29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210 | class Sync:
"""Sync server state into local storage (server -> storage)."""
def __init__(self, session: ImapClient) -> None:
self._session = session
def orchestrate(
self,
storage: StorageABC,
mailbox: Optional[str] = None,
mailbox_names: Optional[list[str]] = None,
max_workers: int = 3,
skip_duplicates: bool = True,
) -> SyncResult:
"""Sync one or all mailboxes with progress and parallel fetch."""
names = (
[mailbox]
if mailbox
else mailbox_names or list(self._session.mailboxes)
)
combined = SyncResult(mailbox=mailbox or "*")
lock = Lock()
progress = Progress()
def sync_one(name: str, retries: int = 3) -> SyncResult:
task = None
for attempt in range(retries):
session = ImapClient(
server=self._session.server,
user=self._session.user,
password=self._session.password,
port=self._session.port,
ssl=self._session.ssl,
)
try:
session.connect()
except Exception as exc:
if attempt < retries - 1:
time.sleep(2**attempt)
continue
with lock:
progress.console.print(
f" [red]✗[/] {name} — connection failed: {exc}"
)
return SyncResult(mailbox=name)
try:
box = session.mailboxes[name]
server_count = box.where().count()
with lock:
task = progress.add_task(
f" [cyan]{name}",
total=max(server_count, 1),
completed=1 if server_count == 0 else 0,
)
def on_progress(done: int, total: int, _task=task) -> None:
with lock:
progress.update(_task, completed=done, total=total)
result = self.sync(
box,
storage,
on_progress=on_progress,
skip_duplicates=skip_duplicates,
)
with lock:
progress.update(task, visible=False)
msg = (
f" [green]✓[/] {name} — "
f"{result.inserted} new, "
f"{result.updated} updated, "
f"{result.skipped} skipped"
)
if result.has_errors:
msg += f", [red]{len(result.errors)} errors[/]"
progress.console.print(msg)
return result
except Exception as exc:
if attempt < retries - 1:
time.sleep(2**attempt)
continue
if task is not None:
with lock:
progress.update(task, visible=False)
with lock:
progress.console.print(
f" [red]✗[/] {name} — sync failed: {exc}"
)
return SyncResult(mailbox=name)
finally:
session.close()
return SyncResult(mailbox=name)
with (
progress,
ThreadPoolExecutor(
max_workers=min(max_workers, len(names))
) as pool,
):
futures = {pool.submit(sync_one, name): name for name in names}
for future in as_completed(futures):
combined = combined.merge(future.result())
return combined
def sync(
self,
mailbox: MailBox,
storage: StorageABC,
on_progress: Optional[Callable[[int, int], None]] = None,
skip_duplicates: bool = True,
) -> SyncResult:
"""Sync one mailbox from IMAP into local storage."""
result = SyncResult(mailbox=mailbox.name)
server_uids = mailbox.where().uids()
total = len(server_uids)
client = mailbox._client
if client is None:
return result
if skip_duplicates:
existing_ids = storage.ids(mailbox.name)
server_msg_ids = Fetch.fetch_message_ids(client, server_uids)
new_uids = [
uid
for uid, mid in server_msg_ids.items()
if mid not in existing_ids
]
else:
new_uids = server_uids
result.skipped = total - len(new_uids)
if on_progress is not None:
on_progress(result.skipped, total)
if not new_uids:
return result
done = result.skipped
fetch = Fetch(
client=client,
mailbox=mailbox,
spec=F.rfc822() + F.flags(),
chunk_size=CHUNK_FETCH,
)
for entry in fetch.parsed(new_uids):
done += 1
raw = RawSerializer(
message_id=entry.message_id,
uid=entry.uid,
mailbox=mailbox.name,
flags=entry.flags,
file=entry.text(),
)
try:
if storage.save(raw):
result.inserted += 1
else:
result.updated += 1
except Exception as exc:
logger.error("Failed to save %s: %s", raw.message_id, exc)
result.errors.append(f"{raw.message_id}: {exc}")
if on_progress is not None:
on_progress(done, total)
return result
|