diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py index 99c5c033e30..3c89ed928ff 100644 --- a/Lib/test/test_urlparse.py +++ b/Lib/test/test_urlparse.py @@ -6,8 +6,8 @@ RFC2396_BASE = "http://a/b/c/d;p?q" RFC3986_BASE = 'http://a/b/c/d;p?q' SIMPLE_BASE = 'http://a/b/c/d' -# A list of test cases. Each test case is a two-tuple that contains -# a string with the query and a dictionary with the expected result. +# Each parse_qsl testcase is a two-tuple that contains +# a string with the query and a list with the expected result. parse_qsl_test_cases = [ ("", []), @@ -42,6 +42,9 @@ parse_qsl_test_cases = [ (b"a=1;a=2", [(b'a', b'1'), (b'a', b'2')]), ] +# Each parse_qs testcase is a two-tuple that contains +# a string with the query and a dictionary with the expected result. + parse_qs_test_cases = [ ("", {}), ("&", {}), @@ -290,7 +293,6 @@ class UrlParseTestCase(unittest.TestCase): def test_RFC2396(self): # cases from RFC 2396 - self.checkJoin(RFC2396_BASE, 'g:h', 'g:h') self.checkJoin(RFC2396_BASE, 'g', 'http://a/b/c/g') self.checkJoin(RFC2396_BASE, './g', 'http://a/b/c/g') @@ -333,9 +335,7 @@ class UrlParseTestCase(unittest.TestCase): # self.checkJoin(RFC2396_BASE, '/./g', 'http://a/./g') # self.checkJoin(RFC2396_BASE, '/../g', 'http://a/../g') - def test_RFC3986(self): - # Test cases from RFC3986 self.checkJoin(RFC3986_BASE, '?y','http://a/b/c/d;p?y') self.checkJoin(RFC3986_BASE, ';x', 'http://a/b/c/;x') self.checkJoin(RFC3986_BASE, 'g:h','g:h') @@ -363,7 +363,7 @@ class UrlParseTestCase(unittest.TestCase): self.checkJoin(RFC3986_BASE, '../../g','http://a/g') self.checkJoin(RFC3986_BASE, '../../../g', 'http://a/g') - #Abnormal Examples + # Abnormal Examples # The 'abnormal scenarios' are incompatible with RFC2986 parsing # Tests are here for reference. diff --git a/Lib/urllib/parse.py b/Lib/urllib/parse.py index f3a309aacc2..5d331596aec 100644 --- a/Lib/urllib/parse.py +++ b/Lib/urllib/parse.py @@ -612,6 +612,7 @@ def unquote(string, encoding='utf-8', errors='replace'): append(bits[i + 1]) return ''.join(res) + def parse_qs(qs, keep_blank_values=False, strict_parsing=False, encoding='utf-8', errors='replace'): """Parse a query given as a string argument. @@ -633,6 +634,8 @@ def parse_qs(qs, keep_blank_values=False, strict_parsing=False, encoding and errors: specify how to decode percent-encoded sequences into Unicode characters, as accepted by the bytes.decode() method. + + Returns a dictionary. """ parsed_result = {} pairs = parse_qsl(qs, keep_blank_values, strict_parsing, @@ -644,28 +647,29 @@ def parse_qs(qs, keep_blank_values=False, strict_parsing=False, parsed_result[name] = [value] return parsed_result + def parse_qsl(qs, keep_blank_values=False, strict_parsing=False, encoding='utf-8', errors='replace'): """Parse a query given as a string argument. - Arguments: + Arguments: - qs: percent-encoded query string to be parsed + qs: percent-encoded query string to be parsed - keep_blank_values: flag indicating whether blank values in - percent-encoded queries should be treated as blank strings. A - true value indicates that blanks should be retained as blank - strings. The default false value indicates that blank values - are to be ignored and treated as if they were not included. + keep_blank_values: flag indicating whether blank values in + percent-encoded queries should be treated as blank strings. + A true value indicates that blanks should be retained as blank + strings. The default false value indicates that blank values + are to be ignored and treated as if they were not included. - strict_parsing: flag indicating what to do with parsing errors. If - false (the default), errors are silently ignored. If true, - errors raise a ValueError exception. + strict_parsing: flag indicating what to do with parsing errors. If + false (the default), errors are silently ignored. If true, + errors raise a ValueError exception. - encoding and errors: specify how to decode percent-encoded sequences - into Unicode characters, as accepted by the bytes.decode() method. + encoding and errors: specify how to decode percent-encoded sequences + into Unicode characters, as accepted by the bytes.decode() method. - Returns a list, as G-d intended. + Returns a list, as G-d intended. """ qs, _coerce_result = _coerce_args(qs) pairs = [s2 for s1 in qs.split('&') for s2 in s1.split(';')]