Issue #5784: Expand documentation and tests for zlib wbits parameter

Based on documentation by AM Kuchling.

Doc/library/zlib.rst

@@ -69,9 +69,22 @@ The available exception and functions in this module are:
    *method* is the compression algorithm. Currently, the only supported value is
    ``DEFLATED``.
 
-   *wbits* is the base two logarithm of the size of the window buffer. This
-   should be an integer from ``8`` to ``15``. Higher values give better
-   compression, but use more memory.
+   The *wbits* argument controls the size of the history buffer (or the
+   "window size") used when compressing data, and whether a header and
+   trailer is included in the output.  It can take several ranges of values:
+
+   * +9 to +15: The base-two logarithm of the window size, which
+     therefore ranges between 512 and 32768.  Larger values produce
+     better compression at the expense of greater memory usage.  The
+     resulting output will include a zlib-specific header and trailer.
+
+   * −9 to −15: Uses the absolute value of *wbits* as the
+     window size logarithm, while producing a raw output stream with no
+     header or trailing checksum.
+
+   * +25 to +31 = 16 + (9 to 15): Uses the low 4 bits of the value as the
+     window size logarithm, while including a basic :program:`gzip` header
+     and trailing checksum in the output.
 
    The *memLevel* argument controls the amount of memory used for the
    internal compression state. Valid values range from ``1`` to ``9``.
@@ -113,20 +126,39 @@ The available exception and functions in this module are:
 .. function:: decompress(data[, wbits[, bufsize]])
 
    Decompresses the bytes in *data*, returning a bytes object containing the
-   uncompressed data.  The *wbits* parameter controls the size of the window
-   buffer, and is discussed further below.
+   uncompressed data.  The *wbits* parameter depends on
+   the format of *data*, and is discussed further below.
    If *bufsize* is given, it is used as the initial size of the output
    buffer.  Raises the :exc:`error` exception if any error occurs.
 
-   The absolute value of *wbits* is the base two logarithm of the size of the
-   history buffer (the "window size") used when compressing data.  Its absolute
-   value should be between 8 and 15 for the most recent versions of the zlib
-   library, larger values resulting in better compression at the expense of greater
-   memory usage.  When decompressing a stream, *wbits* must not be smaller
+   .. _decompress-wbits:
+
+   The *wbits* parameter controls the size of the history buffer
+   (or "window size"), and what header and trailer format is expected.
+   It is similar to the parameter for :func:`compressobj`, but accepts
+   more ranges of values:
+
+   * +8 to +15: The base-two logarithm of the window size.  The input
+     must include a zlib header and trailer.
+
+   * 0: Automatically determine the window size from the zlib header.
+
+   * −8 to −15: Uses the absolute value of *wbits* as the window size
+     logarithm.  The input must be a raw stream with no header or trailer.
+
+   * +24 to +31 = 16 + (8 to 15): Uses the low 4 bits of the value as
+     the window size logarithm.  The input must include a gzip header and
+     trailer.
+
+   * +40 to +47 = 32 + (8 to 15): Uses the low 4 bits of the value as
+     the window size logarithm, and automatically accepts either
+     the zlib or gzip format.
+
+   When decompressing a stream, the window size must not be smaller
    than the size originally used to compress the stream; using a too-small
-   value will result in an exception. The default value is therefore the
-   highest value, 15.  When *wbits* is negative, the standard
-   :program:`gzip` header is suppressed.
+   value may result in an :exc:`error` exception. The default *wbits* value
+   is 15, which corresponds to the largest window size and requires a zlib
+   header and trailer to be included.
 
    *bufsize* is the initial size of the buffer used to hold decompressed data.  If
    more space is required, the buffer size will be increased as needed, so you
@@ -139,7 +171,9 @@ The available exception and functions in this module are:
    Returns a decompression object, to be used for decompressing data streams that
    won't fit into memory at once.
 
-   The *wbits* parameter controls the size of the window buffer.
+   The *wbits* parameter controls the size of the history buffer (or the
+   "window size"), and what header and trailer format is expected.  It has
+   the same meaning as `described for decompress() <#decompress-wbits>`__.
 
