lg_pod_plugin 1.0.4 → 1.0.7
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/lib/git/author.rb +14 -0
- data/lib/git/base/factory.rb +101 -0
- data/lib/git/base.rb +670 -0
- data/lib/git/branch.rb +126 -0
- data/lib/git/branches.rb +71 -0
- data/lib/git/config.rb +22 -0
- data/lib/git/diff.rb +155 -0
- data/lib/git/encoding_utils.rb +33 -0
- data/lib/git/escaped_path.rb +77 -0
- data/lib/git/index.rb +5 -0
- data/lib/git/lib.rb +1215 -0
- data/lib/git/log.rb +135 -0
- data/lib/git/object.rb +312 -0
- data/lib/git/path.rb +31 -0
- data/lib/git/remote.rb +36 -0
- data/lib/git/repository.rb +6 -0
- data/lib/git/stash.rb +27 -0
- data/lib/git/stashes.rb +55 -0
- data/lib/git/status.rb +199 -0
- data/lib/git/url.rb +127 -0
- data/lib/git/version.rb +5 -0
- data/lib/git/working_directory.rb +4 -0
- data/lib/git/worktree.rb +38 -0
- data/lib/git/worktrees.rb +47 -0
- data/lib/git.rb +326 -0
- data/lib/lg_pod_plugin/database.rb +104 -104
- data/lib/lg_pod_plugin/{download.rb → downloader.rb} +1 -1
- data/lib/lg_pod_plugin/file_path.rb +1 -1
- data/lib/lg_pod_plugin/git_util.rb +163 -50
- data/lib/lg_pod_plugin/install.rb +27 -21
- data/lib/lg_pod_plugin/l_cache.rb +13 -14
- data/lib/lg_pod_plugin/l_util.rb +39 -0
- data/lib/lg_pod_plugin/request.rb +37 -12
- data/lib/lg_pod_plugin/version.rb +1 -1
- data/lib/lg_pod_plugin.rb +1 -3
- data/lib/rchardet/big5freq.rb +927 -0
- data/lib/rchardet/big5prober.rb +42 -0
- data/lib/rchardet/chardistribution.rb +250 -0
- data/lib/rchardet/charsetgroupprober.rb +110 -0
- data/lib/rchardet/charsetprober.rb +70 -0
- data/lib/rchardet/codingstatemachine.rb +67 -0
- data/lib/rchardet/constants.rb +42 -0
- data/lib/rchardet/escprober.rb +90 -0
- data/lib/rchardet/escsm.rb +245 -0
- data/lib/rchardet/eucjpprober.rb +88 -0
- data/lib/rchardet/euckrfreq.rb +597 -0
- data/lib/rchardet/euckrprober.rb +42 -0
- data/lib/rchardet/euctwfreq.rb +431 -0
- data/lib/rchardet/euctwprober.rb +42 -0
- data/lib/rchardet/gb18030freq.rb +474 -0
- data/lib/rchardet/gb18030prober.rb +42 -0
- data/lib/rchardet/hebrewprober.rb +289 -0
- data/lib/rchardet/jisfreq.rb +571 -0
- data/lib/rchardet/jpcntx.rb +229 -0
- data/lib/rchardet/langbulgarianmodel.rb +229 -0
- data/lib/rchardet/langcyrillicmodel.rb +330 -0
- data/lib/rchardet/langgreekmodel.rb +227 -0
- data/lib/rchardet/langhebrewmodel.rb +202 -0
- data/lib/rchardet/langhungarianmodel.rb +226 -0
- data/lib/rchardet/langthaimodel.rb +201 -0
- data/lib/rchardet/latin1prober.rb +147 -0
- data/lib/rchardet/mbcharsetprober.rb +89 -0
- data/lib/rchardet/mbcsgroupprober.rb +47 -0
- data/lib/rchardet/mbcssm.rb +542 -0
- data/lib/rchardet/sbcharsetprober.rb +122 -0
