Compare commits

..

21 Commits
9.4.0 ... 9.6.0

Author SHA1 Message Date
Sean Whalen
c350a73e95 Fix ruff formatting in utils.py
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-06 11:51:22 -04:00
Sean Whalen
d1e8d3b3d0 Auto-update DB-IP Country Lite database at startup
Download the latest DB-IP Country Lite mmdb from GitHub on startup and
SIGHUP, caching it locally, with fallback to a previously cached or
bundled copy. Skipped when the offline flag is set. Adds ip_db_url
config option (PARSEDMARC_GENERAL_IP_DB_URL) to override the download
URL. Bumps version to 9.6.0.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-06 11:50:06 -04:00
Sean Whalen
648fb93d6d Update DB-IP-country lite database 2026-04-06 11:14:47 -04:00
Sean Whalen
3d8dba6745 Fix colors in the OpenSearch Message disposition over time visualization 2026-04-05 21:01:16 -04:00
Sean Whalen
814d6985bb Stop hiding results that do not have a failure_reason in the SMTP TLS failures visualization 2026-04-05 18:34:40 -04:00
Sean Whalen
8f7ffb648c Add VSCode task configuration for Dev Dashboard 2026-04-05 18:11:36 -04:00
Sean Whalen
69eee9f1dc Update sponsorship section in README and documentation 2026-04-04 22:14:38 -04:00
Sean Whalen
d6ec35d66f Fix typo in sponsorship note heading in documentation 2026-04-04 21:52:14 -04:00
Sean Whalen
2d931ab4f1 Add sponsor link 2026-04-04 21:51:07 -04:00
Sean Whalen
25fdf53bd8 Update GitHub funding configuration 2026-04-04 20:40:15 -04:00
Sean Whalen
6a13f38ac6 Enhance debug logging for output client initialization and add environment variable aliases for debug settings 2026-03-27 10:31:43 -04:00
Sean Whalen
33ab4d9de9 Update CHANGELOG.md to include fix for current_time format in MSGraphConnection 2026-03-27 10:11:12 -04:00
Sean Whalen
f49ca0863d Bump version to 9.5.5, implement exponential backoff for output client initialization, update http_auth format, and add debug logging for OpenSearch connections 2026-03-27 10:09:08 -04:00
mihugo
e1851d026a Fix current_time format for MSGraphConnection (#708)
Should have caught this on previous fix for since. the current time is used on line 2145: connection.fetch_messages(reports_folder, since=current_time)
if that code is called and it usually won't be depending upon configuration it will fail  with the time format being wrong: yyyy-mm-ddThh:mm:ss.zzzzzz+00:00Z  ---     this removes the extra "Z" that is not needed since utc offset is already specified and becomes invalid.
2026-03-26 13:04:27 -04:00
Sean Whalen
1542936468 Bump version to 9.5.4, enhance Maildir folder handling, and add config key aliases for environment variable compatibility 2026-03-25 23:22:46 -04:00
Sean Whalen
fb3c38a8b8 9.5.3
- Fixed `FileNotFoundError` when using Maildir with Docker volume mounts. Python's `mailbox.Maildir(create=True)` only creates `cur/new/tmp` subdirectories when the top-level directory doesn't exist; Docker volume mounts pre-create the directory as empty, skipping subdirectory creation. parsedmarc now explicitly creates the subdirectories when `maildir_create` is enabled.
- Maildir UID mismatch no longer crashes the process. In Docker containers where volume ownership differs from the container UID, parsedmarc now logs a warning instead of raising an exception. Also handles `os.setuid` failures gracefully in containers without `CAP_SETUID`.
- Token file writes (MS Graph and Gmail) now create parent directories automatically, preventing `FileNotFoundError` when the token path points to a directory that doesn't yet exist.
- File paths from config (`token_file`, `credentials_file`, `cert_path`, `log_file`, `output`, `ip_db_path`, `maildir_path`, syslog cert paths, etc.) now expand `~` and `$VAR` references via `os.path.expanduser`/`os.path
2026-03-25 21:29:08 -04:00
Sean Whalen
c9a6145505 9.5.3
- Fixed `FileNotFoundError` when using Maildir with Docker volume mounts. Python's `mailbox.Maildir(create=True)` only creates `cur/new/tmp` subdirectories when the top-level directory doesn't exist; Docker volume mounts pre-create the directory as empty, skipping subdirectory creation. parsedmarc now explicitly creates the subdirectories when `maildir_create` is enabled.
2026-03-25 21:13:34 -04:00
Sean Whalen
e1bdbeb257 Bump version to 9.5.2 and fix interpolation issues in config parser 2026-03-25 20:21:08 -04:00
Sean Whalen
12c4676b79 9.5.1
- Correct ISO format for MSGraphConnection timestamps (PR #706)
2026-03-25 19:43:24 -04:00
mihugo
cda039ee27 Correct ISO format for MSGraphConnection timestamps (#706)
Fix formatting of ISO 8601 date strings for MSGraphConnection.  format yyyy-dd-mmThh:MM:SS.zzzzzz+00:00 already has a timezone indicated. The extra Z is invalid in this format.  specifying a "since" in config file causes msgraph to error due to invalid time stamp.
2026-03-25 19:38:23 -04:00
Sean Whalen
ff0ca6538c 9.5.0
Add environment variable configuration support and update documentation

- Introduced support for configuration via environment variables using the `PARSEDMARC_{SECTION}_{KEY}` format.
- Added `PARSEDMARC_CONFIG_FILE` variable to specify the config file path.
- Enabled env-only mode for file-less Docker deployments.
- Implemented explicit read permission checks on config files.
- Updated changelog and usage documentation to reflect these changes.
2026-03-25 19:25:21 -04:00
22 changed files with 1153 additions and 130 deletions

1
.github/FUNDING.yml vendored Normal file
View File

@@ -0,0 +1 @@
github: [seanthegeek]

View File

@@ -26,11 +26,13 @@
"boto",
"brakhane",
"Brightmail",
"cafile",
"CEST",
"CHACHA",
"checkdmarc",
"Codecov",
"confnew",
"creds",
"dateparser",
"dateutil",
"Davmail",
@@ -52,6 +54,7 @@
"geoipupdate",
"Geolite",
"geolocation",
"getuid",
"githubpages",
"Grafana",
"hostnames",
@@ -75,6 +78,7 @@
"LISTSERV",
"loganalytics",
"lxml",
"Maildir",
"mailparser",
"mailrelay",
"mailsuite",
@@ -128,6 +132,7 @@
"sdist",
"Servernameone",
"setuptools",
"signum",
"smartquotes",
"SMTPTLS",
"sortlists",

15
.vscode/tasks.json vendored Normal file
View File

@@ -0,0 +1,15 @@
{
"version": "2.0.0",
"tasks": [
{
"label": "Dev Dashboard: Up",
"type": "shell",
"command": "docker compose -f docker-compose.dashboard-dev.yml up -d",
"problemMatcher": [],
"presentation": {
"reveal": "always",
"panel": "new"
}
}
]
}

