diff options
| -rw-r--r-- | Doc/library/urllib.parse.rst | 64 | ||||
| -rw-r--r-- | Lib/email/utils.py | 7 | ||||
| -rw-r--r-- | Lib/test/test_cgi.py | 2 | ||||
| -rw-r--r-- | Lib/test/test_http_cookiejar.py | 5 | ||||
| -rw-r--r-- | Lib/test/test_urllib.py | 249 | ||||
| -rwxr-xr-x | Lib/test/test_wsgiref.py | 2 | ||||
| -rw-r--r-- | Lib/urllib/parse.py | 183 | ||||
| -rw-r--r-- | Misc/NEWS | 7 |
8 files changed, 439 insertions, 80 deletions
diff --git a/Doc/library/urllib.parse.rst b/Doc/library/urllib.parse.rst index a5463e6..0848857 100644 --- a/Doc/library/urllib.parse.rst +++ b/Doc/library/urllib.parse.rst @@ -182,36 +182,84 @@ The :mod:`urllib.parse` module defines the following functions: string. If there is no fragment identifier in *url*, return *url* unmodified and an empty string. -.. function:: quote(string[, safe]) +.. function:: quote(string[, safe[, encoding[, errors]]]) Replace special characters in *string* using the ``%xx`` escape. Letters, digits, and the characters ``'_.-'`` are never quoted. The optional *safe* - parameter specifies additional characters that should not be quoted --- its - default value is ``'/'``. + parameter specifies additional ASCII characters that should not be quoted + --- its default value is ``'/'``. - Example: ``quote('/~connolly/')`` yields ``'/%7econnolly/'``. + *string* may be either a :class:`str` or a :class:`bytes`. + The optional *encoding* and *errors* parameters specify how to deal with + non-ASCII characters, as accepted by the :meth:`str.encode` method. + *encoding* defaults to ``'utf-8'``. + *errors* defaults to ``'strict'``, meaning unsupported characters raise a + :class:`UnicodeEncodeError`. + *encoding* and *errors* must not be supplied if *string* is a + :class:`bytes`, or a :class:`TypeError` is raised. -.. function:: quote_plus(string[, safe]) + Note that ``quote(string, safe, encoding, errors)`` is equivalent to + ``quote_from_bytes(string.encode(encoding, errors), safe)``. + + Example: ``quote('/El Niño/')`` yields ``'/El%20Ni%C3%B1o/'``. + + +.. function:: quote_plus(string[, safe[, encoding[, errors]]]) Like :func:`quote`, but also replace spaces by plus signs, as required for quoting HTML form values. Plus signs in the original string are escaped unless they are included in *safe*. It also does not have *safe* default to ``'/'``. + Example: ``quote_plus('/El Niño/')`` yields ``'%2FEl+Ni%C3%B1o%2F'``. + +.. function:: quote_from_bytes(bytes[, safe]) -.. function:: unquote(string) + Like :func:`quote`, but accepts a :class:`bytes` object rather than a + :class:`str`, and does not perform string-to-bytes encoding. + + Example: ``quote_from_bytes(b'a&\xef')`` yields + ``'a%26%EF'``. + +.. function:: unquote(string[, encoding[, errors]]) Replace ``%xx`` escapes by their single-character equivalent. + The optional *encoding* and *errors* parameters specify how to decode + percent-encoded sequences into Unicode characters, as accepted by the + :meth:`bytes.decode` method. + + *string* must be a :class:`str`. + + *encoding* defaults to ``'utf-8'``. + *errors* defaults to ``'replace'``, meaning invalid sequences are replaced + by a placeholder character. - Example: ``unquote('/%7Econnolly/')`` yields ``'/~connolly/'``. + Example: ``unquote('/El%20Ni%C3%B1o/')`` yields ``'/El Niño/'``. -.. function:: unquote_plus(string) +.. function:: unquote_plus(string[, encoding[, errors]]) Like :func:`unquote`, but also replace plus signs by spaces, as required for unquoting HTML form values. + *string* must be a :class:`str`. + + Example: ``unquote_plus('/El+Ni%C3%B1o/')`` yields ``'/El Niño/'``. + +.. function:: unquote_to_bytes(string) + + Replace ``%xx`` escapes by their single-octet equivalent, and return a + :class:`bytes` object. + + *string* may be either a :class:`str` or a :class:`bytes`. + + If it is a :class:`str`, unescaped non-ASCII characters in *string* + are encoded into UTF-8 bytes. + + Example: ``unquote_to_bytes('a%26%EF')`` yields + ``b'a&\xef'``. + .. function:: urlencode(query[, doseq]) diff --git a/Lib/email/utils.py b/Lib/email/utils.py index e1d21f6..35275f6 100644 --- a/Lib/email/utils.py +++ b/Lib/email/utils.py @@ -219,7 +219,7 @@ def encode_rfc2231(s, charset=None, language=None): charset is given but not language, the string is encoded using the empty string for language. """ - s = urllib.parse.quote(s, safe='') + s = urllib.parse.quote(s, safe='', encoding=charset or 'ascii') if charset is None and language is None: return s if language is None: @@ -271,7 +271,10 @@ def decode_params(params): # language specifiers at the beginning of the string. for num, s, encoded in continuations: if encoded: - s = urllib.parse.unquote(s) + # Decode as "latin-1", so the characters in s directly + # represent the percent-encoded octet values. + # collapse_rfc2231_value treats this as an octet sequence. + s = urllib.parse.unquote(s, encoding="latin-1") extended = True value.append(s) value = quote(EMPTYSTRING.join(value)) diff --git a/Lib/test/test_cgi.py b/Lib/test/test_cgi.py index 9381a3c..cc11acc 100644 --- a/Lib/test/test_cgi.py +++ b/Lib/test/test_cgi.py @@ -68,6 +68,8 @@ parse_qsl_test_cases = [ ("&a=b", [('a', 'b')]), ("a=a+b&b=b+c", [('a', 'a b'), ('b', 'b c')]), ("a=1&a=2", [('a', '1'), ('a', '2')]), + ("a=%26&b=%3D", [('a', '&'), ('b', '=')]), + ("a=%C3%BC&b=%CA%83", [('a', '\xfc'), ('b', '\u0283')]), ] parse_strict_test_cases = [ diff --git a/Lib/test/test_http_cookiejar.py b/Lib/test/test_http_cookiejar.py index 1627923..a97c6fa 100644 --- a/Lib/test/test_http_cookiejar.py +++ b/Lib/test/test_http_cookiejar.py @@ -539,6 +539,8 @@ class CookieTests(TestCase): # unquoted unsafe ("/foo\031/bar", "/foo%19/bar"), ("/\175foo/bar", "/%7Dfoo/bar"), + # unicode, latin-1 range + ("/foo/bar\u00fc", "/foo/bar%C3%BC"), # UTF-8 encoded # unicode ("/foo/bar\uabcd", "/foo/bar%EA%AF%8D"), # UTF-8 encoded ] @@ -1444,7 +1446,8 @@ class LWPCookieTests(TestCase): # Try some URL encodings of the PATHs. # (the behaviour here has changed from libwww-perl) c = CookieJar(DefaultCookiePolicy(rfc2965=True)) - interact_2965(c, "http://www.acme.com/foo%2f%25/%3c%3c%0Anew%E5/%E5", + interact_2965(c, "http://www.acme.com/foo%2f%25/" + "%3c%3c%0Anew%C3%A5/%C3%A5", "foo = bar; version = 1") cookie = interact_2965( diff --git a/Lib/test/test_urllib.py b/Lib/test/test_urllib.py index f5a9d5d..a8a8111 100644 --- a/Lib/test/test_urllib.py +++ b/Lib/test/test_urllib.py @@ -336,10 +336,10 @@ class QuotingTests(unittest.TestCase): "_.-"]) result = urllib.parse.quote(do_not_quote) self.assertEqual(do_not_quote, result, - "using quote(): %s != %s" % (do_not_quote, result)) + "using quote(): %r != %r" % (do_not_quote, result)) result = urllib.parse.quote_plus(do_not_quote) self.assertEqual(do_not_quote, result, - "using quote_plus(): %s != %s" % (do_not_quote, result)) + "using quote_plus(): %r != %r" % (do_not_quote, result)) def test_default_safe(self): # Test '/' is default value for 'safe' parameter @@ -350,11 +350,28 @@ class QuotingTests(unittest.TestCase): quote_by_default = "<>" result = urllib.parse.quote(quote_by_default, safe=quote_by_default) self.assertEqual(quote_by_default, result, - "using