import json

import polars as pl
import pytest
from pyproj import Transformer

from pipeline.transform.crime_spatial import transform_crime_spatial

_TO_WGS84 = Transformer.from_crs("EPSG:27700", "EPSG:4326", always_xy=True)

_CSV_HEADER = (
    "Crime ID,Month,Reported by,Falls within,Longitude,Latitude,Location,"
    "LSOA code,LSOA name,Crime type,Last outcome category,Context"
)

# Average-annual-count crime column name for a window (the filterable feature).
def _raw(t: str, window: str = "7y") -> str:
    return f"{t} (/yr, {window})"


def _bng_to_wgs84(x: float, y: float) -> tuple[float, float]:
    lon, lat = _TO_WGS84.transform(x, y)
    return lon, lat


def _square_feature(postcode: str, x0: float, y0: float, x1: float, y1: float) -> dict:
    ring = [(x0, y0), (x1, y0), (x1, y1), (x0, y1), (x0, y0)]
    coords = [list(_bng_to_wgs84(x, y)) for x, y in ring]
    return {
        "type": "Feature",
        "properties": {"postcodes": postcode, "mapit_code": postcode.replace(" ", "")},
        "geometry": {"type": "Polygon", "coordinates": [coords]},
    }


def _write_boundaries(units_dir, features_by_district: dict[str, list[dict]]) -> None:
    units_dir.mkdir(parents=True)
    for district, features in features_by_district.items():
        collection = {"type": "FeatureCollection", "features": features}
        (units_dir / f"{district}.geojson").write_text(json.dumps(collection))


def _crime_row(month: str, x, y, crime_type: str, location="On or near X", outcome="U") -> str:
    if x is None or y is None:
        lon, lat = "", ""
    else:
        lon, lat = _bng_to_wgs84(x, y)
    return f",{month},F,F,{lon},{lat},{location},E01000001,L,{crime_type},{outcome},"


def _write_month(
    crime_dir, month: str, rows: list[str], force: str = "test-force"
) -> None:
    """Write one force's monthly CSV; an empty ``rows`` list still creates the
    file, which counts as published coverage for that (force, month)."""
    month_dir = crime_dir / month
    month_dir.mkdir(parents=True, exist_ok=True)
    body = "\n".join([_CSV_HEADER, *rows]) + "\n"
    (month_dir / f"{month}-{force}-street.csv").write_text(body)


def _run(tmp_path, crime, units, **kwargs):
    """Run the transform and return (crime, by_year, records) DataFrames.

    The crime table carries the average-annual-count columns ("{type} (/yr, …)"),
    i.e. the raw, absolute number of recorded incidents per year.
    """
    crime_out = tmp_path / "crime_by_postcode.parquet"
    by_year = tmp_path / "crime_by_postcode_by_year.parquet"
    records = tmp_path / "crime_records.parquet"
    transform_crime_spatial(
        crime, units, crime_out, by_year, records, buffer_m=50.0, **kwargs
    )
    return (
        pl.read_parquet(crime_out),
        pl.read_parquet(by_year),
        pl.read_parquet(records),
    )


def test_buffer_overlap_counts_for_each_postcode(tmp_path):
    units = tmp_path / "units"
    # A and B sit 70m apart; their +50m buffers overlap in x in [1030, 1060].
    _write_boundaries(
        units,
        {
            "AB1": [
                _square_feature("AB1 1AA", 1000, 1000, 1010, 1010),
                _square_feature("AB1 1AB", 1080, 1000, 1090, 1010),
                _square_feature("AB1 1AC", 5000, 5000, 5010, 5010),
            ]
        },
    )

    crime = tmp_path / "crime"
    _write_month(
        crime,
        "2024-01",
        [
            # In the overlap: 35m east of A, 35m west of B -> counts for both.
            _crime_row("2024-01", 1045, 1005, "Burglary"),
            # 49m east of C's edge -> inside C's buffer.
            _crime_row("2024-01", 5059, 5005, "Robbery"),
            # 51m east of C's edge -> outside every buffer.
            _crime_row("2024-01", 5061, 5005, "Robbery"),
            # No coordinate -> dropped entirely.
            _crime_row("2024-01", None, None, "Anti-social behaviour"),
        ],
    )

