duplicate-finder/app/sftp.py

"""
SFTP destination management — connection helpers and credential storage.

Credentials live at /data/sftp/{id}.password (mode 600) or /data/sftp/{id}.key
(also mode 600). Public host keys are pinned at /data/sftp/{id}.host_keys after
the first successful connection (TOFU); subsequent connections fail loudly if
the host key changes.
"""

import io
import os
import stat
import errno
from contextlib import contextmanager
from typing import Optional

import paramiko

CRED_DIR = "/data/sftp"


# ── Credential storage ───────────────────────────────────────────────────────

def _ensure_cred_dir() -> None:
    os.makedirs(CRED_DIR, mode=0o700, exist_ok=True)


def _password_path(dest_id: int) -> str:
    return os.path.join(CRED_DIR, f"{dest_id}.password")


def _key_path(dest_id: int) -> str:
    return os.path.join(CRED_DIR, f"{dest_id}.key")


def _host_keys_path(dest_id: int) -> str:
    return os.path.join(CRED_DIR, f"{dest_id}.host_keys")


def write_password(dest_id: int, password: str) -> None:
    _ensure_cred_dir()
    p = _password_path(dest_id)
    with open(p, "w") as f:
        f.write(password)
    os.chmod(p, 0o600)


def write_private_key(dest_id: int, key_text: str) -> None:
    _ensure_cred_dir()
    p = _key_path(dest_id)
    with open(p, "w") as f:
        f.write(key_text if key_text.endswith("\n") else key_text + "\n")
    os.chmod(p, 0o600)


def delete_credentials(dest_id: int) -> None:
    """Best-effort cleanup of all stored secrets for a destination."""
    for p in (_password_path(dest_id), _key_path(dest_id), _host_keys_path(dest_id)):
        try:
            if os.path.exists(p):
                os.unlink(p)
        except Exception:
            pass


def has_credentials(dest_id: int, auth_method: str) -> bool:
    if auth_method == "password":
        return os.path.isfile(_password_path(dest_id))
    if auth_method == "key":
        return os.path.isfile(_key_path(dest_id))
    return False


# ── Keypair generation ──────────────────────────────────────────────────────

def generate_keypair() -> tuple[str, str, str]:
    """Generate an ED25519 keypair. Returns (private_pem, public_openssh, fingerprint)."""
    key = paramiko.Ed25519Key.generate()
    priv_buf = io.StringIO()
    key.write_private_key(priv_buf)
    private_pem = priv_buf.getvalue()
    public_openssh = f"{key.get_name()} {key.get_base64()} dupfinder@miaai"
    fingerprint = key.fingerprint  # SHA-256:base64
    return private_pem, public_openssh, fingerprint


# ── Connection ──────────────────────────────────────────────────────────────

@contextmanager
def open_sftp(dest: dict, timeout: int = 15):
    """Open an SFTP session against the given destination dict.

    `dest` must contain: id, host, port, username, auth_method.
    Yields a paramiko.SFTPClient. Raises on any failure.
    """
    client = paramiko.SSHClient()

    # Pin host key on first success (TOFU). Reject on mismatch afterwards.
    hk_path = _host_keys_path(dest["id"])
    if os.path.isfile(hk_path):
        client.load_host_keys(hk_path)
        client.set_missing_host_key_policy(paramiko.RejectPolicy())
    else:
        # First connection — accept and persist
        client.set_missing_host_key_policy(paramiko.AutoAddPolicy())

    auth_kwargs = {}
    if dest["auth_method"] == "password":
        with open(_password_path(dest["id"])) as f:
            auth_kwargs["password"] = f.read()
        auth_kwargs["look_for_keys"] = False
        auth_kwargs["allow_agent"] = False
    elif dest["auth_method"] == "key":
        try:
            pkey = paramiko.Ed25519Key.from_private_key_file(_key_path(dest["id"]))
        except paramiko.SSHException:
            # Try RSA as fallback for user-pasted keys
            pkey = paramiko.RSAKey.from_private_key_file(_key_path(dest["id"]))
        auth_kwargs["pkey"] = pkey
        auth_kwargs["look_for_keys"] = False
        auth_kwargs["allow_agent"] = False
    else:
        raise ValueError(f"Unknown auth_method: {dest['auth_method']}")

    try:
        client.connect(
            hostname=dest["host"],
            port=int(dest.get("port") or 22),
            username=dest["username"],
            timeout=timeout,
            banner_timeout=timeout,
            auth_timeout=timeout,
            **auth_kwargs,
        )
        # Persist host key after first successful connect
        if not os.path.isfile(hk_path):
            _ensure_cred_dir()
            client.save_host_keys(hk_path)
        sftp = client.open_sftp()
        try:
            yield sftp
        finally:
            try:
                sftp.close()
            except Exception:
                pass
    finally:
        try:
            client.close()
        except Exception:
            pass


def test_connection(dest: dict) -> tuple[bool, str]:
    """Try to connect, chdir to base_path, list it. Returns (ok, message)."""
    try:
        with open_sftp(dest) as sftp:
            try:
                sftp.stat(dest["base_path"])
            except FileNotFoundError:
                return False, f"Base path does not exist: {dest['base_path']}"
            except IOError as e:
                if e.errno == errno.EACCES:
                    return False, f"No permission to access {dest['base_path']}"
                raise
            # Quick write probe — try to mkdir a temp dir, then remove it
            probe = f"{dest['base_path'].rstrip('/')}/.dupfinder_probe"
            try:
                sftp.mkdir(probe)
                sftp.rmdir(probe)
            except IOError:
                return False, f"Connected, but {dest['base_path']} is not writable"
        return True, "ok"
    except paramiko.AuthenticationException:
        return False, "Authentication failed"
    except paramiko.BadHostKeyException as e:
        return False, f"Host key mismatch (possible MITM): {e}"
    except paramiko.SSHException as e:
        return False, f"SSH error: {e}"
    except (TimeoutError, ConnectionError, OSError) as e:
        return False, f"Connection failed: {e}"
    except Exception as e:
        return False, f"Unexpected error: {e}"


# ── Path helpers ────────────────────────────────────────────────────────────

def remote_path_for(source_path: str, dest: dict, photos_root: str = "/photos") -> str:
    """Compute the remote destination path for a given source file.

    If mirror_structure is true, preserves the path under photos_root.
    Otherwise, lands flat in base_path with the source basename.
    """
    base = dest["base_path"].rstrip("/")
    if dest.get("mirror_structure", 1):
        rel = os.path.relpath(source_path, photos_root)
        # On Windows os.path.relpath uses backslashes; force forward
        rel = rel.replace("\\", "/")
        return f"{base}/{rel}"
    return f"{base}/{os.path.basename(source_path)}"