Files
parsedmarc/tests/test_config.py
T
02fcfd6e82 Merge commit from fork
* Evict expired dedup-cache entries on insert and hash the key (GHSA-9fw6-mwqr-p43m)

The seen-aggregate-report cache is an expiringdict.ExpiringDict, which
removes an expired entry only when that same key is read again, or drops
its oldest entry once it holds max_len (100 million) entries. A report
that is never received again is never read again, so in watch mode every
distinct aggregate report stayed in memory for the life of the process.
The key was the JSON of the sender-controlled reporter, Report-ID and
policy domain, so ten 5.6 KB attachments with a 5 MiB report_id held
64 MiB indefinitely.

SeenReportCache (parsedmarc/config.py) subclasses ExpiringDict and removes
expired entries from the head of its insertion order on every insert;
the cache's max_len is now 100,000. _aggregate_report_dedup_key() now
returns the SHA-256 hex digest of that JSON, so a key is 64 characters
whatever the report contains.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* Keep a re-added dedup-cache key at the tail so the expiry sweep is not blocked

OrderedDict refreshes a re-set key's time in place, so a key added again while still stored kept its old position at the head and stopped the insert-time sweep before the expired entries behind it. SeenReportCache now moves such a key to the tail before storing it, keeping insertion order equal to age order.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

* Bound failed reverse-DNS lookups to 120 seconds per aggregate report (GHSA-rwfh-ww9c-jm9m)

Every record of an aggregate report made one blocking PTR lookup of a sender-chosen source IP, with no bound on count or time; an unanswering reverse zone costs the full 8 s DNS lifetime with the default nameservers, and a weak-fallback result is never cached, so one IP repeated in every record was looked up every time. A 3,500-record report could block processing for hours.

Lookups that return no PTR now share a 120-second budget per report; once it is spent, the remaining records are enriched from the local IP database only, their results are not cached, and one warning is logged. Each distinct source IP is looked up at most once per report, and lookups that find a PTR are not charged, so large legitimate reports keep their enrichment.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

* Keep values PostgreSQL rejects out of its output, and let one rejected report not hold the batch (GHSA-fxr7-7h9q-v949)

An aggregate count above 2**31 - 1, an SMTP TLS sending-mta-ip or
receiving-ip that is not an IP address, and a NUL in a failure report's
sample each made the PostgreSQL save raise PostgreSQLError, which marked
the whole mailbox batch unsaved, so legitimate reports from other senders
were never archived. The parser now skips a record whose count is outside
0..MAX_MESSAGE_COUNT and rejects such an SMTP TLS session count (closing
the same rejection in Elasticsearch/OpenSearch), drops an invalid TLS IP
with a warning, and the PostgreSQL output replaces NUL with U+FFFD in
text, text array and JSONB values. Any other psycopg.DataError raises the
new PostgreSQLRejectedReport, which the CLI logs and skips for that one
report unless fail_on_output_error is set.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

* Check an aggregate record's count before its reverse-DNS lookup

A record whose count is outside 0..MAX_MESSAGE_COUNT is dropped, so its
source IP is no longer looked up first, which could cost up to 8 seconds
per record. A regression test mocks dnspython and asserts that the dropped
record's address is never queried.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

* Require TLS for the PostgreSQL output by default and add [postgresql] sslmode and sslrootcert (GHSA-xvp7-7762-gx9g)

PostgreSQLClient connected without an sslmode, so libpq used its default,
prefer: when the server, or an on-path attacker, declined TLS, it continued
over plain TCP and answered a clear-text password request. The client now
passes sslmode=require unless the new sslmode argument, an sslmode in the
connection string, or PGSSLMODE chooses a mode, and sslrootcert names the
CA certificate for verify-ca and verify-full. A warning is logged at
startup when a TCP host other than localhost or a loopback address is used
with a mode that does not verify the server certificate. A malformed
connection string is now rejected by a parse before connecting, with the
same withheld-details error. A server without TLS fails with libpq's
"server does not support SSL, but SSL was required" until sslmode is set
to disable or prefer.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

* Withhold the hosts URL from Elasticsearch and OpenSearch client-build errors (GHSA-74xv-rmpx-2pjm)

