File size: 13,827 Bytes
d1ceb73 |
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 |
import time
from .exceptions import EOF, TIMEOUT
class Expecter(object):
def __init__(self, spawn, searcher, searchwindowsize=-1):
self.spawn = spawn
self.searcher = searcher
# A value of -1 means to use the figure from spawn, which should
# be None or a positive number.
if searchwindowsize == -1:
searchwindowsize = spawn.searchwindowsize
self.searchwindowsize = searchwindowsize
self.lookback = None
if hasattr(searcher, 'longest_string'):
self.lookback = searcher.longest_string
def do_search(self, window, freshlen):
spawn = self.spawn
searcher = self.searcher
if freshlen > len(window):
freshlen = len(window)
index = searcher.search(window, freshlen, self.searchwindowsize)
if index >= 0:
spawn._buffer = spawn.buffer_type()
spawn._buffer.write(window[searcher.end:])
spawn.before = spawn._before.getvalue()[
0:-(len(window) - searcher.start)]
spawn._before = spawn.buffer_type()
spawn._before.write(window[searcher.end:])
spawn.after = window[searcher.start:searcher.end]
spawn.match = searcher.match
spawn.match_index = index
# Found a match
return index
elif self.searchwindowsize or self.lookback:
maintain = self.searchwindowsize or self.lookback
if spawn._buffer.tell() > maintain:
spawn._buffer = spawn.buffer_type()
spawn._buffer.write(window[-maintain:])
def existing_data(self):
# First call from a new call to expect_loop or expect_async.
# self.searchwindowsize may have changed.
# Treat all data as fresh.
spawn = self.spawn
before_len = spawn._before.tell()
buf_len = spawn._buffer.tell()
freshlen = before_len
if before_len > buf_len:
if not self.searchwindowsize:
spawn._buffer = spawn.buffer_type()
window = spawn._before.getvalue()
spawn._buffer.write(window)
elif buf_len < self.searchwindowsize:
spawn._buffer = spawn.buffer_type()
spawn._before.seek(
max(0, before_len - self.searchwindowsize))
window = spawn._before.read()
spawn._buffer.write(window)
else:
spawn._buffer.seek(max(0, buf_len - self.searchwindowsize))
window = spawn._buffer.read()
else:
if self.searchwindowsize:
spawn._buffer.seek(max(0, buf_len - self.searchwindowsize))
window = spawn._buffer.read()
else:
window = spawn._buffer.getvalue()
return self.do_search(window, freshlen)
def new_data(self, data):
# A subsequent call, after a call to existing_data.
spawn = self.spawn
freshlen = len(data)
spawn._before.write(data)
if not self.searchwindowsize:
if self.lookback:
# search lookback + new data.
old_len = spawn._buffer.tell()
spawn._buffer.write(data)
spawn._buffer.seek(max(0, old_len - self.lookback))
window = spawn._buffer.read()
else:
# copy the whole buffer (really slow for large datasets).
spawn._buffer.write(data)
window = spawn.buffer
else:
if len(data) >= self.searchwindowsize or not spawn._buffer.tell():
window = data[-self.searchwindowsize:]
spawn._buffer = spawn.buffer_type()
spawn._buffer.write(window[-self.searchwindowsize:])
else:
spawn._buffer.write(data)
new_len = spawn._buffer.tell()
spawn._buffer.seek(max(0, new_len - self.searchwindowsize))
window = spawn._buffer.read()
return self.do_search(window, freshlen)
def eof(self, err=None):
spawn = self.spawn
spawn.before = spawn._before.getvalue()
spawn._buffer = spawn.buffer_type()
spawn._before = spawn.buffer_type()
spawn.after = EOF
index = self.searcher.eof_index
if index >= 0:
spawn.match = EOF
spawn.match_index = index
return index
else:
spawn.match = None
spawn.match_index = None
msg = str(spawn)
msg += '\nsearcher: %s' % self.searcher
if err is not None:
msg = str(err) + '\n' + msg
exc = EOF(msg)
exc.__cause__ = None # in Python 3.x we can use "raise exc from None"
raise exc
def timeout(self, err=None):
spawn = self.spawn
spawn.before = spawn._before.getvalue()
spawn.after = TIMEOUT
index = self.searcher.timeout_index
if index >= 0:
spawn.match = TIMEOUT
spawn.match_index = index
return index
else:
spawn.match = None
spawn.match_index = None
msg = str(spawn)
msg += '\nsearcher: %s' % self.searcher
if err is not None:
msg = str(err) + '\n' + msg
exc = TIMEOUT(msg)
exc.__cause__ = None # in Python 3.x we can use "raise exc from None"
raise exc
def errored(self):
spawn = self.spawn
spawn.before = spawn._before.getvalue()
spawn.after = None
spawn.match = None
spawn.match_index = None
def expect_loop(self, timeout=-1):
"""Blocking expect"""
spawn = self.spawn
if timeout is not None:
end_time = time.time() + timeout
try:
idx = self.existing_data()
if idx is not None:
return idx
while True:
# No match at this point
if (timeout is not None) and (timeout < 0):
return self.timeout()
# Still have time left, so read more data
incoming = spawn.read_nonblocking(spawn.maxread, timeout)
if self.spawn.delayafterread is not None:
time.sleep(self.spawn.delayafterread)
idx = self.new_data(incoming)
# Keep reading until exception or return.
if idx is not None:
return idx
if timeout is not None:
timeout = end_time - time.time()
except EOF as e:
return self.eof(e)
except TIMEOUT as e:
return self.timeout(e)
except:
self.errored()
raise
class searcher_string(object):
'''This is a plain string search helper for the spawn.expect_any() method.
