attribute_spec.rb +24 -0
  91. data/spec/attributes/each_spec.rb +24 -0
  92. data/spec/attributes/element_reference_spec.rb +18 -0
  93. data/spec/attributes/element_set_spec.rb +25 -0
  94. data/spec/attributes/get_attribute_ns_spec.rb +13 -0
  95. data/spec/attributes/get_attribute_spec.rb +28 -0
  96. data/spec/attributes/initialize_spec.rb +18 -0
  97. data/spec/attributes/length_spec.rb +6 -0
  98. data/spec/attributes/namespaces_spec.rb +5 -0
  99. data/spec/attributes/prefixes_spec.rb +23 -0
  100. data/spec/attributes/shared/add.rb +17 -0
  101. data/spec/attributes/shared/length.rb +12 -0
  102. data/spec/attributes/size_spec.rb +6 -0
  103. data/spec/attributes/to_a_spec.rb +20 -0
  104. data/spec/cdata/clone_spec.rb +9 -0
  105. data/spec/cdata/initialize_spec.rb +24 -0
  106. data/spec/cdata/shared/to_s.rb +11 -0
  107. data/spec/cdata/to_s_spec.rb +6 -0
  108. data/spec/cdata/value_spec.rb +6 -0
  109. data/spec/document/add_element_spec.rb +30 -0
  110. data/spec/document/add_spec.rb +60 -0
  111. data/spec/document/clone_spec.rb +19 -0
  112. data/spec/document/doctype_spec.rb +14 -0
  113. data/spec/document/encoding_spec.rb +21 -0
  114. data/spec/document/expanded_name_spec.rb +15 -0
  115. data/spec/document/new_spec.rb +37 -0
  116. data/spec/document/node_type_spec.rb +7 -0
  117. data/spec/document/root_spec.rb +11 -0
  118. data/spec/document/stand_alone_spec.rb +18 -0
  119. data/spec/document/version_spec.rb +13 -0
  120. data/spec/document/write_spec.rb +38 -0
  121. data/spec/document/xml_decl_spec.rb +14 -0
  122. data/spec/element/add_attribute_spec.rb +40 -0
  123. data/spec/element/add_attributes_spec.rb +21 -0
  124. data/spec/element/add_element_spec.rb +38 -0
  125. data/spec/element/add_namespace_spec.rb +23 -0
  126. data/spec/element/add_text_spec.rb +23 -0
  127. data/spec/element/attribute_spec.rb +16 -0
  128. data/spec/element/attributes_spec.rb +18 -0
  129. data/spec/element/cdatas_spec.rb +23 -0
  130. data/spec/element/clone_spec.rb +28 -0
  131. data/spec/element/comments_spec.rb +20 -0
  132. data/spec/element/delete_attribute_spec.rb +38 -0
  133. data/spec/element/delete_element_spec.rb +50 -0
  134. data/spec/element/delete_namespace_spec.rb +24 -0
  135. data/spec/element/document_spec.rb +17 -0
  136. data/spec/element/each_element_with_attribute_spec.rb +34 -0
  137. data/spec/element/each_element_with_text_spec.rb +30 -0
  138. data/spec/element/get_text_spec.rb +17 -0
  139. data/spec/element/has_attributes_spec.rb +16 -0
  140. data/spec/element/has_elements_spec.rb +17 -0
  141. data/spec/element/has_text_spec.rb +15 -0
  142. data/spec/element/inspect_spec.rb +26 -0
  143. data/spec/element/instructions_spec.rb +20 -0
  144. data/spec/element/namespace_spec.rb +26 -0
  145. data/spec/element/namespaces_spec.rb +31 -0
  146. data/spec/element/new_spec.rb +34 -0
  147. data/spec/element/next_element_spec.rb +18 -0
