tmail_es 1.2.7.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/CHANGES +83 -0
- data/LICENSE +21 -0
- data/NOTES +7 -0
- data/README +182 -0
- data/Rakefile +2 -0
- data/ext/Makefile +20 -0
- data/ext/tmailscanner/tmail/MANIFEST +4 -0
- data/ext/tmailscanner/tmail/depend +1 -0
- data/ext/tmailscanner/tmail/extconf.rb +33 -0
- data/ext/tmailscanner/tmail/tmailscanner.c +614 -0
- data/lib/tmail/Makefile +18 -0
- data/lib/tmail/address.rb +392 -0
- data/lib/tmail/attachments.rb +65 -0
- data/lib/tmail/base64.rb +46 -0
- data/lib/tmail/compat.rb +41 -0
- data/lib/tmail/config.rb +67 -0
- data/lib/tmail/core_extensions.rb +63 -0
- data/lib/tmail/encode.rb +590 -0
- data/lib/tmail/header.rb +962 -0
- data/lib/tmail/index.rb +9 -0
- data/lib/tmail/interface.rb +1162 -0
- data/lib/tmail/loader.rb +3 -0
- data/lib/tmail/mail.rb +578 -0
- data/lib/tmail/mailbox.rb +496 -0
- data/lib/tmail/main.rb +6 -0
- data/lib/tmail/mbox.rb +3 -0
- data/lib/tmail/net.rb +250 -0
- data/lib/tmail/obsolete.rb +132 -0
- data/lib/tmail/parser.rb +1060 -0
- data/lib/tmail/parser.y +416 -0
- data/lib/tmail/port.rb +379 -0
- data/lib/tmail/quoting.rb +164 -0
- data/lib/tmail/require_arch.rb +58 -0
- data/lib/tmail/scanner.rb +49 -0
- data/lib/tmail/scanner_r.rb +261 -0
- data/lib/tmail/stringio.rb +280 -0
- data/lib/tmail/utils.rb +361 -0
- data/lib/tmail/vendor/rchardet-1.3/COPYING +504 -0
- data/lib/tmail/vendor/rchardet-1.3/README +12 -0
- data/lib/tmail/vendor/rchardet-1.3/lib/rchardet/big5freq.rb +927 -0
- data/lib/tmail/vendor/rchardet-1.3/lib/rchardet/big5prober.rb +42 -0
- data/lib/tmail/vendor/rchardet-1.3/lib/rchardet/chardistribution.rb +238 -0
- data/lib/tmail/vendor/rchardet-1.3/lib/rchardet/charsetgroupprober.rb +112 -0
- data/lib/tmail/vendor/rchardet-1.3/lib/rchardet/charsetprober.rb +75 -0
- data/lib/tmail/vendor/rchardet-1.3/lib/rchardet/codingstatemachine.rb +64 -0
- data/lib/tmail/vendor/rchardet-1.3/lib/rchardet/constants.rb +42 -0
- data/lib/tmail/vendor/rchardet-1.3/lib/rchardet/escprober.rb +89 -0
- data/lib/tmail/vendor/rchardet-1.3/lib/rchardet/escsm.rb +244 -0
- data/lib/tmail/vendor/rchardet-1.3/lib/rchardet/eucjpprober.rb +88 -0
- data/lib/tmail/vendor/rchardet-1.3/lib/rchardet/euckrfreq.rb +596 -0
- data/lib/tmail/vendor/rchardet-1.3/lib/rchardet/euckrprober.rb +42 -0
- data/lib/tmail/vendor/rchardet-1.3/lib/rchardet/euctwfreq.rb +430 -0
- data/lib/tmail/vendor/rchardet-1.3/lib/rchardet/euctwprober.rb +42 -0
- data/lib/tmail/vendor/rchardet-1.3/lib/rchardet/gb2312freq.rb +474 -0
- data/lib/tmail/vendor/rchardet-1.3/lib/rchardet/gb2312prober.rb +42 -0
- data/lib/tmail/vendor/rchardet-1.3/lib/rchardet/hebrewprober.rb +289 -0
- data/lib/tmail/vendor/rchardet-1.3/lib/rchardet/jisfreq.rb +570 -0
- data/lib/tmail/vendor/rchardet-1.3/lib/rchardet/jpcntx.rb +229 -0
- data/lib/tmail/vendor/rchardet-1.3/lib/rchardet/langbulgarianmodel.rb +229 -0
- data/lib/tmail/vendor/rchardet-1.3/lib/rchardet/langcyrillicmodel.rb +330 -0
- data/lib/tmail/vendor/rchardet-1.3/lib/rchardet/langgreekmodel.rb +227 -0
- data/lib/tmail/vendor/rchardet-1.3/lib/rchardet/langhebrewmodel.rb +202 -0
- data/lib/tmail/vendor/rchardet-1.3/lib/rchardet/langhungarianmodel.rb +226 -0
- data/lib/tmail/vendor/rchardet-1.3/lib/rchardet/langthaimodel.rb +201 -0
