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
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
|
#-- vim:sw=2:et
#++
#
# :title: rbot utilities provider
#
# Author:: Tom Gilbert <tom@linuxbrit.co.uk>
# Author:: Giuseppe "Oblomov" Bilotta <giuseppe.bilotta@gmail.com>
#
# Copyright:: (C) 2002-2006 Tom Gilbert
# Copyright:: (C) 2007 Giuseppe Bilotta
#
# TODO some of these Utils should be rewritten as extensions to the approriate
# standard Ruby classes and accordingly be moved to extends.rb
require 'net/http'
require 'uri'
require 'tempfile'
begin
$we_have_html_entities_decoder = require 'htmlentities'
rescue LoadError
$we_have_html_entities_decoder = false
module ::Irc
module Utils
UNESCAPE_TABLE = {
'laquo' => '<<',
'raquo' => '>>',
'quot' => '"',
'apos' => '\'',
'micro' => 'u',
'copy' => '(c)',
'trade' => '(tm)',
'reg' => '(R)',
'#174' => '(R)',
'#8220' => '"',
'#8221' => '"',
'#8212' => '--',
'#39' => '\'',
'amp' => '&',
'lt' => '<',
'gt' => '>',
'hellip' => '...',
'nbsp' => ' ',
=begin
# extras codes, for future use...
'zwnj' => '‌',
'aring' => '\xe5',
'gt' => '>',
'yen' => '\xa5',
'ograve' => '\xf2',
'Chi' => 'Χ',
'bull' => '•',
'Egrave' => '\xc8',
'Ntilde' => '\xd1',
'upsih' => 'ϒ',
'Yacute' => '\xdd',
'asymp' => '≈',
'radic' => '√',
'otimes' => '⊗',
'nabla' => '∇',
'aelig' => '\xe6',
'oelig' => 'œ',
'equiv' => '≡',
'Psi' => 'Ψ',
'auml' => '\xe4',
'circ' => 'ˆ',
'Acirc' => '\xc2',
'Epsilon' => 'Ε',
'Yuml' => 'Ÿ',
'Eta' => 'Η',
'Icirc' => '\xce',
'Upsilon' => 'Υ',
'ndash' => '–',
'there4' => '∴',
'Prime' => '″',
'prime' => '′',
'psi' => 'ψ',
'Kappa' => 'Κ',
'rsaquo' => '›',
'Tau' => 'Τ',
'darr' => '↓',
'ocirc' => '\xf4',
'lrm' => '‎',
'zwj' => '‍',
'cedil' => '\xb8',
'Ecirc' => '\xca',
'not' => '\xac',
'AElig' => '\xc6',
'oslash' => '\xf8',
'acute' => '\xb4',
'lceil' => '⌈',
'shy' => '\xad',
'rdquo' => '”',
'ge' => '≥',
'Igrave' => '\xcc',
'Ograve' => '\xd2',
'euro' => '€',
'dArr' => '⇓',
'sdot' => '⋅',
'nbsp' => '\xa0',
'lfloor' => '⌊',
'lArr' => '⇐',
'Auml' => '\xc4',
'larr' => '←',
'Atilde' => '\xc3',
'Otilde' => '\xd5',
'szlig' => '\xdf',
'clubs' => '♣',
'diams' => '♦',
'agrave' => '\xe0',
'Ocirc' => '\xd4',
'Iota' => 'Ι',
'Theta' => 'Θ',
'Pi' => 'Π',
'OElig' => 'Œ',
'Scaron' => 'Š',
'frac14' => '\xbc',
'egrave' => '\xe8',
'sub' => '⊂',
'iexcl' => '\xa1',
'frac12' => '\xbd',
'sbquo' => '‚',
'ordf' => '\xaa',
'sum' => '∑',
'prop' => '∝',
'Uuml' => '\xdc',
'ntilde' => '\xf1',
'sup' => '⊃',
'theta' => 'θ',
'prod' => '∏',
'nsub' => '⊄',
'hArr' => '⇔',
'rlm' => '‏',
'THORN' => '\xde',
'infin' => '∞',
'yuml' => '\xff',
'Mu' => 'Μ',
'le' => '≤',
'Eacute' => '\xc9',
'thinsp' => ' ',
'ecirc' => '\xea',
'bdquo' => '„',
'Sigma' => 'Σ',
'fnof' => 'ƒ',
'Aring' => '\xc5',
'tilde' => '˜',
'frac34' => '\xbe',
'emsp' => ' ',
'mdash' => '—',
'uarr' => '↑',
'permil' => '‰',
'Ugrave' => '\xd9',
'rarr' => '→',
'Agrave' => '\xc0',
'chi' => 'χ',
'forall' => '∀',
'eth' => '\xf0',
'rceil' => '⌉',
'iuml' => '\xef',
'gamma' => 'γ',
'lambda' => 'λ',
'harr' => '↔',
'rang' => '〉',
'xi' => 'ξ',
'dagger' => '†',
'divide' => '\xf7',
'Ouml' => '\xd6',
'image' => 'ℑ',
'alefsym' => 'ℵ',
