fix: decode RFC2047 subjects, OR TO/FROM in to-mode query, tz-aware Date, drop LIST completion line (v0.1.7)

Subject headers were matched/scanned raw (never RFC2047-decoded), so any
provider that base64/quoted-printable encodes non-ASCII subjects silently
failed subject filtering and code extraction. match_field='to' only
server-queried TO, so an older TO-matching message permanently hid a
forwarded-From match the client-side check was documented to accept.
_age_seconds treated a naive datetime (from a "-0000" Date header) as local
time instead of UTC, corrupting max_age freshness on non-UTC hosts. get_folders
appended aioimaplib's tagged LIST completion text as a phantom folder name on
every call against any RFC-compliant server.

Also corrects __init__.py's __version__, which was left at 0.1.5 through the
0.1.6 release.

Signed-off-by: disqualifier <dev@disqualifier.me>

.gitignore

@@ -1,5 +1,5 @@
 # claude
-CLAUDE.md
+.claude/
 
 # python
 __pycache__/

README.md

@@ -11,21 +11,23 @@ This reads codes from email; it does not generate them (that is `pyotp`'s job).
 `requirements.txt`:
 
 ```
-aiomail @ git+ssh://git@git.rethinkstudios.io/rethink-public/aiomail.git@v0.1.0
+aiomail @ git+ssh://git@git.rethinkstudios.io/rethink-public/aiomail.git@v0.1.7
 # OAuth token providers (Microsoft / Google) need the extra:
-aiomail[oauth] @ git+ssh://git@git.rethinkstudios.io/rethink-public/aiomail.git@v0.1.0
+aiomail[oauth] @ git+ssh://git@git.rethinkstudios.io/rethink-public/aiomail.git@v0.1.7
 ```
 
 Direct:
 
 ```bash
-pip install "aiomail @ git+ssh://git@git.rethinkstudios.io/rethink-public/aiomail.git@v0.1.0"
+pip install "aiomail @ git+ssh://git@git.rethinkstudios.io/rethink-public/aiomail.git@v0.1.7"
-pip install "aiomail[oauth] @ git+ssh://git@git.rethinkstudios.io/rethink-public/aiomail.git@v0.1.0"
+pip install "aiomail[oauth] @ git+ssh://git@git.rethinkstudios.io/rethink-public/aiomail.git@v0.1.7"
 ```
 
 Requires `aioimaplib` and `beautifulsoup4` (pulled transitively). The `oauth`
 extra adds `aiohttp` for the refresh-token providers.
 
+Drop the `@v0.1.7` suffix from the line above to install the latest unpinned.
+
 ## Password auth
 
 ```python
@@ -64,6 +66,9 @@ await retrieve_otp(client, sender=re.compile(r"no-?reply@.*\.io")) # regex
 await retrieve_otp(client, sender=lambda f: f.endswith("@x.com"))  # callable
 ```
 
+Subject headers are RFC2047-decoded before matching/extraction, so providers
+that encode non-ASCII subjects (`=?utf-8?B?...?=`) still match on plain text.
+
 Code extraction is tunable too — `patterns` (regexes, first group wins) and
 `lengths` (standalone digit-run fallback):
 

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "aiomail"
-version = "0.1.0"
+version = "0.1.7"
 description = "async IMAP one-time-code retrieval with password/OAuth2 auth and dynamic matching"
 requires-python = ">=3.10"
 dependencies = [

src/aiomail/__init__.py

@@ -11,6 +11,7 @@ from .extract import (
     DEFAULT_PATTERNS,
     MatchSpec,
     as_predicate,
+    decode_header_value,
     extract_code,
 )
 from .retrieve import DEFAULT_FOLDERS, retrieve_otp
@@ -22,6 +23,7 @@ __all__ = [
     "IMAPClient",
     "extract_code",
     "as_predicate",
+    "decode_header_value",
     "retrieve_otp",
     "MatchSpec",
     "DEFAULT_PATTERNS",
@@ -29,4 +31,4 @@ __all__ = [
     "DEFAULT_FOLDERS",
 ]
 
-__version__ = "0.1.0"
+__version__ = "0.1.7"

src/aiomail/auth.py

@@ -38,6 +38,15 @@ class PasswordAuth:
             raise RuntimeError(f"login failed: {result} {data}")
 
