@rivi-software/agentic-seo-check 0.1.1 → 0.3.0

package/dist/core/rules/head.js

@@ -0,0 +1,116 @@
+import { normalizeUrl, resolveUrl } from "../url.js";
+import { cap, defineRule, GOOGLE_DOCS } from "./rule.js";
+/** The HTML spec's limit for the element that declares the encoding. */
+const CHARSET_PRESCAN_BYTES = 1024;
+const plural = (n, one, many = `${one}s`) => `${n} ${n === 1 ? one : many}`;
+export const headRules = [
+    defineRule({
+        id: "head.closed-early",
+        category: "document",
+        severity: "error",
+        description: "An element that does not belong in <head> (an <img>, <iframe>, <div>, stray text) ends it early, so search engines read the metadata after it as part of <body> and ignore it.",
+        recommendation: "Move the element out of <head>, into <body>, or at least below every <title>, <meta> and <link>. Only <title>, <meta>, <link>, <script>, <style>, <base>, <noscript> and <template> belong in <head>. A tag manager's or ad pixel's <noscript><iframe> or <img> goes right after the opening <body> tag.",
+        docs: GOOGLE_DOCS.validMetadata,
+    }, ({ page }, make) => {
+        const { closedBy, closedInNoscript, afterClose } = page.head;
+        if (!closedBy || afterClose.length === 0) {
+            return null;
+        }
+        if (closedInNoscript) {
+            return make(`A <noscript> in <head> holds ${closedBy}, which ends <head> for a parser that does not run JavaScript, so it reads the ${plural(afterClose.length, "metadata element")} after it as <body>: ${cap(afterClose, 5).join(", ")}.`, {
+                severity: "info",
+                recommendation: "Move the <noscript> block below every <title>, <meta> and <link>, or right after the opening <body> tag, where tag managers and ad pixels document it. Inside a <noscript> in <head>, only <link>, <meta> and <style> keep <head> open.",
+                selector: "head > noscript",
+                evidence: {
+                    closedBy,
+                    inNoscript: true,
+                    metadataAfter: cap(afterClose),
+                },
+            });
+        }
+        // Losing the viewport costs the mobile layout; losing the rest costs what Google indexes.
+        const onlyViewport = afterClose.every((m) => m === '<meta name="viewport">');
+        // An invisible character is removed, not moved: it usually comes from a file saved with a BOM.
+        const invisible = closedBy.startsWith("invisible character");
+        return make(`<head> ends at ${closedBy}, so Google ignores the ${plural(afterClose.length, "metadata element")} after it: ${cap(afterClose, 5).join(", ")}.`, {
+            severity: onlyViewport ? "warning" : "error",
+            recommendation: invisible
+                ? "Remove the invisible character from <head>. A U+FEFF byte order mark usually comes from a template or include file saved as UTF-8 with BOM: save it as UTF-8 without BOM. A U+00A0 comes from an &nbsp; in the template's <head>."
+                : undefined,
+            selector: "head",
+            evidence: {
+                closedBy,
+                inNoscript: false,
+                metadataAfter: cap(afterClose),
+            },
+        });
+    }),
+    defineRule({
+        id: "head.metadata-in-body",
+        category: "document",
+        severity: "warning",
+        description: "Metadata that search engines read only in <head> (title, meta description, viewport, canonical, hreflang) is written in <body> (warning). Metadata a framework streams into a hidden part of <body> and moves into <head> with JavaScript, as Next.js does for an async generateMetadata, is info. Robots meta tags are not reported: Google honours them in <body> too.",
+        recommendation: "Move these elements into <head>. Google accepts rel=canonical only in <head>. A framework that renders them in a page component usually has a head API for them (metadata export, <Head>, useHead, <svelte:head>).",
+        docs: GOOGLE_DOCS.validMetadata,
+    }, ({ page }, make) => {
+        const { inBody, streamedInBody } = page.head;
+        if (inBody.length > 0) {
+            return make(`${plural(inBody.length, "metadata element")} ${inBody.length === 1 ? "is" : "are"} in <body>: ${cap(inBody, 5).join(", ")}.`, { selector: "body", evidence: { elements: cap(inBody) } });
+        }
+        // Next.js (15.2+) streams metadata from an async generateMetadata this way to clients it does
+        // not count as HTML-limited bots; Googlebot reads it after rendering.
+        return streamedInBody.length > 0
+            ? make(`${plural(streamedInBody.length, "metadata element")} ${streamedInBody.length === 1 ? "is" : "are"} streamed into a hidden part of <body> (React or Next.js streaming metadata): ${cap(streamedInBody, 5).join(", ")}.`, {
+                severity: "info",
+                recommendation: "Google renders the page and reads streamed metadata, so this is fine for Google Search. Crawlers that do not run JavaScript only get it in <head> if the framework holds the response for them: in Next.js, add their User-Agents to htmlLimitedBots in next.config, or make generateMetadata static.",
+                selector: "body [hidden]",
+                evidence: { elements: cap(streamedInBody), streamed: true },
+            })
+            : null;
+    }),
+    defineRule({
+        id: "meta-refresh.redirect",
+        category: "indexing",
+        severity: "warning",
+        description: 'A <meta http-equiv="refresh"> sends visitors to another URL. Google reads an instant one as a permanent redirect (info) and a delayed one as a temporary redirect (warning), and prefers a redirect from the server.',
+        recommendation: "Redirect on the server with a 301 (or 308) to the new URL. If the server cannot redirect, set the meta refresh to 0 seconds, which Google reads as a permanent redirect.",
+        docs: GOOGLE_DOCS.redirects,
+    }, ({ page }, make) => {
+        const redirect = page.head.refresh.find((r) => r.url);
+        if (!redirect?.url) {
+            return null;
+        }
+        const target = resolveUrl(redirect.url, page.url) ?? redirect.url;
+        const delay = redirect.seconds ?? 0;
+        // A refresh to the page's own URL reloads it (a news front page); it redirects nowhere.
+        if ((normalizeUrl(target) ?? target) ===
+            (normalizeUrl(page.url) ?? page.url)) {
+            return null;
+        }
+        return make(delay > 0
+            ? `Page redirects to ${target} with a meta refresh after ${plural(delay, "second")}, which Google treats as a temporary redirect.`
+            : `Page redirects to ${target} with an instant meta refresh.`, {
+            severity: delay > 0 ? "warning" : "info",
+            selector: 'meta[http-equiv="refresh"]',
+            evidence: { target, seconds: redirect.seconds },
+        });
+    }),
+    defineRule({
+        id: "charset.late",
+        category: "document",
+        severity: "info",
+        description: "The character encoding is declared after the first 1024 bytes, where the HTML spec requires it, and the Content-Type header does not declare it.",
+        recommendation: 'Put <meta charset="utf-8"> first in <head>, before any script, style or comment, or send the encoding in the Content-Type header (text/html; charset=utf-8).',
+        docs: "https://html.spec.whatwg.org/multipage/semantics.html#charset",
+    }, ({ page, response }, make) => {
+        const end = page.head.charsetEndByte;
+        if (end === null || end <= CHARSET_PRESCAN_BYTES) {
+            return null;
+        }
+        if (/charset=/iu.test(response?.contentType ?? "")) {
+            return null;
+        }
+        return make(`The charset declaration ends at byte ${end}, past the first ${CHARSET_PRESCAN_BYTES}.`, { selector: "head > meta[charset]", evidence: { endsAtByte: end } });
+    }),
+];
+//# sourceMappingURL=head.js.map