A password with an unencoded "/", "?" or "#" in a [elasticsearch] or
[opensearch] hosts URL makes elastic_transport raise "Could not parse URL
'<url>'" and opensearch-py (via urllib.parse) raise "Port could not be cast
to integer value as '<password prefix>'". The startup wrapper repeated that
text at ERROR without --debug and chained the original, which the SIGHUP
reload's logger.exception printed again.

set_hosts() now runs through _set_search_hosts(), which replaces any
ValueError with a fixed message raised outside the except block. Other
errors in the block keep their text with URL credentials masked and are
raised from None. This completes the GHSA-hjr3-rx4c-24cv fix.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

* Cache the downloaded IP database in a private per-user directory and validate it (GHSA-5f56-8ph8-v9q5)

load_ip_db() cached the IPinfo Lite download at the fixed, shared
<tmp>/parsedmarc/ipinfo_lite.mmdb, where another local user could plant
a symlink to have the download overwrite a file the parsedmarc user can
write, or plant a database that was used whenever the download failed.

The cache now lives in $XDG_CACHE_HOME/parsedmarc or ~/.cache/parsedmarc
(%LOCALAPPDATA%\parsedmarc\cache on Windows), created 0700 and used only
if it is a real directory the user owns and can write that is not
group- or world-writable; otherwise a per-run mkdtemp() directory is
used. The download is written with mkstemp(), opened with maxminddb to
validate it, and moved into place with os.replace(). A cached copy is
used only if it is a regular file owned by the user.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

* Skip reports over the Logs Ingestion API size limit and publish the Log Analytics streams independently (GHSA-rg4h-58fm-8pc9)

The Azure Monitor ingestion SDK packs whole reports into chunks of up to
1 MiB and never splits one, so a report whose JSON is larger is sent as a
call of its own, and the Logs Ingestion API rejects any call over 1 MB
(https://learn.microsoft.com/en-us/azure/azure-monitor/fundamentals/service-limits).
The rejected upload raised before the failure and SMTP TLS streams were
sent, and the CLI held the whole batch for retry and finally Unsaved.

publish_json() now measures each report as the SDK does and leaves out
one over 1,000,000 bytes with a warning naming it, and publish_results()
publishes each stream in its own try and raises one LogAnalyticsException
naming every stream that failed.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

* Address review: redact the PostgreSQL warning host, drop the connect error chain, and fix Log Analytics and docs wording

libpq ends a URI's userinfo at the first "@", so the rest of a password
containing "@" becomes part of the host. The PostgreSQL startup warning
now credential-masks every host-like value it logs (host list entries,
hostaddr, PGHOST, PGHOSTADDR), checks hostaddr before host as libpq
does, and the general connect error is raised from None so the driver's
unredacted text no longer reaches a logged traceback. The CLI's
output-client Raises docs now say which outputs do not chain.

publish_json() returns the number of reports uploaded, and
publish_results() logs "Successfully pushed" only for a stream that
uploaded something.

The [postgresql] URI example uses the Unix socket and explains that TCP
to localhost needs TLS on the server or sslmode = disable, the
[log_analytics] docs note the SDK's 1 MiB call packing, the
reverse-DNS-budget wording says "local IP database and reverse DNS map"
everywhere, and the GHSA-fxr7 entry no longer claims the parser rejects
every unreadable start-datetime.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

* Require mailsuite 2.3.7

mailsuite 2.3.7 fixes parse_email() keeping a CRLF message's carriage
returns in address header values (seanthegeek/mailsuite#74). The floor
is raised in the base dependency and the msgraph, gmail and all extras,
and the usage docs' stated requirement is updated to match.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

* Drop Python 3.10 and add Python 3.15 to the supported versions and CI (#953)

Python 3.10 reaches end of life in October 2026. requires-python is now
>=3.11, the unused requires_python key under [build-system] (not read by
hatchling, and its <3.15 bound read as excluding 3.15) is removed, and
Python 3.15 joins the CI matrix, classifiers, and support tables. Docs,
AGENTS.md, and comments that named 3.10 as the floor are updated.

Co-authored-by: Claude Sonnet 5.5 <noreply@anthropic.com>

* Keep aggregate identifiers and reasons within their schema (#950)

* Keep aggregate identifiers and reasons within their schema

AI assistance: OpenAI Codex.

