Compare commits

..

1 Commits
9.5.3 ... 9.5.4

6 changed files with 202 additions and 13 deletions

View File

@@ -42,7 +42,7 @@ To skip DNS lookups during testing, set `GITHUB_ACTIONS=true`.
### Key modules
- `parsedmarc/__init__.py` — Core parsing logic. Main functions: `parse_report_file()`, `parse_report_email()`, `parse_aggregate_report_xml()`, `parse_forensic_report()`, `parse_smtp_tls_report_json()`, `get_dmarc_reports_from_mailbox()`, `watch_inbox()`
- `parsedmarc/cli.py` — CLI entry point (`_main`), config file parsing, output orchestration
- `parsedmarc/cli.py` — CLI entry point (`_main`), config file parsing (`_load_config` + `_parse_config`), output orchestration. Supports configuration via INI files, `PARSEDMARC_{SECTION}_{KEY}` environment variables, or both (env vars override file values).
- `parsedmarc/types.py` — TypedDict definitions for all report types (`AggregateReport`, `ForensicReport`, `SMTPTLSReport`, `ParsingResults`)
- `parsedmarc/utils.py` — IP/DNS/GeoIP enrichment, base64 decoding, compression handling
- `parsedmarc/mail/` — Polymorphic mail connections: `IMAPConnection`, `GmailConnection`, `MSGraphConnection`, `MaildirConnection`
@@ -52,6 +52,10 @@ To skip DNS lookups during testing, set `GITHUB_ACTIONS=true`.
`ReportType = Literal["aggregate", "forensic", "smtp_tls"]`. Exception hierarchy: `ParserError``InvalidDMARCReport``InvalidAggregateReport`/`InvalidForensicReport`, and `InvalidSMTPTLSReport`.
### Configuration
Config priority: CLI args > env vars > config file > defaults. Env var naming: `PARSEDMARC_{SECTION}_{KEY}` (e.g. `PARSEDMARC_IMAP_PASSWORD`). Section names with underscores use longest-prefix matching (`PARSEDMARC_SPLUNK_HEC_TOKEN``[splunk_hec] token`). Some INI keys have short aliases for env var friendliness (e.g. `[maildir] create` for `maildir_create`). File path values are expanded via `os.path.expanduser`/`os.path.expandvars`. Config can be loaded purely from env vars with no file (`PARSEDMARC_CONFIG_FILE` sets the file path).
### Caching
IP address info cached for 4 hours, seen aggregate report IDs cached for 1 hour (via `ExpiringDict`).
@@ -62,3 +66,6 @@ IP address info cached for 4 hours, seen aggregate report IDs cached for 1 hour
- TypedDict for structured data, type hints throughout
- Python ≥3.10 required
- Tests are in a single `tests.py` file using unittest; sample reports live in `samples/`
- File path config values must be wrapped with `_expand_path()` in `cli.py`
- Maildir UID checks are intentionally relaxed (warn, don't crash) for Docker compatibility
- Token file writes must create parent directories before opening for write

View File

@@ -1,5 +1,12 @@
# Changelog
## 9.5.4
### Fixed
- Maildir `fetch_messages` now respects the `reports_folder` argument. Previously it always read from the top-level Maildir, ignoring the configured reports folder. `fetch_message`, `delete_message`, and `move_message` now also operate on the correct active folder.
- Config key aliases for env var compatibility: `[maildir] create` and `path` are now accepted as aliases for `maildir_create` and `maildir_path`, and `[msgraph] url` for `graph_url`. This allows natural env var names like `PARSEDMARC_MAILDIR_CREATE` to work without the redundant `PARSEDMARC_MAILDIR_MAILDIR_CREATE`.
## 9.5.3
### Fixed

View File

@@ -581,6 +581,8 @@ def _parse_config(config: ConfigParser, opts):
if "graph_url" in graph_config:
opts.graph_url = graph_config["graph_url"]
elif "url" in graph_config:
opts.graph_url = graph_config["url"]
if "allow_unencrypted_storage" in graph_config:
opts.graph_allow_unencrypted_storage = bool(
@@ -884,10 +886,15 @@ def _parse_config(config: ConfigParser, opts):
if "maildir" in config.sections():
maildir_api_config = config["maildir"]
maildir_p = maildir_api_config.get("maildir_path")
maildir_p = maildir_api_config.get(
"maildir_path", maildir_api_config.get("path")
)
opts.maildir_path = _expand_path(maildir_p) if maildir_p else maildir_p
opts.maildir_create = bool(
maildir_api_config.getboolean("maildir_create", fallback=False)
maildir_api_config.getboolean(
"maildir_create",
fallback=maildir_api_config.getboolean("create", fallback=False),
)
)
if "log_analytics" in config.sections():