'igrave' => '\xec',
'otilde' => '\xf5',
'Oacute' => '\xd3',
'sube' => '⊆',
'alpha' => 'α',
'frasl' => '⁄',
'ETH' => '\xd0',
'lowast' => '∗',
'Nu' => 'Ν',
'plusmn' => '\xb1',
'Euml' => '\xcb',
'real' => 'ℜ',
'sup1' => '\xb9',
'sup2' => '\xb2',
'sup3' => '\xb3',
'Oslash' => '\xd8',
'Aacute' => '\xc1',
'cent' => '\xa2',
'oline' => '‾',
'Beta' => 'Β',
'perp' => '⊥',
'Delta' => 'Δ',
'loz' => '◊',
'pi' => 'π',
'iota' => 'ι',
'empty' => '∅',
'euml' => '\xeb',
'brvbar' => '\xa6',
'iacute' => '\xed',
'para' => '\xb6',
'micro' => '\xb5',
'cup' => '∪',
'weierp' => '℘',
'uuml' => '\xfc',
'part' => '∂',
'icirc' => '\xee',
'delta' => 'δ',
'omicron' => 'ο',
'upsilon' => 'υ',
'Iuml' => '\xcf',
'Lambda' => 'Λ',
'Xi' => 'Ξ',
'kappa' => 'κ',
'ccedil' => '\xe7',
'Ucirc' => '\xdb',
'cap' => '∩',
'mu' => 'μ',
'scaron' => 'š',
'lsquo' => '‘',
'isin' => '∈',
'Zeta' => 'Ζ',
'supe' => '⊇',
'deg' => '\xb0',
'and' => '∧',
'tau' => 'τ',
'pound' => '\xa3',
'hellip' => '…',
'curren' => '\xa4',
'int' => '∫',
'ucirc' => '\xfb',
'rfloor' => '⌋',
'ensp' => ' ',
'crarr' => '↵',
'ugrave' => '\xf9',
'notin' => '∉',
'exist' => '∃',
'uArr' => '⇑',
'cong' => '≅',
'Dagger' => '‡',
'oplus' => '⊕',
'times' => '\xd7',
'atilde' => '\xe3',
'piv' => 'ϖ',
'ni' => '∋',
'Phi' => 'Φ',
'lsaquo' => '‹',
'Uacute' => '\xda',
'Omicron' => 'Ο',
'ang' => '∠',
'ne' => '≠',
'iquest' => '\xbf',
'eta' => 'η',
'yacute' => '\xfd',
'Rho' => 'Ρ',
'uacute' => '\xfa',
'Alpha' => 'Α',
'zeta' => 'ζ',
'Omega' => 'Ω',
'nu' => 'ν',
'sim' => '∼',
'sect' => '\xa7',
'phi' => 'φ',
'sigmaf' => 'ς',
'macr' => '\xaf',
'minus' => '−',
'Ccedil' => '\xc7',
'ordm' => '\xba',
'epsilon' => 'ε',
'beta' => 'β',
'rArr' => '⇒',
'rho' => 'ρ',
'aacute' => '\xe1',
'eacute' => '\xe9',
'omega' => 'ω',
'middot' => '\xb7',
'Gamma' => 'Γ',
'Iacute' => '\xcd',
'lang' => '〈',
'spades' => '♠',
'rsquo' => '’',
'uml' => '\xa8',
'thorn' => '\xfe',
'ouml' => '\xf6',
'thetasym' => 'ϑ',
'or' => '∨',
'raquo' => '\xbb',
'acirc' => '\xe2',
'ldquo' => '“',
'hearts' => '♥',
'sigma' => 'σ',
'oacute' => '\xf3',
=end
}
end
end
end
module ::Irc
# miscellaneous useful functions
module Utils
SEC_PER_MIN = 60
SEC_PER_HR = SEC_PER_MIN * 60
SEC_PER_DAY = SEC_PER_HR * 24
SEC_PER_MNTH = SEC_PER_DAY * 30
SEC_PER_YR = SEC_PER_MNTH * 12
def Utils.secs_to_string_case(array, var, string, plural)
case var
when 1
array << "1 #{string}"
else
array << "#{var} #{plural}"
end
end
# turn a number of seconds into a human readable string, e.g
# 2 days, 3 hours, 18 minutes, 10 seconds
def Utils.secs_to_string(secs)
ret = []
years, secs = secs.divmod SEC_PER_YR
secs_to_string_case(ret, years, "year", "years") if years > 0
months, secs = secs.divmod SEC_PER_MNTH
secs_to_string_case(ret, months, "month", "months") if months > 0
days, secs = secs.divmod SEC_PER_DAY
secs_to_string_case(ret, days, "day", "days") if days > 0
hours, secs = secs.divmod SEC_PER_HR
secs_to_string_case(ret, hours, "hour", "hours") if hours > 0
mins, secs = secs.divmod SEC_PER_MIN
secs_to_string_case(ret, mins, "minute", "minutes") if mins > 0
secs = secs.to_i
secs_to_string_case(ret, secs, "second", "seconds") if secs > 0 or ret.empty?
