diff options
Diffstat (limited to 'third_party/python/urllib3/urllib3/util/url.py')
| -rw-r--r-- | third_party/python/urllib3/urllib3/util/url.py | 17 |
1 files changed, 11 insertions, 6 deletions
diff --git a/third_party/python/urllib3/urllib3/util/url.py b/third_party/python/urllib3/urllib3/util/url.py index 6ff238fe3c..e5682d3be4 100644 --- a/third_party/python/urllib3/urllib3/util/url.py +++ b/third_party/python/urllib3/urllib3/util/url.py @@ -50,7 +50,7 @@ _variations = [ "(?:(?:%(hex)s:){0,6}%(hex)s)?::", ] -UNRESERVED_PAT = r"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789._!\-~" +UNRESERVED_PAT = r"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789._\-~" IPV6_PAT = "(?:" + "|".join([x % _subs for x in _variations]) + ")" ZONE_ID_PAT = "(?:%25|%)(?:[" + UNRESERVED_PAT + "]|%[a-fA-F0-9]{2})+" IPV6_ADDRZ_PAT = r"\[" + IPV6_PAT + r"(?:" + ZONE_ID_PAT + r")?\]" @@ -63,12 +63,12 @@ IPV6_ADDRZ_RE = re.compile("^" + IPV6_ADDRZ_PAT + "$") BRACELESS_IPV6_ADDRZ_RE = re.compile("^" + IPV6_ADDRZ_PAT[2:-2] + "$") ZONE_ID_RE = re.compile("(" + ZONE_ID_PAT + r")\]$") -SUBAUTHORITY_PAT = (u"^(?:(.*)@)?(%s|%s|%s)(?::([0-9]{0,5}))?$") % ( +_HOST_PORT_PAT = ("^(%s|%s|%s)(?::0*?(|0|[1-9][0-9]{0,4}))?$") % ( REG_NAME_PAT, IPV4_PAT, IPV6_ADDRZ_PAT, ) -SUBAUTHORITY_RE = re.compile(SUBAUTHORITY_PAT, re.UNICODE | re.DOTALL) +_HOST_PORT_RE = re.compile(_HOST_PORT_PAT, re.UNICODE | re.DOTALL) UNRESERVED_CHARS = set( "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789._-~" @@ -279,6 +279,9 @@ def _normalize_host(host, scheme): if scheme in NORMALIZABLE_SCHEMES: is_ipv6 = IPV6_ADDRZ_RE.match(host) if is_ipv6: + # IPv6 hosts of the form 'a::b%zone' are encoded in a URL as + # such per RFC 6874: 'a::b%25zone'. Unquote the ZoneID + # separator as necessary to return a valid RFC 4007 scoped IP. match = ZONE_ID_RE.search(host) if match: start, end = match.span(1) @@ -300,7 +303,7 @@ def _normalize_host(host, scheme): def _idna_encode(name): - if name and any([ord(x) > 128 for x in name]): + if name and any(ord(x) >= 128 for x in name): try: import idna except ImportError: @@ -331,7 +334,7 @@ def parse_url(url): """ Given a url, return a parsed :class:`.Url` namedtuple. Best-effort is performed to parse incomplete urls. Fields not provided will be None. - This parser is RFC 3986 compliant. + This parser is RFC 3986 and RFC 6874 compliant. The parser logic and helper functions are based heavily on work done in the ``rfc3986`` module. @@ -365,7 +368,9 @@ def parse_url(url): scheme = scheme.lower() if authority: - auth, host, port = SUBAUTHORITY_RE.match(authority).groups() + auth, _, host_port = authority.rpartition("@") + auth = auth or None + host, port = _HOST_PORT_RE.match(host_port).groups() if auth and normalize_uri: auth = _encode_invalid_chars(auth, USERINFO_CHARS) if port == "": |