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 +1,63 @@
# Changelog
## 9.6.0
### Changes
- The included DB-IP Country Lite database is now automatically updated at startup (and on SIGHUP in watch mode) by downloading the latest copy from GitHub, unless the `offline` flag is set. Falls back to a previously cached copy or the bundled database on failure. This allows the IP-to-country database to stay current without requiring a new package release.
- Updated the included DB-IP Country Lite database to the 2026-04 release.
- Added the `ip_db_url` configuration option (`PARSEDMARC_GENERAL_IP_DB_URL` env var) to override the default download URL for the IP-to-country database.
## 9.5.5
### Fixed
- Output client initialization now retries up to 4 times with exponential backoff before exiting. This fixes persistent `Connection refused` errors in Docker when OpenSearch or Elasticsearch is momentarily unavailable at startup.
- Use tuple format for `http_auth` in OpenSearch and Elasticsearch connections, matching the documented convention and avoiding potential issues if the password contains a colon.
- Fix current_time format for MSGraphConnection (current-time) (PR #708)
### Changes
- Added debug logging to all output client initialization (S3, syslog, Splunk HEC, Kafka, GELF, webhook, Elasticsearch, OpenSearch).
- `DEBUG=true` and `PARSEDMARC_DEBUG=true` are now accepted as short aliases for `PARSEDMARC_GENERAL_DEBUG=true`.
## 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
- Fixed `FileNotFoundError` when using Maildir with Docker volume mounts. Python's `mailbox.Maildir(create=True)` only creates `cur/new/tmp` subdirectories when the top-level directory doesn't exist; Docker volume mounts pre-create the directory as empty, skipping subdirectory creation. parsedmarc now explicitly creates the subdirectories when `maildir_create` is enabled.
- Maildir UID mismatch no longer crashes the process. In Docker containers where volume ownership differs from the container UID, parsedmarc now logs a warning instead of raising an exception. Also handles `os.setuid` failures gracefully in containers without `CAP_SETUID`.
- Token file writes (MS Graph and Gmail) now create parent directories automatically, preventing `FileNotFoundError` when the token path points to a directory that doesn't yet exist.
- File paths from config (`token_file`, `credentials_file`, `cert_path`, `log_file`, `output`, `ip_db_path`, `maildir_path`, syslog cert paths, etc.) now expand `~` and `$VAR` references via `os.path.expanduser`/`os.path.expandvars`.
## 9.5.2
### Fixed
- Fixed `ValueError: invalid interpolation syntax` when config values (from env vars or INI files) contain `%` characters, such as in passwords. Disabled ConfigParser's `%`-based string interpolation.
## 9.5.1
### Changes
- Correct ISO format for MSGraphConnection timestamps (PR #706)
## 9.5.0
### Added
- Environment variable configuration support: any config option can now be set via `PARSEDMARC_{SECTION}_{KEY}` environment variables (e.g. `PARSEDMARC_IMAP_PASSWORD`, `PARSEDMARC_SPLUNK_HEC_TOKEN`). Environment variables override config file values but are overridden by CLI arguments.
- `PARSEDMARC_CONFIG_FILE` environment variable to specify the config file path without the `-c` flag.
- Env-only mode: parsedmarc can now run without a config file when `PARSEDMARC_*` environment variables are set, enabling fully file-less Docker deployments.
- Explicit read permission check on config file, giving a clear error message when the container UID cannot read the file (e.g. `chmod 600` with a UID mismatch).
## 9.4.0
### Added

View File

@@ -21,15 +21,10 @@ ProofPoint Email Fraud Defense, and Valimail.
> [!NOTE]
> __Domain-based Message Authentication, Reporting, and Conformance__ (DMARC) is an email authentication protocol.
## Help Wanted
## Sponsors
This project is maintained by one developer. Please consider reviewing the open
[issues](https://github.com/domainaware/parsedmarc/issues) to see how you can
contribute code, documentation, or user support. Assistance on the pinned
issues would be particularly helpful.
Thanks to all
[contributors](https://github.com/domainaware/parsedmarc/graphs/contributors)!
This is a project is maintained by one developer.
Please consider [sponsoring my work](https://github.com/sponsors/seanthegeek) if you or your organization benefit from it.
## Features

View File

@@ -9,13 +9,9 @@ Package](https://img.shields.io/pypi/v/parsedmarc.svg)](https://pypi.org/project
[![PyPI - Downloads](https://img.shields.io/pypi/dm/parsedmarc?color=blue)](https://pypistats.org/packages/parsedmarc)
:::{note}
**Help Wanted**
This is a project is maintained by one developer.
Please consider reviewing the open [issues] to see how you can contribute code, documentation, or user support.
Assistance on the pinned issues would be particularly helpful.
Thanks to all [contributors]!
Please consider [sponsoring my work](https://github.com/sponsors/seanthegeek) if you or your organization benefit from it.
:::
```{image} _static/screenshots/dmarc-summary-charts.png
@@ -79,6 +75,3 @@ dmarc
contributing
api
```
[contributors]: https://github.com/domainaware/parsedmarc/graphs/contributors
[issues]: https://github.com/domainaware/parsedmarc/issues

View File

@@ -49,11 +49,17 @@ Starting in `parsedmarc` 7.1.0, a static copy of the
`parsedmarc`, under the terms of the
[Creative Commons Attribution 4.0 International License].
as a fallback if the [MaxMind GeoLite2 Country database] is not
installed. However, `parsedmarc` cannot install updated versions of
these databases as they are released, so MaxMind's databases and the
[geoipupdate] tool is still the preferable solution.
installed.
The location of the database file can be overridden by using the
Starting in `parsedmarc` 9.6.0, the bundled DB-IP database is
automatically updated at startup by downloading the latest copy from
GitHub, unless the `offline` flag is set. The database is cached
locally and refreshed on each run (or on `SIGHUP` in watch mode).
If the download fails, a previously cached copy or the bundled
database is used as a fallback.
The download URL can be overridden with the `ip_db_url` setting, and
the location of a local database file can be overridden with the
`ip_db_path` setting.
:::

