stealergram/config.py

"""
config.py — Loads and validates all settings from .env
"""

import json
import logging
import os
from pathlib import Path
from dotenv import load_dotenv

load_dotenv()

log = logging.getLogger(__name__)

# -- Timeouts --
BOT_REPLY_TIMEOUT = 10

# ─── Telegram credentials ────────────────────────────────────────────────────
API_ID   = int(os.environ["API_ID"])
API_HASH = os.environ["API_HASH"]
BOT_TOKEN = os.environ["BOT_TOKEN"]
NOTIFY_CHAT_ID = int(os.environ["NOTIFY_CHAT_ID"])
SESSION_NAME = os.getenv("SESSION_NAME", "monitor_session")

# ─── Runtime config path ─────────────────────────────────────────────────────
RUNTIME_CONFIG_PATH = Path("./data/runtime_config.json")

# ─── Hardcoded defaults (used when runtime_config.json is absent) ─────────────
# Add your org's domains, email patterns, IP ranges, known usernames, etc.
# All patterns are case-insensitive regex.
_DEFAULT_KEYWORDS: list[str] = [
    r"sanatorioaleman\.cl",
    r"@sanatorioaleman\.cl",
    # r"192\.168\.10\.",            # internal IP range example
    # r"specificuser",              # known internal usernames
]

# Use usernames (without @) or numeric channel IDs (-100xxxxxxxxxx)
_DEFAULT_CHANNELS: list[str | int] = [
    #-1002230225603,
    "cloudxlog",
    #-1001967030016, # daisycloud
    #"berserklogs", # berserklogs
    #"BorwitaFreeLogs", # borwita
    -1002748707556, # darkcloud
    -1001684073398, # BHF Cloud
    -1003163621939, # Wich Love from R
    -1003611713618, # Khazan Cloud
    -1003328682684, # LogsPlanet
    -1003204260194, # JDP
    -1002828367761, # HesoyamCloud
    -1003513974925, # Slurm Logs
    -1003599300787, # Arhont Corp
    -1002582513379, # OnlyLogs
    -1002788333372, # Ickis Cloud
    #-1001234567890,  # private channel by ID
]

# ─── Runtime config helpers ───────────────────────────────────────────────────

def _load_runtime_config() -> dict:
    """Load runtime_config.json; return empty dict if absent or malformed."""
    if not RUNTIME_CONFIG_PATH.exists():
        return {}
    try:
        with open(RUNTIME_CONFIG_PATH) as f:
            return json.load(f)
    except Exception as e:
        log.warning("Failed to load %s: %s", RUNTIME_CONFIG_PATH, e)
        return {}


def _keywords_from_groups(groups: list[dict]) -> list[str]:
    """Flatten all group patterns into a single keyword list."""
    return [p["regex"] for g in groups for p in g.get("patterns", [])]


# ─── Live config ──────────────────────────────────────────────────────────────
# Populated from runtime_config.json at import; falls back to hardcoded defaults.

_cfg = _load_runtime_config()

KEYWORD_GROUPS: list[dict] = _cfg.get("groups", [])
TARGET_KEYWORDS: list[str] = (
    _keywords_from_groups(KEYWORD_GROUPS) if KEYWORD_GROUPS else _DEFAULT_KEYWORDS
)
WATCHED_CHANNELS: list[str | int] = _cfg.get("channels", _DEFAULT_CHANNELS)


def save_runtime_config(groups: list[dict], channels: list[str | int]) -> None:
    """
    Persist keyword groups + channel list to runtime_config.json.
    Updates module globals so the running process sees the new values immediately.
    Called by web config routes after validating input.
    """
    global KEYWORD_GROUPS, TARGET_KEYWORDS, WATCHED_CHANNELS
    data = {"groups": groups, "channels": channels}
    RUNTIME_CONFIG_PATH.parent.mkdir(parents=True, exist_ok=True)
    with open(RUNTIME_CONFIG_PATH, "w") as f:
        json.dump(data, f, indent=2)
    KEYWORD_GROUPS = groups
    TARGET_KEYWORDS = _keywords_from_groups(groups) if groups else _DEFAULT_KEYWORDS
    WATCHED_CHANNELS = channels


# ─── File handling ───────────────────────────────────────────────────────────
TEMP_DIR  = Path("./tmp")
HITS_FILE = Path("./hits.txt")
LOG_FILE  = Path("./logs/monitor.log")

# Extensions to download and process
ALLOWED_EXTENSIONS = {".txt", ".zip", ".7z", ".rar"}

# Max file size to download (bytes). Default: 200 MB.
# Very large files are skipped to avoid abuse of your session.
MAX_FILE_SIZE = 4 * 1024 * 1024 * 1024  # 4 GB (Telegram Premium max)

# ─── Archive passwords to try ────────────────────────────────────────────────
ARCHIVE_PASSWORDS: list[bytes] = [
    b"1234",
    b"0000",
    b"infected",
    b"telegram",
    b"password",
    b"12345",
    b"",
    b"Borwita",
    b"@WichLoveFromR",
]

# ─── Backfill settings ───────────────────────────────────────────────────────
# How many historical messages to scan per channel on startup (0 = skip backfill)
BACKFILL_LIMIT = 500

# ─── tdl downloader settings ─────────────────────────────────────────────────
# Namespace tdl was logged into.  Run `tdl login` with no -n flag → namespace
# is "default".  Run `tdl login -n foo` → namespace is "foo".
# Set to None to omit -n entirely (tdl will use "default" anyway).
TDL_NAMESPACE: str | None = "ulpmon"

# Parallel chunk workers per file (-t / --threads global flag)
TDL_THREADS = 8

# Max concurrent files per tdl invocation (-l / --limit global flag)
TDL_PERFILE = 4

# Max messages to batch into a single tdl invocation during backfill.
# tdl handles the parallelism internally via -l and -t.
TDL_AMOUNT = 4

# Whether to use a Telegram takeout session for downloads (lower flood limits).
# Takeout sessions are rate-limited differently — good for bulk backfill.
TDL_TAKEOUT = True