- data/lib/rchardet/sbcsgroupprober.rb +58 -0
- data/lib/rchardet/sjisprober.rb +88 -0
- data/lib/rchardet/universaldetector.rb +179 -0
- data/lib/rchardet/utf8prober.rb +87 -0
- data/lib/rchardet/version.rb +3 -0
- data/lib/rchardet.rb +67 -0
- data/lib/zip/central_directory.rb +212 -0
- data/lib/zip/compressor.rb +9 -0
- data/lib/zip/constants.rb +115 -0
- data/lib/zip/crypto/decrypted_io.rb +40 -0
- data/lib/zip/crypto/encryption.rb +11 -0
- data/lib/zip/crypto/null_encryption.rb +43 -0
- data/lib/zip/crypto/traditional_encryption.rb +99 -0
- data/lib/zip/decompressor.rb +31 -0
- data/lib/zip/deflater.rb +34 -0
- data/lib/zip/dos_time.rb +53 -0
- data/lib/zip/entry.rb +719 -0
- data/lib/zip/entry_set.rb +88 -0
- data/lib/zip/errors.rb +19 -0
- data/lib/zip/extra_field/generic.rb +44 -0
- data/lib/zip/extra_field/ntfs.rb +94 -0
- data/lib/zip/extra_field/old_unix.rb +46 -0
- data/lib/zip/extra_field/universal_time.rb +77 -0
- data/lib/zip/extra_field/unix.rb +39 -0
- data/lib/zip/extra_field/zip64.rb +70 -0
- data/lib/zip/extra_field/zip64_placeholder.rb +15 -0
- data/lib/zip/extra_field.rb +103 -0
- data/lib/zip/file.rb +468 -0
- data/lib/zip/filesystem.rb +643 -0
- data/lib/zip/inflater.rb +54 -0
- data/lib/zip/input_stream.rb +180 -0
- data/lib/zip/ioextras/abstract_input_stream.rb +122 -0
- data/lib/zip/ioextras/abstract_output_stream.rb +43 -0
- data/lib/zip/ioextras.rb +36 -0
- data/lib/zip/null_compressor.rb +15 -0
- data/lib/zip/null_decompressor.rb +19 -0
- data/lib/zip/null_input_stream.rb +10 -0
- data/lib/zip/output_stream.rb +198 -0
- data/lib/zip/pass_thru_compressor.rb +23 -0
- data/lib/zip/pass_thru_decompressor.rb +31 -0
- data/lib/zip/streamable_directory.rb +15 -0
- data/lib/zip/streamable_stream.rb +52 -0
- data/lib/zip/version.rb +3 -0
- data/lib/zip.rb +72 -0
- metadata +103 -31
@@ -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
|
+
@codingSM = CodingStateMachine.new(Big5SMModel)
|
34
|
+
@distributionAnalyzer = Big5DistributionAnalysis.new()
|
35
|
+
reset()
|
36
|
+
end
|
37
|
+
|
38
|
+
def get_charset_name
|
39
|
+
return "Big5"
|
40
|
+
end
|
41
|
+
end
|
42
|
+
end
|
@@ -0,0 +1,250 @@
|
|
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
|
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
|
+
ENOUGH_DATA_THRESHOLD = 1024
|
31
|
+
SURE_YES = 0.99
|
32
|
+
SURE_NO = 0.01
|
33
|
+
|
34
|
+
class CharDistributionAnalysis
|
35
|
+
def initialize
|
36
|
+
@charToFreqOrder = nil # Mapping table to get frequency order from char order (get from GetOrder())
|
37
|
+
@tableSize = nil # Size of above table
|
38
|
+
@typicalDistributionRatio = 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.
