fix: handle XML namespaces in DMARCParser for web.de/gmx.net compatibility

Agent-Logs-Url: https://github.com/christianlouis/dmarq/sessions/56611674-6132-435f-ab36-728464bb9157

Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com>

backend/app/services/dmarc_parser.py

@@ -128,6 +128,14 @@ class DMARCParser:
 
         return None
 
+    @staticmethod
+    def _strip_namespace(el) -> None:
+        """Recursively remove XML namespace prefixes from element tags in-place."""
+        if "}" in el.tag:
+            el.tag = el.tag.split("}", 1)[1]
+        for child in el:
+            DMARCParser._strip_namespace(child)
+
     @staticmethod
     def _parse_metadata(root) -> dict:
         """Parse the report_metadata section of a DMARC XML report."""
@@ -216,6 +224,7 @@ class DMARCParser:
         """
         try:
             root = ET.fromstring(xml_content)
+            DMARCParser._strip_namespace(root)
 
             report = DMARCParser._parse_metadata(root)
 

backend/app/tests/test_data.py

@@ -47,3 +47,51 @@ SAMPLE_XML = """\
     </record>
 </feedback>
 """
+
+SAMPLE_XML_WITH_NAMESPACE = """\
+<?xml version="1.0" encoding="UTF-8" ?>
+<feedback xmlns="urn:ietf:params:xml:ns:dmarc-2.0">
+    <report_metadata>
+        <org_name>web.de</org_name>
+        <email>dmarc@web.de</email>
+        <report_id>987654321</report_id>
+        <date_range>
+            <begin>1597449600</begin>
+            <end>1597535999</end>
+        </date_range>
+    </report_metadata>
+    <policy_published>
+        <domain>example.com</domain>
+        <adkim>r</adkim>
+        <aspf>r</aspf>
+        <p>reject</p>
+        <sp>reject</sp>
+        <pct>100</pct>
+    </policy_published>
+    <record>
+        <row>
+            <source_ip>198.51.100.5</source_ip>
+            <count>3</count>
+            <policy_evaluated>
+                <disposition>reject</disposition>
+                <dkim>pass</dkim>
+                <spf>pass</spf>
+            </policy_evaluated>
+        </row>
+        <identifiers>
+            <header_from>example.com</header_from>
+        </identifiers>
+        <auth_results>
+            <dkim>
+                <domain>example.com</domain>
+                <result>pass</result>
+                <selector>s1</selector>
+            </dkim>
+            <spf>
+                <domain>example.com</domain>
+                <result>pass</result>
+            </spf>
+        </auth_results>
+    </record>
+</feedback>
+"""

backend/app/tests/test_dmarc_parser.py

@@ -4,7 +4,7 @@ import zipfile
 import pytest
 
 from app.services.dmarc_parser import DMARCParser
-from app.tests.test_data import SAMPLE_XML
+from app.tests.test_data import SAMPLE_XML, SAMPLE_XML_WITH_NAMESPACE
 
 
 class TestDMARCParser:
@@ -67,6 +67,37 @@ class TestDMARCParser:
         with pytest.raises(ValueError):
             DMARCParser.parse_file(b"not xml at all", "report.xml")
 
+    def test_parse_xml_report_with_namespace(self):
+        """Test parsing a DMARC XML report that uses an XML namespace (e.g. web.de/gmx.net)."""
+        xml_bytes = SAMPLE_XML_WITH_NAMESPACE.encode("utf-8")
+        result = DMARCParser.parse_file(xml_bytes, "report.xml")
+
+        # Metadata
+        assert result["report_id"] == "987654321"
+        assert result["org_name"] == "web.de"
+        assert result["email"] == "dmarc@web.de"
+        assert result["begin_timestamp"] == 1597449600
+        assert result["end_timestamp"] == 1597535999
+
+        # Policy published
+        assert result["domain"] == "example.com"
+        assert result["policy"]["p"] == "reject"
+
+        # Records
+        assert len(result["records"]) == 1
+        record = result["records"][0]
+        assert record["source_ip"] == "198.51.100.5"
+        assert record["count"] == 3
+        assert record["disposition"] == "reject"
+        assert record["dkim_result"] == "pass"
+        assert record["spf_result"] == "pass"
+        assert record["header_from"] == "example.com"
+
+        # Summary
+        assert result["summary"]["total_count"] == 3
+        assert result["summary"]["passed_count"] == 3
+        assert result["summary"]["failed_count"] == 0
+
     def test_unsupported_extension_returns_none(self):
         """Test that an unsupported file extension raises ValueError."""
         with pytest.raises(ValueError, match="Could not extract XML"):