diff options
Diffstat (limited to 'Lib')
| -rw-r--r-- | Lib/test/test_urlparse.py | 32 | ||||
| -rw-r--r-- | Lib/urllib/parse.py | 64 |
2 files changed, 32 insertions, 64 deletions
diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py index 17cdf9e..b0c46f1 100644 --- a/Lib/test/test_urlparse.py +++ b/Lib/test/test_urlparse.py @@ -7,6 +7,7 @@ import urllib.parse RFC1808_BASE = "http://a/b/c/d;p?q#f" 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 a two-tuple that contains # a string with the query and a dictionary with the expected result. @@ -292,6 +293,37 @@ class UrlParseTestCase(unittest.TestCase): #self.checkJoin(RFC3986_BASE, 'http:g','http:g') # strict parser self.checkJoin(RFC3986_BASE, 'http:g','http://a/b/c/g') #relaxed parser + def test_urljoins(self): + self.checkJoin(SIMPLE_BASE, 'g:h','g:h') + self.checkJoin(SIMPLE_BASE, 'http:g','http://a/b/c/g') + self.checkJoin(SIMPLE_BASE, 'http:','http://a/b/c/d') + self.checkJoin(SIMPLE_BASE, 'g','http://a/b/c/g') + self.checkJoin(SIMPLE_BASE, './g','http://a/b/c/g') + self.checkJoin(SIMPLE_BASE, 'g/','http://a/b/c/g/') + self.checkJoin(SIMPLE_BASE, '/g','http://a/g') + self.checkJoin(SIMPLE_BASE, '//g','http://g') + self.checkJoin(SIMPLE_BASE, '?y','http://a/b/c/d?y') + self.checkJoin(SIMPLE_BASE, 'g?y','http://a/b/c/g?y') + self.checkJoin(SIMPLE_BASE, 'g?y/./x','http://a/b/c/g?y/./x') + self.checkJoin(SIMPLE_BASE, '.','http://a/b/c/') + self.checkJoin(SIMPLE_BASE, './','http://a/b/c/') + self.checkJoin(SIMPLE_BASE, '..','http://a/b/') + self.checkJoin(SIMPLE_BASE, '../','http://a/b/') + self.checkJoin(SIMPLE_BASE, '../g','http://a/b/g') + self.checkJoin(SIMPLE_BASE, '../..','http://a/') + self.checkJoin(SIMPLE_BASE, '../../g','http://a/g') + self.checkJoin(SIMPLE_BASE, '../../../g','http://a/../g') + self.checkJoin(SIMPLE_BASE, './../g','http://a/b/g') + self.checkJoin(SIMPLE_BASE, './g/.','http://a/b/c/g/') + self.checkJoin(SIMPLE_BASE, '/./g','http://a/./g') + self.checkJoin(SIMPLE_BASE, 'g/./h','http://a/b/c/g/h') + self.checkJoin(SIMPLE_BASE, 'g/../h','http://a/b/c/h') + self.checkJoin(SIMPLE_BASE, 'http:g','http://a/b/c/g') + self.checkJoin(SIMPLE_BASE, 'http:','http://a/b/c/d') + self.checkJoin(SIMPLE_BASE, 'http:?y','http://a/b/c/d?y') + self.checkJoin(SIMPLE_BASE, 'http:g?y','http://a/b/c/g?y') + self.checkJoin(SIMPLE_BASE, 'http:g?y/./x','http://a/b/c/g?y/./x') + def test_urldefrag(self): for url, defrag, frag in [ ('http://python.org#frag', 'http://python.org', 'frag'), diff --git a/Lib/urllib/parse.py b/Lib/urllib/parse.py index c95610e..1f54ac6 100644 --- a/Lib/urllib/parse.py +++ b/Lib/urllib/parse.py @@ -774,67 +774,3 @@ def splitvalue(attr): match = _valueprog.match(attr) if match: return match.group(1, 2) return attr, None - -test_input = """ - http://a/b/c/d - - g:h = <URL:g:h> - http:g = <URL:http://a/b/c/g> - http: = <URL:http://a/b/c/d> - g = <URL:http://a/b/c/g> - ./g = <URL:http://a/b/c/g> - g/ = <URL:http://a/b/c/g/> - /g = <URL:http://a/g> - //g = <URL:http://g> - ?y = <URL:http://a/b/c/d?y> - g?y = <URL:http://a/b/c/g?y> - g?y/./x = <URL:http://a/b/c/g?y/./x> - . = <URL:http://a/b/c/> - ./ = <URL:http://a/b/c/> - .. = <URL:http://a/b/> - ../ = <URL:http://a/b/> - ../g = <URL:http://a/b/g> - ../.. = <URL:http://a/> - ../../g = <URL:http://a/g> - ../../../g = <URL:http://a/../g> - ./../g = <URL:http://a/b/g> - ./g/. = <URL:http://a/b/c/g/> - /./g = <URL:http://a/./g> - g/./h = <URL:http://a/b/c/g/h> - g/../h = <URL:http://a/b/c/h> - http:g = <URL:http://a/b/c/g> - http: = <URL:http://a/b/c/d> - http:?y = <URL:http://a/b/c/d?y> - http:g?y = <URL:http://a/b/c/g?y> - http:g?y/./x = <URL:http://a/b/c/g?y/./x> -""" - -def test(): - base = '' - if sys.argv[1:]: - fn = sys.argv[1] - if fn == '-': - fp = sys.stdin - else: - fp = open(fn) - else: - from io import StringIO - fp = StringIO(test_input) - for line in fp: - words = line.split() - if not words: - continue - url = words[0] - parts = urlparse(url) - print('%-10s : %s' % (url, parts)) - abs = urljoin(base, url) - if not base: - base = abs - wrapped = '<URL:%s>' % abs - print('%-10s = %s' % (url, wrapped)) - if len(words) == 3 and words[1] == '=': - if wrapped != words[2]: - print('EXPECTED', words[2], '!!!!!!!!!!') - -if __name__ == '__main__': - test() |