coulomb-social/tests/test_rendering_audit.py

"""Rendering review uses synthetic notes and never accepts private corpus fidelity."""

import hashlib
import json
import os
import subprocess
import sys
from pathlib import Path

from coulomb_social.apps.spaces.content import render_markdown
from coulomb_social.apps.spaces.rendering_audit import audit_body, review_card


def test_audit_uses_product_renderer_and_reports_custom_tags_attributes_and_schemes():
    body = ('# Synthetic\n\n<topic>Placeholder</topic><br>Text\n'
            '<img src="assets/picture.png" onerror="synthetic()">'
            '<a href="javascript:synthetic()">Unsafe</a>')
    audit, rendered = audit_body(body)
    assert rendered == render_markdown(body)
    assert audit["sanitization_changed_html"]
    assert audit["markup_changed_by_sanitization"]
    assert not audit["serialization_only_change"]
    assert audit["removed_tag_counts"] == {"topic": 1}
    assert {a["attribute"] for a in audit["removed_attributes"]} == {"onerror", "href"}
    assert "assets/picture.png" in rendered and "<br>" in rendered
    assert audit["body_sha256"] == hashlib.sha256(body.encode()).hexdigest()
    assert not audit["original_bubble_render_compared"]
    assert not audit["productive_fidelity_accepted"]
    assert audit["reference_occurrences_before"] == 2
    assert audit["reference_occurrences_after"] == 1
    assert not audit["reference_attributes_preserved"]
    assert audit["removed_reference_occurrences"] == 1


def test_link_entities_duplicates_and_relative_assets_preserve_exact_reference_attributes():
    body = ('[first](https://example.invalid/?a=1&b=2#part)\n\n'
            '[second](https://example.invalid/?a=1&b=2#part)\n\n'
            '<a href="https://example.invalid/?a=1&amp;b=2#part">third</a>'
            '<img src="assets/synthetic.png">')
    audit, _ = audit_body(body)
    assert audit['reference_occurrences_before'] == 4
    assert audit['reference_occurrences_after'] == 4
    assert audit['reference_attributes_preserved']
    assert audit['removed_reference_occurrences'] == 0
    assert audit['added_reference_occurrences'] == 0


def test_serialized_line_break_difference_is_not_reported_as_lost_markup():
    audit, _ = audit_body("First<br/>Second")
    assert audit["serialization_only_change"]
    assert not audit["markup_changed_by_sanitization"]
    assert not audit["visible_text_changed_by_sanitization"]


def test_continued_numbered_lists_keep_their_starts_through_sanitization():
    body = "2. Second item\n3. Third item\n\nSeparate paragraph.\n\n8. Eighth item"
    audit, rendered = audit_body(body)
    assert '<ol start="2">' in rendered
    assert '<ol start="8">' in rendered
    assert not audit["markup_changed_by_sanitization"]
    assert not audit["visible_text_changed_by_sanitization"]
    assert not audit["productive_fidelity_accepted"]


def test_list_start_permission_does_not_allow_event_handlers_or_custom_markup():
    body = ('<ol start="4" onclick="synthetic()"><li>Fourth item</li></ol>'
            '<topic name="synthetic">Placeholder</topic>'
            '<a href="javascript:synthetic()">Link</a>')
    audit, rendered = audit_body(body)
    assert '<ol start="4">' in rendered
    assert 'onclick' not in rendered and 'javascript:' not in rendered
    assert '<topic' not in rendered and 'Placeholder' in rendered
    assert {a["attribute"] for a in audit["removed_attributes"]} == {
        "onclick", "name", "href",
    }


def test_review_card_escapes_source_and_blocks_resources_and_interaction():
    body = '<img src="https://example.invalid/synthetic.png"><script>synthetic()</script>'
    audit, rendered = audit_body(body)
    card = review_card("</h1><script>synthetic()</script>", body, rendered, audit,
                       source_id='a/"?b').decode()
    assert "<script>" not in card
    assert "&lt;script&gt;" in card
    assert "default-src 'none'" in card
    assert "base-uri 'none'" in card and "form-action 'none'" in card
    assert "<div inert>" in card
    assert 'https://coulomb.social/pg_chunk/a%2F%22%3Fb' in card


def test_cli_keeps_missing_bodies_and_private_permissions_and_refuses_overwrite(tmp_path):
    repo = Path(__file__).resolve().parents[1]
    source = tmp_path / "articles.json"
    source.write_text(json.dumps({"a": {"content_text": "Synthetic", "nomer_text": "Private"},
                                  "b": {"_id": "b"}}))
    output = tmp_path / "audit"
    cmd = [sys.executable, str(repo / "scripts/audit-bubble-rendering.py"), str(source),
           "--output", str(output)]
    result = subprocess.run(cmd, capture_output=True, text=True)
    assert result.returncode == 0, result.stderr
    assert "Private" not in result.stdout
    report = json.loads((output / "audit.json").read_text())
    assert len(report["records"]) == 2
    assert report["records"][1]["status"] == "body_missing"
    assert (output / "index.html").is_file()
    assert os.stat(output).st_mode & 0o777 == 0o700
    assert all(os.stat(p).st_mode & 0o777 == 0o600 for p in output.iterdir())
    assert subprocess.run(cmd, capture_output=True).returncode == 1