- data/lib/tmail/vendor/rchardet-1.3/lib/rchardet/latin1prober.rb +147 -0
- data/lib/tmail/vendor/rchardet-1.3/lib/rchardet/mbcharsetprober.rb +89 -0
- data/lib/tmail/vendor/rchardet-1.3/lib/rchardet/mbcsgroupprober.rb +45 -0
- data/lib/tmail/vendor/rchardet-1.3/lib/rchardet/mbcssm.rb +542 -0
- data/lib/tmail/vendor/rchardet-1.3/lib/rchardet/sbcharsetprober.rb +124 -0
- data/lib/tmail/vendor/rchardet-1.3/lib/rchardet/sbcsgroupprober.rb +56 -0
- data/lib/tmail/vendor/rchardet-1.3/lib/rchardet/sjisprober.rb +88 -0
- data/lib/tmail/vendor/rchardet-1.3/lib/rchardet/universaldetector.rb +167 -0
- data/lib/tmail/vendor/rchardet-1.3/lib/rchardet/utf8prober.rb +87 -0
- data/lib/tmail/vendor/rchardet-1.3/lib/rchardet.rb +67 -0
- data/lib/tmail/version.rb +40 -0
- data/lib/tmail.rb +6 -0
- data/setup.rb +1482 -0
- data/test/extctrl.rb +6 -0
- data/test/fixtures/apple_unquoted_content_type +44 -0
- data/test/fixtures/inline_attachment.txt +2095 -0
- data/test/fixtures/iso_8859_1_email_without_encoding_and_message_id.txt +16 -0
- data/test/fixtures/mailbox +414 -0
- data/test/fixtures/mailbox.zip +0 -0
- data/test/fixtures/mailbox_without_any_from_or_sender +10 -0
- data/test/fixtures/mailbox_without_from +11 -0
- data/test/fixtures/mailbox_without_return_path +12 -0
- data/test/fixtures/marked_as_iso_8859_1_but_it_is_utf_8.txt +33 -0
- data/test/fixtures/marked_as_utf_8_but_it_is_iso_8859_1.txt +56 -0
- data/test/fixtures/raw_attack_email_with_zero_length_whitespace +29 -0
- data/test/fixtures/raw_base64_decoded_string +0 -0
- data/test/fixtures/raw_base64_email +83 -0
- data/test/fixtures/raw_base64_encoded_string +1 -0
- data/test/fixtures/raw_email +14 -0
- data/test/fixtures/raw_email10 +20 -0
- data/test/fixtures/raw_email11 +34 -0
- data/test/fixtures/raw_email12 +32 -0
- data/test/fixtures/raw_email13 +29 -0
- data/test/fixtures/raw_email2 +114 -0
- data/test/fixtures/raw_email3 +70 -0
- data/test/fixtures/raw_email4 +59 -0
- data/test/fixtures/raw_email5 +19 -0
- data/test/fixtures/raw_email6 +20 -0
- data/test/fixtures/raw_email7 +66 -0
- data/test/fixtures/raw_email8 +47 -0
- data/test/fixtures/raw_email9 +28 -0
- data/test/fixtures/raw_email_bad_time +62 -0
- data/test/fixtures/raw_email_double_at_in_header +14 -0
- data/test/fixtures/raw_email_multiple_from +30 -0
- data/test/fixtures/raw_email_only_attachment +17 -0
- data/test/fixtures/raw_email_quoted_with_0d0a +14 -0
- data/test/fixtures/raw_email_reply +32 -0
- data/test/fixtures/raw_email_simple +11 -0
- data/test/fixtures/raw_email_string_in_date_field +17 -0
- data/test/fixtures/raw_email_trailing_dot +21 -0
- data/test/fixtures/raw_email_with_bad_date +48 -0
- data/test/fixtures/raw_email_with_illegal_boundary +58 -0
- data/test/fixtures/raw_email_with_mimepart_without_content_type +94 -0
- data/test/fixtures/raw_email_with_multipart_mixed_quoted_boundary +50 -0
- data/test/fixtures/raw_email_with_nested_attachment +100 -0
- data/test/fixtures/raw_email_with_partially_quoted_subject +14 -0
- data/test/fixtures/raw_email_with_quoted_attachment_filename +60 -0
- data/test/fixtures/raw_email_with_quoted_illegal_boundary +58 -0
- data/test/fixtures/raw_email_with_wrong_splitted_multibyte_encoded_word_subject +15 -0
