[Python-checkins] r55617 - in python/trunk: Doc/lib/libtarfile.tex Lib/tarfile.py Lib/test/test_tarfile.py Lib/test/testtar.tar Misc/NEWS
lars.gustaebel
python-checkins at python.org
Sun May 27 21:49:32 CEST 2007
Author: lars.gustaebel
Date: Sun May 27 21:49:30 2007
New Revision: 55617
Modified:
python/trunk/Doc/lib/libtarfile.tex
python/trunk/Lib/tarfile.py
python/trunk/Lib/test/test_tarfile.py
python/trunk/Lib/test/testtar.tar
python/trunk/Misc/NEWS
Log:
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.
Modified: python/trunk/Doc/lib/libtarfile.tex
==============================================================================
--- python/trunk/Doc/lib/libtarfile.tex (original)
+++ python/trunk/Doc/lib/libtarfile.tex Sun May 27 21:49:30 2007
@@ -133,24 +133,20 @@
\versionadded{2.6}
\end{excdesc}
+Each of the following constants defines a tar archive format that the
+\module{tarfile} module is able to create. See section \ref{tar-formats} for
+details.
+
\begin{datadesc}{USTAR_FORMAT}
- \POSIX{}.1-1988 (ustar) format. It supports filenames up to a length of
- at best 256 characters and linknames up to 100 characters. The maximum
- file size is 8 gigabytes. This is an old and limited but widely
- supported format.
+ \POSIX{}.1-1988 (ustar) format.
\end{datadesc}
\begin{datadesc}{GNU_FORMAT}
- GNU tar format. It supports arbitrarily long filenames and linknames and
- files bigger than 8 gigabytes. It is the defacto standard on GNU/Linux
- systems.
+ GNU tar format.
\end{datadesc}
\begin{datadesc}{PAX_FORMAT}
- \POSIX{}.1-2001 (pax) format. It is the most flexible format with
- virtually no limits. It supports long filenames and linknames, large files
- and stores pathnames in a portable way. However, not all tar
- implementations today are able to handle pax archives properly.
+ \POSIX{}.1-2001 (pax) format.
\end{datadesc}
\begin{datadesc}{DEFAULT_FORMAT}
@@ -175,15 +171,15 @@
The \class{TarFile} object provides an interface to a tar archive. A tar
archive is a sequence of blocks. An archive member (a stored file) is made up
-of a header block followed by data blocks. It is possible, to store a file in a
+of a header block followed by data blocks. It is possible to store a file in a
tar archive several times. Each archive member is represented by a
\class{TarInfo} object, see \citetitle{TarInfo Objects} (section
\ref{tarinfo-objects}) for details.
\begin{classdesc}{TarFile}{name=None, mode='r', fileobj=None,
format=DEFAULT_FORMAT, tarinfo=TarInfo, dereference=False,
- ignore_zeros=False, encoding=None, pax_headers=None, debug=0,
- errorlevel=0}
+ ignore_zeros=False, encoding=None, errors=None, pax_headers=None,
+ debug=0, errorlevel=0}
All following arguments are optional and can be accessed as instance
attributes as well.
@@ -231,18 +227,14 @@
If \code{2}, all \emph{non-fatal} errors are raised as \exception{TarError}
exceptions as well.
- The \var{encoding} argument defines the local character encoding. It
- defaults to the value from \function{sys.getfilesystemencoding()} or if
- that is \code{None} to \code{"ascii"}. \var{encoding} is used only in
- connection with the pax format which stores text data in \emph{UTF-8}. If
- it is not set correctly, character conversion will fail with a
- \exception{UnicodeError}.
+ The \var{encoding} and \var{errors} arguments control the way strings are
+ converted to unicode objects and vice versa. The default settings will work
+ for most users. See section \ref{tar-unicode} for in-depth information.
\versionadded{2.6}
- The \var{pax_headers} argument must be a dictionary whose elements are
- either unicode objects, numbers or strings that can be decoded to unicode
- using \var{encoding}. This information will be added to the archive as a
- pax global header.
+ The \var{pax_headers} argument is an optional dictionary of unicode strings
+ which will be added as a pax global header if \var{format} is
+ \constant{PAX_FORMAT}.