 
+def _as_str(token) -> str:
+    """coerce a token to str (a provider may hand back bytes)
+
+    both XOAUTH2 entrypoints downstream need a str (one .encode()s it, the SASL
+    builder interpolates it), so normalize here rather than crashing on bytes.
+    """
+    return token.decode() if isinstance(token, bytes) else token
+
+
 def _sasl_xoauth2(user: str, token: str) -> str:
     """build the base64 XOAUTH2 SASL initial-response string"""
     raw = f"user={user}\x01auth=Bearer {token}\x01\x01".encode()
@@ -71,18 +80,23 @@ class OAuth2Auth:
             token = await result if hasattr(result, "__await__") else result
             if not token:
                 raise RuntimeError("token provider returned an empty token")
-            return token
+            return _as_str(token)
-        return self._token  # type: ignore[return-value]
+        return _as_str(self._token)  # type: ignore[arg-type]
 
     async def authenticate(self, mail) -> None:
         token = await self._resolve_token()
-        # aioimaplib exposes mail.xoauth2(user, token: bytes) — note the token must
+        # aioimaplib's mail.xoauth2(user, token) builds the SASL string by f-string
-        # be bytes, not str. older/other clients that lack it but expose a generic
+        # interpolating the token, so token MUST be str — passing bytes interpolates
-        # authenticate() are driven via the SASL string from _sasl_xoauth2.
+        # the b'...' repr and corrupts the Bearer value. _resolve_token already
+        # returns str (via _as_str). clients lacking .xoauth2 are driven via the
+        # SASL callback from _sasl_xoauth2.
         xoauth2 = getattr(mail, "xoauth2", None)
         if xoauth2 is not None:
-            result, data = await xoauth2(self.user, token.encode())
+            result, data = await xoauth2(self.user, token)
         elif hasattr(mail, "authenticate"):
+            # escape hatch for a non-aioimaplib client: the shipped aioimaplib IMAP4
+            # always has .xoauth2 and never .authenticate, so this branch never runs
+            # for it; the SASL-callback signature here is untested against any driver
             result, data = await mail.authenticate(
                 "XOAUTH2", lambda _: _sasl_xoauth2(self.user, token)
             )

src/aiomail/client.py

@@ -4,11 +4,22 @@ a thin, provider-agnostic client: it owns the connection lifecycle (connect with
 retries, reconnect-on-stale, close) and exposes the handful of operations the OTP
 flow needs (folders, search, fetch, mark-seen). auth is injected, so the same
 client serves password and OAuth accounts.
+
+reconnect-on-stale re-selects whatever folder was selected before the drop, so
+search/fetch/store keep working against a reconnected session. sequence-number ids
+from before a reconnect are not valid afterward (a fresh SELECT can renumber the
+mailbox) — pass `use_uid=True` if ids need to survive a reconnect.
+
+concurrency: one `IMAPClient` instance is not safe to drive from multiple
+concurrent tasks/coroutines without external serialization; connect/reconnect
+internally uses a lock to avoid corrupting `_mail`, but overlapping calls to the
+same instance are not the intended usage pattern.
 """
 import asyncio
 import email
 import email.message
 import logging
+import re
 from typing import List, Optional
 
 from aioimaplib import IMAP4, IMAP4_SSL
@@ -17,6 +28,27 @@ from .auth import Auth
 
 log = logging.getLogger(__name__)
 
+# IMAP LIST reply: (flags) "<delim>" <name>  — delim is server-defined (often "/" or
+# "." or NIL); capture the trailing name regardless, quoted or bare
+_LIST_RE = re.compile(rb'^\([^)]*\)\s+(?:"[^"]*"|NIL)\s+(.+)$')
+
+
+def _folder_name(raw: bytes) -> Optional[str]:
+    """extract the folder name from a LIST reply line, delimiter-agnostic
+
+    parses the real reply form `(flags) "<delim>" <name>` so any server hierarchy
+    delimiter works (not just "/"); returns None if the line doesn't match the
+    canonical shape. aioimaplib appends the tagged completion text (e.g. `b"LIST
+    completed."`) as the final entry of the same response list that carries the
+    untagged LIST lines — it never matches LIST syntax, so returning None here
+    (instead of a last-token rsplit fallback) lets the caller drop it instead of
+    treating it as a phantom folder name.
+    """
+    match = _LIST_RE.match(raw.strip())
+    if not match:
+        return None
+    return match.group(1).decode().strip().strip('"')
+
 