* Expand the #948 CHANGELOG entry and tighten its tests

RFC 9990 Appendix A and RFC 7489 Appendix C define only header_from,
envelope_from and envelope_to under identifiers, and only type and
comment in a reason. Cite them in the test, check that envelope_from
and envelope_to survive next to a dropped nested unknown element, and
cover an unknown key on the legacy identities path. The CHANGELOG
entry now names the affected outputs and the compatibility change.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

---------

Co-authored-by: Sean Whalen <44679+seanthegeek@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>

* Reject reports dated in the future and bound what parse_report_file() reads (#954)

* Reject reports whose index-naming date is more than two days in the future (#947)

The date that names a report's dated Elasticsearch/OpenSearch index (an
aggregate report's begin date, a failure report's Arrival-Date, an SMTP
TLS report's start-datetime) was never compared with the present, so a
report dated 2100 named an index for 2100. Each parser now rejects such a
report with its own Invalid*Report; past dates stay unbounded.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>

* Refuse an input larger than the report size cap before parse_report_file() reads it (#949)

The 32 MiB cap was applied only after the whole input was read. A path is
now checked with os.path.getsize(), bytes-like input with len(), and a
file object is read at most one byte past the cap. The error is the
ParserError with the message the content check already gives. Three
existing tests that fed over-cap content now see the earlier rejection.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>

* Measure a memoryview input by its byte size

len() of a memoryview counts items, which are not bytes for every format,
so the size cap in parse_report_file() compares nbytes instead.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>

* Bound the aggregate end date and read file objects to their end

Address the Copilot review of #954. A normalized report's per-day records
name their indexes from their own interval starts, so the report's end date
is bounded like its begin date. A raw stream may return fewer bytes than
asked for before its end, so parse_report_file() now reads in a loop until
end of file or one byte past the cap.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>

* Accumulate bounded reads in one buffer

Address the second Copilot review of #954. Keeping every chunk in a list
cost one bytes object per read, about 85 bytes per byte for a stream that
returns a byte at a time (22.7 MiB for 256 KiB of input). One bytearray
keeps memory proportional to the bytes read.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>

---------

Co-authored-by: Claude Sonnet 5.5 <noreply@anthropic.com>

* Skip a message with an invalid report attachment instead of aborting the mbox (#955)

* Skip a message with an invalid report attachment instead of aborting the mbox

parse_report_email() raised a bare ParserError when a report attachment was
invalid, which get_dmarc_reports_from_mbox() re-raises, so one such message
ended the whole file. Raise InvalidDMARCReport (a ParserError subclass), which
the mbox loop skips with a warning.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>

* Skip an invalid SMTP TLS attachment in an mbox too

Address the Copilot review of #955. An invalid SMTP TLS attachment raised
InvalidSMTPTLSReport, which is not an InvalidDMARCReport, so it still
stopped the mbox. parse_report_email() now names the message's subject in
that error, and both mbox loops skip it with a warning. A message that
cannot be parsed at all still raises a plain ParserError.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>

---------

Co-authored-by: Claude Sonnet 5.5 <noreply@anthropic.com>

* Address the second review: refuse an unencoded @ in a PostgreSQL URI, charge slow reverse-DNS lookups, and smaller fixes

- PostgreSQL: a connection string whose parsed host, hostaddr, port or
  dbname holds an "@" (the rest of a URI password with an unencoded "@",
  which libpq splits at the first "@") is refused with a fixed error
  before any warning is logged or any connection is attempted; _connect
  parses the string on every path. A leading "@" in a host entry (Linux
  abstract socket) is still allowed. _log_safe_host stays as defence in
  depth for the host argument and PGHOST/PGHOSTADDR.
- Log Analytics: publish_json catches AzureError, so a ServiceRequestError
  or ServiceResponseError no longer stops the remaining streams.
- MAX_MESSAGE_COUNT comment and CHANGELOG: the bound matches PostgreSQL's
  INTEGER columns and the Elasticsearch/OpenSearch integer mapping of the
  SMTP TLS session counts; the aggregate message_count is dynamically
  mapped as long.
- Reverse DNS budget: a lookup taking at least SLOW_REVERSE_DNS_SECONDS
  (1.0) is charged whether or not it returned a name; the warning now says
  "failed or were slow".
- An IPv6 zone ID in an aggregate record's source IP skips the record
  before any DNS lookup, and in a failure report's Source-IP raises
  InvalidFailureReport; one helper serves these and the SMTP TLS path.
- IP database cache: a relative candidate directory (HOME unset, no
  passwd entry) is rejected; offline / always_use_local_file creates no
  directory and no temporary directory and logs no "downloaded again".
- No startup warning for sslmode=require with an existing sslrootcert
  file, which libpq verifies as verify-ca.
- PostgreSQLRejectedReport truncates the driver text to 200 characters.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>