    The *zdict* parameter specifies a predefined compression dictionary. If
    provided, this must be the same dictionary as was used by the compressor that

Lib/test/test_zlib.py

@@ -680,6 +680,49 @@ class CompressObjectTestCase(BaseCompressTestCase, unittest.TestCase):
         finally:
             data = None
 
+    def test_wbits(self):
+        co = zlib.compressobj(level=1, wbits=15)
+        zlib15 = co.compress(HAMLET_SCENE) + co.flush()
+        self.assertEqual(zlib.decompress(zlib15, 15), HAMLET_SCENE)
+        self.assertEqual(zlib.decompress(zlib15, 0), HAMLET_SCENE)
+        self.assertEqual(zlib.decompress(zlib15, 32 + 15), HAMLET_SCENE)
+        with self.assertRaisesRegex(zlib.error, 'invalid window size'):
+            zlib.decompress(zlib15, 14)
+        dco = zlib.decompressobj(wbits=32 + 15)
+        self.assertEqual(dco.decompress(zlib15), HAMLET_SCENE)
+        dco = zlib.decompressobj(wbits=14)
+        with self.assertRaisesRegex(zlib.error, 'invalid window size'):
+            dco.decompress(zlib15)
+
+        co = zlib.compressobj(level=1, wbits=9)
+        zlib9 = co.compress(HAMLET_SCENE) + co.flush()
+        self.assertEqual(zlib.decompress(zlib9, 9), HAMLET_SCENE)
+        self.assertEqual(zlib.decompress(zlib9, 15), HAMLET_SCENE)
+        self.assertEqual(zlib.decompress(zlib9, 0), HAMLET_SCENE)
+        self.assertEqual(zlib.decompress(zlib9, 32 + 9), HAMLET_SCENE)
+        dco = zlib.decompressobj(wbits=32 + 9)
+        self.assertEqual(dco.decompress(zlib9), HAMLET_SCENE)
+
+        co = zlib.compressobj(level=1, wbits=-15)
+        deflate15 = co.compress(HAMLET_SCENE) + co.flush()
+        self.assertEqual(zlib.decompress(deflate15, -15), HAMLET_SCENE)
+        dco = zlib.decompressobj(wbits=-15)
+        self.assertEqual(dco.decompress(deflate15), HAMLET_SCENE)
+
+        co = zlib.compressobj(level=1, wbits=-9)
+        deflate9 = co.compress(HAMLET_SCENE) + co.flush()
+        self.assertEqual(zlib.decompress(deflate9, -9), HAMLET_SCENE)
+        self.assertEqual(zlib.decompress(deflate9, -15), HAMLET_SCENE)
+        dco = zlib.decompressobj(wbits=-9)
+        self.assertEqual(dco.decompress(deflate9), HAMLET_SCENE)
+
+        co = zlib.compressobj(level=1, wbits=16 + 15)
+        gzip = co.compress(HAMLET_SCENE) + co.flush()
+        self.assertEqual(zlib.decompress(gzip, 16 + 15), HAMLET_SCENE)
+        self.assertEqual(zlib.decompress(gzip, 32 + 15), HAMLET_SCENE)
+        dco = zlib.decompressobj(32 + 15)
+        self.assertEqual(dco.decompress(gzip), HAMLET_SCENE)
+
 
 def genblock(seed, length, step=1024, generator=random):
     """length-byte stream of random data from a seed (in step-byte blocks)."""

Modules/clinic/zlibmodule.c.h

@@ -48,7 +48,7 @@ PyDoc_STRVAR(zlib_decompress__doc__,
 "  data\n"
 "    Compressed data.\n"
 "  wbits\n"
-"    The window buffer size.\n"
+"    The window buffer size and container format.\n"
 "  bufsize\n"
 "    The initial output buffer size.");
 
