def iri_to_uri(iri):
"""
Convert an Internationalized Resource Identifier (IRI) portion to a URI
portion that is suitable for inclusion in a URL.
This is the algorithm from section 3.1 of RFC 3987. However, since we are
assuming input is either UTF-8 or unicode already, we can simplify things a
little from the full method.
Takes an IRI in UTF-8 bytes (e.g. '/I \xe2\x99\xa5 Django/') or unicode
(e.g. '/I ♥ Django/') and returns ASCII bytes containing the encoded result
(e.g. '/I%20%E2%99%A5%20Django/').
"""
# The list of safe characters here is constructed from the "reserved" and
# "unreserved" characters specified in sections 2.2 and 2.3 of RFC 3986:
# reserved = gen-delims / sub-delims
# gen-delims = ":" / "/" / "?" / "#" / "[" / "]" / "@"
# sub-delims = "!" / "$" / "&" / "'" / "(" / ")"
# / "*" / "+" / "," / ";" / "="
# unreserved = ALPHA / DIGIT / "-" / "." / "_" / "~"
# Of the unreserved characters, urllib.quote already considers all but
# the ~ safe.
# The % character is also added to the list of safe characters here, as the
# end of section 3.1 of RFC 3987 specifically mentions that % must not be
# converted.
if iri is None:
return iri
return quote(force_bytes(iri), safe=b"/#%[]=:;$&()+,!?*@'~")
def repercent_broken_unicode(path):
"""
As per section 3.2 of RFC 3987, step three of converting a URI into an IRI,
we need to re-percent-encode any octet produced that is not part of a
strictly legal UTF-8 octet sequence.
"""
try:
path.decode('utf-8')
except UnicodeDecodeError as e:
repercent = quote(path[e.start:e.end], safe=b"/#%[]=:;$&()+,!?*@'~")
path = repercent_broken_unicode(path[:e.start] +
force_bytes(repercent) + path[e.end:])
return path
def escape_uri_path(path):
"""
Escape the unsafe characters from the path portion of a Uniform Resource
Identifier (URI).
"""
# These are the "reserved" and "unreserved" characters specified in
# sections 2.2 and 2.3 of RFC 2396:
# reserved = ";" | "/" | "?" | ":" | "@" | "&" | "=" | "+" | "$" | ","
# unreserved = alphanum | mark
# mark = "-" | "_" | "." | "!" | "~" | "*" | "'" | "(" | ")"
# The list of safe characters here is constructed subtracting ";", "=",
# and "?" according to section 3.3 of RFC 2396.
# The reason for not subtracting and escaping "/" is that we are escaping
# the entire path, not a path segment.
return quote(force_bytes(path), safe=b"/:@&+$,-_.!~*'()")
def filepath_to_uri(path):
"""Convert a file system path to a URI portion that is suitable for
inclusion in a URL.
We are assuming input is either UTF-8 or unicode already.
This method will encode certain chars that would normally be recognized as
special chars for URIs. Note that this method does not encode the '
character, as it is a valid character within URIs. See
encodeURIComponent() JavaScript function for more details.
Returns an ASCII string containing the encoded result.
"""
if path is None:
return path
# I know about `os.sep` and `os.altsep` but I want to leave
# some flexibility for hardcoding separators.
return quote(force_bytes(path).replace(b"\\", b"/"), safe=b"/~!*()'")