\versionadded{2.6}
\end{classdesc}
@@ -287,7 +279,7 @@
Extract all members from the archive to the current working directory
or directory \var{path}. If optional \var{members} is given, it must be
a subset of the list returned by \method{getmembers()}.
- Directory informations like owner, modification time and permissions are
+ Directory information like owner, modification time and permissions are
set after all members have been extracted. This is done to work around two
problems: A directory's modification time is reset each time a file is
created in it. And, if a directory's permissions do not allow writing,
@@ -365,6 +357,11 @@
\deprecated{2.6}{Use the \member{format} attribute instead.}
\end{memberdesc}
+\begin{memberdesc}{pax_headers}
+ A dictionary containing key-value pairs of pax global headers.
+ \versionadded{2.6}
+\end{memberdesc}
+
%-----------------
% TarInfo Objects
%-----------------
@@ -384,8 +381,8 @@
Create a \class{TarInfo} object.
\end{classdesc}
-\begin{methoddesc}{frombuf}{}
- Create and return a \class{TarInfo} object from a string buffer.
+\begin{methoddesc}{frombuf}{buf}
+ Create and return a \class{TarInfo} object from string buffer \var{buf}.
\versionadded[Raises \exception{HeaderError} if the buffer is
invalid.]{2.6}
\end{methoddesc}
@@ -396,10 +393,11 @@
\versionadded{2.6}
\end{methoddesc}
-\begin{methoddesc}{tobuf}{\optional{format}}
- Create a string buffer from a \class{TarInfo} object. See
- \class{TarFile}'s \member{format} argument for information.
- \versionchanged[The \var{format} parameter]{2.6}
+\begin{methoddesc}{tobuf}{\optional{format\optional{, encoding
+ \optional{, errors}}}}
+ Create a string buffer from a \class{TarInfo} object. For information
+ on the arguments see the constructor of the \class{TarFile} class.
+ \versionchanged[The arguments were added]{2.6}
\end{methoddesc}
A \code{TarInfo} object has the following public data attributes:
@@ -452,6 +450,12 @@
Group name.
\end{memberdesc}
+\begin{memberdesc}{pax_headers}
+ A dictionary containing key-value pairs of an associated pax
+ extended header.
+ \versionadded{2.6}
+\end{memberdesc}
+
A \class{TarInfo} object also provides some convenient query methods:
\begin{methoddesc}{isfile}{}
@@ -554,3 +558,103 @@
tar.extract(tarinfo)
tar.close()
\end{verbatim}
+
+%------------
+% Tar format
+%------------
+
+\subsection{Supported tar formats \label{tar-formats}}
+
+There are three tar formats that can be created with the \module{tarfile}
+module:
+
+\begin{itemize}
+
+\item
+The \POSIX{}.1-1988 ustar format (\constant{USTAR_FORMAT}). It supports
+filenames up to a length of at best 256 characters and linknames up to 100
+characters. The maximum file size is 8 gigabytes. This is an old and limited
+but widely supported format.
+
+\item
+The GNU tar format (\constant{GNU_FORMAT}). It supports long filenames and
+linknames, files bigger than 8 gigabytes and sparse files. It is the de facto
+standard on GNU/Linux systems. \module{tarfile} fully supports the GNU tar
+extensions for long names, sparse file support is read-only.
+
+\item
+The \POSIX{}.1-2001 pax format (\constant{PAX_FORMAT}). It is the most
+flexible format with virtually no limits. It supports long filenames and
+linknames, large files and stores pathnames in a portable way. However, not
+all tar implementations today are able to handle pax archives properly.
+
+The \emph{pax} format is an extension to the existing \emph{ustar} format. It
+uses extra headers for information that cannot be stored otherwise. There are
+two flavours of pax headers: Extended headers only affect the subsequent file
+header, global headers are valid for the complete archive and affect all
+following files. All the data in a pax header is encoded in \emph{UTF-8} for
+portability reasons.
+
+\end{itemize}
+
+There are some more variants of the tar format which can be read, but not
+created:
+
+\begin{itemize}
+
+\item
+The ancient V7 format. This is the first tar format from \UNIX{} Seventh
+Edition, storing only regular files and directories. Names must not be longer
+than 100 characters, there is no user/group name information. Some archives
+have miscalculated header checksums in case of fields with non-\ASCII{}
+characters.
