wip: refactor

This commit is contained in:
Tim Bendt
2025-07-01 22:24:34 -04:00
parent bec09bade8
commit 5232bf3b09
66 changed files with 842 additions and 165 deletions

View File

@@ -0,0 +1,262 @@
"""
Mail operations for Microsoft Graph API.
"""
import os
import re
import glob
from typing import Set
import aiohttp
from .client import (
fetch_with_aiohttp,
patch_with_aiohttp,
post_with_aiohttp,
delete_with_aiohttp,
)
async def fetch_mail_async(
maildir_path,
attachments_dir,
headers,
progress,
task_id,
dry_run=False,
download_attachments=False,
):
"""
Fetch mail from Microsoft Graph API and save to Maildir.
Args:
maildir_path (str): Path to the Maildir.
attachments_dir (str): Path to save attachments.
headers (dict): Headers including authentication.
progress: Progress instance for updating progress bars.
task_id: ID of the task in the progress bar.
dry_run (bool): If True, don't actually make changes.
download_attachments (bool): If True, download email attachments.
Returns:
None
"""
from src.utils.mail_utils.maildir import save_mime_to_maildir_async
from utils.mail_utils.helpers import truncate_id
mail_url = "https://graph.microsoft.com/v1.0/me/mailFolders/inbox/messages?$top=100&$orderby=receivedDateTime asc&$select=id,subject,from,toRecipients,ccRecipients,receivedDateTime,isRead"
messages = []
# Fetch the total count of messages in the inbox
inbox_url = "https://graph.microsoft.com/v1.0/me/mailFolders/inbox"
response = await fetch_with_aiohttp(inbox_url, headers)
total_messages = response.get("totalItemCount", 0)
progress.update(task_id, total=total_messages)
while mail_url:
try:
response_data = await fetch_with_aiohttp(mail_url, headers)
except Exception as e:
progress.console.print(f"Error fetching messages: {e}")
continue
messages.extend(response_data.get("value", []))
progress.advance(task_id, len(response_data.get("value", [])))
# Get the next page URL from @odata.nextLink
mail_url = response_data.get("@odata.nextLink")
inbox_msg_ids = set(message["id"] for message in messages)
progress.update(task_id, completed=(len(messages) / 2))
new_dir = os.path.join(maildir_path, "new")
cur_dir = os.path.join(maildir_path, "cur")
new_files = set(glob.glob(os.path.join(new_dir, "*.eml*")))
cur_files = set(glob.glob(os.path.join(cur_dir, "*.eml*")))
for filename in Set.union(cur_files, new_files):
message_id = filename.split(".")[0].split("/")[
-1
] # Extract the Message-ID from the filename
if message_id not in inbox_msg_ids:
if not dry_run:
progress.console.print(f"Deleting {filename} from inbox")
os.remove(filename)
else:
progress.console.print(f"[DRY-RUN] Would delete {filename} from inbox")
for message in messages:
progress.console.print(
f"Processing message: {message.get('subject', 'No Subject')}", end="\r"
)
await save_mime_to_maildir_async(
maildir_path,
message,
attachments_dir,
headers,
progress,
dry_run,
download_attachments,
)
progress.update(task_id, advance=0.5)
progress.update(task_id, completed=len(messages))
progress.console.print(f"\nFinished saving {len(messages)} messages.")
async def archive_mail_async(maildir_path, headers, progress, task_id, dry_run=False):
"""
Archive mail from Maildir to Microsoft Graph API archive folder.
Args:
maildir_path (str): Path to the Maildir.
headers (dict): Headers including authentication.
progress: Progress instance for updating progress bars.
task_id: ID of the task in the progress bar.
dry_run (bool): If True, don't actually make changes.
Returns:
None
"""
archive_dir = os.path.join(maildir_path, ".Archives")
archive_files = glob.glob(os.path.join(archive_dir, "**", "*.eml*"), recursive=True)
progress.update(task_id, total=len(archive_files))
folder_response = await fetch_with_aiohttp(
"https://graph.microsoft.com/v1.0/me/mailFolders", headers
)
folders = folder_response.get("value", [])
archive_folder_id = next(
(
folder.get("id")
