Compare commits

...

9 Commits

Author SHA1 Message Date
copilot-swe-agent[bot]
2eb91ed67d Address code review feedback on logging configuration
- Use exact type check (type(h) is logging.StreamHandler) instead of isinstance
  to avoid confusion with FileHandler subclass
- Catch specific exceptions (IOError, OSError, PermissionError) instead of
  bare Exception when creating FileHandler
- Kept logging.ERROR as default to maintain consistency with existing behavior

Co-authored-by: seanthegeek <44679+seanthegeek@users.noreply.github.com>
2025-12-29 19:50:26 +00:00
copilot-swe-agent[bot]
da2cf46765 Fix logging configuration propagation to child parser processes
- Add _configure_logging() helper function to set up logging in child processes
- Modified cli_parse() to accept log_level and log_file parameters
- Pass current logging configuration from parent to child processes
- Logging warnings/errors from child processes now properly display

Fixes issue where logging handlers in parent process were not inherited by
child processes created via multiprocessing.Process(). Child processes now
configure their own logging with the same settings as the parent.

Tested with sample files and confirmed warnings from DNS exceptions in child
processes are now visible.

Co-authored-by: seanthegeek <44679+seanthegeek@users.noreply.github.com>
2025-12-29 19:48:53 +00:00
copilot-swe-agent[bot]
359b2e9b8c Initial plan 2025-12-29 19:43:34 +00:00
Sean Whalen
eafa435868 Code cleanup 2025-12-29 14:32:05 -05:00
Sean Whalen
5d772c3b36 Bump version to 9.0.7 and update changelog with IMAP since option fix 2025-12-29 14:23:50 -05:00
Copilot
72cabbef23 Fix IMAP SEARCH SINCE date format to RFC 3501 DD-Mon-YYYY (#645)
* Initial plan

* Fix IMAP since option date format to use RFC 3501 compliant DD-Mon-YYYY format

Co-authored-by: seanthegeek <44679+seanthegeek@users.noreply.github.com>

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: seanthegeek <44679+seanthegeek@users.noreply.github.com>
2025-12-29 14:18:48 -05:00
Sean Whalen
3d74cd6ac0 Update CHANGELOG with issue reference for email read status
Added a reference to issue #625 regarding email read status.
2025-12-29 12:10:19 -05:00
Tomáš Kováčik
d1ac59a016 fix #641 (#642)
* fix smtptls and forensic reports for GELF

* add policy_domain, policy_type and failed_session_count to record row

* Remove unused import of json in gelf.py

---------

Co-authored-by: Sean Whalen <44679+seanthegeek@users.noreply.github.com>
2025-12-29 12:05:07 -05:00
Anael Mobilia
7fdd53008f Update README.md (#644) 2025-12-29 10:36:21 -05:00
6 changed files with 93 additions and 9 deletions

View File

@@ -1,5 +1,11 @@
# Changelog
## 9.0.7
## Fixes
- Fix IMAP `since` option (#PR 645 closes issues #581 and #643).
## 9.0.6
### Fixes
@@ -11,7 +17,7 @@
### Improvements
- Improve type hints across the library (Pylance/Pyright friendliness) and reduce false-positive linter errors.
- Emails in Microsoft 365 are now marked read as they are read. This provides constancy with other mailbox types, and gives you a indication of when emails are being read as they are processed in batches.
- Emails in Microsoft 365 are now marked read as they are read. This provides constancy with other mailbox types, and gives you a indication of when emails are being read as they are processed in batches. (Close #625)
### Compatibility / Dependencies

View File

@@ -61,4 +61,4 @@ for RHEL or Debian.
| 3.11 | ✅ | Actively maintained; supported until June 2028 (Debian 12) |
| 3.12 | ✅ | Actively maintained; supported until May 2035 (RHEL 10) |
| 3.13 | ✅ | Actively maintained; supported until June 2030 (Debian 13) |
| 3.14 | ❌ | Not currently supported due to Not currently supported due to [this imapclient bug](https://github.com/mjs/imapclient/issues/618)|
| 3.14 | ❌ | Not currently supported due to [this imapclient bug](https://github.com/mjs/imapclient/issues/618)|