+
+\item
+The SunOS tar extended format. This format is a variant of the \POSIX{}.1-2001
+pax format, but is not compatible.
+
+\end{itemize}
+
+%----------------
+% Unicode issues
+%----------------
+
+\subsection{Unicode issues \label{tar-unicode}}
+
+The tar format was originally conceived to make backups on tape drives with the
+main focus on preserving file system information. Nowadays tar archives are
+commonly used for file distribution and exchanging archives over networks. One
+problem of the original format (that all other formats are merely variants of)
+is that there is no concept of supporting different character encodings.
+For example, an ordinary tar archive created on a \emph{UTF-8} system cannot be
+read correctly on a \emph{Latin-1} system if it contains non-\ASCII{}
+characters. Names (i.e. filenames, linknames, user/group names) containing
+these characters will appear damaged. Unfortunately, there is no way to
+autodetect the encoding of an archive.
+
+The pax format was designed to solve this problem. It stores non-\ASCII{} names
+using the universal character encoding \emph{UTF-8}. When a pax archive is
+read, these \emph{UTF-8} names are converted to the encoding of the local
+file system.
+
+The details of unicode conversion are controlled by the \var{encoding} and
+\var{errors} keyword arguments of the \class{TarFile} class.
+
+The default value for \var{encoding} is the local character encoding. It is
+deduced from \function{sys.getfilesystemencoding()} and
+\function{sys.getdefaultencoding()}. In read mode, \var{encoding} is used
+exclusively to convert unicode names from a pax archive to strings in the local
+character encoding. In write mode, the use of \var{encoding} depends on the
+chosen archive format. In case of \constant{PAX_FORMAT}, input names that
+contain non-\ASCII{} characters need to be decoded before being stored as
+\emph{UTF-8} strings. The other formats do not make use of \var{encoding}
+unless unicode objects are used as input names. These are converted to
+8-bit character strings before they are added to the archive.
+
+The \var{errors} argument defines how characters are treated that cannot be
+converted to or from \var{encoding}. Possible values are listed in section
+\ref{codec-base-classes}. In read mode, there is an additional scheme
+\code{'utf-8'} which means that bad characters are replaced by their
+\emph{UTF-8} representation. This is the default scheme. In write mode the
+default value for \var{errors} is \code{'strict'} to ensure that name
+information is not altered unnoticed.
Modified: python/trunk/Lib/tarfile.py
==============================================================================
--- python/trunk/Lib/tarfile.py (original)
+++ python/trunk/Lib/tarfile.py Sun May 27 21:49:30 2007
@@ -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:
+
+ pax_headers[keyword] = value
+ pos += length
+
+ # Fetch the next header.
+ next = self.fromtarfile(tarfile)
+
+ if self.type in (XHDTYPE, SOLARIS_XHDTYPE):
+ if next is None:
+ raise HeaderError("missing subsequent header")
+
+ # 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 = type_mapping[keyword](value)
+ value = PAX_NUMBER_FIELDS[keyword](value)
except ValueError:
value = 0
else:
- value = value.encode(tarfile.encoding)
-
- pax_headers[keyword] = value
- pos += length
+ value = uts(value, encoding, errors)
- # Fetch the next header that will be patched with the
- # supplement information from the pax header (extended
- # only).
- t = 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()
+ setattr(self, keyword, value)
- return t
+ 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)
Modified: python/trunk/Lib/test/test_tarfile.py
==============================================================================
--- python/trunk/Lib/test/test_tarfile.py (original)
+++ python/trunk/Lib/test/test_tarfile.py Sun May 27 21:49:30 2007
@@ -1,4 +1,4 @@
-# encoding: iso8859-1
+# -*- coding: iso-8859-15 -*-
import sys
import os
@@ -372,9 +372,9 @@
def test_read_longname(self):
