diff options
Diffstat (limited to 'Lib/tarfile.py')
| -rwxr-xr-x | Lib/tarfile.py | 236 |
1 files changed, 157 insertions, 79 deletions
diff --git a/Lib/tarfile.py b/Lib/tarfile.py index f6d7f79390..5f1a979ad0 100755 --- a/Lib/tarfile.py +++ b/Lib/tarfile.py @@ -38,6 +38,7 @@ __credits__ = "Gustavo Niemeyer, Niels Gust\u00e4bel, Richard Townsend." #--------- # Imports #--------- +from builtins import open as bltn_open import sys import os import io @@ -56,17 +57,15 @@ except ImportError: # os.symlink on Windows prior to 6.0 raises NotImplementedError symlink_exception = (AttributeError, NotImplementedError) try: - # WindowsError (1314) will be raised if the caller does not hold the + # OSError (winerror=1314) will be raised if the caller does not hold the # SeCreateSymbolicLinkPrivilege privilege - symlink_exception += (WindowsError,) + symlink_exception += (OSError,) except NameError: pass # from tarfile import * __all__ = ["TarFile", "TarInfo", "is_tarfile", "TarError"] -from builtins import open as _open # Since 'open' is TarFile.open - #--------------------------------------------------------- # tar constants #--------------------------------------------------------- @@ -140,30 +139,6 @@ PAX_NUMBER_FIELDS = { } #--------------------------------------------------------- -# Bits used in the mode field, values in octal. -#--------------------------------------------------------- -S_IFLNK = 0o120000 # symbolic link -S_IFREG = 0o100000 # regular file -S_IFBLK = 0o060000 # block device -S_IFDIR = 0o040000 # directory -S_IFCHR = 0o020000 # character device -S_IFIFO = 0o010000 # fifo - -TSUID = 0o4000 # set UID on execution -TSGID = 0o2000 # set GID on execution -TSVTX = 0o1000 # reserved - -TUREAD = 0o400 # read by owner -TUWRITE = 0o200 # write by owner -TUEXEC = 0o100 # execute/search by owner -TGREAD = 0o040 # read by group -TGWRITE = 0o020 # write by group -TGEXEC = 0o010 # execute/search by group -TOREAD = 0o004 # read by other -TOWRITE = 0o002 # write by other -TOEXEC = 0o001 # execute/search by other - -#--------------------------------------------------------- # initialization #--------------------------------------------------------- if os.name in ("nt", "ce"): @@ -203,7 +178,8 @@ def nti(s): n = -(256 ** (len(s) - 1) - n) else: try: - n = int(nts(s, "ascii", "strict") or "0", 8) + s = nts(s, "ascii", "strict") + n = int(s.strip() or "0", 8) except ValueError: raise InvalidHeaderError("invalid header") return n @@ -220,7 +196,7 @@ def itn(n, digits=8, format=DEFAULT_FORMAT): # A 0o200 byte indicates a positive number, a 0o377 byte a negative # number. if 0 <= n < 8 ** (digits - 1): - s = bytes("%0*o" % (digits - 1, n), "ascii") + NUL + s = bytes("%0*o" % (digits - 1, int(n)), "ascii") + NUL elif format == GNU_FORMAT and -256 ** (digits - 1) <= n < 256 ** (digits - 1): if n >= 0: s = bytearray([0o200]) @@ -249,7 +225,7 @@ def calc_chksums(buf): signed_chksum = 256 + sum(struct.unpack_from("148b8x356b", buf)) return unsigned_chksum, signed_chksum -def copyfileobj(src, dst, length=None): +def copyfileobj(src, dst, length=None, exception=OSError): """Copy length bytes from fileobj src to fileobj dst. If length is None, copy the entire content. """ @@ -264,13 +240,13 @@ def copyfileobj(src, dst, length=None): for b in range(blocks): buf = src.read(BUFSIZE) if len(buf) < BUFSIZE: - raise IOError("end of file reached") + raise exception("unexpected end of data") dst.write(buf) if remainder != 0: buf = src.read(remainder) if len(buf) < remainder: - raise IOError("end of file reached") + raise exception("unexpected end of data") dst.write(buf) return @@ -405,7 +381,7 @@ class _Stream: if mode == "r": self.dbuf = b"" self.cmp = bz2.BZ2Decompressor() - self.exception = IOError + self.exception = OSError else: self.cmp = bz2.BZ2Compressor() @@ -474,26 +450,26 @@ class _Stream: if self.closed: return - if self.mode == "w" and self.comptype != "tar": - self.buf += self.cmp.flush() - - if self.mode == "w" and self.buf: - self.fileobj.write(self.buf) - self.buf = b"" - if self.comptype == "gz": - # The native zlib crc is an unsigned 32-bit integer, but - # the Python wrapper implicitly casts that to a signed C - # long. So, on a 32-bit box self.crc may "look negative", - # while the same crc on a 64-bit box may "look positive". - # To avoid irksome warnings from the `struct` module, force - # it to look positive on all boxes. - self.fileobj.write(struct.pack("<L", self.crc & 0xffffffff)) - self.fileobj.write(struct.pack("<L", self.pos & 0xffffFFFF)) - - if not self._extfileobj: - self.fileobj.close() - self.closed = True + try: + if self.mode == "w" and self.comptype != "tar": + self.buf += self.cmp.flush() + + if self.mode == "w" and self.buf: + self.fileobj.write(self.buf) + self.buf = b"" + if self.comptype == "gz": + # The native zlib crc is an unsigned 32-bit integer, but + # the Python wrapper implicitly casts that to a signed C + # long. So, on a 32-bit box self.crc may "look negative", + # while the same crc on a 64-bit box may "look positive". + # To avoid irksome warnings from the `struct` module, force + # it to look positive on all boxes. + self.fileobj.write(struct.pack("<L", self.crc & 0xffffffff)) + self.fileobj.write(struct.pack("<L", self.pos & 0xffffFFFF)) + finally: + if not self._extfileobj: + self.fileobj.close() def _init_read_gz(self): """Initialize for reading a gzip compressed fileobj. @@ -714,7 +690,10 @@ class _FileInFile(object): length = min(size, stop - self.position) if data: self.fileobj.seek(offset + (self.position - start)) - buf += self.fileobj.read(length) + b = self.fileobj.read(length) + if len(b) != length: + raise ReadError("unexpected end of data") + buf += b else: buf += NUL * length size -= length @@ -1449,7 +1428,8 @@ class TarFile(object): fileobj = bltn_open(name, self._mode) self._extfileobj = False else: - if name is None and hasattr(fileobj, "name"): + if (name is None and hasattr(fileobj, "name") and + isinstance(fileobj.name, (str, bytes))): name = fileobj.name if hasattr(fileobj, "mode"): self._mode = fileobj.mode @@ -1672,7 +1652,7 @@ class TarFile(object): try: t = cls.taropen(name, mode, fileobj, **kwargs) - except (IOError, EOFError): + except (OSError, EOFError): fileobj.close() if mode == 'r': raise ReadError("not a bzip2 file") @@ -1729,18 +1709,19 @@ class TarFile(object): if self.closed: return - if self.mode in "aw": - self.fileobj.write(NUL * (BLOCKSIZE * 2)) - self.offset += (BLOCKSIZE * 2) - # fill up the end with zero-blocks - # (like option -b20 for tar does) - blocks, remainder = divmod(self.offset, RECORDSIZE) - if remainder > 0: - self.fileobj.write(NUL * (RECORDSIZE - remainder)) - - if not self._extfileobj: - self.fileobj.close() self.closed = True + try: + if self.mode in "aw": + self.fileobj.write(NUL * (BLOCKSIZE * 2)) + self.offset += (BLOCKSIZE * 2) + # fill up the end with zero-blocks + # (like option -b20 for tar does) + blocks, remainder = divmod(self.offset, RECORDSIZE) + if remainder > 0: + self.fileobj.write(NUL * (RECORDSIZE - remainder)) + finally: + if not self._extfileobj: + self.fileobj.close() def getmember(self, name): """Return a TarInfo object for member `name'. If `name' can not be @@ -2042,7 +2023,7 @@ class TarFile(object): try: self._extract_member(tarinfo, os.path.join(path, tarinfo.name), set_attrs=set_attrs) - except EnvironmentError as e: + except OSError as e: if self.errorlevel > 0: raise else: @@ -2154,9 +2135,9 @@ class TarFile(object): if tarinfo.sparse is not None: for offset, size in tarinfo.sparse: target.seek(offset) - copyfileobj(source, target, size) + copyfileobj(source, target, size, ReadError) else: - copyfileobj(source, target, tarinfo.size) + copyfileobj(source, target, tarinfo.size, ReadError) target.seek(tarinfo.size) target.truncate() @@ -2231,9 +2212,8 @@ class TarFile(object): if tarinfo.issym() and hasattr(os, "lchown"): os.lchown(targetpath, u, g) else: - if sys.platform != "os2emx": - os.chown(targetpath, u, g) - except EnvironmentError as e: + os.chown(targetpath, u, g) + except