Added errors argument to TarFile class that allows the user to
specify an error handling scheme for character conversion. Additional
scheme "utf-8" in read mode. Unicode input filenames are now
supported by design. The values of the pax_headers dictionary are now
limited to unicode objects.
Fixed: The prefix field is no longer used in PAX_FORMAT (in
conformance with POSIX).
Fixed: In read mode use a possible pax header size field.
Fixed: Strip trailing slashes from pax header name values.
Fixed: Give values in user-specified pax_headers precedence when
writing.
Added unicode tests. Added pax/regtype4 member to testtar.tar all
possible number fields in a pax header.
Added two chapters to the documentation about the different formats
tarfile.py supports and how unicode issues are handled.
diff --git a/Lib/tarfile.py b/Lib/tarfile.py
index 4f4a1d9..107041e 100644
--- a/Lib/tarfile.py
+++ b/Lib/tarfile.py
@@ -125,6 +125,17 @@
PAX_FIELDS = ("path", "linkpath", "size", "mtime",
"uid", "gid", "uname", "gname")
+# Fields in a pax header that are numbers, all other fields
+# are treated as strings.
+PAX_NUMBER_FIELDS = {
+ "atime": float,
+ "ctime": float,
+ "mtime": float,
+ "uid": int,
+ "gid": int,
+ "size": int
+}
+
#---------------------------------------------------------
# Bits used in the mode field, values in octal.
#---------------------------------------------------------
@@ -154,7 +165,7 @@
#---------------------------------------------------------
ENCODING = sys.getfilesystemencoding()
if ENCODING is None:
- ENCODING = "ascii"
+ ENCODING = sys.getdefaultencoding()
#---------------------------------------------------------
# Some useful functions
@@ -218,6 +229,26 @@
s = chr(0200) + s
return s
+def uts(s, encoding, errors):
+ """Convert a unicode object to a string.
+ """
+ if errors == "utf-8":
+ # An extra error handler similar to the -o invalid=UTF-8 option
+ # in POSIX.1-2001. Replace untranslatable characters with their
+ # UTF-8 representation.
+ try:
+ return s.encode(encoding, "strict")
+ except UnicodeEncodeError:
+ x = []
+ for c in s:
+ try:
+ x.append(c.encode(encoding, "strict"))
+ except UnicodeEncodeError:
+ x.append(c.encode("utf8"))
+ return "".join(x)
+ else:
+ return s.encode(encoding, errors)
+
def calc_chksums(buf):
"""Calculate the checksum for a member's header by summing up all
characters except for the chksum field which is treated as if
@@ -922,7 +953,7 @@
def __repr__(self):
return "<%s %r at %#x>" % (self.__class__.__name__,self.name,id(self))
- def get_info(self):
+ def get_info(self, encoding, errors):
"""Return the TarInfo's attributes as a dictionary.
"""
info = {
@@ -944,24 +975,29 @@
if info["type"] == DIRTYPE and not info["name"].endswith("/"):
info["name"] += "/"
+ for key in ("name", "linkname", "uname", "gname"):
+ if type(info[key]) is unicode:
+ info[key] = info[key].encode(encoding, errors)
+
return info
- def tobuf(self, format=DEFAULT_FORMAT, encoding=ENCODING):
+ def tobuf(self, format=DEFAULT_FORMAT, encoding=ENCODING, errors="strict"):
"""Return a tar header as a string of 512 byte blocks.
"""
+ info = self.get_info(encoding, errors)
+
if format == USTAR_FORMAT:
- return self.create_ustar_header()
+ return self.create_ustar_header(info)
elif format == GNU_FORMAT:
- return self.create_gnu_header()
+ return self.create_gnu_header(info)
elif format == PAX_FORMAT:
- return self.create_pax_header(encoding)
+ return self.create_pax_header(info, encoding, errors)
else:
raise ValueError("invalid format")
- def create_ustar_header(self):
+ def create_ustar_header(self, info):
"""Return the object as a ustar header block.
"""
- info = self.get_info()
info["magic"] = POSIX_MAGIC
if len(info["linkname"]) > LENGTH_LINK:
@@ -972,10 +1008,9 @@
return self._create_header(info, USTAR_FORMAT)
- def create_gnu_header(self):
+ def create_gnu_header(self, info):
"""Return the object as a GNU header block sequence.
"""
- info = self.get_info()
info["magic"] = GNU_MAGIC
buf = ""
@@ -987,12 +1022,11 @@
return buf + self._create_header(info, GNU_FORMAT)
- def create_pax_header(self, encoding):
+ def create_pax_header(self, info, encoding, errors):
"""Return the object as a ustar header block. If it cannot be
represented this way, prepend a pax extended header sequence
with supplement information.
"""
- info = self.get_info()
info["magic"] = POSIX_MAGIC
pax_headers = self.pax_headers.copy()
@@ -1002,7 +1036,11 @@
("name", "path", LENGTH_NAME), ("linkname", "linkpath", LENGTH_LINK),
("uname", "uname", 32), ("gname", "gname", 32)):
- val = info[name].decode(encoding)
+ if hname in pax_headers:
+ # The pax header has priority.