package/dist/core/rules/head.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"head.js","sourceRoot":"","sources":["../../../src/core/rules/head.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,YAAY,EAAE,UAAU,EAAE,MAAM,WAAW,CAAC;AACrD,OAAO,EAAE,GAAG,EAAE,UAAU,EAAE,WAAW,EAAE,MAAM,WAAW,CAAC;AAEzD,wEAAwE;AACxE,MAAM,qBAAqB,GAAG,IAAI,CAAC;AAEnC,MAAM,MAAM,GAAG,CAAC,CAAS,EAAE,GAAW,EAAE,IAAI,GAAG,GAAG,GAAG,GAAG,EAAU,EAAE,CAClE,GAAG,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC;AAEjC,MAAM,CAAC,MAAM,SAAS,GAAG;IACvB,UAAU,CACR;QACE,EAAE,EAAE,mBAAmB;QACvB,QAAQ,EAAE,UAAU;QACpB,QAAQ,EAAE,OAAO;QACjB,WAAW,EACT,gLAAgL;QAClL,cAAc,EACZ,0SAA0S;QAC5S,IAAI,EAAE,WAAW,CAAC,aAAa;KAChC,EACD,CAAC,EAAE,IAAI,EAAE,EAAE,IAAI,EAAE,EAAE;QACjB,MAAM,EAAE,QAAQ,EAAE,gBAAgB,EAAE,UAAU,EAAE,GAAG,IAAI,CAAC,IAAI,CAAC;QAE7D,IAAI,CAAC,QAAQ,IAAI,UAAU,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;YACzC,OAAO,IAAI,CAAC;QACd,CAAC;QAED,IAAI,gBAAgB,EAAE,CAAC;YACrB,OAAO,IAAI,CACT,gCAAgC,QAAQ,kFAAkF,MAAM,CAAC,UAAU,CAAC,MAAM,EAAE,kBAAkB,CAAC,wBAAwB,GAAG,CAAC,UAAU,EAAE,CAAC,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,GAAG,EAC/N;gBACE,QAAQ,EAAE,MAAM;gBAChB,cAAc,EACZ,yOAAyO;gBAC3O,QAAQ,EAAE,iBAAiB;gBAC3B,QAAQ,EAAE;oBACR,QAAQ;oBACR,UAAU,EAAE,IAAI;oBAChB,aAAa,EAAE,GAAG,CAAC,UAAU,CAAC;iBAC/B;aACF,CACF,CAAC;QACJ,CAAC;QAED,0FAA0F;QAC1F,MAAM,YAAY,GAAG,UAAU,CAAC,KAAK,CACnC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,KAAK,wBAAwB,CACtC,CAAC;QAEF,+FAA+F;QAC/F,MAAM,SAAS,GAAG,QAAQ,CAAC,UAAU,CAAC,qBAAqB,CAAC,CAAC;QAE7D,OAAO,IAAI,CACT,kBAAkB,QAAQ,2BAA2B,MAAM,CAAC,UAAU,CAAC,MAAM,EAAE,kBAAkB,CAAC,cAAc,GAAG,CAAC,UAAU,EAAE,CAAC,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,GAAG,EAChJ;YACE,QAAQ,EAAE,YAAY,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,OAAO;YAC5C,cAAc,EAAE,SAAS;gBACvB,CAAC,CAAC,mOAAmO;gBACrO,CAAC,CAAC,SAAS;YACb,QAAQ,EAAE,MAAM;YAChB,QAAQ,EAAE;gBACR,QAAQ;gBACR,UAAU,EAAE,KAAK;gBACjB,aAAa,EAAE,GAAG,CAAC,UAAU,CAAC;aAC/B;SACF,CACF,CAAC;IACJ,CAAC,CACF;IACD,UAAU,CACR;QACE,EAAE,EAAE,uBAAuB;QAC3B,QAAQ,EAAE,UAAU;QACpB,QAAQ,EAAE,SAAS;QACnB,WAAW,EACT,0WAA0W;QAC5W,cAAc,EACZ,oNAAoN;QACtN,IAAI,EAAE,WAAW,CAAC,aAAa;KAChC,EACD,CAAC,EAAE,IAAI,EAAE,EAAE,IAAI,EAAE,EAAE;QACjB,MAAM,EAAE,MAAM,EAAE,cAAc,EAAE,GAAG,IAAI,CAAC,IAAI,CAAC;QAE7C,IAAI,MAAM,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;YACtB,OAAO,IAAI,CACT,GAAG,MAAM,CAAC,MAAM,CAAC,MAAM,EAAE,kBAAkB,CAAC,IAAI,MAAM,CAAC,MAAM,KAAK,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,KAAK,eAAe,GAAG,CAAC,MAAM,EAAE,CAAC,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,GAAG,EAC7H,EAAE,QAAQ,EAAE,MAAM,EAAE,QAAQ,EAAE,EAAE,QAAQ,EAAE,GAAG,CAAC,MAAM,CAAC,EAAE,EAAE,CAC1D,CAAC;QACJ,CAAC;QAED,8FAA8F;QAC9F,sEAAsE;QACtE,OAAO,cAAc,CAAC,MAAM,GAAG,CAAC;YAC9B,CAAC,CAAC,IAAI,CACF,GAAG,MAAM,CAAC,cAAc,CAAC,MAAM,EAAE,kBAAkB,CAAC,IAAI,cAAc,CAAC,MAAM,KAAK,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,KAAK,iFAAiF,GAAG,CAAC,cAAc,EAAE,CAAC,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,GAAG,EACvN;gBACE,QAAQ,EAAE,MAAM;gBAChB,cAAc,EACZ,uSAAuS;gBACzS,QAAQ,EAAE,eAAe;gBACzB,QAAQ,EAAE,EAAE,QAAQ,EAAE,GAAG,CAAC,cAAc,CAAC,EAAE,QAAQ,EAAE,IAAI,EAAE;aAC5D,CACF;YACH,CAAC,CAAC,IAAI,CAAC;IACX,CAAC,CACF;IACD,UAAU,CACR;QACE,EAAE,EAAE,uBAAuB;QAC3B,QAAQ,EAAE,UAAU;QACpB,QAAQ,EAAE,SAAS;QACnB,WAAW,EACT,sNAAsN;QACxN,cAAc,EACZ,0KAA0K;QAC5K,IAAI,EAAE,WAAW,CAAC,SAAS;KAC5B,EACD,CAAC,EAAE,IAAI,EAAE,EAAE,IAAI,EAAE,EAAE;QACjB,MAAM,QAAQ,GAAG,IAAI,CAAC,IAAI,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC;QAEtD,IAAI,CAAC,QAAQ,EAAE,GAAG,EAAE,CAAC;YACnB,OAAO,IAAI,CAAC;QACd,CAAC;QAED,MAAM,MAAM,GAAG,UAAU,CAAC,QAAQ,CAAC,GAAG,EAAE,IAAI,CAAC,GAAG,CAAC,IAAI,QAAQ,CAAC,GAAG,CAAC;QAClE,MAAM,KAAK,GAAG,QAAQ,CAAC,OAAO,IAAI,CAAC,CAAC;QAEpC,wFAAwF;QACxF,IACE,CAAC,YAAY,CAAC,MAAM,CAAC,IAAI,MAAM,CAAC;YAChC,CAAC,YAAY,CAAC,IAAI,CAAC,GAAG,CAAC,IAAI,IAAI,CAAC,GAAG,CAAC,EACpC,CAAC;YACD,OAAO,IAAI,CAAC;QACd,CAAC;QAED,OAAO,IAAI,CACT,KAAK,GAAG,CAAC;YACP,CAAC,CAAC,qBAAqB,MAAM,8BAA8B,MAAM,CAAC,KAAK,EAAE,QAAQ,CAAC,gDAAgD;YAClI,CAAC,CAAC,qBAAqB,MAAM,gCAAgC,EAC/D;YACE,QAAQ,EAAE,KAAK,GAAG,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,MAAM;YACxC,QAAQ,EAAE,4BAA4B;YACtC,QAAQ,EAAE,EAAE,MAAM,EAAE,OAAO,EAAE,QAAQ,CAAC,OAAO,EAAE;SAChD,CACF,CAAC;IACJ,CAAC,CACF;IACD,UAAU,CACR;QACE,EAAE,EAAE,cAAc;QAClB,QAAQ,EAAE,UAAU;QACpB,QAAQ,EAAE,MAAM;QAChB,WAAW,EACT,kJAAkJ;QACpJ,cAAc,EACZ,8JAA8J;QAChK,IAAI,EAAE,+DAA+D;KACtE,EACD,CAAC,EAAE,IAAI,EAAE,QAAQ,EAAE,EAAE,IAAI,EAAE,EAAE;QAC3B,MAAM,GAAG,GAAG,IAAI,CAAC,IAAI,CAAC,cAAc,CAAC;QAErC,IAAI,GAAG,KAAK,IAAI,IAAI,GAAG,IAAI,qBAAqB,EAAE,CAAC;YACjD,OAAO,IAAI,CAAC;QACd,CAAC;QAED,IAAI,YAAY,CAAC,IAAI,CAAC,QAAQ,EAAE,WAAW,IAAI,EAAE,CAAC,EAAE,CAAC;YACnD,OAAO,IAAI,CAAC;QACd,CAAC;QAED,OAAO,IAAI,CACT,wCAAwC,GAAG,oBAAoB,qBAAqB,GAAG,EACvF,EAAE,QAAQ,EAAE,sBAAsB,EAAE,QAAQ,EAAE,EAAE,UAAU,EAAE,GAAG,EAAE,EAAE,CACpE,CAAC;IACJ,CAAC,CACF;CACF,CAAC"}

package/dist/core/rules/index.d.ts

@@ -3,11 +3,15 @@ import type { PageContext, Rule } from "./rule.js";
 export type { PageContext, Rule } from "./rule.js";
 /** Rules evaluated against a single HTML document. */
 export declare const PAGE_RULES: Rule[];
+/** Rules the AEO audit evaluates against each page; the SEO audit never runs them. */
+export declare const AEO_PAGE_RULES: Rule[];
 /** Metadata for every rule the tool can emit, including rules implemented outside the page-rule loop. */
 export declare const ALL_RULES: RuleMeta[];
 export interface RunRulesOptions {
     /** Rule ids to skip. */
     disable?: Set<string>;
+    /** The rules to run (default: the SEO page rules). */
+    rules?: Rule[];
 }
 export declare const sortFindings: (findings: Finding[]) => Finding[];
 export declare const runPageRules: (ctx: PageContext, options?: RunRulesOptions) => Finding[];

package/dist/core/rules/index.js

@@ -1,20 +1,26 @@
+import { AEO_SITE_RULES } from "../aeo/site-rules.js";
 import { PERFORMANCE_RULES } from "../performance-rules.js";
 import { RENDER_RULES } from "../render-rules.js";
 import { SITE_RULES } from "../site-rules.js";
+import { aeoRules } from "./aeo.js";
 import { canonicalRules } from "./canonical.js";
 import { contentRules } from "./content.js";
 import { documentRules } from "./document.js";
+import { headRules } from "./head.js";
 import { headingRules } from "./headings.js";
 import { hreflangRules } from "./hreflang.js";
 import { imageRules } from "./images.js";
 import { indexingRules } from "./indexing.js";
 import { keywordRules } from "./keyword.js";
 import { linkRules } from "./links.js";
+import { loadingRules } from "./loading.js";
 import { metaRules } from "./meta.js";
 import { responseRules } from "./response.js";
 import { socialRules } from "./social.js";
+import { structuredDataValueRules } from "./structured-data-values.js";
 import { structuredDataRules } from "./structured-data.js";
 import { titleRules } from "./title.js";
+import { urlRules } from "./urls.js";
 /** Rules evaluated against a single HTML document. */
 export const PAGE_RULES = [
     ...titleRules,
@@ -23,21 +29,29 @@ export const PAGE_RULES = [
     ...canonicalRules,
     ...indexingRules,
     ...documentRules,
+    ...headRules,
     ...socialRules,
     ...imageRules,
     ...linkRules,
+    ...urlRules,
+    ...loadingRules,
     ...hreflangRules,
     ...structuredDataRules,
+    ...structuredDataValueRules,
     ...contentRules,
     ...keywordRules,
     ...responseRules,
 ];
+/** Rules the AEO audit evaluates against each page; the SEO audit never runs them. */
+export const AEO_PAGE_RULES = aeoRules;
 /** Metadata for every rule the tool can emit, including rules implemented outside the page-rule loop. */
 export const ALL_RULES = [
     ...PAGE_RULES.map((r) => r.meta),
     ...RENDER_RULES,
     ...PERFORMANCE_RULES,
     ...SITE_RULES,
+    ...AEO_PAGE_RULES.map((r) => r.meta),
+    ...AEO_SITE_RULES,
 ];
 export const sortFindings = (findings) => {
     const rank = { error: 0, warning: 1, info: 2 };
@@ -45,7 +59,7 @@ export const sortFindings = (findings) => {
 };
 export const runPageRules = (ctx, options = {}) => {
     const findings = [];
-    for (const rule of PAGE_RULES) {
+    for (const rule of options.rules ?? PAGE_RULES) {
         if (options.disable?.has(rule.meta.id)) {
             continue;
         }

