Better wording

- Fix since option to correctly work with weeks (PR #604)
- Add 183 entries to `base_reverse_dns_map.csv`
- Add 57 entries to `known_unknown_base_reverse_dns.txt`
- Check for invalid UTF-8 bytes in `base_reverse_dns_map.csv` at build
- Remove unneeded items from the `parsedmarc.resources` module at build

.github/workflows/python-tests.yml

@@ -11,13 +11,26 @@ on:
 
 jobs:
   build:
-
     runs-on: ubuntu-latest
 
+    services:
+      elasticsearch:
+        image: elasticsearch:8.18.2
+        env:
+          discovery.type: single-node
+          cluster.name: parsedmarc-cluster
+          discovery.seed_hosts: elasticsearch
+          bootstrap.memory_lock: true
+          xpack.security.enabled: false
+          xpack.license.self_generated.type: basic
+        ports:
+          - 9200:9200
+          - 9300:9300
+
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
+        python-version: ["3.9", "3.10", "3.11", "3.12"]
 
     steps:
     - uses: actions/checkout@v4
@@ -29,13 +42,6 @@ jobs:
       run: |
         sudo apt-get update
         sudo apt-get install -y libemail-outlook-message-perl
-        wget -qO - https://artifacts.elastic.co/GPG-KEY-elasticsearch | sudo gpg --dearmor -o /usr/share/keyrings/elasticsearch-keyring.gpg
-        sudo apt-get install apt-transport-https
-        echo "deb [signed-by=/usr/share/keyrings/elasticsearch-keyring.gpg] https://artifacts.elastic.co/packages/8.x/apt stable main" | sudo tee /etc/apt/sources.list.d/elastic-8.x.list
-        sudo apt-get update && sudo apt-get install elasticsearch
-        sudo sed -i 's/xpack.security.enabled: true/xpack.security.enabled: false/' /etc/elasticsearch/elasticsearch.yml
-        sudo systemctl restart elasticsearch
-        sudo systemctl --no-pager status elasticsearch
     - name: Install Python dependencies
       run: |
         python -m pip install --upgrade pip

.gitignore

@@ -136,3 +136,10 @@ samples/private
 
 *.html
 *.sqlite-journal
+
+parsedmarc.ini
+scratch.py
+
+parsedmarc/resources/maps/base_reverse_dns.csv
+parsedmarc/resources/maps/unknown_base_reverse_dns.csv
+*.bak

.vscode/settings.json

@@ -13,6 +13,7 @@
         "automodule",
         "backported",
         "bellsouth",
+        "boto",
         "brakhane",
         "Brightmail",
         "CEST",
@@ -36,6 +37,7 @@
         "expiringdict",
         "fieldlist",
         "genindex",
+        "geoip",
         "geoipupdate",
         "Geolite",
         "geolocation",
@@ -44,7 +46,10 @@
         "hostnames",
         "htpasswd",
         "httpasswd",
+        "httplib",
         "IMAP",
+        "imapclient",
+        "infile",
         "Interaktive",
         "IPDB",
         "journalctl",
@@ -70,6 +75,7 @@
         "modindex",
         "msgconvert",
         "msgraph",
+        "MSSP",
         "Munge",
         "ndjson",
         "newkey",
@@ -79,14 +85,18 @@
         "nosecureimap",
         "nosniff",
         "nwettbewerb",
+        "opensearch",
         "parsedmarc",
         "passsword",
         "Postorius",
         "premade",
         "procs",
         "publicsuffix",
+        "publicsuffixlist",
         "publixsuffix",
+        "pygelf",
         "pypy",
+        "pytest",
         "quickstart",
         "Reindex",
         "replyto",
@@ -94,10 +104,12 @@
         "Rollup",
         "Rpdm",
         "SAMEORIGIN",
+        "sdist",
         "Servernameone",
         "setuptools",
         "smartquotes",
         "SMTPTLS",
+        "sortmaps",
         "sourcetype",
         "STARTTLS",
         "tasklist",

CHANGELOG.md

@@ -1,6 +1,74 @@
 Changelog
 =========
 
+8.18.6
+------
+
+- Fix since option to correctly work with weeks (PR #604)
+- Add 183 entries to `base_reverse_dns_map.csv`
+- Add 57 entries to `known_unknown_base_reverse_dns.txt`
+- Check for invalid UTF-8 bytes in `base_reverse_dns_map.csv` at build
+- Exclude unneeded items from the `parsedmarc.resources` module at build
+
+8.18.5
+------
+
+- Fix CSV download
+
+8.18.4
+------
+
+- Fix webhooks
+
+8.18.3
+------
+
+- Move `__version__` to `parsedmarc.constants`
+- Create a constant `USER_AGENT`
+- Use the HTTP `User-Agent` header value `parsedmarc/version` for all HTTP requests
+
+8.18.2
+------
+
+- Merged PR #603
+  - Fixes issue #595 - CI test fails for Elasticsearch
+    - Moved Elasticsearch to a separate Docker service container for CI testing
+    - Dropped Python 3.8 from CI testing
+  - Fixes lookup and saving of DMARC forensic reports in Elasticsearch and OpenSearch
+- Updated fallback `base_reverse_dns_map.csv`, which now includes over 1,400 lines
+- Updated included `dbip-country-lite.mmdb` to the June 2025 release
+- Automatically fall back to the internal `base_reverse_dns_map.csv` if the received file is not valid (Fixes #602)
+  - Print the received data to the debug log
+
+8.18.1
+------
+
+- Add missing `https://` to the default Microsoft Graph URL
+
+8.18.0
+------
+
+- Add support for Microsoft national clouds via Graph API base URL (PR #590)
+- Avoid stopping processing when an invalid DMARC report is encountered (PR #587)
+- Increase `http.client._MAXHEADERS` from `100` to `200` to avoid errors connecting to Elasticsearch/OpenSearch (PR #589)
+
+8.17.0
+------
+
+- Ignore duplicate aggregate DMARC reports with the same `org_name` and `report_id` seen within the same hour (Fixes #535)
+- Fix saving SMTP TLS reports to OpenSearch (PR #585 closed issue #576)
+- Add 303 entries to `base_reverse_dns_map.csv`
+
+8.16.1
+------
+
+- Failed attempt to ignore aggregate DMARC reports seen within a period of one hour (#535)
+
+8.16.0
+------
+
+- Add a `since` option to only search for emails since a certain time (PR #527)
+
 8.15.4
 ------
 
@@ -634,7 +702,7 @@ in the ``elasticsearch`` configuration file section (closes issue #78)
 -----
 
 - Add filename and line number to logging output
-- Improved IMAP error handling  
+- Improved IMAP error handling
 - Add CLI options
 