 class IMAPClient:
     """connection-managing IMAP client driven by an injected auth mechanism
@@ -45,6 +77,8 @@ class IMAPClient:
         self.timeout = timeout
         self.max_retries = max_retries
         self._mail = None
+        self._selected_folder: Optional[str] = None
+        self._lock = asyncio.Lock()
 
     async def __aenter__(self) -> "IMAPClient":
         await self.ensure_connection()
@@ -54,8 +88,21 @@ class IMAPClient:
         await self.close()
 
     async def connect(self) -> bool:
-        """open a connection and authenticate, retrying with linear backoff"""
+        """open a connection and authenticate, retrying with linear backoff
-        await self.close()
+
+        serialized by an internal lock: concurrent callers on the same instance queue
+        up rather than tearing down each other's in-progress handshake. a connection
+        superseded while a caller waited is logged out, never silently overwritten.
+        """
+        async with self._lock:
+            return await self._connect_locked()
+
+    async def _connect_locked(self) -> bool:
+        """connect()'s body; caller must hold self._lock"""
+        superseded, self._mail = self._mail, None
+        self._selected_folder = None
+        if superseded is not None:
+            await self._discard_mail(superseded)
         for attempt in range(self.max_retries):
             try:
                 if self.use_ssl:
@@ -67,36 +114,90 @@ class IMAPClient:
                 return True
             except Exception as exc:
                 log.warning("connect attempt %d/%d failed: %s", attempt + 1, self.max_retries, exc)
-                self._mail = None
+                if self._mail is not None:
+                    await self._discard_mail(self._mail)
+                    self._mail = None
                 await asyncio.sleep(2 * (attempt + 1))
         return False
 
+    @staticmethod
+    async def _discard_mail(mail) -> None:
+        """tear down a half-built IMAP4 without leaking its connect task
+
+        aioimaplib's IMAP4 schedules `create_connection` as a fire-and-forget task it
+        never retrieves; on a refused connection that task raises and asyncio logs a
+        noisy "Task exception was never retrieved" traceback. cancel/await it here (and
+        retrieve its exception) before discarding, so a failed connect stays quiet.
+        """
+        task = getattr(mail, "_client_task", None)
+        if task is not None and not task.done():
+            task.cancel()
+        if task is not None:
+            try:
+                await task
+            except (asyncio.CancelledError, Exception):
+                pass
+        try:
+            await mail.logout()
+        except Exception as teardown:
+            log.debug("logout error ignored during failed connect: %s", teardown)
+
     async def close(self) -> None:
         """log out and drop the connection, swallowing teardown errors"""
+        async with self._lock:
+            await self._close_locked()
+
+    async def _close_locked(self) -> None:
+        """close()'s body; caller must hold self._lock"""
         if self._mail is not None:
+            mail, self._mail = self._mail, None
             try:
-                await self._mail.logout()
+                await mail.logout()
             except Exception as exc:
                 log.debug("logout error ignored: %s", exc)
-            self._mail = None
+        self._selected_folder = None
 
     async def ensure_connection(self) -> bool:
-        """return a live connection, reconnecting if the link is stale"""
+        """return a live, SELECTED-if-applicable connection, reconnecting if the link is stale
-        if self._mail is None:
-            return await self.connect()
-        try:
-            await self._mail.noop()
-            return True
-        except Exception:
-            return await self.connect()
 
