def __init__(self, parent, name, nbytes,
description="Padding", pattern=None):
""" pattern is None or repeated string """
assert (pattern is None) or (isinstance(pattern, str))
Bytes.__init__(self, parent, name, nbytes, description)
self.pattern = pattern
self._display_pattern = self.checkPattern()
def __init__(self,
parent,
name,
nbytes,
description="Padding",
pattern=None):
""" pattern is None or repeated string """
assert (pattern is None) or (isinstance(pattern, str))
Bytes.__init__(self, parent, name, nbytes, description)
self.pattern = pattern
self._display_pattern = self.checkPattern()
def __init__(self, parent, name, length, description=None,
parser=None, filename=None, mime_type=None, parser_class=None):
if filename:
if not isinstance(filename, unicode):
filename = makePrintable(filename, "ISO-8859-1")
if not description:
description = 'File "%s" (%s)' % (filename, humanFilesize(length))
Bytes.__init__(self, parent, name, length, description)
def createInputStream(cis, **args):
tags = args.setdefault("tags",[])
if parser_class:
tags.append(( "class", parser_class ))
if parser is not None:
tags.append(( "id", parser.PARSER_TAGS["id"] ))
if mime_type:
tags.append(( "mime", mime_type ))
if filename:
tags.append(( "filename", filename ))
return cis(**args)
self.setSubIStream(createInputStream)
def __init__(self, parent, name, format, description=None,
strip=None, charset=None, nbytes=None, truncate=None):
Bytes.__init__(self, parent, name, 1, description)
# Is format valid?
assert format in self.VALID_FORMATS
# Store options
self._format = format
self._strip = strip
self._truncate = truncate
# Check charset and compute character size in bytes
# (or None when it's not possible to guess character size)
if not charset or charset in self.CHARSET_8BIT:
self._character_size = 1 # one byte per character
elif charset in self.UTF_CHARSET:
self._character_size = None
else:
raise FieldError("Invalid charset for %s: \"%s\"" %
(self.path, charset))
self._charset = charset
# It is a fixed string?
if nbytes is not None:
assert self._format == "fixed"
# Arbitrary limits, just to catch some bugs...
if not (1 <= nbytes <= 0xffff):
raise FieldError("Invalid string size for %s: %s" %
(self.path, nbytes))
self._content_size = nbytes # content length in bytes
self._size = nbytes * 8
self._content_offset = 0
else:
# Format with a suffix: Find the end of the string
if self._format in self.SUFFIX_FORMAT:
self._content_offset = 0
# Choose the suffix
suffix = self.suffix_str
# Find the suffix
length = self._parent.stream.searchBytesLength(
suffix, False, self.absolute_address)
if length is None:
raise FieldError("Unable to find end of string %s (format %s)!"
% (self.path, self._format))
if 1 < len(suffix):
# Fix length for little endian bug with UTF-xx charset:
# u"abc" -> "a\0b\0c\0\0\0" (UTF-16-LE)
# search returns length=5, whereas real lenght is 6
length = alignValue(length, len(suffix))
# Compute sizes
self._content_size = length # in bytes
self._size = (length + len(suffix)) * 8
# Format with a prefix: Read prefixed length in bytes
else:
assert self._format in self.PASCAL_FORMATS
# Get the prefix size
prefix_size = self.PASCAL_FORMATS[self._format]
self._content_offset = prefix_size
# Read the prefix and compute sizes
value = self._parent.stream.readBits(
self.absolute_address, prefix_size*8, self._parent.endian)
self._content_size = value # in bytes
self._size = (prefix_size + value) * 8
# For UTF-16 and UTF-32, choose the right charset using BOM
if self._charset in self.UTF_CHARSET:
# Charset requires a BOM?
bomsize, endian = self.UTF_CHARSET[self._charset]
if endian == "BOM":
# Read the BOM value
nbytes = bomsize // 8
bom = self._parent.stream.readBytes(self.absolute_address, nbytes)
# Choose right charset using the BOM
bom_endian = self.UTF_BOM[bomsize]
if bom not in bom_endian:
raise FieldError("String %s has invalid BOM (%s)!"
% (self.path, repr(bom)))
self._charset = bom_endian[bom]
self._content_size -= nbytes
self._content_offset += nbytes
# Compute length in character if possible
if self._character_size:
self._length = self._content_size // self._character_size
else:
self._length = None
def __init__(self, parent):
Bytes.__init__(self, parent, 'file', parent['size'].value, None)
def __init__(self,
parent,
name,
format,
description=None,
strip=None,
charset=None,
nbytes=None,
truncate=None):
Bytes.__init__(self, parent, name, 1, description)
# Is format valid?
assert format in self.VALID_FORMATS
# Store options
self._format = format
self._strip = strip
self._truncate = truncate
# Check charset and compute character size in bytes
# (or None when it's not possible to guess character size)
if not charset or charset in self.CHARSET_8BIT:
self._character_size = 1 # one byte per character
elif charset in self.UTF_CHARSET:
self._character_size = None
else:
raise FieldError("Invalid charset for %s: \"%s\"" %
(self.path, charset))
self._charset = charset
# It is a fixed string?
if nbytes is not None:
assert self._format == "fixed"
# Arbitrary limits, just to catch some bugs...
if not (1 <= nbytes <= 0xffff):
raise FieldError("Invalid string size for %s: %s" %
(self.path, nbytes))
self._content_size = nbytes # content length in bytes
self._size = nbytes * 8
self._content_offset = 0
else:
# Format with a suffix: Find the end of the string
if self._format in self.SUFFIX_FORMAT:
self._content_offset = 0
# Choose the suffix
suffix = self.suffix_str
# Find the suffix
length = self._parent.stream.searchBytesLength(
suffix, False, self.absolute_address)
if length is None:
raise FieldError(
"Unable to find end of string %s (format %s)!" %
(self.path, self._format))
if 1 < len(suffix):
# Fix length for little endian bug with UTF-xx charset:
# u"abc" -> "a\0b\0c\0\0\0" (UTF-16-LE)
# search returns length=5, whereas real lenght is 6
length = alignValue(length, len(suffix))
# Compute sizes
self._content_size = length # in bytes
self._size = (length + len(suffix)) * 8
# Format with a prefix: Read prefixed length in bytes
else:
assert self._format in self.PASCAL_FORMATS
# Get the prefix size
prefix_size = self.PASCAL_FORMATS[self._format]
self._content_offset = prefix_size
# Read the prefix and compute sizes
value = self._parent.stream.readBits(self.absolute_address,
prefix_size * 8,
self._parent.endian)
self._content_size = value # in bytes
self._size = (prefix_size + value) * 8
# For UTF-16 and UTF-32, choose the right charset using BOM
if self._charset in self.UTF_CHARSET:
# Charset requires a BOM?
bomsize, endian = self.UTF_CHARSET[self._charset]
if endian == "BOM":
# Read the BOM value
nbytes = bomsize // 8
bom = self._parent.stream.readBytes(self.absolute_address,
nbytes)
# Choose right charset using the BOM
bom_endian = self.UTF_BOM[bomsize]
if bom not in bom_endian:
raise FieldError("String %s has invalid BOM (%s)!" %
(self.path, repr(bom)))
self._charset = bom_endian[bom]
self._content_size -= nbytes
self._content_offset += nbytes
# Compute length in character if possible
if self._character_size:
self._length = self._content_size // self._character_size
else:
self._length = None
def __init__(self, parent, name):
Bytes.__init__(self, parent, name, 16)