bpo-38863: Improve is_cgi() in http.server (GH-17312)

is_cgi() function of http.server library does not currently handle a
cgi script if one of the cgi_directories is located at the
sub-directory of given path. Since is_cgi() in CGIHTTPRequestHandler
class separates given path into (dir, rest) based on the first seen
'/', multi-level directories like /sub/dir/cgi-bin/hello.py is divided
into head=/sub, rest=dir/cgi-bin/hello.py then check whether '/sub'
exists in cgi_directories = [..., '/sub/dir/cgi-bin'].
This patch makes the is_cgi() keep expanding dir part to the next '/'
then checking if that expanded path exists in the cgi_directories.

Signed-off-by: Siwon Kang <kkangshawn@gmail.com>





https://bugs.python.org/issue38863

3 files changed, 30 insertions, 2 deletions

diff --git a/Lib/http/server.py b/Lib/http/server.py
index 005dd82..47a4fcf 100644
--- a/Lib/http/server.py
+++ b/Lib/http/server.py
@@ -1014,8 +1014,10 @@ class CGIHTTPRequestHandler(SimpleHTTPRequestHandler):
         """
         collapsed_path = _url_collapse_path(self.path)
         dir_sep = collapsed_path.find('/', 1)
-        head, tail = collapsed_path[:dir_sep], collapsed_path[dir_sep+1:]
-        if head in self.cgi_directories:
+        while dir_sep > 0 and not collapsed_path[:dir_sep] in self.cgi_directories:
+            dir_sep = collapsed_path.find('/', dir_sep+1)
+        if dir_sep > 0:
+            head, tail = collapsed_path[:dir_sep], collapsed_path[dir_sep+1:]
             self.cgi_info = head, tail
             return True
         return False
diff --git a/Lib/test/test_httpservers.py b/Lib/test/test_httpservers.py
index 1c980a2..26da71e 100644
--- a/Lib/test/test_httpservers.py
+++ b/Lib/test/test_httpservers.py
@@ -601,13 +601,20 @@ class CGIHTTPServerTestCase(BaseTestCase):
         self.parent_dir = tempfile.mkdtemp()
         self.cgi_dir = os.path.join(self.parent_dir, 'cgi-bin')
         self.cgi_child_dir = os.path.join(self.cgi_dir, 'child-dir')
+        self.sub_dir_1 = os.path.join(self.parent_dir, 'sub')
+        self.sub_dir_2 = os.path.join(self.sub_dir_1, 'dir')
+        self.cgi_dir_in_sub_dir = os.path.join(self.sub_dir_2, 'cgi-bin')
         os.mkdir(self.cgi_dir)
         os.mkdir(self.cgi_child_dir)
+        os.mkdir(self.sub_dir_1)
+        os.mkdir(self.sub_dir_2)
+        os.mkdir(self.cgi_dir_in_sub_dir)
         self.nocgi_path = None
         self.file1_path = None
         self.file2_path = None
         self.file3_path = None
         self.file4_path = None
+        self.file5_path = None
 
         # The shebang line should be pure ASCII: use symlink if possible.
         # See issue #7668.
@@ -652,6 +659,11 @@ class CGIHTTPServerTestCase(BaseTestCase):
             file4.write(cgi_file4 % (self.pythonexe, 'QUERY_STRING'))
         os.chmod(self.file4_path, 0o777)
 
+        self.file5_path = os.path.join(self.cgi_dir_in_sub_dir, 'file5.py')
+        with open(self.file5_path, 'w', encoding='utf-8') as file5:
+            file5.write(cgi_file1 % self.pythonexe)
+        os.chmod(self.file5_path, 0o777)
+
         os.chdir(self.parent_dir)
 
     def tearDown(self):
@@ -669,8 +681,13 @@ class CGIHTTPServerTestCase(BaseTestCase):
                 os.remove(self.file3_path)
             if self.file4_path:
                 os.remove(self.file4_path)
+            if self.file5_path:
+                os.remove(self.file5_path)
             os.rmdir(self.cgi_child_dir)
             os.rmdir(self.cgi_dir)
+            os.rmdir(self.cgi_dir_in_sub_dir)
+            os.rmdir(self.sub_dir_2)
+            os.rmdir(self.sub_dir_1)
             os.rmdir(self.parent_dir)
         finally:
             BaseTestCase.tearDown(self)
@@ -789,6 +806,13 @@ class CGIHTTPServerTestCase(BaseTestCase):
              'text/html', HTTPStatus.OK),
             (res.read(), res.getheader('Content-type'), res.status))
 
+    def test_cgi_path_in_sub_directories(self):
+        CGIHTTPRequestHandler.cgi_directories.append('/sub/dir/cgi-bin')
+        res = self.request('/sub/dir/cgi-bin/file5.py')
+        self.assertEqual(
+            (b'Hello World' + self.linesep, 'text/html', HTTPStatus.OK),
+            (res.read(), res.getheader('Content-type'), res.status))
+
 
 class SocketlessRequestHandler(SimpleHTTPRequestHandler):
     def __init__(self, directory=None):
diff --git a/Misc/NEWS.d/next/Library/2019-11-21-16-30-00.bpo-38863.RkdTjf.rst b/Misc/NEWS.d/next/Library/2019-11-21-16-30-00.bpo-38863.RkdTjf.rst
new file mode 100644
index 0000000..6b621ee
--- /dev/null
+++ b/Misc/NEWS.d/next/Library/2019-11-21-16-30-00.bpo-38863.RkdTjf.rst
@@ -0,0 +1,2 @@
+Improve :func:`is_cgi` function in :mod:`http.server`, which enables processing
+the case that cgi directory is a child of another directory other than root.