|
39
|
+
reset()
|
40
|
+
end
|
41
|
+
|
42
|
+
def reset
|
43
|
+
# # """reset analyser, clear any state"""
|
44
|
+
@done = false # If this flag is set to constants.True, detection is done and conclusion has been made
|
45
|
+
@totalChars = 0 # Total characters encountered
|
46
|
+
@freqChars = 0 # The number of characters whose frequency order is less than 512
|
47
|
+
end
|
48
|
+
|
49
|
+
def feed(aStr, aCharLen)
|
50
|
+
# # """feed a character with known length"""
|
51
|
+
if aCharLen == 2
|
52
|
+
# we only care about 2-bytes character in our distribution analysis
|
53
|
+
order = get_order(aStr)
|
54
|
+
else
|
55
|
+
order = -1
|
56
|
+
end
|
57
|
+
if order >= 0
|
58
|
+
@totalChars += 1
|
59
|
+
# order is valid
|
60
|
+
if order < @tableSize
|
61
|
+
if 512 > @charToFreqOrder[order]
|
62
|
+
@freqChars += 1
|
63
|
+
end
|
64
|
+
end
|
65
|
+
end
|
66
|
+
end
|
67
|
+
|
68
|
+
def get_confidence
|
69
|
+
# """return confidence based on existing data"""
|
70
|
+
# if we didn't receive any character in our consideration range, return negative answer
|
71
|
+
if @totalChars <= 0
|
72
|
+
return SURE_NO
|
73
|
+
end
|
74
|
+
|
75
|
+
if @totalChars != @freqChars
|
76
|
+
r = @freqChars / ((@totalChars - @freqChars) * @typicalDistributionRatio)
|
77
|
+
if r < SURE_YES
|
78
|
+
return r
|
79
|
+
end
|
80
|
+
end
|
81
|
+
|
82
|
+
# normalize confidence (we don't want to be 100% sure)
|
83
|
+
return SURE_YES
|
84
|
+
end
|
85
|
+
|
86
|
+
def got_enough_data
|
87
|
+
# It is not necessary to receive all data to draw conclusion. For charset detection,
|
88
|
+
# certain amount of data is enough
|
89
|
+
return @totalChars > ENOUGH_DATA_THRESHOLD
|
90
|
+
end
|
91
|
+
|
92
|
+
def get_order(aStr)
|
93
|
+
# We do not handle characters based on the original encoding string, but
|
94
|
+
# convert this encoding string to a number, here called order.
|
95
|
+
# This allows multiple encodings of a language to share one frequency table.
|
96
|
+
return -1
|
97
|
+
end
|
98
|
+
end
|
99
|
+
|
100
|
+
class EUCTWDistributionAnalysis < CharDistributionAnalysis
|
101
|
+
def initialize
|
102
|
+
super()
|
103
|
+
@charToFreqOrder = EUCTWCharToFreqOrder
|
104
|
+
@tableSize = EUCTW_TABLE_SIZE
|
105
|
+
@typicalDistributionRatio = EUCTW_TYPICAL_DISTRIBUTION_RATIO
|
106
|
+
end
|
107
|
+
|
108
|
+
def get_order(aStr)
|
109
|
+
# for euc-TW encoding, we are interested
|
110
|
+
# first byte range: 0xc4 -- 0xfe
|
111
|
+
# second byte range: 0xa1 -- 0xfe
|
112
|
+
# no validation needed here. State machine has done that
|
113
|
+
if aStr[0, 1] >= "\xC4"
|
114
|
+
bytes = aStr.bytes.to_a
|
115
|
+
return 94 * (bytes[0] - 0xC4) + bytes[1] - 0xA1
|
116
|
+
else
|
117
|
+
return -1
|
118
|
+
end
|
119
|
+
end
|
120
|
+
|
121
|
+
def get_confidence
|
122
|
+
if @freqChars <= MINIMUM_DATA_THRESHOLD
|
123
|
+
return SURE_NO
|
124
|
+
end
|
125
|
+
|
126
|
+
super
|
127
|
+
end
|
128
|
+
end
|
129
|
+
|
130
|
+
class EUCKRDistributionAnalysis < CharDistributionAnalysis
|
131
|
+
def initialize
|
132
|
+
super()
|
133
|
+
@charToFreqOrder = EUCKRCharToFreqOrder
|
134
|
