Issue #25232: Fix CGIRequestHandler's splitting of URL query

Patch from Xiang Zhang.

Lib/http/server.py

@@ -1032,11 +1032,7 @@ class CGIHTTPRequestHandler(SimpleHTTPRequestHandler):
                 break
 
         # find an explicit query string, if present.
-        i = rest.rfind('?')
-        if i >= 0:
-            rest, query = rest[:i], rest[i+1:]
-        else:
-            query = ''
+        rest, _, query = rest.partition('?')
 
         # dissect the part after the directory name into a script name &
         # a possible additional path, to be stored in PATH_INFO.

Lib/test/test_httpservers.py

@@ -366,6 +366,16 @@ print("%%s, %%s, %%s" %% (form.getfirst("spam"), form.getfirst("eggs"),
                           form.getfirst("bacon")))
 """
 
+cgi_file4 = """\
+#!%s
+import os
+
+print("Content-type: text/html")
+print()
+
+print(os.environ["%s"])
+"""
+
 
 @unittest.skipIf(hasattr(os, 'geteuid') and os.geteuid() == 0,
         "This test can't be run reliably as root (issue #13308).")
@@ -387,6 +397,7 @@ class CGIHTTPServerTestCase(BaseTestCase):
         self.file1_path = None
         self.file2_path = None
         self.file3_path = None
+        self.file4_path = None
 
         # The shebang line should be pure ASCII: use symlink if possible.
         # See issue #7668.
@@ -425,6 +436,11 @@ class CGIHTTPServerTestCase(BaseTestCase):
             file3.write(cgi_file1 % self.pythonexe)
         os.chmod(self.file3_path, 0o777)
 
+        self.file4_path = os.path.join(self.cgi_dir, 'file4.py')
+        with open(self.file4_path, 'w', encoding='utf-8') as file4:
+            file4.write(cgi_file4 % (self.pythonexe, 'QUERY_STRING'))
+        os.chmod(self.file4_path, 0o777)
+
         os.chdir(self.parent_dir)
 
     def tearDown(self):
@@ -440,6 +456,8 @@ class CGIHTTPServerTestCase(BaseTestCase):
                 os.remove(self.file2_path)
             if self.file3_path:
                 os.remove(self.file3_path)
+            if self.file4_path:
+                os.remove(self.file4_path)
             os.rmdir(self.cgi_child_dir)
             os.rmdir(self.cgi_dir)
             os.rmdir(self.parent_dir)
@@ -541,6 +559,12 @@ class CGIHTTPServerTestCase(BaseTestCase):
         self.assertEqual((b'Hello World' + self.linesep, 'text/html', 200),
                 (res.read(), res.getheader('Content-type'), res.status))
 
+    def test_query_with_multiple_question_mark(self):
+        res = self.request('/cgi-bin/file4.py?a=b?c=d')
+        self.assertEqual(
+            (b'a=b?c=d' + self.linesep, 'text/html', 200),
+            (res.read(), res.getheader('Content-type'), res.status))
+
 
 class SocketlessRequestHandler(SimpleHTTPRequestHandler):
     def __init__(self):

Misc/ACKS

@@ -1531,6 +1531,7 @@ Thomas Wouters
 Daniel Wozniak
 Heiko Wundram
 Doug Wyatt
+Xiang Zhang
 Robert Xiao
 Florent Xicluna
 Hirokazu Yamamoto

Misc/NEWS

@@ -90,6 +90,9 @@ Core and Builtins
 Library
 -------
 
+- Issue #25232: Fix CGIRequestHandler to split the query from the URL at the
+  first question mark (?) rather than the last. Patch from Xiang Zhang.
+
 - Issue #22958: Constructor and update method of weakref.WeakValueDictionary
   now accept the self and the dict keyword arguments.