    raw_df, _, _ = _run(tmp_path, crime, units)
    rows = {r["postcode"]: r for r in raw_df.to_dicts()}
    # Single covered month -> pooled raw rate x12.
    assert rows["AB1 1AA"][_raw("Burglary")] == 12.0
    assert rows["AB1 1AB"][_raw("Burglary")] == 12.0
    assert rows["AB1 1AA"][_raw("Robbery")] == 0.0
    # Only the 49m robbery counts for C; the 51m one and the blank row do not.
    assert rows["AB1 1AC"][_raw("Robbery")] == 12.0
    assert rows["AB1 1AC"][_raw("Burglary")] == 0.0
    # Anti-social behaviour had no coordinate -> nobody gets it.
    assert all(r[_raw("Anti-social behaviour")] == 0.0 for r in rows.values())


def test_counts_are_not_area_normalised(tmp_path):
    # Three postcodes of very different footprint, each with exactly one incident
    # in its buffer. The raw count must be 12/yr for ALL of them: area
    # normalisation has been removed, so footprint no longer changes the number.
    units = tmp_path / "units"
    _write_boundaries(
        units,
        {
            "AB1": [
                _square_feature("AB1 1AA", 1000, 1000, 1010, 1010),  # 10x10
                _square_feature("AB1 1AB", 3000, 3000, 3010, 3020),  # 10x20
                _square_feature("AB1 1AC", 5000, 5000, 5040, 5040),  # 40x40
            ]
        },
    )

    crime = tmp_path / "crime"
    _write_month(
        crime,
        "2024-01",
        [
            _crime_row("2024-01", 1005, 1005, "Burglary"),
            _crime_row("2024-01", 3005, 3010, "Burglary"),
            _crime_row("2024-01", 5020, 5020, "Burglary"),
        ],
    )

    raw_df, _, _ = _run(tmp_path, crime, units, min_bar_months=1)
    rows = {r["postcode"]: r for r in raw_df.to_dicts()}
    for pc in ("AB1 1AA", "AB1 1AB", "AB1 1AC"):
        assert rows[pc][_raw("Burglary")] == pytest.approx(12.0, abs=0.05)


def test_windows_pool_only_recent_years(tmp_path):
    # 2-year window vs 7-year window. An incident in the latest year sits in both
    # windows; one 6 years back sits only in the 7-year window.
    units = tmp_path / "units"
    _write_boundaries(
        units, {"AB1": [_square_feature("AB1 1AA", 1000, 1000, 1010, 1010)]}
    )
    crime = tmp_path / "crime"
    # 12 covered months in 2019 (1 burglary), 12 in 2025 (1 burglary). Latest =
    # 2025: 7y window = 2019..2025 (both), 2y window = 2024..2025 (only 2025).
    for month in range(1, 13):
        ym19 = f"2019-{month:02d}"
        ym25 = f"2025-{month:02d}"
        _write_month(crime, ym19, [_crime_row(ym19, 1005, 1005, "Burglary")] if month == 1 else [])
        _write_month(crime, ym25, [_crime_row(ym25, 1005, 1005, "Burglary")] if month == 1 else [])

    raw_df, _, _ = _run(tmp_path, crime, units)
    row = raw_df.row(0, named=True)
    # 7y: 2 incidents over 24 covered months -> 1/yr.
    assert row[_raw("Burglary", "7y")] == pytest.approx(1.0, abs=0.05)
    # 2y: 1 incident over 12 covered months -> 1/yr (the 2019 one is excluded).
    assert row[_raw("Burglary", "2y")] == pytest.approx(1.0, abs=0.05)


def test_by_year_annualises_and_rolls_up(tmp_path):
    units = tmp_path / "units"
    _write_boundaries(
        units, {"AB1": [_square_feature("AB1 1AA", 1000, 1000, 1010, 1010)]}
    )

    crime = tmp_path / "crime"
    _write_month(
        crime,
        "2023-01",
        [
            _crime_row("2023-01", 1005, 1005, "Burglary"),
            _crime_row("2023-01", 1005, 1005, "Robbery"),
        ],
    )
    _write_month(crime, "2024-01", [_crime_row("2024-01", 1005, 1005, "Burglary")])
    _write_month(
        crime,
        "2024-02",
        [
            _crime_row("2024-02", 1005, 1005, "Burglary"),
            _crime_row("2024-02", 1005, 1005, "Anti-social behaviour"),
        ],
    )

