From: Senthil Kumaran <senthil@uthcode.com>
Date: Wed, 29 May 2013 12:54:31 +0000 (-0700)
Subject: #17403: urllib.parse.robotparser normalizes the urls before adding to ruleline.
X-Git-Tag: v3.4.0a1~608^2
X-Git-Url: http://git.ipfire.org/gitweb.cgi?a=commitdiff_plain;h=c70a6ae49bd162af06130e48a45579d445e058a8;p=thirdparty%2FPython%2Fcpython.git

#17403: urllib.parse.robotparser normalizes the urls before adding to ruleline.
This helps in handling certain types invalid urls in a conservative manner.
---

diff --git a/Lib/test/test_robotparser.py b/Lib/test/test_robotparser.py
index 8c09e7452c56..d1dfd9eeec02 100644
--- a/Lib/test/test_robotparser.py
+++ b/Lib/test/test_robotparser.py
@@ -234,6 +234,18 @@ bad = ['/some/path']
 
 RobotTest(15, doc, good, bad)
 
+# 16. Empty query (issue #17403). Normalizing the url first.
+doc = """
+User-agent: *
+Allow: /some/path?
+Disallow: /another/path?
+"""
+
+good = ['/some/path?']
+bad = ['/another/path?']
+
+RobotTest(16, doc, good, bad)
+
 
 class NetworkTestCase(unittest.TestCase):
 
diff --git a/Lib/urllib/robotparser.py b/Lib/urllib/robotparser.py
index 75be4af40918..978ba58d84a6 100644
--- a/Lib/urllib/robotparser.py
+++ b/Lib/urllib/robotparser.py
@@ -157,6 +157,7 @@ class RuleLine:
         if path == '' and not allowance:
             # an empty value means allow all
             allowance = True
+        path = urllib.parse.urlunparse(urllib.parse.urlparse(path))
         self.path = urllib.parse.quote(path)
         self.allowance = allowance
 
diff --git a/Misc/NEWS b/Misc/NEWS
index 828e240c5bef..be6fd578db26 100644
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -24,6 +24,10 @@ Core and Builtins
 Library
 -------
 
+- Issue #17403: urllib.parse.robotparser normalizes the urls before adding to
+  ruleline. This helps in handling certain types invalid urls in a conservative
+  manner.
+
 - Issue #18025: Fixed a segfault in io.BufferedIOBase.readinto() when raw
   stream's read() returns more bytes than requested.