- data/test/fixtures/the_only_part_is_a_word_document.txt +425 -0
- data/test/fixtures/unquoted_filename_in_attachment +177 -0
- data/test/kcode.rb +14 -0
- data/test/temp_test_one.rb +46 -0
- data/test/test_address.rb +1216 -0
- data/test/test_attachments.rb +133 -0
- data/test/test_base64.rb +64 -0
- data/test/test_encode.rb +139 -0
- data/test/test_header.rb +1021 -0
- data/test/test_helper.rb +9 -0
- data/test/test_mail.rb +756 -0
- data/test/test_mbox.rb +184 -0
- data/test/test_port.rb +440 -0
- data/test/test_quote.rb +107 -0
- data/test/test_scanner.rb +209 -0
- data/test/test_utils.rb +36 -0
- data/tmail_es.gemspec +35 -0
- metadata +257 -0
@@ -0,0 +1,42 @@
|
|
1
|
+
######################## BEGIN LICENSE BLOCK ########################
|
2
|
+
# The Original Code is Mozilla Communicator client code.
|
3
|
+
#
|
4
|
+
# The Initial Developer of the Original Code is
|
5
|
+
# Netscape Communications Corporation.
|
6
|
+
# Portions created by the Initial Developer are Copyright (C) 1998
|
7
|
+
# the Initial Developer. All Rights Reserved.
|
8
|
+
#
|
9
|
+
# Contributor(s):
|
10
|
+
# Jeff Hodges - port to Ruby
|
11
|
+
# Mark Pilgrim - port to Python
|
12
|
+
#
|
13
|
+
# This library is free software; you can redistribute it and/or
|
14
|
+
# modify it under the terms of the GNU Lesser General Public
|
15
|
+
# License as published by the Free Software Foundation; either
|
16
|
+
# version 2.1 of the License, or (at your option) any later version.
|
17
|
+
#
|
18
|
+
# This library is distributed in the hope that it will be useful,
|
19
|
+
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
20
|
+
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
21
|
+
# Lesser General Public License for more details.
|
22
|
+
#
|
23
|
+
# You should have received a copy of the GNU Lesser General Public
|
24
|
+
# License along with this library; if not, write to the Free Software
|
25
|
+
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
|
26
|
+
# 02110-1301 USA
|
27
|
+
######################### END LICENSE BLOCK #########################
|
28
|
+
|
29
|
+
module CharDet
|
30
|
+
class Big5Prober < MultiByteCharSetProber
|
31
|
+
def initialize
|
32
|
+
super
|
33
|
+
@_mCodingSM = CodingStateMachine.new(Big5SMModel)
|
34
|
+
@_mDistributionAnalyzer = Big5DistributionAnalysis.new()
|
35
|
+
reset()
|
36
|
+
end
|
37
|
+
|
38
|
+
def get_charset_name
|
39
|
+
return "Big5"
|
40
|
+
end
|
41
|
+
end
|
42
|
+
end
|
@@ -0,0 +1,238 @@
|
|
1
|
+
######################## BEGIN LICENSE BLOCK ########################
|
2
|
+
# The Original Code is Mozilla Communicator client code.
|
3
|
+
#
|
4
|
+
# The Initial Developer of the Original Code is
|
5
|
+
# Netscape Communications Corporation.
|
6
|
+
# Portions created by the Initial Developer are Copyright (C) 1998
|
7
|
+
# the Initial Developer. All Rights Reserved.
|
8
|
+
#
|
9
|
+
# Contributor(s)
|
10
|
+
|
11
|
+
# Jeff Hodges
|
12
|
+
# Mark Pilgrim - port to Python
|
13
|
+
#
|
14
|
+
# This library is free software; you can redistribute it and/or
|
15
|
+
# modify it under the terms of the GNU Lesser General Public
|
16
|
+
# License as published by the Free Software Foundation; either
|
17
|
+
# version 2.1 of the License, or (at your option) any later version.
|
18
|
+
#
|
19
|
+
# This library is distributed in the hope that it will be useful,
|
20
|
+
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
21
|
+
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
22
|
+
# Lesser General Public License for more details.
|
23
|
+
#
|
24
|
+
# You should have received a copy of the GNU Lesser General Public
|
25
|
+
# License along with this library; if not, write to the Free Software
|
26
|
+
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
|
27
|
+
# 02110-1301 USA
|
28
|
+
######################### END LICENSE BLOCK #########################
|
29
|
+
|
30
|
+
module CharDet
|
31
|
+
ENOUGH_DATA_THRESHOLD = 1024
|
32
|
+
SURE_YES = 0.99
|
33
|
+
SURE_NO = 0.01
|
34
|
+
|
35
|
+
class CharDistributionAnalysis
|
36
|
+
def initialize
|
37
|
+
@_mCharToFreqOrder = nil # Mapping table to get frequency order from char order (get from GetOrder())
|
38
|
+
@_mTableSize = nil # Size of above table
|
39
|
+
@_mTypicalDistributionRatio = nil # This is a constant value which varies from language to language, used in calculating confidence. See http://www.mozilla.org/projects/intl/UniversalCharsetDetection.html for further detail.