    _, by_year_df, _ = _run(tmp_path, crime, units, min_bar_months=1)
    assert by_year_df.height == 1
    cols = set(by_year_df.columns)
    assert {"Burglary (by year)", "Serious crime (by year)", "Minor crime (by year)"} <= cols

    row = by_year_df.row(0, named=True)
    burglary = sorted(row["Burglary (by year)"], key=lambda r: r["year"])
    # 2023: 1 burglary in 1 covered month -> 12/yr; 2024: 2 in 2 months -> 12/yr.
    assert burglary == [
        {"year": 2023, "count": 12.0},
        {"year": 2024, "count": 12.0},
    ]
    serious = {p["year"]: p["count"] for p in row["Serious crime (by year)"]}
    # 2023 serious = Burglary(12) + Robbery(12) = 24; 2024 = Burglary(12).
    assert serious[2023] == 24.0
    assert serious[2024] == 12.0
    coverage = {c["year"]: c["months"] for c in row["covered_years"]}
    assert coverage == {2023: 1, 2024: 2}


def test_raw_is_pooled_rate_over_covered_months(tmp_path):
    # Uneven month coverage: 2023 has 1 month (2 incidents), 2024 has 2 months
    # (2 incidents). The raw figure is the POOLED annualised rate over all covered
    # months: 4 incidents / 3 months * 12 = 16/yr.
    units = tmp_path / "units"
    _write_boundaries(
        units, {"AB1": [_square_feature("AB1 1AA", 1000, 1000, 1010, 1010)]}
    )

    crime = tmp_path / "crime"
    _write_month(
        crime,
        "2023-01",
        [
            _crime_row("2023-01", 1005, 1005, "Burglary"),
            _crime_row("2023-01", 1005, 1005, "Burglary"),
        ],
    )
    _write_month(crime, "2024-01", [_crime_row("2024-01", 1005, 1005, "Burglary")])
    _write_month(crime, "2024-02", [_crime_row("2024-02", 1005, 1005, "Burglary")])

    raw_df, by_year_df, _ = _run(tmp_path, crime, units, min_bar_months=1)

    assert raw_df.row(0, named=True)[_raw("Burglary")] == pytest.approx(16.0, abs=0.05)

    # Bars remain per-year annualised: 2023 -> 24/yr (x12), 2024 -> 12/yr (x6).
    row = by_year_df.row(0, named=True)
    bars = {p["year"]: p["count"] for p in row["Burglary (by year)"]}
    assert bars == {2023: pytest.approx(24.0, abs=0.05), 2024: pytest.approx(12.0, abs=0.05)}


def test_sporadic_type_is_not_inflated_by_years_present(tmp_path):
    # A single robbery in a 24-covered-month window must read as ~0.5/yr (the
    # long-run pooled rate), NOT 12/yr.
    units = tmp_path / "units"
    _write_boundaries(
        units, {"AB1": [_square_feature("AB1 1AA", 1000, 1000, 1010, 1010)]}
    )

    crime = tmp_path / "crime"
    for year in (2023, 2024):
        for month in range(1, 13):
            rows = []
            if (year, month) == (2023, 6):
                rows = [_crime_row(f"{year}-{month:02d}", 1005, 1005, "Robbery")]
            _write_month(crime, f"{year}-{month:02d}", rows)

    raw_df, by_year_df, _ = _run(tmp_path, crime, units)

