bpo-39717: [tarfile] update nested exception raising (GH-23739)

- `from None` if the new exception uses, or doesn't need, the previous one
- `from e` if the previous exception is still relevant

Author: ethanfurman

Lib/tarfile.py

@@ -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 @@ def __init__(self, name, mode, comptype, fileobj, bufsize):
                 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 @@ def __init__(self, name, mode, comptype, fileobj, bufsize):
                 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 @@ def __init__(self, name, mode, comptype, fileobj, bufsize):
                 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()
@@ -541,8 +542,8 @@ def _read(self, size):
                     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)
@@ -1164,8 +1165,8 @@ def _proc_gnulong(self, tarfile):
         # 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.
@@ -1277,8 +1278,8 @@ def _proc_pax(self, tarfile):
         # 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:
@@ -1533,7 +1534,7 @@ def __init__(self, name=None, mode="r", fileobj=None, format=None,
                         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
@@ -1669,21 +1670,21 @@ def gzopen(cls, name, mode="r", fileobj=None, compresslevel=9, **kwargs):
         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()
@@ -1702,16 +1703,16 @@ def bz2open(cls, name, mode="r", fileobj=None, compresslevel=9, **kwargs):
         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()
@@ -1730,16 +1731,16 @@ def xzopen(cls, name, mode="r", fileobj=None, preset=None, **kwargs):
         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()
@@ -2253,7 +2254,7 @@ def makelink(self, tarinfo, targetpath):
                 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
@@ -2281,16 +2282,16 @@ def chown(self, tarinfo, targetpath, numeric_owner):
                     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.
@@ -2299,8 +2300,8 @@ def utime(self, tarinfo, targetpath):
             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):
@@ -2336,15 +2337,15 @@ def next(self):
                     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
             break
 
         if tarinfo is not None:

Misc/NEWS.d/next/Library/2020-12-10-18-36-52.bpo-39717.sK2u0w.rst

@@ -0,0 +1 @@
+[tarfile] update nested exception raising to use `from None` or `from e`