* Address the third review: refuse a URI with more than one @, bound total reverse-DNS time, strip IPv6 zone IDs

- postgres: a URI connection string (postgresql:// or postgres://) with
  more than one literal "@" is refused on the raw string, before any log
  line or connect, closing the abstract-socket host-list and query
  parameter bypasses of the parsed-value check. libpq decodes %40 in a
  password, host, database name and query value, so a URI never needs a
  second "@". The parsed-value check remains for keyword/value strings.
- Reverse DNS: every online lookup is charged to a new 600 s per-report
  total budget (MAX_REVERSE_DNS_SECONDS_PER_REPORT); failed or slow ones
  still also use the 120 s budget. The warning names the limit reached.
- An IPv6 zone ID in an aggregate source_ip or a failure report's
  Source-IP is now stripped with a warning instead of rejecting the
  record or report; SMTP TLS still drops its optional IP fields.
- _rejection_detail truncates the driver text before escaping it.
- Docs and CHANGELOG entries updated.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>

* Withhold everything derived from a PostgreSQL connection string from logs and errors

Fourth review of GHSA-xvp7-7762-gx9g: libpq ends a URI's userinfo at the
first "@" or "/", so postgresql://u:SECRETX/x@db.invalid/d parses to host
"u", port "SECRETX" and dbname "x@db.invalid/d". It has one "@", so the
raw-count refusal let it through, and connecting raised 'invalid integer
value "SECRETX" for connection option "port"', a password fragment in the
error and its traceback. A variant put the fragment in sslmode, which the
startup warning printed. Three rounds of shape checks each missed a shape.

A. With a connection_string, nothing parsed from it is logged or raised:
   - A connection failure raises a fixed "PostgreSQL connection failed
     (details withheld ...)" from None, with " [SQLSTATE xxxxx]" appended
     only when the driver error carries a well-formed SQLSTATE
     (^[0-9A-Z]{5}$). A string libpq cannot parse keeps its own fixed
     message, and any error from the pre-parse is replaced by it.
   - The startup warning names no host and no value from the string; the
     mode is printed only when it is one of SSL_MODES.
   With the separate host/port/user/password/database arguments, the
   driver's message (credential-masked) and the host in the warning are
   kept.

B. The early refusal stays as a convenience that names the common
   mistake, mirroring libpq's scan: a URI is refused when the text after
   "://" holds more than one "@", or an "@" with a "/" before it, and the
   parsed-value check (_has_misplaced_at) runs on URIs again as well as
   keyword/value strings. Docstrings, usage.md and the CHANGELOG now say
   the refusal is a convenience and A is what keeps the password out.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>

