school_compare/backend/app.py

"""
SchoolCompare.co.uk API
Serves primary school (KS2) performance data for comparing schools.
Uses real data from UK Government Compare School Performance downloads.
"""

from contextlib import asynccontextmanager
from typing import Optional

import pandas as pd
from fastapi import FastAPI, HTTPException, Query
from fastapi.middleware.cors import CORSMiddleware
from fastapi.responses import FileResponse
from fastapi.staticfiles import StaticFiles

from .config import settings
from .data_loader import (
    clear_cache,
    geocode_postcodes_bulk,
    geocode_single_postcode,
    haversine_distance,
    load_school_data,
)
from .data_loader import get_data_info as get_db_info
from .database import init_db
from .schemas import METRIC_DEFINITIONS, RANKING_COLUMNS, SCHOOL_COLUMNS
from .utils import clean_for_json


@asynccontextmanager
async def lifespan(app: FastAPI):
    """Application lifespan - startup and shutdown events."""
    # Startup: initialize database and pre-load data
    print("Starting up: Initializing database...")
    init_db()  # Ensure tables exist

    print("Loading school data from database...")
    df = load_school_data()
    if df.empty:
        print("Warning: No data in database. Run the migration script to import data.")
    else:
        print("Data loaded successfully.")

    yield  # Application runs here

    # Shutdown: cleanup if needed
    print("Shutting down...")


app = FastAPI(
    title="SchoolCompare API",
    description="API for comparing primary school (KS2) performance data - schoolcompare.co.uk",
    version="2.0.0",
    lifespan=lifespan,
)

# CORS middleware with configurable origins
app.add_middleware(
    CORSMiddleware,
    allow_origins=settings.allowed_origins,
    allow_credentials=True,
    allow_methods=["*"],
    allow_headers=["*"],
)


@app.get("/")
async def root():
    """Serve the frontend."""
    return FileResponse(settings.frontend_dir / "index.html")


@app.get("/compare")
async def serve_compare():
    """Serve the frontend for /compare route (SPA routing)."""
    return FileResponse(settings.frontend_dir / "index.html")


@app.get("/rankings")
async def serve_rankings():
    """Serve the frontend for /rankings route (SPA routing)."""
    return FileResponse(settings.frontend_dir / "index.html")


@app.get("/api/schools")
async def get_schools(
    search: Optional[str] = Query(None, description="Search by school name"),
    local_authority: Optional[str] = Query(
        None, description="Filter by local authority"
    ),
    school_type: Optional[str] = Query(None, description="Filter by school type"),
    postcode: Optional[str] = Query(None, description="Search near postcode"),
    radius: float = Query(5.0, ge=0.1, le=50, description="Search radius in miles"),
    page: int = Query(1, ge=1, description="Page number"),
    page_size: int = Query(None, ge=1, le=100, description="Results per page"),
):
    """
    Get list of unique primary schools with pagination.

    Returns paginated results with total count for efficient loading.
    Supports location-based search using postcode.
    """
    df = load_school_data()

    if df.empty:
        return {"schools": [], "total": 0, "page": page, "page_size": 0}

    # Use configured default if not specified
    if page_size is None:
        page_size = settings.default_page_size

    # Get unique schools (latest year data for each)
    latest_year = df.groupby("urn")["year"].max().reset_index()
    df_latest = df.merge(latest_year, on=["urn", "year"])

    # Include key result metrics for display on cards
    location_cols = ["latitude", "longitude"]
    result_cols = [
        "year",
        "rwm_expected_pct",
        "reading_expected_pct",
        "writing_expected_pct",
        "maths_expected_pct",
        "total_pupils",
    ]
    available_cols = [
        c
        for c in SCHOOL_COLUMNS + location_cols + result_cols
        if c in df_latest.columns
    ]
    schools_df = df_latest[available_cols].drop_duplicates(subset=["urn"])

    # Location-based search
    search_coords = None
    if postcode:
        coords = geocode_single_postcode(postcode)
        if coords:
            search_coords = coords
            schools_df = schools_df.copy()

            # Geocode school postcodes on-demand if not already cached
            if "postcode" in schools_df.columns:
                unique_postcodes = schools_df["postcode"].dropna().unique().tolist()
                geocoded = geocode_postcodes_bulk(unique_postcodes)

