def get_file_content(url, comes_from=None, session=None):
"""Gets the content of a file; it may be a filename, file: URL, or
http: URL. Returns (location, content). Content is unicode."""
if session is None:
raise TypeError(
"get_file_content() missing 1 required keyword argument: 'session'"
)
match = _scheme_re.search(url)
if match:
scheme = match.group(1).lower()
if (scheme == 'file' and comes_from and comes_from.startswith('http')):
raise InstallationError(
'Requirements file %s references URL %s, which is local' %
(comes_from, url))
if scheme == 'file':
path = url.split(':', 1)[1]
path = path.replace('\\', '/')
match = _url_slash_drive_re.match(path)
if match:
path = match.group(1) + ':' + path.split('|', 1)[1]
path = urllib_parse.unquote(path)
if path.startswith('/'):
path = '/' + path.lstrip('/')
url = path
else:
# FIXME: catch some errors
resp = session.get(url)
resp.raise_for_status()
return resp.url, resp.text
try:
with open(url, 'rb') as f:
content = auto_decode(f.read())
except IOError as exc:
raise InstallationError('Could not open requirements file: %s' %
str(exc))
return url, content
def filename(self):
_, netloc, path, _, _ = urllib_parse.urlsplit(self.url)
name = posixpath.basename(path.rstrip('/')) or netloc
name = urllib_parse.unquote(name)
assert name, ('URL %r produced no filename' % self.url)
return name
def path(self):
return urllib_parse.unquote(urllib_parse.urlsplit(self.url)[2])
def normalize_url(self, url):
"""
Normalize a URL for comparison by unquoting it and removing any
trailing slash.
"""
return urllib_parse.unquote(url).rstrip('/')