lg_pod_plugin 1.0.3 → 1.0.6
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/downloader.rb +98 -0
- data/lib/lg_pod_plugin/file_path.rb +8 -4
- data/lib/lg_pod_plugin/git_util.rb +188 -80
- data/lib/lg_pod_plugin/install.rb +61 -80
- data/lib/lg_pod_plugin/l_cache.rb +236 -0
- data/lib/lg_pod_plugin/l_util.rb +39 -0
- data/lib/lg_pod_plugin/log.rb +26 -0
- data/lib/lg_pod_plugin/request.rb +140 -0
- data/lib/lg_pod_plugin/string.rb +33 -0
- data/lib/lg_pod_plugin/version.rb +1 -1
- data/lib/lg_pod_plugin.rb +6 -60
- 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 +107 -33
- data/lib/lg_pod_plugin/cache.rb +0 -226
- data/lib/lg_pod_plugin/download.rb +0 -140
- data/lib/lg_pod_plugin/pod_spec.rb +0 -66
@@ -0,0 +1,289 @@
|
|
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
|
+
# Shy Shalom
|
6
|
+
# Portions created by the Initial Developer are Copyright (C) 2005
|
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
|
+
# This prober doesn't actually recognize a language or a charset.
|
30
|
+
# It is a helper prober for the use of the Hebrew model probers
|
31
|
+
|
32
|
+
### General ideas of the Hebrew charset recognition ###
|
33
|
+
#
|
34
|
+
# Four main charsets exist in Hebrew:
|
35
|
+
# "ISO-8859-8" - Visual Hebrew
|
36
|
+
# "windows-1255" - Logical Hebrew
|
37
|
+
# "ISO-8859-8-I" - Logical Hebrew
|
38
|
+
# "x-mac-hebrew" - ?? Logical Hebrew ??
|
39
|
+
#
|
40
|
+
# Both "ISO" charsets use a completely identical set of code points, whereas
|
41
|
+
# "windows-1255" and "x-mac-hebrew" are two different proper supersets of
|
42
|
+
# these code points. windows-1255 defines additional characters in the range
|
43
|
+
# 0x80-0x9F as some misc punctuation marks as well as some Hebrew-specific
|
44
|
+
# diacritics and additional 'Yiddish' ligature letters in the range 0xc0-0xd6.
|
45
|
+
# x-mac-hebrew defines similar additional code points but with a different
|
46
|
+
# mapping.
|
47
|
+
#
|
48
|
+
# As far as an average Hebrew text with no diacritics is concerned, all four
|
49
|
+
# charsets are identical with respect to code points. Meaning that for the
|
50
|
+
# main Hebrew alphabet, all four map the same values to all 27 Hebrew letters
|
51
|
+
# (including final letters).
|
52
|
+
#
|
53
|
+
# The dominant difference between these charsets is their directionality.
|
54
|
+
# "Visual" directionality means that the text is ordered as if the renderer is
|
55
|
+
# not aware of a BIDI rendering algorithm. The renderer sees the text and
|
56
|
+
# draws it from left to right. The text itself when ordered naturally is read
|
57
|
+
# backwards. A buffer of Visual Hebrew generally looks like so:
|
58
|
+
# "[last word of first line spelled backwards] [whole line ordered backwards
|
59
|
+
# and spelled backwards] [first word of first line spelled backwards]
|
60
|
+
# [end of line] [last word of second line] ... etc' "
|
61
|
+
# adding punctuation marks, numbers and English text to visual text is
|
62
|
+
# naturally also "visual" and from left to right.
|
63
|
+
#
|
64
|
+
# "Logical" directionality means the text is ordered "naturally" according to
|
65
|
+
# the order it is read. It is the responsibility of the renderer to display
|
66
|
+
# the text from right to left. A BIDI algorithm is used to place general
|
67
|
+
# punctuation marks, numbers and English text in the text.
|
68
|
+
#
|
69
|
+
# Texts in x-mac-hebrew are almost impossible to find on the Internet. From
|
70
|
+
# what little evidence I could find, it seems that its general directionality
|
71
|
+
# is Logical.
|
72
|
+
#
|
73
|
+
# To sum up all of the above, the Hebrew probing mechanism knows about two
|
74
|
+
# charsets:
|
75
|
+
# Visual Hebrew - "ISO-8859-8" - backwards text - Words and sentences are
|
76
|
+