View File

@@ -595,9 +595,12 @@ def parsed_smtp_tls_reports_to_csv_rows(
if "mx_host_patterns" in policy:
record["mx_host_patterns"] = "|".join(policy["mx_host_patterns"])
successful_record = record.copy()
successful_record["policy_domain"] = policy["policy_domain"]
successful_record["policy_type"] = policy["policy_type"]
successful_record["successful_session_count"] = policy[
"successful_session_count"
]
successful_record["failed_session_count"] = policy["failed_session_count"]
rows.append(successful_record)
if "failure_details" in policy:
for failure_details in policy["failure_details"]:
@@ -1939,8 +1942,10 @@ def get_dmarc_reports_from_mailbox(
"Only days and weeks values in 'since' option are \
considered for IMAP connections. Examples: 2d or 1w"
)
since = (datetime.now(timezone.utc) - timedelta(minutes=_since)).date()
current_time = datetime.now(timezone.utc).date()
since = (datetime.now(timezone.utc) - timedelta(minutes=_since)).strftime(
"%d-%b-%Y"
)
current_time = datetime.now(timezone.utc).strftime("%d-%b-%Y")
elif isinstance(connection, MSGraphConnection):
since = (
datetime.now(timezone.utc) - timedelta(minutes=_since)

View File

@@ -67,6 +67,51 @@ def _str_to_list(s):
return list(map(lambda i: i.lstrip(), _list))
def _configure_logging(log_level, log_file=None):
"""
Configure logging for the current process.
This is needed for child processes to properly log messages.
Args:
log_level: The logging level (e.g., logging.DEBUG, logging.WARNING)
log_file: Optional path to log file
"""
# Get the logger
from parsedmarc.log import logger
# Set the log level
logger.setLevel(log_level)
# Add StreamHandler with formatter if not already present
# Check if we already have a StreamHandler to avoid duplicates
# Use exact type check to distinguish from FileHandler subclass
has_stream_handler = any(
type(h) is logging.StreamHandler
for h in logger.handlers
)
if not has_stream_handler:
formatter = logging.Formatter(
fmt="%(levelname)8s:%(filename)s:%(lineno)d:%(message)s",
datefmt="%Y-%m-%d:%H:%M:%S",
)
handler = logging.StreamHandler()
handler.setFormatter(formatter)
logger.addHandler(handler)
# Add FileHandler if log_file is specified
if log_file:
try:
fh = logging.FileHandler(log_file, "a")
formatter = logging.Formatter(
"%(asctime)s - %(levelname)s - [%(filename)s:%(lineno)d] - %(message)s"
)
fh.setFormatter(formatter)
logger.addHandler(fh)
except (IOError, OSError, PermissionError) as error:
logger.warning("Unable to write to log file: {}".format(error))
def cli_parse(
file_path,
sa,
@@ -79,8 +124,29 @@ def cli_parse(
reverse_dns_map_url,
normalize_timespan_threshold_hours,
conn,
log_level=logging.ERROR,
log_file=None,
):
"""Separated this function for multiprocessing"""
"""Separated this function for multiprocessing
Args:
file_path: Path to the report file
sa: Strip attachment payloads flag
nameservers: List of nameservers
dns_timeout: DNS timeout
ip_db_path: Path to IP database
offline: Offline mode flag
always_use_local_files: Always use local files flag
reverse_dns_map_path: Path to reverse DNS map
reverse_dns_map_url: URL to reverse DNS map
normalize_timespan_threshold_hours: Timespan threshold
conn: Pipe connection for IPC
log_level: Logging level for this process
log_file: Optional path to log file
"""
# Configure logging in this child process
_configure_logging(log_level, log_file)
try:
file_results = parse_report_file(
file_path,
@@ -1461,6 +1527,10 @@ def _main():
if n_procs < 1:
n_procs = 1
# Capture the current log level to pass to child processes
current_log_level = logger.level
current_log_file = opts.log_file
for batch_index in range((len(file_paths) + n_procs - 1) // n_procs):
processes = []
connections = []
@@ -1486,6 +1556,8 @@ def _main():
opts.reverse_dns_map_url,
opts.normalize_timespan_threshold_hours,
child_conn,
current_log_level,
current_log_file,
),
)
processes.append(process)

View File

@@ -1,3 +1,3 @@
__version__ = "9.0.6"
__version__ = "9.0.7"
USER_AGENT = f"parsedmarc/{__version__}"

View File

@@ -2,7 +2,6 @@
from __future__ import annotations
import json
import logging
import logging.handlers
import threading
@@ -62,9 +61,11 @@ class GelfClient(object):
def save_forensic_report_to_gelf(self, forensic_reports: list[dict[str, Any]]):
rows = parsed_forensic_reports_to_csv_rows(forensic_reports)
for row in rows:
self.logger.info(json.dumps(row))
log_context_data.parsedmarc = row
self.logger.info("parsedmarc forensic report")
def save_smtp_tls_report_to_gelf(self, smtp_tls_reports: dict[str, Any]):
rows = parsed_smtp_tls_reports_to_csv_rows(smtp_tls_reports)
for row in rows:
self.logger.info(json.dumps(row))
log_context_data.parsedmarc = row
self.logger.info("parsedmarc smtptls report")