  148. data/spec/element/node_type_spec.rb +7 -0
  149. data/spec/element/prefixes_spec.rb +22 -0
  150. data/spec/element/previous_element_spec.rb +19 -0
  151. data/spec/element/raw_spec.rb +23 -0
  152. data/spec/element/root_spec.rb +27 -0
  153. data/spec/element/text_spec.rb +45 -0
  154. data/spec/element/texts_spec.rb +15 -0
  155. data/spec/element/whitespace_spec.rb +22 -0
  156. data/spec/node/each_recursive_spec.rb +20 -0
  157. data/spec/node/find_first_recursive_spec.rb +24 -0
  158. data/spec/node/index_in_parent_spec.rb +14 -0
  159. data/spec/node/next_sibling_node_spec.rb +20 -0
  160. data/spec/node/parent_spec.rb +20 -0
  161. data/spec/node/previous_sibling_node_spec.rb +20 -0
  162. data/spec/shared/each_element.rb +35 -0
  163. data/spec/shared/elements_to_a.rb +35 -0
  164. data/spec/text/append_spec.rb +9 -0
  165. data/spec/text/clone_spec.rb +9 -0
  166. data/spec/text/comparison_spec.rb +24 -0
  167. data/spec/text/empty_spec.rb +11 -0
  168. data/spec/text/indent_text_spec.rb +23 -0
  169. data/spec/text/inspect_spec.rb +7 -0
  170. data/spec/text/new_spec.rb +48 -0
  171. data/spec/text/node_type_spec.rb +7 -0
  172. data/spec/text/normalize_spec.rb +7 -0
  173. data/spec/text/read_with_substitution_spec.rb +12 -0
  174. data/spec/text/to_s_spec.rb +17 -0
  175. data/spec/text/unnormalize_spec.rb +7 -0
  176. data/spec/text/value_spec.rb +36 -0
  177. data/spec/text/wrap_spec.rb +20 -0
  178. data/spec/text/write_with_substitution_spec.rb +32 -0
  179. metadata +385 -0
@@ -0,0 +1,71 @@
1
+ # -*- mode: ruby; ruby-indent-level: 2; indent-tabs-mode: t; tab-width: 2 -*- vim: sw=2 ts=2
2
+ module REXML
3
+ module Encoding
4
+ @encoding_methods = {}
5
+ def self.register(enc, &block)
6
+ @encoding_methods[enc] = block
7
+ end
8
+ def self.apply(obj, enc)
9
+ @encoding_methods[enc][obj]
10
+ end
11
+ def self.encoding_method(enc)
12
+ @encoding_methods[enc]
13
+ end
14
+
15
+ # Native, default format is UTF-8, so it is declared here rather than in
16
+ # an encodings/ definition.
17
+ UTF_8 = 'UTF-8'
18
+ UTF_16 = 'UTF-16'
19
+ UNILE = 'UNILE'
20
+
21
+ # ID ---> Encoding name
22
+ attr_reader :encoding
23
+ def encoding=( enc )
24
+ old_verbosity = $VERBOSE
25
+ begin
26
+ $VERBOSE = false
27
+ enc = enc.nil? ? nil : enc.upcase
28
+ return false if defined? @encoding and enc == @encoding
29
+ if enc and enc != UTF_8
30
+ @encoding = enc
31
+ raise ArgumentError, "Bad encoding name #@encoding" unless @encoding =~ /^[\w-]+$/
32
+ @encoding.untaint
33
+ begin
34
+ require 'rexml/encodings/ICONV.rb'
35
+ Encoding.apply(self, "ICONV")
36
+ rescue LoadError, Exception
37
+ begin
38
+ enc_file = File.join( "rexml", "encodings", "#@encoding.rb" )
39
+ require enc_file
40
+ Encoding.apply(self, @encoding)
41
+ rescue LoadError => err
42
+ puts err.message
43
+ raise ArgumentError, "No decoder found for encoding #@encoding. Please install iconv."