quote(): %s != %s" % (quote_by_default, result)) + "using quote(): %r != %r" % (quote_by_default, result)) result = urllib.parse.quote_plus(quote_by_default, safe=quote_by_default) self.assertEqual(quote_by_default, result, - "using quote_plus(): %s != %s" % + "using quote_plus(): %r != %r" % (quote_by_default, result)) + # Safe expressed as bytes rather than str + result = urllib.parse.quote(quote_by_default, safe=b"<>") + self.assertEqual(quote_by_default, result, + "using quote(): %r != %r" % (quote_by_default, result)) + # "Safe" non-ASCII characters should have no effect + # (Since URIs are not allowed to have non-ASCII characters) + result = urllib.parse.quote("a\xfcb", encoding="latin-1", safe="\xfc") + expect = urllib.parse.quote("a\xfcb", encoding="latin-1", safe="") + self.assertEqual(expect, result, + "using quote(): %r != %r" % + (expect, result)) + # Same as above, but using a bytes rather than str + result = urllib.parse.quote("a\xfcb", encoding="latin-1", safe=b"\xfc") + expect = urllib.parse.quote("a\xfcb", encoding="latin-1", safe="") + self.assertEqual(expect, result, + "using quote(): %r != %r" % + (expect, result)) def test_default_quoting(self): # Make sure all characters that should be quoted are by default sans @@ -378,34 +395,98 @@ class QuotingTests(unittest.TestCase): expected = "ab%5B%5Dcd" result = urllib.parse.quote(partial_quote) self.assertEqual(expected, result, - "using quote(): %s != %s" % (expected, result)) + "using quote(): %r != %r" % (expected, result)) self.assertEqual(expected, result, - "using quote_plus(): %s != %s" % (expected, result)) + "using quote_plus(): %r != %r" % (expected, result)) def test_quoting_space(self): # Make sure quote() and quote_plus() handle spaces as specified in # their unique way result = urllib.parse.quote(' ') self.assertEqual(result, hexescape(' '), - "using quote(): %s != %s" % (result, hexescape(' '))) + "using quote(): %r != %r" % (result, hexescape(' '))) result = urllib.parse.quote_plus(' ') self.assertEqual(result, '+', - "using quote_plus(): %s != +" % result) + "using quote_plus(): %r != +" % result) given = "a b cd e f" expect = given.replace(' ', hexescape(' ')) result = urllib.parse.quote(given) self.assertEqual(expect, result, - "using quote(): %s != %s" % (expect, result)) + "using quote(): %r != %r" % (expect, result)) expect = given.replace(' ', '+') result = urllib.parse.quote_plus(given) self.assertEqual(expect, result, - "using quote_plus(): %s != %s" % (expect, result)) + "using quote_plus(): %r != %r" % (expect, result)) def test_quoting_plus(self): self.assertEqual(urllib.parse.quote_plus('alpha+beta gamma'), 'alpha%2Bbeta+gamma') self.assertEqual(urllib.parse.quote_plus('alpha+beta gamma', '+'), 'alpha+beta+gamma') + # Test with bytes + self.assertEqual(urllib.parse.quote_plus(b'alpha+beta gamma'), + 'alpha%2Bbeta+gamma') + # Test with safe bytes + self.assertEqual(urllib.parse.quote_plus('alpha+beta gamma', b'+'), + 'alpha+beta+gamma') + + def test_quote_bytes(self): + # Bytes should quote directly to percent-encoded values + given = b"\xa2\xd8ab\xff" + expect = "%A2%D8ab%FF" + result = urllib.parse.quote(given) + self.assertEqual(expect, result, + "using quote(): %r != %r" % (expect, result)) + # Encoding argument should raise type error on bytes input + self.assertRaises(TypeError, urllib.parse.quote, given, + encoding="latin-1") + # quote_from_bytes should work the same + result = urllib.parse.quote_from_bytes(given) + self.assertEqual(expect, result, + "using quote_from_bytes(): %r != %r" + % (expect, result)) + + def