-    def is_throttled(self) -> bool:
+        a reconnect only re-authenticates (state AUTH); if a folder was selected before
-        """best-effort detection of a provider throttling response"""
+        the drop, it is re-selected here so search/fetch/store keep working afterward.
-        return bool(
+        note: sequence-number ids from before the reconnect are NOT valid against the
-            self._mail is not None
+        new session (a fresh SELECT can renumber/re-EXISTS the mailbox) unless
-            and getattr(self._mail, "resp", None)
+        use_uid=True, in which case UIDs remain stable across the reconnect.
-            and "THROTTLED" in str(self._mail.resp)
+
-        )
+        serialized by an internal lock, so concurrent callers on the same instance
+        never race each other's connect/reconnect; a caller that waits behind another
+        rechecks liveness first instead of tearing down a connection that just came up.
+        """
+        async with self._lock:
+            if self._mail is not None:
+                try:
+                    await self._mail.noop()
+                    return True
+                except Exception:
+                    pass
+            return await self._connect_and_reselect_locked()
+
+    async def _connect_and_reselect_locked(self) -> bool:
+        """connect() then re-select the previously-selected folder; caller must hold self._lock"""
+        folder = self._selected_folder
+        if not await self._connect_locked():
+            return False
+        if folder is None:
+            return True
+        try:
+            result, _ = await self._mail.select(f'"{folder}"')
+        except Exception as exc:
+            log.debug("re-select %s after reconnect failed: %s", folder, exc)
+            self._selected_folder = None
+            return False
+        if result != "OK":
+            log.debug("re-select %s after reconnect failed: %s", folder, result)
+            self._selected_folder = None
+            return False
+        self._selected_folder = folder
+        return True
 
     async def get_folders(self) -> List[str]:
         """list mailbox folder names"""
@@ -110,9 +211,11 @@ class IMAPClient:
         folders: List[str] = []
         for folder in folder_list or []:
             try:
-                folders.append(folder.decode().split(' "/" ')[-1].strip('"'))
+                name = _folder_name(folder)
             except Exception:
                 continue
+            if name is not None:
+                folders.append(name)
         return folders
 
     async def select(self, folder: str) -> bool:
@@ -121,10 +224,13 @@ class IMAPClient:
             return False
         try:
             result, _ = await self._mail.select(f'"{folder}"')
-            return result == "OK"
         except Exception as exc:
             log.debug("select %s failed: %s", folder, exc)
             return False
+        if result == "OK":
+            self._selected_folder = folder
+            return True
+        return False
 
     async def search(self, query: str) -> List[int]:
         """search the selected folder, returning ids newest-first"""
@@ -138,7 +244,14 @@ class IMAPClient:
             return []
         if result != "OK" or not data or not data[0]:
             return []
-        ids = [int(x) for x in data[0].split()]
+        ids = []
+        for token in data[0].split():
+            try:
+                ids.append(int(token))
+            except (TypeError, ValueError):
+                # tolerate a malformed/non-numeric token in the SEARCH response
+                # instead of crashing the whole search
+                log.debug("skipping non-numeric search token: %r", token)
         return sorted(set(ids), reverse=True)
 
     async def fetch(self, email_id: int, *, icloud: bool = False) -> Optional[email.message.Message]:
@@ -157,8 +270,14 @@ class IMAPClient:
         if result != "OK" or not data:
             return None
         for item in data:
-            if isinstance(item, (bytes, bytearray)) and len(item) > 20:
+            # aioimaplib stores the literal message payload as the only bytearray in
+            # the response; every other line (including the `<id> FETCH (...` header)
+            # is plain bytes. select by structure, not length — a length heuristic
+            # mismatches the header line for any 2+ digit id or a BODY[]/UID fetch.
+            if isinstance(item, bytearray):
                 return email.message_from_bytes(bytes(item))
+            # cross-version fallback: aioimaplib 2.0.x never yields tuples here, but an
+            # imaplib-style (header, payload) tuple is handled if a future/alt driver does
             if isinstance(item, tuple) and len(item) > 1:
                 return email.message_from_bytes(item[1])
         return None

src/aiomail/extract.py

@@ -8,6 +8,7 @@ filter senders and subjects.
 import email.message
 import logging
 import re
+from email.header import decode_header, make_header
 from typing import Callable, Iterable, Iterator, Optional, Pattern, Sequence, Union
 
 from bs4 import BeautifulSoup
@@ -39,6 +40,23 @@ def _compile(patterns: Sequence[Union[str, Pattern]]) -> list[Pattern]:
     return out
 
