#14072: Fix parsing of tel URIs in urlparse by making the check for ports stricter.
diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py
index 5784381..73150cf 100755
--- a/Lib/test/test_urlparse.py
+++ b/Lib/test/test_urlparse.py
@@ -806,6 +806,13 @@
encoding='utf-8')
self.assertRaises(TypeError, urllib.parse.quote, b'foo', errors='strict')
+ def test_issue14072(self):
+ p1 = urllib.parse.urlsplit('tel:+31-641044153')
+ self.assertEqual(p1.scheme, 'tel')
+ self.assertEqual(p1.path, '+31-641044153')
+ p2 = urllib.parse.urlsplit('tel:+31641044153')
+ self.assertEqual(p2.scheme, 'tel')
+ self.assertEqual(p2.path, '+31641044153')
def test_main():
support.run_unittest(UrlParseTestCase)
diff --git a/Lib/urllib/parse.py b/Lib/urllib/parse.py
index 47b7962..92170ad 100644
--- a/Lib/urllib/parse.py
+++ b/Lib/urllib/parse.py
@@ -338,12 +338,12 @@
if c not in scheme_chars:
break
else:
- try:
- # make sure "url" is not actually a port number (in which case
- # "scheme" is really part of the path
- _testportnum = int(url[i+1:])
- except ValueError:
- scheme, url = url[:i].lower(), url[i+1:]
+ # make sure "url" is not actually a port number (in which case
+ # "scheme" is really part of the path)
+ rest = url[i+1:]
+ if not rest or any(c not in '0123456789' for c in rest):
+ # not a port number
+ scheme, url = url[:i].lower(), rest
if url[:2] == '//':
netloc, url = _splitnetloc(url, 2)
diff --git a/Misc/NEWS b/Misc/NEWS
index 4cbea24..ead1bbf 100644
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -66,6 +66,9 @@
- Issue #14721: Send the correct 'Content-length: 0' header when the body is an
empty string ''. Initial Patch contributed by Arve Knudsen.
+- Issue #14072: Fix parsing of 'tel' URIs in urlparse by making the check for
+ ports stricter.
+
- Issue #9374: Generic parsing of query and fragment portions of url for any
scheme. Supported both by RFC3986 and RFC2396.