# backwards while line order is natural. For charset recognition purposes
|
77
|
+
# the line order is unimportant (In fact, for this implementation, even
|
78
|
+
# word order is unimportant).
|
79
|
+
# Logical Hebrew - "windows-1255" - normal, naturally ordered text.
|
80
|
+
#
|
81
|
+
# "ISO-8859-8-I" is a subset of windows-1255 and doesn't need to be
|
82
|
+
# specifically identified.
|
83
|
+
# "x-mac-hebrew" is also identified as windows-1255. A text in x-mac-hebrew
|
84
|
+
# that contain special punctuation marks or diacritics is displayed with
|
85
|
+
# some unconverted characters showing as question marks. This problem might
|
86
|
+
# be corrected using another model prober for x-mac-hebrew. Due to the fact
|
87
|
+
# that x-mac-hebrew texts are so rare, writing another model prober isn't
|
88
|
+
# worth the effort and performance hit.
|
89
|
+
#
|
90
|
+
#### The Prober ####
|
91
|
+
#
|
92
|
+
# The prober is divided between two SBCharSetProbers and a HebrewProber,
|
93
|
+
# all of which are managed, created, fed data, inquired and deleted by the
|
94
|
+
# SBCSGroupProber. The two SBCharSetProbers identify that the text is in
|
95
|
+
# fact some kind of Hebrew, Logical or Visual. The final decision about which
|
96
|
+
# one is it is made by the HebrewProber by combining final-letter scores
|
97
|
+
# with the scores of the two SBCharSetProbers to produce a final answer.
|
98
|
+
#
|
99
|
+
# The SBCSGroupProber is responsible for stripping the original text of HTML
|
100
|
+
# tags, English characters, numbers, low-ASCII punctuation characters, spaces
|
101
|
+
# and new lines. It reduces any sequence of such characters to a single space.
|
102
|
+
# The buffer fed to each prober in the SBCS group prober is pure text in
|
103
|
+
# high-ASCII.
|
104
|
+
# The two SBCharSetProbers (model probers) share the same language model:
|
105
|
+
# Win1255Model.
|
106
|
+
# The first SBCharSetProber uses the model normally as any other
|
107
|
+
# SBCharSetProber does, to recognize windows-1255, upon which this model was
|
108
|
+
# built. The second SBCharSetProber is told to make the pair-of-letter
|
109
|
+
# lookup in the language model backwards. This in practice exactly simulates
|
110
|
+
# a visual Hebrew model using the windows-1255 logical Hebrew model.
|
111
|
+
#
|
112
|
+
# The HebrewProber is not using any language model. All it does is look for
|
113
|
+
# final-letter evidence suggesting the text is either logical Hebrew or visual
|
114
|
+
# Hebrew. Disjointed from the model probers, the results of the HebrewProber
|
115
|
+
# alone are meaningless. HebrewProber always returns 0.00 as confidence
|
116
|
+
# since it never identifies a charset by itself. Instead, the pointer to the
|
117
|
+
# HebrewProber is passed to the model probers as a helper "Name Prober".
|
118
|
+
# When the Group prober receives a positive identification from any prober,
|
119
|
+
# it asks for the name of the charset identified. If the prober queried is a
|
120
|
+
# Hebrew model prober, the model prober forwards the call to the
|
121
|
+
# HebrewProber to make the final decision. In the HebrewProber, the
|
122
|
+
# decision is made according to the final-letters scores maintained and Both
|
123
|
+
# model probers scores. The answer is returned in the form of the name of the
|
124
|
+
# charset identified, either "windows-1255" or "ISO-8859-8".
|
125
|
+
|
126
|
+
# windows-1255 / ISO-8859-8 code points of interest
|
127
|
+
module CharDet
|
128
|
+
FINAL_KAF = "\xea"
|
129
|
+
NORMAL_KAF = "\xeb"
|
130
|
+
FINAL_MEM = "\xed"
|
131
|
+
NORMAL_MEM = "\xee"
|
132
|
+
FINAL_NUN = "\xef"
|
133
|
+
NORMAL_NUN = "\xf0"
|
134
|
+
FINAL_PE = "\xf3"
|
135
|
+
NORMAL_PE = "\xf4"
|
136
|
+
FINAL_TSADI = "\xf5"
|
137
|
+
NORMAL_TSADI = "\xf6"
