rubysl-rexml 1.0.0 → 2.0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.travis.yml +3 -2
- data/lib/rexml/attlistdecl.rb +56 -56
- data/lib/rexml/attribute.rb +155 -149
- data/lib/rexml/cdata.rb +48 -48
- data/lib/rexml/child.rb +82 -82
- data/lib/rexml/comment.rb +59 -59
- data/lib/rexml/doctype.rb +22 -24
- data/lib/rexml/document.rb +185 -129
- data/lib/rexml/dtd/attlistdecl.rb +7 -7
- data/lib/rexml/dtd/dtd.rb +41 -41
- data/lib/rexml/dtd/elementdecl.rb +13 -13
- data/lib/rexml/dtd/entitydecl.rb +49 -49
- data/lib/rexml/dtd/notationdecl.rb +32 -32
- data/lib/rexml/element.rb +122 -107
- data/lib/rexml/encoding.rb +37 -58
- data/lib/rexml/entity.rb +144 -144
- data/lib/rexml/formatters/default.rb +6 -4
- data/lib/rexml/formatters/pretty.rb +11 -8
- data/lib/rexml/formatters/transitive.rb +4 -3
- data/lib/rexml/functions.rb +33 -21
- data/lib/rexml/instruction.rb +49 -49
- data/lib/rexml/light/node.rb +190 -191
- data/lib/rexml/namespace.rb +39 -39
- data/lib/rexml/node.rb +38 -38
- data/lib/rexml/output.rb +17 -12
- data/lib/rexml/parent.rb +26 -25
- data/lib/rexml/parseexception.rb +4 -4
- data/lib/rexml/parsers/baseparser.rb +90 -61
- data/lib/rexml/parsers/lightparser.rb +41 -43
- data/lib/rexml/parsers/pullparser.rb +1 -1
- data/lib/rexml/parsers/sax2parser.rb +233 -198
- data/lib/rexml/parsers/streamparser.rb +6 -2
- data/lib/rexml/parsers/treeparser.rb +9 -6
- data/lib/rexml/parsers/ultralightparser.rb +40 -40
- data/lib/rexml/parsers/xpathparser.rb +51 -52
- data/lib/rexml/quickpath.rb +247 -248
- data/lib/rexml/rexml.rb +9 -10
- data/lib/rexml/sax2listener.rb +92 -92
- data/lib/rexml/security.rb +27 -0
- data/lib/rexml/source.rb +95 -50
- data/lib/rexml/streamlistener.rb +90 -90
- data/lib/rexml/syncenumerator.rb +3 -4
- data/lib/rexml/text.rb +157 -76
- data/lib/rexml/validation/relaxng.rb +18 -18
- data/lib/rexml/validation/validation.rb +5 -5
- data/lib/rexml/xmldecl.rb +59 -63
- data/lib/rexml/xmltokens.rb +14 -14
- data/lib/rexml/xpath.rb +67 -53
- data/lib/rexml/xpath_parser.rb +49 -38
- data/lib/rubysl/rexml.rb +1 -0
- data/lib/rubysl/rexml/version.rb +1 -1
- data/rubysl-rexml.gemspec +3 -1
- metadata +19 -28
- data/lib/rexml/encodings/CP-1252.rb +0 -103
- data/lib/rexml/encodings/EUC-JP.rb +0 -35
- data/lib/rexml/encodings/ICONV.rb +0 -22
- data/lib/rexml/encodings/ISO-8859-1.rb +0 -7
- data/lib/rexml/encodings/ISO-8859-15.rb +0 -72
- data/lib/rexml/encodings/SHIFT-JIS.rb +0 -37
- data/lib/rexml/encodings/SHIFT_JIS.rb +0 -1
- data/lib/rexml/encodings/UNILE.rb +0 -34
- data/lib/rexml/encodings/US-ASCII.rb +0 -30
- data/lib/rexml/encodings/UTF-16.rb +0 -35
- data/lib/rexml/encodings/UTF-8.rb +0 -18
@@ -1,103 +0,0 @@
|
|
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
|
@@ -1,35 +0,0 @@
|
|
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
|
@@ -1,22 +0,0 @@
|
|
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
|
@@ -1,72 +0,0 @@
|
|
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 << '¤'
|
21
|
-
when 0xA6; array_enc << '¦'
|
22
|
-
when 0xA8; array_enc << '¨'
|
23
|
-
when 0xB4; array_enc << '´'
|
24
|
-
when 0xB8; array_enc << '¸'
|
25
|
-
when 0xBC; array_enc << '¼'
|
26
|
-
when 0xBD; array_enc << '½'
|
27
|
-
when 0xBE; array_enc << '¾'
|
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
|
@@ -1,37 +0,0 @@
|
|
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
|
@@ -1 +0,0 @@
|
|
1
|
-
require 'rexml/encodings/SHIFT-JIS'
|
@@ -1,34 +0,0 @@
|
|
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
|
@@ -1,30 +0,0 @@
|
|
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
|
@@ -1,35 +0,0 @@
|
|
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
|