mschoi/RustPython
1
0
Fork 0
forked from Rust-related/RustPython
Code Pull Requests Actions Activity

Update tarfile and its test from CPython 3.10.5

Browse Source
This commit is contained in:
CPython Developers
2022-08-09 06:06:46 +09:00
committed by Jeong YunWon
parent 50d5c6d4a5
commit eba72d41f9
1 changed files with 90 additions and 47 deletions
Download Patch File Download Diff File Expand all files Collapse all files

137
Lib/tarfile.py vendored
View File

@@ -200,6 +200,7 @@ def itn(n, digits=8, format=DEFAULT_FORMAT):
# base-256 representation. This allows values up to (256**(digits-1))-1.
# A 0o200 byte indicates a positive number, a 0o377 byte a negative
# number.
original_n = n
n = int(n)
if 0 <= n < 8 ** (digits - 1):
s = bytes("%0*o" % (digits - 1, n), "ascii") + NUL
@@ -363,7 +364,7 @@ class _Stream:
try:
import zlib
except ImportError:
raise CompressionError("zlib module is not available")
raise CompressionError("zlib module is not available") from None
self.zlib = zlib
self.crc = zlib.crc32(b"")
if mode == "r":
@@ -376,7 +377,7 @@ class _Stream:
try:
import bz2
except ImportError:
raise CompressionError("bz2 module is not available")
raise CompressionError("bz2 module is not available") from None
if mode == "r":
self.dbuf = b""
self.cmp = bz2.BZ2Decompressor()
@@ -388,7 +389,7 @@ class _Stream:
try:
import lzma
except ImportError:
raise CompressionError("lzma module is not available")
raise CompressionError("lzma module is not available") from None
if mode == "r":
self.dbuf = b""
self.cmp = lzma.LZMADecompressor()
@@ -420,6 +421,8 @@ class _Stream:
self.__write(b"\037\213\010\010" + timestamp + b"\002\377")
if self.name.endswith(".gz"):
self.name = self.name[:-3]
# Honor "directory components removed" from RFC1952
self.name = os.path.basename(self.name)
# RFC1952 says we must use ISO-8859-1 for the FNAME field.
self.__write(self.name.encode("iso-8859-1", "replace") + NUL)
@@ -539,8 +542,8 @@ class _Stream:
break
try:
buf = self.cmp.decompress(buf)
except self.exception:
raise ReadError("invalid compressed data")
except self.exception as e:
raise ReadError("invalid compressed data") from e
t.append(buf)
c += len(buf)
t = b"".join(t)
@@ -885,15 +888,24 @@ class TarInfo(object):
# 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
needs_pax = False
val = info[name]
if not 0 <= val < 8 ** (digits - 1) or isinstance(val, float):
pax_headers[name] = str(val)
val_is_float = isinstance(val, float)
val_int = round(val) if val_is_float else val
if not 0 <= val_int < 8 ** (digits - 1):
# Avoid overflow.
info[name] = 0
needs_pax = True
elif val_is_float:
# Put rounded value in ustar header, and full
# precision value in pax header.
info[name] = val_int
needs_pax = True
# The existing pax header has priority.
if needs_pax and name not in pax_headers:
pax_headers[name] = str(val)
# Create a pax extended header if necessary.
if pax_headers:
@@ -930,6 +942,14 @@ class TarInfo(object):
"""Return a header block. info is a dictionary with file
information, format must be one of the *_FORMAT constants.
"""
has_device_fields = info.get("type") in (CHRTYPE, BLKTYPE)
if has_device_fields:
devmajor = itn(info.get("devmajor", 0), 8, format)
devminor = itn(info.get("devminor", 0), 8, format)
else:
devmajor = stn("", 8, encoding, errors)
devminor = stn("", 8, encoding, errors)
parts = [
stn(info.get("name", ""), 100, encoding, errors),
itn(info.get("mode", 0) & 0o7777, 8, format),
@@ -943,8 +963,8 @@ class TarInfo(object):
info.get("magic", POSIX_MAGIC),
stn(info.get("uname", ""), 32, encoding, errors),
stn(info.get("gname", ""), 32, encoding, errors),
itn(info.get("devmajor", 0), 8, format),
itn(info.get("devminor", 0), 8, format),
devmajor,
devminor,
stn(info.get("prefix", ""), 155, encoding, errors)
]
@@ -1154,8 +1174,8 @@ class TarInfo(object):