@@ -95,7 +95,10 @@ PyDoc_STRVAR(zlib_compressobj__doc__,
 "  method\n"
 "    The compression algorithm.  If given, this must be DEFLATED.\n"
 "  wbits\n"
-"    The base two logarithm of the window size (range: 8..15).\n"
+"    +9 to +15: The base-two logarithm of the window size.  Include a zlib\n"
+"        container.\n"
+"    -9 to -15: Generate a raw stream.\n"
+"    +25 to +31: Include a gzip container.\n"
 "  memLevel\n"
 "    Controls the amount of memory used for internal compression state.\n"
 "    Valid values range from 1 to 9.  Higher values result in higher memory\n"
@@ -146,7 +149,7 @@ PyDoc_STRVAR(zlib_decompressobj__doc__,
 "Return a decompressor object.\n"
 "\n"
 "  wbits\n"
-"    The window buffer size.\n"
+"    The window buffer size and container format.\n"
 "  zdict\n"
 "    The predefined compression dictionary.  This must be the same\n"
 "    dictionary as used by the compressor that produced the input data.");
@@ -439,4 +442,4 @@ exit:
 #ifndef ZLIB_COMPRESS_COPY_METHODDEF
     #define ZLIB_COMPRESS_COPY_METHODDEF
 #endif /* !defined(ZLIB_COMPRESS_COPY_METHODDEF) */
-/*[clinic end generated code: output=cf81e1deae3af0ce input=a9049054013a1b77]*/
+/*[clinic end generated code: output=f31627b314a7bd2f input=a9049054013a1b77]*/

Modules/zlibmodule.c

@@ -271,7 +271,7 @@ zlib.decompress
     data: Py_buffer
         Compressed data.
     wbits: int(c_default="MAX_WBITS") = MAX_WBITS
-        The window buffer size.
+        The window buffer size and container format.
     bufsize: capped_uint(c_default="DEF_BUF_SIZE") = DEF_BUF_SIZE
         The initial output buffer size.
     /
@@ -282,7 +282,7 @@ Returns a bytes object containing the uncompressed data.
 static PyObject *
 zlib_decompress_impl(PyModuleDef *module, Py_buffer *data, int wbits,
                      unsigned int bufsize)
-/*[clinic end generated code: output=444d0987f3429574 input=da095118b3243b27]*/
+/*[clinic end generated code: output=444d0987f3429574 input=75123b0d4ff0541d]*/
 {
     PyObject *result_str = NULL;
     Byte *input;
@@ -396,7 +396,10 @@ zlib.compressobj
     method: int(c_default="DEFLATED") = DEFLATED
         The compression algorithm.  If given, this must be DEFLATED.
     wbits: int(c_default="MAX_WBITS") = MAX_WBITS
-        The base two logarithm of the window size (range: 8..15).
+        +9 to +15: The base-two logarithm of the window size.  Include a zlib
+            container.
+        -9 to -15: Generate a raw stream.
+        +25 to +31: Include a gzip container.
     memLevel: int(c_default="DEF_MEM_LEVEL") = DEF_MEM_LEVEL
         Controls the amount of memory used for internal compression state.
         Valid values range from 1 to 9.  Higher values result in higher memory
@@ -414,7 +417,7 @@ Return a compressor object.
 static PyObject *
 zlib_compressobj_impl(PyModuleDef *module, int level, int method, int wbits,
                       int memLevel, int strategy, Py_buffer *zdict)
-/*[clinic end generated code: output=2949bbb9a5723ccd input=de2ffab6e910cd8b]*/
+/*[clinic end generated code: output=2949bbb9a5723ccd input=2fa3d026f90ab8d5]*/
 {
     compobject *self = NULL;
     int err;
@@ -475,7 +478,7 @@ zlib_compressobj_impl(PyModuleDef *module, int level, int method, int wbits,
 zlib.decompressobj
 
     wbits: int(c_default="MAX_WBITS") = MAX_WBITS
-        The window buffer size.
+        The window buffer size and container format.
     zdict: object(c_default="NULL") = b''
         The predefined compression dictionary.  This must be the same
         dictionary as used by the compressor that produced the input data.
@@ -485,7 +488,7 @@ Return a decompressor object.
 
 static PyObject *
 zlib_decompressobj_impl(PyModuleDef *module, int wbits, PyObject *zdict)
-/*[clinic end generated code: output=8ccd583fbd631798 input=67f05145a6920127]*/
+/*[clinic end generated code: output=8ccd583fbd631798 input=d3832b8511fc977b]*/
 {
     int err;
     compobject *self;
@@ -1329,7 +1332,7 @@ PyDoc_STRVAR(zlib_module_documentation,
 "decompress(string,[wbits],[bufsize]) -- Decompresses a compressed string.\n"
 "decompressobj([wbits[, zdict]]]) -- Return a decompressor object.\n"
 "\n"
-"'wbits' is window buffer size.\n"
+"'wbits' is window buffer size and container format.\n"
 "Compressor objects support compress() and flush() methods; decompressor\n"
 "objects support decompress() and flush().");