package/dist/core/rules/index.js.map

@@ -1 +1 @@
-{"version":3,"file":"index.js","sourceRoot":"","sources":["../../../src/core/rules/index.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,iBAAiB,EAAE,MAAM,yBAAyB,CAAC;AAC5D,OAAO,EAAE,YAAY,EAAE,MAAM,oBAAoB,CAAC;AAClD,OAAO,EAAE,UAAU,EAAE,MAAM,kBAAkB,CAAC;AAE9C,OAAO,EAAE,cAAc,EAAE,MAAM,gBAAgB,CAAC;AAChD,OAAO,EAAE,YAAY,EAAE,MAAM,cAAc,CAAC;AAC5C,OAAO,EAAE,aAAa,EAAE,MAAM,eAAe,CAAC;AAC9C,OAAO,EAAE,YAAY,EAAE,MAAM,eAAe,CAAC;AAC7C,OAAO,EAAE,aAAa,EAAE,MAAM,eAAe,CAAC;AAC9C,OAAO,EAAE,UAAU,EAAE,MAAM,aAAa,CAAC;AACzC,OAAO,EAAE,aAAa,EAAE,MAAM,eAAe,CAAC;AAC9C,OAAO,EAAE,YAAY,EAAE,MAAM,cAAc,CAAC;AAC5C,OAAO,EAAE,SAAS,EAAE,MAAM,YAAY,CAAC;AACvC,OAAO,EAAE,SAAS,EAAE,MAAM,WAAW,CAAC;AACtC,OAAO,EAAE,aAAa,EAAE,MAAM,eAAe,CAAC;AAE9C,OAAO,EAAE,WAAW,EAAE,MAAM,aAAa,CAAC;AAC1C,OAAO,EAAE,mBAAmB,EAAE,MAAM,sBAAsB,CAAC;AAC3D,OAAO,EAAE,UAAU,EAAE,MAAM,YAAY,CAAC;AAIxC,sDAAsD;AACtD,MAAM,CAAC,MAAM,UAAU,GAAW;IAChC,GAAG,UAAU;IACb,GAAG,SAAS;IACZ,GAAG,YAAY;IACf,GAAG,cAAc;IACjB,GAAG,aAAa;IAChB,GAAG,aAAa;IAChB,GAAG,WAAW;IACd,GAAG,UAAU;IACb,GAAG,SAAS;IACZ,GAAG,aAAa;IAChB,GAAG,mBAAmB;IACtB,GAAG,YAAY;IACf,GAAG,YAAY;IACf,GAAG,aAAa;CACjB,CAAC;AAEF,yGAAyG;AACzG,MAAM,CAAC,MAAM,SAAS,GAAe;IACnC,GAAG,UAAU,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,IAAI,CAAC;IAChC,GAAG,YAAY;IACf,GAAG,iBAAiB;IACpB,GAAG,UAAU;CACd,CAAC;AAOF,MAAM,CAAC,MAAM,YAAY,GAAG,CAAC,QAAmB,EAAa,EAAE;IAC7D,MAAM,IAAI,GAAG,EAAE,KAAK,EAAE,CAAC,EAAE,OAAO,EAAE,CAAC,EAAE,IAAI,EAAE,CAAC,EAAW,CAAC;IAExD,OAAO,QAAQ,CAAC,QAAQ,CACtB,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CACP,IAAI,CAAC,CAAC,CAAC,QAAQ,CAAC,GAAG,IAAI,CAAC,CAAC,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC,IAAI,CAAC,aAAa,CAAC,CAAC,CAAC,IAAI,CAAC,CACtE,CAAC;AACJ,CAAC,CAAC;AAEF,MAAM,CAAC,MAAM,YAAY,GAAG,CAC1B,GAAgB,EAChB,OAAO,GAAoB,EAAE,EAClB,EAAE;IACb,MAAM,QAAQ,GAAc,EAAE,CAAC;IAE/B,KAAK,MAAM,IAAI,IAAI,UAAU,EAAE,CAAC;QAC9B,IAAI,OAAO,CAAC,OAAO,EAAE,GAAG,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC,EAAE,CAAC;YACvC,SAAS;QACX,CAAC;QAED,IAAI,IAAI,CAAC,IAAI,CAAC,QAAQ,KAAK,SAAS,IAAI,CAAC,GAAG,CAAC,OAAO,EAAE,CAAC;YACrD,SAAS;QACX,CAAC;QAED,IAAI,CAAC;YACH,KAAK,MAAM,CAAC,IAAI,IAAI,CAAC,KAAK,CAAC,GAAG,CAAC,EAAE,CAAC;gBAChC,IAAI,CAAC,CAAC,CAAC,GAAG,EAAE,CAAC;oBACX,CAAC,CAAC,GAAG,GAAG,GAAG,CAAC,QAAQ,EAAE,QAAQ,IAAI,GAAG,CAAC,IAAI,CAAC,GAAG,CAAC;gBACjD,CAAC;gBAED,QAAQ,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;YACnB,CAAC;QACH,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YACf,QAAQ,CAAC,IAAI,CAAC;gBACZ,IAAI,EAAE,iBAAiB;gBACvB,QAAQ,EAAE,MAAM;gBAChB,QAAQ,EAAE,MAAM;gBAChB,OAAO,EAAE,QAAQ,IAAI,CAAC,IAAI,CAAC,EAAE,YAAY,KAAK,YAAY,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,EAAE;gBACjG,cAAc,EACZ,yHAAyH;gBAC3H,GAAG,EAAE,GAAG,CAAC,IAAI,CAAC,GAAG;aAClB,CAAC,CAAC;QACL,CAAC;IACH,CAAC;IAED,OAAO,YAAY,CAAC,QAAQ,CAAC,CAAC;AAChC,CAAC,CAAC;AAEF,MAAM,CAAC,MAAM,QAAQ,GAAG,CAAC,EAAU,EAAwB,EAAE,CAC3D,SAAS,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,EAAE,KAAK,EAAE,CAAC,CAAC"}
+{"version":3,"file":"index.js","sourceRoot":"","sources":["../../../src/core/rules/index.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,cAAc,EAAE,MAAM,sBAAsB,CAAC;AACtD,OAAO,EAAE,iBAAiB,EAAE,MAAM,yBAAyB,CAAC;AAC5D,OAAO,EAAE,YAAY,EAAE,MAAM,oBAAoB,CAAC;AAClD,OAAO,EAAE,UAAU,EAAE,MAAM,kBAAkB,CAAC;AAE9C,OAAO,EAAE,QAAQ,EAAE,MAAM,UAAU,CAAC;AACpC,OAAO,EAAE,cAAc,EAAE,MAAM,gBAAgB,CAAC;AAChD,OAAO,EAAE,YAAY,EAAE,MAAM,cAAc,CAAC;AAC5C,OAAO,EAAE,aAAa,EAAE,MAAM,eAAe,CAAC;AAC9C,OAAO,EAAE,SAAS,EAAE,MAAM,WAAW,CAAC;AACtC,OAAO,EAAE,YAAY,EAAE,MAAM,eAAe,CAAC;AAC7C,OAAO,EAAE,aAAa,EAAE,MAAM,eAAe,CAAC;AAC9C,OAAO,EAAE,UAAU,EAAE,MAAM,aAAa,CAAC;AACzC,OAAO,EAAE,aAAa,EAAE,MAAM,eAAe,CAAC;AAC9C,OAAO,EAAE,YAAY,EAAE,MAAM,cAAc,CAAC;AAC5C,OAAO,EAAE,SAAS,EAAE,MAAM,YAAY,CAAC;AACvC,OAAO,EAAE,YAAY,EAAE,MAAM,cAAc,CAAC;AAC5C,OAAO,EAAE,SAAS,EAAE,MAAM,WAAW,CAAC;AACtC,OAAO,EAAE,aAAa,EAAE,MAAM,eAAe,CAAC;AAE9C,OAAO,EAAE,WAAW,EAAE,MAAM,aAAa,CAAC;AAC1C,OAAO,EAAE,wBAAwB,EAAE,MAAM,6BAA6B,CAAC;AACvE,OAAO,EAAE,mBAAmB,EAAE,MAAM,sBAAsB,CAAC;AAC3D,OAAO,EAAE,UAAU,EAAE,MAAM,YAAY,CAAC;AACxC,OAAO,EAAE,QAAQ,EAAE,MAAM,WAAW,CAAC;AAIrC,sDAAsD;AACtD,MAAM,CAAC,MAAM,UAAU,GAAW;IAChC,GAAG,UAAU;IACb,GAAG,SAAS;IACZ,GAAG,YAAY;IACf,GAAG,cAAc;IACjB,GAAG,aAAa;IAChB,GAAG,aAAa;IAChB,GAAG,SAAS;IACZ,GAAG,WAAW;IACd,GAAG,UAAU;IACb,GAAG,SAAS;IACZ,GAAG,QAAQ;IACX,GAAG,YAAY;IACf,GAAG,aAAa;IAChB,GAAG,mBAAmB;IACtB,GAAG,wBAAwB;IAC3B,GAAG,YAAY;IACf,GAAG,YAAY;IACf,GAAG,aAAa;CACjB,CAAC;AAEF,sFAAsF;AACtF,MAAM,CAAC,MAAM,cAAc,GAAW,QAAQ,CAAC;AAE/C,yGAAyG;AACzG,MAAM,CAAC,MAAM,SAAS,GAAe;IACnC,GAAG,UAAU,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,IAAI,CAAC;IAChC,GAAG,YAAY;IACf,GAAG,iBAAiB;IACpB,GAAG,UAAU;IACb,GAAG,cAAc,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,IAAI,CAAC;IACpC,GAAG,cAAc;CAClB,CAAC;AASF,MAAM,CAAC,MAAM,YAAY,GAAG,CAAC,QAAmB,EAAa,EAAE;IAC7D,MAAM,IAAI,GAAG,EAAE,KAAK,EAAE,CAAC,EAAE,OAAO,EAAE,CAAC,EAAE,IAAI,EAAE,CAAC,EAAW,CAAC;IAExD,OAAO,QAAQ,CAAC,QAAQ,CACtB,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CACP,IAAI,CAAC,CAAC,CAAC,QAAQ,CAAC,GAAG,IAAI,CAAC,CAAC,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC,IAAI,CAAC,aAAa,CAAC,CAAC,CAAC,IAAI,CAAC,CACtE,CAAC;AACJ,CAAC,CAAC;AAEF,MAAM,CAAC,MAAM,YAAY,GAAG,CAC1B,GAAgB,EAChB,OAAO,GAAoB,EAAE,EAClB,EAAE;IACb,MAAM,QAAQ,GAAc,EAAE,CAAC;IAE/B,KAAK,MAAM,IAAI,IAAI,OAAO,CAAC,KAAK,IAAI,UAAU,EAAE,CAAC;QAC/C,IAAI,OAAO,CAAC,OAAO,EAAE,GAAG,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC,EAAE,CAAC;YACvC,SAAS;QACX,CAAC;QAED,IAAI,IAAI,CAAC,IAAI,CAAC,QAAQ,KAAK,SAAS,IAAI,CAAC,GAAG,CAAC,OAAO,EAAE,CAAC;YACrD,SAAS;QACX,CAAC;QAED,IAAI,CAAC;YACH,KAAK,MAAM,CAAC,IAAI,IAAI,CAAC,KAAK,CAAC,GAAG,CAAC,EAAE,CAAC;gBAChC,IAAI,CAAC,CAAC,CAAC,GAAG,EAAE,CAAC;oBACX,CAAC,CAAC,GAAG,GAAG,GAAG,CAAC,QAAQ,EAAE,QAAQ,IAAI,GAAG,CAAC,IAAI,CAAC,GAAG,CAAC;gBACjD,CAAC;gBAED,QAAQ,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;YACnB,CAAC;QACH,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YACf,QAAQ,CAAC,IAAI,CAAC;gBACZ,IAAI,EAAE,iBAAiB;gBACvB,QAAQ,EAAE,MAAM;gBAChB,QAAQ,EAAE,MAAM;gBAChB,OAAO,EAAE,QAAQ,IAAI,CAAC,IAAI,CAAC,EAAE,YAAY,KAAK,YAAY,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,EAAE;gBACjG,cAAc,EACZ,yHAAyH;gBAC3H,GAAG,EAAE,GAAG,CAAC,IAAI,CAAC,GAAG;aAClB,CAAC,CAAC;QACL,CAAC;IACH,CAAC;IAED,OAAO,YAAY,CAAC,QAAQ,CAAC,CAAC;AAChC,CAAC,CAAC;AAEF,MAAM,CAAC,MAAM,QAAQ,GAAG,CAAC,EAAU,EAAwB,EAAE,CAC3D,SAAS,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,EAAE,KAAK,EAAE,CAAC,CAAC"}

