w3c-validate-html 1.0.1 → 1.1.0

package/README.md

@@ -124,21 +124,14 @@ jobs:
   html-validate:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
       - uses: actions/setup-node@v4
         with:
           node-version: 18
 
-      - run: npm ci
-      - run: npm start &
-
-      - run: |
-          for i in {1..30}; do
-            curl -fsS http://localhost:8080 >/dev/null && break
-            sleep 1
-          done
-
-      - run: npx w3c-validate-html --url http://localhost:8080 --depth 3 --concurrency 4 --errors-only --json > html-report.json
+      - name: validate url
+        env:
+          TARGET_URL: https://example.com
+        run: npx w3c-validate-html --target "$TARGET_URL" --depth 2 --errors-only --json > html-report.json
 
       - uses: actions/upload-artifact@v4
         with:

package/index.js

@@ -154,14 +154,49 @@ function toList(v) {
  */
 function toSafeName(href) {
     var s = String(href || '');
+    var out = '';
+    var i;
+    var ch;
+
     s = s.replace(/^https?:\/\//i, '');
-    s = s.replace(/[?#].*$/, '');
     s = s.replace(/\/+/g, '/');
-    s = s.replace(/[^a-z0-9/._-]+/gi, '_');
-    s = s.replace(/\//g, '_');
-    if (!s) { s = 'index.html'; }
-    if (!/\.html?$/i.test(s)) { s += '.html'; }
-    return s;
+
+    /* convert url chars to filename safe chars without stripping query */
+    for (i = 0; i < s.length; i++) {
+        ch = s.charAt(i);
+
+        /* keep common safe chars */
+        if (/[a-z0-9]/i.test(ch) || ch === '/' || ch === '.' || ch === '_' || ch === '-') {
+            out += ch;
+        }
+        /* map separators to readable tokens */
+        else if (ch === '?') {
+            out += '__q__';
+        }
+        else if (ch === '&') {
+            out += '__and__';
+        }
+        else if (ch === '=') {
+            out += '__eq__';
+        }
+        else if (ch === '#') {
+            out += '__hash__';
+        }
+        /* everything else becomes underscore */
+        else {
+            out += '_';
+        }
+    }
+
+    out = out.replace(/\/+/g, '/');
+    out = out.replace(/_+/g, '_');
+    out = out.replace(/\//g, '_');
+    out = out.replace(/^_+|_+$/g, '');
+
+    if (!out) { out = 'index.html'; }
+    if (!/\.html?$/i.test(out)) { out += '.html'; }
+
+    return out;
 }
 
 /**
@@ -389,6 +424,15 @@ function isCrawlable(href, cfg, origin) {
         return false;
     }
 
+    // skip common non-HTML file types (e.g., pdf, zip, docx, etc)
+    if (/\.(pdf|zip|docx?|xlsx?|pptx?|jpg|jpeg|png|gif|svg|mp3|mp4|avi|mov|wmv|exe|dmg|tar|gz|rar|7z)(\?|#|$)/i.test(href)) {
+        return false;
+    }
+    // skip links that look like downloads
+    if (/download(=|\b|\/|\.)|attachment(=|\b|\/|\.)|file(=|\b|\/|\.)/i.test(href)) {
+        return false;
+    }
+
     if (cfg && cfg.sameOrigin) {
         try {
             if (new URL(href).origin !== origin) {
@@ -432,6 +476,12 @@ async function fetchHtml(pageUrl, cfg) {
         throw new Error('request failed ' + res.status + ' ' + pageUrl);
     }
 
+    // Only process HTML or XHTML
+    var contentType = res.headers.get('content-type') || '';
+    if (!/text\/html|application\/xhtml\+xml/i.test(contentType)) {
+        return null;
+    }
+
     var finalUrl = (res.url && String(res.url)) ? String(res.url) : pageUrl;
     var html = await res.text();
 
@@ -560,7 +610,19 @@ async function asyncPool(items, concurrency, worker) {
  * @returns {Promise<{url:string,ok:boolean,errors:Array,warnings:Array,finalUrl:string,links:Array}>} - Result
  */
 async function validateOneUrl(pageUrl, cfg, tmpDir) {
+
     var fetched = await fetchHtml(pageUrl, cfg);
+    if (!fetched) {
+        // Not HTML, skip crawling and validation
+        return {
+            url: pageUrl,
+            finalUrl: pageUrl,
+            ok: true,
+            errors: [],
+            warnings: [],
+            links: []
+        };
+    }
     var finalUrl = fetched.finalUrl;
     var html = fetched.html;
 
@@ -973,11 +1035,25 @@ if (require.main === module) {
         userAgent: argv['user-agent']
     };
 
+    const startTime = Date.now();
     validate(target, cfg).then(function (summary) {
         if (argv.json) {
             try { console.log(JSON.stringify(summary)); }
             catch (e) { console.error('{"error":"failed to stringify results"}'); }
         }
+
+        // Jasmine-style summary (simplified)
+        const total = summary.passed + summary.failed;
+        const duration = ((Date.now() - startTime) / 1000).toFixed(3);
+        console.log('\nSummary:');
+        if (summary.failed === 0) {
+            console.log('\n👊  Passed');
+        } else {
+            console.log('\n❌  Failed');
+        }
+        console.log('Pages:   ' + summary.passed + ' of ' + total);
+        console.log('Errors:  ' + summary.failed);
+        console.log('Finished in ' + duration + ' seconds');
         process.exit(summary.failed > 0 ? 1 : 0);
     })
     .catch(function (err) {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "w3c-validate-html",
-  "version": "1.0.1",
+  "version": "1.1.0",
   "description": "Validate HTML offline using the official W3C vnu.jar",
   "type": "commonjs",
   "main": "index.js",