* Wrap every PostgreSQL connect failure and narrow the connection-string refusal

- postgres._connect(): everything from parsing the settings to holding a
  configured connection (pre-parse, ssl kwargs, connect, autocommit,
  dumper registration) is protected. A non-driver error (psycopg's
  UnicodeEncodeError carrying the whole built connection string for a
  password with a lone surrogate; on Python 3.15 the unwrapped
  UnicodeEncodeError('idna', '<host>') for an over-long host label) is
  replaced with a fixed message from None: the withheld connection
  failure message with a connection string, a new fixed "a connection
  setting could not be passed to the driver" message with the separate
  settings. KeyboardInterrupt/SystemExit still propagate.
- cli._init_output_clients(): the PostgreSQL wrapper no longer chains
  (from None), and a non-PostgreSQLError gets a fixed message.
- _has_unencoded_at() now mirrors libpq's URI scan (userinfo up to the
  first "@" or "/") instead of counting "@", so a percent-encoded
  database name (d%40x) and an "@" in a query value after a "/" (a
  certificate path) are accepted, while every password-spill shape in
  the table is still refused except two that read like legitimate
  strings.
- _has_misplaced_at() is removed: a keyword/value password is its own
  keyword, so an "@" in a kv host, hostaddr or dbname is not a password
  fragment, and libpq does not percent-decode kv values, so the encoding
  advice was wrong. The refusal message now names the database name.
- Docstrings, usage.md and the GHSA-xvp7 CHANGELOG entry updated; tests
  for real psycopg (surrogate password, long host label), fake-psycopg
  non-driver errors at connect/autocommit/dumpers for both modes, a
  KeyboardInterrupt check, the rule table (also checked against the real
  parser), legitimate strings that must connect, and the CLI wrapper.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: jwalith4418-Mj <jwalith4418@gmail.com>
2026-11-10 18:44:59 -05:00

