#!/usr/bin/env python3
"""
Deep-dive into specific secondary categories to find the best
transport-adjacent indicators. Searches targeted terms and inspects
results to pick the most useful ones per category.
"""

import json
import requests
from pathlib import Path

BASE = "https://data360api.worldbank.org/data360"
RESULTS_DIR = Path(__file__).parent.parent / "results"

SELECT_FIELDS = ",".join([
    "series_description/idno",
    "series_description/name",
    "series_description/database_id",
    "series_description/database_name",
    "series_description/definition_short",
    "series_description/measurement_unit",
    "series_description/periodicity",
    "series_description/topics",
])


def search(query, top=50, filter_expr=None):
    body = {
        "search": query,
        "select": SELECT_FIELDS,
        "top": top,
        "count": True,
    }
    if filter_expr:
        body["filter"] = filter_expr
    resp = requests.post(f"{BASE}/searchv2", json=body)
    resp.raise_for_status()
    return resp.json()


def print_results(data, label, max_show=20):
    count = data.get("@odata.count", 0)
    values = data.get("value", [])
    print(f"\n  [{label}] ({count} total, showing {min(len(values), max_show)}):")
    for v in values[:max_show]:
        sd = v.get("series_description", {})
        idno = sd.get("idno", "")
        name = (sd.get("name") or "")[:80]
        db = sd.get("database_id", "")
        unit = sd.get("measurement_unit", "")
        print(f"    {idno} [{db}] {name} ({unit})")


def main():
    all_results = {}

    # ── CLIMATE / EMISSIONS (transport-specific) ──
    print("\n" + "=" * 70)
    print("CLIMATE & EMISSIONS - transport-specific")
    print("=" * 70)

    for q in [
        "CO2 emissions transport",
        "greenhouse gas transport sector",
        "fossil fuel subsidy transport",
        "carbon tax fuel",
        "air pollution PM2.5",
        "climate vulnerability infrastructure",
        "flood risk infrastructure",
        "sea level rise coastal",
    ]:
        data = search(q, top=15)
        print_results(data, q)

    # ── ENERGY / FUEL (for transport) ──
    print("\n" + "=" * 70)
    print("ENERGY & FUEL - transport-relevant")
    print("=" * 70)

    for q in [
        "fuel price oil petroleum",
        "fuel import export",
        "electric vehicle charging",
        "electricity access rural",
        "energy consumption per capita",
        "renewable energy capacity",
        "pump price gasoline diesel",
    ]:
        data = search(q, top=15)
        print_results(data, q)

    # ── CONFLICT / FRAGILITY ──
    print("\n" + "=" * 70)
    print("CONFLICT & FRAGILITY")
    print("=" * 70)

    for q in [
        "political stability violence",
        "conflict intensity",
        "internally displaced refugee",
        "government effectiveness regulatory quality",
        "fragile conflict affected state",
        "battle deaths armed conflict",
    ]:
        data = search(q, top=10)
        print_results(data, q)

    # ── LAND USE & URBANIZATION ──
    print("\n" + "=" * 70)
    print("LAND USE & URBANIZATION")
    print("=" * 70)

    for q in [
        "urban population growth city",
        "population density",
        "slum population",
        "land area surface",
        "rural population access",
        "urban agglomeration",
        "deforestation land use change",
        "elevation sea level low coastal",
    ]:
        data = search(q, top=10)
        print_results(data, q)

    # ── WATER & WATERWAYS ──
    print("\n" + "=" * 70)
    print("WATER & WATERWAYS")
    print("=" * 70)

    for q in [
        "inland waterway navigation",
        "river basin transboundary",
        "dam capacity reservoir",
        "coastal flood",
        "ocean shipping maritime",
        "fishery port coastal economy",
    ]:
        data = search(q, top=10)
        print_results(data, q)

    # ── TRADE & CORRIDORS ──
    print("\n" + "=" * 70)
    print("TRADE & ECONOMIC CORRIDORS")
    print("=" * 70)

    for q in [
        "trade GDP merchandise",
        "customs clearance border time",
        "foreign direct investment",
        "transport services exports imports",
        "tariff trade barrier",
        "special economic zone",
        "trade in value added",
    ]:
        data = search(q, top=10)
        print_results(data, q)

    # ── GOVERNMENT SPENDING ──
    print("\n" + "=" * 70)
    print("GOVERNMENT SPENDING - infrastructure/transport")
    print("=" * 70)

    for q in [
        "government expenditure transport",
        "government expenditure economic affairs",
        "public investment infrastructure",
        "budget allocation transport road",
        "pump price gasoline diesel",
    ]:
        data = search(q, top=15)
        print_results(data, q)

    # ── DEMOGRAPHICS ──
    print("\n" + "=" * 70)
    print("POPULATION & DEMOGRAPHICS")
    print("=" * 70)

    for q in [
        "population total growth rate",
        "GDP per capita PPP",
        "labor force employment",
        "remittance migration",
        "poverty headcount",
    ]:
        data = search(q, top=10)
        print_results(data, q)


if __name__ == "__main__":
    main()