 
+def decode_header_value(raw: str) -> str:
+    """decode an RFC2047 encoded-word header (=?charset?B/Q?...?=) to text
+
+    messages are parsed with email.message_from_bytes (compat32 policy), which
+    leaves encoded-word headers raw; decode before scanning so the subject-first
+    pass sees real text instead of base64/quoted-printable. falls back to the
+    raw value if decoding fails.
+    """
+    if not raw:
+        return raw
+    try:
+        return str(make_header(decode_header(raw)))
+    except (UnicodeDecodeError, LookupError, ValueError) as exc:
+        log.debug("header decode failed (%s): %s", raw, exc)
+        return raw
+
+
 def _decode_part(part: email.message.Message) -> Optional[str]:
     """decode a single message part to text, tolerating bad charsets"""
     payload = part.get_payload(decode=True)
@@ -76,7 +94,7 @@ def _scan(text: str, patterns: list[Pattern], lengths: set[int]) -> Optional[str
             return m.group(1) if m.groups() else m.group(0)
     for token in re.split(r"\s+", text):
         digits = "".join(c for c in token if c.isdigit())
-        if digits and len(digits) in lengths and digits.isdigit():
+        if digits and len(digits) in lengths:
             return digits
     return None
 
@@ -97,7 +115,7 @@ def extract_code(
     compiled = _compile(patterns)
     length_set = set(lengths)
 
-    subject = message.get("Subject", "") or ""
+    subject = decode_header_value(message.get("Subject", "") or "")
     hit = _scan(subject, compiled, length_set)
     if hit:
         return hit
@@ -121,6 +139,8 @@ def as_predicate(spec: MatchSpec) -> Callable[[Optional[str]], bool]:
     if isinstance(spec, re.Pattern):
         return lambda value: bool(spec.search(value or ""))
     if callable(spec):
-        return spec
+        # coalesce None like the string/regex branches so the documented Optional[str]
+        # predicate contract holds even if a caller's callable assumes a real string
+        return lambda value: bool(spec(value or ""))
     needle = str(spec).lower()
     return lambda value: needle in (value or "").lower()

src/aiomail/oauth.py

@@ -6,6 +6,7 @@ without aiohttp raises a clear error only when a provider is instantiated.
 
 credentials (client_id, refresh_token) are always supplied by the caller.
 """
+import asyncio
 import logging
 import time
 from typing import Optional, Sequence
@@ -75,18 +76,21 @@ class _RefreshTokenProvider:
                     async with aiohttp.ClientSession(timeout=timeout) as session:
                         async with session.post(endpoint, data=data) as resp:
                             if resp.status == 200:
-                                token = (await resp.json()).get("access_token")
+                                # content_type=None: some token endpoints return a 200 with
+                                # text/plain or text/javascript; default json() would raise
+                                # ContentTypeError and discard a valid token body
+                                token = (await resp.json(content_type=None)).get("access_token")
                                 if token:
                                     self._failures = 0
                                     return token
                             else:
-                                body = await resp.text()
+                                # log a truncated error body only — a token-endpoint
+                                # response can carry sensitive material; never dump it whole
+                                body = (await resp.text())[:200]
                                 log.warning("token endpoint %s -> %s: %s", endpoint, resp.status, body)
                 except Exception as exc:
                     log.warning("token request to %s failed: %s", endpoint, exc)
             if attempt < self.max_retries - 1:
-                import asyncio
-
                 await asyncio.sleep(2 ** attempt)
 
         self._failures += 1

src/aiomail/retrieve.py

@@ -8,11 +8,19 @@ branches inside the function.
 import asyncio
 import logging
 import time
+from datetime import timezone
 from email.utils import parsedate_to_datetime
 from typing import Iterable, List, Optional, Pattern, Sequence, Union
 
 from .client import IMAPClient
-from .extract import DEFAULT_LENGTHS, DEFAULT_PATTERNS, MatchSpec, as_predicate, extract_code
+from .extract import (
+    DEFAULT_LENGTHS,
+    DEFAULT_PATTERNS,
+    MatchSpec,
+    as_predicate,
+    decode_header_value,
+    extract_code,
+)
 
 log = logging.getLogger(__name__)
 
@@ -20,16 +28,23 @@ log = logging.getLogger(__name__)
 DEFAULT_FOLDERS: Sequence[str] = ("INBOX", "Junk", "Spam", "Archive", "All Mail")
 