246 lines
11 KiB
Python

"""Tests for parsedmarc.config"""
import dataclasses
import pickle
import time
import unittest
from collections import OrderedDict
from unittest import mock
import parsedmarc
import parsedmarc.config as parsedmarc_config
class TestParserConfigCaches(unittest.TestCase):
"""Covers per-instance cache isolation for `ParserConfig`."""
def test_each_instance_gets_isolated_caches(self):
"""Two independently constructed ParserConfig instances must never
share cache objects with each other or with the module defaults, and
mutating one instance's caches must not leak into the others."""
cfg_a = parsedmarc_config.ParserConfig()
cfg_b = parsedmarc_config.ParserConfig()
# All distinct objects.
self.assertIsNot(cfg_a.ip_address_cache, cfg_b.ip_address_cache)
self.assertIsNot(
cfg_a.seen_aggregate_report_ids, cfg_b.seen_aggregate_report_ids
)
self.assertIsNot(cfg_a.reverse_dns_map, cfg_b.reverse_dns_map)
self.assertIsNot(cfg_a.ip_address_cache, parsedmarc_config.IP_ADDRESS_CACHE)
self.assertIsNot(
cfg_a.seen_aggregate_report_ids,
parsedmarc_config.SEEN_AGGREGATE_REPORT_IDS,
)
self.assertIsNot(cfg_a.reverse_dns_map, parsedmarc_config.REVERSE_DNS_MAP)
self.assertIsNot(cfg_b.ip_address_cache, parsedmarc_config.IP_ADDRESS_CACHE)
self.assertIsNot(
cfg_b.seen_aggregate_report_ids,
parsedmarc_config.SEEN_AGGREGATE_REPORT_IDS,
)
self.assertIsNot(cfg_b.reverse_dns_map, parsedmarc_config.REVERSE_DNS_MAP)
# Mutating one instance's caches must not affect the other, nor the
# module defaults.
cfg_a.ip_address_cache["1.2.3.4"] = {"ip_address": "1.2.3.4"}
cfg_a.seen_aggregate_report_ids["report-id-a"] = True
cfg_a.reverse_dns_map["example.com"] = {"name": "Example", "type": None}
self.assertNotIn("1.2.3.4", cfg_b.ip_address_cache)
self.assertNotIn("report-id-a", cfg_b.seen_aggregate_report_ids)
self.assertNotIn("example.com", cfg_b.reverse_dns_map)
self.assertNotIn("1.2.3.4", parsedmarc_config.IP_ADDRESS_CACHE)
self.assertNotIn("report-id-a", parsedmarc_config.SEEN_AGGREGATE_REPORT_IDS)
self.assertNotIn("example.com", parsedmarc_config.REVERSE_DNS_MAP)
def test_module_default_caches_are_the_public_globals(self):
"""The three module-default caches in `parsedmarc.config` must be the
very same objects re-exported as `parsedmarc.IP_ADDRESS_CACHE`,
`parsedmarc.SEEN_AGGREGATE_REPORT_IDS`, and
`parsedmarc.REVERSE_DNS_MAP`, so that pre-refactor callers who
imported these names directly from the top-level package keep
observing the same cache objects as code that goes through
ParserConfig.
"""
self.assertIs(parsedmarc.IP_ADDRESS_CACHE, parsedmarc_config.IP_ADDRESS_CACHE)
self.assertIs(
parsedmarc.SEEN_AGGREGATE_REPORT_IDS,
parsedmarc_config.SEEN_AGGREGATE_REPORT_IDS,
)
self.assertIs(parsedmarc.REVERSE_DNS_MAP, parsedmarc_config.REVERSE_DNS_MAP)
class TestSeenReportCache(unittest.TestCase):
"""Covers `SeenReportCache`, the seen-aggregate-report-ID cache that
drops expired entries on insert (GHSA-9fw6-mwqr-p43m)."""
def test_expired_entry_is_removed_when_another_is_added(self):
"""An entry older than ``max_age`` is removed from storage when a
different key is added, not only when its own key is read again.
On a plain ``ExpiringDict`` the same sequence leaves both entries
stored (``len == 2``, measured against expiringdict 1.2.2), which is
how every distinct report stayed in memory for the life of a watch
process. ``len()`` and ``OrderedDict.keys()`` look at storage
directly; ``in`` would hide the stale entry by expiring it on read.
"""
cache = parsedmarc_config.SeenReportCache(max_len=100, max_age_seconds=3600)
cache.__setitem__("old", True, set_time=time.time() - 7200)
cache["new"] = True
self.assertEqual(len(cache), 1)
self.assertEqual(list(OrderedDict.keys(cache)), ["new"])
def test_unexpired_entry_survives_the_next_insert(self):
"""The sweep stops at the first entry that has not expired, so an
entry still inside ``max_age`` is kept and still reads as seen."""
cache = parsedmarc_config.SeenReportCache(max_len=100, max_age_seconds=3600)
cache.__setitem__("recent", True, set_time=time.time() - 60)
cache["new"] = True
self.assertEqual(len(cache), 2)
self.assertEqual(list(OrderedDict.keys(cache)), ["recent", "new"])
self.assertIn("recent", cache)
def test_re_added_key_moves_to_the_tail(self):
"""A key set again while still stored moves to the tail, so an
expired entry behind it is still swept on the next insert.
A is added, B a second later, A again 30 minutes later (still
unexpired, so the sweep keeps it), and C once B is over an hour old
but A is not. Without the move, ``OrderedDict.__setitem__`` refreshed
A in place at the head, the sweep stopped there, and B survived:
storage held ``['A', 'B', 'C']`` (measured on c8b3c26 with this same
fake clock).
"""
clock = [1_000_000.0]
with mock.patch("time.time", side_effect=lambda: clock[0]):
cache = parsedmarc_config.SeenReportCache(max_len=100, max_age_seconds=3600)
cache["A"] = True
clock[0] += 1
cache["B"] = True