case ret.length
when 0
raise "Empty ret array!"
when 1
return ret.to_s
else
return [ret[0, ret.length-1].join(", ") , ret[-1]].join(" and ")
end
end
def Utils.safe_exec(command, *args)
IO.popen("-") {|p|
if(p)
return p.readlines.join("\n")
else
begin
$stderr = $stdout
exec(command, *args)
rescue Exception => e
puts "exec of #{command} led to exception: #{e.inspect}"
Kernel::exit! 0
end
puts "exec of #{command} failed"
Kernel::exit! 0
end
}
end
@@safe_save_dir = nil unless defined?(@@safe_save_dir)
def Utils.set_safe_save_dir(str)
@@safe_save_dir = str.dup
end
def Utils.safe_save(file)
raise 'No safe save directory defined!' if @@safe_save_dir.nil?
basename = File.basename(file)
temp = Tempfile.new(basename,@@safe_save_dir)
temp.binmode
yield temp if block_given?
temp.close
File.rename(temp.path, file)
end
# returns a string containing the result of an HTTP GET on the uri
def Utils.http_get(uristr, readtimeout=8, opentimeout=4)
# ruby 1.7 or better needed for this (or 1.6 and debian unstable)
Net::HTTP.version_1_2
# (so we support the 1_1 api anyway, avoids problems)
uri = URI.parse uristr
query = uri.path
if uri.query
query += "?#{uri.query}"
end
proxy_host = nil
proxy_port = nil
if(ENV['http_proxy'] && proxy_uri = URI.parse(ENV['http_proxy']))
proxy_host = proxy_uri.host
proxy_port = proxy_uri.port
end
begin
http = Net::HTTP.new(uri.host, uri.port, proxy_host, proxy_port)
http.open_timeout = opentimeout
http.read_timeout = readtimeout
http.start {|http|
resp = http.get(query)
if resp.code == "200"
return resp.body
end
}
rescue => e
# cheesy for now
error "Utils.http_get exception: #{e.inspect}, while trying to get #{uristr}"
return nil
end
end
def Utils.decode_html_entities(str)
if $we_have_html_entities_decoder
return HTMLEntities.decode_entities(str)
else
str.gsub(/(&(.+?);)/) {
symbol = $2
# remove the 0-paddng from unicode integers
if symbol =~ /#(.+)/
symbol = "##{$1.to_i.to_s}"
end
# output the symbol's irc-translated character, or a * if it's unknown
UNESCAPE_TABLE[symbol] || '*'
}
end
end
H1_REGEX = /<h1(?:\s+[^>]*)?>(.*?)<\/h1>/im
PAR_REGEX = /<p(?:\s+[^>]*)?>.*?<\/p>/im
# Try to grab and IRCify the first HTML par (<p> tag) in the given string.
# If possible, grab the one after the first h1 heading
#
# It is possible to pass some options to determine how the stripping
# occurs. Currently, only one option is supported:
# * :strip => Regex or String to strip at the beginning of the obtained
# text
#
def Utils.ircify_first_html_par(xml, opts={})
txt = String.new
strip = opts[:strip]
strip = Regexp.new(/^#{Regexp.escape(strip)}/) if strip.kind_of?(String)
header_found = xml.match(H1_REGEX)
if header_found
header_found = $'
debug "Found header: #{header_found[1].inspect}"
while txt.empty?
candidate = header_found[PAR_REGEX]
break unless candidate
txt = candidate.ircify_html
header_found = $'
txt.sub!(strip, '') if strip
end
end
# If we haven't found a first par yet, try to get it from the whole
# document
if txt.empty?
header_found = xml
while txt.empty?
candidate = header_found[PAR_REGEX]
break unless candidate
txt = candidate.ircify_html
header_found = $'
txt.sub!(strip, '') if strip
end
end
return txt
end
# Get the first pars of the first _count_ _urls_.
# The pages are downloaded using an HttpUtil service passed as _opts_ :http_util,
# and echoed as replies to the IRC message passed as _opts_ :message.
#
def Utils.get_first_pars(urls, count, opts={})
idx = 0
msg = opts[:message]
while count > 0 and urls.length > 0
url = urls.shift
idx += 1
# FIXME what happens if some big file is returned? We should share
# code with the url plugin to only retrieve partial file content!
xml = opts[:http_util].get_cached(url)
if xml.nil?
debug "Unable to retrieve #{url}"
next
end
par = Utils.ircify_first_html_par(xml, opts)
if par.empty?
debug "No first par found\n#{xml}"
# FIXME only do this if the 'url' plugin is loaded
# TODO even better, put the code here
# par = @bot.plugins['url'].get_title_from_html(xml)
next if par.empty?
end
msg.reply "[#{idx}] #{par}", :overlong => :truncate if msg
count -=1
end
end
end
end
|