View File

@@ -134,9 +134,13 @@ The full set of configuration options are:
JSON output file
- `ip_db_path` - str: An optional custom path to a MMDB file
from MaxMind or DBIP
- `ip_db_url` - str: Overrides the default download URL for the
IP-to-country database (env var: `PARSEDMARC_GENERAL_IP_DB_URL`)
- `offline` - bool: Do not use online queries for geolocation
or DNS
- `always_use_local_files` - Disables the download of the reverse DNS map
or DNS. Also disables automatic downloading of the IP-to-country
database and reverse DNS map.
- `always_use_local_files` - Disables the download of the
IP-to-country database and reverse DNS map
- `local_reverse_dns_map_path` - Overrides the default local file path to use for the reverse DNS map
- `reverse_dns_map_url` - Overrides the default download URL for the reverse DNS map
- `nameservers` - str: A comma separated list of
@@ -531,6 +535,96 @@ PUT _cluster/settings
Increasing this value increases resource usage.
:::
## Environment variable configuration
Any configuration option can be set via environment variables using the
naming convention `PARSEDMARC_{SECTION}_{KEY}` (uppercase). This is
especially useful for Docker deployments where file permissions make it
difficult to use config files for secrets.
**Priority order:** CLI arguments > environment variables > config file > defaults
### Examples
```bash
# Set IMAP credentials via env vars
export PARSEDMARC_IMAP_HOST=imap.example.com
export PARSEDMARC_IMAP_USER=dmarc@example.com
export PARSEDMARC_IMAP_PASSWORD=secret
# Elasticsearch
export PARSEDMARC_ELASTICSEARCH_HOSTS=http://localhost:9200
export PARSEDMARC_ELASTICSEARCH_SSL=false
# Splunk HEC (note: section name splunk_hec becomes SPLUNK_HEC)
export PARSEDMARC_SPLUNK_HEC_URL=https://splunk.example.com
export PARSEDMARC_SPLUNK_HEC_TOKEN=my-hec-token
export PARSEDMARC_SPLUNK_HEC_INDEX=email
# General settings
export PARSEDMARC_GENERAL_SAVE_AGGREGATE=true
export PARSEDMARC_GENERAL_DEBUG=true
```
### Specifying the config file via environment variable
```bash
export PARSEDMARC_CONFIG_FILE=/etc/parsedmarc.ini
parsedmarc
```
### Running without a config file (env-only mode)
When no config file is given (neither `-c` flag nor `PARSEDMARC_CONFIG_FILE`),
parsedmarc will still pick up any `PARSEDMARC_*` environment variables. This
enables fully file-less deployments:
```bash
export PARSEDMARC_GENERAL_SAVE_AGGREGATE=true
export PARSEDMARC_GENERAL_OFFLINE=true
export PARSEDMARC_ELASTICSEARCH_HOSTS=http://elasticsearch:9200
parsedmarc /path/to/reports/*
```
### Docker Compose example
```yaml
services:
parsedmarc:
image: parsedmarc:latest
environment:
PARSEDMARC_IMAP_HOST: imap.example.com
PARSEDMARC_IMAP_USER: dmarc@example.com
PARSEDMARC_IMAP_PASSWORD: ${IMAP_PASSWORD}
PARSEDMARC_MAILBOX_WATCH: "true"
PARSEDMARC_ELASTICSEARCH_HOSTS: http://elasticsearch:9200
PARSEDMARC_GENERAL_SAVE_AGGREGATE: "true"
PARSEDMARC_GENERAL_SAVE_FORENSIC: "true"
```
### Section name mapping
For sections with underscores in the name, the full section name is used:
| Section | Env var prefix |
|------------------|-------------------------------|
| `general` | `PARSEDMARC_GENERAL_` |
| `mailbox` | `PARSEDMARC_MAILBOX_` |
| `imap` | `PARSEDMARC_IMAP_` |
| `msgraph` | `PARSEDMARC_MSGRAPH_` |
| `elasticsearch` | `PARSEDMARC_ELASTICSEARCH_` |
| `opensearch` | `PARSEDMARC_OPENSEARCH_` |
| `splunk_hec` | `PARSEDMARC_SPLUNK_HEC_` |
| `kafka` | `PARSEDMARC_KAFKA_` |
| `smtp` | `PARSEDMARC_SMTP_` |
| `s3` | `PARSEDMARC_S3_` |
| `syslog` | `PARSEDMARC_SYSLOG_` |
| `gmail_api` | `PARSEDMARC_GMAIL_API_` |
| `maildir` | `PARSEDMARC_MAILDIR_` |
| `log_analytics` | `PARSEDMARC_LOG_ANALYTICS_` |
| `gelf` | `PARSEDMARC_GELF_` |
| `webhook` | `PARSEDMARC_WEBHOOK_` |
## Performance tuning
For large mailbox imports or backfills, parsedmarc can consume a noticeable amount
@@ -661,7 +755,7 @@ for that batch have completed. The following settings are reloaded:
- Multi-tenant index prefix domain map (`index_prefix_domain_map` —
the referenced YAML file is re-read on reload)
- DNS and GeoIP settings (`nameservers`, `dns_timeout`, `ip_db_path`,
`offline`, etc.)
`ip_db_url`, `offline`, etc.)
- Processing flags (`strip_attachment_payloads`, `batch_size`,
`check_timeout`, etc.)
- Log level (`debug`, `verbose`, `warnings`, `silent`)

54
opensearch/opensearch_dashboards.ndjson Normal file → Executable file

File diff suppressed because one or more lines are too long

View File

@@ -1955,10 +1955,8 @@ def get_dmarc_reports_from_mailbox(
)
current_time = datetime.now(timezone.utc).strftime("%d-%b-%Y")
elif isinstance(connection, MSGraphConnection):
since = (
datetime.now(timezone.utc) - timedelta(minutes=_since)
).isoformat() + "Z"
current_time = datetime.now(timezone.utc).isoformat() + "Z"
since = (datetime.now(timezone.utc) - timedelta(minutes=_since)).isoformat()
current_time = datetime.now(timezone.utc).isoformat()
elif isinstance(connection, GmailConnection):
since = (datetime.now(timezone.utc) - timedelta(minutes=_since)).strftime(
"%s"