   ```text

README.md

@@ -42,6 +42,6 @@ Thanks to all
 - Consistent data structures
 - Simple JSON and/or CSV output
 - Optionally email the results
-- Optionally send the results to Elasticsearch and/or Splunk, for use
+- Optionally send the results to Elasticsearch, Opensearch, and/or Splunk, for use
     with premade dashboards
 - Optionally send reports to Apache Kafka

build.sh

@@ -14,8 +14,15 @@ cd docs
 make clean 
 make html
 touch build/html/.nojekyll
-cp -rf build/html/* ../../parsedmarc-docs/
+if [  -d "./../parsedmarc-docs" ]; then
+  cp -rf build/html/* ../../parsedmarc-docs/
+fi
 cd ..
+cd parsedmarc/resources/maps
+python3 sortmaps.py
+echo "Checking for invalid UTF-8 bytes in base_reverse_dns_map.csv"
+python3 find_bad_utf8.py base_reverse_dns_map.csv
+cd ../../..
 python3 tests.py
 rm -rf dist/ build/
-hatch build
+hatch build

docker-compose.yml

@@ -28,3 +28,30 @@ services:
       interval: 10s
       timeout: 10s
       retries: 24
+
+  opensearch:
+    image: opensearchproject/opensearch:2.18.0
+    environment:
+      - network.host=127.0.0.1
+      - http.host=0.0.0.0
+      - node.name=opensearch
+      - discovery.type=single-node
+      - cluster.name=parsedmarc-cluster
+      - discovery.seed_hosts=opensearch
+      - bootstrap.memory_lock=true
+      - OPENSEARCH_INITIAL_ADMIN_PASSWORD=${OPENSEARCH_INITIAL_ADMIN_PASSWORD}
+    ports:
+      - 127.0.0.1:9201:9200
+    ulimits:
+      memlock:
+        soft: -1
+        hard: -1
+    healthcheck:
+      test:
+        [
+          "CMD-SHELL",
+          "curl -s -XGET http://localhost:9201/_cluster/health?pretty | grep status | grep -q '\\(green\\|yellow\\)'"
+        ]
+      interval: 10s
+      timeout: 10s
+      retries: 24

docs/source/usage.md

@@ -208,6 +208,8 @@ The full set of configuration options are:
   - `mailbox` - str: The mailbox name. This defaults to the
       current user if using the UsernamePassword auth method, but
       could be a shared mailbox if the user has access to the mailbox
+  - `graph_url` - str: Microsoft Graph URL.  Allows for use of National Clouds (ex Azure Gov)
+      (Default: https://graph.microsoft.com)
   - `token_file` - str: Path to save the token file
       (Default: `.token`)
   - `allow_unencrypted_storage` - bool: Allows the Azure Identity
@@ -367,7 +369,7 @@ The full set of configuration options are:
   - `mode` - str: The GELF transport type to use. Valid modes: `tcp`, `udp`, `tls`
 
 - `maildir`
-  - `reports_folder` - str: Full path for mailbox maidir location (Default: `INBOX`)
+  - `maildir_path` - str: Full path for mailbox maidir location (Default: `INBOX`)
   - `maildir_create` - bool: Create maildir if not present (Default: False)
 
 - `webhook` - Post the individual reports to a webhook url with the report as the JSON body

parsedmarc/__init__.py

@@ -34,12 +34,13 @@ from parsedmarc.mail import (
     MSGraphConnection,
     GmailConnection,
 )
+
+from parsedmarc.constants import __version__
 from parsedmarc.utils import get_base_domain, get_ip_address_info
 from parsedmarc.utils import is_outlook_msg, convert_outlook_msg
 from parsedmarc.utils import parse_email
 from parsedmarc.utils import timestamp_to_human, human_timestamp_to_datetime
 
-__version__ = "8.15.4"
 
 logger.debug("parsedmarc v{0}".format(__version__))
 
@@ -54,6 +55,7 @@ MAGIC_XML = b"\x3c\x3f\x78\x6d\x6c\x20"
 MAGIC_JSON = b"\7b"
 
 IP_ADDRESS_CACHE = ExpiringDict(max_len=10000, max_age_seconds=14400)
+SEEN_AGGREGATE_REPORT_IDS = ExpiringDict(max_len=100000000, max_age_seconds=3600)
 REVERSE_DNS_MAP = dict()
 
 
@@ -271,7 +273,7 @@ def _parse_smtp_tls_failure_details(failure_details):
         return new_failure_details
 
     except KeyError as e:
-        raise InvalidSMTPTLSReport(f"Missing required failure details field:" f" {e}")
+        raise InvalidSMTPTLSReport(f"Missing required failure details field: {e}")
     except Exception as e:
         raise InvalidSMTPTLSReport(str(e))
 
@@ -283,7 +285,7 @@ def _parse_smtp_tls_report_policy(policy):
         policy_type = policy["policy"]["policy-type"]
         failure_details = []
         if policy_type not in policy_types:
-            raise InvalidSMTPTLSReport(f"Invalid policy type " f"{policy_type}")
+            raise InvalidSMTPTLSReport(f"Invalid policy type {policy_type}")
         new_policy = OrderedDict(policy_domain=policy_domain, policy_type=policy_type)
         if "policy-string" in policy["policy"]:
             if isinstance(policy["policy"]["policy-string"], list):
@@ -331,9 +333,7 @@ def parse_smtp_tls_report_json(report):
                 raise Exception(f"Missing required field: {required_field}]")
         if not isinstance(report["policies"], list):
             policies_type = type(report["policies"])
-            raise InvalidSMTPTLSReport(
-                f"policies must be a list, " f"not {policies_type}"
-            )
+            raise InvalidSMTPTLSReport(f"policies must be a list, not {policies_type}")
         for policy in report["policies"]:
             policies.append(_parse_smtp_tls_report_policy(policy))
 
@@ -1245,11 +1245,11 @@ def parse_report_email(
                         field_name = match[0].lower().replace(" ", "-")
                         fields[field_name] = match[1].strip()
 
-                    feedback_report = "Arrival-Date: {}\n" "Source-IP: {}" "".format(
+                    feedback_report = "Arrival-Date: {}\nSource-IP: {}".format(
                         fields["received-date"], fields["sender-ip-address"]
                     )
                 except Exception as e:
-                    error = "Unable to parse message with " 'subject "{0}": {1}'.format(
+                    error = 'Unable to parse message with subject "{0}": {1}'.format(
                         subject, e
                     )
                     raise InvalidDMARCReport(error)
@@ -1293,10 +1293,10 @@ def parse_report_email(
                     "is not a valid "
                     "aggregate DMARC report: {1}".format(subject, e)
                 )
-                raise ParserError(error)
+                raise InvalidDMARCReport(error)
 
             except Exception as e:
-                error = "Unable to parse message with " 'subject "{0}": {1}'.format(
+                error = 'Unable to parse message with subject "{0}": {1}'.format(
                     subject, e
                 )
                 raise ParserError(error)
@@ -1330,7 +1330,7 @@ def parse_report_email(
         return result
 
     if result is None:
-        error = 'Message with subject "{0}" is ' "not a valid report".format(subject)
+        error = 'Message with subject "{0}" is not a valid report'.format(subject)
         raise InvalidDMARCReport(error)
 
 
@@ -1470,7 +1470,17 @@ def get_dmarc_reports_from_mbox(
                     strip_attachment_payloads=sa,
                 )
                 if parsed_email["report_type"] == "aggregate":
-                    aggregate_reports.append(parsed_email["report"])
+                    report_org = parsed_email["report"]["report_metadata"]["org_name"]
+                    report_id = parsed_email["report"]["report_metadata"]["report_id"]
+                    report_key = f"{report_org}_{report_id}"
+                    if report_key not in SEEN_AGGREGATE_REPORT_IDS:
+                        SEEN_AGGREGATE_REPORT_IDS[report_key] = True
+                        aggregate_reports.append(parsed_email["report"])
+                    else:
+                        logger.debug(
+                            "Skipping duplicate aggregate report "
+                            f"from {report_org} with ID: {report_id}"
+                        )
                 elif parsed_email["report_type"] == "forensic":
                     forensic_reports.append(parsed_email["report"])
                 elif parsed_email["report_type"] == "smtp_tls":
@@ -1570,7 +1580,7 @@ def get_dmarc_reports_from_mailbox(
 
     if since:
         _since = 1440  # default one day
-        if re.match(r"\d+[mhd]$", since):
+        if re.match(r"\d+[mhdw]$", since):
             s = re.split(r"(\d+)", since)
             if s[2] == "m":
                 _since = int(s[1])
@@ -1647,7 +1657,16 @@ def get_dmarc_reports_from_mailbox(
                 keep_alive=connection.keepalive,
             )
             if parsed_email["report_type"] == "aggregate":
-                aggregate_reports.append(parsed_email["report"])
+                report_org = parsed_email["report"]["report_metadata"]["org_name"]
+                report_id = parsed_email["report"]["report_metadata"]["report_id"]
+                report_key = f"{report_org}_{report_id}"
+                if report_key not in SEEN_AGGREGATE_REPORT_IDS:
+                    SEEN_AGGREGATE_REPORT_IDS[report_key] = True
+                    aggregate_reports.append(parsed_email["report"])
+                else:
+                    logger.debug(
+                        f"Skipping duplicate aggregate report with ID: {report_id}"
+                    )
                 aggregate_report_msg_uids.append(msg_uid)
             elif parsed_email["report_type"] == "forensic":
                 forensic_reports.append(parsed_email["report"])
@@ -1688,7 +1707,7 @@ def get_dmarc_reports_from_mailbox(
 
                 except Exception as e:
                     message = "Error deleting message UID"
-                    e = "{0} {1}: " "{2}".format(message, msg_uid, e)
+                    e = "{0} {1}: {2}".format(message, msg_uid, e)
                     logger.error("Mailbox error: {0}".format(e))
         else:
             if len(aggregate_report_msg_uids) > 0:

parsedmarc/cli.py

@@ -14,6 +14,7 @@ import json
 from ssl import CERT_NONE, create_default_context
 from multiprocessing import Pipe, Process
 import sys
+import http.client
 from tqdm import tqdm
 
 from parsedmarc import (
@@ -46,6 +47,9 @@ from parsedmarc.mail.graph import AuthMethod
 
 from parsedmarc.log import logger
 from parsedmarc.utils import is_mbox, get_reverse_dns
+from parsedmarc import SEEN_AGGREGATE_REPORT_IDS
+
+http.client._MAXHEADERS = 200  # pylint:disable=protected-access
 
 formatter = logging.Formatter(
     fmt="%(levelname)8s:%(filename)s:%(lineno)d:%(message)s",
@@ -395,7 +399,7 @@ def _main():
     arg_parser.add_argument(
         "-c",
         "--config-file",
-        help="a path to a configuration file " "(--silent implied)",
+        help="a path to a configuration file (--silent implied)",
     )
     arg_parser.add_argument(
         "file_path",
@@ -403,7 +407,7 @@ def _main():
         help="one or more paths to aggregate or forensic "
         "report files, emails, or mbox files'",
     )
-    strip_attachment_help = "remove attachment payloads from forensic " "report output"
+    strip_attachment_help = "remove attachment payloads from forensic report output"
     arg_parser.add_argument(
         "--strip-attachment-payloads", help=strip_attachment_help, action="store_true"
     )
@@ -446,14 +450,14 @@ def _main():
     arg_parser.add_argument(
         "-t",
         "--dns_timeout",
-        help="number of seconds to wait for an answer " "from DNS (default: 2.0)",
+        help="number of seconds to wait for an answer from DNS (default: 2.0)",
         type=float,
         default=2.0,
     )
     arg_parser.add_argument(
         "--offline",
         action="store_true",
-        help="do not make online queries for geolocation " " or  DNS",
+        help="do not make online queries for geolocation  or  DNS",
     )
     arg_parser.add_argument(
         "-s", "--silent", action="store_true", help="only print errors"
@@ -527,6 +531,7 @@ def _main():
         graph_tenant_id=None,
         graph_mailbox=None,
         graph_allow_unencrypted_storage=False,
+        graph_url="https://graph.microsoft.com",
         hec=None,
         hec_token=None,
         hec_index=None,
@@ -729,7 +734,7 @@ def _main():
             if "host" in imap_config:
                 opts.imap_host = imap_config["host"]
             else:
-                logger.error("host setting missing from the " "imap config section")
