migration wip

scripts/test-numeric-entities.js

@@ -0,0 +1,68 @@
+#!/usr/bin/env node
+
+// Test numeric entity decoding
+
+const testString = 'type=”in_container”';
+
+console.log('Original:', testString);
+
+// Method 1: Manual replacement
+let method1 = testString
+  .replace(/”/g, '"')
+  .replace(/“/g, '"')
+  .replace(/‘/g, "'")
+  .replace(/’/g, "'")
+  .replace(/–/g, '-')
+  .replace(/—/g, '—');
+
+console.log('Method 1 (Unicode chars):', method1);
+
+// Method 2: Numeric entity decoding
+let method2 = testString
+  .replace(/”/g, '"')
+  .replace(/“/g, '"')
+  .replace(/‘/g, "'")
+  .replace(/’/g, "'")
+  .replace(/–/g, '-')
+  .replace(/—/g, '—')
+  .replace(/…/g, '…')
+  .replace(/″/g, '"')
+  .replace(/′/g, "'");
+
+console.log('Method 2 (Numeric entities):', method2);
+
+// Method 3: Using a function to decode all numeric entities
+function decodeHTMLEntities(str) {
+  return str.replace(/&#(\d+);/g, (match, dec) => {
+    return String.fromCharCode(dec);
+  });
+}
+
+let method3 = decodeHTMLEntities(testString);
+console.log('Method 3 (All numeric):', method3);
+
+// Method 4: Combined approach
+function comprehensiveEntityDecode(str) {
+  return str
+    // First decode numeric entities
+    .replace(/&#(\d+);/g, (match, dec) => String.fromCharCode(dec))
+    // Then handle any remaining Unicode characters
+    .replace(/”/g, '"')
+    .replace(/“/g, '"')
+    .replace(/‘/g, "'")
+    .replace(/’/g, "'")
+    .replace(/–/g, '-')
+    .replace(/—/g, '—')
+    .replace(/…/g, '…')
+    .replace(/″/g, '"')
+    .replace(/′/g, "'");
+}
+
+let method4 = comprehensiveEntityDecode(testString);
+console.log('Method 4 (Combined):', method4);
+
+// Test with the actual excerpt
+const actualExcerpt = '<p>[vc_row type=”in_container” full_screen_row_position=”middle” column_margin=”default”]';
+console.log('\n=== Real Test ===');
+console.log('Original:', actualExcerpt);
+console.log('Decoded:', comprehensiveEntityDecode(actualExcerpt));