test_quote_with_unicode(self): + # Characters in Latin-1 range, encoded by default in UTF-8 + given = "\xa2\xd8ab\xff" + expect = "%C2%A2%C3%98ab%C3%BF" + result = urllib.parse.quote(given) + self.assertEqual(expect, result, + "using quote(): %r != %r" % (expect, result)) + # Characters in Latin-1 range, encoded by with None (default) + result = urllib.parse.quote(given, encoding=None, errors=None) + self.assertEqual(expect, result, + "using quote(): %r != %r" % (expect, result)) + # Characters in Latin-1 range, encoded with Latin-1 + given = "\xa2\xd8ab\xff" + expect = "%A2%D8ab%FF" + result = urllib.parse.quote(given, encoding="latin-1") + self.assertEqual(expect, result, + "using quote(): %r != %r" % (expect, result)) + # Characters in BMP, encoded by default in UTF-8 + given = "\u6f22\u5b57" # "Kanji" + expect = "%E6%BC%A2%E5%AD%97" + result = urllib.parse.quote(given) + self.assertEqual(expect, result, + "using quote(): %r != %r" % (expect, result)) + # Characters in BMP, encoded with Latin-1 + given = "\u6f22\u5b57" + self.assertRaises(UnicodeEncodeError, urllib.parse.quote, given, + encoding="latin-1") + # Characters in BMP, encoded with Latin-1, with replace error handling + given = "\u6f22\u5b57" + expect = "%3F%3F" # "??" + result = urllib.parse.quote(given, encoding="latin-1", + errors="replace") + self.assertEqual(expect, result, + "using quote(): %r != %r" % (expect, result)) + # Characters in BMP, Latin-1, with xmlcharref error handling + given = "\u6f22\u5b57" + expect = "%26%2328450%3B%26%2323383%3B" # "漢字" + result = urllib.parse.quote(given, encoding="latin-1", + errors="xmlcharrefreplace") + self.assertEqual(expect, result, + "using quote(): %r != %r" % (expect, result)) class UnquotingTests(unittest.TestCase): """Tests for unquote() and unquote_plus() @@ -422,23 +503,62 @@ class UnquotingTests(unittest.TestCase): expect = chr(num) result = urllib.parse.unquote(given) self.assertEqual(expect, result, - "using unquote(): %s != %s" % (expect, result)) + "using unquote(): %r != %r" % (expect, result)) result = urllib.parse.unquote_plus(given) self.assertEqual(expect, result, - "using unquote_plus(): %s != %s" % + "using unquote_plus(): %r != %r" % (expect, result)) escape_list.append(given) escape_string = ''.join(escape_list) del escape_list result = urllib.parse.unquote(escape_string) self.assertEqual(result.count('%'), 1, - "using quote(): not all characters escaped; %s" % - result) - result = urllib.parse.unquote(escape_string) - self.assertEqual(result.count('%'), 1, "using unquote(): not all characters escaped: " "%s" % result) + def test_unquoting_badpercent(self): + # Test unquoting on bad percent-escapes + given = '%xab' + expect = given + result = urllib.parse.unquote(given) + self.assertEqual(expect, result, "using unquote(): %r != %r" + % (expect, result)) + given = '%x' + expect = given + result = urllib.parse.unquote(given) + self.assertEqual(expect, result, "using unquote(): %r != %r" + % (expect, result)) + given = '%' + expect = given + result = urllib.parse.unquote(given) + self.assertEqual(expect, result, "using unquote(): %r != %r" + % (expect, result)) + # unquote_to_bytes + given = '%xab' + expect = bytes(given, 'ascii') + result = urllib.parse.unquote_to_bytes(given) + self.assertEqual(expect, result, "using unquote_to_bytes(): %r != %r" + % (expect, result)) + given = '%x' + expect = bytes(given, 'ascii') + result = urllib.parse.unquote_to_bytes(given) + self.assertEqual(expect, result, "using unquote_to_bytes(): %r != %r" + % (expect, result)) + given = '%' + expect = bytes(given, 'ascii') + result = urllib.parse.unquote_to_bytes(given) + self.assertEqual(expect, result, "using unquote_to_bytes(): %r != %r" + % (expect, result)) + + def test_unquoting_mixed_case(self): + # Test unquoting on mixed-case hex digits in the percent-escapes + given = '%Ab%eA' + expect = b'\xab\xea' + result = urllib.parse.unquote_to_bytes(given) + self.assertEqual(expect, result, + "using unquote_to_bytes(): %r != %r" + % (expect, result)) + def test_unquoting_parts(self): # Make sure unquoting works when have non-quoted characters # interspersed @@ -446,10 +566,10 @@ class UnquotingTests(unittest.TestCase): expect = "abcd" result = urllib.parse.unquote(given) self.assertEqual(expect, result, - "using quote(): %s != %s" % (expect, result)) + "using quote(): %r != %r" % (expect, result)) result = urllib.parse.unquote_plus(given) self.assertEqual(expect, result, - "using unquote_plus(): %s != %s" % (expect, result)) + "using unquote_plus(): %r != %r" % (expect, result)) def test_unquoting_plus(self): # Test difference between unquote() and unquote_plus() @@ -457,15 +577,100 @@ class UnquotingTests(unittest.TestCase): expect = given result = urllib.parse.unquote(given) self.assertEqual(expect, result, - "using unquote(): %s != %s" % (expect, result)) + "using unquote(): %r != %r" % (expect, result)) expect = given.replace('+', ' ') result = urllib.parse.unquote_plus(given) self.assertEqual(expect, result, - "using unquote_plus(): %s != %s" % (expect, result)) + "using unquote_plus(): %r != %r" % (expect, result)) + + def test_unquote_to_bytes(self): + given = 'br%C3%BCckner_sapporo_20050930.doc' + expect = b'br\xc3\xbcckner_sapporo_20050930.doc' + result = urllib.parse.unquote_to_bytes(given) + self.assertEqual(expect, result, + "using unquote_to_bytes(): %r != %r" + % (expect, result)) + # Test on a string with unescaped non-ASCII characters + # (Technically an invalid URI; expect those characters to be UTF-8 + # encoded). + result = urllib.parse.unquote_to_bytes("\u6f22%C3%BC") + expect = b'\xe6\xbc\xa2\xc3\xbc' # UTF-8 for "\u6f22\u00fc" + self.assertEqual(expect, result, + "using unquote_to_bytes(): %r != %r" + % (expect, result)) + # Test with a bytes as input + given = b'%A2%D8ab%FF' + expect = b'\xa2\xd8ab\xff' + result = urllib.parse.unquote_to_bytes(given) + self.assertEqual(expect, result, + "using unquote_to_bytes(): %r != %r" + % (expect, result)) + # Test with a bytes as input, with unescaped non-ASCII bytes + # (Technically an invalid URI; expect those bytes to be preserved) + given = b'%A2\xd8ab%FF' + expect = b'\xa2\xd8ab\xff' + result = urllib.parse.unquote_to_bytes(given) + self.assertEqual(expect, result, + "using unquote_to_bytes(): %r != %r" + % (expect, result)) def test_unquote_with_unicode(self): - r = urllib.parse.unquote('br%C3%BCckner_sapporo_20050930.doc') - self.assertEqual(r, 'br\xc3\xbcckner_sapporo_20050930.doc') + # Characters in the Latin-1 range, encoded with UTF-8 + given = 'br%C3%BCckner_sapporo_20050930.doc' + expect = 'br\u00fcckner_sapporo_20050930.doc' + result = urllib.parse.unquote(given) + self.assertEqual(expect, result, + "using unquote(): %r != %r" % (expect, result)) + # Characters in the Latin-1 range, encoded with None (default) + result = urllib.parse.unquote(given, encoding=None, errors=None) + self.assertEqual(expect, result, + "using unquote(): %r != %r" % (expect, result)) + + # Characters in the Latin-1 range, encoded with Latin-1 + result = urllib.parse.unquote('br%FCckner_sapporo_20050930.doc', + encoding="latin-1") + expect = 