44
+ end
45
+ end
46
+ else
47
+ @encoding = UTF_8
48
+ require 'rexml/encodings/UTF-8.rb'
49
+ Encoding.apply(self, @encoding)
50
+ end
51
+ ensure
52
+ $VERBOSE = old_verbosity
53
+ end
54
+ true
55
+ end
56
+
57
+ def check_encoding str
58
+ # We have to recognize UTF-16, LSB UTF-16, and UTF-8
59
+ if str[0] == 0xfe && str[1] == 0xff
60
+ str[0,2] = ""
61
+ return UTF_16
62
+ elsif str[0] == 0xff && str[1] == 0xfe
63
+ str[0,2] = ""
64
+ return UNILE
65
+ end
66
+ str =~ /^\s*<\?xml\s+version\s*=\s*(['"]).*?\1\s+encoding\s*=\s*(["'])(.*?)\2/um
67
+ return $3.upcase if $3
68
+ return UTF_8
69
+ end
70
+ end
71
+ end
@@ -0,0 +1,103 @@
1
+ #
2
+ # This class was contributed by Mikko Tiihonen mikko DOT tiihonen AT hut DOT fi
3
+ #
4
+ module REXML
5
+ module Encoding
6
+ register( "CP-1252" ) do |o|
7
+ class << o
8
+ alias encode encode_cp1252
9
+ alias decode decode_cp1252
10
+ end
11
+ end
12
+
13
+ # Convert from UTF-8
14
+ def encode_cp1252(content)
15
+ array_utf8 = content.unpack('U*')
16
+ array_enc = []
17
+ array_utf8.each do |num|
18
+ case num
19
+ # shortcut first bunch basic characters
20
+ when 0..0xFF; array_enc << num
21
+ # characters added compared to iso-8859-1
22
+ when 0x20AC; array_enc << 0x80 # 0xe2 0x82 0xac
23
+ when 0x201A; array_enc << 0x82 # 0xe2 0x82 0x9a
24
+ when 0x0192; array_enc << 0x83 # 0xc6 0x92
25
+ when 0x201E; array_enc << 0x84 # 0xe2 0x82 0x9e
26
+ when 0x2026; array_enc << 0x85 # 0xe2 0x80 0xa6
27
+ when 0x2020; array_enc << 0x86 # 0xe2 0x80 0xa0
28
+ when 0x2021; array_enc << 0x87 # 0xe2 0x80 0xa1
29
+ when 0x02C6; array_enc << 0x88 # 0xcb 0x86
30
+ when 0x2030; array_enc << 0x89 # 0xe2 0x80 0xb0
31
+ when 0x0160; array_enc << 0x8A # 0xc5 0xa0
32
+ when 0x2039; array_enc << 0x8B # 0xe2 0x80 0xb9
33
+ when 0x0152; array_enc << 0x8C # 0xc5 0x92
34
+ when 0x017D; array_enc << 0x8E # 0xc5 0xbd
35
+ when 0x2018; array_enc << 0x91 # 0xe2 0x80 0x98
36
+ when 0x2019; array_enc << 0x92 # 0xe2 0x80 0x99
37
+ when 0x201C; array_enc << 0x93 # 0xe2 0x80 0x9c
38
+ when 0x201D; array_enc << 0x94 # 0xe2 0x80 0x9d
39
+ when 0x2022; array_enc << 0x95 # 0xe2 0x80 0xa2
40
+ when 0x2013; array_enc << 0x96 # 0xe2 0x80 0x93
41
+ when 0x2014; array_enc << 0x97 # 0xe2 0x80 0x94
42
+ when 0x02DC; array_enc << 0x98 # 0xcb 0x9c
43
+ when 0x2122; array_enc << 0x99 # 0xe2 0x84 0xa2
44
+ when 0x0161; array_enc << 0x9A # 0xc5 0xa1
45
+ when 0x203A; array_enc << 0x9B # 0xe2 0x80 0xba
46
+ when 0x0152; array_enc << 0x9C # 0xc5 0x93
47
+ when 0x017E; array_enc << 0x9E # 0xc5 0xbe
48
+ when 0x0178; array_enc << 0x9F # 0xc5 0xb8
49
+ else
50
+ # all remaining basic characters can be used directly
51
+ if num <= 0xFF
52
+ array_enc << num
53
+ else
54
+ # Numeric entity (&#nnnn;); shard by Stefan Scholl
55
+ array_enc.concat "&\##{num};".unpack('C*')
56
+ end
57
+ end
58
+ end
59
+ array_enc.pack('C*')
60
+ end
61
+
62
+ # Convert to UTF-8
63
+ def decode_cp1252(str)
64
+ array_latin9 = str.unpack('C*')
65
+ array_enc = []
66