View File

@@ -9,6 +9,7 @@ import logging
import os
import signal
import sys
import time
from argparse import ArgumentParser, Namespace
from configparser import ConfigParser
from glob import glob
@@ -53,6 +54,7 @@ from parsedmarc.utils import (
get_base_domain,
get_reverse_dns,
is_mbox,
load_ip_db,
load_reverse_dns_map,
)
@@ -75,6 +77,92 @@ def _str_to_list(s):
return list(map(lambda i: i.lstrip(), _list))
def _expand_path(p: str) -> str:
"""Expand ``~`` and ``$VAR`` references in a file path."""
return os.path.expanduser(os.path.expandvars(p))
# All known INI config section names, used for env var resolution.
_KNOWN_SECTIONS = frozenset(
{
"general",
"mailbox",
"imap",
"msgraph",
"elasticsearch",
"opensearch",
"splunk_hec",
"kafka",
"smtp",
"s3",
"syslog",
"gmail_api",
"maildir",
"log_analytics",
"gelf",
"webhook",
}
)
def _resolve_section_key(suffix: str) -> tuple:
"""Resolve an env var suffix like ``IMAP_PASSWORD`` to ``('imap', 'password')``.
Uses longest-prefix matching against known section names so that
multi-word sections like ``splunk_hec`` are handled correctly.
Returns ``(None, None)`` when no known section matches.
"""
suffix_lower = suffix.lower()
best_section = None
best_key = None
for section in _KNOWN_SECTIONS:
section_prefix = section + "_"
if suffix_lower.startswith(section_prefix):
key = suffix_lower[len(section_prefix) :]
if key and (best_section is None or len(section) > len(best_section)):
best_section = section
best_key = key
return best_section, best_key
def _apply_env_overrides(config: ConfigParser) -> None:
"""Inject ``PARSEDMARC_*`` environment variables into *config*.
Environment variables matching ``PARSEDMARC_{SECTION}_{KEY}`` override
(or create) the corresponding config-file values. Sections are created
automatically when they do not yet exist.
"""
prefix = "PARSEDMARC_"
# Short aliases that don't follow the PARSEDMARC_{SECTION}_{KEY} pattern.
_ENV_ALIASES = {
"DEBUG": ("general", "debug"),
"PARSEDMARC_DEBUG": ("general", "debug"),
}
for env_key, env_value in os.environ.items():
if env_key in _ENV_ALIASES:
section, key = _ENV_ALIASES[env_key]
elif env_key.startswith(prefix) and env_key != "PARSEDMARC_CONFIG_FILE":
suffix = env_key[len(prefix) :]
section, key = _resolve_section_key(suffix)
else:
continue
if section is None:
logger.debug("Ignoring unrecognized env var: %s", env_key)
continue
if not config.has_section(section):
config.add_section(section)
config.set(section, key, env_value)
logger.debug("Config override from env: [%s] %s", section, key)
def _configure_logging(log_level, log_file=None):
"""
Configure logging for the current process.
@@ -178,12 +266,39 @@ class ConfigurationError(Exception):
pass
def _parse_config_file(config_file, opts):
"""Parse a config file and update opts in place.
def _load_config(config_file: str | None = None) -> ConfigParser:
"""Load configuration from an INI file and/or environment variables.
Args:
config_file: Path to the .ini config file
opts: Namespace object to update with parsed values
config_file: Optional path to an .ini config file.
Returns:
A ``ConfigParser`` populated from the file (if given) and from any
``PARSEDMARC_*`` environment variables.
Raises:
ConfigurationError: If *config_file* is given but does not exist.
"""
config = ConfigParser(interpolation=None)
if config_file is not None:
abs_path = os.path.abspath(config_file)
if not os.path.exists(abs_path):
raise ConfigurationError("A file does not exist at {0}".format(abs_path))
if not os.access(abs_path, os.R_OK):
raise ConfigurationError(
"Unable to read {0} — check file permissions".format(abs_path)
)
config.read(config_file)
_apply_env_overrides(config)
return config
def _parse_config(config: ConfigParser, opts):
"""Apply a loaded ``ConfigParser`` to *opts* in place.
Args:
config: A ``ConfigParser`` (from ``_load_config``).
opts: Namespace object to update with parsed values.
Returns:
index_prefix_domain_map or None
@@ -191,13 +306,8 @@ def _parse_config_file(config_file, opts):
Raises:
ConfigurationError: If required settings are missing or invalid.
"""
abs_path = os.path.abspath(config_file)
if not os.path.exists(abs_path):
raise ConfigurationError("A file does not exist at {0}".format(abs_path))
opts.silent = True
config = ConfigParser()
index_prefix_domain_map = None
config.read(config_file)
if "general" in config.sections():
general_config = config["general"]
if "silent" in general_config:
@@ -207,7 +317,7 @@ def _parse_config_file(config_file, opts):
"normalize_timespan_threshold_hours"
)
if "index_prefix_domain_map" in general_config:
with open(general_config["index_prefix_domain_map"]) as f:
with open(_expand_path(general_config["index_prefix_domain_map"])) as f:
index_prefix_domain_map = yaml.safe_load(f)
if "offline" in general_config:
opts.offline = bool(general_config.getboolean("offline"))
@@ -216,7 +326,7 @@ def _parse_config_file(config_file, opts):
general_config.getboolean("strip_attachment_payloads")
)
if "output" in general_config:
opts.output = general_config["output"]
opts.output = _expand_path(general_config["output"])
if "aggregate_json_filename" in general_config:
opts.aggregate_json_filename = general_config["aggregate_json_filename"]
if "forensic_json_filename" in general_config:
@@ -272,19 +382,23 @@ def _parse_config_file(config_file, opts):
general_config.getboolean("fail_on_output_error")
)
if "log_file" in general_config:
opts.log_file = general_config["log_file"]
opts.log_file = _expand_path(general_config["log_file"])
if "n_procs" in general_config:
opts.n_procs = general_config.getint("n_procs")
if "ip_db_path" in general_config:
opts.ip_db_path = general_config["ip_db_path"]
opts.ip_db_path = _expand_path(general_config["ip_db_path"])
else:
opts.ip_db_path = None
if "ip_db_url" in general_config:
opts.ip_db_url = general_config["ip_db_url"]
if "always_use_local_files" in general_config:
opts.always_use_local_files = bool(
general_config.getboolean("always_use_local_files")
)
if "local_reverse_dns_map_path" in general_config:
opts.reverse_dns_map_path = general_config["local_reverse_dns_map_path"]
opts.reverse_dns_map_path = _expand_path(
general_config["local_reverse_dns_map_path"]
)
if "reverse_dns_map_url" in general_config:
opts.reverse_dns_map_url = general_config["reverse_dns_map_url"]
if "prettify_json" in general_config:
@@ -399,7 +513,7 @@ def _parse_config_file(config_file, opts):
if "msgraph" in config.sections():
graph_config = config["msgraph"]
opts.graph_token_file = graph_config.get("token_file", ".token")
opts.graph_token_file = _expand_path(graph_config.get("token_file", ".token"))
if "auth_method" not in graph_config:
logger.info(
@@ -453,7 +567,9 @@ def _parse_config_file(config_file, opts):
if opts.graph_auth_method == AuthMethod.Certificate.name:
if "certificate_path" in graph_config:
opts.graph_certificate_path = graph_config["certificate_path"]
opts.graph_certificate_path = _expand_path(
graph_config["certificate_path"]
)
else:
raise ConfigurationError(
"certificate_path setting missing from the msgraph config section"
@@ -477,6 +593,8 @@ def _parse_config_file(config_file, 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(
@@ -510,7 +628,9 @@ def _parse_config_file(config_file, opts):
if "ssl" in elasticsearch_config:
opts.elasticsearch_ssl = bool(elasticsearch_config.getboolean("ssl"))
if "cert_path" in elasticsearch_config:
opts.elasticsearch_ssl_cert_path = elasticsearch_config["cert_path"]
opts.elasticsearch_ssl_cert_path = _expand_path(
elasticsearch_config["cert_path"]
)
if "skip_certificate_verification" in elasticsearch_config:
opts.elasticsearch_skip_certificate_verification = bool(
elasticsearch_config.getboolean("skip_certificate_verification")
@@ -553,7 +673,7 @@ def _parse_config_file(config_file, opts):
if "ssl" in opensearch_config:
opts.opensearch_ssl = bool(opensearch_config.getboolean("ssl"))
if "cert_path" in opensearch_config:
opts.opensearch_ssl_cert_path = opensearch_config["cert_path"]
opts.opensearch_ssl_cert_path = _expand_path(opensearch_config["cert_path"])
if "skip_certificate_verification" in opensearch_config:
opts.opensearch_skip_certificate_verification = bool(
opensearch_config.getboolean("skip_certificate_verification")
@@ -680,7 +800,7 @@ def _parse_config_file(config_file, opts):
if "subject" in smtp_config:
opts.smtp_subject = smtp_config["subject"]
if "attachment" in smtp_config:
opts.smtp_attachment = smtp_config["attachment"]
opts.smtp_attachment = _expand_path(smtp_config["attachment"])
if "message" in smtp_config:
opts.smtp_message = smtp_config["message"]
@@ -727,11 +847,11 @@ def _parse_config_file(config_file, opts):
else:
opts.syslog_protocol = "udp"
if "cafile_path" in syslog_config:
opts.syslog_cafile_path = syslog_config["cafile_path"]
opts.syslog_cafile_path = _expand_path(syslog_config["cafile_path"])
if "certfile_path" in syslog_config:
opts.syslog_certfile_path = syslog_config["certfile_path"]
opts.syslog_certfile_path = _expand_path(syslog_config["certfile_path"])
if "keyfile_path" in syslog_config:
opts.syslog_keyfile_path = syslog_config["keyfile_path"]
opts.syslog_keyfile_path = _expand_path(syslog_config["keyfile_path"])
if "timeout" in syslog_config:
opts.syslog_timeout = float(syslog_config["timeout"])
else:
@@ -747,8 +867,13 @@ def _parse_config_file(config_file, opts):
if "gmail_api" in config.sections():
gmail_api_config = config["gmail_api"]
opts.gmail_api_credentials_file = gmail_api_config.get("credentials_file")
opts.gmail_api_token_file = gmail_api_config.get("token_file", ".token")
gmail_creds = gmail_api_config.get("credentials_file")
opts.gmail_api_credentials_file = (
_expand_path(gmail_creds) if gmail_creds else gmail_creds
)
opts.gmail_api_token_file = _expand_path(
gmail_api_config.get("token_file", ".token")
)
opts.gmail_api_include_spam_trash = bool(
gmail_api_config.getboolean("include_spam_trash", False)
)
@@ -773,9 +898,15 @@ def _parse_config_file(config_file, opts):
if "maildir" in config.sections():
maildir_api_config = config["maildir"]
opts.maildir_path = 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():
@@ -869,6 +1000,7 @@ def _init_output_clients(opts):
try:
if opts.s3_bucket:
logger.debug("Initializing S3 client: bucket=%s", opts.s3_bucket)
clients["s3_client"] = s3.S3Client(
bucket_name=opts.s3_bucket,
bucket_path=opts.s3_path,
@@ -882,6 +1014,11 @@ def _init_output_clients(opts):
try:
if opts.syslog_server:
logger.debug(
"Initializing syslog client: server=%s:%s",
opts.syslog_server,
opts.syslog_port,
)
clients["syslog_client"] = syslog.SyslogClient(
server_name=opts.syslog_server,
server_port=int(opts.syslog_port),
@@ -906,6 +1043,7 @@ def _init_output_clients(opts):
"HEC token and HEC index are required when using HEC URL"
)
try:
logger.debug("Initializing Splunk HEC client: url=%s", opts.hec)
verify = True
if opts.hec_skip_certificate_verification:
verify = False
@@ -917,6 +1055,7 @@ def _init_output_clients(opts):
try:
if opts.kafka_hosts:
logger.debug("Initializing Kafka client: hosts=%s", opts.kafka_hosts)
ssl_context = None
if opts.kafka_skip_certificate_verification:
logger.debug("Skipping Kafka certificate verification")
@@ -934,6 +1073,11 @@ def _init_output_clients(opts):
try:
if opts.gelf_host:
logger.debug(
"Initializing GELF client: host=%s:%s",
opts.gelf_host,
opts.gelf_port,
)
clients["gelf_client"] = gelf.GelfClient(
host=opts.gelf_host,
port=int(opts.gelf_port),
@@ -948,6 +1092,7 @@ def _init_output_clients(opts):
or opts.webhook_forensic_url
or opts.webhook_smtp_tls_url
):
logger.debug("Initializing webhook client")
clients["webhook_client"] = webhook.WebhookClient(
aggregate_url=opts.webhook_aggregate_url,
forensic_url=opts.webhook_forensic_url,
@@ -960,11 +1105,16 @@ def _init_output_clients(opts):
# Elasticsearch and OpenSearch mutate module-level global state via
# connections.create_connection(), which cannot be rolled back if a later
# step fails. Initialise them last so that all other clients are created
# successfully first; this minimises the window for partial-init problems
# successfully first; this minimizes the window for partial-init problems
# during config reload.
if opts.save_aggregate or opts.save_forensic or opts.save_smtp_tls:
try:
if opts.elasticsearch_hosts:
logger.debug(
"Initializing Elasticsearch client: hosts=%s, ssl=%s",
opts.elasticsearch_hosts,
opts.elasticsearch_ssl,
)
es_aggregate_index = "dmarc_aggregate"
es_forensic_index = "dmarc_forensic"
es_smtp_tls_index = "smtp_tls"
@@ -1003,6 +1153,11 @@ def _init_output_clients(opts):
try:
if opts.opensearch_hosts:
logger.debug(
"Initializing OpenSearch client: hosts=%s, ssl=%s",
opts.opensearch_hosts,
opts.opensearch_ssl,
)
os_aggregate_index = "dmarc_aggregate"
os_forensic_index = "dmarc_forensic"
os_smtp_tls_index = "smtp_tls"
@@ -1654,6 +1809,7 @@ def _main():
log_file=args.log_file,
n_procs=1,
ip_db_path=None,
ip_db_url=None,
always_use_local_files=False,
reverse_dns_map_path=None,
reverse_dns_map_url=None,
@@ -1683,9 +1839,16 @@ def _main():
index_prefix_domain_map = None
if args.config_file:
config_file = args.config_file or os.environ.get("PARSEDMARC_CONFIG_FILE")
has_env_config = any(
k.startswith("PARSEDMARC_") and k != "PARSEDMARC_CONFIG_FILE"
for k in os.environ
)
if config_file or has_env_config:
try:
index_prefix_domain_map = _parse_config_file(args.config_file, opts)
config = _load_config(config_file)
index_prefix_domain_map = _parse_config(config, opts)
except ConfigurationError as e:
logger.critical(str(e))
exit(-1)
@@ -1723,15 +1886,38 @@ def _main():
logger.info("Starting parsedmarc")
# Initialize output clients
try:
clients = _init_output_clients(opts)
except ConfigurationError as e:
logger.critical(str(e))
exit(1)
except Exception as error_:
logger.error("Output client error: {0}".format(error_))
exit(1)
load_ip_db(
always_use_local_file=opts.always_use_local_files,
local_file_path=opts.ip_db_path,
url=opts.ip_db_url,
offline=opts.offline,
)
# Initialize output clients (with retry for transient connection errors)
clients = {}
max_retries = 4
retry_delay = 5
for attempt in range(max_retries + 1):
try:
clients = _init_output_clients(opts)
break
except ConfigurationError as e:
logger.critical(str(e))
exit(1)
except Exception as error_:
if attempt < max_retries:
logger.warning(
"Output client error (attempt %d/%d, retrying in %ds): %s",
attempt + 1,
max_retries + 1,
retry_delay,
error_,
)
time.sleep(retry_delay)
retry_delay *= 2
else:
logger.error("Output client error: {0}".format(error_))
exit(1)
file_paths = []
mbox_paths = []
@@ -2102,9 +2288,8 @@ def _main():
# Build a fresh opts starting from CLI-only defaults so that
# sections removed from the config file actually take effect.
new_opts = Namespace(**vars(opts_from_cli))
new_index_prefix_domain_map = _parse_config_file(
args.config_file, new_opts
)
new_config = _load_config(config_file)
new_index_prefix_domain_map = _parse_config(new_config, new_opts)
new_clients = _init_output_clients(new_opts)
# All steps succeeded — commit the changes atomically.
@@ -2122,6 +2307,15 @@ def _main():
offline=new_opts.offline,
)
# Reload the IP database so changes to the
# db path/URL in the config take effect.
load_ip_db(
always_use_local_file=new_opts.always_use_local_files,
local_file_path=new_opts.ip_db_path,
url=new_opts.ip_db_url,
offline=new_opts.offline,
)
for k, v in vars(new_opts).items():
setattr(opts, k, v)

