set CAP signature check based on env variable (#831)

* set CAP signature check based on env variable

* use str2bool as suggested

docs/source/reference/running/data-pipeline-plugins.rst

@@ -119,7 +119,7 @@ A typical BUFR4 plugin workflow definition would be defined as follows:
 
 This plugin takes the incoming XML file, then validates it against the
 `CAP v1.2 schema <https://docs.oasis-open.org/emergency/cap/v1.2/CAP-v1.2-os.html>`_
-and verifies the digital signature before publishing.
+and optionally verifies the digital signature before publishing.
 
 The validation is performed using the `capvalidator <https://github.com/wmo-im/capvalidator>`_
 package.
@@ -135,6 +135,12 @@ A typical CAP message plugin workflow definition would be defined as follows:
             - ${WIS2BOX_STORAGE_INCOMING}
          file-pattern: '^.*\.xml$'
 
+By default the XML signature validation is set to ``False``. To enable the validation add the following environment variable to your ``wis2box.env`` file:
+
+.. code-block:: bash
+
+    CHECK_CAP_SIGNATURE=True
+
 ``wis2box.data.universal.UniversalData``
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 

wis2box-management/wis2box/data/cap_message.py

@@ -20,13 +20,16 @@
 ###############################################################################
 
 from datetime import datetime
+import os
 import logging
+
 from pathlib import Path
 from typing import Union
 
 from capvalidator import validate_cap_message, get_dates
 
 from wis2box.data.base import BaseAbstractData
+from wis2box.util import str2bool
 
 LOGGER = logging.getLogger(__name__)
 
@@ -74,8 +77,12 @@ def transform(self, input_data: Union[Path, bytes],
         # add relative filepath to _meta
         _meta['relative_filepath'] = self.get_local_filepath(_meta['data_date'])  # noqa
 
+        # check CAP signature based on ENV variable, default is False
+        check_cap_signature = str2bool(os.getenv('CHECK_CAP_SIGNATURE', False))
+
+        LOGGER.info(f'Checking CAP signature: {check_cap_signature}')
         # validate the CAP XML string content using the capvalidator package
-        result = validate_cap_message(input_bytes, strict=False)
+        result = validate_cap_message(input_bytes, strict=check_cap_signature)
         if not result.passed:
             LOGGER.error(
                 f'Invalid CAP XML, not publishing. Reason: {result.message}')

wis2box-management/wis2box/util.py

@@ -34,6 +34,26 @@
 LOGGER = logging.getLogger(__name__)
 
 
+def str2bool(value: Union[bool, str]) -> bool:
+    """
+    helper function to return Python boolean
+    type (source: https://stackoverflow.com/a/715468)
+
+    :param value: value to be evaluated
+
+    :returns: `bool` of whether the value is boolean-ish
+    """
+
+    value2 = False
+
+    if isinstance(value, bool):
+        value2 = value
+    else:
+        value2 = value.lower() in ('yes', 'true', 't', '1', 'on')
+
+    return value2
+
+
 def get_typed_value(value) -> Union[float, int, str]:
     """
     Derive true type from data value