clock[0] += 1800
cache["A"] = True
clock[0] += 1900
cache["C"] = True
self.assertEqual(list(OrderedDict.keys(cache)), ["A", "C"])
self.assertIn("A", cache)
def test_default_seen_report_cache_is_bounded(self):
"""The factory builds a `SeenReportCache` with a one-hour expiry and
a hard ceiling of 100,000 entries (it was 100 million)."""
cache = parsedmarc_config._new_seen_aggregate_report_ids()
self.assertIsInstance(cache, parsedmarc_config.SeenReportCache)
self.assertEqual(cache.max_len, 100_000)
self.assertEqual(cache.max_age, 3600)
self.assertIsInstance(
parsedmarc_config.SEEN_AGGREGATE_REPORT_IDS,
parsedmarc_config.SeenReportCache,
)
class TestParserConfigPickling(unittest.TestCase):
"""Covers the pickle strategy documented on `ParserConfig`: option fields
round-trip, but cache contents never cross process boundaries and the
unpickled object's caches rebind to the unpickling process's module
defaults."""
def test_pickle_drops_cache_contents_and_binds_process_defaults(self):
"""Pickling and unpickling a ParserConfig must preserve option
fields, but must NOT carry cache contents across the round-trip, and
must leave the unpickled instance's caches bound to this module's
(the "unpickling process's") default cache objects rather than
fresh, empty ones. Fresh-per-unpickle caches would silently defeat
per-worker caching, since a functools.partial payload carrying a
ParserConfig is re-pickled for every task submitted to a
multiprocessing worker."""
cfg = parsedmarc_config.ParserConfig(
dns_timeout=9.5, nameservers=["192.0.2.53"]
)
cfg.ip_address_cache["sentinel-ip"] = "sentinel-ip-value"
cfg.seen_aggregate_report_ids["sentinel-report-id"] = True
cfg.reverse_dns_map["sentinel.example"] = {
"name": "Sentinel",
"type": None,
}
restored = pickle.loads(pickle.dumps(cfg))
# Option fields compare equal (cache fields are compare=False).
self.assertEqual(cfg, restored)
self.assertEqual(restored.dns_timeout, 9.5)
self.assertEqual(restored.nameservers, ["192.0.2.53"])
# Caches rebind to this process's module defaults, not fresh copies.
self.assertIs(restored.ip_address_cache, parsedmarc_config.IP_ADDRESS_CACHE)
self.assertIs(
restored.seen_aggregate_report_ids,
parsedmarc_config.SEEN_AGGREGATE_REPORT_IDS,
)
self.assertIs(restored.reverse_dns_map, parsedmarc_config.REVERSE_DNS_MAP)
# Sentinel entries placed on the original instance's caches must NOT
# have crossed into the module defaults.
self.assertNotIn("sentinel-ip", parsedmarc_config.IP_ADDRESS_CACHE)
self.assertNotIn(
"sentinel-report-id", parsedmarc_config.SEEN_AGGREGATE_REPORT_IDS
)
self.assertNotIn("sentinel.example", parsedmarc_config.REVERSE_DNS_MAP)
def test_setstate_defaults_fields_missing_from_older_pickles(self):
"""__setstate__ must initialize every non-cache field to its class
default before applying the pickled state, so a ParserConfig
serialized by an older parsedmarc version (whose state lacks fields
added since) unpickles with the newer fields at their defaults
instead of unset — __init__ never runs during unpickling, so an
absent field would otherwise raise AttributeError on first access.
Simulated by calling __setstate__ directly with a partial state
dict, exactly what pickle.loads does with an old payload."""
restored = object.__new__(parsedmarc_config.ParserConfig)
restored.__setstate__({"offline": True, "dns_timeout": 7.5})
self.assertTrue(restored.offline)
self.assertEqual(restored.dns_timeout, 7.5)
# Fields absent from the old state get their class defaults.
self.assertIsNone(restored.ip_db_path)
self.assertIsNone(restored.nameservers)
self.assertEqual(restored.normalize_timespan_threshold_hours, 24.0)
# Caches still rebind to the module defaults.
self.assertIs(restored.ip_address_cache, parsedmarc_config.IP_ADDRESS_CACHE)
self.assertIs(
restored.seen_aggregate_report_ids,
parsedmarc_config.SEEN_AGGREGATE_REPORT_IDS,
)
self.assertIs(restored.reverse_dns_map, parsedmarc_config.REVERSE_DNS_MAP)
class TestParserConfigFrozenAndReplace(unittest.TestCase):
"""Covers frozen-dataclass immutability and the `dataclasses.replace`
escape hatch for deriving variants that keep sharing caches."""
def test_frozen_and_replace_shares_caches(self):
"""ParserConfig is frozen, so attribute assignment must raise
FrozenInstanceError. `dataclasses.replace(cfg, ...)` must return a
new config that shares the SAME cache objects as the source (all
fields, including the three cache fields, are init fields), since
that is the documented way to derive a variant that keeps warm
caches."""
cfg = parsedmarc_config.ParserConfig()
with self.assertRaises(dataclasses.FrozenInstanceError):
cfg.offline = True # type: ignore[misc]
variant = dataclasses.replace(cfg, offline=True)
self.assertTrue(variant.offline)
self.assertIs(variant.ip_address_cache, cfg.ip_address_cache)
self.assertIs(variant.seen_aggregate_report_ids, cfg.seen_aggregate_report_ids)
self.assertIs(variant.reverse_dns_map, cfg.reverse_dns_map)