github/plexpy
1
0
Fork 0
mirror of https://github.com/Tautulli/Tautulli.git synced 2025-07-06 13:11:15 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

Update dnspython-2.2.0

Browse source
This commit is contained in:
JonnyWong16 2021-10-14 21:36:41 -07:00
parent 4b28040d59
commit 4d62245cf5
No known key found for this signature in database
GPG key ID: B1F1F9807184697A
111 changed files with 9077 additions and 5877 deletions
Download patch file Download diff file Expand all files Collapse all files

372
lib/dns/tokenizer.py
View file

@ -1,4 +1,6 @@
# Copyright (C) 2003-2007, 2009-2011 Nominum, Inc.
# Copyright (C) Dnspython Contributors, see LICENSE for text of ISC license
# Copyright (C) 2003-2017 Nominum, Inc.
#
# Permission to use, copy, modify, and distribute this software and its
# documentation for any purpose with or without fee is hereby granted,
@ -15,24 +17,15 @@
"""Tokenize DNS master file format"""
from io import StringIO
import io
import sys
import dns.exception
import dns.name
import dns.ttl
from ._compat import long, text_type, binary_type
_DELIMITERS = {
' ': True,
'\t': True,
'\n': True,
';': True,
'(': True,
')': True,
'"': True}
_QUOTING_DELIMITERS = {'"': True}
_DELIMITERS = {' ', '\t', '\n', ';', '(', ')', '"'}
_QUOTING_DELIMITERS = {'"'}
EOF = 0
EOL = 1
@ -44,32 +37,20 @@ DELIMITER = 6
class UngetBufferFull(dns.exception.DNSException):
"""An attempt was made to unget a token when the unget buffer was full."""
class Token(object):
class Token:
"""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
ttype: The token type
value: The token value
has_escape: Does the token value contain escapes?
"""
def __init__(self, ttype, value='', has_escape=False):
"""Initialize a token instance.
"""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
@ -92,11 +73,11 @@ class Token(object):
def is_comment(self):
return self.ttype == COMMENT
def is_delimiter(self):
def is_delimiter(self): # pragma: no cover (we don't return delimiters yet)
return self.ttype == DELIMITER
def is_eol_or_eof(self):
return (self.ttype == EOL or self.ttype == EOF)
return self.ttype == EOL or self.ttype == EOF
def __eq__(self, other):
if not isinstance(other, Token):
@ -142,72 +123,120 @@ class Token(object):
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
def unescape_to_bytes(self):
# We used to use unescape() for TXT-like records, but this
# caused problems as we'd process DNS escapes into Unicode code
# points instead of byte values, and then a to_text() of the
# processed data would not equal the original input. For
# example, \226 in the TXT record would have a to_text() of
# \195\162 because we applied UTF-8 encoding to Unicode code
# point 226.
#
# We now apply escapes while converting directly to bytes,
# avoiding this double encoding.
#
# This code also handles cases where the unicode input has
# non-ASCII code-points in it by converting it to UTF-8. TXT
# records aren't defined for Unicode, but this is the best we
# can do to preserve meaning. For example,
#
# foo\u200bbar
#
# (where \u200b is Unicode code point 0x200b) will be treated
# as if the input had been the UTF-8 encoding of that string,
# namely:
#
# foo\226\128\139bar
#
unescaped = b''
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
unescaped += b'%c' % (int(c) * 100 + int(c2) * 10 + int(c3))
else:
# Note that as mentioned above, if c is a Unicode
# code point outside of the ASCII range, then this
# += is converting that code point to its UTF-8
# encoding and appending multiple bytes to
# unescaped.
unescaped += c.encode()
else:
unescaped += c.encode()
return Token(self.ttype, bytes(unescaped))
class Tokenizer(object):
class Tokenizer:
"""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.
A token object is basically a (type, value) tuple. 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
file: The file to tokenize
ungotten_char: The most recently ungotten character, or None.
ungotten_token: The most recently ungotten token, or None.
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
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
eof: This variable is true if the tokenizer has encountered EOF.
delimiters: The current delimiter dictionary.
line_number: The current line number
filename: A filename that will be returned by the where() method.
idna_codec: A dns.name.IDNACodec, specifies the IDNA
encoder/decoder. If None, the default IDNA 2003
encoder/decoder is used.
