summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorMartin Panter <vadmium+py@gmail.com>2016-05-27 07:32:11 (GMT)
committerMartin Panter <vadmium+py@gmail.com>2016-05-27 07:32:11 (GMT)
commit9c946bbf2093f6fb85a4bbe68362d87daead6c98 (patch)
treefd97176f9fb1b44bdc8eb189071fae90e4c496de
parent5541aa35d04ed2bb168bc81e7dae31f5367b15c5 (diff)
downloadcpython-9c946bbf2093f6fb85a4bbe68362d87daead6c98.zip
cpython-9c946bbf2093f6fb85a4bbe68362d87daead6c98.tar.gz
cpython-9c946bbf2093f6fb85a4bbe68362d87daead6c98.tar.bz2
Issue #5784: Expand documentation and tests for zlib wbits parameter
Based on documentation by AM Kuchling.
-rw-r--r--Doc/library/zlib.rst66
-rw-r--r--Lib/test/test_zlib.py43
-rw-r--r--Modules/zlibmodule.c8
3 files changed, 98 insertions, 19 deletions
diff --git a/Doc/library/zlib.rst b/Doc/library/zlib.rst
index 26b0dfc..1e2df00 100644
--- a/Doc/library/zlib.rst
+++ b/Doc/library/zlib.rst
@@ -81,9 +81,23 @@ 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 default is 15.
+ 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.
+ The default is 15.
+
+ * +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.
*memlevel* controls the amount of memory used for internal compression state.
Valid values range from ``1`` to ``9``. Higher values using more memory,
@@ -130,20 +144,39 @@ The available exception and functions in this module are:
.. function:: decompress(string[, wbits[, bufsize]])
Decompresses the data in *string*, returning a string 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 *string*, 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
@@ -154,8 +187,11 @@ The available exception and functions in this module are:
.. function:: decompressobj([wbits])
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.
+ won't fit into memory at once.
+
+ 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>`__.
Compression objects support the following methods:
diff --git a/Lib/test/test_zlib.py b/Lib/test/test_zlib.py
index cc13409..c537c2a 100644
--- a/Lib/test/test_zlib.py
+++ b/Lib/test/test_zlib.py
@@ -527,6 +527,49 @@ class CompressObjectTestCase(BaseCompressTestCase, unittest.TestCase):
decompress = lambda s: d.decompress(s) + d.flush()
self.check_big_decompress_buffer(size, decompress)
+ def test_wbits(self):
+ co = zlib.compressobj(1, zlib.DEFLATED, 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.assertRaisesRegexp(zlib.error, 'invalid window size'):
+ zlib.decompress(zlib15, 14)
+ dco = zlib.decompressobj(32 + 15)
+ self.assertEqual(dco.decompress(zlib15), HAMLET_SCENE)
+ dco = zlib.decompressobj(14)
+ with self.assertRaisesRegexp(zlib.error, 'invalid window size'):
+ dco.decompress(zlib15)
+
+ co = zlib.compressobj(1, zlib.DEFLATED, 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(32 + 9)
+ self.assertEqual(dco.decompress(zlib9), HAMLET_SCENE)
+
+ co = zlib.compressobj(1, zlib.DEFLATED, -15)
+ deflate15 = co.compress(HAMLET_SCENE) + co.flush()
+ self.assertEqual(zlib.decompress(deflate15, -15), HAMLET_SCENE)
+ dco = zlib.decompressobj(-15)
+ self.assertEqual(dco.decompress(deflate15), HAMLET_SCENE)
+
+ co = zlib.compressobj(1, zlib.DEFLATED, -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(-9)
+ self.assertEqual(dco.decompress(deflate9), HAMLET_SCENE)
+
+ co = zlib.compressobj(1, zlib.DEFLATED, 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)."""
diff --git a/Modules/zlibmodule.c b/Modules/zlibmodule.c
index 799e7df..153a86c 100644
--- a/Modules/zlibmodule.c
+++ b/Modules/zlibmodule.c
@@ -106,7 +106,7 @@ PyDoc_STRVAR(compressobj__doc__,
PyDoc_STRVAR(decompressobj__doc__,
"decompressobj([wbits]) -- Return a decompressor object.\n"
"\n"
-"Optional arg wbits is the window buffer size.");
+"Optional arg wbits indicates the window buffer size and container format.");
static compobject *
newcompobject(PyTypeObject *type)
@@ -208,8 +208,8 @@ PyZlib_compress(PyObject *self, PyObject *args)
PyDoc_STRVAR(decompress__doc__,
"decompress(string[, wbits[, bufsize]]) -- Return decompressed string.\n"
"\n"
-"Optional arg wbits is the window buffer size. Optional arg bufsize is\n"
-"the initial output buffer size.");
+"Optional arg wbits indicates the window buffer size and container format.\n"
+"Optional arg bufsize is the initial output buffer size.");
static PyObject *
PyZlib_decompress(PyObject *self, PyObject *args)
@@ -1039,7 +1039,7 @@ PyDoc_STRVAR(zlib_module_documentation,
"decompress(string,[wbits],[bufsize]) -- Decompresses a compressed string.\n"
"decompressobj([wbits]) -- 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().");