+                logger.error("host setting missing from the imap config section")
                 exit(-1)
             if "port" in imap_config:
                 opts.imap_port = imap_config.getint("port")
@@ -745,14 +750,12 @@ def _main():
             if "user" in imap_config:
                 opts.imap_user = imap_config["user"]
             else:
-                logger.critical("user setting missing from the " "imap config section")
+                logger.critical("user setting missing from the imap config section")
                 exit(-1)
             if "password" in imap_config:
                 opts.imap_password = imap_config["password"]
             else:
-                logger.critical(
-                    "password setting missing from the " "imap config section"
-                )
+                logger.critical("password setting missing from the imap config section")
                 exit(-1)
             if "reports_folder" in imap_config:
                 opts.mailbox_reports_folder = imap_config["reports_folder"]
@@ -821,21 +824,20 @@ def _main():
                     opts.graph_user = graph_config["user"]
                 else:
                     logger.critical(
-                        "user setting missing from the " "msgraph config section"
+                        "user setting missing from the msgraph config section"
                     )
                     exit(-1)
                 if "password" in graph_config:
                     opts.graph_password = graph_config["password"]
                 else:
                     logger.critical(
-                        "password setting missing from the " "msgraph config section"
+                        "password setting missing from the msgraph config section"
                     )
                 if "client_secret" in graph_config:
                     opts.graph_client_secret = graph_config["client_secret"]
                 else:
                     logger.critical(
-                        "client_secret setting missing from the "
-                        "msgraph config section"
+                        "client_secret setting missing from the msgraph config section"
                     )
                     exit(-1)
 
@@ -848,7 +850,7 @@ def _main():
                     opts.graph_tenant_id = graph_config["tenant_id"]
                 else:
                     logger.critical(
-                        "tenant_id setting missing from the " "msgraph config section"
+                        "tenant_id setting missing from the msgraph config section"
                     )
                     exit(-1)
 
@@ -857,8 +859,7 @@ def _main():
                     opts.graph_client_secret = graph_config["client_secret"]
                 else:
                     logger.critical(
-                        "client_secret setting missing from the "
-                        "msgraph config section"
+                        "client_secret setting missing from the msgraph config section"
                     )
                     exit(-1)
 
@@ -866,7 +867,7 @@ def _main():
                 opts.graph_client_id = graph_config["client_id"]
             else:
                 logger.critical(
-                    "client_id setting missing from the " "msgraph config section"
+                    "client_id setting missing from the msgraph config section"
                 )
                 exit(-1)
 
@@ -874,10 +875,13 @@ def _main():
                 opts.graph_mailbox = graph_config["mailbox"]
             elif opts.graph_auth_method != AuthMethod.UsernamePassword.name:
                 logger.critical(
-                    "mailbox setting missing from the " "msgraph config section"
+                    "mailbox setting missing from the msgraph config section"
                 )
                 exit(-1)
 
+            if "graph_url" in graph_config:
+                opts.graph_url = graph_config["graph_url"]
+
             if "allow_unencrypted_storage" in graph_config:
                 opts.graph_allow_unencrypted_storage = graph_config.getboolean(
                     "allow_unencrypted_storage"
@@ -889,7 +893,7 @@ def _main():
                 opts.elasticsearch_hosts = _str_to_list(elasticsearch_config["hosts"])
             else:
                 logger.critical(
-                    "hosts setting missing from the " "elasticsearch config section"
+                    "hosts setting missing from the elasticsearch config section"
                 )
                 exit(-1)
             if "timeout" in elasticsearch_config:
@@ -927,7 +931,7 @@ def _main():
                 opts.opensearch_hosts = _str_to_list(opensearch_config["hosts"])
             else:
                 logger.critical(
-                    "hosts setting missing from the " "opensearch config section"
+                    "hosts setting missing from the opensearch config section"
                 )
                 exit(-1)
             if "timeout" in opensearch_config:
@@ -963,21 +967,21 @@ def _main():
                 opts.hec = hec_config["url"]
             else:
                 logger.critical(
-                    "url setting missing from the " "splunk_hec config section"
+                    "url setting missing from the splunk_hec config section"
                 )
                 exit(-1)
             if "token" in hec_config:
                 opts.hec_token = hec_config["token"]
             else:
                 logger.critical(
-                    "token setting missing from the " "splunk_hec config section"
+                    "token setting missing from the splunk_hec config section"
                 )
                 exit(-1)
             if "index" in hec_config:
                 opts.hec_index = hec_config["index"]
             else:
                 logger.critical(
-                    "index setting missing from the " "splunk_hec config section"
+                    "index setting missing from the splunk_hec config section"
                 )
                 exit(-1)
             if "skip_certificate_verification" in hec_config:
@@ -990,9 +994,7 @@ def _main():
             if "hosts" in kafka_config:
                 opts.kafka_hosts = _str_to_list(kafka_config["hosts"])
             else:
-                logger.critical(
-                    "hosts setting missing from the " "kafka config section"
-                )
+                logger.critical("hosts setting missing from the kafka config section")
                 exit(-1)
             if "user" in kafka_config:
                 opts.kafka_username = kafka_config["user"]
@@ -1007,21 +1009,20 @@ def _main():
                 opts.kafka_aggregate_topic = kafka_config["aggregate_topic"]
             else:
                 logger.critical(
-                    "aggregate_topic setting missing from the " "kafka config section"
+                    "aggregate_topic setting missing from the kafka config section"
                 )
                 exit(-1)
             if "forensic_topic" in kafka_config:
                 opts.kafka_forensic_topic = kafka_config["forensic_topic"]
             else:
                 logger.critical(
-                    "forensic_topic setting missing from the " "kafka config section"
+                    "forensic_topic setting missing from the kafka config section"
                 )
             if "smtp_tls_topic" in kafka_config:
                 opts.kafka_smtp_tls_topic = kafka_config["smtp_tls_topic"]
             else:
                 logger.critical(
-                    "forensic_topic setting missing from the "
-                    "splunk_hec config section"
+                    "forensic_topic setting missing from the splunk_hec config section"
                 )
 
         if "smtp" in config.sections():
@@ -1029,7 +1030,7 @@ def _main():
             if "host" in smtp_config:
                 opts.smtp_host = smtp_config["host"]
             else:
-                logger.critical("host setting missing from the " "smtp config section")
+                logger.critical("host setting missing from the smtp config section")
                 exit(-1)
             if "port" in smtp_config:
                 opts.smtp_port = smtp_config.getint("port")
@@ -1041,23 +1042,21 @@ def _main():
             if "user" in smtp_config:
                 opts.smtp_user = smtp_config["user"]
             else:
-                logger.critical("user setting missing from the " "smtp config section")
+                logger.critical("user setting missing from the smtp config section")
                 exit(-1)
             if "password" in smtp_config:
                 opts.smtp_password = smtp_config["password"]
             else:
-                logger.critical(
-                    "password setting missing from the " "smtp config section"
-                )
+                logger.critical("password setting missing from the smtp config section")
                 exit(-1)
             if "from" in smtp_config:
                 opts.smtp_from = smtp_config["from"]
             else:
-                logger.critical("from setting missing from the " "smtp config section")
+                logger.critical("from setting missing from the smtp config section")
             if "to" in smtp_config:
                 opts.smtp_to = _str_to_list(smtp_config["to"])
             else:
-                logger.critical("to setting missing from the " "smtp config section")
+                logger.critical("to setting missing from the smtp config section")
             if "subject" in smtp_config:
                 opts.smtp_subject = smtp_config["subject"]
             if "attachment" in smtp_config:
@@ -1070,7 +1069,7 @@ def _main():
             if "bucket" in s3_config:
                 opts.s3_bucket = s3_config["bucket"]
             else:
-                logger.critical("bucket setting missing from the " "s3 config section")
+                logger.critical("bucket setting missing from the s3 config section")
                 exit(-1)
             if "path" in s3_config:
                 opts.s3_path = s3_config["path"]
@@ -1095,9 +1094,7 @@ def _main():
             if "server" in syslog_config:
                 opts.syslog_server = syslog_config["server"]
             else:
-                logger.critical(
-                    "server setting missing from the " "syslog config section"
-                )
+                logger.critical("server setting missing from the syslog config section")
                 exit(-1)
             if "port" in syslog_config:
                 opts.syslog_port = syslog_config["port"]
@@ -1148,17 +1145,17 @@ def _main():
             if "host" in gelf_config:
                 opts.gelf_host = gelf_config["host"]
             else:
-                logger.critical("host setting missing from the " "gelf config section")
+                logger.critical("host setting missing from the gelf config section")
                 exit(-1)
             if "port" in gelf_config:
                 opts.gelf_port = gelf_config["port"]
             else:
-                logger.critical("port setting missing from the " "gelf config section")
+                logger.critical("port setting missing from the gelf config section")
                 exit(-1)
             if "mode" in gelf_config:
                 opts.gelf_mode = gelf_config["mode"]
             else:
-                logger.critical("mode setting missing from the " "gelf config section")
+                logger.critical("mode setting missing from the gelf config section")
                 exit(-1)
 
         if "webhook" in config.sections():
@@ -1184,8 +1181,7 @@ def _main():
         try:
             fh = logging.FileHandler(opts.log_file, "a")
             formatter = logging.Formatter(
-                "%(asctime)s - "
-                "%(levelname)s - [%(filename)s:%(lineno)d] - %(message)s"
+                "%(asctime)s - %(levelname)s - [%(filename)s:%(lineno)d] - %(message)s"
             )
             fh.setFormatter(formatter)
             logger.addHandler(fh)
@@ -1293,7 +1289,7 @@ def _main():
 
     if opts.hec:
