/usr/lib/python3/dist-packages/dns/tokenizer.py is in python3-dnspython 1.11.1-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 | # Copyright (C) 2003-2007, 2009-2011 Nominum, Inc.
#
# Permission to use, copy, modify, and distribute this software and its
# documentation for any purpose with or without fee is hereby granted,
# provided that the above copyright notice and this permission notice
# appear in all copies.
#
# THE SOFTWARE IS PROVIDED "AS IS" AND NOMINUM DISCLAIMS ALL WARRANTIES
# WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
# MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL NOMINUM BE LIABLE FOR
# ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
# WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
# ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT
# OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
"""Tokenize DNS master file format"""
import io
import sys
import dns.exception
import dns.name
import dns.ttl
_DELIMITERS = frozenset(' \t\n;()"')
_QUOTING_DELIMITERS = frozenset('"')
EOF = 0
EOL = 1
WHITESPACE = 2
IDENTIFIER = 3
QUOTED_STRING = 4
COMMENT = 5
DELIMITER = 6
class UngetBufferFull(dns.exception.DNSException):
"""Raised when an attempt is made to unget a token when the unget
buffer is full."""
pass
class Token(object):
"""A DNS master file format token.
@ivar ttype: The token type
@type ttype: int
@ivar value: The token value
@type value: string
@ivar has_escape: Does the token value contain escapes?
@type has_escape: bool
"""
def __init__(self, ttype, value='', has_escape=False):
"""Initialize a token instance.
@param ttype: The token type
@type ttype: int
@param value: The token value
@type value: string
@param has_escape: Does the token value contain escapes?
@type has_escape: bool
"""
self.ttype = ttype
self.value = value
self.has_escape = has_escape
def is_eof(self):
return self.ttype == EOF
def is_eol(self):
return self.ttype == EOL
def is_whitespace(self):
return self.ttype == WHITESPACE
def is_identifier(self):
return self.ttype == IDENTIFIER
def is_quoted_string(self):
return self.ttype == QUOTED_STRING
def is_comment(self):
return self.ttype == COMMENT
def is_delimiter(self):
return self.ttype == DELIMITER
def is_eol_or_eof(self):
return (self.ttype == EOL or self.ttype == EOF)
def __eq__(self, other):
if not isinstance(other, Token):
return False
return (self.ttype == other.ttype and
self.value == other.value)
def __ne__(self, other):
if not isinstance(other, Token):
return True
return (self.ttype != other.ttype or
self.value != other.value)
def __str__(self):
return '%d "%s"' % (self.ttype, self.value)
def unescape(self):
if not self.has_escape:
return self
unescaped = ''
l = len(self.value)
i = 0
while i < l:
c = self.value[i]
i += 1
if c == '\\':
if i >= l:
raise dns.exception.UnexpectedEnd
c = self.value[i]
i += 1
if c.isdigit():
if i >= l:
raise dns.exception.UnexpectedEnd
c2 = self.value[i]
i += 1
if i >= l:
raise dns.exception.UnexpectedEnd
c3 = self.value[i]
i += 1
if not (c2.isdigit() and c3.isdigit()):
raise dns.exception.SyntaxError
c = chr(int(c) * 100 + int(c2) * 10 + int(c3))
unescaped += c
return Token(self.ttype, unescaped)
# compatibility for old-style tuple tokens
def __len__(self):
return 2
def __iter__(self):
return iter((self.ttype, self.value))
def __getitem__(self, i):
if i == 0:
return self.ttype
elif i == 1:
return self.value
else:
raise IndexError
class Tokenizer(object):
"""A DNS master file format tokenizer.
A token is a (type, value) tuple, where I{type} is an int, and
I{value} is a string. The valid types are EOF, EOL, WHITESPACE,
IDENTIFIER, QUOTED_STRING, COMMENT, and DELIMITER.
@ivar file: The file to tokenize
@type file: file
@ivar ungotten_char: The most recently ungotten character, or None.
@type ungotten_char: string
@ivar ungotten_token: The most recently ungotten token, or None.
@type ungotten_token: (int, string) token tuple
@ivar multiline: The current multiline level. This value is increased
by one every time a '(' delimiter is read, and decreased by one every time
a ')' delimiter is read.
@type multiline: int
@ivar quoting: This variable is true if the tokenizer is currently
reading a quoted string.
@type quoting: bool
@ivar eof: This variable is true if the tokenizer has encountered EOF.
@type eof: bool
@ivar delimiters: The current delimiter dictionary.