+
@tableSize = EUCKR_TABLE_SIZE
|
135
|
+
@typicalDistributionRatio = EUCKR_TYPICAL_DISTRIBUTION_RATIO
|
136
|
+
end
|
137
|
+
|
138
|
+
def get_order(aStr)
|
139
|
+
# for euc-KR encoding, we are interested
|
140
|
+
# first byte range: 0xb0 -- 0xfe
|
141
|
+
# second byte range: 0xa1 -- 0xfe
|
142
|
+
# no validation needed here. State machine has done that
|
143
|
+
if aStr[0, 1] >= "\xB0"
|
144
|
+
bytes = aStr.bytes.to_a
|
145
|
+
return 94 * (bytes[0] - 0xB0) + bytes[1] - 0xA1
|
146
|
+
else
|
147
|
+
return -1
|
148
|
+
end
|
149
|
+
end
|
150
|
+
end
|
151
|
+
|
152
|
+
class GB18030DistributionAnalysis < CharDistributionAnalysis
|
153
|
+
def initialize
|
154
|
+
super()
|
155
|
+
@charToFreqOrder = GB18030CharToFreqOrder
|
156
|
+
@tableSize = GB18030_TABLE_SIZE
|
157
|
+
@typicalDistributionRatio = GB18030_TYPICAL_DISTRIBUTION_RATIO
|
158
|
+
end
|
159
|
+
|
160
|
+
def get_order(aStr)
|
161
|
+
# for GB18030 encoding, we are interested
|
162
|
+
# first byte range: 0xb0 -- 0xfe
|
163
|
+
# second byte range: 0xa1 -- 0xfe
|
164
|
+
# no validation needed here. State machine has done that
|
165
|
+
if (aStr[0, 1] >= "\xB0") and (aStr[1, 1] >= "\xA1")
|
166
|
+
bytes = aStr.bytes.to_a
|
167
|
+
return 94 * (bytes[0] - 0xB0) + bytes[1] - 0xA1
|
168
|
+
else
|
169
|
+
return -1
|
170
|
+
end
|
171
|
+
end
|
172
|
+
end
|
173
|
+
|
174
|
+
class Big5DistributionAnalysis < CharDistributionAnalysis
|
175
|
+
def initialize
|
176
|
+
super
|
177
|
+
@charToFreqOrder = Big5CharToFreqOrder
|
178
|
+
@tableSize = BIG5_TABLE_SIZE
|
179
|
+
@typicalDistributionRatio = BIG5_TYPICAL_DISTRIBUTION_RATIO
|
180
|
+
end
|
181
|
+
|
182
|
+
def get_order(aStr)
|
183
|
+
# for big5 encoding, we are interested
|
184
|
+
# first byte range: 0xa4 -- 0xfe
|
185
|
+
# second byte range: 0x40 -- 0x7e , 0xa1 -- 0xfe
|
186
|
+
# no validation needed here. State machine has done that
|
187
|
+
if aStr[0, 1] >= "\xA4"
|
188
|
+
bytes = aStr.bytes.to_a
|
189
|
+
if aStr[1, 1] >= "\xA1"
|
190
|
+
return 157 * (bytes[0] - 0xA4) + bytes[1] - 0xA1 + 63
|
191
|
+
else
|
192
|
+
return 157 * (bytes[0] - 0xA4) + bytes[1] - 0x40
|
193
|
+
end
|
194
|
+
else
|
195
|
+
return -1
|
196
|
+
end
|
197
|
+
end
|
198
|
+
end
|
199
|
+
|
200
|
+
class SJISDistributionAnalysis < CharDistributionAnalysis
|
201
|
+
def initialize
|
202
|
+
super()
|
203
|
+
@charToFreqOrder = JISCharToFreqOrder
|
204
|
+
@tableSize = JIS_TABLE_SIZE
|
205
|
+
@typicalDistributionRatio = JIS_TYPICAL_DISTRIBUTION_RATIO
|
206
|
+
end
|
207
|
+
|
208
|
+
def get_order(aStr)
|
209
|
+
# for sjis encoding, we are interested
|
210
|
+
# first byte range: 0x81 -- 0x9f , 0xe0 -- 0xfe
|
211
|
+
# second byte range: 0x40 -- 0x7e, 0x81 -- oxfe
|
212
|
+
# no validation needed here. State machine has done that
|
213
|
+
bytes = aStr.bytes.to_a
|
214
|
+
if (aStr[0, 1] >= "\x81") and (aStr[0, 1] <= "\x9F")
|
215
|
+
order = 188 * (bytes[0] - 0x81)
|
216
|
+
elsif (aStr[0, 1] >= "\xE0") and (aStr[0, 1] <= "\xEF")
|
217
|
+
order = 188 * (bytes[0] - 0xE0 + 31)
|
218
|
+
else
|
219
|
+
return -1
|
220
|
+
end
|
221
|
+