 
-def _server_query(sender: MatchSpec, subject: MatchSpec) -> str:
+def _server_query(sender: MatchSpec, subject: MatchSpec, match_field: str = "from") -> str:
     """build a narrowing IMAP query from plain-string specs only
 
-    only plain strings translate to server-side FROM/SUBJECT filters; regex and
+    only plain strings translate to server-side filters; regex and callable specs
-    callable specs fall back to ALL and are filtered client-side, so dynamic
+    fall back to ALL and are filtered client-side, so dynamic matching always works
-    matching always works even when the server cannot express it.
+    even when the server cannot express it. `match_field` selects which header the
+    `sender` spec searches: "from" filters by the sender address (default); "to"
+    filters by the recipient address (the per-user alias the code was sent to) OR
+    the From header, matching the client-side check's forwarded-From fallback so
+    the server query never narrows out a result the client would have accepted.
     """
     parts: List[str] = []
     if isinstance(sender, str):
-        parts.append(f'FROM "{sender}"')
+        if match_field == "to":
+            parts.append(f'OR TO "{sender}" FROM "{sender}"')
+        else:
+            parts.append(f'FROM "{sender}"')
     if isinstance(subject, str):
         parts.append(f'SUBJECT "{subject}"')
     return f"({' '.join(parts)})" if parts else "ALL"
@@ -41,7 +56,13 @@ def _age_seconds(message) -> Optional[float]:
     if not raw:
         return None
     try:
-        return time.time() - parsedate_to_datetime(raw).timestamp()
+        dt = parsedate_to_datetime(raw)
+        if dt.tzinfo is None:
+            # parsedate_to_datetime returns a naive datetime for a "-0000" zone
+            # (RFC 2822: unknown/unspecified offset); treat it as UTC rather
+            # than letting .timestamp() interpret the wall time as local
+            dt = dt.replace(tzinfo=timezone.utc)
+        return time.time() - dt.timestamp()
     except (TypeError, ValueError) as exc:
         log.debug("date parse failed (%s): %s", raw, exc)
         return None
@@ -52,6 +73,7 @@ async def retrieve_otp(
     *,
     sender: MatchSpec = None,
     subject: MatchSpec = None,
+    match_field: str = "from",
     folders: Optional[Iterable[str]] = None,
     patterns: Sequence[Union[str, Pattern]] = DEFAULT_PATTERNS,
     lengths: Iterable[int] = DEFAULT_LENGTHS,
@@ -64,14 +86,18 @@ async def retrieve_otp(
 ) -> Optional[str]:
     """return the newest OTP matching the filters, or None
 
-    sender/subject accept a substring, a compiled regex, or a callable. folders,
+    sender/subject accept a substring, a compiled regex, or a callable. `match_field`
-    patterns, code lengths, max age and retry behavior are all tunable. set
+    selects which header the `sender` spec is matched against: "from" (default)
-    `max_age=None` to disable the freshness check.
+    matches the sender address; "to" matches the recipient address (the per-user
+    alias the code was sent to) and additionally accepts a forwarded match on the
+    From header, so a forwarded code still resolves. folders, patterns, code lengths,
+    max age and retry behavior are all tunable. set `max_age=None` to disable the
+    freshness check.
     """
     folders = list(folders) if folders is not None else list(DEFAULT_FOLDERS)
     sender_ok = as_predicate(sender)
     subject_ok = as_predicate(subject)
-    query = _server_query(sender, subject)
+    query = _server_query(sender, subject, match_field)
 
     for attempt in range(retries + 1):
         for folder in folders:
@@ -90,8 +116,13 @@ async def retrieve_otp(
                     continue
 
                 from_hdr = message.get("From", "")
-                subj_hdr = message.get("Subject", "")
+                subj_hdr = decode_header_value(message.get("Subject", ""))
-                if not sender_ok(from_hdr) or not subject_ok(subj_hdr):
+                if match_field == "to":
+                    to_hdr = message.get("To", "")
+                    matched = sender_ok(to_hdr) or sender_ok(from_hdr)
+                else:
+                    matched = sender_ok(from_hdr)
+                if not matched or not subject_ok(subj_hdr):
                     continue
 
                 code = extract_code(message, patterns=patterns, lengths=lengths)