+ array_latin9.each do |num|
67
+ case num
68
+ # characters that added compared to iso-8859-1
69
+ when 0x80; array_enc << 0x20AC # 0xe2 0x82 0xac
70
+ when 0x82; array_enc << 0x201A # 0xe2 0x82 0x9a
71
+ when 0x83; array_enc << 0x0192 # 0xc6 0x92
72
+ when 0x84; array_enc << 0x201E # 0xe2 0x82 0x9e
73
+ when 0x85; array_enc << 0x2026 # 0xe2 0x80 0xa6
74
+ when 0x86; array_enc << 0x2020 # 0xe2 0x80 0xa0
75
+ when 0x87; array_enc << 0x2021 # 0xe2 0x80 0xa1
76
+ when 0x88; array_enc << 0x02C6 # 0xcb 0x86
77
+ when 0x89; array_enc << 0x2030 # 0xe2 0x80 0xb0
78
+ when 0x8A; array_enc << 0x0160 # 0xc5 0xa0
79
+ when 0x8B; array_enc << 0x2039 # 0xe2 0x80 0xb9
80
+ when 0x8C; array_enc << 0x0152 # 0xc5 0x92
81
+ when 0x8E; array_enc << 0x017D # 0xc5 0xbd
82
+ when 0x91; array_enc << 0x2018 # 0xe2 0x80 0x98
83
+ when 0x92; array_enc << 0x2019 # 0xe2 0x80 0x99
84
+ when 0x93; array_enc << 0x201C # 0xe2 0x80 0x9c
85
+ when 0x94; array_enc << 0x201D # 0xe2 0x80 0x9d
86
+ when 0x95; array_enc << 0x2022 # 0xe2 0x80 0xa2
87
+ when 0x96; array_enc << 0x2013 # 0xe2 0x80 0x93
88
+ when 0x97; array_enc << 0x2014 # 0xe2 0x80 0x94
89
+ when 0x98; array_enc << 0x02DC # 0xcb 0x9c
90
+ when 0x99; array_enc << 0x2122 # 0xe2 0x84 0xa2
91
+ when 0x9A; array_enc << 0x0161 # 0xc5 0xa1
92
+ when 0x9B; array_enc << 0x203A # 0xe2 0x80 0xba
93
+ when 0x9C; array_enc << 0x0152 # 0xc5 0x93
94
+ when 0x9E; array_enc << 0x017E # 0xc5 0xbe
95
+ when 0x9F; array_enc << 0x0178 # 0xc5 0xb8
96
+ else
97
+ array_enc << num
98
+ end
99
+ end
100
+ array_enc.pack('U*')
101
+ end
102
+ end
103
+ end
@@ -0,0 +1,35 @@
1
+ module REXML
2
+ module Encoding
3
+ begin
4
+ require 'uconv'
5
+
6
+ def decode_eucjp(str)
7
+ Uconv::euctou8(str)
8
+ end
9
+
10
+ def encode_eucjp content
11
+ Uconv::u8toeuc(content)
12
+ end
13
+ rescue LoadError
14
+ require 'nkf'
15
+
16
+ EUCTOU8 = '-Ewm0'
17
+ U8TOEUC = '-Wem0'
18
+
19
+ def decode_eucjp(str)
20
+ NKF.nkf(EUCTOU8, str)
21
+ end
22
+
23
+ def encode_eucjp content
24
+ NKF.nkf(U8TOEUC, content)
25
+ end
26
+ end
27
+
28
+ register("EUC-JP") do |obj|
29
+ class << obj
30
+ alias decode decode_eucjp
31
+ alias encode encode_eucjp
32
+ end
33
+ end
34
+ end
35
+ end
@@ -0,0 +1,22 @@
1
+ require "iconv"
2
+ raise LoadError unless defined? Iconv
3
+
4
+ module REXML
5
+ module Encoding
6
+ def decode_iconv(str)
7
+ Iconv.conv(UTF_8, @encoding, str)
8
+ end
9
+
10
+ def encode_iconv(content)
11
+ Iconv.conv(@encoding, UTF_8, content)
12
+ end
13
+
14
+ register("ICONV") do |obj|
15
+ Iconv.conv(UTF_8, obj.encoding, nil)
16
+ class << obj
17
+ alias decode decode_iconv
18
+ alias encode encode_iconv
19
+ end
20
+ end
21
+ end
22
+ end
@@ -0,0 +1,7 @@
1
+ require 'rexml/encodings/US-ASCII'
2
+
3
+ module REXML
4
+ module Encoding
5
+ register("ISO-8859-1", &encoding_method("US-ASCII"))
6
+ end
7
+ end
@@ -0,0 +1,72 @@
1
+ #
2
+ # This class was contributed by Mikko Tiihonen mikko DOT tiihonen AT hut DOT fi
3
+ #
4
+ module REXML
5
+ module Encoding