"""
def __init__(self, f=sys.stdin, filename=None):
def __init__(self, f=sys.stdin, filename=None, idna_codec=None):
"""Initialize a tokenizer instance.
@param f: The file to tokenize. The default is sys.stdin.
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
filename: the name of the filename that the where() method
will return.
@type filename: string
idna_codec: A dns.name.IDNACodec, specifies the IDNA
encoder/decoder. If None, the default IDNA 2003
encoder/decoder is used.
"""
if isinstance(f, text_type):
f = StringIO(f)
if isinstance(f, str):
f = io.StringIO(f)
if filename is None:
filename = '<string>'
elif isinstance(f, binary_type):
f = StringIO(f.decode())
elif isinstance(f, bytes):
f = io.StringIO(f.decode())
if filename is None:
filename = '<string>'
else:
@ -225,10 +254,12 @@ class Tokenizer(object):
self.delimiters = _DELIMITERS
self.line_number = 1
self.filename = filename
if idna_codec is None:
idna_codec = dns.name.IDNA_2003
self.idna_codec = idna_codec
def _get_char(self):
"""Read a character from input.
@rtype: string
"""
if self.ungotten_char is None:
@ -248,7 +279,7 @@ class Tokenizer(object):
def where(self):
"""Return the current location in the input.
@rtype: (string, int) tuple. The first item is the filename of
Returns a (string, int) tuple. The first item is the filename of
the input, the second is the current line number.
"""
@ -261,13 +292,13 @@ class Tokenizer(object):
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
c: the character to unget
raises UngetBufferFull: there is already an ungotten char
"""
if self.ungotten_char is not None:
raise UngetBufferFull
# this should never happen!
raise UngetBufferFull # pragma: no cover
self.ungotten_char = c
def skip_whitespace(self):
@ -278,7 +309,7 @@ class Tokenizer(object):
If the tokenizer is in multiline mode, then newlines are whitespace.
@rtype: int
Returns the number of characters skipped.
"""
skipped = 0
@ -293,15 +324,17 @@ class Tokenizer(object):
def get(self, want_leading=False, want_comment=False):
"""Get the next token.
@param want_leading: If True, return a WHITESPACE token if the
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
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
Raises dns.exception.UnexpectedEnd: input ended prematurely
Raises dns.exception.SyntaxError: input was badly formed
Returns a Token.
"""
if self.ungotten_token is not None:
@ -332,7 +365,7 @@ class Tokenizer(object):
self.skip_whitespace()
continue
elif c == ')':
if not self.multiline > 0:
if self.multiline <= 0:
raise dns.exception.SyntaxError
self.multiline -= 1
self.skip_whitespace()
@ -379,23 +412,8 @@ class Tokenizer(object):
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 self.quoting and c == '\n':
raise dns.exception.SyntaxError('newline in quoted string')
elif c == '\\':
#
# It's an escape. Put it and the next character into
@ -420,9 +438,9 @@ class Tokenizer(object):
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
token: the token to unget
Raises UngetBufferFull: there is already an ungotten token
"""
if self.ungotten_token is not None:
@ -431,7 +449,8 @@ class Tokenizer(object):
def next(self):
"""Return the next item in an iteration.
@rtype: (int, string)
Returns a Token.
"""
token = self.get()
@ -446,11 +465,12 @@ class Tokenizer(object):
# Helpers
def get_int(self):
"""Read the next token and interpret it as an integer.
def get_int(self, base=10):
"""Read the next token and interpret it as an unsigned integer.
@raises dns.exception.SyntaxError:
@rtype: int
Raises dns.exception.SyntaxError if not an unsigned integer.
Returns an int.
"""
token = self.get().unescape()
@ -458,14 +478,15 @@ class Tokenizer(object):
raise dns.exception.SyntaxError('expecting an identifier')
if not token.value.isdigit():
raise dns.exception.SyntaxError('expecting an integer')
return int(token.value)
return int(token.value, base)
def get_uint8(self):
"""Read the next token and interpret it as an 8-bit unsigned
integer.
@raises dns.exception.SyntaxError:
@rtype: int
Raises dns.exception.SyntaxError if not an 8-bit unsigned integer.
