"""Helper used while compiling the hand-curated tables: fetch abstracts from Europe PMC.
Not part of run_all.py (the curated tables carry the verified values); kept for transparency.
Usage: python3 lit_lookup.py 'EPMC QUERY' ['EPMC QUERY' ...]      e.g. 'TITLE:"The oldest gnathostome teeth"'
"""
import sys, json, re, time, urllib.request, urllib.parse


def epmc(query, n=1, maxlen=1300):
    url = ("https://www.ebi.ac.uk/europepmc/webservices/rest/search?" +
           urllib.parse.urlencode(dict(query=query, format="json", resultType="core", pageSize=n)))
    d = None
    for attempt in range(3):
        try:
            with urllib.request.urlopen(url, timeout=25) as r:
                d = json.loads(r.read().decode())
            break
        except Exception:  # noqa: BLE001
            time.sleep(3)
    if d is None:
        return "## FAILED: " + query + "\n"
    out = []
    for r in d.get("resultList", {}).get("result", []):
        j = r.get("journalInfo", {})
        out.append("## %s | %s | %s %s %s | %s | doi:%s" % (
            (r.get("authorString") or "")[:80], r.get("pubYear"),
            j.get("journal", {}).get("title"), j.get("volume"), r.get("pageInfo"),
            r.get("title"), r.get("doi")))
        out.append(re.sub("<[^>]+>", "", r.get("abstractText") or "")[:maxlen])
        out.append("")
    return "\n".join(out) if out else "## NO HIT: " + query + "\n"


if __name__ == "__main__":
    for q in sys.argv[1:]:
        print(epmc(q), flush=True); time.sleep(1.0)