View File

@@ -1,3 +1,3 @@
__version__ = "9.5.3"
__version__ = "9.5.4"
USER_AGENT = f"parsedmarc/{__version__}"

View File

@@ -46,16 +46,27 @@ class MaildirConnection(MailboxConnection):
for subdir in ("cur", "new", "tmp"):
os.makedirs(os.path.join(maildir_path, subdir), exist_ok=True)
self._client = mailbox.Maildir(maildir_path, create=maildir_create)
self._active_folder: mailbox.Maildir = self._client
self._subfolder_client: Dict[str, mailbox.Maildir] = {}
def _get_folder(self, folder_name: str) -> mailbox.Maildir:
"""Return a cached subfolder handle, creating it if needed."""
if folder_name not in self._subfolder_client:
self._subfolder_client[folder_name] = self._client.add_folder(folder_name)
return self._subfolder_client[folder_name]
def create_folder(self, folder_name: str):
self._subfolder_client[folder_name] = self._client.add_folder(folder_name)
self._get_folder(folder_name)
def fetch_messages(self, reports_folder: str, **kwargs):
return self._client.keys()
if reports_folder and reports_folder != "INBOX":
self._active_folder = self._get_folder(reports_folder)
else:
self._active_folder = self._client
return self._active_folder.keys()
def fetch_message(self, message_id: str) -> str:
msg = self._client.get(message_id)
msg = self._active_folder.get(message_id)
if msg is not None:
msg = msg.as_string()
if msg is not None:
@@ -63,16 +74,15 @@ class MaildirConnection(MailboxConnection):
return ""
def delete_message(self, message_id: str):
self._client.remove(message_id)
self._active_folder.remove(message_id)
def move_message(self, message_id: str, folder_name: str):
message_data = self._client.get(message_id)
message_data = self._active_folder.get(message_id)
if message_data is None:
return
if folder_name not in self._subfolder_client:
self._subfolder_client[folder_name] = self._client.add_folder(folder_name)
self._subfolder_client[folder_name].add(message_data)
self._client.remove(message_id)
dest = self._get_folder(folder_name)
dest.add(message_data)
self._active_folder.remove(message_id)
def keepalive(self):
return