View File

@@ -1,3 +1,3 @@
__version__ = "9.4.0"
__version__ = "9.6.0"
USER_AGENT = f"parsedmarc/{__version__}"

View File

@@ -299,7 +299,7 @@ def set_hosts(
else:
conn_params["verify_certs"] = True
if username and password:
conn_params["http_auth"] = username + ":" + password
conn_params["http_auth"] = (username, password)
if api_key:
conn_params["api_key"] = api_key
connections.create_connection(**conn_params)

View File

@@ -55,6 +55,7 @@ def _get_creds(
flow = InstalledAppFlow.from_client_secrets_file(credentials_file, scopes)
creds = flow.run_local_server(open_browser=False, oauth2_port=oauth2_port)
# Save the credentials for the next run
Path(token_file).parent.mkdir(parents=True, exist_ok=True)
with Path(token_file).open("w") as token:
token.write(creds.to_json())
return creds

View File

@@ -56,6 +56,7 @@ def _load_token(token_path: Path) -> Optional[str]:
def _cache_auth_record(record: AuthenticationRecord, token_path: Path):
token = record.serialize()
token_path.parent.mkdir(parents=True, exist_ok=True)
with token_path.open("w") as token_file:
token_file.write(token)

View File

@@ -19,29 +19,54 @@ class MaildirConnection(MailboxConnection):
):
self._maildir_path = maildir_path
self._maildir_create = maildir_create
maildir_owner = os.stat(maildir_path).st_uid
if os.getuid() != maildir_owner:
if os.getuid() == 0:
logger.warning(
"Switching uid to {} to access Maildir".format(maildir_owner)
)
os.setuid(maildir_owner)
try:
maildir_owner = os.stat(maildir_path).st_uid
except OSError:
maildir_owner = None
current_uid = os.getuid()
if maildir_owner is not None and current_uid != maildir_owner:
if current_uid == 0:
try:
logger.warning(
"Switching uid to {} to access Maildir".format(maildir_owner)
)
os.setuid(maildir_owner)
except OSError as e:
logger.warning(
"Failed to switch uid to {}: {}".format(maildir_owner, e)
)
else:
ex = "runtime uid {} differ from maildir {} owner {}".format(
os.getuid(), maildir_path, maildir_owner
logger.warning(
"Runtime uid {} differs from maildir {} owner {}. "
"Access may fail if permissions are insufficient.".format(
current_uid, maildir_path, maildir_owner
)
)
raise Exception(ex)
if maildir_create:
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:
@@ -49,16 +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