# Fetch the next header and process it.
try:
next = self.fromtarfile(tarfile)
except HeaderError:
raise SubsequentHeaderError("missing or bad subsequent header")
except HeaderError as e:
raise SubsequentHeaderError(str(e)) from None
# Patch the TarInfo object from the next header with
# the longname information.
@@ -1241,6 +1261,8 @@ class TarInfo(object):
length, keyword = match.groups()
length = int(length)
if length == 0:
raise InvalidHeaderError("invalid header")
value = buf[match.end(2) + 1:match.start(1) + length - 1]
# Normally, we could just use "utf-8" as the encoding and "strict"
@@ -1265,8 +1287,8 @@ class TarInfo(object):
# Fetch the next header.
try:
next = self.fromtarfile(tarfile)
except HeaderError:
raise SubsequentHeaderError("missing or bad subsequent header")
except HeaderError as e:
raise SubsequentHeaderError(str(e)) from None
# Process GNU sparse information.
if "GNU.sparse.map" in pax_headers:
@@ -1521,7 +1543,7 @@ class TarFile(object):
self.fileobj.seek(self.offset)
break
except HeaderError as e:
raise ReadError(str(e))
raise ReadError(str(e)) from None
if self.mode in ("a", "w", "x"):
self._loaded = True
@@ -1591,17 +1613,20 @@ class TarFile(object):
# Find out which *open() is appropriate for opening the file.
def not_compressed(comptype):
return cls.OPEN_METH[comptype] == 'taropen'
error_msgs = []
for comptype in sorted(cls.OPEN_METH, key=not_compressed):
func = getattr(cls, cls.OPEN_METH[comptype])
if fileobj is not None:
saved_pos = fileobj.tell()
try:
return func(name, "r", fileobj, **kwargs)
except (ReadError, CompressionError):
except (ReadError, CompressionError) as e:
error_msgs.append(f'- method {comptype}: {e!r}')
if fileobj is not None:
fileobj.seek(saved_pos)
continue
raise ReadError("file could not be opened successfully")
error_msgs_summary = '\n'.join(error_msgs)
raise ReadError(f"file could not be opened successfully:\n{error_msgs_summary}")
elif ":" in mode:
filemode, comptype = mode.split(":", 1)
@@ -1657,21 +1682,21 @@ class TarFile(object):
try:
from gzip import GzipFile
except ImportError:
raise CompressionError("gzip module is not available")
raise CompressionError("gzip module is not available") from None
try:
fileobj = GzipFile(name, mode + "b", compresslevel, fileobj)
except OSError:
except OSError as e:
if fileobj is not None and mode == 'r':
raise ReadError("not a gzip file")
raise ReadError("not a gzip file") from e
raise
try:
t = cls.taropen(name, mode, fileobj, **kwargs)
except OSError:
except OSError as e:
fileobj.close()
if mode == 'r':
raise ReadError("not a gzip file")
raise ReadError("not a gzip file") from e
raise
except:
fileobj.close()
@@ -1690,16 +1715,16 @@ class TarFile(object):
try:
from bz2 import BZ2File
except ImportError:
raise CompressionError("bz2 module is not available")
raise CompressionError("bz2 module is not available") from None
fileobj = BZ2File(fileobj or name, mode, compresslevel=compresslevel)
try:
t = cls.taropen(name, mode, fileobj, **kwargs)
except (OSError, EOFError):
except (OSError, EOFError) as e:
fileobj.close()
if mode == 'r':
raise ReadError("not a bzip2 file")
raise ReadError("not a bzip2 file") from e
raise
except:
fileobj.close()
@@ -1718,16 +1743,16 @@ class TarFile(object):
try:
from lzma import LZMAFile, LZMAError
except ImportError:
raise CompressionError("lzma module is not available")
raise CompressionError("lzma module is not available") from None
fileobj = LZMAFile(fileobj or name, mode, preset=preset)
try:
t = cls.taropen(name, mode, fileobj, **kwargs)
except (LZMAError, EOFError):
except (LZMAError, EOFError) as e:
fileobj.close()
if mode == 'r':
raise ReadError("not an lzma file")
raise ReadError("not an lzma file") from e
raise
except:
fileobj.close()
@@ -1773,7 +1798,7 @@ class TarFile(object):
than once in the archive, its last occurrence is assumed to be the
most up-to-date version.
