#!/usr/bin/env python3
"""Load HPO's gene-to-phenotype annotations into the gene_phenotypes table.

This is the reference data the ranking matches a case's phenotype against. Source file:
https://purl.obolibrary.org/obo/hp/hpoa/genes_to_phenotype.txt (HPO release, ~20 MB).

Cite the Human Phenotype Ontology when showing results; see docs/data.md.
"""
import argparse
import csv
import io
import os
import sys
import urllib.request

from sqlalchemy import create_engine, text
from sqlalchemy.engine import make_url

URL = "https://purl.obolibrary.org/obo/hp/hpoa/genes_to_phenotype.txt"


def rows(handle: io.TextIOBase) -> list[tuple[str, str, str]]:
    """Unique (gene, term) pairs; the file repeats them once per associated disease."""
    seen: set[tuple[str, str]] = set()
    out: list[tuple[str, str, str]] = []
    for row in csv.DictReader(handle, delimiter="\t"):
        gene, hpo_id, name = row["gene_symbol"], row["hpo_id"], row["hpo_name"]
        if not gene or not hpo_id or (gene, hpo_id) in seen:
            continue
        seen.add((gene, hpo_id))
        out.append((gene[:60], hpo_id[:20], name[:200]))
    return out


def main() -> None:
    p = argparse.ArgumentParser()
    p.add_argument("--url", default=URL)
    p.add_argument("--file", help="use a local copy instead of downloading")
    a = p.parse_args()

    url = os.environ.get("DATABASE_URL")
    if not url:
        sys.exit("DATABASE_URL is not set")

    if a.file:
        with open(a.file) as fh:
            annotations = rows(fh)
    else:
        print(f"downloading {a.url}", file=sys.stderr)
        with urllib.request.urlopen(a.url) as response:  # noqa: S310 - fixed HPO release URL
            annotations = rows(io.TextIOWrapper(response, encoding="utf-8"))
    print(f"{len(annotations)} gene/term pairs", file=sys.stderr)

    engine = create_engine(make_url(url).set(drivername="postgresql+psycopg"))
    with engine.begin() as conn:
        conn.execute(text("TRUNCATE gene_phenotypes RESTART IDENTITY"))
        cursor = conn.connection.cursor()
        with cursor.copy("COPY gene_phenotypes (gene_symbol, hpo_id, hpo_name) FROM STDIN") as copy:
            for row in annotations:
                copy.write_row(row)
    print(f"loaded {len(annotations)} annotations", file=sys.stderr)


if __name__ == "__main__":
    main()