import re

from jev import ask

THRESHOLD = 0.5
CITE = re.compile(r"\[(c\d+)\]")


def cited_sentences(answer):
    sentences = re.split(r"(?<=[.!?\]])\s+(?=[A-Z0-9\"'*(])", answer.strip())
    out = []
    for sentence in sentences:
        ids = sorted(set(CITE.findall(sentence)))
        text = re.sub(r"\s+([.,;:!?])", r"\1", CITE.sub("", sentence)).strip()
        if ids and len(text) > 3:
            out.append({"sentence": text, "cites": ids})
    return out


def verify(answer, chunks):
    claims = [c for c in cited_sentences(answer) if all(int(i[1:]) <= len(chunks) for i in c["cites"])]
    if not claims:
        return {"checked": 0, "passed": True, "escalate": False, "claims": []}
    notes = {f"c{i + 1}": c["text"] for i, c in enumerate(chunks)}
    state = {"notes": notes, "sentences": {f"s{i}": c["sentence"] for i, c in enumerate(claims)}}
    questions = {
        f"s{i}": {
            "type": "noul",
            "instructions": f"Is every fact in `sentences.s{i}` stated in "
                            + " or ".join(f"`notes.{cid}`" for cid in c["cites"]) + "?",
            "criteria": {"true": "The cited note states the facts, names, and numbers in the sentence.",
                         "false": "The sentence adds or changes a fact, name, or number the cited note does not state."},
        }
        for i, c in enumerate(claims)
    }
    answers = ask(state, questions, stage="verify")
    for i, claim in enumerate(claims):
        claim["support"] = answers[f"s{i}"]["noul"]
    weak = [c for c in claims if c["support"] < THRESHOLD]
    return {"checked": len(claims), "passed": not weak, "escalate": bool(weak), "claims": claims, "weak": weak}