"""sec-edgar-python-submissions-fts-xbrl.py — the three free EDGAR JSON endpoints in one small tool: submissions, full-text search, XBRL company facts.

What it does:
  --cik 320193 --filings 10-K     recent filings of one company with accession numbers and primary-document URLs
                                  (https://data.sec.gov/submissions/CIK##########.json)
  --fts "generative artificial intelligence" --forms 10-K --since 2025-01-01
                                  full-text search hits with accession numbers (https://efts.sec.gov/LATEST/search-index)
  --cik 320193 --fact Revenues    one us-gaap concept from company facts, fiscal-year rows only, deduplicated so
                                  each period is taken from the filing that first reported it
                                  (https://data.sec.gov/api/xbrl/companyfacts/CIK##########.json)
Requirements: the SEC asks for a descriptive User-Agent with contact information and no more than 10 requests
              per second (stated on the SEC's 'Accessing EDGAR Data' page). Set EDGAR_UA to your own string.
Run  : python code/sec-edgar-python-submissions-fts-xbrl.py --cik 320193 --filings 10-K --max 5
Needs: Python 3.13 standard library only.
"""
import argparse
import datetime as dt
import json
import os
import urllib.parse
import urllib.request

UA = os.environ.get("EDGAR_UA", "prism-data-lab/1.0 (research; contact via site)")


def get_json(url: str):
    req = urllib.request.Request(url, headers={"User-Agent": UA, "Accept-Encoding": "identity"})
    with urllib.request.urlopen(req, timeout=60) as r:
        return json.loads(r.read().decode("utf-8"))


def filings(cik: str, form: str | None, max_results: int):
    cik10 = str(int(cik)).zfill(10)
    j = get_json(f"https://data.sec.gov/submissions/CIK{cik10}.json")
    rec = j["filings"]["recent"]
    out = []
    for i in range(len(rec["accessionNumber"])):
        if form and rec["form"][i] != form:
            continue
        acc = rec["accessionNumber"][i]
        out.append({"entity": j["name"], "form": rec["form"][i], "filed": rec["filingDate"][i],
                    "period": rec["reportDate"][i], "accession": acc,
                    "url": f"https://www.sec.gov/Archives/edgar/data/{int(cik)}/{acc.replace('-', '')}/{rec['primaryDocument'][i]}"})
        if len(out) >= max_results:
            break
    return out


def fts(phrase: str, forms: str | None, since: str | None, max_results: int):
    url = "https://efts.sec.gov/LATEST/search-index?q=" + urllib.parse.quote(f'"{phrase}"')
    if forms:
        url += "&forms=" + urllib.parse.quote(forms)
    if since:
        url += f"&dateRange=custom&startdt={since}&enddt={dt.date.today().isoformat()}"
    j = get_json(url)
    total = j["hits"]["total"]["value"]
    hits = []
    for h in j["hits"]["hits"][:max_results]:
        s = h["_source"]
        adsh = h["_id"].split(":")[0]
        cik = str(s["ciks"][0]).lstrip("0")
        hits.append({"entity": s["display_names"][0], "form": s["form"], "filed": s["file_date"], "accession": adsh,
                     "cik": cik, "url": f"https://www.sec.gov/Archives/edgar/data/{cik}/{adsh.replace('-', '')}/"})
    return total, hits


def fact(cik: str, concept: str):
    cik10 = str(int(cik)).zfill(10)
    j = get_json(f"https://data.sec.gov/api/xbrl/companyfacts/CIK{cik10}.json")
    f = j["facts"]["us-gaap"][concept]
    unit = next(iter(f["units"]))
    seen, rows = set(), []
    for v in sorted(f["units"][unit], key=lambda v: (v["end"], v["filed"])):
        if v.get("fp") != "FY" or v.get("form") != "10-K":
            continue
        key = (v.get("start"), v["end"])
        if key in seen:
            continue                      # later 10-Ks restate the same period; keep the first report
        seen.add(key)
        rows.append({"entity": j["entityName"], "concept": concept, "unit": unit, "start": v.get("start", ""),
                     "end": v["end"], "value": v["val"], "fy": v["fy"], "accession": v["accn"], "filed": v["filed"]})
    return rows


def main():
    ap = argparse.ArgumentParser()
    ap.add_argument("--cik")
    ap.add_argument("--filings")
    ap.add_argument("--fact")
    ap.add_argument("--fts")
    ap.add_argument("--forms")
    ap.add_argument("--since")
    ap.add_argument("--max", type=int, default=10)
    a = ap.parse_args()
    if a.cik and a.filings:
        print(json.dumps(filings(a.cik, a.filings, a.max), indent=1))
    elif a.cik and a.fact:
        print(json.dumps(fact(a.cik, a.fact), indent=1))
    elif a.fts:
        total, hits = fts(a.fts, a.forms, a.since, a.max)
        print(json.dumps({"total_documents": total, "hits": hits}, indent=1))
    else:
        ap.print_help()


if __name__ == "__main__":
    main()