package/dist/core/rules/indexing.d.ts

@@ -1,4 +1,14 @@
 import type { ExtractedPage, ResponseInfo } from "../types.js";
+export interface ScopedDirective {
+    /** The user agent the directive is for, or null when it is for every crawler. */
+    agent: string | null;
+    directive: string;
+}
+/**
+ * X-Robots-Tag values. "googlebot: nosnippet, noarchive" scopes every directive after the prefix
+ * to googlebot, up to the next prefix.
+ */
+export declare const parseRobotsHeader: (value: string) => ScopedDirective[];
 export interface RobotsDirectives {
     noindex: boolean;
     nofollow: boolean;

package/dist/core/rules/indexing.js

@@ -1,4 +1,108 @@
-import { defineRule, GOOGLE_DOCS } from "./rule.js";
+import { cap, defineRule, GOOGLE_DOCS } from "./rule.js";
+/** Directives that carry a value after a colon, which is not a user agent prefix. */
+const VALUE_DIRECTIVES = new Set([
+    "max-snippet",
+    "max-image-preview",
+    "max-video-preview",
+    "unavailable_after",
+]);
+/**
+ * X-Robots-Tag values. "googlebot: nosnippet, noarchive" scopes every directive after the prefix
+ * to googlebot, up to the next prefix.
+ */
+export const parseRobotsHeader = (value) => {
+    const out = [];
+    let agent = null;
+    let scoped = new Set();
+    for (const piece of value.toLowerCase().split(",")) {
+        let directive = piece.trim();
+        const match = /^(?<name>[a-z0-9_-]+)\s*:\s*(?<rest>.*)$/u.exec(directive);
+        const name = match?.groups?.name;
+        if (name && !VALUE_DIRECTIVES.has(name)) {
+            agent = name;
+            scoped = new Set();
+            directive = match.groups?.rest?.trim() ?? "";
+        }
+        directive = directive.replaceAll(/\s+/gu, "");
+        /*
+         * Two X-Robots-Tag headers arrive joined with ", ", so "GPTBot: noindex" and a plain "noindex"
+         * read as "gptbot: noindex, noindex". A directive that repeats under one agent cannot belong to
+         * it twice: it starts a header for every crawler.
+         */
+        if (agent !== null && scoped.has(directive)) {
+            agent = null;
+        }
+        if (directive) {
+            scoped.add(directive);
+            out.push({ agent, directive });
+        }
+    }
+    return out;
+};
+/** Robots directives Google or Bing document, which take no value. */
+const KNOWN_DIRECTIVES = new Set([
+    "all",
+    "index",
+    "follow",
+    "noindex",
+    "nofollow",
+    "none",
+    "noarchive",
+    "nocache",
+    "nosnippet",
+    "notranslate",
+    "noimageindex",
+    "indexifembedded",
+    "nositelinkssearchbox",
+]);
+/** Directives Google applies: meta robots and googlebot, and X-Robots-Tag for every crawler or Googlebot. */
+const googleDirectives = (page, response) => {
+    const out = [];
+    for (const meta of page.answer.robotsMeta) {
+        if (meta.name === "robots" || meta.name === "googlebot") {
+            for (const d of meta.content.split(",")) {
+                const directive = d.trim();
+                if (directive) {
+                    out.push({ source: `<meta name="${meta.name}">`, directive });
+                }
+            }
+        }
+    }
+    const header = response?.headers["x-robots-tag"];
+    if (header) {
+        for (const d of parseRobotsHeader(header)) {
+            if (d.agent === null || d.agent === "googlebot") {
+                out.push({ source: "X-Robots-Tag", directive: d.directive });
+            }
+        }
+    }
+    return out;
+};
+/**
+ * How a directive Google would not read was meant: "no-index" was meant as noindex, and
+ * "noindex nofollow" as two directives. Null for directives Google reads, and for names it does not
+ * document, which other crawlers may read.
+ */
+const misreadDirective = (directive) => {
+    if (KNOWN_DIRECTIVES.has(directive) ||
+        VALUE_DIRECTIVES.has(directive.split(":")[0]?.trim() ?? "")) {
+        return null;
+    }
+    const squashed = directive.replaceAll(/[\s_-]+/gu, "");
+    if (KNOWN_DIRECTIVES.has(squashed)) {
+        return { meant: [squashed], kind: "misspelled" };
+    }
+    const parts = directive.split(/[\s;]+/u).filter(Boolean);
+    return parts.length > 1 && parts.every((p) => KNOWN_DIRECTIVES.has(p))
+        ? { meant: parts, kind: "not-comma-separated" }
+        : null;
+};
+/** User agents whose robots directives count for search: the same ones the meta tags are read for. */
+const SEARCH_ENGINE_AGENTS = new Set([
+    "googlebot",
+    "googlebot-news",
+    "bingbot",
+]);
 /** Combine <meta name="robots"> / googlebot and the X-Robots-Tag header. */
 export const robotsDirectives = (page, response) => {
     const directives = [];
@@ -14,14 +118,12 @@ export const robotsDirectives = (page, response) => {
     }
     const header = response?.headers["x-robots-tag"];
     if (header) {
-        for (const d of header
-            .toLowerCase()
-            .split(",")
-            .map((s) => s.trim())
-            .filter(Boolean)) {
-            // "googlebot: noindex" form
-            directives.push(d.includes(":") ? (d.split(":").pop() ?? d).trim() : d);
-            sources.push("header");
+        // "gptbot: noindex" keeps one AI crawler out; it says nothing about search engines.
+        for (const d of parseRobotsHeader(header)) {
+            if (d.agent === null || SEARCH_ENGINE_AGENTS.has(d.agent)) {
+                directives.push(d.directive);
+                sources.push("header");
+            }
         }
     }
     const noindex = directives.some((d) => d === "noindex" || d === "none");
@@ -71,5 +173,65 @@ export const indexingRules = [
             })
             : null;
     }),
+    defineRule({
+        id: "robots.conflicting",
+        category: "indexing",
+        severity: "info",
+        description: "The page's robots directives contradict each other (index and noindex, or follow and nofollow); Google applies the more restrictive one.",
+        recommendation: "Keep one directive for indexing and one for following, in one place. A platform or CDN often adds X-Robots-Tag on top of the page's own meta robots; remove the one you did not mean.",
+        docs: GOOGLE_DOCS.robotsMeta,
+    }, ({ page, response }, make) => {
+        const directives = googleDirectives(page, response);
+        const where = (names) => [
+            ...new Set(directives
+                .filter((d) => names.includes(d.directive.toLowerCase()))
+                .map((d) => `${d.directive.toLowerCase()} (${d.source})`)),
+        ];
+        const pairs = [
+            { allow: ["index", "all"], deny: ["noindex", "none"], wins: "noindex" },
+            {
+                allow: ["follow", "all"],
+                deny: ["nofollow", "none"],
+                wins: "nofollow",
+            },
+        ];
+        return pairs.flatMap(({ allow, deny, wins }) => {
+            const allowed = where(allow);
+            const denied = where(deny);
+            return allowed.length > 0 && denied.length > 0
+                ? [
+                    make(`The page says ${allowed.join(" and ")} but also ${denied.join(" and ")}; Google applies ${wins}.`, { evidence: { allow: allowed, deny: denied, applied: wins } }),
+                ]
+                : [];
+        });
+    }),
+    defineRule({
+        id: "robots.malformed-directive",
+        category: "indexing",
+        severity: "warning",
+        description: 'A robots directive is written in a form Google does not document, such as "no-index" for noindex (warning) or "noindex nofollow" without a comma (info).',
+        recommendation: 'Write each directive the way Google documents it, separated by commas: content="noindex, nofollow". A misspelled noindex is ignored, so the page stays indexable.',
+        docs: GOOGLE_DOCS.robotsMeta,
+    }, ({ page, response }, make) => {
+        const misread = googleDirectives(page, response).flatMap((d) => {
+            const how = misreadDirective(d.directive.toLowerCase());
+            return how ? [{ ...d, ...how }] : [];
+        });
+        if (misread.length === 0) {
+            return null;
+        }
+        const misspelled = misread.some((m) => m.kind === "misspelled");
+        const listed = misread.map((m) => `"${m.directive}" (${m.source}, meant as ${m.meant.join(", ")})`);
+        return make(`${misread.length === 1 ? "A robots directive is" : `${misread.length} robots directives are`} not written the way Google documents: ${cap(listed, 5).join("; ")}.`, {
+            severity: misspelled ? "warning" : "info",
+            evidence: {
+                directives: cap(misread.map((m) => ({
+                    written: m.directive,
+                    source: m.source,
+                    meant: m.meant,
+                }))),
+            },
+        });
+    }),
 ];
 //# sourceMappingURL=indexing.js.map

