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
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
|
#
# scanner_r.rb
#
# Copyright (c) 1998-2003 Minero Aoki <aamine@loveruby.net>
#
# This program is free software.
# You can distribute/modify this program under the terms of
# the GNU Lesser General Public License version 2 or later.
#
require 'tmail/config'
module TMail
class Scanner_R
Version = '0.10.7'
Version.freeze
MIME_HEADERS = {
:CTYPE => true,
:CENCODING => true,
:CDISPOSITION => true
}
alnum = 'a-zA-Z0-9'
atomsyms = %q[ _#!$%&`'*+-{|}~^/=? ].strip
tokensyms = %q[ _#!$%&`'*+-{|}~^. ].strip
atomchars = alnum + Regexp.quote(atomsyms)
tokenchars = alnum + Regexp.quote(tokensyms)
iso2022str = '\e(?!\(B)..(?:[^\e]+|\e(?!\(B)..)*\e\(B'
eucstr = '(?:[\xa1-\xfe][\xa1-\xfe])+'
sjisstr = '(?:[\x81-\x9f\xe0-\xef][\x40-\x7e\x80-\xfc])+'
utf8str = '(?:[\xc0-\xdf][\x80-\xbf]|[\xe0-\xef][\x80-\xbf][\x80-\xbf])+'
quoted_with_iso2022 = /\A(?:[^\\\e"]+|#{iso2022str})+/n
domlit_with_iso2022 = /\A(?:[^\\\e\]]+|#{iso2022str})+/n
comment_with_iso2022 = /\A(?:[^\\\e()]+|#{iso2022str})+/n
quoted_without_iso2022 = /\A[^\\"]+/n
domlit_without_iso2022 = /\A[^\\\]]+/n
comment_without_iso2022 = /\A[^\\()]+/n
PATTERN_TABLE = {}
PATTERN_TABLE['EUC'] =
[
/\A(?:[#{atomchars}]+|#{iso2022str}|#{eucstr})+/n,
/\A(?:[#{tokenchars}]+|#{iso2022str}|#{eucstr})+/n,
quoted_with_iso2022,
domlit_with_iso2022,
comment_with_iso2022
]
PATTERN_TABLE['SJIS'] =
[
/\A(?:[#{atomchars}]+|#{iso2022str}|#{sjisstr})+/n,
/\A(?:[#{tokenchars}]+|#{iso2022str}|#{sjisstr})+/n,
quoted_with_iso2022,
domlit_with_iso2022,
comment_with_iso2022
]
PATTERN_TABLE['UTF8'] =
[
/\A(?:[#{atomchars}]+|#{utf8str})+/n,
/\A(?:[#{tokenchars}]+|#{utf8str})+/n,
quoted_without_iso2022,
domlit_without_iso2022,
comment_without_iso2022
]
PATTERN_TABLE['NONE'] =
[
/\A[#{atomchars}]+/n,
/\A[#{tokenchars}]+/n,
quoted_without_iso2022,
domlit_without_iso2022,
comment_without_iso2022
]
def initialize( str, scantype, comments )
init_scanner str
@comments = comments || []
@debug = false
# fix scanner mode
@received = (scantype == :RECEIVED)
@is_mime_header = MIME_HEADERS[scantype]
atom, token, @quoted_re, @domlit_re, @comment_re = PATTERN_TABLE[$KCODE]
@word_re = (MIME_HEADERS[scantype] ? token : atom)
end
attr_accessor :debug
def scan( &block )
if @debug
scan_main do |arr|
s, v = arr
printf "%7d %-10s %s\n",
rest_size(),
s.respond_to?(:id2name) ? s.id2name : s.inspect,
v.inspect
yield arr
end
else
scan_main(&block)
end
end
private
RECV_TOKEN = {
'from' => :FROM,
'by' => :BY,
'via' => :VIA,
'with' => :WITH,
'id' => :ID,
'for' => :FOR
}
def scan_main
until eof?
if skip(/\A[\n\r\t ]+/n) # LWSP
break if eof?
end
if s = readstr(@word_re)
if @is_mime_header
yield :TOKEN, s
else
# atom
if /\A\d+\z/ === s
yield :DIGIT, s
elsif @received
yield RECV_TOKEN[s.downcase] || :ATOM, s
else
yield :ATOM, s
end
end
elsif skip(/\A"/)
yield :QUOTED, scan_quoted_word()
elsif skip(/\A\[/)
yield :DOMLIT, scan_domain_literal()
elsif skip(/\A\(/)
@comments.push scan_comment()
else
c = readchar()
yield c, c
end
end
yield false, '$'
end
def scan_quoted_word
scan_qstr(@quoted_re, /\A"/, 'quoted-word')
end
def scan_domain_literal
'[' + scan_qstr(@domlit_re, /\A\]/, 'domain-literal') + ']'
end
def scan_qstr( pattern, terminal, type )
result = ''
until eof?
if s = readstr(pattern) then result << s
elsif skip(terminal) then return result
elsif skip(/\A\\/) then result << readchar()
else
raise "TMail FATAL: not match in #{type}"
end
end
scan_error! "found unterminated #{type}"
end
def scan_comment
result = ''
nest = 1
content = @comment_re
until eof?
if s = readstr(content) then result << s
elsif skip(/\A\)/) then nest -= 1
return result if nest == 0
result << ')'
elsif skip(/\A\(/) then nest += 1
result << '('
elsif skip(/\A\\/) then result << readchar()
else
raise 'TMail FATAL: not match in comment'
end
end
scan_error! 'found unterminated comment'
end
# string scanner
def init_scanner( str )
@src = str
end
def eof?
@src.empty?
end
def rest_size
@src.size
end
def readstr( re )
if m = re.match(@src)
@src = m.post_match
m[0]
else
nil
end
end
def readchar
readstr(/\A./)
end
def skip( re )
if m = re.match(@src)
@src = m.post_match
true
else
false
end
end
def scan_error!( msg )
raise SyntaxError, msg
end
end
end # module TMail
|