"""
tarinfo = self._getmember(name)
tarinfo = self._getmember(name.rstrip('/'))
if tarinfo is None:
raise KeyError("filename %r not found" % name)
return tarinfo
@@ -2081,9 +2106,10 @@ class TarFile(object):
def extractfile(self, member):
"""Extract a member from the archive as a file object. `member' may be
a filename or a TarInfo object. If `member' is a regular file or a
link, an io.BufferedReader object is returned. Otherwise, None is
returned.
a filename or a TarInfo object. If `member' is a regular file or
a link, an io.BufferedReader object is returned. For all other
existing members, None is returned. If `member' does not appear
in the archive, KeyError is raised.
"""
self._check("r")
@@ -2224,6 +2250,9 @@ class TarFile(object):
try:
# For systems that support symbolic and hard links.
if tarinfo.issym():
if os.path.lexists(targetpath):
# Avoid FileExistsError on following os.symlink.
os.unlink(targetpath)
os.symlink(tarinfo.linkname, targetpath)
else:
# See extract().
@@ -2237,7 +2266,7 @@ class TarFile(object):
self._extract_member(self._find_link_target(tarinfo),
targetpath)
except KeyError:
raise ExtractError("unable to resolve link inside archive")
raise ExtractError("unable to resolve link inside archive") from None
def chown(self, tarinfo, targetpath, numeric_owner):
"""Set owner of targetpath according to tarinfo. If numeric_owner
@@ -2265,16 +2294,16 @@ class TarFile(object):
os.lchown(targetpath, u, g)
else:
os.chown(targetpath, u, g)
except OSError:
raise ExtractError("could not change owner")
except OSError as e:
raise ExtractError("could not change owner") from e
def chmod(self, tarinfo, targetpath):
"""Set file permissions of targetpath according to tarinfo.
"""
try:
os.chmod(targetpath, tarinfo.mode)
except OSError:
raise ExtractError("could not change mode")
except OSError as e:
raise ExtractError("could not change mode") from e
def utime(self, tarinfo, targetpath):
"""Set modification time of targetpath according to tarinfo.
@@ -2283,8 +2312,8 @@ class TarFile(object):
return
try:
os.utime(targetpath, (tarinfo.mtime, tarinfo.mtime))
except OSError:
raise ExtractError("could not change modification time")
except OSError as e:
raise ExtractError("could not change modification time") from e
#--------------------------------------------------------------------------
def next(self):
@@ -2320,15 +2349,24 @@ class TarFile(object):
self.offset += BLOCKSIZE
continue
elif self.offset == 0:
raise ReadError(str(e))
raise ReadError(str(e)) from None
except EmptyHeaderError:
if self.offset == 0:
raise ReadError("empty file")
raise ReadError("empty file") from None
except TruncatedHeaderError as e:
if self.offset == 0:
raise ReadError(str(e))
raise ReadError(str(e)) from None
except SubsequentHeaderError as e:
raise ReadError(str(e))
raise ReadError(str(e)) from None
except Exception as e:
try:
import zlib
if isinstance(e, zlib.error):
raise ReadError(f'zlib error: {e}') from None
else:
raise e
except ImportError:
raise e
break
if tarinfo is not None:
@@ -2459,9 +2497,14 @@ class TarFile(object):
def is_tarfile(name):
"""Return True if name points to a tar archive that we
are able to handle, else return False.
'name' should be a string, file, or file-like object.
"""
try:
t = open(name)
if hasattr(name, "read"):
t = open(fileobj=name)
else:
t = open(name)
t.close()
return True
except TarError: