[h5py] 266/455: Implement Unicode filename handling; doc updates

[Ghislain Vaillant]

This is an automated email from the git hooks/post-receive script.

ghisvail-guest pushed a commit to annotated tag 1.3.0
in repository h5py.

commit f363743e1e2d63c8c189bdc56a265ae796144e44
Author: andrewcollette <andrew.collette at gmail.com>
Date:   Tue Jun 2 21:45:59 2009 +0000

    Implement Unicode filename handling; doc updates
---
 docs/source/guide/file.rst   | 12 +++++++-----
 h5py/highlevel.py            | 24 +++++++++++++++++++++---
 h5py/tests/test_highlevel.py | 26 ++++++++++++++++++++++++++
 3 files changed, 54 insertions(+), 8 deletions(-)

diff --git a/docs/source/guide/file.rst b/docs/source/guide/file.rst
index 5cfd4a1..e8dc02e 100644
--- a/docs/source/guide/file.rst
+++ b/docs/source/guide/file.rst
@@ -30,7 +30,7 @@ HDF5 ships with a variety of different low-level drivers, which map the logical
 HDF5 address space to different storage mechanisms.  You can specify which
 driver you want to use when the file is opened::
 
-    >>> f = h5py.File('myfile.hdf5', driver=*driver name*, *driver_kwds*)
+    >>> f = h5py.File('myfile.hdf5', driver=<driver name>, <driver_kwds>)
 
 For example, the HDF5 "core" driver can be used to create a purely in-memory
 HDF5 file, optionally written out to disk when it is closed.  Currently
@@ -63,8 +63,8 @@ None
 'family'
     Store the file on disk as a series of fixed-length chunks.  Useful
     if the file system doesn't allow large files.  Note: the filename
-    you provide *must* contain the string "%d", which will be replaced
-    by the file sequence number.  Keywords:
+    you provide *must* contain a printf-style integer format code (e.g "%d"),
+    which will be replaced by the file sequence number.  Keywords:
 
         memb_size
             Maximum file size (default is 2**31-1).
@@ -85,7 +85,8 @@ the full API of Group objects; in this case, the group in question is the
 
     .. attribute:: filename
 
-        HDF5 filename
+        HDF5 filename on disk.  This is a plain string (str) for ASCII names,
+        Unicode otherwise.
 
     .. attribute:: mode
 
@@ -97,7 +98,8 @@ the full API of Group objects; in this case, the group in question is the
 
     .. method:: __init__(name, mode='a', driver=None, **driver_kwds)
         
-        Open or create an HDF5 file.
+        Open or create an HDF5 file.  See above for a summary of options.
+        Argument *name* may be an ASCII or Unicode string.
 
     .. method:: close()
 
diff --git a/h5py/highlevel.py b/h5py/highlevel.py
index 17cfc37..e5de0c9 100644
--- a/h5py/highlevel.py
+++ b/h5py/highlevel.py
@@ -539,8 +539,9 @@ class File(Group):
         'family'
             Store the file on disk as a series of fixed-length chunks.  Useful
             if the file system doesn't allow large files.  Note: the filename
-            you provide *must* contain the string "%d", which will be replaced
-            by the file sequence number.  Keywords:
+            you provide *must* contain a printf-style integer format code
+            (e.g. %d"), which will be replaced by the file sequence number.
+            Keywords:
 
             memb_size:  Maximum file size (default is 2**31-1).
     """
@@ -548,7 +549,17 @@ class File(Group):
     @property
     def filename(self):
         """File name on disk"""
-        return h5f.get_name(self.fid)
+        name = h5f.get_name(self.fid)
+        # Note the exception can happen in one of two ways:
+        # 1. The name doesn't comply with the file system encoding;
+        #    return the raw byte string
+        # 2. The name can't be encoded down to ASCII; return it as
+        #    a Unicode string object
+        try:
+            name = name.decode(sys.getfilesystemencoding())
+            return name.encode('ascii')
+        except UnicodeError:
+            return name
 
     @property
     def mode(self):
@@ -596,6 +607,13 @@ class File(Group):
             else:
                 raise ValueError('Unknown driver type "%s"' % driver)
 
+        try:
+            # If the byte string doesn't match the default encoding, just
+            # pass it on as-is.  Note Unicode objects can always be encoded.
+            name = name.encode(sys.getfilesystemencoding())
+        except UnicodeError:
+            pass
+
         if mode == 'r':
             self.fid = h5f.open(name, h5f.ACC_RDONLY, fapl=plist)
         elif mode == 'r+':
diff --git a/h5py/tests/test_highlevel.py b/h5py/tests/test_highlevel.py
index b13ba03..001104e 100644
--- a/h5py/tests/test_highlevel.py
+++ b/h5py/tests/test_highlevel.py
@@ -55,6 +55,32 @@ class TestFile(HDF5TestCase):
     def tearDown(self):
         os.unlink(self.fname)
 
+    def test_unicode(self):
+        # Three cases:
+        # 1. Unicode
+        #       Store w/filesystem encoding; should be readable as Unicode
+        # 2. Raw byte string in ASCII range
+        #       Store w/filesystem encoding; should be read as ASCII
+        # 3. Raw byte string out of ASCII range
+        #       Store as-is; since it doesn't conform to the filesystem
+        #       encoding, just return the raw string.
+        fnames = (tempfile.mktemp(u'_\u1201.hdf5'),
+                  tempfile.mktemp('_.hdf5'),
+                  tempfile.mktemp('\xff\xff\xff.hdf5'))
+        print ""
+        for fname, typ in zip(fnames, (unicode, str, str)):
+            print 'checking "%r" (%s)' % (fname, typ)
+            try:
+                f = File(fname, 'w')
+                self.assert_(isinstance(f.filename, typ))
+                self.assertEqual(f.filename, fname)
+            finally:
+                try:
+                    f.close()
+                finally:
+                    if os.path.exists(fname):
+                        os.unlink(fname)
+        
     def test_File_init_r(self):
         with File(self.fname, 'r') as f:
             self.assert_(isinstance(f["CompoundChunked"], Dataset))

-- 
Alioth's /usr/local/bin/git-commit-notice on /srv/git.debian.org/git/debian-science/packages/h5py.git