View File

@@ -298,6 +298,7 @@ def set_hosts(
"""
if not isinstance(hosts, list):
hosts = [hosts]
logger.debug("Connecting to OpenSearch: hosts=%s, use_ssl=%s", hosts, use_ssl)
conn_params = {"hosts": hosts, "timeout": timeout}
if use_ssl:
conn_params["use_ssl"] = True
@@ -323,7 +324,7 @@ def set_hosts(
conn_params["connection_class"] = RequestsHttpConnection
elif normalized_auth_type == "basic":
if username and password:
conn_params["http_auth"] = username + ":" + password
conn_params["http_auth"] = (username, password)
if api_key:
conn_params["api_key"] = api_key
else:

BIN
parsedmarc/resources/dbip/dbip-country-lite.mmdb Normal file → Executable file

Binary file not shown.

View File

@@ -271,6 +271,75 @@ def human_timestamp_to_unix_timestamp(human_timestamp: str) -> int:
return int(human_timestamp_to_datetime(human_timestamp).timestamp())
_IP_DB_PATH: Optional[str] = None
def load_ip_db(
*,
always_use_local_file: bool = False,
local_file_path: Optional[str] = None,
url: Optional[str] = None,
offline: bool = False,
) -> None:
"""
Downloads the IP-to-country MMDB database from a URL and caches it
locally. Falls back to the bundled copy on failure or when offline.
Args:
always_use_local_file: Always use a local/bundled database file
local_file_path: Path to a local MMDB file
url: URL to the MMDB database file
offline: Do not make online requests
"""
global _IP_DB_PATH
if url is None:
url = (
"https://github.com/domainaware/parsedmarc/raw/"
"refs/heads/master/parsedmarc/resources/dbip/"
"dbip-country-lite.mmdb"
)
if local_file_path is not None and os.path.isfile(local_file_path):
_IP_DB_PATH = local_file_path
logger.info(f"Using local IP database at {local_file_path}")
return
cache_dir = os.path.join(tempfile.gettempdir(), "parsedmarc")
cached_path = os.path.join(cache_dir, "dbip-country-lite.mmdb")
if not (offline or always_use_local_file):
try:
logger.debug(f"Trying to fetch IP database from {url}...")
headers = {"User-Agent": USER_AGENT}
response = requests.get(url, headers=headers, timeout=60)
response.raise_for_status()
os.makedirs(cache_dir, exist_ok=True)
tmp_path = cached_path + ".tmp"
with open(tmp_path, "wb") as f:
f.write(response.content)
shutil.move(tmp_path, cached_path)
_IP_DB_PATH = cached_path
logger.info("IP database updated successfully")
return
except requests.exceptions.RequestException as e:
logger.warning(f"Failed to fetch IP database: {e}")
except Exception as e:
logger.warning(f"Failed to save IP database: {e}")
# Fall back to a previously cached copy if available
if os.path.isfile(cached_path):
_IP_DB_PATH = cached_path
logger.info("Using cached IP database")
return
# Final fallback: bundled copy
_IP_DB_PATH = str(
files(parsedmarc.resources.dbip).joinpath("dbip-country-lite.mmdb")
)
logger.info("Using bundled IP database")
def get_ip_address_country(
ip_address: str, *, db_path: Optional[str] = None
) -> Optional[str]:
@@ -315,9 +384,12 @@ def get_ip_address_country(
break
if db_path is None:
db_path = str(
files(parsedmarc.resources.dbip).joinpath("dbip-country-lite.mmdb")
)
if _IP_DB_PATH is not None:
db_path = _IP_DB_PATH
else:
db_path = str(
files(parsedmarc.resources.dbip).joinpath("dbip-country-lite.mmdb")
)
db_age = datetime.now() - datetime.fromtimestamp(os.stat(db_path).st_mtime)
if db_age > timedelta(days=30):

