Patch #918101: Add tarfile open mode r|* for auto-detection of the

stream compression; add, for symmetry reasons, r:* as a synonym of r.

4 files changed, 98 insertions, 33 deletions

diff --git a/Doc/lib/libtarfile.tex b/Doc/lib/libtarfile.tex
index 018e8b9..9088473 100644
--- a/Doc/lib/libtarfile.tex
+++ b/Doc/lib/libtarfile.tex
@@ -32,7 +32,7 @@ Some facts and figures:
     it defaults to \code{'r'}. Here is a full list of mode combinations:
 
     \begin{tableii}{c|l}{code}{mode}{action}
-    \lineii{'r'}{Open for reading with transparent compression (recommended).}
+    \lineii{'r' or 'r:*'}{Open for reading with transparent compression (recommended).}
     \lineii{'r:'}{Open for reading exclusively without compression.}
     \lineii{'r:gz'}{Open for reading with gzip compression.}
     \lineii{'r:bz2'}{Open for reading with bzip2 compression.}
@@ -65,6 +65,7 @@ Some facts and figures:
     (section~\ref{tar-examples}).  The currently possible modes:
 
     \begin{tableii}{c|l}{code}{Mode}{Action}
+    \lineii{'r|*'}{Open a \emph{stream} of tar blocks for reading with transparent compression.}
     \lineii{'r|'}{Open a \emph{stream} of uncompressed tar blocks for reading.}
     \lineii{'r|gz'}{Open a gzip compressed \emph{stream} for reading.}
     \lineii{'r|bz2'}{Open a bzip2 compressed \emph{stream} for reading.}
diff --git a/Lib/tarfile.py b/Lib/tarfile.py
index 8bce5d0..56cce03 100644
--- a/Lib/tarfile.py
+++ b/Lib/tarfile.py
@@ -274,7 +274,7 @@ class _Stream:
        _Stream is intended to be used only internally.
     """
 
-    def __init__(self, name, mode, type, fileobj, bufsize):
+    def __init__(self, name, mode, comptype, fileobj, bufsize):
         """Construct a _Stream object.
         """
         self._extfileobj = True
@@ -282,16 +282,22 @@ class _Stream:
             fileobj = _LowLevelFile(name, mode)
             self._extfileobj = False
 
-        self.name    = name or ""
-        self.mode    = mode
-        self.type    = type
-        self.fileobj = fileobj
-        self.bufsize = bufsize
-        self.buf     = ""
-        self.pos     = 0L
-        self.closed  = False
-
-        if type == "gz":
+        if comptype == '*':
+            # Enable transparent compression detection for the
+            # stream interface
+            fileobj = _StreamProxy(fileobj)
+            comptype = fileobj.getcomptype()
+
+        self.name     = name or ""
+        self.mode     = mode
+        self.comptype = comptype
+        self.fileobj  = fileobj
+        self.bufsize  = bufsize
+        self.buf      = ""
+        self.pos      = 0L
+        self.closed   = False
+
+        if comptype == "gz":
             try:
                 import zlib
             except ImportError:
@@ -303,7 +309,7 @@ class _Stream:
             else:
                 self._init_write_gz()
 
-        if type == "bz2":
+        if comptype == "bz2":
             try:
                 import bz2
             except ImportError:
@@ -315,7 +321,7 @@ class _Stream:
                 self.cmp = bz2.BZ2Compressor()
 
     def __del__(self):
-        if not self.closed:
+        if hasattr(self, "closed") and not self.closed:
             self.close()
 
     def _init_write_gz(self):
@@ -334,10 +340,10 @@ class _Stream:
     def write(self, s):
         """Write string s to the stream.
         """
-        if self.type == "gz":
+        if self.comptype == "gz":
             self.crc = self.zlib.crc32(s, self.crc)
         self.pos += len(s)
-        if self.type != "tar":
+        if self.comptype != "tar":
             s = self.cmp.compress(s)
         self.__write(s)
 
@@ -357,12 +363,16 @@ class _Stream:
         if self.closed:
             return
 
-        if self.mode == "w" and self.type != "tar":
+        if self.mode == "w" and self.comptype != "tar":
             self.buf += self.cmp.flush()
+
         if self.mode == "w" and self.buf:
+            blocks, remainder = divmod(len(self.buf), self.bufsize)
+            if remainder > 0:
+                self.buf += NUL * (self.bufsize - remainder)
             self.fileobj.write(self.buf)
             self.buf = ""
-            if self.type == "gz":
+            if self.comptype == "gz":
                 self.fileobj.write(struct.pack("<l", self.crc))
                 self.fileobj.write(struct.pack("<L", self.pos & 0xffffFFFFL))
 
@@ -441,7 +451,7 @@ class _Stream:
     def _read(self, size):
         """Return size bytes from the stream.
         """
-        if self.type == "tar":
+        if self.comptype == "tar":
             return self.__read(size)
 
         c = len(self.dbuf)
@@ -474,6 +484,30 @@ class _Stream:
         return t[:size]
 # class _Stream
 
+class _StreamProxy(object):
+    """Small proxy class that enables transparent compression
+       detection for the Stream interface (mode 'r|*').
+    """
+
+    def __init__(self, fileobj):
+        self.fileobj = fileobj
+        self.buf = self.fileobj.read(BLOCKSIZE)
+
+    def read(self, size):
+        self.read = self.fileobj.read
+        return self.buf
+
+    def getcomptype(self):
+        if self.buf.startswith("\037\213\010"):
+            return "gz"
+        if self.buf.startswith("BZh91"):
+            return "bz2"
+        return "tar"
+
+    def close(self):
+        self.fileobj.close()
+# class StreamProxy
+
 #------------------------
 # Extraction file object
 #------------------------
@@ -879,7 +913,7 @@ class TarFile(object):
            an appropriate TarFile class.
 