package/dist/core/rules/indexing.js.map

@@ -1 +1 @@
-{"version":3,"file":"indexing.js","sourceRoot":"","sources":["../../../src/core/rules/indexing.ts"],"names":[],"mappings":"AACA,OAAO,EAAE,UAAU,EAAE,WAAW,EAAE,MAAM,WAAW,CAAC;AASpD,4EAA4E;AAC5E,MAAM,CAAC,MAAM,gBAAgB,GAAG,CAC9B,IAAmB,EACnB,QAAuB,EACL,EAAE;IACpB,MAAM,UAAU,GAAa,EAAE,CAAC;IAChC,MAAM,OAAO,GAAa,EAAE,CAAC;IAE7B,KAAK,MAAM,OAAO,IAAI,IAAI,CAAC,UAAU,EAAE,CAAC;QACtC,KAAK,MAAM,CAAC,IAAI,OAAO;aACpB,KAAK,CAAC,GAAG,CAAC;aACV,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC;aACpB,MAAM,CAAC,OAAO,CAAC,EAAE,CAAC;YACnB,UAAU,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;YACnB,OAAO,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC;QACvB,CAAC;IACH,CAAC;IAED,MAAM,MAAM,GAAG,QAAQ,EAAE,OAAO,CAAC,cAAc,CAAC,CAAC;IAEjD,IAAI,MAAM,EAAE,CAAC;QACX,KAAK,MAAM,CAAC,IAAI,MAAM;aACnB,WAAW,EAAE;aACb,KAAK,CAAC,GAAG,CAAC;aACV,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC;aACpB,MAAM,CAAC,OAAO,CAAC,EAAE,CAAC;YACnB,4BAA4B;YAC5B,UAAU,CAAC,IAAI,CAAC,CAAC,CAAC,QAAQ,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,GAAG,EAAE,IAAI,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC;YACxE,OAAO,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC;QACzB,CAAC;IACH,CAAC;IAED,MAAM,OAAO,GAAG,UAAU,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,KAAK,SAAS,IAAI,CAAC,KAAK,MAAM,CAAC,CAAC;IACxE,MAAM,QAAQ,GAAG,UAAU,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,KAAK,UAAU,IAAI,CAAC,KAAK,MAAM,CAAC,CAAC;IAE1E,OAAO;QACL,OAAO;QACP,QAAQ;QACR,OAAO,EAAE,CAAC,GAAG,IAAI,GAAG,CAAC,OAAO,CAAC,CAAC;QAC9B,UAAU,EAAE,CAAC,GAAG,IAAI,GAAG,CAAC,UAAU,CAAC,CAAC;KACrC,CAAC;AACJ,CAAC,CAAC;AAEF,MAAM,CAAC,MAAM,aAAa,GAAG;IAC3B,UAAU,CACR;QACE,EAAE,EAAE,gBAAgB;QACpB,QAAQ,EAAE,UAAU;QACpB,QAAQ,EAAE,SAAS;QACnB,WAAW,EACT,8EAA8E;QAChF,cAAc,EACZ,2QAA2Q;QAC7Q,IAAI,EAAE,WAAW,CAAC,UAAU;KAC7B,EACD,CAAC,EAAE,IAAI,EAAE,QAAQ,EAAE,EAAE,IAAI,EAAE,EAAE;QAC3B,MAAM,CAAC,GAAG,gBAAgB,CAAC,IAAI,EAAE,QAAQ,CAAC,CAAC;QAE3C,OAAO,CAAC,CAAC,OAAO;YACd,CAAC,CAAC,IAAI,CAAC,8BAA8B,CAAC,CAAC,OAAO,CAAC,IAAI,CAAC,OAAO,CAAC,GAAG,EAAE;gBAC7D,QAAQ,EAAE,CAAC,CAAC,OAAO,CAAC,QAAQ,CAAC,MAAM,CAAC;oBAClC,CAAC,CAAC,4BAA4B;oBAC9B,CAAC,CAAC,SAAS;gBACb,QAAQ,EAAE;oBACR,UAAU,EAAE,CAAC,CAAC,UAAU;oBACxB,OAAO,EAAE,CAAC,CAAC,OAAO;oBAClB,UAAU,EAAE,QAAQ,EAAE,OAAO,CAAC,cAAc,CAAC,IAAI,IAAI;iBACtD;aACF,CAAC;YACJ,CAAC,CAAC,IAAI,CAAC;IACX,CAAC,CACF;IACD,UAAU,CACR;QACE,EAAE,EAAE,iBAAiB;QACrB,QAAQ,EAAE,UAAU;QACpB,QAAQ,EAAE,MAAM;QAChB,WAAW,EAAE,wDAAwD;QACrE,cAAc,EACZ,2HAA2H;QAC7H,IAAI,EAAE,WAAW,CAAC,UAAU;KAC7B,EACD,CAAC,EAAE,IAAI,EAAE,QAAQ,EAAE,EAAE,IAAI,EAAE,EAAE;QAC3B,MAAM,CAAC,GAAG,gBAAgB,CAAC,IAAI,EAAE,QAAQ,CAAC,CAAC;QAE3C,OAAO,CAAC,CAAC,QAAQ;YACf,CAAC,CAAC,IAAI,CAAC,kCAAkC,CAAC,CAAC,OAAO,CAAC,IAAI,CAAC,OAAO,CAAC,GAAG,EAAE;gBACjE,QAAQ,EAAE,EAAE,UAAU,EAAE,CAAC,CAAC,UAAU,EAAE;aACvC,CAAC;YACJ,CAAC,CAAC,IAAI,CAAC;IACX,CAAC,CACF;CACF,CAAC"}
+{"version":3,"file":"indexing.js","sourceRoot":"","sources":["../../../src/core/rules/indexing.ts"],"names":[],"mappings":"AACA,OAAO,EAAE,GAAG,EAAE,UAAU,EAAE,WAAW,EAAE,MAAM,WAAW,CAAC;AAEzD,qFAAqF;AACrF,MAAM,gBAAgB,GAAG,IAAI,GAAG,CAAC;IAC/B,aAAa;IACb,mBAAmB;IACnB,mBAAmB;IACnB,mBAAmB;CACpB,CAAC,CAAC;AAQH;;;GAGG;AACH,MAAM,CAAC,MAAM,iBAAiB,GAAG,CAAC,KAAa,EAAqB,EAAE;IACpE,MAAM,GAAG,GAAsB,EAAE,CAAC;IAClC,IAAI,KAAK,GAAkB,IAAI,CAAC;IAChC,IAAI,MAAM,GAAG,IAAI,GAAG,EAAU,CAAC;IAE/B,KAAK,MAAM,KAAK,IAAI,KAAK,CAAC,WAAW,EAAE,CAAC,KAAK,CAAC,GAAG,CAAC,EAAE,CAAC;QACnD,IAAI,SAAS,GAAG,KAAK,CAAC,IAAI,EAAE,CAAC;QAC7B,MAAM,KAAK,GAAG,2CAA2C,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC;QAC1E,MAAM,IAAI,GAAG,KAAK,EAAE,MAAM,EAAE,IAAI,CAAC;QAEjC,IAAI,IAAI,IAAI,CAAC,gBAAgB,CAAC,GAAG,CAAC,IAAI,CAAC,EAAE,CAAC;YACxC,KAAK,GAAG,IAAI,CAAC;YACb,MAAM,GAAG,IAAI,GAAG,EAAE,CAAC;YACnB,SAAS,GAAG,KAAK,CAAC,MAAM,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,CAAC;QAC/C,CAAC;QAED,SAAS,GAAG,SAAS,CAAC,UAAU,CAAC,OAAO,EAAE,EAAE,CAAC,CAAC;QAE9C;;;;WAIG;QACH,IAAI,KAAK,KAAK,IAAI,IAAI,MAAM,CAAC,GAAG,CAAC,SAAS,CAAC,EAAE,CAAC;YAC5C,KAAK,GAAG,IAAI,CAAC;QACf,CAAC;QAED,IAAI,SAAS,EAAE,CAAC;YACd,MAAM,CAAC,GAAG,CAAC,SAAS,CAAC,CAAC;YACtB,GAAG,CAAC,IAAI,CAAC,EAAE,KAAK,EAAE,SAAS,EAAE,CAAC,CAAC;QACjC,CAAC;IACH,CAAC;IAED,OAAO,GAAG,CAAC;AACb,CAAC,CAAC;AAEF,sEAAsE;AACtE,MAAM,gBAAgB,GAAG,IAAI,GAAG,CAAC;IAC/B,KAAK;IACL,OAAO;IACP,QAAQ;IACR,SAAS;IACT,UAAU;IACV,MAAM;IACN,WAAW;IACX,SAAS;IACT,WAAW;IACX,aAAa;IACb,cAAc;IACd,iBAAiB;IACjB,sBAAsB;CACvB,CAAC,CAAC;AAQH,6GAA6G;AAC7G,MAAM,gBAAgB,GAAG,CACvB,IAAmB,EACnB,QAAuB,EACH,EAAE;IACtB,MAAM,GAAG,GAAuB,EAAE,CAAC;IAEnC,KAAK,MAAM,IAAI,IAAI,IAAI,CAAC,MAAM,CAAC,UAAU,EAAE,CAAC;QAC1C,IAAI,IAAI,CAAC,IAAI,KAAK,QAAQ,IAAI,IAAI,CAAC,IAAI,KAAK,WAAW,EAAE,CAAC;YACxD,KAAK,MAAM,CAAC,IAAI,IAAI,CAAC,OAAO,CAAC,KAAK,CAAC,GAAG,CAAC,EAAE,CAAC;gBACxC,MAAM,SAAS,GAAG,CAAC,CAAC,IAAI,EAAE,CAAC;gBAE3B,IAAI,SAAS,EAAE,CAAC;oBACd,GAAG,CAAC,IAAI,CAAC,EAAE,MAAM,EAAE,eAAe,IAAI,CAAC,IAAI,IAAI,EAAE,SAAS,EAAE,CAAC,CAAC;gBAChE,CAAC;YACH,CAAC;QACH,CAAC;IACH,CAAC;IAED,MAAM,MAAM,GAAG,QAAQ,EAAE,OAAO,CAAC,cAAc,CAAC,CAAC;IAEjD,IAAI,MAAM,EAAE,CAAC;QACX,KAAK,MAAM,CAAC,IAAI,iBAAiB,CAAC,MAAM,CAAC,EAAE,CAAC;YAC1C,IAAI,CAAC,CAAC,KAAK,KAAK,IAAI,IAAI,CAAC,CAAC,KAAK,KAAK,WAAW,EAAE,CAAC;gBAChD,GAAG,CAAC,IAAI,CAAC,EAAE,MAAM,EAAE,cAAc,EAAE,SAAS,EAAE,CAAC,CAAC,SAAS,EAAE,CAAC,CAAC;YAC/D,CAAC;QACH,CAAC;IACH,CAAC;IAED,OAAO,GAAG,CAAC;AACb,CAAC,CAAC;AAEF;;;;GAIG;AACH,MAAM,gBAAgB,GAAG,CACvB,SAAiB,EACuD,EAAE;IAC1E,IACE,gBAAgB,CAAC,GAAG,CAAC,SAAS,CAAC;QAC/B,gBAAgB,CAAC,GAAG,CAAC,SAAS,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,EAAE,IAAI,EAAE,IAAI,EAAE,CAAC,EAC3D,CAAC;QACD,OAAO,IAAI,CAAC;IACd,CAAC;IAED,MAAM,QAAQ,GAAG,SAAS,CAAC,UAAU,CAAC,WAAW,EAAE,EAAE,CAAC,CAAC;IAEvD,IAAI,gBAAgB,CAAC,GAAG,CAAC,QAAQ,CAAC,EAAE,CAAC;QACnC,OAAO,EAAE,KAAK,EAAE,CAAC,QAAQ,CAAC,EAAE,IAAI,EAAE,YAAY,EAAE,CAAC;IACnD,CAAC;IAED,MAAM,KAAK,GAAG,SAAS,CAAC,KAAK,CAAC,SAAS,CAAC,CAAC,MAAM,CAAC,OAAO,CAAC,CAAC;IAEzD,OAAO,KAAK,CAAC,MAAM,GAAG,CAAC,IAAI,KAAK,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,gBAAgB,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC;QACpE,CAAC,CAAC,EAAE,KAAK,EAAE,KAAK,EAAE,IAAI,EAAE,qBAAqB,EAAE;QAC/C,CAAC,CAAC,IAAI,CAAC;AACX,CAAC,CAAC;AASF,sGAAsG;AACtG,MAAM,oBAAoB,GAAG,IAAI,GAAG,CAAC;IACnC,WAAW;IACX,gBAAgB;IAChB,SAAS;CACV,CAAC,CAAC;AAEH,4EAA4E;AAC5E,MAAM,CAAC,MAAM,gBAAgB,GAAG,CAC9B,IAAmB,EACnB,QAAuB,EACL,EAAE;IACpB,MAAM,UAAU,GAAa,EAAE,CAAC;IAChC,MAAM,OAAO,GAAa,EAAE,CAAC;IAE7B,KAAK,MAAM,OAAO,IAAI,IAAI,CAAC,UAAU,EAAE,CAAC;QACtC,KAAK,MAAM,CAAC,IAAI,OAAO;aACpB,KAAK,CAAC,GAAG,CAAC;aACV,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC;aACpB,MAAM,CAAC,OAAO,CAAC,EAAE,CAAC;YACnB,UAAU,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;YACnB,OAAO,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC;QACvB,CAAC;IACH,CAAC;IAED,MAAM,MAAM,GAAG,QAAQ,EAAE,OAAO,CAAC,cAAc,CAAC,CAAC;IAEjD,IAAI,MAAM,EAAE,CAAC;QACX,oFAAoF;QACpF,KAAK,MAAM,CAAC,IAAI,iBAAiB,CAAC,MAAM,CAAC,EAAE,CAAC;YAC1C,IAAI,CAAC,CAAC,KAAK,KAAK,IAAI,IAAI,oBAAoB,CAAC,GAAG,CAAC,CAAC,CAAC,KAAK,CAAC,EAAE,CAAC;gBAC1D,UAAU,CAAC,IAAI,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC;gBAC7B,OAAO,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC;YACzB,CAAC;QACH,CAAC;IACH,CAAC;IAED,MAAM,OAAO,GAAG,UAAU,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,KAAK,SAAS,IAAI,CAAC,KAAK,MAAM,CAAC,CAAC;IACxE,MAAM,QAAQ,GAAG,UAAU,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,KAAK,UAAU,IAAI,CAAC,KAAK,MAAM,CAAC,CAAC;IAE1E,OAAO;QACL,OAAO;QACP,QAAQ;QACR,OAAO,EAAE,CAAC,GAAG,IAAI,GAAG,CAAC,OAAO,CAAC,CAAC;QAC9B,UAAU,EAAE,CAAC,GAAG,IAAI,GAAG,CAAC,UAAU,CAAC,CAAC;KACrC,CAAC;AACJ,CAAC,CAAC;AAEF,MAAM,CAAC,MAAM,aAAa,GAAG;IAC3B,UAAU,CACR;QACE,EAAE,EAAE,gBAAgB;QACpB,QAAQ,EAAE,UAAU;QACpB,QAAQ,EAAE,SAAS;QACnB,WAAW,EACT,8EAA8E;QAChF,cAAc,EACZ,2QAA2Q;QAC7Q,IAAI,EAAE,WAAW,CAAC,UAAU;KAC7B,EACD,CAAC,EAAE,IAAI,EAAE,QAAQ,EAAE,EAAE,IAAI,EAAE,EAAE;QAC3B,MAAM,CAAC,GAAG,gBAAgB,CAAC,IAAI,EAAE,QAAQ,CAAC,CAAC;QAE3C,OAAO,CAAC,CAAC,OAAO;YACd,CAAC,CAAC,IAAI,CAAC,8BAA8B,CAAC,CAAC,OAAO,CAAC,IAAI,CAAC,OAAO,CAAC,GAAG,EAAE;gBAC7D,QAAQ,EAAE,CAAC,CAAC,OAAO,CAAC,QAAQ,CAAC,MAAM,CAAC;oBAClC,CAAC,CAAC,4BAA4B;oBAC9B,CAAC,CAAC,SAAS;gBACb,QAAQ,EAAE;oBACR,UAAU,EAAE,CAAC,CAAC,UAAU;oBACxB,OAAO,EAAE,CAAC,CAAC,OAAO;oBAClB,UAAU,EAAE,QAAQ,EAAE,OAAO,CAAC,cAAc,CAAC,IAAI,IAAI;iBACtD;aACF,CAAC;YACJ,CAAC,CAAC,IAAI,CAAC;IACX,CAAC,CACF;IACD,UAAU,CACR;QACE,EAAE,EAAE,iBAAiB;QACrB,QAAQ,EAAE,UAAU;QACpB,QAAQ,EAAE,MAAM;QAChB,WAAW,EAAE,wDAAwD;QACrE,cAAc,EACZ,2HAA2H;QAC7H,IAAI,EAAE,WAAW,CAAC,UAAU;KAC7B,EACD,CAAC,EAAE,IAAI,EAAE,QAAQ,EAAE,EAAE,IAAI,EAAE,EAAE;QAC3B,MAAM,CAAC,GAAG,gBAAgB,CAAC,IAAI,EAAE,QAAQ,CAAC,CAAC;QAE3C,OAAO,CAAC,CAAC,QAAQ;YACf,CAAC,CAAC,IAAI,CAAC,kCAAkC,CAAC,CAAC,OAAO,CAAC,IAAI,CAAC,OAAO,CAAC,GAAG,EAAE;gBACjE,QAAQ,EAAE,EAAE,UAAU,EAAE,CAAC,CAAC,UAAU,EAAE;aACvC,CAAC;YACJ,CAAC,CAAC,IAAI,CAAC;IACX,CAAC,CACF;IACD,UAAU,CACR;QACE,EAAE,EAAE,oBAAoB;QACxB,QAAQ,EAAE,UAAU;QACpB,QAAQ,EAAE,MAAM;QAChB,WAAW,EACT,0IAA0I;QAC5I,cAAc,EACZ,uLAAuL;QACzL,IAAI,EAAE,WAAW,CAAC,UAAU;KAC7B,EACD,CAAC,EAAE,IAAI,EAAE,QAAQ,EAAE,EAAE,IAAI,EAAE,EAAE;QAC3B,MAAM,UAAU,GAAG,gBAAgB,CAAC,IAAI,EAAE,QAAQ,CAAC,CAAC;QAEpD,MAAM,KAAK,GAAG,CAAC,KAAe,EAAY,EAAE,CAAC;YAC3C,GAAG,IAAI,GAAG,CACR,UAAU;iBACP,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,KAAK,CAAC,QAAQ,CAAC,CAAC,CAAC,SAAS,CAAC,WAAW,EAAE,CAAC,CAAC;iBACxD,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,GAAG,CAAC,CAAC,SAAS,CAAC,WAAW,EAAE,KAAK,CAAC,CAAC,MAAM,GAAG,CAAC,CAC5D;SACF,CAAC;QAEF,MAAM,KAAK,GAAG;YACZ,EAAE,KAAK,EAAE,CAAC,OAAO,EAAE,KAAK,CAAC,EAAE,IAAI,EAAE,CAAC,SAAS,EAAE,MAAM,CAAC,EAAE,IAAI,EAAE,SAAS,EAAE;YACvE;gBACE,KAAK,EAAE,CAAC,QAAQ,EAAE,KAAK,CAAC;gBACxB,IAAI,EAAE,CAAC,UAAU,EAAE,MAAM,CAAC;gBAC1B,IAAI,EAAE,UAAU;aACjB;SACF,CAAC;QAEF,OAAO,KAAK,CAAC,OAAO,CAAC,CAAC,EAAE,KAAK,EAAE,IAAI,EAAE,IAAI,EAAE,EAAE,EAAE;YAC7C,MAAM,OAAO,GAAG,KAAK,CAAC,KAAK,CAAC,CAAC;YAC7B,MAAM,MAAM,GAAG,KAAK,CAAC,IAAI,CAAC,CAAC;YAE3B,OAAO,OAAO,CAAC,MAAM,GAAG,CAAC,IAAI,MAAM,CAAC,MAAM,GAAG,CAAC;gBAC5C,CAAC,CAAC;oBACE,IAAI,CACF,iBAAiB,OAAO,CAAC,IAAI,CAAC,OAAO,CAAC,aAAa,MAAM,CAAC,IAAI,CAAC,OAAO,CAAC,oBAAoB,IAAI,GAAG,EAClG,EAAE,QAAQ,EAAE,EAAE,KAAK,EAAE,OAAO,EAAE,IAAI,EAAE,MAAM,EAAE,OAAO,EAAE,IAAI,EAAE,EAAE,CAC9D;iBACF;gBACH,CAAC,CAAC,EAAE,CAAC;QACT,CAAC,CAAC,CAAC;IACL,CAAC,CACF;IACD,UAAU,CACR;QACE,EAAE,EAAE,4BAA4B;QAChC,QAAQ,EAAE,UAAU;QACpB,QAAQ,EAAE,SAAS;QACnB,WAAW,EACT,0JAA0J;QAC5J,cAAc,EACZ,mKAAmK;QACrK,IAAI,EAAE,WAAW,CAAC,UAAU;KAC7B,EACD,CAAC,EAAE,IAAI,EAAE,QAAQ,EAAE,EAAE,IAAI,EAAE,EAAE;QAC3B,MAAM,OAAO,GAAG,gBAAgB,CAAC,IAAI,EAAE,QAAQ,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,EAAE,EAAE;YAC7D,MAAM,GAAG,GAAG,gBAAgB,CAAC,CAAC,CAAC,SAAS,CAAC,WAAW,EAAE,CAAC,CAAC;YAExD,OAAO,GAAG,CAAC,CAAC,CAAC,CAAC,EAAE,GAAG,CAAC,EAAE,GAAG,GAAG,EAAE,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC;QACvC,CAAC,CAAC,CAAC;QAEH,IAAI,OAAO,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;YACzB,OAAO,IAAI,CAAC;QACd,CAAC;QAED,MAAM,UAAU,GAAG,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,IAAI,KAAK,YAAY,CAAC,CAAC;QAEhE,MAAM,MAAM,GAAG,OAAO,CAAC,GAAG,CACxB,CAAC,CAAC,EAAE,EAAE,CAAC,IAAI,CAAC,CAAC,SAAS,MAAM,CAAC,CAAC,MAAM,cAAc,CAAC,CAAC,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,GAAG,CACxE,CAAC;QAEF,OAAO,IAAI,CACT,GAAG,OAAO,CAAC,MAAM,KAAK,CAAC,CAAC,CAAC,CAAC,uBAAuB,CAAC,CAAC,CAAC,GAAG,OAAO,CAAC,MAAM,wBAAwB,0CAA0C,GAAG,CAAC,MAAM,EAAE,CAAC,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,GAAG,EACnK;YACE,QAAQ,EAAE,UAAU,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,MAAM;YACzC,QAAQ,EAAE;gBACR,UAAU,EAAE,GAAG,CACb,OAAO,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC;oBAClB,OAAO,EAAE,CAAC,CAAC,SAAS;oBACpB,MAAM,EAAE,CAAC,CAAC,MAAM;oBAChB,KAAK,EAAE,CAAC,CAAC,KAAK;iBACf,CAAC,CAAC,CACJ;aACF;SACF,CACF,CAAC;IACJ,CAAC,CACF;CACF,CAAC"}