         if opts.hec_token is None or opts.hec_index is None:
-            logger.error("HEC token and HEC index are required when " "using HEC URL")
+            logger.error("HEC token and HEC index are required when using HEC URL")
             exit(1)
 
         verify = True
@@ -1418,7 +1414,17 @@ def _main():
             logger.error("Failed to parse {0} - {1}".format(result[1], result[0]))
         else:
             if result[0]["report_type"] == "aggregate":
-                aggregate_reports.append(result[0]["report"])
+                report_org = result[0]["report"]["report_metadata"]["org_name"]
+                report_id = result[0]["report"]["report_metadata"]["report_id"]
+                report_key = f"{report_org}_{report_id}"
+                if report_key not in SEEN_AGGREGATE_REPORT_IDS:
+                    SEEN_AGGREGATE_REPORT_IDS[report_key] = True
+                    aggregate_reports.append(result[0]["report"])
+                else:
+                    logger.debug(
+                        "Skipping duplicate aggregate report "
+                        f"from {report_org} with ID: {report_id}"
+                    )
             elif result[0]["report_type"] == "forensic":
                 forensic_reports.append(result[0]["report"])
             elif result[0]["report_type"] == "smtp_tls":
@@ -1446,7 +1452,7 @@ def _main():
         try:
             if opts.imap_user is None or opts.imap_password is None:
                 logger.error(
-                    "IMAP user and password must be specified if" "host is specified"
+                    "IMAP user and password must be specified ifhost is specified"
                 )
 
             ssl = True
@@ -1485,6 +1491,7 @@ def _main():
                 password=opts.graph_password,
                 token_file=opts.graph_token_file,
                 allow_unencrypted_storage=opts.graph_allow_unencrypted_storage,
+                graph_url=opts.graph_url,
             )
 
         except Exception:

parsedmarc/constants.py

@@ -0,0 +1,2 @@
+__version__ = "8.18.6"
+USER_AGENT = f"parsedmarc/{__version__}"

parsedmarc/elastic.py

@@ -552,8 +552,8 @@ def save_forensic_report_to_elasticsearch(
     for original_header in original_headers:
         headers[original_header.lower()] = original_headers[original_header]
 
-    arrival_date_human = forensic_report["arrival_date_utc"]
-    arrival_date = human_timestamp_to_datetime(arrival_date_human)
+    arrival_date = human_timestamp_to_datetime(forensic_report["arrival_date_utc"])
+    arrival_date_epoch_milliseconds = int(arrival_date.timestamp() * 1000)
 
     if index_suffix is not None:
         search_index = "dmarc_forensic_{0}*".format(index_suffix)
@@ -562,20 +562,35 @@ def save_forensic_report_to_elasticsearch(
     if index_prefix is not None:
         search_index = "{0}{1}".format(index_prefix, search_index)
     search = Search(index=search_index)
-    arrival_query = {"match": {"arrival_date": arrival_date}}
-    q = Q(arrival_query)
+    q = Q(dict(match=dict(arrival_date=arrival_date_epoch_milliseconds)))
 
     from_ = None
     to_ = None
     subject = None
     if "from" in headers:
-        from_ = headers["from"]
-        from_query = {"match_phrase": {"sample.headers.from": from_}}
-        q = q & Q(from_query)
+        # We convert the FROM header from a string list to a flat string.
+        headers["from"] = headers["from"][0]
+        if headers["from"][0] == "":
+            headers["from"] = headers["from"][1]
+        else:
+            headers["from"] = " <".join(headers["from"]) + ">"
+
+        from_ = dict()
+        from_["sample.headers.from"] = headers["from"]
+        from_query = Q(dict(match_phrase=from_))
+        q = q & from_query
     if "to" in headers:
-        to_ = headers["to"]
-        to_query = {"match_phrase": {"sample.headers.to": to_}}
-        q = q & Q(to_query)
+        # We convert the TO header from a string list to a flat string.
+        headers["to"] = headers["to"][0]
+        if headers["to"][0] == "":
+            headers["to"] = headers["to"][1]
+        else:
+            headers["to"] = " <".join(headers["to"]) + ">"
+
+        to_ = dict()
+        to_["sample.headers.to"] = headers["to"]
+        to_query = Q(dict(match_phrase=to_))
+        q = q & to_query
     if "subject" in headers:
         subject = headers["subject"]
         subject_query = {"match_phrase": {"sample.headers.subject": subject}}
@@ -589,7 +604,9 @@ def save_forensic_report_to_elasticsearch(
             "A forensic sample to {0} from {1} "
             "with a subject of {2} and arrival date of {3} "
             "already exists in "
-            "Elasticsearch".format(to_, from_, subject, arrival_date_human)
+            "Elasticsearch".format(
+                to_, from_, subject, forensic_report["arrival_date_utc"]
+            )
         )
 
     parsed_sample = forensic_report["parsed_sample"]
@@ -625,7 +642,7 @@ def save_forensic_report_to_elasticsearch(
             user_agent=forensic_report["user_agent"],
             version=forensic_report["version"],
             original_mail_from=forensic_report["original_mail_from"],
-            arrival_date=arrival_date,
+            arrival_date=arrival_date_epoch_milliseconds,
             domain=forensic_report["reported_domain"],
             original_envelope_id=forensic_report["original_envelope_id"],
             authentication_results=forensic_report["authentication_results"],

parsedmarc/mail/gmail.py

@@ -63,9 +63,7 @@ class GmailConnection(MailboxConnection):
             ).execute()
         except HttpError as e:
             if e.status_code == 409:
-                logger.debug(
-                    f"Folder {folder_name} already exists, " f"skipping creation"
-                )
+                logger.debug(f"Folder {folder_name} already exists, skipping creation")
             else:
                 raise e
 

parsedmarc/mail/graph.py

@@ -89,6 +89,7 @@ class MSGraphConnection(MailboxConnection):
         self,
         auth_method: str,
         mailbox: str,
+        graph_url: str,
         client_id: str,
         client_secret: str,
         username: str,
@@ -108,7 +109,10 @@ class MSGraphConnection(MailboxConnection):
             token_path=token_path,
             allow_unencrypted_storage=allow_unencrypted_storage,
         )
-        client_params = {"credential": credential}
+        client_params = {
+            "credential": credential,
+            "cloud": graph_url,
+        }
         if not isinstance(credential, ClientSecretCredential):
             scopes = ["Mail.ReadWrite"]
             # Detect if mailbox is shared
@@ -137,16 +141,16 @@ class MSGraphConnection(MailboxConnection):
         request_url = f"/users/{self.mailbox_name}/mailFolders{sub_url}"
         resp = self._client.post(request_url, json=request_body)
         if resp.status_code == 409:
-            logger.debug(f"Folder {folder_name} already exists, " f"skipping creation")
+            logger.debug(f"Folder {folder_name} already exists, skipping creation")
         elif resp.status_code == 201:
             logger.debug(f"Created folder {folder_name}")
         else:
-            logger.warning(f"Unknown response " f"{resp.status_code} {resp.json()}")
+            logger.warning(f"Unknown response {resp.status_code} {resp.json()}")
 
     def fetch_messages(self, folder_name: str, **kwargs) -> List[str]:
         """Returns a list of message UIDs in the specified folder"""
         folder_id = self._find_folder_id_from_folder_path(folder_name)
-        url = f"/users/{self.mailbox_name}/mailFolders/" f"{folder_id}/messages"
+        url = f"/users/{self.mailbox_name}/mailFolders/{folder_id}/messages"
         since = kwargs.get("since")
         if not since:
             since = None
@@ -185,7 +189,7 @@ class MSGraphConnection(MailboxConnection):
         resp = self._client.patch(url, json={"isRead": "true"})
         if resp.status_code != 200:
             raise RuntimeWarning(
-                f"Failed to mark message read" f"{resp.status_code}: {resp.json()}"
+                f"Failed to mark message read{resp.status_code}: {resp.json()}"
             )
 
     def fetch_message(self, message_id: str, **kwargs):
@@ -193,7 +197,7 @@ class MSGraphConnection(MailboxConnection):
         result = self._client.get(url)
         if result.status_code != 200:
             raise RuntimeWarning(
-                f"Failed to fetch message" f"{result.status_code}: {result.json()}"
+                f"Failed to fetch message{result.status_code}: {result.json()}"
             )
         mark_read = kwargs.get("mark_read")
         if mark_read:
@@ -205,7 +209,7 @@ class MSGraphConnection(MailboxConnection):
         resp = self._client.delete(url)
         if resp.status_code != 204:
             raise RuntimeWarning(
-                f"Failed to delete message " f"{resp.status_code}: {resp.json()}"
+                f"Failed to delete message {resp.status_code}: {resp.json()}"
             )
 
     def move_message(self, message_id: str, folder_name: str):
@@ -215,7 +219,7 @@ class MSGraphConnection(MailboxConnection):
         resp = self._client.post(url, json=request_body)
         if resp.status_code != 201:
             raise RuntimeWarning(
-                f"Failed to move message " f"{resp.status_code}: {resp.json()}"
+                f"Failed to move message {resp.status_code}: {resp.json()}"
             )
 
     def keepalive(self):
@@ -250,7 +254,7 @@ class MSGraphConnection(MailboxConnection):
         filter = f"?$filter=displayName eq '{folder_name}'"
         folders_resp = self._client.get(url + filter)
         if folders_resp.status_code != 200:
-            raise RuntimeWarning(f"Failed to list folders." f"{folders_resp.json()}")
+            raise RuntimeWarning(f"Failed to list folders.{folders_resp.json()}")
         folders: list = folders_resp.json()["value"]
         matched_folders = [
             folder for folder in folders if folder["displayName"] == folder_name

parsedmarc/mail/imap.py

@@ -85,7 +85,5 @@ class IMAPConnection(MailboxConnection):
                 logger.warning("IMAP connection timeout. Reconnecting...")
                 sleep(check_timeout)
             except Exception as e:
-                logger.warning(
-                    "IMAP connection error. {0}. " "Reconnecting...".format(e)
-                )
+                logger.warning("IMAP connection error. {0}. Reconnecting...".format(e))
                 sleep(check_timeout)

parsedmarc/opensearch.py

@@ -202,13 +202,15 @@ class _SMTPTLSPolicyDoc(InnerDoc):
         receiving_ip,
         receiving_mx_helo,
         failed_session_count,
+        sending_mta_ip=None,
         receiving_mx_hostname=None,
         additional_information_uri=None,
         failure_reason_code=None,
     ):
-        self.failure_details.append(
+        _details = _SMTPTLSFailureDetailsDoc(
             result_type=result_type,
             ip_address=ip_address,
+            sending_mta_ip=sending_mta_ip,
             receiving_mx_hostname=receiving_mx_hostname,
             receiving_mx_helo=receiving_mx_helo,
             receiving_ip=receiving_ip,
@@ -216,9 +218,10 @@ class _SMTPTLSPolicyDoc(InnerDoc):
             additional_information=additional_information_uri,
             failure_reason_code=failure_reason_code,
         )
+        self.failure_details.append(_details)
 
 
-class _SMTPTLSFailureReportDoc(Document):
+class _SMTPTLSReportDoc(Document):
     class Index:
         name = "smtp_tls"
 
@@ -499,6 +502,7 @@ def save_aggregate_report_to_opensearch(
             index = "{0}_{1}".format(index, index_suffix)
         if index_prefix:
             index = "{0}{1}".format(index_prefix, index)
+
         index = "{0}-{1}".format(index, index_date)
         index_settings = dict(
             number_of_shards=number_of_shards, number_of_replicas=number_of_replicas
@@ -548,8 +552,8 @@ def save_forensic_report_to_opensearch(
     for original_header in original_headers:
         headers[original_header.lower()] = original_headers[original_header]
 
