Issue #13158: Fix decoding and encoding of base-256 number fields in tarfile.
The nti() function that converts a number field from a tar header to a number
failed to decode GNU tar specific base-256 fields. I also added support for
decoding and encoding negative base-256 number fields.
diff --git a/Lib/tarfile.py b/Lib/tarfile.py
index 1ece716..d8d94f0 100644
--- a/Lib/tarfile.py
+++ b/Lib/tarfile.py
@@ -196,16 +196,18 @@
"""
# There are two possible encodings for a number field, see
# itn() below.
- if s[0] != chr(0o200):
+ if s[0] in (0o200, 0o377):
+ n = 0
+ for i in range(len(s) - 1):
+ n <<= 8
+ n += s[i + 1]
+ if s[0] == 0o377:
+ n = -(256 ** (len(s) - 1) - n)
+ else:
try:
n = int(nts(s, "ascii", "strict") or "0", 8)
except ValueError:
raise InvalidHeaderError("invalid header")
- else:
- n = 0
- for i in range(len(s) - 1):
- n <<= 8
- n += ord(s[i + 1])
return n
def itn(n, digits=8, format=DEFAULT_FORMAT):
@@ -214,25 +216,26 @@
# POSIX 1003.1-1988 requires numbers to be encoded as a string of
# octal digits followed by a null-byte, this allows values up to
# (8**(digits-1))-1. GNU tar allows storing numbers greater than
- # that if necessary. A leading 0o200 byte indicates this particular
- # encoding, the following digits-1 bytes are a big-endian
- # representation. This allows values up to (256**(digits-1))-1.
+ # that if necessary. A leading 0o200 or 0o377 byte indicate this
+ # particular encoding, the following digits-1 bytes are a big-endian
+ # 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.
if 0 <= n < 8 ** (digits - 1):
s = bytes("%0*o" % (digits - 1, n), "ascii") + NUL
- else:
- if format != GNU_FORMAT or n >= 256 ** (digits - 1):
- raise ValueError("overflow in number field")
+ elif format == GNU_FORMAT and -256 ** (digits - 1) <= n < 256 ** (digits - 1):
+ if n >= 0:
+ s = bytearray([0o200])
+ else:
+ s = bytearray([0o377])
+ n = 256 ** digits + n
- if n < 0:
- # XXX We mimic GNU tar's behaviour with negative numbers,
- # this could raise OverflowError.
- n = struct.unpack("L", struct.pack("l", n))[0]
-
- s = bytearray()
for i in range(digits - 1):
- s.insert(0, n & 0o377)
+ s.insert(1, n & 0o377)
n >>= 8
- s.insert(0, 0o200)
+ else:
+ raise ValueError("overflow in number field")
+
return s
def calc_chksums(buf):