|
40
|
+
reset()
|
41
|
+
end
|
42
|
+
|
43
|
+
def reset
|
44
|
+
# # """reset analyser, clear any state"""
|
45
|
+
@_mDone = false # If this flag is set to constants.True, detection is done and conclusion has been made
|
46
|
+
@_mTotalChars = 0 # Total characters encountered
|
47
|
+
@_mFreqChars = 0 # The number of characters whose frequency order is less than 512
|
48
|
+
end
|
49
|
+
|
50
|
+
def feed(aStr, aCharLen)
|
51
|
+
# # """feed a character with known length"""
|
52
|
+
if aCharLen == 2
|
53
|
+
# we only care about 2-bytes character in our distribution analysis
|
54
|
+
order = get_order(aStr)
|
55
|
+
else
|
56
|
+
order = -1
|
57
|
+
end
|
58
|
+
if order >= 0
|
59
|
+
@_mTotalChars += 1
|
60
|
+
# order is valid
|
61
|
+
if order < @_mTableSize
|
62
|
+
if 512 > @_mCharToFreqOrder[order]
|
63
|
+
@_mFreqChars += 1
|
64
|
+
end
|
65
|
+
end
|
66
|
+
end
|
67
|
+
end
|
68
|
+
|
69
|
+
def get_confidence
|
70
|
+
# """return confidence based on existing data"""
|
71
|
+
# if we didn't receive any character in our consideration range, return negative answer
|
72
|
+
if @_mTotalChars <= 0
|
73
|
+
return SURE_NO
|
74
|
+
end
|
75
|
+
|
76
|
+
if @_mTotalChars != @_mFreqChars
|
77
|
+
r = @_mFreqChars / ((@_mTotalChars - @_mFreqChars) * @_mTypicalDistributionRatio)
|
78
|
+
if r < SURE_YES
|
79
|
+
return r
|
80
|
+
end
|
81
|
+
end
|
82
|
+
|
83
|
+
# normalize confidence (we don't want to be 100% sure)
|
84
|
+
return SURE_YES
|
85
|
+
end
|
86
|
+
|
87
|
+
def got_enough_data
|
88
|
+
# It is not necessary to receive all data to draw conclusion. For charset detection,
|
89
|
+
# certain amount of data is enough
|
90
|
+
return @_mTotalChars > ENOUGH_DATA_THRESHOLD
|
91
|
+
end
|
92
|
+
|
93
|
+
def get_order(aStr)
|
94
|
+
# We do not handle characters based on the original encoding string, but
|
95
|
+
# convert this encoding string to a number, here called order.
|
96
|
+
# This allows multiple encodings of a language to share one frequency table.
|
97
|
+
return -1
|
98
|
+
end
|
99
|
+
end
|
100
|
+
|
101
|
+
class EUCTWDistributionAnalysis < CharDistributionAnalysis
|
102
|
+
def initialize
|
103
|
+
super()
|
104
|
+
@_mCharToFreqOrder = EUCTWCharToFreqOrder
|
105
|
+
@_mTableSize = EUCTW_TABLE_SIZE
|
106
|
+
@_mTypicalDistributionRatio = EUCTW_TYPICAL_DISTRIBUTION_RATIO
|
107
|
+
end
|
108
|
+
|
109
|
+
def get_order(aStr)
|
110
|
+
# for euc-TW encoding, we are interested
|
111
|
+
# first byte range: 0xc4 -- 0xfe
|
112
|
+
# second byte range: 0xa1 -- 0xfe
|
113
|
+
# no validation needed here. State machine has done that
|
114
|
+
if aStr[0..0] >= "\xC4"
|
115
|
+
return 94 * (aStr[0] - 0xC4) + aStr[1] - 0xA1
|
116
|
+
else
|
117
|
+
return -1
|
118
|
+
end
|
119
|
+
end
|
120
|
+
end
|
121
|
+
|
122
|
+
class EUCKRDistributionAnalysis < CharDistributionAnalysis
|
123
|
+
def initialize
|
124
|
+
super()
|
125
|
+
@_mCharToFreqOrder = EUCKRCharToFreqOrder
|
126
|
+
@_mTableSize = EUCKR_TABLE_SIZE
|
127
|
+
@_mTypicalDistributionRatio = EUCKR_TYPICAL_DISTRIBUTION_RATIO
|
128
|
+
end
|
129
|
+
|
130
|
+
def get_order(aStr)
|
131
|
+
# for euc-KR encoding, we are interested
|
132
|
+
# first byte range: 0xb0 -- 0xfe
|
133
|
+
# second byte range: 0xa1 -- 0xfe
|
134
|
+
# no validation needed here. State machine has done that
|
135
|
+
if aStr[0..0] >= "\xB0"
|
136