    # 1 incident over 24 covered months -> 0.5/yr.
    assert raw_df.row(0, named=True)[_raw("Robbery")] == pytest.approx(0.5, abs=0.05)
    row = by_year_df.row(0, named=True)
    bars = {p["year"]: p["count"] for p in row["Robbery (by year)"]}
    assert bars == {2023: pytest.approx(1.0, abs=0.05)}
    coverage = {c["year"]: c["months"] for c in row["covered_years"]}
    assert coverage == {2023: 12, 2024: 12}


def test_force_gap_years_are_excluded_not_zeroed(tmp_path):
    # Two postcodes policed by different forces. force-a publishes 2023+2024;
    # force-b publishes only 2023 (a 2024 gap). The b-postcode's raw figure must
    # pool over force-b's 12 covered months only.
    units = tmp_path / "units"
    _write_boundaries(
        units,
        {
            "AB1": [_square_feature("AB1 1AA", 1000, 1000, 1010, 1010)],
            "CD1": [_square_feature("CD1 1AA", 9000, 9000, 9010, 9010)],
        },
    )

    crime = tmp_path / "crime"
    for month in range(1, 13):
        ym23 = f"2023-{month:02d}"
        ym24 = f"2024-{month:02d}"
        _write_month(crime, ym23, [], force="force-a")
        _write_month(
            crime, ym24, [_crime_row(ym24, 1005, 1005, "Burglary")], force="force-a"
        )
        _write_month(
            crime, ym23, [_crime_row(ym23, 9005, 9005, "Burglary")], force="force-b"
        )

    raw_df, by_year_df, _ = _run(tmp_path, crime, units)
    rows = {r["postcode"]: r for r in raw_df.to_dicts()}

    # force-a postcode: 12 burglaries over 24 covered months -> 6/yr.
    assert rows["AB1 1AA"][_raw("Burglary")] == pytest.approx(6.0, abs=0.05)
    # force-b postcode: 12 burglaries over 12 covered months -> 12/yr.
    assert rows["CD1 1AA"][_raw("Burglary")] == pytest.approx(12.0, abs=0.05)

    by_rows = {r["postcode"]: r for r in by_year_df.to_dicts()}
    b_coverage = {c["year"]: c["months"] for c in by_rows["CD1 1AA"]["covered_years"]}
    assert b_coverage == {2023: 12}
    b_bars = {p["year"]: p["count"] for p in by_rows["CD1 1AA"]["Burglary (by year)"]}
    assert set(b_bars) == {2023}
    a_coverage = {c["year"]: c["months"] for c in by_rows["AB1 1AA"]["covered_years"]}
    assert a_coverage == {2023: 12, 2024: 12}


def test_partial_years_below_min_bar_months_get_no_bar(tmp_path):
    # 2023 fully covered; 2024 has only 2 published months. With the default
    # 6-month minimum, 2024 must produce no bar -- but its incidents and months
    # still count toward the pooled raw figure.
    units = tmp_path / "units"
    _write_boundaries(
        units, {"AB1": [_square_feature("AB1 1AA", 1000, 1000, 1010, 1010)]}
    )

    crime = tmp_path / "crime"
    for month in range(1, 13):
        ym = f"2023-{month:02d}"
        _write_month(crime, ym, [_crime_row(ym, 1005, 1005, "Burglary")])
    for month in (1, 2):
        ym = f"2024-{month:02d}"
        _write_month(crime, ym, [_crime_row(ym, 1005, 1005, "Burglary")])

    raw_df, by_year_df, _ = _run(tmp_path, crime, units)

    # Pooled: 14 incidents over 14 covered months -> 12/yr.
    assert raw_df.row(0, named=True)[_raw("Burglary")] == pytest.approx(12.0, abs=0.05)
    row = by_year_df.row(0, named=True)
    bars = {p["year"]: p["count"] for p in row["Burglary (by year)"]}
    assert set(bars) == {2023}
    coverage = {c["year"]: c["months"] for c in row["covered_years"]}
    assert coverage == {2023: 12}