order = order + bytes[1] - 0x40
|
222
|
+
if aStr[1, 1] > "\x7F"
|
223
|
+
order =- 1
|
224
|
+
end
|
225
|
+
return order
|
226
|
+
end
|
227
|
+
end
|
228
|
+
|
229
|
+
class EUCJPDistributionAnalysis < CharDistributionAnalysis
|
230
|
+
def initialize
|
231
|
+
super()
|
232
|
+
@charToFreqOrder = JISCharToFreqOrder
|
233
|
+
@tableSize = JIS_TABLE_SIZE
|
234
|
+
@typicalDistributionRatio = JIS_TYPICAL_DISTRIBUTION_RATIO
|
235
|
+
end
|
236
|
+
|
237
|
+
def get_order(aStr)
|
238
|
+
# for euc-JP encoding, we are interested
|
239
|
+
# first byte range: 0xa0 -- 0xfe
|
240
|
+
# second byte range: 0xa1 -- 0xfe
|
241
|
+
# no validation needed here. State machine has done that
|
242
|
+
if aStr[0, 1] >= "\xA0"
|
243
|
+
bytes = aStr.bytes.to_a
|
244
|
+
return 94 * (bytes[0] - 0xA1) + bytes[1] - 0xa1
|
245
|
+
else
|
246
|
+
return -1
|
247
|
+
end
|
248
|
+
end
|
249
|
+
end
|
250
|
+
end
|
@@ -0,0 +1,110 @@
|
|
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 :probers
|
32
|
+
def initialize
|
33
|
+
super
|
34
|
+
@activeNum = 0
|
35
|
+
@probers = []
|
36
|
+
@bestGuessProber = nil
|
37
|
+
end
|
38
|
+
|
39
|
+
def reset
|
40
|
+
super
|
41
|
+
@activeNum = 0
|
42
|
+
|
43
|
+
for prober in @probers
|
44
|
+
if prober
|
45
|
+
prober.reset()
|
46
|
+
prober.active = true
|
47
|
+
@activeNum += 1
|
48
|
+
end
|
49
|
+
end
|
50
|
+
@bestGuessProber = nil
|
51
|
+
end
|
52
|
+
|
53
|
+
def get_charset_name
|
54
|
+
if !@bestGuessProber
|
55
|
+
get_confidence()
|
56
|
+
if !@bestGuessProber
|
57
|
+
return nil
|
58
|
+
end
|
59
|
+
end
|
60
|
+
return @bestGuessProber.get_charset_name()
|
61
|
+
end
|
62
|
+
|
63
|
+
def feed(aBuf)
|
64
|
+
for prober in @probers
|
65
|
+
next unless prober
|
66
|
+
next unless prober.active
|
67
|
+
st = prober.feed(aBuf)
|
68
|
+
next unless st
|
69
|
+
if st == EFoundIt
|
70
|
+
@bestGuessProber = prober
|
71
|
+
return get_state()
|
72
|
+
elsif st == ENotMe
|
73
|
+
prober.active = false
|
74
|
+
@activeNum -= 1
|
75
|
+
if @activeNum <= 0
|
76
|
+
@state = ENotMe
|
77
|
+
return get_state()
|
78
|
+
end
|
79
|
+
end
|
80
|
+
end
|
81
|
+
return get_state()
|
82
|
+
end
|
83
|
+
|
84
|
+
def get_confidence()
|
85
|
+
st = get_state()
|
86
|
+
if st == EFoundIt
|
87
|
+
return 0.99
|
88
|
+
elsif st == ENotMe
|
89
|
+
return 0.01
|
90
|
+
end
|
91
|
+
bestConf = 0.0
|
92
|
+
@bestGuessProber = nil
|
93
|
+
for prober in @probers
|
94
|
+
next unless prober
|
95
|
+
unless prober.active
|
96
|
+
$stderr << "#{prober.get_charset_name()} not active\n" if $debug
|
97
|
+
next
|
98
|
+
end
|
99
|
+
cf = prober.get_confidence()
|
100
|
+
$stderr << "#{prober.get_charset_name} confidence = #{cf}\n" if $debug
|
101
|
+
if bestConf < cf
|
102
|
+
bestConf = cf
|
103
|
+
@bestGuessProber = prober
|
104
|
+
end
|
105
|
+
end
|
106
|
+
return 0.0 unless @bestGuessProber
|
107
|
+
return bestConf
|
108
|
+
end
|
109
|
+
end
|
110
|
+
end
|
@@ -0,0 +1,70 @@
|
|
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
|
+
@state = 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 @state
|
49
|
+
end
|
50
|
+
|
51
|
+