'br\u00fcckner_sapporo_20050930.doc' + self.assertEqual(expect, result, + "using unquote(): %r != %r" % (expect, result)) + + # Characters in BMP, encoded with UTF-8 + given = "%E6%BC%A2%E5%AD%97" + expect = "\u6f22\u5b57" # "Kanji" + result = urllib.parse.unquote(given) + self.assertEqual(expect, result, + "using unquote(): %r != %r" % (expect, result)) + + # Decode with UTF-8, invalid sequence + given = "%F3%B1" + expect = "\ufffd" # Replacement character + result = urllib.parse.unquote(given) + self.assertEqual(expect, result, + "using unquote(): %r != %r" % (expect, result)) + + # Decode with UTF-8, invalid sequence, replace errors + result = urllib.parse.unquote(given, errors="replace") + self.assertEqual(expect, result, + "using unquote(): %r != %r" % (expect, result)) + + # Decode with UTF-8, invalid sequence, ignoring errors + given = "%F3%B1" + expect = "" + result = urllib.parse.unquote(given, errors="ignore") + self.assertEqual(expect, result, + "using unquote(): %r != %r" % (expect, result)) + + # A mix of non-ASCII and percent-encoded characters, UTF-8 + result = urllib.parse.unquote("\u6f22%C3%BC") + expect = '\u6f22\u00fc' + self.assertEqual(expect, result, + "using unquote(): %r != %r" % (expect, result)) + + # A mix of non-ASCII and percent-encoded characters, Latin-1 + # (Note, the string contains non-Latin-1-representable characters) + result = urllib.parse.unquote("\u6f22%FC", encoding="latin-1") + expect = '\u6f22\u00fc' + self.assertEqual(expect, result, + "using unquote(): %r != %r" % (expect, result)) class urlencode_Tests(unittest.TestCase): """Tests for urlencode()""" diff --git a/Lib/test/test_wsgiref.py b/Lib/test/test_wsgiref.py index ac5ada3..b98452d 100755 --- a/Lib/test/test_wsgiref.py +++ b/Lib/test/test_wsgiref.py @@ -291,6 +291,7 @@ class UtilityTests(TestCase): def testAppURIs(self): self.checkAppURI("http://127.0.0.1/") self.checkAppURI("http://127.0.0.1/spam", SCRIPT_NAME="/spam") + self.checkAppURI("http://127.0.0.1/sp%C3%A4m", SCRIPT_NAME="/späm") self.checkAppURI("http://spam.example.com:2071/", HTTP_HOST="spam.example.com:2071", SERVER_PORT="2071") self.checkAppURI("http://spam.example.com/", @@ -304,6 +305,7 @@ class UtilityTests(TestCase): def testReqURIs(self): self.checkReqURI("http://127.0.0.1/") self.checkReqURI("http://127.0.0.1/spam", SCRIPT_NAME="/spam") + self.checkReqURI("http://127.0.0.1/sp%C3%A4m", SCRIPT_NAME="/späm") self.checkReqURI("http://127.0.0.1/spammity/spam", SCRIPT_NAME="/spammity", PATH_INFO="/spam") self.checkReqURI("http://127.0.0.1/spammity/spam?say=ni", diff --git a/Lib/urllib/parse.py b/Lib/urllib/parse.py index 3e00695..94d77eb 100644 --- a/Lib/urllib/parse.py +++ b/Lib/urllib/parse.py @@ -5,9 +5,12 @@ UC Irvine, June 1995. """ import sys +import collections __all__ = ["urlparse", "urlunparse", "urljoin", "urldefrag", - "urlsplit", "urlunsplit"] + "urlsplit", "urlunsplit", + "quote", "quote_plus", "quote_from_bytes", + "unquote", "unquote_plus", "unquote_to_bytes"] # A classification of schemes ('' means apply by default) uses_relative = ['ftp', 'http', 'gopher', 'nntp', 'imap', @@ -269,50 +272,101 @@ def urldefrag(url): else: return url, '' - -_hextochr = dict(('%02x' % i, chr(i)) for i in range(256)) -_hextochr.update(('%02X' % i, chr(i)) for i in range(256)) - -def unquote(s): - """unquote('abc%20def') -> 'abc def'.""" - res = s.split('%') +def unquote_to_bytes(string): + """unquote_to_bytes('abc%20def') -> b'abc def'.""" + # Note: strings are encoded as UTF-8. This is only an issue if it contains + # unescaped non-ASCII characters, which URIs should not. + if