-    arrival_date_human = forensic_report["arrival_date_utc"]
-    arrival_date = human_timestamp_to_datetime(arrival_date_human)
+    arrival_date = human_timestamp_to_datetime(forensic_report["arrival_date_utc"])
+    arrival_date_epoch_milliseconds = int(arrival_date.timestamp() * 1000)
 
     if index_suffix is not None:
         search_index = "dmarc_forensic_{0}*".format(index_suffix)
@@ -558,20 +562,35 @@ def save_forensic_report_to_opensearch(
     if index_prefix is not None:
         search_index = "{0}{1}".format(index_prefix, search_index)
     search = Search(index=search_index)
-    arrival_query = {"match": {"arrival_date": arrival_date}}
-    q = Q(arrival_query)
+    q = Q(dict(match=dict(arrival_date=arrival_date_epoch_milliseconds)))
 
     from_ = None
     to_ = None
     subject = None
     if "from" in headers:
-        from_ = headers["from"]
-        from_query = {"match_phrase": {"sample.headers.from": from_}}
-        q = q & Q(from_query)
+        # We convert the FROM header from a string list to a flat string.
+        headers["from"] = headers["from"][0]
+        if headers["from"][0] == "":
+            headers["from"] = headers["from"][1]
+        else:
+            headers["from"] = " <".join(headers["from"]) + ">"
+
+        from_ = dict()
+        from_["sample.headers.from"] = headers["from"]
+        from_query = Q(dict(match_phrase=from_))
+        q = q & from_query
     if "to" in headers:
-        to_ = headers["to"]
-        to_query = {"match_phrase": {"sample.headers.to": to_}}
-        q = q & Q(to_query)
+        # We convert the TO header from a string list to a flat string.
+        headers["to"] = headers["to"][0]
+        if headers["to"][0] == "":
+            headers["to"] = headers["to"][1]
+        else:
+            headers["to"] = " <".join(headers["to"]) + ">"
+
+        to_ = dict()
+        to_["sample.headers.to"] = headers["to"]
+        to_query = Q(dict(match_phrase=to_))
+        q = q & to_query
     if "subject" in headers:
         subject = headers["subject"]
         subject_query = {"match_phrase": {"sample.headers.subject": subject}}
@@ -585,7 +604,9 @@ def save_forensic_report_to_opensearch(
             "A forensic sample to {0} from {1} "
             "with a subject of {2} and arrival date of {3} "
             "already exists in "
-            "OpenSearch".format(to_, from_, subject, arrival_date_human)
+            "OpenSearch".format(
+                to_, from_, subject, forensic_report["arrival_date_utc"]
+            )
         )
 
     parsed_sample = forensic_report["parsed_sample"]
@@ -621,7 +642,7 @@ def save_forensic_report_to_opensearch(
             user_agent=forensic_report["user_agent"],
             version=forensic_report["version"],
             original_mail_from=forensic_report["original_mail_from"],
-            arrival_date=arrival_date,
+            arrival_date=arrival_date_epoch_milliseconds,
             domain=forensic_report["reported_domain"],
             original_envelope_id=forensic_report["original_envelope_id"],
             authentication_results=forensic_report["authentication_results"],
@@ -685,7 +706,7 @@ def save_smtp_tls_report_to_opensearch(
             AlreadySaved
     """
     logger.info("Saving aggregate report to OpenSearch")
-    org_name = report["org_name"]
+    org_name = report["organization_name"]
     report_id = report["report_id"]
     begin_date = human_timestamp_to_datetime(report["begin_date"], to_utc=True)
     end_date = human_timestamp_to_datetime(report["end_date"], to_utc=True)
@@ -741,11 +762,11 @@ def save_smtp_tls_report_to_opensearch(
         number_of_shards=number_of_shards, number_of_replicas=number_of_replicas
     )
 
-    smtp_tls_doc = _SMTPTLSFailureReportDoc(
-        organization_name=report["organization_name"],
-        date_range=[report["date_begin"], report["date_end"]],
-        date_begin=report["date_begin"],
-        date_end=report["date_end"],
+    smtp_tls_doc = _SMTPTLSReportDoc(
+        org_name=report["organization_name"],
+        date_range=[report["begin_date"], report["end_date"]],
+        date_begin=report["begin_date"],
+        date_end=report["end_date"],
         contact_info=report["contact_info"],
         report_id=report["report_id"],
     )
@@ -760,32 +781,48 @@ def save_smtp_tls_report_to_opensearch(
         policy_doc = _SMTPTLSPolicyDoc(
             policy_domain=policy["policy_domain"],
             policy_type=policy["policy_type"],
+            succesful_session_count=policy["successful_session_count"],
+            failed_session_count=policy["failed_session_count"],
             policy_string=policy_strings,
             mx_host_patterns=mx_host_patterns,
         )
         if "failure_details" in policy:
-            failure_details = policy["failure_details"]
-            receiving_mx_hostname = None
-            additional_information_uri = None
-            failure_reason_code = None
-            if "receiving_mx_hostname" in failure_details:
-                receiving_mx_hostname = failure_details["receiving_mx_hostname"]
-            if "additional_information_uri" in failure_details:
-                additional_information_uri = failure_details[
-                    "additional_information_uri"
-                ]
-            if "failure_reason_code" in failure_details:
-                failure_reason_code = failure_details["failure_reason_code"]
-            policy_doc.add_failure_details(
-                result_type=failure_details["result_type"],
-                ip_address=failure_details["ip_address"],
-                receiving_ip=failure_details["receiving_ip"],
-                receiving_mx_helo=failure_details["receiving_mx_helo"],
-                failed_session_count=failure_details["failed_session_count"],
-                receiving_mx_hostname=receiving_mx_hostname,
-                additional_information_uri=additional_information_uri,
-                failure_reason_code=failure_reason_code,
-            )
+            for failure_detail in policy["failure_details"]:
+                receiving_mx_hostname = None
+                additional_information_uri = None
+                failure_reason_code = None
+                ip_address = None
+                receiving_ip = None
+                receiving_mx_helo = None
+                sending_mta_ip = None
+
+                if "receiving_mx_hostname" in failure_detail:
+                    receiving_mx_hostname = failure_detail["receiving_mx_hostname"]
+                if "additional_information_uri" in failure_detail:
+                    additional_information_uri = failure_detail[
+                        "additional_information_uri"
+                    ]
+                if "failure_reason_code" in failure_detail:
+                    failure_reason_code = failure_detail["failure_reason_code"]
+                if "ip_address" in failure_detail:
+                    ip_address = failure_detail["ip_address"]
+                if "receiving_ip" in failure_detail:
+                    receiving_ip = failure_detail["receiving_ip"]
+                if "receiving_mx_helo" in failure_detail:
+                    receiving_mx_helo = failure_detail["receiving_mx_helo"]
+                if "sending_mta_ip" in failure_detail:
+                    sending_mta_ip = failure_detail["sending_mta_ip"]
+                policy_doc.add_failure_details(
+                    result_type=failure_detail["result_type"],
+                    ip_address=ip_address,
+                    receiving_ip=receiving_ip,
+                    receiving_mx_helo=receiving_mx_helo,
+                    failed_session_count=failure_detail["failed_session_count"],
+                    sending_mta_ip=sending_mta_ip,
+                    receiving_mx_hostname=receiving_mx_hostname,
+                    additional_information_uri=additional_information_uri,
+                    failure_reason_code=failure_reason_code,
+                )
         smtp_tls_doc.policies.append(policy_doc)
 
     create_indexes([index], index_settings)

parsedmarc/resources/dbip/README.md

@@ -1,7 +1,7 @@
 # About
 
 `dbip-country-lite.mmdb` is provided by [dbip][dbip] under a
-[ Creative Commons Attribution 4.0 International License][cc].
+[Creative Commons Attribution 4.0 International License][cc].
 
-[dbip]: https://db-ip.com/db/lite.php
+[dbip]: https://db-ip.com/db/download/ip-to-country-lite
 [cc]: http://creativecommons.org/licenses/by/4.0/

parsedmarc/resources/maps/README.md

@@ -3,6 +3,8 @@
 A mapping is meant to make it easier to identify who or what a sending source is. Please consider contributing
 additional mappings in a GitHub Pull Request.
 
+Do not open these CSV files in Excel. It will replace Unicode characters with question marks. Use LibreOffice Calc instead.
+
 ## base_reverse_dns_map.csv
 
 A CSV file with three fields: `base_reverse_dns`, `name`, and `type`.
@@ -19,33 +21,72 @@ The `service_type` is based on the following rule precedence:
 3. All telecommunications providers that offer internet access are identified as `ISP`, even if they also offer other services, such as web hosting or email hosting.
 4. All web hosting providers are identified as `Web Hosting`, even if the service also offers email hosting.
 5. All email account providers are identified as `Email Provider`, no matter how or where they are hosted
-6. All legitimate platforms offering their Software as a Service SaaS) are identified as `SaaS`, regardless of industry. This helps simplify metrics.
+6. All legitimate platforms offering their Software as a Service (SaaS) are identified as `SaaS`, regardless of industry. This helps simplify metrics.
 7. All other senders that use their own domain as a Reverse DNS base domain should be identified based on their industry
 
+- Agriculture
+- Automotive
+- Beauty
+- Conglomerate
+- Construction
+- Consulting
+- Defense
+- Education
 - Email Provider
 - Email Security
-- Education
 - Entertainment
+- Event Planning
 - Finance
 - Food
 - Government
 - Government Media
 - Healthcare
+- IaaS
 - Industrial
 - ISP
+- Legal
 - Logistics
+- Manufacturing
 - Marketing
 - MSP
+- MSSP
+- News
 - Nonprofit
+- PaaS
+- Photography
+- Physical Security
 - Print
+- Publishing
 - Real Estate
 - Retail
 - SaaS
+- Science
+- Search Engine
 - Social Media
+- Sports
+- Staffing
 - Technology
 - Travel
 - Web Host
 
-The file currently contains over 600 mappings from a wide variety of email sending services, including large email
-providers, SaaS platforms, small web hosts, and healthcare companies. Ideally this mapping will continuously grow to
-include many other services and industries.
+The file currently contains over 1,400 mappings from a wide variety of email sending sources.
+
+## known_unknown_base_reverse_dns.txt
+
+A list of reverse DNS base domains that could not be identified as belonging to a particular organization, service, or industry.
+
+## base_reverse_dns.csv
+
+A CSV with the fields `source_name` and optionally `message_count`. This CSV can be generated by exporting the base DNS data from the Kibana or Splunk dashboards provided by parsedmarc. This file is not tracked by Git.
+
+## unknown_base_reverse_dns.csv
+
+A CSV file with the fields `source_name` and `message_count`. This file is not tracked by Git.
+
+## find_bad_utf8.py
+
+Locates invalid UTF-8 bytes in files and optionally tries to current them. Generated by GPT5. Helped me find where I had introduced invalid bytes in `base_reverse_dns_map.csv`.
+
+## find_unknown_base_reverse_dns.py
+
+This is a python script that reads the domains in `base_reverse_dns.csv` and writes the domains that are not in `base_reverse_dns_map.csv` or `known_unknown_base_reverse_dns.txt` to `unknown_base_reverse_dns.csv`. This is useful for identifying potential additional domains to contribute to `base_reverse_dns_map.csv` and `known_unknown_base_reverse_dns.txt`.

parsedmarc/resources/maps/find_bad_utf8.py

@@ -0,0 +1,488 @@
+#!/usr/bin/env python3
+
+
+import argparse
+import codecs
+import os
+import sys
+import shutil
+from typing import List, Tuple
+
+"""