+ continue
+
+ val = info[name].decode(encoding, errors)
# Try to encode the string as ASCII.
try:
@@ -1011,27 +1049,23 @@
pax_headers[hname] = val
continue
- if len(val) > length:
- if name == "name":
- # Try to squeeze a longname in the prefix and name fields as in
- # ustar format.
- try:
- info["prefix"], info["name"] = self._posix_split_name(info["name"])
- except ValueError:
- pax_headers[hname] = val
- else:
- continue
- else:
- pax_headers[hname] = val
+ if len(info[name]) > length:
+ pax_headers[hname] = val
# Test number fields for values that exceed the field limit or values
# that like to be stored as float.
for name, digits in (("uid", 8), ("gid", 8), ("size", 12), ("mtime", 12)):
+ if name in pax_headers:
+ # The pax header has priority. Avoid overflow.
+ info[name] = 0
+ continue
+
val = info[name]
if not 0 <= val < 8 ** (digits - 1) or isinstance(val, float):
pax_headers[name] = unicode(val)
info[name] = 0
+ # Create a pax extended header if necessary.
if pax_headers:
buf = self._create_pax_generic_header(pax_headers)
else:
@@ -1040,26 +1074,10 @@
return buf + self._create_header(info, USTAR_FORMAT)
@classmethod
- def create_pax_global_header(cls, pax_headers, encoding):
+ def create_pax_global_header(cls, pax_headers):
"""Return the object as a pax global header block sequence.
"""
- new_headers = {}
- for key, val in pax_headers.iteritems():
- key = cls._to_unicode(key, encoding)
- val = cls._to_unicode(val, encoding)
- new_headers[key] = val
- return cls._create_pax_generic_header(new_headers, type=XGLTYPE)
-
- @staticmethod
- def _to_unicode(value, encoding):
- if isinstance(value, unicode):
- return value
- elif isinstance(value, (int, long, float)):
- return unicode(value)
- elif isinstance(value, str):
- return unicode(value, encoding)
- else:
- raise ValueError("unable to convert to unicode: %r" % value)
+ return cls._create_pax_generic_header(pax_headers, type=XGLTYPE)
def _posix_split_name(self, name):
"""Split a name longer than 100 chars into a prefix
@@ -1091,9 +1109,9 @@
" ", # checksum field
info.get("type", REGTYPE),
stn(info.get("linkname", ""), 100),
- stn(info.get("magic", ""), 8),
- stn(info.get("uname", ""), 32),
- stn(info.get("gname", ""), 32),
+ stn(info.get("magic", POSIX_MAGIC), 8),
+ stn(info.get("uname", "root"), 32),
+ stn(info.get("gname", "root"), 32),
itn(info.get("devmajor", 0), 8, format),
itn(info.get("devminor", 0), 8, format),
stn(info.get("prefix", ""), 155)
@@ -1254,12 +1272,9 @@
offset += self._block(self.size)
tarfile.offset = offset
- # Patch the TarInfo object with saved extended
+ # Patch the TarInfo object with saved global
# header information.
- for keyword, value in tarfile.pax_headers.iteritems():
- if keyword in PAX_FIELDS:
- setattr(self, keyword, value)
- self.pax_headers[keyword] = value
+ self._apply_pax_info(tarfile.pax_headers, tarfile.encoding, tarfile.errors)
return self
@@ -1270,18 +1285,17 @@
buf = tarfile.fileobj.read(self._block(self.size))
# Fetch the next header and process it.
- b = tarfile.fileobj.read(BLOCKSIZE)
- t = self.frombuf(b)
- t.offset = self.offset
- next = t._proc_member(tarfile)
+ next = self.fromtarfile(tarfile)
+ if next is None:
+ raise HeaderError("missing subsequent header")
# Patch the TarInfo object from the next header with
# the longname information.
next.offset = self.offset
if self.type == GNUTYPE_LONGNAME:
- next.name = buf.rstrip(NUL)
+ next.name = nts(buf)
elif self.type == GNUTYPE_LONGLINK:
- next.linkname = buf.rstrip(NUL)
+ next.linkname = nts(buf)
return next
@@ -1356,21 +1370,10 @@
else:
pax_headers = tarfile.pax_headers.copy()
- # Fields in POSIX.1-2001 that are numbers, all other fields
- # are treated as UTF-8 strings.
- type_mapping = {
- "atime": float,
- "ctime": float,
- "mtime": float,
- "uid": int,
- "gid": int,
- "size": int
- }
-
# Parse pax header information. A record looks like that:
# "%d %s=%s\n" % (length, keyword, value). length is the size
# of the complete record including the length field itself and
- # the newline.