|
+
return 94 * (aStr[0] - 0xB0) + aStr[1] - 0xA1
|
137
|
+
else
|
138
|
+
return -1
|
139
|
+
end
|
140
|
+
end
|
141
|
+
end
|
142
|
+
|
143
|
+
class GB2312DistributionAnalysis < CharDistributionAnalysis
|
144
|
+
def initialize
|
145
|
+
super()
|
146
|
+
@_mCharToFreqOrder = GB2312CharToFreqOrder
|
147
|
+
@_mTableSize = GB2312_TABLE_SIZE
|
148
|
+
@_mTypicalDistributionRatio = GB2312_TYPICAL_DISTRIBUTION_RATIO
|
149
|
+
end
|
150
|
+
|
151
|
+
def get_order(aStr)
|
152
|
+
# for GB2312 encoding, we are interested
|
153
|
+
# first byte range: 0xb0 -- 0xfe
|
154
|
+
# second byte range: 0xa1 -- 0xfe
|
155
|
+
# no validation needed here. State machine has done that
|
156
|
+
if (aStr[0..0] >= "\xB0") and (aStr[1..1] >= "\xA1")
|
157
|
+
return 94 * (aStr[0] - 0xB0) + aStr[1] - 0xA1
|
158
|
+
else
|
159
|
+
return -1
|
160
|
+
end
|
161
|
+
end
|
162
|
+
end
|
163
|
+
|
164
|
+
class Big5DistributionAnalysis < CharDistributionAnalysis
|
165
|
+
def initialize
|
166
|
+
super
|
167
|
+
@_mCharToFreqOrder = Big5CharToFreqOrder
|
168
|
+
@_mTableSize = BIG5_TABLE_SIZE
|
169
|
+
@_mTypicalDistributionRatio = BIG5_TYPICAL_DISTRIBUTION_RATIO
|
170
|
+
end
|
171
|
+
|
172
|
+
def get_order(aStr)
|
173
|
+
# for big5 encoding, we are interested
|
174
|
+
# first byte range: 0xa4 -- 0xfe
|
175
|
+
# second byte range: 0x40 -- 0x7e , 0xa1 -- 0xfe
|
176
|
+
# no validation needed here. State machine has done that
|
177
|
+
if aStr[0..0] >= "\xA4"
|
178
|
+
if aStr[1..1] >= "\xA1"
|
179
|
+
return 157 * (aStr[0] - 0xA4) + aStr[1] - 0xA1 + 63
|
180
|
+
else
|
181
|
+
return 157 * (aStr[0] - 0xA4) + aStr[1] - 0x40
|
182
|
+
end
|
183
|
+
else
|
184
|
+
return -1
|
185
|
+
end
|
186
|
+
end
|
187
|
+
end
|
188
|
+
|
189
|
+
class SJISDistributionAnalysis < CharDistributionAnalysis
|
190
|
+
def initialize
|
191
|
+
super()
|
192
|
+
@_mCharToFreqOrder = JISCharToFreqOrder
|
193
|
+
@_mTableSize = JIS_TABLE_SIZE
|
194
|
+
@_mTypicalDistributionRatio = JIS_TYPICAL_DISTRIBUTION_RATIO
|
195
|
+
end
|
196
|
+
|
197
|
+
def get_order(aStr)
|
198
|
+
# for sjis encoding, we are interested
|
199
|
+
# first byte range: 0x81 -- 0x9f , 0xe0 -- 0xfe
|
200
|
+
# second byte range: 0x40 -- 0x7e, 0x81 -- oxfe
|
201
|
+
# no validation needed here. State machine has done that
|
202
|
+
aStr = aStr[0..1].join if aStr.class == Array
|
203
|
+
if (aStr[0..0] >= "\x81") and (aStr[0..0] <= "\x9F")
|
204
|
+
order = 188 * (aStr[0] - 0x81)
|
205
|
+
elsif (aStr[0..0] >= "\xE0") and (aStr[0..0] <= "\xEF")
|
206
|
+
order = 188 * (aStr[0] - 0xE0 + 31)
|
207
|
+
else
|
208
|
+
return -1
|
209
|
+
end
|
210
|
+
order = order + aStr[1] - 0x40
|
211
|
+
if aStr[1..1] > "\x7F"
|
212
|
+
order =- 1
|
213
|
+
end
|
214
|
+
return order
|
215
|
+
end
|
216
|
+
end
|
217
|
+
|
218
|
+
class EUCJPDistributionAnalysis < CharDistributionAnalysis
|
219
|
+
def initialize
|
220
|
+
super()
|
221
|
+
@_mCharToFreqOrder = JISCharToFreqOrder
|
222
|
+
@_mTableSize = JIS_TABLE_SIZE
|
223
|
+
@_mTypicalDistributionRatio = JIS_TYPICAL_DISTRIBUTION_RATIO
|
224
|
+
end
|
225
|
+
|
226
|
+
def get_order(aStr)
|
227
|
+
# for euc-JP encoding, we are interested
|
228
|
+
# first byte range: 0xa0 -- 0xfe
|
229
|
+
# second byte range: 0xa1 -- 0xfe
|
230
|
+
# no validation needed here. State machine has done that
|
231
|
+
if aStr[0..0] >= "\xA0"