+Locates and optionally corrects bad UTF-8 bytes in a file.
+Generated by GPT-5 Use at your own risk.
+"""
+
+# -------------------------
+# UTF-8 scanning
+# -------------------------
+
+
+def scan_line_for_utf8_errors(
+    line_bytes: bytes, line_no: int, base_offset: int, context: int
+):
+    """
+    Scan one line of raw bytes for UTF-8 decoding errors.
+    Returns a list of dicts describing each error.
+    """
+    pos = 0
+    results = []
+    while pos < len(line_bytes):
+        dec = codecs.getincrementaldecoder("utf-8")("strict")
+        try:
+            dec.decode(line_bytes[pos:], final=True)
+            break
+        except UnicodeDecodeError as e:
+            rel_index = e.start
+            abs_index_in_line = pos + rel_index
+            abs_offset = base_offset + abs_index_in_line
+
+            start_ctx = max(0, abs_index_in_line - context)
+            end_ctx = min(len(line_bytes), abs_index_in_line + 1 + context)
+            ctx_bytes = line_bytes[start_ctx:end_ctx]
+            bad_byte = line_bytes[abs_index_in_line : abs_index_in_line + 1]
+            col = abs_index_in_line + 1  # 1-based byte column
+
+            results.append(
+                {
+                    "line": line_no,
+                    "column": col,
+                    "abs_offset": abs_offset,
+                    "bad_byte_hex": bad_byte.hex(),
+                    "context_hex": ctx_bytes.hex(),
+                    "context_preview": ctx_bytes.decode("utf-8", errors="replace"),
+                }
+            )
+            # Move past the offending byte and continue
+            pos = abs_index_in_line + 1
+    return results
+
+
+def scan_file_for_utf8_errors(path: str, context: int, limit: int):
+    errors_found = 0
+    limit_val = limit if limit != 0 else float("inf")
+
+    with open(path, "rb") as f:
+        total_offset = 0
+        line_no = 0
+        while True:
+            line = f.readline()
+            if not line:
+                break
+            line_no += 1
+            results = scan_line_for_utf8_errors(line, line_no, total_offset, context)
+            for r in results:
+                errors_found += 1
+                print(
+                    f"[ERROR {errors_found}] Line {r['line']}, Column {r['column']}, "
+                    f"Absolute byte offset {r['abs_offset']}"
+                )
+                print(f"  Bad byte: 0x{r['bad_byte_hex']}")
+                print(f"  Context (hex): {r['context_hex']}")
+                print(f"  Context (preview): {r['context_preview']}")
+                print()
+                if errors_found >= limit_val:
+                    print(f"Reached limit of {limit} errors. Stopping.")
+                    return errors_found
+            total_offset += len(line)
+
+    if errors_found == 0:
+        print("No invalid UTF-8 bytes found. 🎉")
+    else:
+        print(f"Found {errors_found} invalid UTF-8 byte(s).")
+    return errors_found
+
+
+# -------------------------
+# Whole-file conversion
+# -------------------------
+
+
+def detect_encoding_text(path: str) -> Tuple[str, str]:
+    """
+    Use charset-normalizer to detect file encoding.
+    Return (encoding_name, decoded_text). Falls back to cp1252 if needed.
+    """
+    try:
+        from charset_normalizer import from_path
+    except ImportError:
+        print(
+            "Please install charset-normalizer: pip install charset-normalizer",
+            file=sys.stderr,
+        )
+        sys.exit(4)
+
+    matches = from_path(path)
+    match = matches.best()
+    if match is None or match.encoding is None:
+        # Fallback heuristic for Western single-byte text
+        with open(path, "rb") as fb:
+            data = fb.read()
+        try:
+            return "cp1252", data.decode("cp1252", errors="strict")
+        except UnicodeDecodeError:
+            print("Unable to detect encoding reliably.", file=sys.stderr)
+            sys.exit(5)
+
+    return match.encoding, str(match)
+
+
+def convert_to_utf8(src_path: str, out_path: str, src_encoding: str = None) -> str:
+    """
+    Convert an entire file to UTF-8 (re-decoding everything).
+    If src_encoding is provided, use it; else auto-detect.
+    Returns the encoding actually used.
+    """
+    if src_encoding:
+        with open(src_path, "rb") as fb:
+            data = fb.read()
+        try:
+            text = data.decode(src_encoding, errors="strict")
+        except LookupError:
+            print(f"Unknown encoding: {src_encoding}", file=sys.stderr)
+            sys.exit(6)
+        except UnicodeDecodeError as e:
+            print(f"Decoding failed with {src_encoding}: {e}", file=sys.stderr)
+            sys.exit(7)
+        used = src_encoding
+    else:
+        used, text = detect_encoding_text(src_path)
+
+    with open(out_path, "w", encoding="utf-8", newline="") as fw:
+        fw.write(text)
+    return used
+
+
+def verify_utf8_file(path: str) -> Tuple[bool, str]:
+    try:
+        with open(path, "rb") as fb:
+            fb.read().decode("utf-8", errors="strict")
+        return True, ""
+    except UnicodeDecodeError as e:
+        return False, str(e)
+
+
+# -------------------------
+# Targeted single-byte fixer
+# -------------------------
+
+
+def iter_lines_with_offsets(b: bytes):
+    """
+    Yield (line_bytes, line_start_abs_offset). Preserves LF/CRLF/CR in bytes.
+    """
+    start = 0
+    for i, byte in enumerate(b):
+        if byte == 0x0A:  # LF
+            yield b[start : i + 1], start
+            start = i + 1
+    if start < len(b):
+        yield b[start:], start
+
+
+def detect_probable_fallbacks() -> List[str]:
+    # Good defaults for Western/Portuguese text
+    return ["cp1252", "iso-8859-1", "iso-8859-15"]
+
+
+def repair_mixed_utf8_line(line: bytes, base_offset: int, fallback_chain: List[str]):
+    """
+    Strictly validate UTF-8 and fix *only* the exact offending byte when an error occurs.
+    This avoids touching adjacent valid UTF-8 (prevents mojibake like 'é').
+    """
+    out_fragments: List[str] = []
+    fixes = []
+    pos = 0
+    n = len(line)
+
+    while pos < n:
+        dec = codecs.getincrementaldecoder("utf-8")("strict")
+        try:
+            s = dec.decode(line[pos:], final=True)
+            out_fragments.append(s)
+            break
+        except UnicodeDecodeError as e:
+            # Append the valid prefix before the error
+            if e.start > 0:
+                out_fragments.append(
+                    line[pos : pos + e.start].decode("utf-8", errors="strict")
+                )
+
+            bad_index = pos + e.start  # absolute index in 'line'
+            bad_slice = line[bad_index : bad_index + 1]  # FIX EXACTLY ONE BYTE
+
+            # Decode that single byte using the first working fallback
+            decoded = None
+            used_enc = None
+            for enc in fallback_chain:
+                try:
+                    decoded = bad_slice.decode(enc, errors="strict")
+                    used_enc = enc
+                    break
+                except Exception:
+                    continue
+            if decoded is None:
+                # latin-1 always succeeds (byte->same code point)
+                decoded = bad_slice.decode("latin-1")
+                used_enc = "latin-1 (fallback)"
+
+            out_fragments.append(decoded)
+
+            # Log the fix
+            col_1based = bad_index + 1  # byte-based column
+            fixes.append(
+                {
+                    "line_base_offset": base_offset,
+                    "line": None,  # caller fills line number
+                    "column": col_1based,
+                    "abs_offset": base_offset + bad_index,
+                    "bad_bytes_hex": bad_slice.hex(),
+                    "used_encoding": used_enc,
+                    "replacement_preview": decoded,
+                }
+            )
+
+            # Advance exactly one byte past the offending byte and continue
+            pos = bad_index + 1
+
+    return "".join(out_fragments), fixes
+
+
+def targeted_fix_to_utf8(
+    src_path: str,
+    out_path: str,
+    fallback_chain: List[str],
+    dry_run: bool,
+    max_fixes: int,
+):
+    with open(src_path, "rb") as fb:
+        data = fb.read()
+
+    total_fixes = 0
+    repaired_lines: List[str] = []
+    line_no = 0
+    max_val = max_fixes if max_fixes != 0 else float("inf")
+
+    for line_bytes, base_offset in iter_lines_with_offsets(data):
+        line_no += 1
+        # Fast path: keep lines that are already valid UTF-8
+        try:
+            repaired_lines.append(line_bytes.decode("utf-8", errors="strict"))
+            continue
+        except UnicodeDecodeError:
+            pass
+
+        fixed_text, fixes = repair_mixed_utf8_line(
+            line_bytes, base_offset, fallback_chain=fallback_chain
+        )
+        for f in fixes:
+            f["line"] = line_no
+
+        repaired_lines.append(fixed_text)
+
+        # Log fixes
+        for f in fixes:
+            total_fixes += 1
+            print(
+                f"[FIX {total_fixes}] Line {f['line']}, Column {f['column']}, Abs offset {f['abs_offset']}"
+            )
+            print(f"  Bad bytes: 0x{f['bad_bytes_hex']}")
+            print(f"  Used encoding: {f['used_encoding']}")
+            preview = f["replacement_preview"].replace("\r", "\\r").replace("\n", "\\n")
+            if len(preview) > 40:
+                preview = preview[:40] + "…"
+            print(f"  Replacement preview: {preview}")
+            print()
+            if total_fixes >= max_val:
+                print(f"Reached max fixes limit ({max_fixes}). Stopping scan.")
+                break
+        if total_fixes >= max_val:
+            break
+
+    if dry_run:
+        print(f"Dry run complete. Detected {total_fixes} fix(es). No file written.")
+        return total_fixes
+
+    # Join and verify result can be encoded to UTF-8
+    repaired_text = "".join(repaired_lines)
+    try:
+        repaired_text.encode("utf-8", errors="strict")
+    except UnicodeEncodeError as e:
+        print(f"Internal error: repaired text not valid UTF-8: {e}", file=sys.stderr)
+        sys.exit(3)
+
+    with open(out_path, "w", encoding="utf-8", newline="") as fw:
+        fw.write(repaired_text)
+
+    print(f"Fixed file written to: {out_path}")
+    print(f"Total fixes applied: {total_fixes}")
+    return total_fixes
+
+
+# -------------------------
+# CLI
+# -------------------------
+
+
+def main():
+    ap = argparse.ArgumentParser(
+        description=(
+            "Scan for invalid UTF-8; optionally convert whole file or fix only invalid bytes.\n\n"
+            "By default, --convert and --fix **edit the input file in place** and create a backup "
+            "named '<input>.bak' before writing. If you pass --output, the original file is left "
+            "unchanged and no backup is created. Use --dry-run to preview fixes without writing."
+        ),
+        formatter_class=argparse.RawTextHelpFormatter,
+    )
+    ap.add_argument("path", help="Path to the CSV/text file")
+    ap.add_argument(
+        "--context",
+        type=int,
+        default=20,
+        help="Bytes of context to show around errors (default: 20)",
+    )
+    ap.add_argument(
+        "--limit",
+        type=int,
+        default=100,
+        help="Max errors to report during scan (0 = unlimited)",
+    )
+    ap.add_argument(
+        "--skip-scan", action="store_true", help="Skip initial scan for speed"
+    )
+
+    # Whole-file convert
+    ap.add_argument(
+        "--convert",
+        action="store_true",
+        help="Convert entire file to UTF-8 using auto/forced encoding "
+        "(in-place by default; creates '<input>.bak').",
+    )
+    ap.add_argument(
+        "--encoding",
+        help="Force source encoding for --convert or first fallback for --fix",
+    )
+    ap.add_argument(
+        "--output",
+        help="Write to this path instead of in-place (no .bak is created in that case)",
+    )
+
+    # Targeted fix
+    ap.add_argument(
+        "--fix",
+        action="store_true",
