@marvalt/wparser 0.1.66 → 0.1.67

package/dist/index.cjs

@@ -1519,29 +1519,64 @@ function renderTextWithShortcodes(text, registry) {
  * Content extraction utilities for WordPress blocks
  * Extracts text content from various block formats
  */
+/**
+ * Decode HTML entities in a string
+ * Handles both named entities (&, ") and numeric entities (', ’)
+ */
+function decodeHtmlEntities(text) {
+    if (!text)
+        return '';
+    // Use browser's built-in decoder if available (most efficient)
+    if (typeof document !== 'undefined') {
+        const textarea = document.createElement('textarea');
+        textarea.innerHTML = text;
+        return textarea.value;
+    }
+    // Fallback for server-side or when document is not available
+    // Decode numeric entities (', ’, etc.)
+    let decoded = text.replace(/&#(\d+);/g, (match, dec) => {
+        return String.fromCharCode(parseInt(dec, 10));
+    });
+    // Decode hex entities (', etc.)
+    decoded = decoded.replace(/&#x([0-9a-fA-F]+);/g, (match, hex) => {
+        return String.fromCharCode(parseInt(hex, 16));
+    });
+    // Decode common named entities
+    const namedEntities = {
+        '&': '&',
+        '&lt;': '<',
+        '&gt;': '>',
+        '&quot;': '"',
+        '&apos;': "'",
+        '&nbsp;': ' ',
+        '&copy;': '©',
+        '&reg;': '®',
+        '&trade;': '™',
+        '&hellip;': '…',
+        '&mdash;': '—',
+        '&ndash;': '–',
+        '&lsquo;': '\u2018', // Left single quotation mark
+        '&rsquo;': '\u2019', // Right single quotation mark
+        '&ldquo;': '\u201C', // Left double quotation mark
+        '&rdquo;': '\u201D', // Right double quotation mark
+    };
+    Object.entries(namedEntities).forEach(([entity, char]) => {
+        decoded = decoded.replace(new RegExp(entity, 'g'), char);
+    });
+    return decoded;
+}
 /**
  * Extract text content from a block's innerHTML by stripping HTML tags
  */
 function extractTextFromHTML(html) {
     if (!html)
         return '';
-    // Remove HTML tags and decode entities
-    let text = html
-        .replace(/<[^>]*>/g, '') // Remove HTML tags
-        .replace(/&nbsp;/g, ' ') // Replace &nbsp; with space
-        .replace(/&#8217;/g, "'") // Replace apostrophe entity
-        .replace(/&#8220;/g, '"') // Replace left double quote
-        .replace(/&#8221;/g, '"') // Replace right double quote
-        .replace(/&#8230;/g, '...') // Replace ellipsis
-        .replace(/&amp;/g, '&') // Replace &amp;
-        .replace(/&lt;/g, '<') // Replace &lt;
-        .replace(/&gt;/g, '>') // Replace &gt;
-        .replace(/&quot;/g, '"') // Replace &quot;
-        .replace(/&#8211;/g, '–') // Replace en dash
-        .replace(/&#8212;/g, '—') // Replace em dash
-        .trim();
+    // Remove HTML tags first
+    let text = html.replace(/<[^>]*>/g, '');
+    // Decode all HTML entities (comprehensive)
+    text = decodeHtmlEntities(text);
     // Clean up extra whitespace
-    text = text.replace(/\s+/g, ' ');
+    text = text.replace(/\s+/g, ' ').trim();
     return text;
 }
 /**