OSError as e: raise ExtractError("could not change owner") def chmod(self, tarinfo, targetpath): @@ -2242,7 +2222,7 @@ class TarFile(object): if hasattr(os, 'chmod'): try: os.chmod(targetpath, tarinfo.mode) - except EnvironmentError as e: + except OSError as e: raise ExtractError("could not change mode") def utime(self, tarinfo, targetpath): @@ -2252,7 +2232,7 @@ class TarFile(object): return try: os.utime(targetpath, (tarinfo.mtime, tarinfo.mtime)) - except EnvironmentError as e: + except OSError as e: raise ExtractError("could not change modification time") #-------------------------------------------------------------------------- @@ -2267,8 +2247,13 @@ class TarFile(object): self.firstmember = None return m + # Advance the file pointer. + if self.offset != self.fileobj.tell(): + self.fileobj.seek(self.offset - 1) + if not self.fileobj.read(1): + raise ReadError("unexpected end of data") + # Read the next block. - self.fileobj.seek(self.offset) tarinfo = None while True: try: @@ -2343,9 +2328,9 @@ class TarFile(object): corresponds to TarFile's mode. """ if self.closed: - raise IOError("%s is closed" % self.__class__.__name__) + raise OSError("%s is closed" % self.__class__.__name__) if mode is not None and self.mode not in mode: - raise IOError("bad operation for mode %r" % self.mode) + raise OSError("bad operation for mode %r" % self.mode) def _find_link_target(self, tarinfo): """Find the target member of a symlink or hardlink member in the @@ -2447,5 +2432,98 @@ def is_tarfile(name): except TarError: return False -bltn_open = open open = TarFile.open + + +def main(): + import argparse + + description = 'A simple command line interface for tarfile module.' + parser = argparse.ArgumentParser(description=description) + parser.add_argument('-v', '--verbose', action='store_true', default=False, + help='Verbose output') + group = parser.add_mutually_exclusive_group() + group.add_argument('-l', '--list', metavar='<tarfile>', + help='Show listing of a tarfile') + group.add_argument('-e', '--extract', nargs='+', + metavar=('<tarfile>', '<output_dir>'), + help='Extract tarfile into target dir') + group.add_argument('-c', '--create', nargs='+', + metavar=('<name>', '<file>'), + help='Create tarfile from sources') + group.add_argument('-t', '--test', metavar='<tarfile>', + help='Test if a tarfile is valid') + args = parser.parse_args() + + if args.test: + src = args.test + if is_tarfile(src): + with open(src, 'r') as tar: + tar.getmembers() + print(tar.getmembers(), file=sys.stderr) + if args.verbose: + print('{!r} is a tar archive.'.format(src)) + else: + parser.exit(1, '{!r} is not a tar archive.\n'.format(src)) + + elif args.list: + src = args.list + if is_tarfile(src): + with TarFile.open(src, 'r:*') as tf: + tf.list(verbose=args.verbose) + else: + parser.exit(1, '{!r} is not a tar archive.\n'.format(src)) + + elif args.extract: + if len(args.extract) == 1: + src = args.extract[0] + curdir = os.curdir + elif len(args.extract) == 2: + src, curdir = args.extract + else: + parser.exit(1, parser.format_help()) + + if is_tarfile(src): + with TarFile.open(src, 'r:*') as tf: + tf.extractall(path=curdir) + if args.verbose: + if curdir == '.': + msg = '{!r} file is extracted.'.format(src) + else: + msg = ('{!r} file is extracted ' + 'into {!r} directory.').format(src, curdir) + print(msg) + else: + parser.exit(1, '{!r} is not a tar archive.\n'.format(src)) + + elif args.create: + tar_name = args.create.pop(0) + _, ext = os.path.splitext(tar_name) + compressions = { + # gz + '.gz': 'gz', + '.tgz': 'gz', + # xz + '.xz': 'xz', + '.txz': 'xz', + # bz2 + '.bz2': 'bz2', + '.tbz': 'bz2', + '.tbz2': 'bz2', + '.tb2': 'bz2', + } + tar_mode = 'w:' + compressions[ext] if ext in compressions else 'w' + tar_files = args.create + + with TarFile.open(tar_name, tar_mode) as tf: + for file_name in tar_files: + tf.add(file_name) + + if args.verbose: + print('{!r} file created.'.format(tar_name)) + + else: + parser.exit(1, parser.format_help()) + +if __name__ == '__main__': + main() |