for folder in folders
if folder.get("displayName", "").lower() == "archive"
),
None,
)
if not archive_folder_id:
raise Exception("No folder named 'Archive' found on the server.")
for filepath in archive_files:
message_id = os.path.basename(filepath).split(".")[
0
] # Extract the Message-ID from the filename
if not dry_run:
status = await post_with_aiohttp(
f"https://graph.microsoft.com/v1.0/me/messages/{message_id}/microsoft.graph.move",
headers,
{"destinationId": archive_folder_id},
)
if status != 201: # 201 Created indicates success
progress.console.print(
f"Failed to move message to 'Archive': {message_id}, {status}"
)
if status == 404:
os.remove(filepath) # Remove the file from local archive if not found
progress.console.print(
f"Message not found on server, removed local copy: {message_id}"
)
elif status == 204:
progress.console.print(f"Moved message to 'Archive': {message_id}")
else:
progress.console.print(
f"[DRY-RUN] Would move message to 'Archive' folder: {message_id}"
)
progress.advance(task_id)
return
async def delete_mail_async(maildir_path, headers, progress, task_id, dry_run=False):
"""
Delete mail from Maildir and Microsoft Graph API.
Args:
maildir_path (str): Path to the Maildir.
headers (dict): Headers including authentication.
progress: Progress instance for updating progress bars.
task_id: ID of the task in the progress bar.
dry_run (bool): If True, don't actually make changes.
Returns:
None
"""
trash_dir = os.path.join(maildir_path, ".Trash", "cur")
trash_files = set(glob.glob(os.path.join(trash_dir, "*.eml*")))
progress.update(task_id, total=len(trash_files))
for filepath in trash_files:
message_id = os.path.basename(filepath).split(".")[
0
] # Extract the Message-ID from the filename
if not dry_run:
progress.console.print(f"Moving message to trash: {message_id}")
status = await delete_with_aiohttp(
f"https://graph.microsoft.com/v1.0/me/messages/{message_id}", headers
)
if status == 204 or status == 404:
os.remove(filepath) # Remove the file from local trash
else:
progress.console.print(f"[DRY-RUN] Would delete message: {message_id}")
progress.advance(task_id)
async def synchronize_maildir_async(
maildir_path, headers, progress, task_id, dry_run=False
):
"""
Synchronize Maildir with Microsoft Graph API.
Args:
maildir_path (str): Path to the Maildir.
headers (dict): Headers including authentication.
progress: Progress instance for updating progress bars.
task_id: ID of the task in the progress bar.
dry_run (bool): If True, don't actually make changes.
Returns:
None
"""
from src.utils.mail_utils.helpers import (
load_last_sync_timestamp,
save_sync_timestamp,
truncate_id,
)
last_sync = load_last_sync_timestamp()
# Find messages moved from "new" to "cur" and mark them as read
new_dir = os.path.join(maildir_path, "new")
cur_dir = os.path.join(maildir_path, "cur")
new_files = set(glob.glob(os.path.join(new_dir, "*.eml*")))
cur_files = set(glob.glob(os.path.join(cur_dir, "*.eml*")))
moved_to_cur = [os.path.basename(f) for f in cur_files - new_files]
progress.update(task_id, total=len(moved_to_cur))
for filename in moved_to_cur:
# TODO: this isn't scalable, we should use a more efficient way to check if the file was modified
if os.path.getmtime(os.path.join(cur_dir, filename)) < last_sync:
progress.update(task_id, advance=1)
continue
message_id = re.sub(
r"\:2.+", "", filename.split(".")[0]
) # Extract the Message-ID from the filename
if not dry_run:
status = await patch_with_aiohttp(
f"https://graph.microsoft.com/v1.0/me/messages/{message_id}",
headers,
{"isRead": True},
)
if status == 404:
os.remove(os.path.join(cur_dir, filename))
else:
progress.console.print(
f"[DRY-RUN] Would mark message as read: {truncate_id(message_id)}"
)
progress.advance(task_id)
# Save the current sync timestamp
if not dry_run:
save_sync_timestamp()
else:
progress.console.print("[DRY-RUN] Would save sync timestamp.")