isinstance(string, str): + string = string.encode('utf-8') + res = string.split(b'%') + res[0] = res[0] + for i in range(1, len(res)): + item = res[i] + try: + res[i] = bytes([int(item[:2], 16)]) + item[2:] + except ValueError: + res[i] = b'%' + item + return b''.join(res) + +def unquote(string, encoding='utf-8', errors='replace'): + """Replace %xx escapes by their single-character equivalent. The optional + encoding and errors parameters specify how to decode percent-encoded + sequences into Unicode characters, as accepted by the bytes.decode() + method. + By default, percent-encoded sequences are decoded with UTF-8, and invalid + sequences are replaced by a placeholder character. + + unquote('abc%20def') -> 'abc def'. + """ + if encoding is None: encoding = 'utf-8' + if errors is None: errors = 'replace' + # pct_sequence: contiguous sequence of percent-encoded bytes, decoded + # (list of single-byte bytes objects) + pct_sequence = [] + res = string.split('%') for i in range(1, len(res)): item = res[i] try: - res[i] = _hextochr[item[:2]] + item[2:] - except KeyError: - res[i] = '%' + item - except UnicodeDecodeError: - res[i] = chr(int(item[:2], 16)) + item[2:] - return "".join(res) - -def unquote_plus(s): - """unquote('%7e/abc+def') -> '~/abc def'""" - s = s.replace('+', ' ') - return unquote(s) - -always_safe = ('ABCDEFGHIJKLMNOPQRSTUVWXYZ' - 'abcdefghijklmnopqrstuvwxyz' - '0123456789' '_.-') + if not item: raise ValueError + pct_sequence.append(bytes.fromhex(item[:2])) + rest = item[2:] + except ValueError: + rest = '%' + item + if not rest: + # This segment was just a single percent-encoded character. + # May be part of a sequence of code units, so delay decoding. + # (Stored in pct_sequence). + res[i] = '' + else: + # Encountered non-percent-encoded characters. Flush the current + # pct_sequence. + res[i] = b''.join(pct_sequence).decode(encoding, errors) + rest + pct_sequence = [] + if pct_sequence: + # Flush the final pct_sequence + # res[-1] will always be empty if pct_sequence != [] + assert not res[-1], "string=%r, res=%r" % (string, res) + res[-1] = b''.join(pct_sequence).decode(encoding, errors) + return ''.join(res) + +def unquote_plus(string, encoding='utf-8', errors='replace'): + """Like unquote(), but also replace plus signs by spaces, as required for + unquoting HTML form values. + + unquote_plus('%7e/abc+def') -> '~/abc def' + """ + string = string.replace('+', ' ') + return unquote(string, encoding, errors) + +_ALWAYS_SAFE = frozenset(b'ABCDEFGHIJKLMNOPQRSTUVWXYZ' + b'abcdefghijklmnopqrstuvwxyz' + b'0123456789' + b'_.-') _safe_quoters= {} -class Quoter: +class Quoter(collections.defaultdict): + """A mapping from bytes (in range(0,256)) to strings. + + String values are percent-encoded byte values, unless the key < 128, and + in the "safe" set (either the specified safe set, or default set). + """ + # Keeps a cache internally, using defaultdict, for efficiency (lookups + # of cached keys don't call Python code at all). def __init__(self, safe): - self.cache = {} - self.safe = safe + always_safe + """safe: bytes object.""" + self.safe = _ALWAYS_SAFE.union(c for c in safe if c < 128) - def __call__(self, c): - try: - return self.cache[c] - except KeyError: - if ord(c) < 256: - res = (c in self.safe) and c or ('%%%02X' % ord(c)) - self.cache[c] = res - return res - else: - return "".join(['%%%02X' % i for i in c.encode("utf-8")]) + def __repr__(self): + # Without this, will just display as a defaultdict + return "<Quoter %r>" % dict(self) + + def __missing__(self, b): + # Handle a cache miss. Store