package/dist/core/rules/loading.d.ts

@@ -0,0 +1 @@
+export declare const loadingRules: import("./rule.js").Rule[];

package/dist/core/rules/loading.js

@@ -0,0 +1,138 @@
+import { isHomePage } from "../aeo/page.js";
+import { isLocalHost } from "./canonical.js";
+import { cap, defineRule } from "./rule.js";
+/** Below this size compression saves less than the request costs (Lighthouse's own cut-off). */
+const MIN_COMPRESSIBLE_BYTES = 1400;
+/** An image shown before this many words of text is likely in the first screen. */
+const ABOVE_FOLD_WORDS = 100;
+/** Images narrower than this (by their width attribute) gain little from other sizes. */
+const SRCSET_MIN_WIDTH = 640;
+/** A width or height attribute in pixels; pages also write "800px", which browsers read as 800. */
+const pixels = (value) => {
+    const digits = value === null ? undefined : /^\s*\d+(?:\.\d+)?/u.exec(value)?.[0];
+    return digits === undefined ? null : Number(digits);
+};
+/** Icons, logos, spacers and tracking pixels: not the image a visitor waits for. */
+const isSmall = (image) => {
+    const width = pixels(image.width);
+    const height = pixels(image.height);
+    return (width !== null && width < 200) || (height !== null && height < 100);
+};
+/** A vector file: in the first screen it is nearly always a logo or an icon. */
+const isVector = (src) => /\.svg(?:[?#]|$)/iu.test(src) || /^data:image\/svg/iu.test(src);
+const isLazy = (image) => image.loading?.trim().toLowerCase() === "lazy";
+/** Vector, animated and inline images, which one file serves at every size. */
+const isFixedFormat = (src) => /^data:/iu.test(src) || /\.(?:svg|gif)(?:[?#]|$)/iu.test(src);
+export const loadingRules = [
+    defineRule({
+        id: "loading.render-blocking-script",
+        category: "performance",
+        severity: "info",
+        description: 'Scripts in <head> load without async, defer or type="module", so the browser stops building the page until each one has downloaded and run.',
+        recommendation: 'Add defer to scripts the page needs once it is parsed, or async to independent ones such as analytics; type="module" scripts are deferred already. A script that must run before anything renders (a consent manager, an A/B test) can stay, but keep it small.',
+        docs: "https://developer.chrome.com/docs/lighthouse/performance/render-blocking-resources",
+    }, ({ page }, make) => {
+        const scripts = page.head.blockingScripts;
+        return scripts.length > 0
+            ? make(`${scripts.length} script(s) in <head> block rendering: ${cap(scripts, 3).join(", ")}.`, {
+                selector: "head > script[src]:not([async]):not([defer])",
+                evidence: { count: scripts.length, scripts: cap(scripts) },
+            })
+            : null;
+    }),
+    defineRule({
+        id: "loading.no-compression",
+        category: "performance",
+        severity: "warning",
+        description: "The HTML is sent uncompressed although the request accepted gzip, so every visitor and crawler downloads several times more bytes than needed.",
+        recommendation: "Turn on gzip or Brotli compression for text/html (and CSS, JavaScript, JSON, SVG) in the web server, CDN or hosting settings: gzip on in nginx, mod_deflate in Apache, compression() middleware in Express.",
+        docs: "https://developer.chrome.com/docs/lighthouse/performance/uses-text-compression",
+    }, ({ page, source, response }, make) => {
+        if (source !== "url" ||
+            !response ||
+            response.status !== 200 ||
+            isLocalHost(response.finalUrl) ||
+            page.htmlBytes < MIN_COMPRESSIBLE_BYTES) {
+            return null;
+        }
+        const encoding = (response.headers["content-encoding"] ?? "")
+            .trim()
+            .toLowerCase();
+        return encoding === "" || encoding === "identity"
+            ? make(`The ${Math.round(page.htmlBytes / 1024)} KB of HTML arrived without Content-Encoding.`, { evidence: { bytes: page.htmlBytes, contentEncoding: null } })
+            : null;
+    }),
+    defineRule({
+        id: "img.lazy-above-fold",
+        category: "images",
+        severity: "info",
+        description: 'The first large image on the page, likely in the first screen and often the Largest Contentful Paint, has loading="lazy", which delays it (info). An image with both fetchpriority="high" and loading="lazy" contradicts itself (warning).',
+        recommendation: 'Remove loading="lazy" from images in the first screen, and give the main one fetchpriority="high". Keep lazy loading for images further down the page. In Next.js, set priority (or preload) on that <Image>.',
+        docs: "https://web.dev/articles/browser-level-image-lazy-loading",
+    }, ({ page }, make) => {
+        const contradicting = page.images.filter((i) => isLazy(i) && i.fetchpriority === "high");
+        if (contradicting.length > 0) {
+            return make(`${contradicting.length} image(s) have both fetchpriority="high" and loading="lazy".`, {
+                severity: "warning",
+                selector: 'img[loading="lazy"][fetchpriority="high"]',
+                evidence: { images: cap(contradicting.map((i) => i.src)) },
+            });
+        }
+        // An image in a <template> is not on the page until a script stamps it out.
+        const first = page.images.find((i) => i.src && i.wordsBefore !== null && !isVector(i.src) && !isSmall(i));
+        const wordsBefore = first?.wordsBefore ?? null;
+        return first &&
+            wordsBefore !== null &&
+            isLazy(first) &&
+            wordsBefore < ABOVE_FOLD_WORDS
+            ? make(`The first image (${first.src}) comes after ${wordsBefore} words of text and has loading="lazy".`, {
+                selector: 'img[loading="lazy"]',
+                evidence: { src: first.src, wordsBefore },
+            })
+            : null;
+    }),
+    defineRule({
+        id: "img.srcset-missing",
+        category: "images",
+        severity: "info",
+        description: `Images ${SRCSET_MIN_WIDTH} pixels wide or more (by their width attribute) have no srcset or <picture>, so phones download the full-size file.`,
+        recommendation: 'Offer smaller versions with srcset and sizes (srcset="hero-480.jpg 480w, hero-960.jpg 960w" sizes="100vw"), or use the framework\'s image component (next/image, astro:assets, NuxtImg), which generates them.',
+        docs: "https://web.dev/articles/serve-responsive-images",
+    }, ({ page }, make) => {
+        const large = page.images.filter((i) => {
+            const width = pixels(i.width);
+            return (i.src !== null &&
+                !isFixedFormat(i.src) &&
+                !i.srcset &&
+                !i.inPicture &&
+                width !== null &&
+                width >= SRCSET_MIN_WIDTH);
+        });
+        return large.length > 0
+            ? make(`${large.length} image(s) at least ${SRCSET_MIN_WIDTH} pixels wide have no srcset.`, {
+                evidence: {
+                    count: large.length,
+                    examples: cap(large.map((i) => ({ src: i.src, width: i.width }))),
+                },
+            })
+            : null;
+    }),
+    defineRule({
+        id: "favicon.missing",
+        category: "document",
+        severity: "info",
+        description: 'The home page has no <link rel="icon"> (or apple-touch-icon). Google takes the icon it shows next to the site in search results from the home page.',
+        recommendation: 'Add <link rel="icon" href="/favicon.svg"> (or a square PNG larger than 48x48 pixels) to the home page\'s <head>, and keep the file crawlable. Google documents only the link, not a /favicon.ico fallback.',
+        docs: "https://developers.google.com/search/docs/appearance/favicon-in-search",
+    }, 
+    // An error or a bot challenge is not the home page the site serves.
+    ({ page, source, response }, make) => source !== "html" &&
+        (response?.status ?? 200) < 400 &&
+        isHomePage(page.url) &&
+        page.head.icons.length === 0
+        ? make("The home page links to no icon.", {
+            selector: 'head > link[rel="icon"]',
+        })
+        : null),
+];
+//# sourceMappingURL=loading.js.map

