Merge branch 'develop' of github.com:pycompression/python-isal into develop

Author: rhpvorderman

CHANGELOG.rst

@@ -9,6 +9,8 @@ Changelog
 
 version 0.5.0-dev
 -----------------
++ Fix a bug where negative integers were not allowed for the ``adler32`` and
+  ``crc32`` functions in ``isal_zlib``.
 + Provided stubs (type-hint files) for ``isal_zlib`` and ``_isal`` modules.
   Package is now tested with mypy to ensure correct type information.
 + The command-line interface now reads in blocks of 32K instead of 8K. This

README.rst

@@ -129,8 +129,6 @@ Differences with zlib and gzip modules
   in ``isal_zlib`` and ``igzip`` this is the **lowest compression level**.
   This is a design choice that was inherited from the ISA-L library.
 + Compression levels range from 0 to 3, not 1 to 9.
-+ ``isal_zlib.crc32`` and ``isal_zlib.adler32`` do not support negative
-  numbers for the value parameter.
 + ``zlib.Z_DEFAULT_STRATEGY``, ``zlib.Z_RLE`` etc. are exposed as
   ``isal_zlib.Z_DEFAULT_STRATEGY``, ``isal_zlib.Z_RLE`` etc. for compatibility
   reasons. However, ``isal_zlib`` only supports a default strategy and will

src/isal/isal_zlib.pyx

@@ -34,7 +34,7 @@ from cpython.mem cimport PyMem_Malloc, PyMem_Free
 from cpython.buffer cimport PyBUF_READ, PyBUF_C_CONTIGUOUS, PyObject_GetBuffer, \
     PyBuffer_Release
 from cpython.bytes cimport PyBytes_FromStringAndSize
-
+from cpython.long cimport PyLong_AsUnsignedLongMask
 
 cdef extern from "<Python.h>":
     const Py_ssize_t PY_SSIZE_T_MAX
@@ -86,41 +86,43 @@ if ISAL_DEF_MAX_HIST_BITS > zlib.MAX_WBITS:
                      "Please contact the developers.")
 
 
-def adler32(data, unsigned int value = 1):
+def adler32(data, value = 1):
     """
     Computes an Adler-32 checksum of *data*. Returns the checksum as unsigned
     32-bit integer.
 
     :param data: Binary data (bytes, bytearray, memoryview).
     :param value: The starting value of the checksum.
     """
+    cdef unsigned long init = PyLong_AsUnsignedLongMask(value)
     cdef Py_buffer buffer_data
     cdef Py_buffer* buffer = &buffer_data
     if PyObject_GetBuffer(data, buffer, PyBUF_READ & PyBUF_C_CONTIGUOUS) != 0:
         raise TypeError("Failed to get buffer")
     try:
         if buffer.len > UINT64_MAX:
             raise ValueError("Data too big for adler32")
-        return isal_adler32(value, <unsigned char*>buffer.buf, buffer.len)
+        return isal_adler32(init, <unsigned char*>buffer.buf, buffer.len)
     finally:
         PyBuffer_Release(buffer)
 
-def crc32(data, unsigned int value = 0):
+def crc32(data, value = 0):
     """
     Computes a CRC-32 checksum of *data*. Returns the checksum as unsigned
     32-bit integer.
 
     :param data: Binary data (bytes, bytearray, memoryview).
     :param value: The starting value of the checksum.
     """
+    cdef unsigned long init = PyLong_AsUnsignedLongMask(value)
     cdef Py_buffer buffer_data
     cdef Py_buffer* buffer = &buffer_data
     if PyObject_GetBuffer(data, buffer, PyBUF_READ & PyBUF_C_CONTIGUOUS) != 0:
         raise TypeError("Failed to get buffer")
     try:
         if buffer.len > UINT64_MAX:
             raise ValueError("Data too big for adler32")
-        return crc32_gzip_refl(value, <unsigned char*>buffer.buf, buffer.len)
+        return crc32_gzip_refl(init, <unsigned char*>buffer.buf, buffer.len)
     finally:
         PyBuffer_Release(buffer)
 

tests/test_isal.py

@@ -35,8 +35,10 @@
 DATA_SIZES = [2**i for i in range(3, 20)]
 # 100 seeds generated with random.randint(0, 2**32-1)
 SEEDS_FILE = DATA_DIR / "seeds.txt"
-# Create seeds 0, 1 and 20 seeds from the seeds file.
-SEEDS = [0, 1] + [int(seed) for seed in SEEDS_FILE.read_text().splitlines()]
+INT_OVERFLOW = 211928379812738912738917238971289378912379823871932719823798123
+# Get some negative ints and some really big ints into the mix.
+SEEDS = [-INT_OVERFLOW, -3, -1, 0, 1, INT_OVERFLOW] + [
+    int(seed) for seed in SEEDS_FILE.read_text().splitlines()]
 
 # Wbits for ZLIB compression, GZIP compression, and RAW compressed streams
 WBITS_RANGE = list(range(9, 16)) + list(range(25, 32)) + list(range(-15, -8))