6
+ register("ISO-8859-15") do |o|
7
+ alias encode to_iso_8859_15
8
+ alias decode from_iso_8859_15
9
+ end
10
+
11
+ # Convert from UTF-8
12
+ def to_iso_8859_15(content)
13
+ array_utf8 = content.unpack('U*')
14
+ array_enc = []
15
+ array_utf8.each do |num|
16
+ case num
17
+ # shortcut first bunch basic characters
18
+ when 0..0xA3; array_enc << num
19
+ # characters removed compared to iso-8859-1
20
+ when 0xA4; array_enc << '&#164;'
21
+ when 0xA6; array_enc << '&#166;'
22
+ when 0xA8; array_enc << '&#168;'
23
+ when 0xB4; array_enc << '&#180;'
24
+ when 0xB8; array_enc << '&#184;'
25
+ when 0xBC; array_enc << '&#188;'
26
+ when 0xBD; array_enc << '&#189;'
27
+ when 0xBE; array_enc << '&#190;'
28
+ # characters added compared to iso-8859-1
29
+ when 0x20AC; array_enc << 0xA4 # 0xe2 0x82 0xac
30
+ when 0x0160; array_enc << 0xA6 # 0xc5 0xa0
31
+ when 0x0161; array_enc << 0xA8 # 0xc5 0xa1
32
+ when 0x017D; array_enc << 0xB4 # 0xc5 0xbd
33
+ when 0x017E; array_enc << 0xB8 # 0xc5 0xbe
34
+ when 0x0152; array_enc << 0xBC # 0xc5 0x92
35
+ when 0x0153; array_enc << 0xBD # 0xc5 0x93
36
+ when 0x0178; array_enc << 0xBE # 0xc5 0xb8
37
+ else
38
+ # all remaining basic characters can be used directly
39
+ if num <= 0xFF
40
+ array_enc << num
41
+ else
42
+ # Numeric entity (&#nnnn;); shard by Stefan Scholl
43
+ array_enc.concat "&\##{num};".unpack('C*')
44
+ end
45
+ end
46
+ end
47
+ array_enc.pack('C*')
48
+ end
49
+
50
+ # Convert to UTF-8
51
+ def from_iso_8859_15(str)
52
+ array_latin9 = str.unpack('C*')
53
+ array_enc = []
54
+ array_latin9.each do |num|
55
+ case num
56
+ # characters that differ compared to iso-8859-1
57
+ when 0xA4; array_enc << 0x20AC
58
+ when 0xA6; array_enc << 0x0160
59
+ when 0xA8; array_enc << 0x0161
60
+ when 0xB4; array_enc << 0x017D
61
+ when 0xB8; array_enc << 0x017E
62
+ when 0xBC; array_enc << 0x0152
63
+ when 0xBD; array_enc << 0x0153
64
+ when 0xBE; array_enc << 0x0178
65
+ else
66
+ array_enc << num
67
+ end
68
+ end
69
+ array_enc.pack('U*')
70
+ end
71
+ end
72
+ end
@@ -0,0 +1,37 @@
1
+ module REXML
2
+ module Encoding
3
+ begin
4
+ require 'uconv'
5
+
6
+ def decode_sjis content
7
+ Uconv::sjistou8(content)
8
+ end
9
+
10
+ def encode_sjis(str)
11
+ Uconv::u8tosjis(str)
12
+ end
13
+ rescue LoadError
14
+ require 'nkf'
15
+
16
+ SJISTOU8 = '-Swm0x'
17
+ U8TOSJIS = '-Wsm0x'
18
+
19
+ def decode_sjis(str)
20
+ NKF.nkf(SJISTOU8, str)
21
+ end
22
+
23
+ def encode_sjis content
24
+ NKF.nkf(U8TOSJIS, content)
25
+ end
26
+ end
27
+
28
+ b = proc do |obj|
29
+ class << obj
30
+ alias decode decode_sjis
31
+ alias encode encode_sjis
32
+ end
33
+ end
34
+ register("SHIFT-JIS", &b)
35
+ register("SHIFT_JIS", &b)
36
+ end
37
+ end
@@ -0,0 +1 @@
1
+ require 'rexml/encodings/SHIFT-JIS'
@@ -0,0 +1,34 @@
1
+ module REXML
2
+ module Encoding
3
+ def encode_unile content
4
+ array_utf8 = content.unpack("U*")
5
+ array_enc = []
6
+ array_utf8.each do |num|
7
+ if ((num>>16) > 0)
8
+ array_enc << ??
