SickGear/lib/httplib2/iri2uri.py
echel0n 0d9fbc1ad7 Welcome to our SickBeard-TVRage Edition ...
This version of SickBeard uses both TVDB and TVRage to search and gather it's series data from allowing you to now have access to and download shows that you couldn't before because of being locked into only what TheTVDB had to offer.

Also this edition is based off the code we used in our XEM editon so it does come with scene numbering support as well as all the other features our XEM edition has to offer.

Please before using this with your existing database (sickbeard.db) please make a backup copy of it and delete any other database files such as cache.db and failed.db if present, we HIGHLY recommend starting out with no database files at all to make this a fresh start but the choice is at your own risk!

Enjoy!
2014-03-09 22:39:12 -07:00

110 lines
3.8 KiB
Python

"""
iri2uri
Converts an IRI to a URI.
"""
__author__ = "Joe Gregorio (joe@bitworking.org)"
__copyright__ = "Copyright 2006, Joe Gregorio"
__contributors__ = []
__version__ = "1.0.0"
__license__ = "MIT"
__history__ = """
"""
import urlparse
# Convert an IRI to a URI following the rules in RFC 3987
#
# The characters we need to enocde and escape are defined in the spec:
#
# iprivate = %xE000-F8FF / %xF0000-FFFFD / %x100000-10FFFD
# ucschar = %xA0-D7FF / %xF900-FDCF / %xFDF0-FFEF
# / %x10000-1FFFD / %x20000-2FFFD / %x30000-3FFFD
# / %x40000-4FFFD / %x50000-5FFFD / %x60000-6FFFD
# / %x70000-7FFFD / %x80000-8FFFD / %x90000-9FFFD
# / %xA0000-AFFFD / %xB0000-BFFFD / %xC0000-CFFFD
# / %xD0000-DFFFD / %xE1000-EFFFD
escape_range = [
(0xA0, 0xD7FF ),
(0xE000, 0xF8FF ),
(0xF900, 0xFDCF ),
(0xFDF0, 0xFFEF),
(0x10000, 0x1FFFD ),
(0x20000, 0x2FFFD ),
(0x30000, 0x3FFFD),
(0x40000, 0x4FFFD ),
(0x50000, 0x5FFFD ),
(0x60000, 0x6FFFD),
(0x70000, 0x7FFFD ),
(0x80000, 0x8FFFD ),
(0x90000, 0x9FFFD),
(0xA0000, 0xAFFFD ),
(0xB0000, 0xBFFFD ),
(0xC0000, 0xCFFFD),
(0xD0000, 0xDFFFD ),
(0xE1000, 0xEFFFD),
(0xF0000, 0xFFFFD ),
(0x100000, 0x10FFFD)
]
def encode(c):
retval = c
i = ord(c)
for low, high in escape_range:
if i < low:
break
if i >= low and i <= high:
retval = "".join(["%%%2X" % ord(o) for o in c.encode('utf-8')])
break
return retval
def iri2uri(uri):
"""Convert an IRI to a URI. Note that IRIs must be
passed in a unicode strings. That is, do not utf-8 encode
the IRI before passing it into the function."""
if isinstance(uri ,unicode):
(scheme, authority, path, query, fragment) = urlparse.urlsplit(uri)
authority = authority.encode('idna')
# For each character in 'ucschar' or 'iprivate'
# 1. encode as utf-8
# 2. then %-encode each octet of that utf-8
uri = urlparse.urlunsplit((scheme, authority, path, query, fragment))
uri = "".join([encode(c) for c in uri])
return uri
if __name__ == "__main__":
import unittest
class Test(unittest.TestCase):
def test_uris(self):
"""Test that URIs are invariant under the transformation."""
invariant = [
u"ftp://ftp.is.co.za/rfc/rfc1808.txt",
u"http://www.ietf.org/rfc/rfc2396.txt",
u"ldap://[2001:db8::7]/c=GB?objectClass?one",
u"mailto:John.Doe@example.com",
u"news:comp.infosystems.www.servers.unix",
u"tel:+1-816-555-1212",
u"telnet://192.0.2.16:80/",
u"urn:oasis:names:specification:docbook:dtd:xml:4.1.2" ]
for uri in invariant:
self.assertEqual(uri, iri2uri(uri))
def test_iri(self):
""" Test that the right type of escaping is done for each part of the URI."""
self.assertEqual("http://xn--o3h.com/%E2%98%84", iri2uri(u"http://\N{COMET}.com/\N{COMET}"))
self.assertEqual("http://bitworking.org/?fred=%E2%98%84", iri2uri(u"http://bitworking.org/?fred=\N{COMET}"))
self.assertEqual("http://bitworking.org/#%E2%98%84", iri2uri(u"http://bitworking.org/#\N{COMET}"))
self.assertEqual("#%E2%98%84", iri2uri(u"#\N{COMET}"))
self.assertEqual("/fred?bar=%E2%98%9A#%E2%98%84", iri2uri(u"/fred?bar=\N{BLACK LEFT POINTING INDEX}#\N{COMET}"))
self.assertEqual("/fred?bar=%E2%98%9A#%E2%98%84", iri2uri(iri2uri(u"/fred?bar=\N{BLACK LEFT POINTING INDEX}#\N{COMET}")))
self.assertNotEqual("/fred?bar=%E2%98%9A#%E2%98%84", iri2uri(u"/fred?bar=\N{BLACK LEFT POINTING INDEX}#\N{COMET}".encode('utf-8')))
unittest.main()