+        help="Fix only invalid byte(s) via fallback encodings "
+        "(in-place by default; creates '<input>.bak').",
+    )
+    ap.add_argument(
+        "--fallbacks",
+        help="Comma-separated fallback encodings (default: cp1252,iso-8859-1,iso-8859-15)",
+    )
+    ap.add_argument(
+        "--dry-run",
+        action="store_true",
+        help="(fix) Print fixes but do not write or create a .bak",
+    )
+    ap.add_argument(
+        "--max-fixes",
+        type=int,
+        default=0,
+        help="(fix) Stop after N fixes (0 = unlimited)",
+    )
+
+    args = ap.parse_args()
+    path = args.path
+
+    if not os.path.isfile(path):
+        print(f"File not found: {path}", file=sys.stderr)
+        sys.exit(2)
+
+    # Optional scan first
+    if not args.skip_scan:
+        scan_file_for_utf8_errors(path, context=args.context, limit=args.limit)
+
+    # Mode selection guards
+    if args.convert and args.fix:
+        print("Choose either --convert or --fix (not both).", file=sys.stderr)
+        sys.exit(9)
+    if not args.convert and not args.fix and args.skip_scan:
+        print("No action selected (use --convert or --fix).")
+        return
+    if not args.convert and not args.fix:
+        # User only wanted a scan
+        return
+
+    # Determine output path and backup behavior
+    # In-place by default: create '<input>.bak' before overwriting.
+    if args.output:
+        out_path = args.output
+        in_place = False
+    else:
+        out_path = path
+        in_place = True
+
+    # CONVERT mode
+    if args.convert:
+        print("\n[CONVERT MODE] Converting file to UTF-8...")
+        if in_place:
+            # Create backup before overwriting original
+            backup_path = path + ".bak"
+            shutil.copy2(path, backup_path)
+            print(f"Backup created: {backup_path}")
+        used = convert_to_utf8(path, out_path, src_encoding=args.encoding)
+        print(f"Source encoding used: {used}")
+        print(f"Saved UTF-8 file as: {out_path}")
+        ok, err = verify_utf8_file(out_path)
+        if ok:
+            print("Verification: output is valid UTF-8 ✅")
+        else:
+            print(f"Verification failed: {err}")
+            sys.exit(8)
+        return
+
+    # FIX mode (targeted, single-byte)
+    if args.fix:
+        print("\n[FIX MODE] Fixing only invalid bytes to UTF-8...")
+        if args.dry_run:
+            # Dry-run: never write or create backup
+            out_path_effective = os.devnull
+            in_place_effective = False
+        else:
+            out_path_effective = out_path
+            in_place_effective = in_place
+
+        # Build fallback chain (if --encoding provided, try it first)
+        if args.fallbacks:
+            fallback_chain = [e.strip() for e in args.fallbacks.split(",") if e.strip()]
+        else:
+            fallback_chain = detect_probable_fallbacks()
+        if args.encoding and args.encoding not in fallback_chain:
+            fallback_chain = [args.encoding] + fallback_chain
+
+        if in_place_effective:
+            # Create backup before overwriting original (only when actually writing)
+            backup_path = path + ".bak"
+            shutil.copy2(path, backup_path)
+            print(f"Backup created: {backup_path}")
+
+        fix_count = targeted_fix_to_utf8(
+            path,
+            out_path_effective,
+            fallback_chain=fallback_chain,
+            dry_run=args.dry_run,
+            max_fixes=args.max_fixes,
+        )
+
+        if not args.dry_run:
+            ok, err = verify_utf8_file(out_path_effective)
+            if ok:
+                print("Verification: output is valid UTF-8 ✅")
+                print(f"Fix mode completed — {fix_count} byte(s) corrected.")
+            else:
+                print(f"Verification failed: {err}")
+                sys.exit(8)
+        return
+
+
+if __name__ == "__main__":
+    main()

parsedmarc/resources/maps/find_unknown_base_reverse_dns.py

@@ -0,0 +1,93 @@
+#!/usr/bin/env python
+
+import logging
+import os
+import csv
+
+
+def _main():
+    input_csv_file_path = "base_reverse_dns.csv"
+    base_reverse_dns_map_file_path = "base_reverse_dns_map.csv"
+    known_unknown_list_file_path = "known_unknown_base_reverse_dns.txt"
+    psl_overrides_file_path = "psl_overrides.txt"
+    output_csv_file_path = "unknown_base_reverse_dns.csv"
+
+    csv_headers = ["source_name", "message_count"]
+
+    output_rows = []
+
+    logging.basicConfig()
+    logger = logging.getLogger(__name__)
+    logger.setLevel(logging.INFO)
+
+    for p in [
+        input_csv_file_path,
+        base_reverse_dns_map_file_path,
+        known_unknown_list_file_path,
+        psl_overrides_file_path,
+    ]:
+        if not os.path.exists(p):
+            logger.error(f"{p} does not exist")
+            exit(1)
+    logger.info(f"Loading {known_unknown_list_file_path}")
+    known_unknown_domains = []
+    with open(known_unknown_list_file_path) as f:
+        for line in f.readlines():
+            domain = line.lower().strip()
+            if domain in known_unknown_domains:
+                logger.warning(
+                    f"{domain} is in {known_unknown_list_file_path} multiple times"
+                )
+            else:
+                known_unknown_domains.append(domain)
+    logger.info(f"Loading {psl_overrides_file_path}")
+    psl_overrides = []
+    with open(psl_overrides_file_path) as f:
+        for line in f.readlines():
+            domain = line.lower().strip()
+            if domain in psl_overrides:
+                logger.warning(
+                    f"{domain} is in {psl_overrides_file_path} multiple times"
+                )
+            else:
+                psl_overrides.append(domain)
+    logger.info(f"Loading {base_reverse_dns_map_file_path}")
+    known_domains = []
+    with open(base_reverse_dns_map_file_path) as f:
+        for row in csv.DictReader(f):
+            domain = row["base_reverse_dns"].lower().strip()
+            if domain in known_domains:
+                logger.warning(
+                    f"{domain} is in {base_reverse_dns_map_file_path} multiple times"
+                )
+            else:
+                known_domains.append(domain)
+            if domain in known_unknown_domains and known_domains:
+                pass
+                logger.warning(
+                    f"{domain} is in {known_unknown_list_file_path} and \
+                        {base_reverse_dns_map_file_path}"
+                )
+
+    logger.info(f"Checking domains against {base_reverse_dns_map_file_path}")
+    with open(input_csv_file_path) as f:
+        for row in csv.DictReader(f):
+            domain = row["source_name"].lower().strip()
+            if domain == "":
+                continue
+            for psl_domain in psl_overrides:
+                if domain.endswith(psl_domain):
+                    domain = psl_domain
+                    break
+            if domain not in known_domains and domain not in known_unknown_domains:
+                logger.info(f"New unknown domain found: {domain}")
+                output_rows.append(row)
+    logger.info(f"Writing {output_csv_file_path}")
+    with open(output_csv_file_path, "w") as f:
+        writer = csv.DictWriter(f, fieldnames=csv_headers)
+        writer.writeheader()
+        writer.writerows(output_rows)
+
+
+if __name__ == "__main__":
+    _main()

parsedmarc/resources/maps/known_unknown_base_reverse_dns.txt

@@ -0,0 +1,309 @@
+185.in-addr.arpa
+190.in-addr.arpa
+200.in-addr.arpa
+9services.com
+a7e.ru
+a94434500-blog.com
+abv-10.top
+adlucrumnewsletter.com
+admin.corpivensa.gob.ve
+advantageiq.com
+advrider.ro
+aerospacevitro.us.com
+agenturserver.de
+aghories.com
+ai270.net
+albagroup-eg.com
+alchemy.net
+anchorfundhub.com
+anglishment.com
+anteldata.net.uy
+antis.edu
+antonaoll.com
+anviklass.org
+anwrgrp.lat
+aosau.net
+arandomserver.com
+aransk.ru
+ardcs.cn
+as29550.net
+asmecam.it
+aurelienvos.com
+automatech.lat
+avistaadvantage.com
+b8sales.com
+bearandbullmarketnews.com
+bestinvestingtime.com
+biocorp.com
+bitter-echo.com
+blguss.com
+bluenet.ch
+bluhosting.com
+bodiax.pp.ua
+bost-law.com
+brainity.com
+brnonet.cz
+brushinglegal.de
+brw.net
+budgeteasehub.com
+buoytoys.com
+cashflowmasterypro.com
+cavabeen.com
+cbti.net
+checkpox.fun
+chegouseuvlache.org
+christus.mx
+ckaik.cn
+cloud-edm.com
+cloudaccess.net
+cloudflare-email.org
+cloudhosting.rs
+cloudlogin.co
+cnode.io
+code-it.net
+colombiaceropapel.org
+commerceinsurance.com
+coolblaze.com
+coowo.com
+corpemail.net
+cp2-myorderbox.com
+cps.com.ar
+ctla.co.kr
+dastans.ru
+datahost36.de
+descarca-counter-strike.net
+detrot.xyz
+digi.net.my
+dinofelis.cn
+diwkyncbi.top
+dkginternet.com
+dns-oid.com
+domconfig.com
+doorsrv.com
+dreampox.fun
+dreamtechmedia.com
+ds.network
+dvj.theworkpc.com
+dwlcka.com
+dyntcorp.com
+economiceagles.com
+egosimail.com
+emailgids.net
+emailperegrine.com
+entretothom.net
+epsilon-group.com
+erestaff.com
+example.com
+exposervers.com-new
+eyecandyhosting.xyz
+fetscorp.shop
+fin-crime.com
+financeaimpoint.com
+financeupward.com
+flex-video.bnr.la
+formicidaehunt.net
+fosterheap.com
+frontiernet.net
+gendns.com
+getthatroi.com
+gigidea.net
+giize.com
+ginous.eu.com
+gist-th.com
+gophermedia.com
+gqlists.us.com
+gratzl.de
+greatestworldnews.com
+greennutritioncare.com
+h-serv.co.uk
+hgnbroken.us.com
+hosting1337.com
+hostinglotus.cloud
+hostingmichigan.com
+hostiran.name
+hostmnl.com
+hostname.localhost
+hostnetwork.com
+hosts.net.nz
+hostwhitelabel.com
+hpms1.jp
+hypericine.com
+i-mecca.net
+iaasdns.com
+iam.net.ma
+iconmarketingguy.com
+idcfcloud.net
+idealconcept.live
+igppevents.org.uk
+imjtmn.cn
+immenzaces.com
+inshaaegypt.com
+ip-147-135-108.us
+ip-178-33-109.eu
+ip-ptr.tech
+itsidc.com
+itwebs.com
+ivol.co
+jalanet.co.id
+jimishare.com
+jumanra.org
+kahlaa.com
+kbronet.com.tw
+kdnursing.org
+kihy.theworkpc.com
+kitchenaildbd.com
+layerdns.cloud
+legenditds.com
+lighthouse-media.com
+listertermoformadoa.com
+llsend.com
+lohkal.com
+lonestarmm.net
+longwoodmgmt.com
+lwl-puehringer.at
+lynx.net.lb
+magnetmail.net
+mail-fire.com
+manhattanbulletpoint.com
+manpowerservices.com
+marketmysterycode.com
+marketwizardspro.com
+masterclassjournal.com
+matroguel.cam
+maximpactipo.com
+mechanicalwalk.store
+mediavobis.com
+misorpresa.com
+moderntradingnews.com
+moonjaws.com
+morningnewscatcher.com
+motion4ever.net
+mschosting.com
+msdp1.com
+mspnet.pro
+mts-nn.ru
+mxserver.ro
+mxthunder.net
+myrewards.net
+mysagestore.com
+mysecurewebserver.com
+myvps.jp
+name.tools
+nanshenqfurniture.com
+nask.pl
+ncport.ru
+ncsdi.ws
+nebdig.com
+neovet-base.ru
+netbri.com
+netkl.org
+newinvestingguide.com
+newwallstreetcode.com
+ngvcv.cn
+nic.name
+nidix.net
+nlscanme.com
+nmeuh.cn
+noisndametal.com
+nwo.giize.com
+offerslatedeals.com
+office365.us
+ogicom.net
+omegabrasil.inf.br
+onnet21.com
+oppt-ac.fit
+orbitel.net.co
+ovaltinalization.co
+overta.ru
+panaltyspot.space
+passionatesmiles.com
+perimetercenter.net
+permanentscreen.com
+phdns3.es
+planethoster.net
+plesk.page
+pmnhost.net
+pokupki5.ru
+popiup.com
+ports.net
+prima.com.ar
+prima.net.ar
+prohealthmotion.com
+proudserver.com
+psnm.ru
+pvcwindowsprices.live
+qontenciplc.autos
+quatthonggiotico.com
+rapidns.com
+raxa.host
+reliablepanel.com
+rgb365.eu
+riddlecamera.net
+rwdhosting.ca
+s500host.com
+sahacker-2020.com
+samsales.site
+saransk.ru
+satirogluet.com
+seaspraymta3.net
+secorp.mx
+securen.net
+securerelay.in
+securev.net
+servershost.biz
+silvestrejaguar.sbs
+silvestreonca.sbs
+siriuscloud.jp
+sisglobalresearch.com
+smallvillages.com
+smartape-vps.com
+solusoftware.com
+spiritualtechnologies.io
+sprout.org
+stableserver.net
+stockepictigers.com
+stockexchangejournal.com
+suksangroup.com
+sysop4.com
+system.eu.com
+szhongbing.com
+t-jon.com
+tecnoxia.net
+tel-xyz.fit
+tenkids.net
+terminavalley.com
+thaicloudsolutions.com
+thaimonster.com
+thepushcase.com
+totaal.net
+traderlearningcenter.com
+tullostrucking.com
+ultragate.com
+unite.services
+urawasl.com
+us.servername.us
+varvia.de
+vendimetry.com
+vibrantwellnesscorp.com
+viviotech.us
+vlflgl.com
+volganet.ru
+wallstreetsgossip.com