9
+ array_enc << 0
10
+ else
11
+ array_enc << (num & 0xFF)
12
+ array_enc << (num >> 8)
13
+ end
14
+ end
15
+ array_enc.pack('C*')
16
+ end
17
+
18
+ def decode_unile(str)
19
+ array_enc=str.unpack('C*')
20
+ array_utf8 = []
21
+ 0.step(array_enc.size-1, 2){|i|
22
+ array_utf8 << (array_enc.at(i) + array_enc.at(i+1)*0x100)
23
+ }
24
+ array_utf8.pack('U*')
25
+ end
26
+
27
+ register(UNILE) do |obj|
28
+ class << obj
29
+ alias decode decode_unile
30
+ alias encode encode_unile
31
+ end
32
+ end
33
+ end
34
+ end
@@ -0,0 +1,30 @@
1
+ module REXML
2
+ module Encoding
3
+ # Convert from UTF-8
4
+ def encode_ascii content
5
+ array_utf8 = content.unpack('U*')
6
+ array_enc = []
7
+ array_utf8.each do |num|
8
+ if num <= 0x7F
9
+ array_enc << num
10
+ else
11
+ # Numeric entity (&#nnnn;); shard by Stefan Scholl
12
+ array_enc.concat "&\##{num};".unpack('C*')
13
+ end
14
+ end
15
+ array_enc.pack('C*')
16
+ end
17
+
18
+ # Convert to UTF-8
19
+ def decode_ascii(str)
20
+ str.unpack('C*').pack('U*')
21
+ end
22
+
23
+ register("US-ASCII") do |obj|
24
+ class << obj
25
+ alias decode decode_ascii
26
+ alias encode encode_ascii
27
+ end
28
+ end
29
+ end
30
+ end
@@ -0,0 +1,35 @@
1
+ module REXML
2
+ module Encoding
3
+ def encode_utf16 content
4
+ array_utf8 = content.unpack("U*")
5
+ array_enc = []
6
+ array_utf8.each do |num|
7
+ if ((num>>16) > 0)
8
+ array_enc << 0
9
+ array_enc << ??
10
+ else
11
+ array_enc << (num >> 8)
12
+ array_enc << (num & 0xFF)
13
+ end
14
+ end
15
+ array_enc.pack('C*')
16
+ end
17
+
18
+ def decode_utf16(str)
19
+ str = str[2..-1] if /^\376\377/n =~ str
20
+ array_enc=str.unpack('C*')
21
+ array_utf8 = []
22
+ 0.step(array_enc.size-1, 2){|i|
23
+ array_utf8 << (array_enc.at(i+1) + array_enc.at(i)*0x100)
24
+ }
25
+ array_utf8.pack('U*')
26
+ end
27
+
28
+ register(UTF_16) do |obj|
29
+ class << obj
30
+ alias decode decode_utf16
31
+ alias encode encode_utf16
32
+ end
33
+ end
34
+ end
35
+ end