package/dist/core/rules/loading.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"loading.js","sourceRoot":"","sources":["../../../src/core/rules/loading.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,UAAU,EAAE,MAAM,gBAAgB,CAAC;AAE5C,OAAO,EAAE,WAAW,EAAE,MAAM,gBAAgB,CAAC;AAC7C,OAAO,EAAE,GAAG,EAAE,UAAU,EAAE,MAAM,WAAW,CAAC;AAE5C,gGAAgG;AAChG,MAAM,sBAAsB,GAAG,IAAI,CAAC;AAEpC,mFAAmF;AACnF,MAAM,gBAAgB,GAAG,GAAG,CAAC;AAE7B,yFAAyF;AACzF,MAAM,gBAAgB,GAAG,GAAG,CAAC;AAE7B,mGAAmG;AACnG,MAAM,MAAM,GAAG,CAAC,KAAoB,EAAiB,EAAE;IACrD,MAAM,MAAM,GACV,KAAK,KAAK,IAAI,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,oBAAoB,CAAC,IAAI,CAAC,KAAK,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC;IAErE,OAAO,MAAM,KAAK,SAAS,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC;AACtD,CAAC,CAAC;AAEF,oFAAoF;AACpF,MAAM,OAAO,GAAG,CAAC,KAAgB,EAAW,EAAE;IAC5C,MAAM,KAAK,GAAG,MAAM,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC;IAClC,MAAM,MAAM,GAAG,MAAM,CAAC,KAAK,CAAC,MAAM,CAAC,CAAC;IAEpC,OAAO,CAAC,KAAK,KAAK,IAAI,IAAI,KAAK,GAAG,GAAG,CAAC,IAAI,CAAC,MAAM,KAAK,IAAI,IAAI,MAAM,GAAG,GAAG,CAAC,CAAC;AAC9E,CAAC,CAAC;AAEF,gFAAgF;AAChF,MAAM,QAAQ,GAAG,CAAC,GAAW,EAAW,EAAE,CACxC,mBAAmB,CAAC,IAAI,CAAC,GAAG,CAAC,IAAI,oBAAoB,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC;AAElE,MAAM,MAAM,GAAG,CAAC,KAAgB,EAAW,EAAE,CAC3C,KAAK,CAAC,OAAO,EAAE,IAAI,EAAE,CAAC,WAAW,EAAE,KAAK,MAAM,CAAC;AAEjD,+EAA+E;AAC/E,MAAM,aAAa,GAAG,CAAC,GAAW,EAAW,EAAE,CAC7C,UAAU,CAAC,IAAI,CAAC,GAAG,CAAC,IAAI,2BAA2B,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC;AAEhE,MAAM,CAAC,MAAM,YAAY,GAAG;IAC1B,UAAU,CACR;QACE,EAAE,EAAE,gCAAgC;QACpC,QAAQ,EAAE,aAAa;QACvB,QAAQ,EAAE,MAAM;QAChB,WAAW,EACT,6IAA6I;QAC/I,cAAc,EACZ,iQAAiQ;QACnQ,IAAI,EAAE,oFAAoF;KAC3F,EACD,CAAC,EAAE,IAAI,EAAE,EAAE,IAAI,EAAE,EAAE;QACjB,MAAM,OAAO,GAAG,IAAI,CAAC,IAAI,CAAC,eAAe,CAAC;QAE1C,OAAO,OAAO,CAAC,MAAM,GAAG,CAAC;YACvB,CAAC,CAAC,IAAI,CACF,GAAG,OAAO,CAAC,MAAM,yCAAyC,GAAG,CAAC,OAAO,EAAE,CAAC,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,GAAG,EACvF;gBACE,QAAQ,EAAE,8CAA8C;gBACxD,QAAQ,EAAE,EAAE,KAAK,EAAE,OAAO,CAAC,MAAM,EAAE,OAAO,EAAE,GAAG,CAAC,OAAO,CAAC,EAAE;aAC3D,CACF;YACH,CAAC,CAAC,IAAI,CAAC;IACX,CAAC,CACF;IACD,UAAU,CACR;QACE,EAAE,EAAE,wBAAwB;QAC5B,QAAQ,EAAE,aAAa;QACvB,QAAQ,EAAE,SAAS;QACnB,WAAW,EACT,gJAAgJ;QAClJ,cAAc,EACZ,6MAA6M;QAC/M,IAAI,EAAE,gFAAgF;KACvF,EACD,CAAC,EAAE,IAAI,EAAE,MAAM,EAAE,QAAQ,EAAE,EAAE,IAAI,EAAE,EAAE;QACnC,IACE,MAAM,KAAK,KAAK;YAChB,CAAC,QAAQ;YACT,QAAQ,CAAC,MAAM,KAAK,GAAG;YACvB,WAAW,CAAC,QAAQ,CAAC,QAAQ,CAAC;YAC9B,IAAI,CAAC,SAAS,GAAG,sBAAsB,EACvC,CAAC;YACD,OAAO,IAAI,CAAC;QACd,CAAC;QAED,MAAM,QAAQ,GAAG,CAAC,QAAQ,CAAC,OAAO,CAAC,kBAAkB,CAAC,IAAI,EAAE,CAAC;aAC1D,IAAI,EAAE;aACN,WAAW,EAAE,CAAC;QAEjB,OAAO,QAAQ,KAAK,EAAE,IAAI,QAAQ,KAAK,UAAU;YAC/C,CAAC,CAAC,IAAI,CACF,OAAO,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,SAAS,GAAG,IAAI,CAAC,+CAA+C,EACvF,EAAE,QAAQ,EAAE,EAAE,KAAK,EAAE,IAAI,CAAC,SAAS,EAAE,eAAe,EAAE,IAAI,EAAE,EAAE,CAC/D;YACH,CAAC,CAAC,IAAI,CAAC;IACX,CAAC,CACF;IACD,UAAU,CACR;QACE,EAAE,EAAE,qBAAqB;QACzB,QAAQ,EAAE,QAAQ;QAClB,QAAQ,EAAE,MAAM;QAChB,WAAW,EACT,4OAA4O;QAC9O,cAAc,EACZ,+MAA+M;QACjN,IAAI,EAAE,2DAA2D;KAClE,EACD,CAAC,EAAE,IAAI,EAAE,EAAE,IAAI,EAAE,EAAE;QACjB,MAAM,aAAa,GAAG,IAAI,CAAC,MAAM,CAAC,MAAM,CACtC,CAAC,CAAC,EAAE,EAAE,CAAC,MAAM,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,aAAa,KAAK,MAAM,CAC/C,CAAC;QAEF,IAAI,aAAa,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;YAC7B,OAAO,IAAI,CACT,GAAG,aAAa,CAAC,MAAM,8DAA8D,EACrF;gBACE,QAAQ,EAAE,SAAS;gBACnB,QAAQ,EAAE,2CAA2C;gBACrD,QAAQ,EAAE,EAAE,MAAM,EAAE,GAAG,CAAC,aAAa,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,EAAE;aAC3D,CACF,CAAC;QACJ,CAAC;QAED,4EAA4E;QAC5E,MAAM,KAAK,GAAG,IAAI,CAAC,MAAM,CAAC,IAAI,CAC5B,CAAC,CAAC,EAAE,EAAE,CACJ,CAAC,CAAC,GAAG,IAAI,CAAC,CAAC,WAAW,KAAK,IAAI,IAAI,CAAC,QAAQ,CAAC,CAAC,CAAC,GAAG,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC,CAAC,CACrE,CAAC;QAEF,MAAM,WAAW,GAAG,KAAK,EAAE,WAAW,IAAI,IAAI,CAAC;QAE/C,OAAO,KAAK;YACV,WAAW,KAAK,IAAI;YACpB,MAAM,CAAC,KAAK,CAAC;YACb,WAAW,GAAG,gBAAgB;YAC9B,CAAC,CAAC,IAAI,CACF,oBAAoB,KAAK,CAAC,GAAG,iBAAiB,WAAW,wCAAwC,EACjG;gBACE,QAAQ,EAAE,qBAAqB;gBAC/B,QAAQ,EAAE,EAAE,GAAG,EAAE,KAAK,CAAC,GAAG,EAAE,WAAW,EAAE;aAC1C,CACF;YACH,CAAC,CAAC,IAAI,CAAC;IACX,CAAC,CACF;IACD,UAAU,CACR;QACE,EAAE,EAAE,oBAAoB;QACxB,QAAQ,EAAE,QAAQ;QAClB,QAAQ,EAAE,MAAM;QAChB,WAAW,EAAE,UAAU,gBAAgB,qHAAqH;QAC5J,cAAc,EACZ,gNAAgN;QAClN,IAAI,EAAE,kDAAkD;KACzD,EACD,CAAC,EAAE,IAAI,EAAE,EAAE,IAAI,EAAE,EAAE;QACjB,MAAM,KAAK,GAAG,IAAI,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE;YACrC,MAAM,KAAK,GAAG,MAAM,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC;YAE9B,OAAO,CACL,CAAC,CAAC,GAAG,KAAK,IAAI;gBACd,CAAC,aAAa,CAAC,CAAC,CAAC,GAAG,CAAC;gBACrB,CAAC,CAAC,CAAC,MAAM;gBACT,CAAC,CAAC,CAAC,SAAS;gBACZ,KAAK,KAAK,IAAI;gBACd,KAAK,IAAI,gBAAgB,CAC1B,CAAC;QACJ,CAAC,CAAC,CAAC;QAEH,OAAO,KAAK,CAAC,MAAM,GAAG,CAAC;YACrB,CAAC,CAAC,IAAI,CACF,GAAG,KAAK,CAAC,MAAM,sBAAsB,gBAAgB,8BAA8B,EACnF;gBACE,QAAQ,EAAE;oBACR,KAAK,EAAE,KAAK,CAAC,MAAM;oBACnB,QAAQ,EAAE,GAAG,CACX,KAAK,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,EAAE,GAAG,EAAE,CAAC,CAAC,GAAG,EAAE,KAAK,EAAE,CAAC,CAAC,KAAK,EAAE,CAAC,CAAC,CACnD;iBACF;aACF,CACF;YACH,CAAC,CAAC,IAAI,CAAC;IACX,CAAC,CACF;IACD,UAAU,CACR;QACE,EAAE,EAAE,iBAAiB;QACrB,QAAQ,EAAE,UAAU;QACpB,QAAQ,EAAE,MAAM;QAChB,WAAW,EACT,qJAAqJ;QACvJ,cAAc,EACZ,4MAA4M;QAC9M,IAAI,EAAE,wEAAwE;KAC/E;IACD,oEAAoE;IACpE,CAAC,EAAE,IAAI,EAAE,MAAM,EAAE,QAAQ,EAAE,EAAE,IAAI,EAAE,EAAE,CACnC,MAAM,KAAK,MAAM;QACjB,CAAC,QAAQ,EAAE,MAAM,IAAI,GAAG,CAAC,GAAG,GAAG;QAC/B,UAAU,CAAC,IAAI,CAAC,GAAG,CAAC;QACpB,IAAI,CAAC,IAAI,CAAC,KAAK,CAAC,MAAM,KAAK,CAAC;QAC1B,CAAC,CAAC,IAAI,CAAC,iCAAiC,EAAE;YACtC,QAAQ,EAAE,yBAAyB;SACpC,CAAC;QACJ,CAAC,CAAC,IAAI,CACX;CACF,CAAC"}

package/dist/core/rules/rule.d.ts

@@ -31,6 +31,8 @@ export declare const GOOGLE_DOCS: {
     readonly hreflang: "https://developers.google.com/search/docs/specialty/international/localized-versions";
     readonly images: "https://developers.google.com/search/docs/appearance/google-images";
     readonly links: "https://developers.google.com/search/docs/crawling-indexing/links-crawlable";
+    readonly urlStructure: "https://developers.google.com/search/docs/crawling-indexing/url-structure";
+    readonly validMetadata: "https://developers.google.com/search/docs/crawling-indexing/valid-page-metadata";
     readonly structuredData: "https://developers.google.com/search/docs/appearance/structured-data/intro-structured-data";
     readonly javascript: "https://developers.google.com/search/docs/crawling-indexing/javascript/javascript-seo-basics";
     readonly cwv: "https://web.dev/articles/vitals";