#4431 - Introduce sitescripts.reports.web.resolveReport handler

sitescripts/reports/web/resolveReport.py

Index: sitescripts/reports/web/resolveReport.py
===================================================================
new file mode 100644
--- /dev/null
+++ b/sitescripts/reports/web/resolveReport.py
@@ -0,0 +1,69 @@
+# This file is part of the Adblock Plus web scripts,
+# Copyright (C) 2006-present eyeo GmbH
+#
+# Adblock Plus is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License version 3 as
+# published by the Free Software Foundation.
+#
+# Adblock Plus 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 General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with Adblock Plus.  If not, see <http://www.gnu.org/licenses/>.
+
+import base64
+
+from cryptography.hazmat.primitives.ciphers import aead
+from cryptography.exceptions import InvalidTag
+
+from sitescripts.utils import get_config
+from sitescripts.web import url_handler
+
+CONF_SECTION = 'reports_anonymization'
+CONF_KEY_KEY = 'encryption_key'
+CONF_URL_KEY = 'redirect_url'
+
+
+def _decrypt_report_id(guid):
+    """Decrypt and verify the report id.
+
+    Returns
+    -------
+    str or None
+        Decrypted id if successfully decrypted, None otherwise.
+
+    """
+    config = get_config()
+    key = base64.b64decode(config.get(CONF_SECTION, CONF_KEY_KEY))
+
+    # https://cryptography.io/en/latest/hazmat/primitives/aead/
+    aes_gcm = aead.AESGCM(key)
+
+    try:
+        encoded_nonce, encoded_data = guid.split(',', 1)
+        nonce = base64.b64decode(encoded_nonce)
+        encypted_data = base64.b64decode(encoded_data)
+        return aes_gcm.decrypt(nonce, encypted_data, None)
+    except (ValueError, TypeError, InvalidTag):

[mathias, 2017/10/24 14:53:44]

Exceptions should get logged (they'll appear in our Nginx error log if written
to sys.stderr).

[Vasily Kuznetsov, 2017/10/24 15:36:58]

Done.

+        return None
+
+
+@url_handler('/resolveReport')
+def resolve_report(environ, start_response):
+    """Decrypt report guid and redirect to report URL."""
+    config = get_config()
+    redirect_url_template = config.get(CONF_SECTION, CONF_URL_KEY)
+
+    guid = environ.get('QUERY_STRING', '')
+    report_id = _decrypt_report_id(guid)
+
+    if report_id is None:
+        code, message, headers = 404, 'Not Found', []

[mathias, 2017/10/24 14:53:45]

Please use httplib.NOT_FOUND. even if (or, for educational purpose, especially
because) every reader of the code should know that magic number.

[Vasily Kuznetsov, 2017/10/24 15:36:57]

Done.

+    else:
+        location = redirect_url_template.format(report_id=report_id)
+        code, message, headers = 302, 'Found', [('Location', location)]

[mathias, 2017/10/24 14:53:44]

Same here, httplib.FOUND should do the trick.

[Vasily Kuznetsov, 2017/10/24 15:36:58]

Done.

+
+    start_response('{} {}'.format(code, message), headers)

[mathias, 2017/10/24 14:53:44]

Why don't you get the message via lookup based on the code? I.e. `message =
httplib.responses[code]` or something similar. Why the hazzle?

[Vasily Kuznetsov, 2017/10/24 15:36:57]

Done.

+    return [message]