@type delimiters: dict
@ivar line_number: The current line number
@type line_number: int
@ivar filename: A filename that will be returned by the L{where} method.
@type filename: string
"""
def __init__(self, f=sys.stdin, filename=None):
"""Initialize a tokenizer instance.
@param f: The file to tokenize. The default is sys.stdin.
This parameter may also be a string, in which case the tokenizer
will take its input from the contents of the string.
@type f: file or string
@param filename: the name of the filename that the L{where} method
will return.
@type filename: string
"""
if isinstance(f, str):
f = io.StringIO(f)
if filename is None:
filename = '<string>'
else:
if filename is None:
if f is sys.stdin:
filename = '<stdin>'
else:
filename = '<file>'
self.file = f
self.ungotten_char = None
self.ungotten_token = None
self.multiline = 0
self.quoting = False
self.eof = False
self.delimiters = _DELIMITERS
self.line_number = 1
self.filename = filename
def _get_char(self):
"""Read a character from input.
@rtype: string
"""
if self.ungotten_char is None:
if self.eof:
c = ''
else:
c = self.file.read(1)
if c == '':
self.eof = True
elif c == '\n':
self.line_number += 1
else:
c = self.ungotten_char
self.ungotten_char = None
return c
def where(self):
"""Return the current location in the input.
@rtype: (string, int) tuple. The first item is the filename of
the input, the second is the current line number.
"""
return (self.filename, self.line_number)
def _unget_char(self, c):
"""Unget a character.
The unget buffer for characters is only one character large; it is
an error to try to unget a character when the unget buffer is not
empty.
@param c: the character to unget
@type c: string
@raises UngetBufferFull: there is already an ungotten char
"""
if not self.ungotten_char is None:
raise UngetBufferFull
self.ungotten_char = c
def skip_whitespace(self):
"""Consume input until a non-whitespace character is encountered.
The non-whitespace character is then ungotten, and the number of
whitespace characters consumed is returned.
If the tokenizer is in multiline mode, then newlines are whitespace.
@rtype: int
"""
skipped = 0
while True:
c = self._get_char()
if c != ' ' and c != '\t':
if (c != '\n') or not self.multiline:
self._unget_char(c)
return skipped
skipped += 1
def get(self, want_leading = False, want_comment = False):
"""Get the next token.
@param want_leading: If True, return a WHITESPACE token if the
first character read is whitespace. The default is False.
@type want_leading: bool
@param want_comment: If True, return a COMMENT token if the
first token read is a comment. The default is False.
@type want_comment: bool
@rtype: Token object
@raises dns.exception.UnexpectedEnd: input ended prematurely
@raises dns.exception.SyntaxError: input was badly formed
"""
if not self.ungotten_token is None:
token = self.ungotten_token
self.ungotten_token = None
if token.is_whitespace():
if want_leading:
return token
elif token.is_comment():
if want_comment:
return token
else:
return token
skipped = self.skip_whitespace()
if want_leading and skipped > 0:
return Token(WHITESPACE, ' ')
token = ''
ttype = IDENTIFIER
has_escape = False
while True:
c = self._get_char()
if c == '' or c in self.delimiters:
if c == '' and self.quoting:
raise dns.exception.UnexpectedEnd
if token == '' and ttype != QUOTED_STRING:
if c == '(':
self.multiline += 1
self.skip_whitespace()
continue
elif c == ')':
if not self.multiline > 0:
raise dns.exception.SyntaxError
self.multiline -= 1
self.skip_whitespace()
continue
elif c == '"':
if not self.quoting:
self.quoting = True
self.delimiters = _QUOTING_DELIMITERS
ttype = QUOTED_STRING
continue
else:
self.quoting = False
self.delimiters = _DELIMITERS
self.skip_whitespace()
continue
elif c == '\n':
return Token(EOL, '\n')
elif c == ';':
while 1:
c = self._get_char()
if c == '\n' or c == '':
break
token += c
if want_comment:
self._unget_char(c)
return Token(COMMENT, token)
elif c == '':
if self.multiline:
raise dns.exception.SyntaxError('unbalanced parentheses')
return Token(EOF)
elif self.multiline:
self.skip_whitespace()
token = ''
continue
else:
return Token(EOL, '\n')
else:
# This code exists in case we ever want a
# delimiter to be returned. It never produces
# a token currently.
token = c
ttype = DELIMITER
else:
self._unget_char(c)
break
elif self.quoting:
if c == '\\':
c = self._get_char()
if c == '':
raise dns.exception.UnexpectedEnd
if c.isdigit():
c2 = self._get_char()
if c2 == '':
raise dns.exception.UnexpectedEnd
c3 = self._get_char()
if c == '':
raise dns.exception.UnexpectedEnd
if not (c2.isdigit() and c3.isdigit()):
raise dns.exception.SyntaxError
c = chr(int(c) * 100 + int(c2) * 10 + int(c3))
elif c == '\n':
raise dns.exception.SyntaxError('newline in quoted string')
elif c == '\\':
