#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Robust outlier removal for per-satellite TLE record sequences.

Why: raw TLE archives contain corrupted records (bad element fields, wrong
epochs, mis-decoded mean anomaly / rev counter). These single-point outliers
poison linear interpolation onto the daily grid and the angle unwrapping. The
cm-tle-pred benchmark reports that outlier removal (DBSCAN on 1st/2nd-order
differences of the elements) gave their single biggest accuracy gain (~2 orders
of magnitude). We use a cheaper, dependency-free equivalent: flag any record
whose element deviates from a time-linear interpolation of its neighbors by more
than ``k_mad`` robust (MAD) scales, on the elements that should evolve smoothly.

Cleaning runs on the raw record list BEFORE daily resampling / unwrapping.
"""

from __future__ import annotations

import sys
from pathlib import Path
from typing import List, Tuple

import numpy as np

# reuse the parser's record type + helpers from the original code/utils
_CODE_UTILS = Path(__file__).resolve().parents[2] / "code" / "utils"
if str(_CODE_UTILS) not in sys.path:
    sys.path.insert(0, str(_CODE_UTILS))
from tle_future_dataset import TLERecord, signed_log1p  # noqa: E402

SECONDS_PER_DAY = 86400.0


def cumulative_mean_anomaly(recs: List[TLERecord]) -> np.ndarray:
    """Unwrap mean anomaly into a monotone cumulative phase (deg).

    Revolution count between epochs is disambiguated with the mean motion
    (rev/day), which is far more reliable than the TLE rev-counter field.
    """
    n = len(recs)
    phi = np.empty(n, dtype=np.float64)
    phi[0] = recs[0].mean_anomaly_deg
    for i in range(1, n):
        dt_days = (recs[i].epoch_unix - recs[i - 1].epoch_unix) / SECONDS_PER_DAY
        n_avg = 0.5 * (recs[i].mean_motion_rev_per_day + recs[i - 1].mean_motion_rev_per_day)
        predicted = phi[i - 1] + n_avg * dt_days * 360.0
        m_i = recs[i].mean_anomaly_deg
        k = round((predicted - m_i) / 360.0)
        phi[i] = 360.0 * k + m_i
    return phi


def _neighbor_interp_resid(t: np.ndarray, x: np.ndarray) -> np.ndarray:
    """Residual of each interior point vs a time-linear interp of its neighbors."""
    resid = np.zeros_like(x, dtype=np.float64)
    if len(x) < 3:
        return resid
    t0, t1, t2 = t[:-2], t[1:-1], t[2:]
    denom = np.where((t2 - t0) == 0, 1.0, (t2 - t0))
    w = (t1 - t0) / denom
    x_hat = x[:-2] + (x[2:] - x[:-2]) * w
    resid[1:-1] = x[1:-1] - x_hat
    return resid


def _mad(v: np.ndarray) -> float:
    v = v[np.isfinite(v)]
    if v.size == 0:
        return 0.0
    med = np.median(v)
    return float(1.4826 * np.median(np.abs(v - med)))


def clean_records(
    recs: List[TLERecord], k_mad: float = 6.0, max_passes: int = 2,
) -> Tuple[List[TLERecord], int]:
    """Remove single-point outlier records. Returns (cleaned, n_removed).

    Flags the union of outliers across the smoothly-evolving quantities:
    mean motion, inclination, eccentricity, bstar(log), and the cumulative /
    unwrapped angles (mean anomaly phase, RAAN, argp).
    """
    recs = sorted(recs, key=lambda r: r.epoch_unix)
    removed = 0
    for _ in range(max_passes):
        n = len(recs)
        if n < 5:
            break
        t = np.array([r.epoch_unix for r in recs], dtype=np.float64)
        series = {
            "mm": np.array([r.mean_motion_rev_per_day for r in recs]),
            "inc": np.array([r.inclination_deg for r in recs]),
            "ecc": np.array([r.eccentricity for r in recs]),
            "bstar": np.array([signed_log1p(r.bstar) for r in recs]),
            "phiM": cumulative_mean_anomaly(recs),
            "raan": np.degrees(np.unwrap(np.radians([r.raan_deg for r in recs]))),
            "argp": np.degrees(np.unwrap(np.radians([r.argp_deg for r in recs]))),
        }
        flag = np.zeros(n, dtype=bool)
        for s in series.values():
            resid = _neighbor_interp_resid(t, s)
            scale = _mad(resid[1:-1])
            if scale > 0:
                flag |= np.abs(resid) > (k_mad * scale)
        flag[0] = flag[-1] = False  # keep endpoints (no two-sided neighbors)
        if not flag.any():
            break
        recs = [r for r, bad in zip(recs, flag) if not bad]
        removed += int(flag.sum())
    return recs, removed