576
tests.py
View File

@@ -11,6 +11,7 @@ import sys
import tempfile
import unittest
from base64 import urlsafe_b64encode
from configparser import ConfigParser
from glob import glob
from pathlib import Path
from tempfile import NamedTemporaryFile, TemporaryDirectory
@@ -1985,7 +1986,8 @@ watch = true
"SIGHUP not available on this platform",
)
@patch("parsedmarc.cli._init_output_clients")
@patch("parsedmarc.cli._parse_config_file")
@patch("parsedmarc.cli._parse_config")
@patch("parsedmarc.cli._load_config")
@patch("parsedmarc.cli.get_dmarc_reports_from_mailbox")
@patch("parsedmarc.cli.watch_inbox")
@patch("parsedmarc.cli.IMAPConnection")
@@ -1994,6 +1996,7 @@ watch = true
mock_imap,
mock_watch,
mock_get_reports,
mock_load_config,
mock_parse_config,
mock_init_clients,
):
@@ -2007,7 +2010,9 @@ watch = true
"smtp_tls_reports": [],
}
def parse_side_effect(config_file, opts):
mock_load_config.return_value = ConfigParser()
def parse_side_effect(config, opts):
opts.imap_host = "imap.example.com"
opts.imap_user = "user"
opts.imap_password = "pass"
@@ -2046,7 +2051,7 @@ watch = true
self.assertEqual(cm.exception.code, 1)
# watch_inbox was called twice: initial run + after reload
self.assertEqual(mock_watch.call_count, 2)
# _parse_config_file called for initial load + reload
# _parse_config called for initial load + reload
self.assertGreaterEqual(mock_parse_config.call_count, 2)
@unittest.skipUnless(
@@ -2054,7 +2059,8 @@ watch = true
"SIGHUP not available on this platform",
)
@patch("parsedmarc.cli._init_output_clients")
@patch("parsedmarc.cli._parse_config_file")
@patch("parsedmarc.cli._parse_config")
@patch("parsedmarc.cli._load_config")
@patch("parsedmarc.cli.get_dmarc_reports_from_mailbox")
@patch("parsedmarc.cli.watch_inbox")
@patch("parsedmarc.cli.IMAPConnection")
@@ -2063,6 +2069,7 @@ watch = true
mock_imap,
mock_watch,
mock_get_reports,
mock_load_config,
mock_parse_config,
mock_init_clients,
):
@@ -2076,11 +2083,13 @@ watch = true
"smtp_tls_reports": [],
}
mock_load_config.return_value = ConfigParser()
# Initial parse sets required opts; reload parse raises
initial_map = {"prefix_": ["example.com"]}
call_count = [0]
def parse_side_effect(config_file, opts):
def parse_side_effect(config, opts):
call_count[0] += 1
opts.imap_host = "imap.example.com"
opts.imap_user = "user"
@@ -2130,7 +2139,8 @@ watch = true
"SIGHUP not available on this platform",
)
@patch("parsedmarc.cli._init_output_clients")
@patch("parsedmarc.cli._parse_config_file")
@patch("parsedmarc.cli._parse_config")
@patch("parsedmarc.cli._load_config")
@patch("parsedmarc.cli.get_dmarc_reports_from_mailbox")
@patch("parsedmarc.cli.watch_inbox")
@patch("parsedmarc.cli.IMAPConnection")
@@ -2139,6 +2149,7 @@ watch = true
mock_imap,
mock_watch,
mock_get_reports,
mock_load_config,
mock_parse_config,
mock_init_clients,
):
@@ -2152,7 +2163,9 @@ watch = true
"smtp_tls_reports": [],
}
def parse_side_effect(config_file, opts):
mock_load_config.return_value = ConfigParser()
def parse_side_effect(config, opts):
opts.imap_host = "imap.example.com"
opts.imap_user = "user"
opts.imap_password = "pass"
@@ -2284,7 +2297,8 @@ watch = true
"SIGHUP not available on this platform",
)
@patch("parsedmarc.cli._init_output_clients")
@patch("parsedmarc.cli._parse_config_file")
@patch("parsedmarc.cli._parse_config")
@patch("parsedmarc.cli._load_config")
@patch("parsedmarc.cli.get_dmarc_reports_from_mailbox")
@patch("parsedmarc.cli.watch_inbox")
@patch("parsedmarc.cli.IMAPConnection")
@@ -2293,6 +2307,7 @@ watch = true
mock_imap,
mock_watch,
mock_get_reports,
mock_load_config,
mock_parse_config,
mock_init_clients,
):
@@ -2308,7 +2323,9 @@ watch = true
"smtp_tls_reports": [],
}
def parse_side_effect(config_file, opts):
mock_load_config.return_value = ConfigParser()
def parse_side_effect(config, opts):
opts.imap_host = "imap.example.com"
opts.imap_user = "user"
opts.imap_password = "pass"
@@ -2474,5 +2491,546 @@ password = test-password
self.assertNotIn("unmapped-1", report_ids)
class TestMaildirConnection(unittest.TestCase):
"""Tests for MaildirConnection subdirectory creation."""
def test_create_subdirs_when_missing(self):
"""maildir_create=True creates cur/new/tmp in an empty directory."""
from parsedmarc.mail.maildir import MaildirConnection
with TemporaryDirectory() as d:
for subdir in ("cur", "new", "tmp"):
self.assertFalse(os.path.exists(os.path.join(d, subdir)))
conn = MaildirConnection(d, maildir_create=True)
for subdir in ("cur", "new", "tmp"):
self.assertTrue(os.path.isdir(os.path.join(d, subdir)))
# Should be able to list messages without error
self.assertEqual(conn.fetch_messages("INBOX"), [])
def test_create_subdirs_idempotent(self):
"""maildir_create=True is safe when subdirs already exist."""
from parsedmarc.mail.maildir import MaildirConnection
with TemporaryDirectory() as d:
for subdir in ("cur", "new", "tmp"):
os.makedirs(os.path.join(d, subdir))
# Should not raise
conn = MaildirConnection(d, maildir_create=True)
self.assertEqual(conn.fetch_messages("INBOX"), [])
def test_no_create_raises_on_missing_subdirs(self):
"""maildir_create=False does not create subdirs; keys() fails."""
from parsedmarc.mail.maildir import MaildirConnection
with TemporaryDirectory() as d:
conn = MaildirConnection(d, maildir_create=False)
with self.assertRaises(FileNotFoundError):
conn.fetch_messages("INBOX")
def test_fetch_and_delete_message(self):
"""Round-trip: add a message, fetch it, delete it."""
from parsedmarc.mail.maildir import MaildirConnection
with TemporaryDirectory() as d:
conn = MaildirConnection(d, maildir_create=True)
# Add a message via the underlying client
msg_key = conn._client.add("From: test@example.com\n\nHello")
keys = conn.fetch_messages("INBOX")
self.assertIn(msg_key, keys)
content = conn.fetch_message(msg_key)
self.assertIn("test@example.com", content)
conn.delete_message(msg_key)
self.assertEqual(conn.fetch_messages("INBOX"), [])
def test_move_message_creates_subfolder(self):
"""move_message auto-creates the destination subfolder."""
from parsedmarc.mail.maildir import MaildirConnection
with TemporaryDirectory() as d:
conn = MaildirConnection(d, maildir_create=True)
msg_key = conn._client.add("From: test@example.com\n\nHello")
conn.move_message(msg_key, "archive")
# Original should be gone
self.assertEqual(conn.fetch_messages("INBOX"), [])
# Archive subfolder should have the message
self.assertIn("archive", conn._subfolder_client)
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."""
def test_uid_mismatch_warns_instead_of_crashing(self):
"""UID mismatch logs a warning instead of raising an exception."""
from parsedmarc.mail.maildir import MaildirConnection
with TemporaryDirectory() as d:
# Create subdirs so Maildir works
for subdir in ("cur", "new", "tmp"):
os.makedirs(os.path.join(d, subdir))
# Mock os.stat to return a different UID than os.getuid
fake_stat = os.stat(d)
with (
patch("parsedmarc.mail.maildir.os.stat") as mock_stat,
patch("parsedmarc.mail.maildir.os.getuid", return_value=9999),
):
mock_stat.return_value = fake_stat
# Should not raise — just warn
conn = MaildirConnection(d, maildir_create=False)
self.assertEqual(conn.fetch_messages("INBOX"), [])
def test_uid_match_no_warning(self):
"""No warning when UIDs match."""
from parsedmarc.mail.maildir import MaildirConnection
with TemporaryDirectory() as d:
conn = MaildirConnection(d, maildir_create=True)
self.assertEqual(conn.fetch_messages("INBOX"), [])
def test_stat_failure_does_not_crash(self):
"""If os.stat fails on the maildir path, we don't crash."""
from parsedmarc.mail.maildir import MaildirConnection
with TemporaryDirectory() as d:
for subdir in ("cur", "new", "tmp"):
os.makedirs(os.path.join(d, subdir))
original_stat = os.stat
def stat_that_fails_once(path, *args, **kwargs):
"""Fail on the first call (UID check), pass through after."""
stat_that_fails_once.calls += 1
if stat_that_fails_once.calls == 1:
raise OSError("no stat")
return original_stat(path, *args, **kwargs)
stat_that_fails_once.calls = 0
with patch(
"parsedmarc.mail.maildir.os.stat", side_effect=stat_that_fails_once
):
conn = MaildirConnection(d, maildir_create=False)
