"""neutralize — opt-in, pure defang of active content in model OUTPUT.

Query-time guardrails guard the answer; this guards the *persisted artifact*.
When model output is written to a wiki, doc, or knowledge base and later rendered,
active-content constructs become an exfiltration channel: a markdown image URL is
auto-fetched the moment the page renders, leaking whatever the attacker packed
into it — with no click. This is the EchoLeak class (CVE-2025-32711). Such
carriers are neither injection strings nor high-entropy blobs, so ``lexicon`` and
``entropy`` do not see them; neutralizing them is a distinct control (OWASP
LLM05 — Improper Output Handling).

Defang, don't delete. Each active construct is rewritten to an inert but still
human-auditable form: URLs get a non-resolvable scheme and bracketed dots
(``https://evil.com`` -> ``hxxps://evil[.]com``), and raw active HTML is escaped
so a renderer shows it as literal text instead of executing it. The visible
information survives review; only the machine-actionable affordance dies.

The pattern table this mutator rewrites is shared with the report-only detector
:func:`~llm_ingestion_guard.active_content.scan_active_content` and lives in
``active_content`` — detection feeds the standard gate; defanging stays the
separate, opt-in mutation below.

Two properties are load-bearing and mirror the sanitizer:

1. **Opt-in and separate.** Calling this function *is* the opt-in to mutate.
   Detection elsewhere in the library stays report-only (design principles 3 & 4);
   the report-only output gate (``output``) never rewrites. A caller that wants
   findings without mutation reads ``result.report`` and discards ``result.text``.
2. **Byte-identical on clean input.** Output with no active construct is returned
   unchanged with an empty report. Benign inline formatting (``<b>``, ``<em>``)
   and prose containing stray ``<``, ``>``, ``[`` are left untouched.

Scope note (conceded, not hidden): this is a targeted defanger, not a full HTML
sanitizer. Text *between* escaped tags (e.g. a ``<script>`` body) is neutralized
as active content by escaping the tags, but bare URLs left in that residual text
stay visible; balanced-parenthesis link URLs are matched conservatively. The goal
is to kill the zero-click auto-fetch/execute affordance, not to rewrite every URL.
"""
from __future__ import annotations

import re
from dataclasses import dataclass

from .active_content import (
    AUTOLINK_RE,
    DATA_URI_RE,
    HTML_TAG_RE,
    MD_IMAGE_RE,
    MD_LINK_RE,
    MD_REFDEF_RE,
    URL_IN_TEXT_RE,
    defang_url,
    is_active_tag,
    redact,
)
from .calibration import MAX_INPUT_CHARS
from .contract import assert_within_input_cap
from .report import Finding, Report, Severity, Source


@dataclass(frozen=True)
class NeutralizeResult:
    """The defanged text plus a report of every construct that was neutralized."""

    text: str
    report: Report


def neutralize(
    text: str,
    source: Source = Source.OUTPUT,
    max_input_chars: int = MAX_INPUT_CHARS,
) -> NeutralizeResult:
    """Defang active-content constructs in ``text`` and report each class.

    Rewrites markdown images/links, reference-link definitions, angle-bracket
    autolinks, raw active HTML, and ``data:`` URIs into inert forms. Text with no
    such construct is returned byte-identical with an empty report.

    Raises :class:`~llm_ingestion_guard.contract.OversizeInputError` above
    ``max_input_chars``. A partially defanged artifact is the worst outcome
    available here: it *looks* neutralized, and the live constructs are all in
    the tail nobody re-reads.
    """
    assert_within_input_cap(text, surface="neutralize", max_input_chars=max_input_chars)
    report = Report()
    out = text

    def _flag(label: str, severity: Severity, count: int, evidence: str) -> None:
        report.add(Finding(
            label=label, severity=severity, source=source, detector="neutralize",
            count=count, evidence=redact(evidence), owasp="LLM05",
        ))

    # 1. Markdown images — the zero-click auto-fetch primitive (EchoLeak). Run
    #    first so the leading `!` is consumed before the inline-link pass.
    img_ev: list[str] = []

    def _img(m: re.Match[str]) -> str:
        defanged = defang_url(m.group("url"))
        img_ev.append(defanged)
        return f'![{m.group("alt")}]({defanged}{m.group("title")})'

    out, n_img = MD_IMAGE_RE.subn(_img, out)
    if n_img:
        _flag("neutralize:markdown-image", Severity.HIGH, n_img, img_ev[0])

    # 2. Markdown inline links — clickable / prefetchable exfil target.
    link_ev: list[str] = []

    def _link(m: re.Match[str]) -> str:
        defanged = defang_url(m.group("url"))
        link_ev.append(defanged)
        return f'[{m.group("text")}]({defanged}{m.group("title")})'

    out, n_link = MD_LINK_RE.subn(_link, out)
    if n_link:
        _flag("neutralize:markdown-link", Severity.MEDIUM, n_link, link_ev[0])

    # 3. Reference-style link definitions — the documented image-filter bypass.
    ref_ev: list[str] = []

    def _ref(m: re.Match[str]) -> str:
        defanged = defang_url(m.group("url"))
        ref_ev.append(defanged)
        return m.group("pre") + defanged

    out, n_ref = MD_REFDEF_RE.subn(_ref, out)
    if n_ref:
        _flag("neutralize:reference-link", Severity.MEDIUM, n_ref, ref_ev[0])

    # 4. Angle-bracket autolinks.
    auto_ev: list[str] = []

    def _auto(m: re.Match[str]) -> str:
        defanged = defang_url(m.group("url"))
        auto_ev.append(defanged)
        return f"<{defanged}>"

    out, n_auto = AUTOLINK_RE.subn(_auto, out)
    if n_auto:
        _flag("neutralize:autolink", Severity.MEDIUM, n_auto, auto_ev[0])

    # 5. Raw active HTML — escape so a renderer shows it as inert literal text.
    html_state = {"count": 0, "ev": ""}

    def _html(m: re.Match[str]) -> str:
        tag = m.group(0)
        if not is_active_tag(m.group("name"), m.group("attrs") or ""):
            return tag
        html_state["count"] += 1
        if not html_state["ev"]:
            html_state["ev"] = tag
        inert = URL_IN_TEXT_RE.sub(lambda u: defang_url(u.group(0)), tag)
        return inert.replace("<", "&lt;").replace(">", "&gt;")

    out = HTML_TAG_RE.sub(_html, out)
    if html_state["count"]:
        _flag("neutralize:raw-html", Severity.HIGH, html_state["count"], html_state["ev"])

    # 6. Standalone `data:` URIs left in prose (those inside constructs above are
    #    already defanged; the literal `data:` colon is gone, so no double count).
    data_ev: list[str] = []

    def _data(m: re.Match[str]) -> str:
        defanged = defang_url(m.group(0))
        data_ev.append(defanged)
        return defanged

    out, n_data = DATA_URI_RE.subn(_data, out)
    if n_data:
        _flag("neutralize:data-uri", Severity.HIGH, n_data, data_ev[0])

    return NeutralizeResult(text=out, report=report)