Returns an int.
"""
value = self.get_int()
@ -474,56 +495,63 @@ class Tokenizer(object):
'%d is not an unsigned 8-bit integer' % value)
return value
def get_uint16(self):
def get_uint16(self, base=10):
"""Read the next token and interpret it as a 16-bit unsigned
integer.
@raises dns.exception.SyntaxError:
@rtype: int
Raises dns.exception.SyntaxError if not a 16-bit unsigned integer.
Returns an int.
"""
value = self.get_int()
value = self.get_int(base=base)
if value < 0 or value > 65535:
raise dns.exception.SyntaxError(
'%d is not an unsigned 16-bit integer' % value)
if base == 8:
raise dns.exception.SyntaxError(
'%o is not an octal unsigned 16-bit integer' % value)
else:
raise dns.exception.SyntaxError(
'%d is not an unsigned 16-bit integer' % value)
return value
def get_uint32(self):
def get_uint32(self, base=10):
"""Read the next token and interpret it as a 32-bit unsigned
integer.
@raises dns.exception.SyntaxError:
@rtype: int
Raises dns.exception.SyntaxError if not a 32-bit unsigned integer.
Returns an 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 = long(token.value)
if value < 0 or value > long(4294967296):
value = self.get_int(base=base)
if value < 0 or value > 4294967295:
raise dns.exception.SyntaxError(
'%d is not an unsigned 32-bit integer' % value)
return value
def get_string(self, origin=None):
def get_string(self, max_length=None):
"""Read the next token and interpret it as a string.
@raises dns.exception.SyntaxError:
@rtype: string
Raises dns.exception.SyntaxError if not a string.
Raises dns.exception.SyntaxError if token value length
exceeds max_length (if specified).
Returns a string.
"""
token = self.get().unescape()
if not (token.is_identifier() or token.is_quoted_string()):
raise dns.exception.SyntaxError('expecting a string')
if max_length and len(token.value) > max_length:
raise dns.exception.SyntaxError("string too long")
return token.value
def get_identifier(self, origin=None):
"""Read the next token and raise an exception if it is not an identifier.
def get_identifier(self):
"""Read the next token, which should be an identifier.
@raises dns.exception.SyntaxError:
@rtype: string
Raises dns.exception.SyntaxError if not an identifier.
Returns a string.
"""
token = self.get().unescape()
@ -531,23 +559,53 @@ class Tokenizer(object):
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.
def concatenate_remaining_identifiers(self):
"""Read the remaining tokens on the line, which should be identifiers.
@raises dns.exception.SyntaxError:
@rtype: dns.name.Name object"""
Raises dns.exception.SyntaxError if a token is seen that is not an
identifier.
token = self.get()
Returns a string containing a concatenation of the remaining
identifiers.
"""
s = ""
while True:
token = self.get().unescape()
if token.is_eol_or_eof():
break
if not token.is_identifier():
raise dns.exception.SyntaxError
s += token.value
return s
def as_name(self, token, origin=None, relativize=False, relativize_to=None):
"""Try to interpret the token as a DNS name.
Raises dns.exception.SyntaxError if not a name.
Returns a dns.name.Name.
"""
if not token.is_identifier():
raise dns.exception.SyntaxError('expecting an identifier')
return dns.name.from_text(token.value, origin)
name = dns.name.from_text(token.value, origin, self.idna_codec)
return name.choose_relativity(relativize_to or origin, relativize)
def get_name(self, origin=None, relativize=False, relativize_to=None):
"""Read the next token and interpret it as a DNS name.
Raises dns.exception.SyntaxError if not a name.
Returns a dns.name.Name.
"""
token = self.get()
return self.as_name(token, origin, relativize, relativize_to)
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
Returns a string.
"""
token = self.get()
@ -558,6 +616,14 @@ class Tokenizer(object):
return token.value
def get_ttl(self):
"""Read the next token and interpret it as a DNS TTL.
Raises dns.exception.SyntaxError or dns.ttl.BadTTL if not an
identifier or badly formed.
Returns an int.
"""
token = self.get().unescape()
if not token.is_identifier():
raise dns.exception.SyntaxError('expecting an identifier')