def test_decode_encode_path():
temp_dir = ckan_io.decode_path(tempfile.mkdtemp())
try:
filename = u"\xf6\xe4\xfc.txt"
path = os.path.join(temp_dir, filename)
with io.open(ckan_io.encode_path(path), u"w", encoding=u"utf-8") as f:
f.write(u"foo")
# Force str return type
filenames = os.listdir(ckan_io.encode_path(temp_dir))
assert ckan_io.decode_path(filenames[0]) == filename
finally:
shutil.rmtree(temp_dir)
def test_decode_encode_path(self):
temp_dir = ckan_io.decode_path(tempfile.mkdtemp())
try:
filename = u'\xf6\xe4\xfc.txt'
path = os.path.join(temp_dir, filename)
with io.open(ckan_io.encode_path(path), u'w',
encoding=u'utf-8') as f:
f.write(u'foo')
# Force str return type
filenames = os.listdir(ckan_io.encode_path(temp_dir))
eq_(ckan_io.decode_path(filenames[0]), filename)
finally:
shutil.rmtree(temp_dir)
def test_decode_encode_path(self):
temp_dir = ckan_io.decode_path(tempfile.mkdtemp())
try:
filename = u'\xf6\xe4\xfc.txt'
path = os.path.join(temp_dir, filename)
with io.open(ckan_io.encode_path(path), u'w',
encoding=u'utf-8') as f:
f.write(u'foo')
# Force str return type
filenames = os.listdir(ckan_io.encode_path(temp_dir))
eq_(ckan_io.decode_path(filenames[0]), filename)
finally:
shutil.rmtree(temp_dir)
def munge_filename(filename):
''' Tidies a filename
Keeps the filename extension (e.g. .csv).
Strips off any path on the front.
Returns a Unicode string.
'''
if not isinstance(filename, text_type):
filename = decode_path(filename)
# Ignore path
filename = os.path.split(filename)[1]
# Clean up
filename = filename.lower().strip()
filename = substitute_ascii_equivalents(filename)
filename = re.sub(u'[^a-zA-Z0-9_. -]', '', filename).replace(u' ', u'-')
filename = re.sub(u'-+', u'-', filename)
# Enforce length constraints
name, ext = os.path.splitext(filename)
ext = ext[:MAX_FILENAME_EXTENSION_LENGTH]
ext_len = len(ext)
name = _munge_to_length(name, max(1, MIN_FILENAME_TOTAL_LENGTH - ext_len),
MAX_FILENAME_TOTAL_LENGTH - ext_len)
filename = name + ext
return filename
def munge_filename(filename):
''' Tidies a filename
Keeps the filename extension (e.g. .csv).
Strips off any path on the front.
Returns a Unicode string.
'''
if not isinstance(filename, unicode):
filename = decode_path(filename)
# Ignore path
filename = os.path.split(filename)[1]
# Clean up
filename = filename.lower().strip()
filename = substitute_ascii_equivalents(filename)
filename = re.sub(ur'[^a-zA-Z0-9_. -]', '', filename).replace(u' ', u'-')
filename = re.sub(ur'-+', u'-', filename)
# Enforce length constraints
name, ext = os.path.splitext(filename)
ext = ext[:MAX_FILENAME_EXTENSION_LENGTH]
ext_len = len(ext)
name = _munge_to_length(name, max(1, MIN_FILENAME_TOTAL_LENGTH - ext_len),
MAX_FILENAME_TOTAL_LENGTH - ext_len)
filename = name + ext
return filename
def test_decode_path_returns_unicode(self):
ok_(isinstance(ckan_io.decode_path(b'just_a_str'), unicode))
def test_decode_path_fails_for_unicode(self):
ckan_io.decode_path(u'just_a_unicode')
def test_decode_path_returns_unicode(self):
ok_(isinstance(ckan_io.decode_path(b'just_a_str'), unicode))
def test_decode_path_fails_for_unicode(self):
ckan_io.decode_path(u'just_a_unicode')
def test_decode_path_returns_unicode():
assert isinstance(ckan_io.decode_path(b"just_a_str"), text_type)
def test_decode_path_fails_for_unicode():
with pytest.raises(TypeError):
ckan_io.decode_path(u"just_a_unicode")