|
232
|
+
return 94 * (aStr[0] - 0xA1) + aStr[1] - 0xa1
|
233
|
+
else
|
234
|
+
return -1
|
235
|
+
end
|
236
|
+
end
|
237
|
+
end
|
238
|
+
end
|
@@ -0,0 +1,112 @@
|
|
1
|
+
######################## BEGIN LICENSE BLOCK ########################
|
2
|
+
# The Original Code is Mozilla Communicator client code.
|
3
|
+
#
|
4
|
+
# The Initial Developer of the Original Code is
|
5
|
+
# Netscape Communications Corporation.
|
6
|
+
# Portions created by the Initial Developer are Copyright (C) 1998
|
7
|
+
# the Initial Developer. All Rights Reserved.
|
8
|
+
#
|
9
|
+
# Contributor(s)
|
10
|
+
# Jeff Hodges - port to Ruby
|
11
|
+
# Mark Pilgrim - port to Python
|
12
|
+
#
|
13
|
+
# This library is free software; you can redistribute it and/or
|
14
|
+
# modify it under the terms of the GNU Lesser General Public
|
15
|
+
# License as published by the Free Software Foundation; either
|
16
|
+
# version 2.1 of the License, or (at your option) any later version.
|
17
|
+
#
|
18
|
+
# This library is distributed in the hope that it will be useful,
|
19
|
+
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
20
|
+
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
21
|
+
# Lesser General Public License for more details.
|
22
|
+
#
|
23
|
+
# You should have received a copy of the GNU Lesser General Public
|
24
|
+
# License along with this library; if not, write to the Free Software
|
25
|
+
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
|
26
|
+
# 02110-1301 USA
|
27
|
+
######################### END LICENSE BLOCK #########################
|
28
|
+
|
29
|
+
module CharDet
|
30
|
+
class CharSetGroupProber < CharSetProber
|
31
|
+
attr_accessor :_mProbers
|
32
|
+
def initialize
|
33
|
+
super
|
34
|
+
@_mActiveNum = 0
|
35
|
+
@_mProbers = []
|
36
|
+
@_mBestGuessProber = nil
|
37
|
+
end
|
38
|
+
|
39
|
+
def reset
|
40
|
+
super
|
41
|
+
@_mActiveNum = 0
|
42
|
+
|
43
|
+
for prober in @_mProbers
|
44
|
+
if prober
|
45
|
+
prober.reset()
|
46
|
+
prober.active = true
|
47
|
+
@_mActiveNum += 1
|
48
|
+
end
|
49
|
+
end
|
50
|
+
@_mBestGuessProber = nil
|
51
|
+
end
|
52
|
+
|
53
|
+
def get_charset_name
|
54
|
+
if not @_mBestGuessProber
|
55
|
+
get_confidence()
|
56
|
+
return nil unless @_mBestGuessProber
|
57
|
+
# self._mBestGuessProber = self._mProbers[0]
|
58
|
+
end
|
59
|
+
return @_mBestGuessProber.get_charset_name()
|
60
|
+
end
|
61
|
+
|
62
|
+
def feed(aBuf)
|
63
|
+
for prober in @_mProbers
|
64
|
+
next unless prober
|
65
|
+
next unless prober.active
|
66
|
+
st = prober.feed(aBuf)
|
67
|
+
next unless st
|
68
|
+
if st == EFoundIt
|
69
|
+
@_mBestGuessProber = prober
|
70
|
+
return get_state()
|
71
|
+
elsif st == ENotMe
|
72
|
+
prober.active = false
|
73
|
+
@_mActiveNum -= 1
|
74
|
+
if @_mActiveNum <= 0
|
75
|
+
@_mState = ENotMe
|
76
|
+
return get_state()
|
77
|
+
end
|
78
|
+
end
|
79
|
+
end
|
80
|
+
return get_state()
|
81
|
+
end
|
82
|
+
|
83
|
+
def get_confidence()
|
84
|
+
st = get_state()
|
85
|
+
if st == EFoundIt
|
86
|
+
return 0.99
|
87
|
+
elsif st == ENotMe
|
88
|
+
return 0.01
|
89
|
+
end
|
90
|
+
bestConf = 0.0
|
91
|
+
@_mBestGuessProber = nil
|
92
|
+
for prober in @_mProbers
|
93
|
+
next unless prober
|
94
|
+
unless prober.active
|
95
|
+
$stderr << "#{prober.get_charset_name()} not active\n" if $debug
|
96
|
+
next
|
97
|
+
end
|
98
|
+
cf = prober.get_confidence()
