summaryrefslogtreecommitdiff
path: root/doc/source
diff options
context:
space:
mode:
authorDavid Cournapeau <cournape@gmail.com>2009-06-30 10:08:27 +0000
committerDavid Cournapeau <cournape@gmail.com>2009-06-30 10:08:27 +0000
commit8e96f6afadbb5e985442d5821e6f79eb5f795a7b (patch)
tree2477f1b3ff95708a16cf82cca45810e5ba48cd5a /doc/source
parentdfd3b749cb4c423ea4c211044f34d36bc07218ba (diff)
downloadnumpy-8e96f6afadbb5e985442d5821e6f79eb5f795a7b.tar.gz
BUG: Fix NPY_* macros for endianness (#1154).
I managed to screw them up: they did not actually mimic the gblic endian.h behavior, that is NPY_BIG_ENDIAN and NPY_LITTLE_ENDIAN should always be defined, and endianness should be detected by comparison with NPY_BYTE_ORDER. This needs to be fixed because the behavior of the NPY_ macros was different depending on whether endian.h was available or not. Let's hope nobody depended on it...
Diffstat (limited to 'doc/source')
-rw-r--r--doc/source/reference/c-api.config.rst4
1 files changed, 2 insertions, 2 deletions
diff --git a/doc/source/reference/c-api.config.rst b/doc/source/reference/c-api.config.rst
index 0c7f6b147..0989c53d7 100644
--- a/doc/source/reference/c-api.config.rst
+++ b/doc/source/reference/c-api.config.rst
@@ -89,8 +89,8 @@ Platform information
.. versionadded:: 1.3.0
Portable alternatives to the ``endian.h`` macros of GNU Libc.
- One of :cdata:`NPY_BIG_ENDIAN` :cdata:`NPY_LITTLE_ENDIAN` or
- is defined, and :cdata:`NPY_BYTE_ORDER` is either 4321 or 1234.
+ If big endian, :cdata:`NPY_BYTE_ORDER` == :cdata:`NPY_BIG_ENDIAN`, and
+ similarly for little endian architectures.
Defined in ``numpy/npy_endian.h``.