shippingszn 0.3.0 → 0.4.0

package/dist/checks/public-assets.js

@@ -1,4 +1,55 @@
+import { readFileSafe } from "../scan.js";
 import { findPublicDirs, isAssetEmittedDynamically } from "./helpers.js";
+/**
+ * Parse a robots.txt body and return true if the `User-agent: *` block (or
+ * any wildcard block) disallows everything (`Disallow: /`). That's a
+ * declaration that the site intentionally opts out of all crawling, so we
+ * shouldn't nag about a missing sitemap — sitemaps for disallowed sites are
+ * contradictory.
+ */
+function robotsDisallowsAll(content) {
+    const lines = content.split(/\r?\n/);
+    let inWildcardBlock = false;
+    let sawWildcardBlock = false;
+    for (const raw of lines) {
+        // Strip comments and trailing whitespace.
+        const line = raw.replace(/#.*$/, "").trim();
+        if (line === "") {
+            // Blank line ends the current block.
+            inWildcardBlock = false;
+            continue;
+        }
+        const match = line.match(/^([A-Za-z-]+)\s*:\s*(.*)$/);
+        if (!match)
+            continue;
+        const directive = match[1].toLowerCase();
+        const value = match[2].trim();
+        if (directive === "user-agent") {
+            inWildcardBlock = value === "*";
+            if (inWildcardBlock)
+                sawWildcardBlock = true;
+            continue;
+        }
+        if (inWildcardBlock && directive === "disallow" && value === "/") {
+            return true;
+        }
+    }
+    // If the file has no wildcard block at all, conservatively assume it
+    // doesn't disallow everything (some sites only target specific bots).
+    void sawWildcardBlock;
+    return false;
+}
+async function hasDisallowAllRobots(ctx) {
+    const robotsFiles = ctx.files.filter((f) => /(^|\/)robots\.txt$/i.test(f.relPath));
+    for (const file of robotsFiles) {
+        const content = await readFileSafe(file);
+        if (!content)
+            continue;
+        if (robotsDisallowsAll(content))
+            return true;
+    }
+    return false;
+}
 export async function checkRobotsTxt(ctx) {
     const has = ctx.files.some((f) => /(^|\/)robots\.txt$/i.test(f.relPath));
     if (has)
@@ -26,6 +77,11 @@ export async function checkSitemapXml(ctx) {
     const dirs = await findPublicDirs(ctx);
     if (dirs.length === 0)
         return [];
+    // If the project has declared itself non-indexable via robots.txt
+    // (User-agent: * / Disallow: /), a sitemap would be contradictory.
+    // Suppress the nag — the site owner has made a deliberate choice.
+    if (await hasDisallowAllRobots(ctx))
+        return [];
     return [
         {
             checkId: "missing-sitemap-xml",

package/dist/index.js

@@ -30,7 +30,7 @@ function applyTrackingAwareSeverity(findings, tracked) {
     });
 }
 const DEFAULT_BASE_URL = "https://shippingszn.com";
-const PKG_VERSION = "0.3.0";
+const PKG_VERSION = "0.4.0";
 function parseArgs(argv) {
     const opts = {
         cwd: process.cwd(),

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "shippingszn",
-  "version": "0.3.0",
+  "version": "0.4.0",
   "description": "Read-only CLI scanner that checks a project for common pre-launch issues from the shippingszn.com launch checklist.",
   "license": "MIT",
   "type": "module",