def test_by_year_output_is_dense_with_coverage(tmp_path):
    # A postcode with zero incidents still gets a by-year row carrying its
    # coverage calendar, so "covered and crime-free" is distinguishable from
    # "no data" downstream.
    units = tmp_path / "units"
    _write_boundaries(
        units,
        {
            "AB1": [
                _square_feature("AB1 1AA", 1000, 1000, 1010, 1010),
                _square_feature("AB1 1AB", 5000, 5000, 5010, 5010),
            ]
        },
    )

    crime = tmp_path / "crime"
    _write_month(crime, "2024-01", [_crime_row("2024-01", 1005, 1005, "Burglary")])

    raw_df, by_year_df, _ = _run(tmp_path, crime, units, min_bar_months=1)
    assert by_year_df.height == 2

    quiet = by_year_df.filter(pl.col("postcode") == "AB1 1AB").row(0, named=True)
    assert quiet["Burglary (by year)"] is None
    assert [c["year"] for c in quiet["covered_years"]] == [2024]
    # The raw figure for the covered, crime-free postcode is a genuine 0, not null.
    quiet_raw = raw_df.filter(pl.col("postcode") == "AB1 1AB").row(0, named=True)
    assert quiet_raw[_raw("Burglary")] == 0.0


def test_serious_rollup_equals_sum_of_components(tmp_path):
    # Burglary only in 2023, Robbery only in 2024 (one incident each, 2 covered
    # months total, both inside the 7-year window). Components pool over the same
    # covered window (each 1 x 12 / 2 = 6/yr) and the rollup equals their sum.
    units = tmp_path / "units"
    _write_boundaries(
        units, {"AB1": [_square_feature("AB1 1AA", 1000, 1000, 1010, 1010)]}
    )

    crime = tmp_path / "crime"
    _write_month(crime, "2023-01", [_crime_row("2023-01", 1005, 1005, "Burglary")])
    _write_month(crime, "2024-01", [_crime_row("2024-01", 1005, 1005, "Robbery")])

    raw_df, by_year_df, _ = _run(tmp_path, crime, units, min_bar_months=1)

    row = raw_df.row(0, named=True)
    assert row[_raw("Burglary")] == pytest.approx(6.0, abs=0.05)
    assert row[_raw("Robbery")] == pytest.approx(6.0, abs=0.05)
    assert row[_raw("Serious crime")] == pytest.approx(12.0, abs=0.05)
    assert row[_raw("Serious crime")] == pytest.approx(
        row[_raw("Burglary")] + row[_raw("Robbery")], abs=0.05
    )

    serious_bars = {
        p["year"]: p["count"]
        for p in by_year_df.row(0, named=True)["Serious crime (by year)"]
    }
    assert serious_bars == {
        2023: pytest.approx(12.0, abs=0.05),
        2024: pytest.approx(12.0, abs=0.05),
    }


def test_records_capture_each_counted_incident(tmp_path):
    # Each (incident, postcode) match within the records window becomes a record
    # row, carrying month/type/location/outcome/coords. A boundary incident
    # counted for two postcodes appears once per postcode.
    units = tmp_path / "units"
    _write_boundaries(
        units,
        {
            "AB1": [
                _square_feature("AB1 1AA", 1000, 1000, 1010, 1010),
                _square_feature("AB1 1AB", 1080, 1000, 1090, 1010),
            ]
        },
    )
    crime = tmp_path / "crime"
    _write_month(
        crime,
        "2024-03",
        [
            # In the buffer overlap -> recorded for both postcodes.
            _crime_row("2024-03", 1045, 1005, "Burglary", location="On or near High St", outcome="Under investigation"),
            # Only in AB1 1AA's buffer; null outcome (police.uk leaves ASB blank).
            _crime_row("2024-03", 1005, 1005, "Anti-social behaviour", location="On or near Mill Ln", outcome=""),
        ],
    )