def get_confidence
|
52
|
+
return 0.0
|
53
|
+
end
|
54
|
+
|
55
|
+
def filter_high_bit_only(aBuf)
|
56
|
+
newBuf = aBuf.gsub(/([\x00-\x7F])+/, ' ')
|
57
|
+
return newBuf
|
58
|
+
end
|
59
|
+
|
60
|
+
def filter_without_english_letters(aBuf)
|
61
|
+
newBuf = aBuf.gsub(/([A-Za-z])+/,' ')
|
62
|
+
return newBuf
|
63
|
+
end
|
64
|
+
|
65
|
+
def filter_with_english_letters(aBuf)
|
66
|
+
# TODO
|
67
|
+
return aBuf
|
68
|
+
end
|
69
|
+
end
|
70
|
+
end
|
@@ -0,0 +1,67 @@
|
|
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
|
+
attr_accessor :active
|
32
|
+
|
33
|
+
def initialize(sm)
|
34
|
+
@model = sm
|
35
|
+
@currentBytePos = 0
|
36
|
+
@currentCharLen = 0
|
37
|
+
reset()
|
38
|
+
end
|
39
|
+
|
40
|
+
def reset
|
41
|
+
@currentState = EStart
|
42
|
+
end
|
43
|
+
|
44
|
+
def next_state(c)
|
45
|
+
# for each byte we get its class
|
46
|
+
# if it is first byte, we also get byte length
|
47
|
+
b = c.bytes.first
|
48
|
+
byteCls = @model['classTable'][b]
|
49
|
+
if @currentState == EStart
|
50
|
+
@currentBytePos = 0
|
51
|
+
@currentCharLen = @model['charLenTable'][byteCls]
|
52
|
+
end
|
53
|
+
# from byte's class and stateTable, we get its next state
|
54
|
+
@currentState = @model['stateTable'][@currentState * @model['classFactor'] + byteCls]
|
55
|
+
@currentBytePos += 1
|
56
|
+
return @currentState
|
57
|
+
end
|
58
|
+
|
59
|
+
def get_current_charlen
|
60
|
+
return @currentCharLen
|
61
|
+
end
|
62
|
+
|
63
|
+
def get_coding_state_machine
|
64
|
+
return @model['name']
|
65
|
+
end
|
66
|
+
end
|
67
|
+
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 +1,90 @@
|
|
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
|
+
@codingSM = [
|
34
|
+
CodingStateMachine.new(HZSMModel),
|
35
|
+
CodingStateMachine.new(ISO2022CNSMModel),
|
36
|
+
CodingStateMachine.new(ISO2022JPSMModel),
|
37
|
+
CodingStateMachine.new(ISO2022KRSMModel)
|
38
|
+
]
|
39
|
+
reset()
|
40
|
+
end
|
41
|
+
|
42
|
+
def reset
|
43
|
+
super()
|
44
|
+
for codingSM in @codingSM
|
45
|
+
next if !codingSM
|
46
|
+
codingSM.active = true
|
47
|
+
codingSM.reset()
|
48
|
+
end
|
49
|
+
@activeSM = @codingSM.length
|
50
|
+
@detectedCharset = nil
|
51
|
+
end
|
52
|
+
|
53
|
+
def get_charset_name
|
54
|
+
return @detectedCharset
|
55
|
+
end
|
56
|
+
|
57
|
+
def get_confidence
|
58
|
+
if @detectedCharset
|
59
|
+
return 0.99
|
60
|
+
else
|
61
|
+
return 0.00
|
62
|
+
end
|
63
|
+
end
|
64
|
+
|
65
|
+
def feed(aBuf)
|
66
|
+
aBuf.each_byte do |b|
|
67
|
+
c = b.chr
|
68
|
+
for codingSM in @codingSM
|
69
|
+
next unless codingSM
|
70
|
+
next unless codingSM.active
|
71
|
+
codingState = codingSM.next_state(c)
|
72
|
+
if codingState == EError
|
73
|
+
codingSM.active = false
|
74
|
+
@activeSM -= 1
|
75
|
+
if @activeSM <= 0
|
76
|
+
@state = ENotMe
|
77
|
+
return get_state()
|
78
|
+
end
|
79
|
+
elsif codingState == EItsMe
|
80
|
+
@state = EFoundIt
|
81
|
+
@detectedCharset = codingSM.get_coding_state_machine()
|
82
|
+
return get_state()
|
83
|
+
end
|
84
|
+
end
|
85
|
+
end
|
86
|
+
|
87
|
+
return get_state()
|
88
|
+
end
|
89
|
+
end
|
90
|
+
end
|