Christian Krakau-Louis
132 lines
5.0 KiB
Python
132 lines
5.0 KiB
Python
import io
|
|
import zipfile
|
|
|
|
import pytest
|
|
|
|
from app.services.dmarc_parser import DMARCParser
|
|
from app.tests.test_data import SAMPLE_XML, SAMPLE_XML_WITH_NAMESPACE
|
|
|
|
|
|
class TestDMARCParser:
|
|
"""Tests for the DMARC XML parser."""
|
|
|
|
def test_parse_xml_report(self):
|
|
"""Test parsing a plain XML DMARC report."""
|
|
xml_bytes = SAMPLE_XML.encode("utf-8")
|
|
result = DMARCParser.parse_file(xml_bytes, "report.xml")
|
|
|
|
# Report metadata (flat keys from _parse_xml)
|
|
assert result["report_id"] == "123456789"
|
|
assert result["org_name"] == "google.com"
|
|
assert result["email"] == "noreply-dmarc-support@google.com"
|
|
assert result["begin_timestamp"] == 1597449600
|
|
assert result["end_timestamp"] == 1597535999
|
|
|
|
# Policy published
|
|
assert result["domain"] == "example.com"
|
|
assert result["policy"]["p"] == "none"
|
|
|
|
# Records
|
|
assert len(result["records"]) == 1
|
|
record = result["records"][0]
|
|
assert record["source_ip"] == "203.0.113.1"
|
|
assert record["count"] == 2
|
|
assert record["disposition"] == "none"
|
|
assert record["dkim_result"] == "pass"
|
|
assert record["spf_result"] == "fail"
|
|
assert record["header_from"] == "example.com"
|
|
|
|
# Summary
|
|
assert result["summary"]["total_count"] == 2
|
|
assert result["summary"]["passed_count"] == 2 # dkim passed
|
|
assert result["summary"]["failed_count"] == 0
|
|
|
|
def test_parse_zip_report(self):
|
|
"""Test parsing a DMARC report inside a ZIP archive."""
|
|
xml_bytes = SAMPLE_XML.encode("utf-8")
|
|
|
|
zip_buffer = io.BytesIO()
|
|
with zipfile.ZipFile(zip_buffer, "w") as zf:
|
|
zf.writestr("report.xml", xml_bytes)
|
|
zip_content = zip_buffer.getvalue()
|
|
|
|
result = DMARCParser.parse_file(zip_content, "report.zip")
|
|
|
|
assert result["report_id"] == "123456789"
|
|
assert result["domain"] == "example.com"
|
|
assert len(result["records"]) == 1
|
|
|
|
def test_file_too_large(self):
|
|
"""Test that files exceeding the size limit are rejected."""
|
|
large_content = b"x" * (11 * 1024 * 1024) # 11 MB
|
|
with pytest.raises(ValueError, match="too large"):
|
|
DMARCParser.parse_file(large_content, "report.xml")
|
|
|
|
def test_invalid_xml(self):
|
|
"""Test that invalid XML raises a ValueError."""
|
|
with pytest.raises(ValueError, match="Error parsing DMARC XML"):
|
|
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"):
|
|
DMARCParser.parse_file(b"some content", "report.pdf")
|
|
|
|
def test_bad_zip_file_returns_no_xml_content(self):
|
|
"""A corrupt ZIP should be handled as no extractable XML content."""
|
|
with pytest.raises(ValueError, match="Could not extract XML"):
|
|
DMARCParser.parse_file(b"not a zip file", "report.zip")
|
|
|
|
def test_bad_gzip_file_returns_no_xml_content(self):
|
|
"""A corrupt GZIP should be handled as no extractable XML content."""
|
|
with pytest.raises(ValueError, match="Could not extract XML"):
|
|
DMARCParser.parse_file(b"not a gzip file", "report.gz")
|
|
|
|
def test_parse_xml_without_report_metadata(self):
|
|
"""Missing report_metadata should not crash parsing otherwise valid XML."""
|
|
xml = b"""
|
|
<feedback>
|
|
<policy_published>
|
|
<domain>example.com</domain>
|
|
<p>none</p>
|
|
</policy_published>
|
|
</feedback>
|
|
"""
|
|
|
|
result = DMARCParser.parse_file(xml, "report.xml")
|
|
|
|
assert result["domain"] == "example.com"
|
|
assert result["records"] == []
|
|
assert result["summary"]["total_count"] == 0
|