utils: add origin module (#53879)

passerelle/utils/origin.py

@@ -0,0 +1,47 @@
+# passerelle - uniform access to multiple data sources and services
+# Copyright (C) 2021 Entr'ouvert
+#
+# This program is free software: you can redistribute it and/or modify it
+# under the terms of the GNU Affero General Public License as published
+# by the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+import urllib.parse
+
+
+def get_url_origin(url):
+    '''Build origin of an URL'''
+    parsed = urllib.parse.urlparse(url)
+    if ':' in parsed.netloc:
+        host, port = parsed.netloc.split(':', 1)
+        if parsed.scheme == 'http' and port == 80:
+            port = None
+        if parsed.scheme == 'https' and port == 443:
+            port = None
+    else:
+        host, port = parsed.netloc, None
+    result = '%s://%s' % (parsed.scheme, host)
+    if port:
+        result += ':%s' % port
+    return result
+
+
+def is_same_origin(url1, url2):
+    if 'null' in [url1, url2] or not url1 or not url2:
+        return False
+
+    try:
+        origin1 = get_url_origin(url1)
+        origin2 = get_url_origin(url2)
+    except (ValueError, TypeError):
+        return False
+
+    return origin1 == origin2