|
99
|
+
$stderr << "#{prober.get_charset_name} confidence = #{cf}\n" if $debug
|
100
|
+
if bestConf < cf
|
101
|
+
bestConf = cf
|
102
|
+
@_mBestGuessProber = prober
|
103
|
+
end
|
104
|
+
end
|
105
|
+
return 0.0 unless @_mBestGuessProber
|
106
|
+
return bestConf
|
107
|
+
# else
|
108
|
+
# self._mBestGuessProber = self._mProbers[0]
|
109
|
+
# return self._mBestGuessProber.get_confidence()
|
110
|
+
end
|
111
|
+
end
|
112
|
+
end
|
@@ -0,0 +1,75 @@
|
|
1
|
+
######################## BEGIN LICENSE BLOCK ########################
|
2
|
+
# The Original Code is Mozilla Universal charset detector code.
|
3
|
+
#
|
4
|
+
# The Initial Developer of the Original Code is
|
5
|
+
# Netscape Communications Corporation.
|
6
|
+
# Portions created by the Initial Developer are Copyright (C) 2001
|
7
|
+
# the Initial Developer. All Rights Reserved.
|
8
|
+
#
|
9
|
+
# Contributor(s):
|
10
|
+
# Jeff Hodges - port to Ruby
|
11
|
+
# Mark Pilgrim - port to Python
|
12
|
+
# Shy Shalom - original C code
|
13
|
+
#
|
14
|
+
# This library is free software; you can redistribute it and/or
|
15
|
+
# modify it under the terms of the GNU Lesser General Public
|
16
|
+
# License as published by the Free Software Foundation; either
|
17
|
+
# version 2.1 of the License, or (at your option) any later version.
|
18
|
+
#
|
19
|
+
# This library is distributed in the hope that it will be useful,
|
20
|
+
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
21
|
+
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
22
|
+
# Lesser General Public License for more details.
|
23
|
+
#
|
24
|
+
# You should have received a copy of the GNU Lesser General Public
|
25
|
+
# License along with this library; if not, write to the Free Software
|
26
|
+
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
|
27
|
+
# 02110-1301 USA
|
28
|
+
######################### END LICENSE BLOCK #########################
|
29
|
+
|
30
|
+
module CharDet
|
31
|
+
class CharSetProber
|
32
|
+
attr_accessor :active
|
33
|
+
def initialize
|
34
|
+
end
|
35
|
+
|
36
|
+
def reset
|
37
|
+
@_mState = EDetecting
|
38
|
+
end
|
39
|
+
|
40
|
+
def get_charset_name
|
41
|
+
return nil
|
42
|
+
end
|
43
|
+
|
44
|
+
def feed(aBuf)
|
45
|
+
end
|
46
|
+
|
47
|
+
def get_state
|
48
|
+
return @_mState
|
49
|
+
end
|
50
|
+
|
51
|
+
def get_confidence
|
52
|
+
return 0.0
|
53
|
+
end
|
54
|
+
|
55
|
+
def filter_high_bit_only(aBuf)
|
56
|
+
# DO NOT USE `gsub!`
|
57
|
+
# It will remove all characters from the buffer that is later used by
|
58
|
+
# other probers. This is because gsub! removes data from the instance variable
|
59
|
+
# that will be passed to later probers, while gsub makes a new instance variable
|
60
|
+
# that will not.
|
61
|
+
newBuf = aBuf.gsub(/([\x00-\x7F])+/, ' ')
|
62
|
+
return newBuf
|
63
|
+
end
|
64
|
+
|
65
|
+
def filter_without_english_letters(aBuf)
|
66
|
+
newBuf = aBuf.gsub(/([A-Za-z])+/,' ')
|
67
|
+
return newBuf
|
68
|
+
end
|
69
|
+
|
70
|
+
def filter_with_english_letters(aBuf)
|
71
|
+
# TODO
|
72
|
+
return aBuf
|
73
|
+
end
|
74
|
+
end
|
75
|
+
end
|
@@ -0,0 +1,64 @@
|
|
1
|
+
######################## BEGIN LICENSE BLOCK ########################
|
2
|
+
# The Original Code is mozilla.org code.
|
3
|
+
#
|
4
|
+
# The Initial Developer of the Original Code is
|
5
|
+
# Netscape Communications Corporation.
|
6
|
+
# Portions created by the Initial Developer are Copyright (C) 1998
|
7
|
+
# the Initial Developer. All Rights Reserved.
|
8
|
+
#
|
9
|
+
# Contributor(s):
|
10
|
+
# Jeff Hodges - port to Ruby
|
11
|
+
# Mark Pilgrim - port to Python
|
12
|
+
#
|
13
|
+
# This library is free software; you can redistribute it and/or
|
14
|
+
# modify it under the terms of the GNU Lesser General Public
|
15
|
+
# License as published by the Free Software Foundation; either
|
16
|
+
# version 2.1 of the License, or (at your option) any later version.
|
17
|
+
#
|
18
|
+
# This library is distributed in the hope that it will be useful,
|
19
|
+
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
20
|
+
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
21
|
+
# Lesser General Public License for more details.
|
22
|
+
#
|
23
|
+
# You should have received a copy of the GNU Lesser General Public
|
24
|
+
# License along with this library; if not, write to the Free Software
|
25
|
+
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
|
26
|
+
# 02110-1301 USA
|
27
|
+
######################### END LICENSE BLOCK #########################
|
28
|
+
|
29
|
+
module CharDet
|
30
|
+
class CodingStateMachine
|
31
|
+
def initialize(sm)
|
32
|
+
@_mModel = sm
|
33
|
+
@_mCurrentBytePos = 0
|
34
|
+
@_mCurrentCharLen = 0
|
35
|
+
reset()
|
36
|
+
end
|
37
|
+
|
38
|
+
def reset
|
39
|
+
@_mCurrentState = EStart
|
40
|
+
end
|
41
|
+
|
42
|
+
def next_state(c)
|
43
|
+
# for each byte we get its class
|
44
|
+
# if it is first byte, we also get byte length
|
45
|
+
byteCls = @_mModel['classTable'][c[0]]
|
46
|
+
if @_mCurrentState == EStart
|
47
|
+
@_mCurrentBytePos = 0
|
48
|
+
@_mCurrentCharLen = @_mModel['charLenTable'][byteCls]
|
49
|
+
end
|
50
|
+
# from byte's class and stateTable, we get its next state
|
51
|
+
@_mCurrentState = @_mModel['stateTable'][@_mCurrentState * @_mModel['classFactor'] + byteCls]
|
52
|
+
@_mCurrentBytePos += 1
|
53
|
+
return @_mCurrentState
|
54
|
+
end
|
55
|
+
|
56
|
+
def get_current_charlen
|
57
|
+
return @_mCurrentCharLen
|
58
|
+
end
|
59
|
+
|
60
|
+
def get_coding_state_machine
|
61
|
+
return @_mModel['name']