# Test reading of longname (bug #1471427).
- name = self.subdir + "/" + "123/" * 125 + "longname"
+ longname = self.subdir + "/" + "123/" * 125 + "longname"
try:
- tarinfo = self.tar.getmember(name)
+ tarinfo = self.tar.getmember(longname)
except KeyError:
self.fail("longname not found")
self.assert_(tarinfo.type != tarfile.DIRTYPE, "read longname as dirtype")
@@ -393,13 +393,24 @@
tarinfo = self.tar.getmember(longname)
offset = tarinfo.offset
self.tar.fileobj.seek(offset)
- fobj = StringIO.StringIO(self.tar.fileobj.read(1536))
+ fobj = StringIO.StringIO(self.tar.fileobj.read(3 * 512))
self.assertRaises(tarfile.ReadError, tarfile.open, name="foo.tar", fileobj=fobj)
+ def test_header_offset(self):
+ # Test if the start offset of the TarInfo object includes
+ # the preceding extended header.
+ longname = self.subdir + "/" + "123/" * 125 + "longname"
+ offset = self.tar.getmember(longname).offset
+ fobj = open(tarname)
+ fobj.seek(offset)
+ tarinfo = tarfile.TarInfo.frombuf(fobj.read(512))
+ self.assertEqual(tarinfo.type, self.longnametype)
+
class GNUReadTest(LongnameTest):
subdir = "gnu"
+ longnametype = tarfile.GNUTYPE_LONGNAME
def test_sparse_file(self):
tarinfo1 = self.tar.getmember("ustar/sparse")
@@ -410,26 +421,40 @@
"sparse file extraction failed")
-class PaxReadTest(ReadTest):
+class PaxReadTest(LongnameTest):
subdir = "pax"
+ longnametype = tarfile.XHDTYPE
- def test_pax_globheaders(self):
+ def test_pax_global_headers(self):
tar = tarfile.open(tarname, encoding="iso8859-1")
+
tarinfo = tar.getmember("pax/regtype1")
self.assertEqual(tarinfo.uname, "foo")
self.assertEqual(tarinfo.gname, "bar")
- self.assertEqual(tarinfo.pax_headers.get("VENDOR.umlauts"), "ÄÖÜäöüß")
+ self.assertEqual(tarinfo.pax_headers.get("VENDOR.umlauts"), u"ÄÖÜäöüß")
tarinfo = tar.getmember("pax/regtype2")
self.assertEqual(tarinfo.uname, "")
self.assertEqual(tarinfo.gname, "bar")
- self.assertEqual(tarinfo.pax_headers.get("VENDOR.umlauts"), "ÄÖÜäöüß")
+ self.assertEqual(tarinfo.pax_headers.get("VENDOR.umlauts"), u"ÄÖÜäöüß")
tarinfo = tar.getmember("pax/regtype3")
self.assertEqual(tarinfo.uname, "tarfile")
self.assertEqual(tarinfo.gname, "tarfile")
- self.assertEqual(tarinfo.pax_headers.get("VENDOR.umlauts"), "ÄÖÜäöüß")
+ self.assertEqual(tarinfo.pax_headers.get("VENDOR.umlauts"), u"ÄÖÜäöüß")
+
+ def test_pax_number_fields(self):
+ # All following number fields are read from the pax header.
+ tar = tarfile.open(tarname, encoding="iso8859-1")
+ tarinfo = tar.getmember("pax/regtype4")
+ self.assertEqual(tarinfo.size, 7011)
+ self.assertEqual(tarinfo.uid, 123)
+ self.assertEqual(tarinfo.gid, 123)
+ self.assertEqual(tarinfo.mtime, 1041808783.0)
+ self.assertEqual(type(tarinfo.mtime), float)
+ self.assertEqual(float(tarinfo.pax_headers["atime"]), 1041808783.0)
+ self.assertEqual(float(tarinfo.pax_headers["ctime"]), 1041808783.0)
class WriteTest(unittest.TestCase):
@@ -700,68 +725,161 @@
n = tar.getmembers()[0].name
self.assert_(name == n, "PAX longname creation failed")
- def test_iso8859_15_filename(self):
- self._test_unicode_filename("iso8859-15")
+ def test_pax_global_header(self):
+ pax_headers = {
+ u"foo": u"bar",
+ u"uid": u"0",
+ u"mtime": u"1.23",
+ u"test": u"äöü",
+ u"äöü": u"test"}
+
+ tar = tarfile.open(tmpname, "w", format=tarfile.PAX_FORMAT, \
+ pax_headers=pax_headers)
+ tar.addfile(tarfile.TarInfo("test"))
+ tar.close()
+
+ # Test if the global header was written correctly.