+ # the newline. keyword and value are both UTF-8 encoded strings.
regex = re.compile(r"(\d+) ([^=]+)=", re.U)
pos = 0
while True:
@@ -1383,35 +1386,55 @@
value = buf[match.end(2) + 1:match.start(1) + length - 1]
keyword = keyword.decode("utf8")
- keyword = keyword.encode(tarfile.encoding)
-
value = value.decode("utf8")
- if keyword in type_mapping:
- try:
- value = type_mapping[keyword](value)
- except ValueError:
- value = 0
- else:
- value = value.encode(tarfile.encoding)
pax_headers[keyword] = value
pos += length
- # Fetch the next header that will be patched with the
- # supplement information from the pax header (extended
- # only).
- t = self.fromtarfile(tarfile)
+ # Fetch the next header.
+ next = self.fromtarfile(tarfile)
- if self.type != XGLTYPE and t is not None:
- # Patch the TarInfo object from the next header with
- # the pax header's information.
- for keyword, value in pax_headers.items():
- if keyword in PAX_FIELDS:
- setattr(t, keyword, value)
- pax_headers[keyword] = value
- t.pax_headers = pax_headers.copy()
+ if self.type in (XHDTYPE, SOLARIS_XHDTYPE):
+ if next is None:
+ raise HeaderError("missing subsequent header")
- return t
+ # Patch the TarInfo object with the extended header info.
+ next._apply_pax_info(pax_headers, tarfile.encoding, tarfile.errors)
+ next.offset = self.offset
+
+ if pax_headers.has_key("size"):
+ # If the extended header replaces the size field,
+ # we need to recalculate the offset where the next
+ # header starts.
+ offset = next.offset_data
+ if next.isreg() or next.type not in SUPPORTED_TYPES:
+ offset += next._block(next.size)
+ tarfile.offset = offset
+
+ return next
+
+ def _apply_pax_info(self, pax_headers, encoding, errors):
+ """Replace fields with supplemental information from a previous
+ pax extended or global header.
+ """
+ for keyword, value in pax_headers.iteritems():
+ if keyword not in PAX_FIELDS:
+ continue
+
+ if keyword == "path":
+ value = value.rstrip("/")
+
+ if keyword in PAX_NUMBER_FIELDS:
+ try:
+ value = PAX_NUMBER_FIELDS[keyword](value)
+ except ValueError:
+ value = 0
+ else:
+ value = uts(value, encoding, errors)
+
+ setattr(self, keyword, value)
+
+ self.pax_headers = pax_headers.copy()
def _block(self, count):
"""Round up a byte count by BLOCKSIZE and return it,
@@ -1462,8 +1485,9 @@
format = DEFAULT_FORMAT # The format to use when creating an archive.
- encoding = ENCODING # Transfer UTF-8 strings from POSIX.1-2001
- # headers to this encoding.
+ encoding = ENCODING # Encoding for 8-bit character strings.
+
+ errors = None # Error handler for unicode conversion.
tarinfo = TarInfo # The default TarInfo class to use.
@@ -1471,7 +1495,7 @@
def __init__(self, name=None, mode="r", fileobj=None, format=None,
tarinfo=None, dereference=None, ignore_zeros=None, encoding=None,
- pax_headers=None, debug=None, errorlevel=None):
+ errors=None, pax_headers=None, debug=None, errorlevel=None):
"""Open an (uncompressed) tar archive `name'. `mode' is either 'r' to
read from an existing archive, 'a' to append data to an existing
file or 'w' to create a new file overwriting an existing one. `mode'
@@ -1512,6 +1536,19 @@
self.ignore_zeros = ignore_zeros
if encoding is not None:
self.encoding = encoding
+
+ if errors is not None:
+ self.errors = errors
+ elif mode == "r":
+ self.errors = "utf-8"
+ else:
+ self.errors = "strict"
+
+ if pax_headers is not None and self.format == PAX_FORMAT:
+ self.pax_headers = pax_headers
+ else:
+ self.pax_headers = {}
+
if debug is not None:
self.debug = debug
if errorlevel is not None:
@@ -1524,7 +1561,6 @@
self.offset = 0L # current position in the archive file
self.inodes = {} # dictionary caching the inodes of
# archive members already added
- self.pax_headers = {} # save contents of global pax headers
if self.mode == "r":
self.firstmember = None
@@ -1543,9 +1579,8 @@
if self.mode in "aw":
self._loaded = True
- if pax_headers:
- buf = self.tarinfo.create_pax_global_header(
- pax_headers.copy(), self.encoding)
+ if self.pax_headers:
+ buf = self.tarinfo.create_pax_global_header(self.pax_headers.copy())
self.fileobj.write(buf)
self.offset += len(buf)
@@ -1817,8 +1852,6 @@
self.inodes[inode] = arcname
elif stat.S_ISDIR(stmd):
type = DIRTYPE
- if arcname[-1:] != "/":
- arcname += "/"
elif stat.S_ISFIFO(stmd):
type = FIFOTYPE
elif stat.S_ISLNK(stmd):
@@ -1952,7 +1985,7 @@
tarinfo = copy.copy(tarinfo)
- buf = tarinfo.tobuf(self.format, self.encoding)
+ buf = tarinfo.tobuf(self.format, self.encoding, self.errors)
self.fileobj.write(buf)
self.offset += len(buf)