|
62
|
+
end
|
63
|
+
end
|
64
|
+
end
|
@@ -0,0 +1,42 @@
|
|
1
|
+
######################## BEGIN LICENSE BLOCK ########################
|
2
|
+
# The Original Code is Mozilla Universal charset detector code.
|
3
|
+
#
|
4
|
+
# The Initial Developer of the Original Code is
|
5
|
+
# Netscape Communications Corporation.
|
6
|
+
# Portions created by the Initial Developer are Copyright (C) 2001
|
7
|
+
# the Initial Developer. All Rights Reserved.
|
8
|
+
#
|
9
|
+
# Contributor(s):
|
10
|
+
# Jeff Hodges - port to Ruby
|
11
|
+
# Mark Pilgrim - port to Python
|
12
|
+
# Shy Shalom - original C code
|
13
|
+
#
|
14
|
+
# This library is free software; you can redistribute it and/or
|
15
|
+
# modify it under the terms of the GNU Lesser General Public
|
16
|
+
# License as published by the Free Software Foundation; either
|
17
|
+
# version 2.1 of the License, or (at your option) any later version.
|
18
|
+
#
|
19
|
+
# This library is distributed in the hope that it will be useful,
|
20
|
+
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
21
|
+
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
22
|
+
# Lesser General Public License for more details.
|
23
|
+
#
|
24
|
+
# You should have received a copy of the GNU Lesser General Public
|
25
|
+
# License along with this library; if not, write to the Free Software
|
26
|
+
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
|
27
|
+
# 02110-1301 USA
|
28
|
+
######################### END LICENSE BLOCK #########################
|
29
|
+
|
30
|
+
module CharDet
|
31
|
+
$debug = false
|
32
|
+
|
33
|
+
EDetecting = 0
|
34
|
+
EFoundIt = 1
|
35
|
+
ENotMe = 2
|
36
|
+
|
37
|
+
EStart = 0
|
38
|
+
EError = 1
|
39
|
+
EItsMe = 2
|
40
|
+
|
41
|
+
SHORTCUT_THRESHOLD = 0.95
|
42
|
+
end
|
@@ -0,0 +1,89 @@
|
|
1
|
+
######################## BEGIN LICENSE BLOCK ########################
|
2
|
+
# The Original Code is mozilla.org code.
|
3
|
+
#
|
4
|
+
# The Initial Developer of the Original Code is
|
5
|
+
# Netscape Communications Corporation.
|
6
|
+
# Portions created by the Initial Developer are Copyright (C) 1998
|
7
|
+
# the Initial Developer. All Rights Reserved.
|
8
|
+
#
|
9
|
+
# Contributor(s):
|
10
|
+
# Jeff Hodges - port to Ruby
|
11
|
+
# Mark Pilgrim - port to Python
|
12
|
+
#
|
13
|
+
# This library is free software; you can redistribute it and/or
|
14
|
+
# modify it under the terms of the GNU Lesser General Public
|
15
|
+
# License as published by the Free Software Foundation; either
|
16
|
+
# version 2.1 of the License, or (at your option) any later version.
|
17
|
+
#
|
18
|
+
# This library is distributed in the hope that it will be useful,
|
19
|
+
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
20
|
+
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
21
|
+
# Lesser General Public License for more details.
|
22
|
+
#
|
23
|
+
# You should have received a copy of the GNU Lesser General Public
|
24
|
+
# License along with this library; if not, write to the Free Software
|
25
|
+
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
|
26
|
+
# 02110-1301 USA
|
27
|
+
######################### END LICENSE BLOCK #########################
|
28
|
+
|
29
|
+
module CharDet
|
30
|
+
class EscCharSetProber < CharSetProber
|
31
|
+
def initialize
|
32
|
+
super()
|
33
|
+
@_mCodingSM = [ CodingStateMachine.new(HZSMModel),
|
34
|
+
CodingStateMachine.new(ISO2022CNSMModel),
|
35
|
+
CodingStateMachine.new(ISO2022JPSMModel),
|
36
|
+
CodingStateMachine.new(ISO2022KRSMModel) ]
|
37
|
+
reset()
|
38
|
+
end
|
39
|
+
|
40
|
+
def reset
|
41
|
+
super()
|
42
|
+
for codingSM in @_mCodingSM
|
43
|
+
next if not codingSM
|
44
|
+
codingSM.active = true
|
45
|
+
codingSM.reset()
|
46
|
+
end
|
47
|
+
@_mActiveSM = @_mCodingSM.length
|
48
|
+
@_mDetectedCharset = nil
|
49
|
+
end
|
50
|
+
|
51
|
+
def get_charset_name
|
52
|
+
return @_mDetectedCharset
|
53
|
+
end
|
54
|
+
|
55
|
+
def get_confidence
|
56
|
+
if @_mDetectedCharset
|
57
|
+
return 0.99
|
58
|
+
else
|
59
|
+
return 0.00
|
60
|
+
end
|
61
|
+
end
|
62
|
+
|
63
|
+
def feed(aBuf)
|
64
|
+
aBuf.each_byte do |b|
|
65
|
+
c = b.chr
|
66
|
+
for codingSM in @_mCodingSM
|
67
|
+
next unless codingSM
|
68
|
+
next unless codingSM.active
|
69
|
+
codingState = codingSM.next_state(c)
|
70
|
+
if codingState == EError
|
71
|
+
codingSM.active = false
|
72
|
+
@_mActiveSM -= 1
|
73
|
+
if @_mActiveSM <= 0
|
74
|
+
@_mState = ENotMe
|
75
|
+
return get_state()
|
76
|
+
end
|
77
|
+
elsif codingState == EItsMe
|
78
|
+
@_mState = EFoundIt
|
79
|
+
@_mDetectedCharset = codingSM.get_coding_state_machine()
|
80
|
+
return get_state()
|
81
|
+
end
|
82
|
+
end
|
83
|
+
end
|
84
|
+
return get_state()
|
85
|
+
|
86
|
+
end
|
87
|
+
|
88
|
+
end
|
89
|
+
end
|