                # Add lat/long from geocoded data
                schools_df["latitude"] = schools_df["postcode"].apply(
                    lambda pc: geocoded.get(str(pc).strip().upper(), (None, None))[0]
                    if pd.notna(pc)
                    else None
                )
                schools_df["longitude"] = schools_df["postcode"].apply(
                    lambda pc: geocoded.get(str(pc).strip().upper(), (None, None))[1]
                    if pd.notna(pc)
                    else None
                )

            # Filter by distance
            def calc_distance(row):
                if pd.isna(row.get("latitude")) or pd.isna(row.get("longitude")):
                    return float("inf")
                return haversine_distance(
                    search_coords[0],
                    search_coords[1],
                    row["latitude"],
                    row["longitude"],
                )

            schools_df["distance"] = schools_df.apply(calc_distance, axis=1)
            schools_df = schools_df[schools_df["distance"] <= radius]
            schools_df = schools_df.sort_values("distance")

    # Apply filters
    if search:
        search_lower = search.lower()
        mask = (
            schools_df["school_name"].str.lower().str.contains(search_lower, na=False)
        )
        if "address" in schools_df.columns:
            mask = mask | schools_df["address"].str.lower().str.contains(
                search_lower, na=False
            )
        schools_df = schools_df[mask]

    if local_authority:
        schools_df = schools_df[
            schools_df["local_authority"].str.lower() == local_authority.lower()
        ]

    if school_type:
        schools_df = schools_df[
            schools_df["school_type"].str.lower() == school_type.lower()
        ]

    # Pagination
    total = len(schools_df)
    start_idx = (page - 1) * page_size
    end_idx = start_idx + page_size
    schools_df = schools_df.iloc[start_idx:end_idx]

    # Remove internal columns before sending
    output_cols = [c for c in schools_df.columns if c not in ["latitude", "longitude"]]
    if "distance" in schools_df.columns:
        output_cols.append("distance")

    return {
        "schools": clean_for_json(schools_df[output_cols]),
        "total": total,
        "page": page,
        "page_size": page_size,
        "total_pages": (total + page_size - 1) // page_size if page_size > 0 else 0,
        "search_location": {"postcode": postcode, "radius": radius}
        if search_coords
        else None,
    }


@app.get("/api/schools/{urn}")
async def get_school_details(urn: int):
    """Get detailed KS2 data for a specific primary school across all years."""
    df = load_school_data()

    if df.empty:
        raise HTTPException(status_code=404, detail="No data available")

    school_data = df[df["urn"] == urn]

    if school_data.empty:
        raise HTTPException(status_code=404, detail="School not found")

    # Sort by year
    school_data = school_data.sort_values("year")

    # Get latest info for the school
    latest = school_data.iloc[-1]

    return {
        "school_info": {
            "urn": urn,
            "school_name": latest.get("school_name", ""),
            "local_authority": latest.get("local_authority", ""),
            "school_type": latest.get("school_type", ""),
            "address": latest.get("address", ""),
            "phase": "Primary",
        },
        "yearly_data": clean_for_json(school_data),
    }


@app.get("/api/compare")
async def compare_schools(urns: str = Query(..., description="Comma-separated URNs")):
    """Compare multiple primary schools side by side."""
    df = load_school_data()

    if df.empty:
        raise HTTPException(status_code=404, detail="No data available")

    try:
        urn_list = [int(u.strip()) for u in urns.split(",")]
    except ValueError:
        raise HTTPException(status_code=400, detail="Invalid URN format")

    comparison_data = df[df["urn"].isin(urn_list)]

    if comparison_data.empty:
        raise HTTPException(status_code=404, detail="No schools found")

    result = {}
    for urn in urn_list:
        school_data = comparison_data[comparison_data["urn"] == urn].sort_values("year")
        if not school_data.empty:
            latest = school_data.iloc[-1]
            result[str(urn)] = {
                "school_info": {
                    "urn": urn,
                    "school_name": latest.get("school_name", ""),
                    "local_authority": latest.get("local_authority", ""),
                    "address": latest.get("address", ""),
                },
                "yearly_data": clean_for_json(school_data),
            }

    return {"comparison": result}


@app.get("/api/filters")
async def get_filter_options():
    """Get available filter options (local authorities, school types, years)."""
    df = load_school_data()

    if df.empty:
        return {
            "local_authorities": [],
            "school_types": [],
            "years": [],
        }

    return {
        "local_authorities": sorted(df["local_authority"].dropna().unique().tolist()),
        "school_types": sorted(df["school_type"].dropna().unique().tolist()),
        "years": sorted(df["year"].dropna().unique().tolist()),
    }


