import requests
import csv
import json

# https://www2.census.gov/programs-surveys/popest/technical-documentation/file-layouts/2020-2022/SUB-EST2022.pdf
INCORPORATED_PLACE = "162" 

res = requests.get("https://www2.census.gov/programs-surveys/popest/datasets/2020-2022/cities/totals/sub-est2022.csv")
res.raise_for_status()

cities_by_state = {}
for line in csv.DictReader(res.content.decode('utf-8-sig').split('\n')):
    if line['SUMLEV'] != INCORPORATED_PLACE:
        continue

    if not line['STNAME'] in cities_by_state:
        cities_by_state[line['STNAME']] = []

    cities_by_state[line['STNAME']].append({
        "name": " ".join(line['NAME'].split(" ")[:-1]), # Remove "city" or "town" from the end
        "pop": int(line['POPESTIMATE2022']),
    })

for state, cities in cities_by_state.items():
    cities.sort(key=lambda i: i["pop"], reverse=True)

    with open(f"data/{state}.json", 'w') as f:
        f.write(json.dumps(cities))

with open(f"data/states.json", 'w') as f:
    f.write(json.dumps(list(cities_by_state.keys())))

# ----- MAP -----

import subprocess

CMD="""
curl --silent --remote-name https://www2.census.gov/geo/tiger/GENZ2022/shp/cb_2022_us_state_20m.zip
unzip -q -o cb_2022_us_state_20m.zip
ogr2ogr -f GeoJSON data/states.geojson cb_2022_us_state_20m.shp
sed -i '/^"crs":/d' data/states.geojson
rm cb_2022_us_state_20m.*
"""

subprocess.run(CMD, shell=True)