quoted string in cache and return. + res = b in self.safe and chr(b) or ('%%%02X' % b) + self[b] = res + return res -def quote(s, safe = '/'): +def quote(string, safe='/', encoding=None, errors=None): """quote('abc def') -> 'abc%20def' Each part of a URL, e.g. the path info, the query, etc., has a @@ -332,22 +386,57 @@ def quote(s, safe = '/'): is reserved, but in typical usage the quote function is being called on a path where the existing slash characters are used as reserved characters. + + string and safe may be either str or bytes objects. encoding must + not be specified if string is a str. + + The optional encoding and errors parameters specify how to deal with + non-ASCII characters, as accepted by the str.encode method. + By default, encoding='utf-8' (characters are encoded with UTF-8), and + errors='strict' (unsupported characters raise a UnicodeEncodeError). + """ + if isinstance(string, str): + if encoding is None: + encoding = 'utf-8' + if errors is None: + errors = 'strict' + string = string.encode(encoding, errors) + else: + if encoding is not None: + raise TypeError("quote() doesn't support 'encoding' for bytes") + if errors is not None: + raise TypeError("quote() doesn't support 'errors' for bytes") + return quote_from_bytes(string, safe) + +def quote_plus(string, safe='', encoding=None, errors=None): + """Like quote(), but also replace ' ' with '+', as required for quoting + HTML form values. Plus signs in the original string are escaped unless + they are included in safe. It also does not have safe default to '/'. """ - cachekey = (safe, always_safe) + # Check if ' ' in string, where string may either be a str or bytes + if ' ' in string if isinstance(string, str) else b' ' in string: + string = quote(string, + safe + ' ' if isinstance(safe, str) else safe + b' ') + return string.replace(' ', '+') + return quote(string, safe, encoding, errors) + +def quote_from_bytes(bs, safe='/'): + """Like quote(), but accepts a bytes object rather than a str, and does + not perform string-to-bytes encoding. It always returns an ASCII string. + quote_from_bytes(b'abc def\xab') -> 'abc%20def%AB' + """ + if isinstance(safe, str): + # Normalize 'safe' by converting to bytes and removing non-ASCII chars + safe = safe.encode('ascii', 'ignore') + cachekey = bytes(safe) # In case it was a bytearray + if not (isinstance(bs, bytes) or isinstance(bs, bytearray)): + raise TypeError("quote_from_bytes() expected a bytes") try: quoter = _safe_quoters[cachekey] except KeyError: quoter = Quoter(safe) _safe_quoters[cachekey] = quoter - res = map(quoter, s) - return ''.join(res) - -def quote_plus(s, safe = ''): - """Quote the query fragment of a URL; replacing ' ' with '+'""" - if ' ' in s: - s = quote(s, safe + ' ') - return s.replace(' ', '+') - return quote(s, safe) + return ''.join(map(quoter.__getitem__, bs)) def urlencode(query,doseq=0): """Encode a sequence of two-element tuples or dictionary into a URL query string. @@ -30,6 +30,13 @@ Core and Builtins Library ------- +- Issue #3300: make urllib.parse.[un]quote() default to UTF-8. + Code contributed by Matt Giuca. quote() now encodes the input + before quoting, unquote() decodes after unquoting. There are + new arguments to change the encoding and errors settings. + There are also new APIs to skip the encode/decode steps. + [un]quote_plus() are also affected. + - Issue #2235: numbers.Number now blocks inheritance of the default id() based hash because that hash mechanism is not correct for numeric types. All concrete numeric types that inherit from Number (rather than just |