Add offline mode for tests in GitHub Actions to skip DNS lookups

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

.github/workflows/python-tests.yml

@@ -30,7 +30,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.9", "3.10", "3.11", "3.12", "3.13"]
+        python-version: ["3.9", "3.10", "3.11", "3.12", "3.13", "3.14"]
 
     steps:
     - uses: actions/checkout@v5

CHANGELOG.md

@@ -1,5 +1,22 @@
 # Changelog
 
+## 9.0.10
+
+- Support Python 3.14+
+
+## 9.0.9
+
+### Fixes
+
+- Validate that a string is base64-encoded before trying to base64 decode it. (PRs #648 and #649)
+
+## 9.0.8
+
+### Fixes
+
+- Fix logging configuration not propagating to child parser processes (#646).
+- Update `mailsuite` dependency to `?=1.11.1` to solve issues with iCloud IMAP (#493).
+
 ## 9.0.7
 
 ## Fixes

README.md

@@ -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 [this imapclient bug](https://github.com/mjs/imapclient/issues/618)|
+| 3.14    | ✅         | Actively maintained                                        |

ci.ini

@@ -3,6 +3,7 @@ save_aggregate = True
 save_forensic = True
 save_smtp_tls = True
 debug = True
+offline = True
 
 [elasticsearch]
 hosts = http://localhost:9200

docs/source/index.md

@@ -61,7 +61,7 @@ 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 [this imapclient bug](https://github.com/mjs/imapclient/issues/618)|
+| 3.14    | ✅         | Actively maintained                                        |
 
 ```{toctree}
 :caption: 'Contents'

parsedmarc/__init__.py

@@ -751,8 +751,8 @@ def parse_aggregate_report_xml(
         new_report_metadata["report_id"] = report_id
         date_range = report["report_metadata"]["date_range"]
 
-        begin_ts = int(date_range["begin"])
+        begin_ts = int(date_range["begin"].split(".")[0])
-        end_ts = int(date_range["end"])
+        end_ts = int(date_range["end"].split(".")[0])
         span_seconds = end_ts - begin_ts
 
         normalize_timespan = span_seconds > normalize_timespan_threshold_hours * 3600
@@ -892,7 +892,11 @@ def extract_report(content: Union[bytes, str, BinaryIO]) -> str:
     try:
         if isinstance(content, str):
             try:
-                file_object = BytesIO(b64decode(content))
+                file_object = BytesIO(
+                    b64decode(
+                        content.replace("\n", "").replace("\r", ""), validate=True
+                    )
+                )
             except binascii.Error:
                 return content
             header = file_object.read(6)

parsedmarc/cli.py

@@ -46,6 +46,7 @@ from parsedmarc.mail import (
     MSGraphConnection,
 )
 from parsedmarc.mail.graph import AuthMethod
+from parsedmarc.types import ParsingResults
 from parsedmarc.utils import get_base_domain, get_reverse_dns, is_mbox
 
 # Increase the max header limit for very large emails. `_MAXHEADERS` is a
@@ -67,6 +68,48 @@ 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 +122,29 @@ 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 +1525,10 @@ 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 +1554,8 @@ def _main():
                     opts.reverse_dns_map_url,
                     opts.normalize_timespan_threshold_hours,
                     child_conn,
+                    current_log_level,
+                    current_log_file,
                 ),
             )
             processes.append(process)
@@ -1688,13 +1758,13 @@ def _main():
             logger.exception("Mailbox Error")
             exit(1)
 
-    results = {
+    parsing_results: ParsingResults = {
         "aggregate_reports": aggregate_reports,
         "forensic_reports": forensic_reports,
         "smtp_tls_reports": smtp_tls_reports,
     }
 
-    process_reports(results)
+    process_reports(parsing_results)
 
     if opts.smtp_host:
         try:
@@ -1708,7 +1778,7 @@ def _main():
                 else _str_to_list(str(opts.smtp_to))
             )
             email_results(
-                results,
+                parsing_results,
                 opts.smtp_host,
                 opts.smtp_from,
                 smtp_to_value,

parsedmarc/constants.py

@@ -1,3 +1,3 @@
-__version__ = "9.0.7"
+__version__ = "9.0.10"
 
 USER_AGENT = f"parsedmarc/{__version__}"

pyproject.toml

@@ -29,7 +29,7 @@ classifiers = [
     "Operating System :: OS Independent",
     "Programming Language :: Python :: 3"
 ]
-requires-python = ">=3.9, <3.14"
+requires-python = ">=3.9"
 dependencies = [
     "azure-identity>=1.8.0",
     "azure-monitor-ingestion>=1.0.0",
@@ -48,7 +48,7 @@ dependencies = [
     "imapclient>=2.1.0",
     "kafka-python-ng>=2.2.2",
     "lxml>=4.4.0",
-    "mailsuite>=1.11.0",
+    "mailsuite>=1.11.2",
     "msgraph-core==0.2.2",
     "opensearch-py>=2.4.2,<=3.0.0",
     "publicsuffixlist>=0.10.0",

tests.py

@@ -12,6 +12,9 @@ from lxml import etree
 import parsedmarc
 import parsedmarc.utils
 
+# Detect if running in GitHub Actions to skip DNS lookups
+OFFLINE_MODE = os.environ.get("GITHUB_ACTIONS", "false").lower() == "true"
+
 
 def minify_xml(xml_string):
     parser = etree.XMLParser(remove_blank_text=True)
@@ -121,7 +124,7 @@ class Test(unittest.TestCase):
                 continue
             print("Testing {0}: ".format(sample_path), end="")
             parsed_report = parsedmarc.parse_report_file(
-                sample_path, always_use_local_files=True
+                sample_path, always_use_local_files=True, offline=OFFLINE_MODE
             )["report"]
             parsedmarc.parsed_aggregate_reports_to_csv(parsed_report)
             print("Passed!")
@@ -129,7 +132,7 @@ class Test(unittest.TestCase):
     def testEmptySample(self):
         """Test empty/unparasable report"""
         with self.assertRaises(parsedmarc.ParserError):
-            parsedmarc.parse_report_file("samples/empty.xml")
+            parsedmarc.parse_report_file("samples/empty.xml", offline=OFFLINE_MODE)
 
     def testForensicSamples(self):
         """Test sample forensic/ruf/failure DMARC reports"""
@@ -139,8 +142,12 @@ class Test(unittest.TestCase):
             print("Testing {0}: ".format(sample_path), end="")
             with open(sample_path) as sample_file:
                 sample_content = sample_file.read()
-                parsed_report = parsedmarc.parse_report_email(sample_content)["report"]
+                parsed_report = parsedmarc.parse_report_email(
-            parsed_report = parsedmarc.parse_report_file(sample_path)["report"]
+                    sample_content, offline=OFFLINE_MODE
+                )["report"]
+            parsed_report = parsedmarc.parse_report_file(
+                sample_path, offline=OFFLINE_MODE
+            )["report"]
             parsedmarc.parsed_forensic_reports_to_csv(parsed_report)
             print("Passed!")
 
@@ -152,7 +159,9 @@ class Test(unittest.TestCase):
             if os.path.isdir(sample_path):
                 continue
             print("Testing {0}: ".format(sample_path), end="")
-            parsed_report = parsedmarc.parse_report_file(sample_path)["report"]
+            parsed_report = parsedmarc.parse_report_file(
+                sample_path, offline=OFFLINE_MODE
+            )["report"]
             parsedmarc.parsed_smtp_tls_reports_to_csv(parsed_report)
             print("Passed!")