+ tar = tarfile.open(tmpname, encoding="iso8859-1")
+ self.assertEqual(tar.pax_headers, pax_headers)
+ self.assertEqual(tar.getmembers()[0].pax_headers, pax_headers)
+
+ # Test if all the fields are unicode.
+ for key, val in tar.pax_headers.iteritems():
+ self.assert_(type(key) is unicode)
+ self.assert_(type(val) is unicode)
+ if key in tarfile.PAX_NUMBER_FIELDS:
+ try:
+ tarfile.PAX_NUMBER_FIELDS[key](val)
+ except (TypeError, ValueError):
+ self.fail("unable to convert pax header field")
+
+ def test_pax_extended_header(self):
+ # The fields from the pax header have priority over the
+ # TarInfo.
+ pax_headers = {u"path": u"foo", u"uid": u"123"}
+
+ tar = tarfile.open(tmpname, "w", format=tarfile.PAX_FORMAT, encoding="iso8859-1")
+ t = tarfile.TarInfo()
+ t.name = u"äöü" # non-ASCII
+ t.uid = 8**8 # too large
+ t.pax_headers = pax_headers
+ tar.addfile(t)
+ tar.close()
+
+ tar = tarfile.open(tmpname, encoding="iso8859-1")
+ t = tar.getmembers()[0]
+ self.assertEqual(t.pax_headers, pax_headers)
+ self.assertEqual(t.name, "foo")
+ self.assertEqual(t.uid, 123)
+
+
+class UstarUnicodeTest(unittest.TestCase):
+ # All *UnicodeTests FIXME
+
+ format = tarfile.USTAR_FORMAT
+
+ def test_iso8859_1_filename(self):
+ self._test_unicode_filename("iso8859-1")
+
+ def test_utf7_filename(self):
+ self._test_unicode_filename("utf7")
def test_utf8_filename(self):
self._test_unicode_filename("utf8")
- def test_utf16_filename(self):
- self._test_unicode_filename("utf16")
-
def _test_unicode_filename(self, encoding):
- tar = tarfile.open(tmpname, "w", format=tarfile.PAX_FORMAT)
- name = u"\u20ac".encode(encoding) # Euro sign
- tar.encoding = encoding
+ tar = tarfile.open(tmpname, "w", format=self.format, encoding=encoding, errors="strict")
+ name = u"äöü"
tar.addfile(tarfile.TarInfo(name))
tar.close()
tar = tarfile.open(tmpname, encoding=encoding)
- self.assertEqual(tar.getmembers()[0].name, name)
+ self.assert_(type(tar.getnames()[0]) is not unicode)
+ self.assertEqual(tar.getmembers()[0].name, name.encode(encoding))
tar.close()
def test_unicode_filename_error(self):
- # The euro sign filename cannot be translated to iso8859-1 encoding.
