"""Separate supported answer scope from the search's technical selection limits.

Supported means the delivered facts/excerpts have evidence; it never promises
exhaustive retrieval, a complete source document or absence of other records.
"""

import re

from tools.answers.context_policy import normalized


def response_scope(question: str, *, content: bool = False) -> str:
    query = normalized(re.sub(r'[„“"«][^„“”"»]+[“”"»]', " ", question))
    # Record lists differ from the numbered assignment of one selected work.
    records = r"(?:prac\w*|projekt\w*|student\w*|osob\w*|autor\w*|tag\w*|kategori\w*|zdroj\w*)"
    modifiers = (
        r"(?:(?:vsetk\w*|diplomov\w*|bakalarsk\w*|zaverecn\w*|timov\w*|vyskumn\w*|a|aj)\s+)*"
    )
    if re.search(r"\b(?:kolko|pocet|spocitaj)\b", query):
        return "count"
    if re.search(
        rf"\b(?:vsetk\w*|upln\w*|kompletn\w*)\s+{modifiers}{records}\b"
        rf"|\b(?:ake|ktore|vypis|zoznam|prehlad)\s+{modifiers}{records}\b",
        query,
    ):
        return "list"
    if content:
        if re.search(r"\b(?:zadani\w*|ciel\w*)\b", query) and not re.search(
            r"\b(?:strucn\w*|zhrn\w*)\b", query
        ):
            return "assignment"
        if re.search(
            r"\b(?:comu|o com|opis\w*|popis\w*|obsah\w*|zamer\w*|zhrn\w*|strucn\w*)\b", query
        ):
            return "overview"
    return "fact"


def answer_coverage(answer: dict, context: dict) -> dict:
    """Describe only the scope of an already validated RAG selection."""
    requirements = context.get("requirements", {})
    scope = response_scope(context.get("question", ""), content=requirements.get("content", False))
    reasons = list(context.get("truncation_reasons") or [])
    selected = {row.get("source_id") for row in answer.get("evidence_quotes", [])}
    cited = set(answer.get("source_urls", []))
    clipped = any(
        "[OBSAH ZDROJA OREZANÝ]" in row.get("body", "")
        for row in context.get("source_blocks", [])
        if row.get("source_id") in selected
        or (
            not selected and (row.get("source_url") in cited or answer.get("status") == "no_answer")
        )
    )
    # A context budget may drop only unrelated sources. A clipping marker in
    # the actual cited block is stronger evidence than this global reason.
    context_limited = any(
        reason in reasons
        for reason in ["llm_context_budget", "answer_candidate_budget", "evidence_unit_limit"]
    )
    limited = context.get("complete") is not True or context.get("truncated") is True
    limitations = [*reasons]
    if clipped:
        limitations.append("cited_source_text_clipped")
    warnings = []
    status = answer.get("status")
    if status == "ok":
        coverage = "supported"
        if any(
            requirements.get(key) and key not in fields
            for fields in requirements.get("available_fields", {}).values()
            for key in ["title", "year", "start_year"]
        ):
            coverage = "partial"
            warnings.append("partial_requested_fields")
        if requirements.get("facets"):
            from tools.answers.content_selection import missing_facets

            if missing_facets(answer, context):
                coverage = "partial"
                warnings.append("partial_requested_aspects")
        elif requirements.get("content"):
            from tools.answers.rag_evidence import missing_content_people

            if missing_content_people(answer, context):
                coverage = "partial"
                warnings.append("partial_requested_aspects")
        if scope == "overview" and (clipped or context_limited):
            coverage = "partial"
            warnings.append("overview_aspects_clipped")
        if scope == "list" and (limited or clipped):
            coverage = "partial"
            warnings.append("list_may_be_incomplete")
        elif scope == "count" and (context.get("aggregation") or {}).get("complete") is not True:
            coverage = "unknown"
            warnings.append("count_not_established")
        elif scope == "assignment" and clipped:
            coverage = "partial"
            warnings.append("assignment_text_clipped")
        elif (
            scope == "assignment"
            and limited
            and re.search(
                r"\b(?:vsetk\w*|upln\w*|kompletn\w*|cele)\b",
                normalized(context.get("question", "")),
            )
        ):
            coverage = "partial"
            warnings.append("assignment_completeness_unknown")
    elif status == "no_answer":
        coverage = "not_found"
        if clipped or context_limited:
            warnings.append("missing_information_with_clipped_context")
    else:
        coverage = "unavailable"
    return {
        "scope": scope,
        "status": coverage,
        "warnings": warnings,
        "limitations": list(dict.fromkeys(limitations)),
    }


def coverage_notices(coverage: dict) -> list[str]:
    messages = {
        "overview_aspects_clipped": "Časť podkladov bola skrátená; prehľad preto nemusí pokrývať všetky oblasti práce.",
        "list_may_be_incomplete": "Uvedený zoznam nemusí obsahovať všetky záznamy.",
        "assignment_text_clipped": "Časť podkladov k zadaniu bola skrátená; uvedené body nemusia tvoriť celé zadanie.",
        "assignment_completeness_unknown": "Z dostupných podkladov nemožno zaručiť všetky body zadania.",
        "missing_information_with_clipped_context": "Časť podkladov bola pri príprave kontextu skrátená.",
        "count_not_established": "Celkový počet sa z dostupných podkladov nedá spoľahlivo určiť.",
    }
    notices = [messages[reason] for reason in coverage["warnings"] if reason in messages]
    if "list_may_be_incomplete" in coverage["warnings"]:
        notices.append("Výpis môžeš zúžiť uvedením osoby, typu práce alebo konkrétneho roku.")
    return notices