#
# It's an escape. Put it and the next character into
# the token; it will be checked later for goodness.
#
token += c
has_escape = True
c = self._get_char()
if c == '' or c == '\n':
raise dns.exception.UnexpectedEnd
token += c
if token == '' and ttype != QUOTED_STRING:
if self.multiline:
raise dns.exception.SyntaxError('unbalanced parentheses')
ttype = EOF
return Token(ttype, token, has_escape)
def unget(self, token):
"""Unget a token.
The unget buffer for tokens is only one token large; it is
an error to try to unget a token when the unget buffer is not
empty.
@param token: the token to unget
@type token: Token object
@raises UngetBufferFull: there is already an ungotten token
"""
if not self.ungotten_token is None:
raise UngetBufferFull
self.ungotten_token = token
def __next__(self):
"""Return the next item in an iteration.
@rtype: (int, string)
"""
token = self.get()
if token.is_eof():
raise StopIteration
return token
def __iter__(self):
return self
# Helpers
def get_int(self):
"""Read the next token and interpret it as an integer.
@raises dns.exception.SyntaxError:
@rtype: int
"""
token = self.get().unescape()
if not token.is_identifier():
raise dns.exception.SyntaxError('expecting an identifier')
if not token.value.isdigit():
raise dns.exception.SyntaxError('expecting an integer')
return int(token.value)
def get_uint8(self):
"""Read the next token and interpret it as an 8-bit unsigned
integer.
@raises dns.exception.SyntaxError:
@rtype: int
"""
value = self.get_int()
if value < 0 or value > 255:
raise dns.exception.SyntaxError('%d is not an unsigned 8-bit integer' % value)
return value
def get_uint16(self):
"""Read the next token and interpret it as a 16-bit unsigned
integer.
@raises dns.exception.SyntaxError:
@rtype: int
"""
value = self.get_int()
if value < 0 or value > 65535:
raise dns.exception.SyntaxError('%d is not an unsigned 16-bit integer' % value)
return value
def get_uint32(self):
"""Read the next token and interpret it as a 32-bit unsigned
integer.
@raises dns.exception.SyntaxError:
@rtype: int
"""
token = self.get().unescape()
if not token.is_identifier():
raise dns.exception.SyntaxError('expecting an identifier')
if not token.value.isdigit():
raise dns.exception.SyntaxError('expecting an integer')
value = int(token.value)
if value < 0 or value > 4294967296:
raise dns.exception.SyntaxError('%d is not an unsigned 32-bit integer' % value)
return value
def get_string(self, origin=None):
"""Read the next token and interpret it as a string.
@raises dns.exception.SyntaxError:
@rtype: string
"""
token = self.get().unescape()
if not (token.is_identifier() or token.is_quoted_string()):
raise dns.exception.SyntaxError('expecting a string')
return token.value
def get_identifier(self, origin=None):
"""Read the next token and raise an exception if it is not an identifier.
@raises dns.exception.SyntaxError:
@rtype: string
"""
token = self.get().unescape()
if not token.is_identifier():
raise dns.exception.SyntaxError('expecting an identifier')
return token.value
def get_name(self, origin=None):
"""Read the next token and interpret it as a DNS name.
@raises dns.exception.SyntaxError:
@rtype: dns.name.Name object"""
token = self.get()
if not token.is_identifier():
raise dns.exception.SyntaxError('expecting an identifier')
return dns.name.from_text(token.value, origin)
def get_eol(self):
"""Read the next token and raise an exception if it isn't EOL or
EOF.
@raises dns.exception.SyntaxError:
@rtype: string
"""
token = self.get()
if not token.is_eol_or_eof():
raise dns.exception.SyntaxError('expected EOL or EOF, got %d "%s"' % (token.ttype, token.value))
return token.value
def get_ttl(self):
token = self.get().unescape()
if not token.is_identifier():
raise dns.exception.SyntaxError('expecting an identifier')
return dns.ttl.from_text(token.value)
|