- tar = tarfile.open(tmpname, "w", format=tarfile.PAX_FORMAT, encoding="utf8")
- name = u"\u20ac".encode("utf8") # Euro sign
- tar.addfile(tarfile.TarInfo(name))
+ tar = tarfile.open(tmpname, "w", format=self.format, encoding="ascii", errors="strict")
+ tarinfo = tarfile.TarInfo()
+
+ tarinfo.name = "äöü"
+ if self.format == tarfile.PAX_FORMAT:
+ self.assertRaises(UnicodeError, tar.addfile, tarinfo)
+ else:
+ tar.addfile(tarinfo)
+
+ tarinfo.name = u"äöü"
+ self.assertRaises(UnicodeError, tar.addfile, tarinfo)
+
+ tarinfo.name = "foo"
+ tarinfo.uname = u"äöü"
+ self.assertRaises(UnicodeError, tar.addfile, tarinfo)
+
+ def test_unicode_argument(self):
+ tar = tarfile.open(tarname, "r", encoding="iso8859-1", errors="strict")
+ for t in tar:
+ self.assert_(type(t.name) is str)
+ self.assert_(type(t.linkname) is str)
+ self.assert_(type(t.uname) is str)
+ self.assert_(type(t.gname) is str)
tar.close()
- self.assertRaises(UnicodeError, tarfile.open, tmpname, encoding="iso8859-1")
+ def test_uname_unicode(self):
+ for name in (u"äöü", "äöü"):
+ t = tarfile.TarInfo("foo")
+ t.uname = name
+ t.gname = name
- def test_pax_headers(self):
- self._test_pax_headers({"foo": "bar", "uid": 0, "mtime": 1.23})
+ fobj = StringIO.StringIO()
+ tar = tarfile.open("foo.tar", mode="w", fileobj=fobj, format=self.format, encoding="iso8859-1")
+ tar.addfile(t)
+ tar.close()
+ fobj.seek(0)
- self._test_pax_headers({"euro": u"\u20ac".encode("utf8")})
+ tar = tarfile.open("foo.tar", fileobj=fobj, encoding="iso8859-1")
+ t = tar.getmember("foo")
+ self.assertEqual(t.uname, "äöü")
+ self.assertEqual(t.gname, "äöü")
- self._test_pax_headers({"euro": u"\u20ac"},
- {"euro": u"\u20ac".encode("utf8")})
- self._test_pax_headers({u"\u20ac": "euro"},
- {u"\u20ac".encode("utf8"): "euro"})
+class GNUUnicodeTest(UstarUnicodeTest):
- def _test_pax_headers(self, pax_headers, cmp_headers=None):
- if cmp_headers is None:
- cmp_headers = pax_headers
+ format = tarfile.GNU_FORMAT
- tar = tarfile.open(tmpname, "w", format=tarfile.PAX_FORMAT, \
- pax_headers=pax_headers, encoding="utf8")
- tar.addfile(tarfile.TarInfo("test"))
- tar.close()
- tar = tarfile.open(tmpname, encoding="utf8")
- self.assertEqual(tar.pax_headers, cmp_headers)
+class PaxUnicodeTest(UstarUnicodeTest):
- def test_truncated_header(self):
- tar = tarfile.open(tmpname, "w", format=tarfile.PAX_FORMAT)
- tarinfo = tarfile.TarInfo("123/" * 126 + "longname")
- tar.addfile(tarinfo)
+ format = tarfile.PAX_FORMAT
+
+ def _create_unicode_name(self, name):
+ tar = tarfile.open(tmpname, "w", format=self.format)
+ t = tarfile.TarInfo()
+ t.pax_headers["path"] = name
+ tar.addfile(t)
tar.close()
- # Simulate a premature EOF.
- open(tmpname, "rb+").truncate(1536)
- tar = tarfile.open(tmpname)
- self.assertEqual(tar.getmembers(), [])
+ def test_error_handlers(self):
+ # Test if the unicode error handlers work correctly for characters
+ # that cannot be expressed in a given encoding.
+ self._create_unicode_name(u"äöü")
+
+ for handler, name in (("utf-8", u"äöü".encode("utf8")),
+ ("replace", "???"), ("ignore", "")):
+ tar = tarfile.open(tmpname, format=self.format, encoding="ascii",
+ errors=handler)
+ self.assertEqual(tar.getnames()[0], name)
+
+ self.assertRaises(UnicodeError, tarfile.open, tmpname,
+ encoding="ascii", errors="strict")
+
+ def test_error_handler_utf8(self):
+ # Create a pathname that has one component representable using
+ # iso8859-1 and the other only in iso8859-15.