            mode:
-           'r'          open for reading with transparent compression
+           'r' or 'r:*' open for reading with transparent compression
            'r:'         open for reading exclusively uncompressed
            'r:gz'       open for reading with gzip compression
            'r:bz2'      open for reading with bzip2 compression
@@ -887,6 +921,8 @@ class TarFile(object):
            'w' or 'w:'  open for writing without compression
            'w:gz'       open for writing with gzip compression
            'w:bz2'      open for writing with bzip2 compression
+
+           'r|*'        open a stream of tar blocks with transparent compression
            'r|'         open an uncompressed stream of tar blocks for reading
            'r|gz'       open a gzip compressed stream of tar blocks
            'r|bz2'      open a bzip2 compressed stream of tar blocks
@@ -898,7 +934,17 @@ class TarFile(object):
         if not name and not fileobj:
             raise ValueError, "nothing to open"
 
-        if ":" in mode:
+        if mode in ("r", "r:*"):
+            # Find out which *open() is appropriate for opening the file.
+            for comptype in cls.OPEN_METH:
+                func = getattr(cls, cls.OPEN_METH[comptype])
+                try:
+                    return func(name, "r", fileobj)
+                except (ReadError, CompressionError):
+                    continue
+            raise ReadError, "file could not be opened successfully"
+
+        elif ":" in mode:
             filemode, comptype = mode.split(":", 1)
             filemode = filemode or "r"
             comptype = comptype or "tar"
@@ -924,16 +970,6 @@ class TarFile(object):
             t._extfileobj = False
             return t
 
-        elif mode == "r":
-            # Find out which *open() is appropriate for opening the file.
-            for comptype in cls.OPEN_METH:
-                func = getattr(cls, cls.OPEN_METH[comptype])
-                try:
-                    return func(name, "r", fileobj)
-                except (ReadError, CompressionError):
-                    continue
-            raise ReadError, "file could not be opened successfully"
-
         elif mode in "aw":
             return cls.taropen(name, mode, fileobj)
 
diff --git a/Lib/test/test_tarfile.py b/Lib/test/test_tarfile.py
index a6c4c4a..cc5e505 100644
--- a/Lib/test/test_tarfile.py
+++ b/Lib/test/test_tarfile.py
@@ -181,6 +181,18 @@ class ReadStreamTest(ReadTest):
 
         stream.close()
 
+class ReadAsteriskTest(ReadTest):
+
+    def setUp(self):
+        mode = self.mode + self.sep + "*"
+        self.tar = tarfile.open(tarname(self.comp), mode)
+
+class ReadStreamAsteriskTest(ReadStreamTest):
+
+    def setUp(self):
+        mode = self.mode + self.sep + "*"
+        self.tar = tarfile.open(tarname(self.comp), mode)
+
 class WriteTest(BaseTest):
     mode = 'w'
 
@@ -336,6 +348,11 @@ class WriteTestGzip(WriteTest):
     comp = "gz"
 class WriteStreamTestGzip(WriteStreamTest):
     comp = "gz"
+class ReadAsteriskTestGzip(ReadAsteriskTest):
+    comp = "gz"
+class ReadStreamAsteriskTestGzip(ReadStreamAsteriskTest):
+    comp = "gz"
+
 
 # Filemode test cases
 
@@ -355,6 +372,10 @@ if bz2:
         comp = "bz2"
     class WriteStreamTestBzip2(WriteStreamTestGzip):
         comp = "bz2"
+    class ReadAsteriskTestBzip2(ReadAsteriskTest):
+        comp = "bz2"
+    class ReadStreamAsteriskTestBzip2(ReadStreamAsteriskTest):
+        comp = "bz2"
 
 # If importing gzip failed, discard the Gzip TestCases.
 if not gzip:
@@ -375,6 +396,8 @@ def test_main():
         FileModeTest,
         ReadTest,
         ReadStreamTest,
+        ReadAsteriskTest,
+        ReadStreamAsteriskTest,
         WriteTest,
         WriteStreamTest,
         WriteGNULongTest,
@@ -386,13 +409,15 @@ def test_main():
     if gzip:
         tests.extend([
             ReadTestGzip, ReadStreamTestGzip,
-            WriteTestGzip, WriteStreamTestGzip
+            WriteTestGzip, WriteStreamTestGzip,
+            ReadAsteriskTestGzip, ReadStreamAsteriskTestGzip
         ])
 
     if bz2:
         tests.extend([
             ReadTestBzip2, ReadStreamTestBzip2,
-            WriteTestBzip2, WriteStreamTestBzip2
+            WriteTestBzip2, WriteStreamTestBzip2,
+            ReadAsteriskTestBzip2, ReadStreamAsteriskTestBzip2
         ])
     try:
         test_support.run_unittest(*tests)
diff --git a/Misc/NEWS b/Misc/NEWS
index 08a8f43..3db47a3 100644
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -78,6 +78,9 @@ Extension Modules
 Library
 -------
 
+- Patch #918101: Add tarfile open mode r|* for auto-detection of the 
+  stream compression; add, for symmetry reasons, r:* as a synonym of r.
+
 - Patch #1043890: Add extractall method to tarfile.
 
 - Patch #1075887: Don't require MSVC in distutils if there is nothing