|
138
|
+
|
139
|
+
# Minimum Visual vs Logical final letter score difference.
|
140
|
+
# If the difference is below this, don't rely solely on the final letter score distance.
|
141
|
+
MIN_FINAL_CHAR_DISTANCE = 5
|
142
|
+
|
143
|
+
# Minimum Visual vs Logical model score difference.
|
144
|
+
# If the difference is below this, don't rely at all on the model score distance.
|
145
|
+
MIN_MODEL_DISTANCE = 0.01
|
146
|
+
|
147
|
+
VISUAL_HEBREW_NAME = "ISO-8859-8"
|
148
|
+
LOGICAL_HEBREW_NAME = "windows-1255"
|
149
|
+
|
150
|
+
class HebrewProber < CharSetProber
|
151
|
+
def initialize
|
152
|
+
super()
|
153
|
+
@logicalProber = nil
|
154
|
+
@visualProber = nil
|
155
|
+
reset()
|
156
|
+
end
|
157
|
+
|
158
|
+
def reset
|
159
|
+
@finalCharLogicalScore = 0
|
160
|
+
@finalCharVisualScore = 0
|
161
|
+
# The two last characters seen in the previous buffer,
|
162
|
+
# mPrev and mBeforePrev are initialized to space in order to simulate a word
|
163
|
+
# delimiter at the beginning of the data
|
164
|
+
@prev = ' '
|
165
|
+
@beforePrev = ' '
|
166
|
+
# These probers are owned by the group prober.
|
167
|
+
end
|
168
|
+
|
169
|
+
def set_model_probers(logicalProber, visualProber)
|
170
|
+
@logicalProber = logicalProber
|
171
|
+
@visualProber = visualProber
|
172
|
+
end
|
173
|
+
|
174
|
+
def is_final(c)
|
175
|
+
return [FINAL_KAF, FINAL_MEM, FINAL_NUN, FINAL_PE, FINAL_TSADI].include?(c)
|
176
|
+
end
|
177
|
+
|
178
|
+
def is_non_final(c)
|
179
|
+
# The normal Tsadi is not a good Non-Final letter due to words like
|
180
|
+
# 'lechotet' (to chat) containing an apostrophe after the tsadi. This
|
181
|
+
# apostrophe is converted to a space in FilterWithoutEnglishLetters causing
|
182
|
+
# the Non-Final tsadi to appear at an end of a word even though this is not
|
183
|
+
# the case in the original text.
|
184
|
+
# The letters Pe and Kaf rarely display a related behavior of not being a
|
185
|
+
# good Non-Final letter. Words like 'Pop', 'Winamp' and 'Mubarak' for
|
186
|
+
# example legally end with a Non-Final Pe or Kaf. However, the benefit of
|
187
|
+
# these letters as Non-Final letters outweighs the damage since these words
|
188
|
+
# are quite rare.
|
189
|
+
return [NORMAL_KAF, NORMAL_MEM, NORMAL_NUN, NORMAL_PE].include?(c)
|
190
|
+
end
|
191
|
+
|
192
|
+
def feed(aBuf)