158
tests.py
View File

@@ -2566,6 +2566,164 @@ class TestMaildirConnection(unittest.TestCase):
self.assertEqual(len(conn._subfolder_client["archive"].keys()), 1)
class TestMaildirReportsFolder(unittest.TestCase):
"""Tests for Maildir reports_folder support in fetch_messages."""
def test_fetch_from_subfolder(self):
"""fetch_messages with a subfolder name reads from that subfolder."""
from parsedmarc.mail.maildir import MaildirConnection
with TemporaryDirectory() as d:
conn = MaildirConnection(d, maildir_create=True)
# Add message to a subfolder
subfolder = conn._client.add_folder("reports")
msg_key = subfolder.add("From: test@example.com\n\nSubfolder msg")
# Root should be empty
self.assertEqual(conn.fetch_messages("INBOX"), [])
# Subfolder should have the message
keys = conn.fetch_messages("reports")
self.assertIn(msg_key, keys)
def test_fetch_message_uses_active_folder(self):
"""fetch_message reads from the folder set by fetch_messages."""
from parsedmarc.mail.maildir import MaildirConnection
with TemporaryDirectory() as d:
conn = MaildirConnection(d, maildir_create=True)
subfolder = conn._client.add_folder("reports")
msg_key = subfolder.add("From: sub@example.com\n\nIn subfolder")
conn.fetch_messages("reports")
content = conn.fetch_message(msg_key)
self.assertIn("sub@example.com", content)
def test_delete_message_uses_active_folder(self):
"""delete_message removes from the folder set by fetch_messages."""
from parsedmarc.mail.maildir import MaildirConnection
with TemporaryDirectory() as d:
conn = MaildirConnection(d, maildir_create=True)
subfolder = conn._client.add_folder("reports")
msg_key = subfolder.add("From: del@example.com\n\nDelete me")
conn.fetch_messages("reports")
conn.delete_message(msg_key)
self.assertEqual(conn.fetch_messages("reports"), [])
def test_move_message_from_subfolder(self):
"""move_message works when active folder is a subfolder."""
from parsedmarc.mail.maildir import MaildirConnection
with TemporaryDirectory() as d:
conn = MaildirConnection(d, maildir_create=True)
subfolder = conn._client.add_folder("reports")
msg_key = subfolder.add("From: move@example.com\n\nMove me")
conn.fetch_messages("reports")
conn.move_message(msg_key, "archive")
# Source should be empty
self.assertEqual(conn.fetch_messages("reports"), [])
# Destination should have the message
archive_keys = conn.fetch_messages("archive")
self.assertEqual(len(archive_keys), 1)
def test_inbox_reads_root(self):
"""INBOX reads from the top-level Maildir."""
from parsedmarc.mail.maildir import MaildirConnection
with TemporaryDirectory() as d:
conn = MaildirConnection(d, maildir_create=True)
msg_key = conn._client.add("From: root@example.com\n\nRoot msg")
keys = conn.fetch_messages("INBOX")
self.assertIn(msg_key, keys)
def test_empty_folder_reads_root(self):
"""Empty string reports_folder reads from the top-level Maildir."""
from parsedmarc.mail.maildir import MaildirConnection
with TemporaryDirectory() as d:
conn = MaildirConnection(d, maildir_create=True)
msg_key = conn._client.add("From: root@example.com\n\nRoot msg")
keys = conn.fetch_messages("")
self.assertIn(msg_key, keys)
class TestConfigAliases(unittest.TestCase):
"""Tests for config key aliases (env var friendly short names)."""
def test_maildir_create_alias(self):
"""[maildir] create works as alias for maildir_create."""
from argparse import Namespace
from parsedmarc.cli import _load_config, _parse_config
env = {
"PARSEDMARC_MAILDIR_CREATE": "true",
"PARSEDMARC_MAILDIR_PATH": "/tmp/test",
}
with patch.dict(os.environ, env, clear=False):
config = _load_config(None)
opts = Namespace()
_parse_config(config, opts)
self.assertTrue(opts.maildir_create)
def test_maildir_path_alias(self):
"""[maildir] path works as alias for maildir_path."""
from argparse import Namespace
from parsedmarc.cli import _load_config, _parse_config
env = {"PARSEDMARC_MAILDIR_PATH": "/var/mail/dmarc"}
with patch.dict(os.environ, env, clear=False):
config = _load_config(None)
opts = Namespace()
_parse_config(config, opts)
self.assertEqual(opts.maildir_path, "/var/mail/dmarc")
def test_msgraph_url_alias(self):
"""[msgraph] url works as alias for graph_url."""
from parsedmarc.cli import _load_config, _parse_config
from argparse import Namespace
env = {
"PARSEDMARC_MSGRAPH_AUTH_METHOD": "ClientSecret",
"PARSEDMARC_MSGRAPH_CLIENT_ID": "test-id",
"PARSEDMARC_MSGRAPH_CLIENT_SECRET": "test-secret",
"PARSEDMARC_MSGRAPH_TENANT_ID": "test-tenant",
"PARSEDMARC_MSGRAPH_MAILBOX": "test@example.com",
"PARSEDMARC_MSGRAPH_URL": "https://custom.graph.example.com",
}
with patch.dict(os.environ, env, clear=False):
config = _load_config(None)
opts = Namespace()
_parse_config(config, opts)
self.assertEqual(opts.graph_url, "https://custom.graph.example.com")
def test_original_keys_still_work(self):
"""Original INI key names (maildir_create, maildir_path) still work."""
from argparse import Namespace
from parsedmarc.cli import _parse_config
config = ConfigParser(interpolation=None)
config.add_section("maildir")
config.set("maildir", "maildir_path", "/original/path")
config.set("maildir", "maildir_create", "true")
opts = Namespace()
_parse_config(config, opts)
self.assertEqual(opts.maildir_path, "/original/path")
self.assertTrue(opts.maildir_create)
class TestMaildirUidHandling(unittest.TestCase):
"""Tests for Maildir UID mismatch handling in Docker-like environments."""