self.assertEqual(conn.fetch_messages("INBOX"), [])
class TestExpandPath(unittest.TestCase):
"""Tests for _expand_path config path expansion."""
def test_expand_tilde(self):
from parsedmarc.cli import _expand_path
result = _expand_path("~/some/path")
self.assertFalse(result.startswith("~"))
self.assertTrue(result.endswith("/some/path"))
def test_expand_env_var(self):
from parsedmarc.cli import _expand_path
with patch.dict(os.environ, {"PARSEDMARC_TEST_DIR": "/opt/data"}):
result = _expand_path("$PARSEDMARC_TEST_DIR/tokens/.token")
self.assertEqual(result, "/opt/data/tokens/.token")
def test_expand_both(self):
from parsedmarc.cli import _expand_path
with patch.dict(os.environ, {"MY_APP": "parsedmarc"}):
result = _expand_path("~/$MY_APP/config")
self.assertNotIn("~", result)
self.assertIn("parsedmarc/config", result)
def test_no_expansion_needed(self):
from parsedmarc.cli import _expand_path
self.assertEqual(_expand_path("/absolute/path"), "/absolute/path")
self.assertEqual(_expand_path("relative/path"), "relative/path")
class TestTokenParentDirCreation(unittest.TestCase):
"""Tests for parent directory creation when writing token files."""
def test_graph_cache_creates_parent_dirs(self):
from parsedmarc.mail.graph import _cache_auth_record
with TemporaryDirectory() as d:
token_path = Path(d) / "subdir" / "nested" / ".token"
self.assertFalse(token_path.parent.exists())
mock_record = MagicMock()
mock_record.serialize.return_value = "serialized-token"
_cache_auth_record(mock_record, token_path)
self.assertTrue(token_path.exists())
self.assertEqual(token_path.read_text(), "serialized-token")
def test_gmail_token_write_creates_parent_dirs(self):
"""Gmail token write creates parent directories."""
with TemporaryDirectory() as d:
token_path = Path(d) / "deep" / "nested" / "token.json"
self.assertFalse(token_path.parent.exists())
# Directly test the mkdir + open pattern
token_path.parent.mkdir(parents=True, exist_ok=True)
with token_path.open("w") as f:
f.write('{"token": "test"}')
self.assertTrue(token_path.exists())
self.assertEqual(token_path.read_text(), '{"token": "test"}')
class TestEnvVarConfig(unittest.TestCase):
"""Tests for environment variable configuration support."""
def test_resolve_section_key_simple(self):
"""Simple section names resolve correctly."""
from parsedmarc.cli import _resolve_section_key
self.assertEqual(_resolve_section_key("IMAP_PASSWORD"), ("imap", "password"))
self.assertEqual(_resolve_section_key("GENERAL_DEBUG"), ("general", "debug"))
self.assertEqual(_resolve_section_key("S3_BUCKET"), ("s3", "bucket"))
self.assertEqual(_resolve_section_key("GELF_HOST"), ("gelf", "host"))
def test_resolve_section_key_underscore_sections(self):
"""Multi-word section names (splunk_hec, gmail_api, etc.) resolve correctly."""
from parsedmarc.cli import _resolve_section_key
self.assertEqual(
_resolve_section_key("SPLUNK_HEC_TOKEN"), ("splunk_hec", "token")
)
self.assertEqual(
_resolve_section_key("GMAIL_API_CREDENTIALS_FILE"),
("gmail_api", "credentials_file"),
)
self.assertEqual(
_resolve_section_key("LOG_ANALYTICS_CLIENT_ID"),
("log_analytics", "client_id"),
)
def test_resolve_section_key_unknown(self):
"""Unknown prefixes return (None, None)."""
from parsedmarc.cli import _resolve_section_key
self.assertEqual(_resolve_section_key("UNKNOWN_FOO"), (None, None))
# Just a section name with no key should not match
self.assertEqual(_resolve_section_key("IMAP"), (None, None))
def test_apply_env_overrides_injects_values(self):
"""Env vars are injected into an existing ConfigParser."""
from configparser import ConfigParser
from parsedmarc.cli import _apply_env_overrides
config = ConfigParser()
config.add_section("imap")
config.set("imap", "host", "original.example.com")
env = {
"PARSEDMARC_IMAP_HOST": "new.example.com",
"PARSEDMARC_IMAP_PASSWORD": "secret123",
}
with patch.dict(os.environ, env, clear=False):
_apply_env_overrides(config)
self.assertEqual(config.get("imap", "host"), "new.example.com")
self.assertEqual(config.get("imap", "password"), "secret123")
def test_apply_env_overrides_creates_sections(self):
"""Env vars create new sections when they don't exist."""
from configparser import ConfigParser
from parsedmarc.cli import _apply_env_overrides
config = ConfigParser()
env = {"PARSEDMARC_ELASTICSEARCH_HOSTS": "http://localhost:9200"}
with patch.dict(os.environ, env, clear=False):
_apply_env_overrides(config)
self.assertTrue(config.has_section("elasticsearch"))
self.assertEqual(config.get("elasticsearch", "hosts"), "http://localhost:9200")
def test_apply_env_overrides_ignores_config_file_var(self):
"""PARSEDMARC_CONFIG_FILE is not injected as a config key."""
from configparser import ConfigParser
from parsedmarc.cli import _apply_env_overrides
config = ConfigParser()
env = {"PARSEDMARC_CONFIG_FILE": "/some/path.ini"}
with patch.dict(os.environ, env, clear=False):
_apply_env_overrides(config)
self.assertEqual(config.sections(), [])
def test_load_config_with_file_and_env_override(self):
"""Env vars override values from an INI file."""
from parsedmarc.cli import _load_config
with NamedTemporaryFile(mode="w", suffix=".ini", delete=False) as f:
f.write(
"[imap]\nhost = file.example.com\nuser = alice\npassword = fromfile\n"
)
f.flush()
config_path = f.name
try:
env = {"PARSEDMARC_IMAP_PASSWORD": "fromenv"}
with patch.dict(os.environ, env, clear=False):
config = _load_config(config_path)
self.assertEqual(config.get("imap", "host"), "file.example.com")
self.assertEqual(config.get("imap", "user"), "alice")
self.assertEqual(config.get("imap", "password"), "fromenv")
finally:
os.unlink(config_path)
def test_load_config_env_only(self):
"""Config can be loaded purely from env vars with no file."""
from parsedmarc.cli import _load_config
env = {
"PARSEDMARC_GENERAL_DEBUG": "true",
"PARSEDMARC_ELASTICSEARCH_HOSTS": "http://localhost:9200",
}
with patch.dict(os.environ, env, clear=False):
config = _load_config(None)
self.assertEqual(config.get("general", "debug"), "true")
self.assertEqual(config.get("elasticsearch", "hosts"), "http://localhost:9200")
def test_parse_config_from_env(self):
"""Full round-trip: env vars -> ConfigParser -> opts."""
from argparse import Namespace
from parsedmarc.cli import _load_config, _parse_config
env = {
"PARSEDMARC_GENERAL_DEBUG": "true",
"PARSEDMARC_GENERAL_SAVE_AGGREGATE": "true",
"PARSEDMARC_GENERAL_OFFLINE": "true",
}
with patch.dict(os.environ, env, clear=False):
config = _load_config(None)
opts = Namespace()
_parse_config(config, opts)
self.assertTrue(opts.debug)
self.assertTrue(opts.save_aggregate)
self.assertTrue(opts.offline)
def test_config_file_env_var(self):
"""PARSEDMARC_CONFIG_FILE env var specifies the config file path."""
from argparse import Namespace
from parsedmarc.cli import _load_config, _parse_config
with NamedTemporaryFile(mode="w", suffix=".ini", delete=False) as f:
f.write("[general]\ndebug = true\noffline = true\n")
f.flush()
config_path = f.name
try:
env = {"PARSEDMARC_CONFIG_FILE": config_path}
with patch.dict(os.environ, env, clear=False):
config = _load_config(os.environ.get("PARSEDMARC_CONFIG_FILE"))
opts = Namespace()
_parse_config(config, opts)
self.assertTrue(opts.debug)
self.assertTrue(opts.offline)
finally:
os.unlink(config_path)
def test_boolean_values_from_env(self):
"""Various boolean string representations work through ConfigParser."""
from configparser import ConfigParser
from parsedmarc.cli import _apply_env_overrides
for true_val in ("true", "yes", "1", "on", "True", "YES"):
config = ConfigParser()
env = {"PARSEDMARC_GENERAL_DEBUG": true_val}
with patch.dict(os.environ, env, clear=False):
_apply_env_overrides(config)
self.assertTrue(
config.getboolean("general", "debug"),
f"Expected truthy for {true_val!r}",
)
for false_val in ("false", "no", "0", "off", "False", "NO"):
config = ConfigParser()
env = {"PARSEDMARC_GENERAL_DEBUG": false_val}
with patch.dict(os.environ, env, clear=False):
_apply_env_overrides(config)
self.assertFalse(
config.getboolean("general", "debug"),
f"Expected falsy for {false_val!r}",
)
if __name__ == "__main__":
unittest.main(verbosity=2)