|
193
|
+
# Final letter analysis for logical-visual decision.
|
194
|
+
# Look for evidence that the received buffer is either logical Hebrew or
|
195
|
+
# visual Hebrew.
|
196
|
+
# The following cases are checked:
|
197
|
+
# 1) A word longer than 1 letter, ending with a final letter. This is an
|
198
|
+
# indication that the text is laid out "naturally" since the final letter
|
199
|
+
# really appears at the end. +1 for logical score.
|
200
|
+
# 2) A word longer than 1 letter, ending with a Non-Final letter. In normal
|
201
|
+
# Hebrew, words ending with Kaf, Mem, Nun, Pe or Tsadi, should not end with
|
202
|
+
# the Non-Final form of that letter. Exceptions to this rule are mentioned
|
203
|
+
# above in isNonFinal(). This is an indication that the text is laid out
|
204
|
+
# backwards. +1 for visual score
|
205
|
+
# 3) A word longer than 1 letter, starting with a final letter. Final letters
|
206
|
+
# should not appear at the beginning of a word. This is an indication that
|
207
|
+
# the text is laid out backwards. +1 for visual score.
|
208
|
+
#
|
209
|
+
# The visual score and logical score are accumulated throughout the text and
|
210
|
+
# are finally checked against each other in GetCharSetName().
|
211
|
+
# No checking for final letters in the middle of words is done since that case
|
212
|
+
# is not an indication for either Logical or Visual text.
|
213
|
+
#
|
214
|
+
# We automatically filter out all 7-bit characters (replace them with spaces)
|
215
|
+
# so the word boundary detection works properly. [MAP]
|
216
|
+
|
217
|
+
if get_state() == ENotMe
|
218
|
+
# Both model probers say it's not them. No reason to continue.
|
219
|
+
return ENotMe
|
220
|
+
end
|
221
|
+
|
222
|
+
aBuf = filter_high_bit_only(aBuf)
|
223
|
+
|
224
|
+
for cur in aBuf.split(' ')
|
225
|
+
if cur == ' '
|
226
|
+
# We stand on a space - a word just ended
|
227
|
+
if @beforePrev != ' '
|
228
|
+
# next-to-last char was not a space so self._mPrev is not a 1 letter word
|
229
|
+
if is_final(@prev)
|
230
|
+
# case (1) [-2:not space][-1:final letter][cur:space]
|
231
|
+
@finalCharLogicalScore += 1
|
232
|
+
elsif is_non_final(@prev)
|
233
|
+
# case (2) [-2:not space][-1:Non-Final letter][cur:space]
|
234
|
+
@finalCharVisualScore += 1
|
235
|
+
end
|
236
|
+
end
|
237
|
+
else
|
238
|
+
# Not standing on a space
|
239
|
+
if (@beforePrev == ' ') and (is_final(@prev)) and (cur != ' ')
|
240
|
+
# case (3) [-2:space][-1:final letter][cur:not space]
|
241
|
+
@finalCharVisualScore += 1
|
242
|
+
end
|
243
|
+
end
|
244
|
+
@beforePrev = @prev
|
245
|
+
@prev = cur
|
246
|
+
end
|
247
|
+
|
248
|
+
# Forever detecting, till the end or until both model probers return eNotMe (handled above)
|
249
|
+
return EDetecting
|
250
|
+
end
|
251
|
+
|
252
|
+
def get_charset_name
|
253
|
+
# Make the decision: is it Logical or Visual?
|
254
|
+
# If the final letter score distance is dominant enough, rely on it.
|
255
|
+
finalsub = @finalCharLogicalScore - @finalCharVisualScore
|
256
|
+
if finalsub >= MIN_FINAL_CHAR_DISTANCE
|
257
|
+
return LOGICAL_HEBREW_NAME
|
258
|
+
end
|
259
|
+
if finalsub <= -MIN_FINAL_CHAR_DISTANCE
|
260
|
+
return VISUAL_HEBREW_NAME
|
261
|
+
end
|
262
|
+
|
263
|
+
# It's not dominant enough, try to rely on the model scores instead.
|
264
|
+
modelsub = @logicalProber.get_confidence() - @visualProber.get_confidence()
|
265
|
+
if modelsub > MIN_MODEL_DISTANCE
|
266
|
+
return LOGICAL_HEBREW_NAME
|
267
|
+
end
|
268
|
+
if modelsub < -MIN_MODEL_DISTANCE
|
269
|
+
return VISUAL_HEBREW_NAME
|
270
|
+
end
|
271
|
+
|
272
|
+
# Still no good, back to final letter distance, maybe it'll save the day.
|
273
|
+
if finalsub < 0.0
|
274
|
+
return VISUAL_HEBREW_NAME
|
275
|
+
end
|
276
|
+
|
277
|
+
# (finalsub > 0 - Logical) or (don't know what to do) default to Logical.
|
278
|
+
return LOGICAL_HEBREW_NAME
|
279
|
+
end
|
280
|
+
|
281
|
+
def get_state
|
282
|
+
# Remain active as long as any of the model probers are active.
|
283
|
+
if (@logicalProber.get_state() == ENotMe) and (@visualProber.get_state() == ENotMe)
|
284
|
+
return ENotMe
|
285
|
+
end
|
286
|
+
return EDetecting
|
287
|
+
end
|
288
|
+
end
|
289
|
+
end
|