    _, _, records_df = _run(tmp_path, crime, units, min_bar_months=1)

    assert set(records_df.columns) == {
        "postcode", "month_index", "crime_type", "location", "outcome", "lat", "lon"
    }
    # Sorted by postcode.
    assert records_df["postcode"].is_sorted()
    # Burglary appears for BOTH postcodes (boundary multiplicity); ASB only for AA.
    by_pc = records_df.group_by("postcode").agg(pl.col("crime_type").sort())
    counts = {r["postcode"]: r["crime_type"] for r in by_pc.to_dicts()}
    assert counts["AB1 1AA"] == ["Anti-social behaviour", "Burglary"]
    assert counts["AB1 1AB"] == ["Burglary"]
    # month_index = year*12 + (month-1) for 2024-03.
    assert set(records_df["month_index"].to_list()) == {2024 * 12 + 2}
    # Null outcome round-trips as null, not the string "".
    asb = records_df.filter(pl.col("crime_type") == "Anti-social behaviour").row(0, named=True)
    assert asb["outcome"] is None
    assert asb["location"] == "On or near Mill Ln"


def test_records_window_aligns_to_the_headline_calendar_window(tmp_path):
    # Records must cover exactly the longest (7y) headline window, which is
    # calendar-year based. With a mid-year latest month (2025-06) the 7y window
    # is calendar years 2019..2025, so an incident in 2018-09 -- which the
    # headline excludes -- must also be excluded from the records, even though a
    # naive rolling 84-month span (ending 2025-06) would wrongly include it. The
    # first month of the earliest window year (2019-01) is kept.
    units = tmp_path / "units"
    _write_boundaries(
        units, {"AB1": [_square_feature("AB1 1AA", 1000, 1000, 1010, 1010)]}
    )
    crime = tmp_path / "crime"
    _write_month(crime, "2018-09", [_crime_row("2018-09", 1005, 1005, "Burglary")])
    _write_month(crime, "2019-01", [_crime_row("2019-01", 1005, 1005, "Burglary")])
    _write_month(crime, "2025-06", [_crime_row("2025-06", 1005, 1005, "Burglary")])

    _, _, records_df = _run(tmp_path, crime, units, min_bar_months=1)

    # 2018-09 (year*12+8) is in the rolling 84-month span but NOT the 7y calendar
    # window, so it is excluded; 2019-01 and 2025-06 are kept.
    assert set(records_df["month_index"].to_list()) == {2019 * 12 + 0, 2025 * 12 + 5}


def test_unknown_crime_type_is_dropped_with_warning(tmp_path, capsys):
    units = tmp_path / "units"
    _write_boundaries(
        units, {"AB1": [_square_feature("AB1 1AA", 1000, 1000, 1010, 1010)]}
    )

    crime = tmp_path / "crime"
    _write_month(
        crime,
        "2024-01",
        [
            _crime_row("2024-01", 1005, 1005, "Burglary"),
            _crime_row("2024-01", 1005, 1005, "Cyber fraud"),
        ],
    )

    raw_df, _, _ = _run(tmp_path, crime, units)
    columns = raw_df.columns
    assert _raw("Cyber fraud") not in columns
    assert _raw("Burglary") in columns
    err = capsys.readouterr().err
    assert "Cyber fraud" in err
    assert "WARNING" in err


def test_legacy_crime_types_are_mapped(tmp_path):
    """Pre-2014 crime-type names are aliased to current equivalents in the
    spatial transform instead of being dropped as unknown types."""
    units = tmp_path / "units"
    _write_boundaries(
        units, {"AB1": [_square_feature("AB1 1AA", 1000, 1000, 1010, 1010)]}
    )

    crime = tmp_path / "crime"
    _write_month(
        crime,
        "2013-01",
        [
            _crime_row("2013-01", 1005, 1005, "Violent crime"),
            _crime_row("2013-01", 1005, 1005, "Public disorder and weapons"),
        ],
    )

    raw_df, by_year_df, _ = _run(tmp_path, crime, units, min_bar_months=1)
    row = raw_df.to_dicts()[0]
    # Single covered month (relative to a 2013-latest window) -> x12.
    assert row[_raw("Violence and sexual offences")] == 12.0
    assert row[_raw("Public order")] == 12.0

    by_year_row = by_year_df.row(0, named=True)
    assert by_year_row["Violence and sexual offences (by year)"] == [
        {"year": 2013, "count": 12.0}
    ]
    assert by_year_row["Public order (by year)"] == [{"year": 2013, "count": 12.0}]