This helper class is for speed. For more powerful regex patterns
see the helper class, searcher_re.
Attributes:
eof_index - index of EOF, or -1
timeout_index - index of TIMEOUT, or -1
After a successful match by the search() method the following attributes
are available:
start - index into the buffer, first byte of match
end - index into the buffer, first byte after match
match - the matching string itself
'''
def __init__(self, strings):
'''This creates an instance of searcher_string. This argument 'strings'
may be a list; a sequence of strings; or the EOF or TIMEOUT types. '''
self.eof_index = -1
self.timeout_index = -1
self._strings = []
self.longest_string = 0
for n, s in enumerate(strings):
if s is EOF:
self.eof_index = n
continue
if s is TIMEOUT:
self.timeout_index = n
continue
self._strings.append((n, s))
if len(s) > self.longest_string:
self.longest_string = len(s)
def __str__(self):
'''This returns a human-readable string that represents the state of
the object.'''
ss = [(ns[0], ' %d: %r' % ns) for ns in self._strings]
ss.append((-1, 'searcher_string:'))
if self.eof_index >= 0:
ss.append((self.eof_index, ' %d: EOF' % self.eof_index))
if self.timeout_index >= 0:
ss.append((self.timeout_index,
' %d: TIMEOUT' % self.timeout_index))
ss.sort()
ss = list(zip(*ss))[1]
return '\n'.join(ss)
def search(self, buffer, freshlen, searchwindowsize=None):
'''This searches 'buffer' for the first occurrence of one of the search
strings. 'freshlen' must indicate the number of bytes at the end of
'buffer' which have not been searched before. It helps to avoid
searching the same, possibly big, buffer over and over again.
See class spawn for the 'searchwindowsize' argument.
If there is a match this returns the index of that string, and sets
'start', 'end' and 'match'. Otherwise, this returns -1. '''
first_match = None
# 'freshlen' helps a lot here. Further optimizations could
# possibly include:
#
# using something like the Boyer-Moore Fast String Searching
# Algorithm; pre-compiling the search through a list of
# strings into something that can scan the input once to
# search for all N strings; realize that if we search for
# ['bar', 'baz'] and the input is '...foo' we need not bother
# rescanning until we've read three more bytes.
#
# Sadly, I don't know enough about this interesting topic. /grahn
for index, s in self._strings:
if searchwindowsize is None:
# the match, if any, can only be in the fresh data,
# or at the very end of the old data
offset = -(freshlen + len(s))
else:
# better obey searchwindowsize
offset = -searchwindowsize
n = buffer.find(s, offset)
if n >= 0 and (first_match is None or n < first_match):
first_match = n
best_index, best_match = index, s
if first_match is None:
return -1
self.match = best_match
self.start = first_match
self.end = self.start + len(self.match)
return best_index
class searcher_re(object):
'''This is regular expression string search helper for the
spawn.expect_any() method. This helper class is for powerful
pattern matching. For speed, see the helper class, searcher_string.
Attributes:
eof_index - index of EOF, or -1
timeout_index - index of TIMEOUT, or -1
After a successful match by the search() method the following attributes
are available:
start - index into the buffer, first byte of match
end - index into the buffer, first byte after match
match - the re.match object returned by a successful re.search
'''
def __init__(self, patterns):
'''This creates an instance that searches for 'patterns' Where
'patterns' may be a list or other sequence of compiled regular
expressions, or the EOF or TIMEOUT types.'''
self.eof_index = -1
self.timeout_index = -1
self._searches = []
for n, s in enumerate(patterns):
if s is EOF:
self.eof_index = n
continue
if s is TIMEOUT:
self.timeout_index = n
continue
self._searches.append((n, s))
def __str__(self):
'''This returns a human-readable string that represents the state of
the object.'''
#ss = [(n, ' %d: re.compile("%s")' %
# (n, repr(s.pattern))) for n, s in self._searches]
ss = list()
for n, s in self._searches:
ss.append((n, ' %d: re.compile(%r)' % (n, s.pattern)))
ss.append((-1, 'searcher_re:'))
if self.eof_index >= 0:
ss.append((self.eof_index, ' %d: EOF' % self.eof_index))
if self.timeout_index >= 0:
ss.append((self.timeout_index, ' %d: TIMEOUT' %
self.timeout_index))
ss.sort()
ss = list(zip(*ss))[1]
return '\n'.join(ss)
def search(self, buffer, freshlen, searchwindowsize=None):
'''This searches 'buffer' for the first occurrence of one of the regular
expressions. 'freshlen' must indicate the number of bytes at the end of
'buffer' which have not been searched before.
See class spawn for the 'searchwindowsize' argument.
If there is a match this returns the index of that string, and sets
'start', 'end' and 'match'. Otherwise, returns -1.'''
first_match = None
# 'freshlen' doesn't help here -- we cannot predict the
# length of a match, and the re module provides no help.
if searchwindowsize is None:
searchstart = 0
else:
searchstart = max(0, len(buffer) - searchwindowsize)
for index, s in self._searches:
match = s.search(buffer, searchstart)
if match is None:
continue
n = match.start()
if first_match is None or n < first_match:
first_match = n
the_match = match
best_index = index
if first_match is None:
return -1
self.start = first_match
self.match = the_match
self.end = self.match.end()
return best_index
|