+wealthexpertisepro.com
+web-login.eu
+weblinkinternational.com
+webnox.io
+welllivinghive.com
+wisdomhard.com
+wisewealthcircle.com
+wsiph2.com
+xnt.mx
+xpnuf.cn
+xsfati.us.com
+xspmail.jp
+yourciviccompass.com
+yourinvestworkbook.com
+yoursitesecure.net
+zerowebhosting.net
+znlc.jp
+ztomy.com

parsedmarc/resources/maps/psl_overrides.txt

@@ -0,0 +1,6 @@
+akura.ne.jp
+amazonaws.com
+cloudaccess.net
+h-serv.co.uk
+linode.com
+plesk.page

parsedmarc/resources/maps/sortmaps.py

@@ -0,0 +1,59 @@
+#!/usr/bin/env python3
+
+import os
+import csv
+
+maps_dir = os.path.join(".")
+map_files = ["base_reverse_dns_map.csv"]
+list_files = ["known_unknown_base_reverse_dns.txt", "psl_overrides.txt"]
+
+
+def sort_csv(filepath, column=0):
+    with open(filepath, mode="r", newline="") as infile:
+        reader = csv.reader(infile)
+        header = next(reader)
+        sorted_rows = sorted(reader, key=lambda row: row[column])
+        existing_values = []
+        for row in sorted_rows:
+            if row[column] in existing_values:
+                print(f"Warning: {row[column]} is in {filepath} multiple times")
+
+    with open(filepath, mode="w", newline="\n") as outfile:
+        writer = csv.writer(outfile)
+        writer.writerow(header)
+        writer.writerows(sorted_rows)
+
+
+def sort_list_file(
+    filepath,
+    lowercase=True,
+    strip=True,
+    deduplicate=True,
+    remove_blank_lines=True,
+    ending_newline=True,
+    newline="\n",
+):
+    with open(filepath, mode="r", newline=newline) as infile:
+        lines = infile.readlines()
+        for i in range(len(lines)):
+            if lowercase:
+                lines[i] = lines[i].lower()
+            if strip:
+                lines[i] = lines[i].strip()
+        if deduplicate:
+            lines = list(set(lines))
+        if remove_blank_lines:
+            while "" in lines:
+                lines.remove("")
+        lines = sorted(lines)
+        if ending_newline:
+            if lines[-1] != "":
+                lines.append("")
+    with open(filepath, mode="w", newline=newline) as outfile:
+        outfile.write("\n".join(lines))
+
+
+for csv_file in map_files:
+    sort_csv(os.path.join(maps_dir, csv_file))
+for list_file in list_files:
+    sort_list_file(os.path.join(maps_dir, list_file))

parsedmarc/splunk.py

@@ -5,7 +5,7 @@ import json
 import urllib3
 import requests
 
-from parsedmarc import __version__
+from parsedmarc.constants import USER_AGENT
 from parsedmarc.log import logger
 from parsedmarc.utils import human_timestamp_to_unix_timestamp
 
@@ -51,7 +51,7 @@ class HECClient(object):
         self._common_data = dict(host=self.host, source=self.source, index=self.index)
 
         self.session.headers = {
-            "User-Agent": "parsedmarc/{0}".format(__version__),
+            "User-Agent": USER_AGENT,
             "Authorization": "Splunk {0}".format(self.access_token),
         }
 

parsedmarc/utils.py

@@ -19,10 +19,11 @@ import csv
 import io
 
 try:
-    import importlib.resources as pkg_resources
+    from importlib.resources import files
 except ImportError:
-    # Try backported to PY<37 `importlib_resources`
-    import importlib_resources as pkg_resources
+    # Try backported to PY<3 `importlib_resources`
+    from importlib.resources import files
+
 
 from dateutil.parser import parse as parse_date
 import dns.reversename
@@ -36,7 +37,7 @@ import requests
 from parsedmarc.log import logger
 import parsedmarc.resources.dbip
 import parsedmarc.resources.maps
-
+from parsedmarc.constants import USER_AGENT
 
 parenthesis_regex = re.compile(r"\s*\(.*\)\s*")
 
@@ -280,14 +281,13 @@ def get_ip_address_country(ip_address, db_path=None):
                 break
 
     if db_path is None:
-        with pkg_resources.path(
-            parsedmarc.resources.dbip, "dbip-country-lite.mmdb"
-        ) as path:
-            db_path = path
+        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):
-            logger.warning("IP database is more than a month old")
+    db_age = datetime.now() - datetime.fromtimestamp(os.stat(db_path).st_mtime)
+    if db_age > timedelta(days=30):
+        logger.warning("IP database is more than a month old")
 
     db_reader = geoip2.database.Reader(db_path)
 
@@ -344,21 +344,30 @@ def get_service_from_reverse_dns_base_domain(
 
     if not (offline or always_use_local_file) and len(reverse_dns_map) == 0:
         try:
-            logger.debug(f"Trying to fetch " f"reverse DNS map from {url}...")
-            csv_file.write(requests.get(url).text)
+            logger.debug(f"Trying to fetch reverse DNS map from {url}...")
+            headers = {"User-Agent": USER_AGENT}
+            response = requests.get(url, headers=headers)
+            response.raise_for_status()
+            csv_file.write(response.text)
             csv_file.seek(0)
             load_csv(csv_file)
         except requests.exceptions.RequestException as e:
             logger.warning(f"Failed to fetch reverse DNS map: {e}")
+        except Exception:
+            logger.warning("Not a valid CSV file")
+            csv_file.seek(0)
+            logging.debug("Response body:")
+            logger.debug(csv_file.read())
+
     if len(reverse_dns_map) == 0:
         logger.info("Loading included reverse DNS map...")
-        with pkg_resources.path(
-            parsedmarc.resources.maps, "base_reverse_dns_map.csv"
-        ) as path:
-            if local_file_path is not None:
-                path = local_file_path
-            with open(path) as csv_file:
-                load_csv(csv_file)
+        path = str(
+            files(parsedmarc.resources.maps).joinpath("base_reverse_dns_map.csv")
+        )
+        if local_file_path is not None:
+            path = local_file_path
+        with open(path) as csv_file:
+            load_csv(csv_file)
     try:
         service = reverse_dns_map[base_domain]
     except KeyError:

parsedmarc/webhook.py

@@ -1,6 +1,7 @@
 import requests
 
 from parsedmarc import logger
+from parsedmarc.constants import USER_AGENT
 
 
 class WebhookClient(object):
@@ -21,7 +22,7 @@ class WebhookClient(object):
         self.timeout = timeout
         self.session = requests.Session()
         self.session.headers = {
-            "User-Agent": "parsedmarc",
+            "User-Agent": USER_AGENT,
             "Content-Type": "application/json",
         }
 

pyproject.toml

@@ -1,6 +1,6 @@
 [build-system]
 requires = [
-    "hatchling>=1.8.1",
+    "hatchling>=1.27.0",
 ]
 build-backend = "hatchling.build"
 
@@ -59,7 +59,7 @@ dependencies = [
 
 [project.optional-dependencies]
 build = [
-    "hatch",
+    "hatch>=1.14.0",
     "myst-parser[linkify]",
     "nose",
     "pytest",
@@ -76,9 +76,20 @@ parsedmarc = "parsedmarc.cli:_main"
 Homepage = "https://domainaware.github.io/parsedmarc"
 
 [tool.hatch.version]
-path = "parsedmarc/__init__.py"
+path = "parsedmarc/constants.py"
 
 [tool.hatch.build.targets.sdist]
 include = [
     "/parsedmarc",
 ]
+
+[tool.hatch.build]
+exclude = [
+"base_reverse_dns.csv",
+"find_bad_utf8.py",
+"find_unknown_base_reverse_dns.py",
+"unknown_base_reverse_dns.csv",
+"sortmaps.py",
+"README.md",
+"*.bak"
+]

splunk/smtp_tls_dashboard.xml

@@ -0,0 +1,107 @@
+<form version="1.1" theme="dark">
+  <label>SMTP TLS Reporting</label>
+  <fieldset submitButton="false" autoRun="true">
+    <input type="time" token="time">
+      <label></label>
+      <default>
+        <earliest>-7d@h</earliest>
+        <latest>now</latest>
+      </default>
+    </input>
+    <input type="text" token="organization_name" searchWhenChanged="true">
+      <label>Organization name</label>
+      <default>*</default>
+      <initialValue>*</initialValue>
+    </input>
+    <input type="text" token="policy_domain">
+      <label>Policy domain</label>
+      <default>*</default>
+      <initialValue>*</initialValue>
+    </input>
+    <input type="dropdown" token="policy_type" searchWhenChanged="true">
+      <label>Policy type</label>
+      <choice value="*">Any</choice>
+      <choice value="tlsa">tlsa</choice>
+      <choice value="sts">sts</choice>
+      <choice value="no-policy-found">no-policy-found</choice>
+      <default>*</default>
+      <initialValue>*</initialValue>
+    </input>
+  </fieldset>
+  <row>
+    <panel>
+      <title>Reporting organizations</title>
+      <table>
+        <search>
+          <query>index=email sourcetype=smtp:tls organization_name=$organization_name$ policies{}.policy_domain=$policy_domain$
+| rename policies{}.policy_domain as policy_domain
+| rename policies{}.policy_type as policy_type
+| rename policies{}.failed_session_count as failed_sessions
+| rename policies{}.failure_details{}.failed_session_count as failed_sessions
+| rename policies{}.successful_session_count as successful_sessions
+| rename policies{}.failure_details{}.sending_mta_ip as sending_mta_ip
+| rename policies{}.failure_details{}.receiving_ip as receiving_ip
+| rename policies{}.failure_details{}.receiving_mx_hostname as receiving_mx_hostname
+| rename policies{}.failure_details{}.result_type as failure_type
+| fillnull value=0 failed_sessions
+| stats sum(failed_sessions) as failed_sessions sum(successful_sessions) as successful_sessions by organization_name
+| sort -successful_sessions 0</query>
+          <earliest>$time.earliest$</earliest>
+          <latest>$time.latest$</latest>
+        </search>
+        <option name="drilldown">none</option>
+        <option name="refresh.display">progressbar</option>
+      </table>
+    </panel>
+    <panel>
+      <title>Domains</title>
+      <table>
+        <search>
+          <query>index=email sourcetype=smtp:tls organization_name=$organization_name$ policies{}.policy_domain=$policy_domain$
+| rename policies{}.policy_domain as policy_domain
+| rename policies{}.policy_type as policy_type
+| rename policies{}.failed_session_count as failed_sessions
+| rename policies{}.failure_details{}.failed_session_count as failed_sessions
+| rename policies{}.successful_session_count as successful_sessions
+| rename policies{}.failure_details{}.sending_mta_ip as sending_mta_ip
+| rename policies{}.failure_details{}.receiving_ip as receiving_ip
+| rename policies{}.failure_details{}.receiving_mx_hostname as receiving_mx_hostname
+| rename policies{}.failure_details{}.result_type as failure_type
+| fillnull value=0 failed_sessions
+| stats sum(failed_sessions) as failed_sessions sum(successful_sessions) as successful_sessions  by policy_domain
+| sort -successful_sessions 0</query>
+          <earliest>$time.earliest$</earliest>
+          <latest>$time.latest$</latest>
+        </search>
+        <option name="drilldown">none</option>
+        <option name="refresh.display">progressbar</option>
+      </table>
+    </panel>
+  </row>
+  <row>
+    <panel>
+      <title>Failure details</title>
+      <table>
+        <search>
+          <query>index=email sourcetype=smtp:tls organization_name=$organization_name$ policies{}.policy_domain=$policy_domain$ policies{}.failure_details{}.result_type=*
+| rename policies{}.policy_domain as policy_domain
+| rename policies{}.policy_type as policy_type
+| rename policies{}.failed_session_count as failed_sessions
+| rename policies{}.failure_details{}.failed_session_count as failed_sessions
+| rename policies{}.successful_session_count as successful_sessions
+| rename policies{}.failure_details{}.sending_mta_ip as sending_mta_ip
+| rename policies{}.failure_details{}.receiving_ip as receiving_ip
+| rename policies{}.failure_details{}.receiving_mx_hostname as receiving_mx_hostname
+| fillnull value=0 failed_sessions
+| rename policies{}.failure_details{}.result_type as failure_type
+| table _time organization_name policy_domain policy_type failed_sessions successful_sessions sending_mta_ip receiving_ip receiving_mx_hostname failure_type
+| sort by -_time 0</query>
+          <earliest>$time.earliest$</earliest>
+          <latest>$time.latest$</latest>
+        </search>
+        <option name="drilldown">none</option>
+        <option name="refresh.display">progressbar</option>
+      </table>
+    </panel>
+  </row>
+</form>