+ self._create_unicode_name(u"äöü/¤")
+
+ tar = tarfile.open(tmpname, format=self.format, encoding="iso8859-1",
+ errors="utf-8")
+ self.assertEqual(tar.getnames()[0], "äöü/" + u"¤".encode("utf8"))
class AppendTest(unittest.TestCase):
@@ -836,63 +954,58 @@
def test_ustar_limits(self):
# 100 char name
tarinfo = tarfile.TarInfo("0123456789" * 10)
- tarinfo.create_ustar_header()
+ tarinfo.tobuf(tarfile.USTAR_FORMAT)
# 101 char name that cannot be stored
tarinfo = tarfile.TarInfo("0123456789" * 10 + "0")
- self.assertRaises(ValueError, tarinfo.create_ustar_header)
+ self.assertRaises(ValueError, tarinfo.tobuf, tarfile.USTAR_FORMAT)
# 256 char name with a slash at pos 156
tarinfo = tarfile.TarInfo("123/" * 62 + "longname")
- tarinfo.create_ustar_header()
+ tarinfo.tobuf(tarfile.USTAR_FORMAT)
# 256 char name that cannot be stored
tarinfo = tarfile.TarInfo("1234567/" * 31 + "longname")
- self.assertRaises(ValueError, tarinfo.create_ustar_header)
+ self.assertRaises(ValueError, tarinfo.tobuf, tarfile.USTAR_FORMAT)
# 512 char name
tarinfo = tarfile.TarInfo("123/" * 126 + "longname")
- self.assertRaises(ValueError, tarinfo.create_ustar_header)
+ self.assertRaises(ValueError, tarinfo.tobuf, tarfile.USTAR_FORMAT)
# 512 char linkname
tarinfo = tarfile.TarInfo("longlink")
tarinfo.linkname = "123/" * 126 + "longname"
- self.assertRaises(ValueError, tarinfo.create_ustar_header)
+ self.assertRaises(ValueError, tarinfo.tobuf, tarfile.USTAR_FORMAT)
# uid > 8 digits
tarinfo = tarfile.TarInfo("name")
tarinfo.uid = 010000000
- self.assertRaises(ValueError, tarinfo.create_ustar_header)
+ self.assertRaises(ValueError, tarinfo.tobuf, tarfile.USTAR_FORMAT)
def test_gnu_limits(self):
tarinfo = tarfile.TarInfo("123/" * 126 + "longname")
- tarinfo.create_gnu_header()
+ tarinfo.tobuf(tarfile.GNU_FORMAT)
tarinfo = tarfile.TarInfo("longlink")
tarinfo.linkname = "123/" * 126 + "longname"
- tarinfo.create_gnu_header()
+ tarinfo.tobuf(tarfile.GNU_FORMAT)
# uid >= 256 ** 7
tarinfo = tarfile.TarInfo("name")
tarinfo.uid = 04000000000000000000L
- self.assertRaises(ValueError, tarinfo.create_gnu_header)
+ self.assertRaises(ValueError, tarinfo.tobuf, tarfile.GNU_FORMAT)
def test_pax_limits(self):
- # A 256 char name that can be stored without an extended header.
- tarinfo = tarfile.TarInfo("123/" * 62 + "longname")
- self.assert_(len(tarinfo.create_pax_header("utf8")) == 512,
- "create_pax_header attached superfluous extended header")
-
tarinfo = tarfile.TarInfo("123/" * 126 + "longname")
- tarinfo.create_pax_header("utf8")
+ tarinfo.tobuf(tarfile.PAX_FORMAT)
tarinfo = tarfile.TarInfo("longlink")
tarinfo.linkname = "123/" * 126 + "longname"
- tarinfo.create_pax_header("utf8")
+ tarinfo.tobuf(tarfile.PAX_FORMAT)
tarinfo = tarfile.TarInfo("name")
tarinfo.uid = 04000000000000000000L
- tarinfo.create_pax_header("utf8")
+ tarinfo.tobuf(tarfile.PAX_FORMAT)
class GzipMiscReadTest(MiscReadTest):
@@ -940,6 +1053,9 @@
StreamWriteTest,
GNUWriteTest,
PaxWriteTest,
+ UstarUnicodeTest,
+ GNUUnicodeTest,
+ PaxUnicodeTest,
AppendTest,
LimitsTest,
]
Modified: python/trunk/Lib/test/testtar.tar
==============================================================================
Binary files. No diff available.
Modified: python/trunk/Misc/NEWS
==============================================================================
--- python/trunk/Misc/NEWS (original)
+++ python/trunk/Misc/NEWS Sun May 27 21:49:30 2007
@@ -220,6 +220,9 @@
Library
-------
+- tarfile.py: Improved unicode support. Unicode input names are now
+ officially supported. Added "errors" argument to the TarFile class.
+
- urllib.ftpwrapper class now accepts an optional timeout.
- shlex.split() now has an optional "posix" parameter.
More information about the Python-checkins
mailing list