@app.get("/api/metrics")
async def get_available_metrics():
    """
    Get list of available KS2 performance metrics for primary schools.

    This is the single source of truth for metric definitions.
    Frontend should consume this to avoid duplication.
    """
    df = load_school_data()

    available = []
    for key, info in METRIC_DEFINITIONS.items():
        if df.empty or key in df.columns:
            available.append({"key": key, **info})

    return {"metrics": available}


@app.get("/api/rankings")
async def get_rankings(
    metric: str = Query("rwm_expected_pct", description="KS2 metric to rank by"),
    year: Optional[int] = Query(
        None, description="Specific year (defaults to most recent)"
    ),
    limit: int = Query(20, ge=1, le=100, description="Number of schools to return"),
    local_authority: Optional[str] = Query(
        None, description="Filter by local authority"
    ),
):
    """Get primary school rankings by a specific KS2 metric."""
    df = load_school_data()

    if df.empty:
        return {"metric": metric, "year": None, "rankings": [], "total": 0}

    if metric not in df.columns:
        raise HTTPException(status_code=400, detail=f"Metric '{metric}' not available")

    # Filter by year
    if year:
        df = df[df["year"] == year]
    else:
        # Use most recent year
        max_year = df["year"].max()
        df = df[df["year"] == max_year]

    # Filter by local authority if specified
    if local_authority:
        df = df[df["local_authority"].str.lower() == local_authority.lower()]

    # Sort and rank (exclude rows with no data for this metric)
    df = df.dropna(subset=[metric])
    total = len(df)

    # For progress scores, higher is better. For percentages, higher is also better.
    df = df.sort_values(metric, ascending=False).head(limit)

    # Return only relevant fields for rankings
    available_cols = [c for c in RANKING_COLUMNS if c in df.columns]
    df = df[available_cols]

    return {
        "metric": metric,
        "year": int(df["year"].iloc[0]) if not df.empty else None,
        "rankings": clean_for_json(df),
        "total": total,
    }


@app.get("/api/data-info")
async def get_data_info():
    """Get information about loaded data."""
    # Get info directly from database
    db_info = get_db_info()

    if db_info["total_schools"] == 0:
        return {
            "status": "no_data",
            "message": "No data in database. Run the migration script: python scripts/migrate_csv_to_db.py",
            "data_source": "PostgreSQL",
        }

    # Also get DataFrame-based stats for backwards compatibility
    df = load_school_data()

    if df.empty:
        return {
            "status": "no_data",
            "message": "No data available",
            "data_source": "PostgreSQL",
        }

    years = [int(y) for y in sorted(df["year"].unique())]
    schools_per_year = {
        str(int(k)): int(v)
        for k, v in df.groupby("year")["urn"].nunique().to_dict().items()
    }
    la_counts = {
        str(k): int(v)
        for k, v in df["local_authority"].value_counts().to_dict().items()
    }

    return {
        "status": "loaded",
        "data_source": "PostgreSQL",
        "total_records": int(len(df)),
        "unique_schools": int(df["urn"].nunique()),
        "years_available": years,
        "schools_per_year": schools_per_year,
        "local_authorities": la_counts,
    }


@app.post("/api/admin/reload")
async def reload_data():
    """Admin endpoint to force data reload (useful after data updates)."""
    clear_cache()
    load_school_data()
    return {"status": "reloaded"}


# Mount static files directly (must be after all routes to avoid catching API calls)
if settings.frontend_dir.exists():
    app.mount("/static", StaticFiles(directory=settings.frontend_dir), name="static")


if __name__ == "__main__":
    import uvicorn

    uvicorn.run(app, host=settings.host, port=settings.port)