sitemap contract audit derived

{
  "input": {
    "body": {
      "sitemap": "<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n<urlset xmlns=\"http://www.sitemaps.org/schemas/sitemap/0.9\">\n<url><loc>https://example.test/widgets/widget-1</loc><lastmod>2026-09-30</lastmod></url>\n<url><loc>https://example.test/search?q=widget&page=2</loc><lastmod>2026-13-40</lastmod></url>\n<url><loc>https://example.test/widgets/widget-1</loc></url>\n<url><loc>https://staging.example.test/widgets/widget-9</loc><lastmod>2026-09-29T10:00:00Z</lastmod></url>\n<url><loc>https://example.test/widgets/widget-2#reviews</loc><lastmod>2026-09-28</lastmod></url>\n<url><loc>/widgets/widget-3</loc></url>\n</urlset>",
      "max_urls": 50000,
      "expected_host": "example.test",
      "require_lastmod": true
    },
    "type": "http",
    "method": "POST",
    "bodyType": "json"
  },
  "output": {
    "type": "json",
    "example": {
      "hosts": [
        "example.test",
        "staging.example.test"
      ],
      "valid": false,
      "limits": {
        "maxPages": 50,
        "maxListed": 200,
        "maxCookies": 100,
        "maxHeaders": 200,
        "maxFindings": 500,
        "maxHtmlBytes": 262144,
        "maxSitemapUrls": 10000,
        "maxSitemapBytes": 1048576
      },
      "passed": false,
      "entries": [
        {
          "loc": "https://example.test/widgets/widget-1",
          "host": "example.test",
          "lastmod": "2026-09-30"
        },
        {
          "loc": "https://example.test/search?q=widget&page=2",
          "host": "example.test",
          "lastmod": "2026-13-40"
        },
        {
          "loc": "https://example.test/widgets/widget-1",
          "host": "example.test",
          "lastmod": null
        }
      ],
      "complete": true,
      "findings": [
        {
          "url": "https://example.test/search?q=widget&page=2",
          "code": "LOC_CONTAINS_UNESCAPED_AMPERSAND",
          "detail": "https://example.test/search?q=widget&page=2 contains a bare ampersand, which makes the document invalid XML."
        },
        {
          "url": "https://example.test/search?q=widget&page=2",
          "code": "LASTMOD_NOT_A_REAL_DATE",
          "detail": "https://example.test/search?q=widget&page=2 declares lastmod \"2026-13-40\", which matches the shape but is not a real date."
        },
        {
          "url": "https://example.test/widgets/widget-1",
          "code": "LOC_DUPLICATED",
          "detail": "https://example.test/widgets/widget-1 appears at entries 1 and 3."
        }
      ],
      "request_id": "example-request",
      "service_id": "sitemap_contract_audit",
      "assumptions": [
        "Entries are read by pattern rather than by a full XML parser, which is enough to extract loc and lastmod and avoids taking on a parser as a dependency. A document that is not well-formed XML may there...",
        "An unescaped ampersand and a double-escaped one are reported separately: the first makes the document invalid XML and the second names a URL that does not exist.",
        "lastmod is checked against the W3C datetime shape and then against being a real date, because a crawler ignores one that is neither."
      ],
      "entry_count": 6,
      "limitations": [
        "Structure of the document supplied. No URL is fetched, so whether each one resolves is not known here.",
        "valid is true only when every entry was examined and none broke a rule."
      ],
      "observed_at": "2026-10-02T00:00:00.000Z",
      "not_examined": [],
      "finding_count": 7,
      "service_version": "1.0.0",
      "findings_by_code": {
        "LASTMOD_ABSENT": 1,
        "LOC_DUPLICATED": 1,
        "LOC_CROSSES_HOST": 1,
        "LOC_NOT_ABSOLUTE_URL": 1,
        "LOC_CONTAINS_FRAGMENT": 1,
        "LASTMOD_NOT_A_REAL_DATE": 1,
        "LOC_CONTAINS_UNESCAPED_AMPERSAND": 1
      },
      "is_sitemap_index": false,
      "distinct_loc_count": 4,
      "with_lastmod_count": 4,
      "examined_entry_count": 5
    }
  }
}