n8n-nodes-notion-advanced 1.2.22-beta → 1.2.24-beta

package/nodes/NotionAdvanced/NotionAITool.node.d.ts

@@ -49,6 +49,7 @@ export declare class NotionAITool implements INodeType {
     static applyHierarchicalReplacements(content: string, nodes: XMLNode[], replacements: Map<string, string>): string;
     static getAllNodesFromTree(nodes: XMLNode[]): XMLNode[];
     static processXmlTags(content: string, blocks: IDataObject[]): string;
+    static cleanupAllPlaceholders(content: string): string;
     static decodeHtmlEntities(content: string): string;
     static cleanupRemainingHtml(content: string, placeholderPrefix?: string): string;
     static processNestedHtmlInListItem(content: string): string;

package/nodes/NotionAdvanced/NotionAITool.node.js

@@ -1157,7 +1157,9 @@ class NotionAITool {
             const replacements = NotionAITool.processXMLTreeDepthFirst(xmlTree, blocks, counterRef);
             // Step 3: Apply hierarchical replacements to content
             processedContent = NotionAITool.applyHierarchicalReplacements(processedContent, xmlTree, replacements);
-            // Step 4: Clean up any remaining HTML tags
+            // Step 4: Immediately replace all placeholders with empty strings since blocks are already in blocks array
+            processedContent = NotionAITool.cleanupAllPlaceholders(processedContent);
+            // Step 5: Clean up any remaining HTML tags
             processedContent = NotionAITool.cleanupRemainingHtml(processedContent);
             if (DEBUG_ORDERING) {
                 console.log(`Processed ${xmlTree.length} root XML nodes hierarchically, created ${blocks.length} blocks`);
@@ -1210,6 +1212,55 @@ class NotionAITool {
         }
         return processedContent;
     }
+    // Helper function to immediately clean up all placeholders after hierarchical processing
+    static cleanupAllPlaceholders(content) {
+        let cleaned = content;
+        // Since blocks have already been added to the blocks array during hierarchical processing,
+        // we can safely remove all placeholders immediately to prevent partial replacement issues
+        // Primary sequential placeholder patterns: __BLOCK_N__
+        const sequentialPatterns = [
+            /__BLOCK_\d+__/g, // Standard format: __BLOCK_1__, __BLOCK_2__, etc.
+            /\b__BLOCK_\d+__\b/g, // Word boundary version
+            /__BL\w*_\d+__/g, // Partial matches like __BL..._N__
+            /\b\w*OCK\d+_\b/g, // Catch patterns like "OCK23_"
+            /\b\w*CK\d+_\b/g, // Catch patterns like "CK23_"
+            /\b\w*K\d+_\b/g, // Catch patterns like "K23_"
+            /\b\d+__\b/g, // Remnants like "23__"
+            /__\d+__/g, // Alternative format: __1__, __2__, etc.
+            /__\w*\d+_*/g, // Any underscore-digit patterns
+            /\b[A-Z]*OCK\d+_*\b/g, // Case variations of OCK patterns
+        ];
+        // Apply all sequential cleanup patterns
+        sequentialPatterns.forEach(pattern => {
+            cleaned = cleaned.replace(pattern, '');
+        });
+        // Legacy UUID-based placeholder cleanup (for backwards compatibility)
+        const legacyPatterns = [
+            /__XML_[a-f0-9]{8}_\d+__/g, // Standard format: __XML_abc12345_1__
+            /\b[A-Z]{2}[a-z0-9]{8,12}_+\b/g, // Variations like "MLb82d670450__"
+            /\b[A-Za-z]{2,4}[a-f0-9]{6,12}_+\b/g, // More flexible pattern matching
+            /_[a-f0-9]{8,12}_\d+_*/g, // Underscore variations
+            /[a-f0-9]{8,12}_\d+__/g, // Without prefix
+        ];
+        // Apply legacy cleanup patterns
+        legacyPatterns.forEach(pattern => {
+            cleaned = cleaned.replace(pattern, '');
+        });
+        // Additional aggressive patterns to catch any partial remnants
+        const aggressivePatterns = [
+            /\b[A-Z]{1,4}\d{1,3}_+\b/g, // Patterns like "OCK23_", "CK23_", "K23_"
+            /\b[A-Za-z]{1,6}\d{1,4}_+\b/g, // More general partial patterns
+            /_{2,}\d+_{0,2}/g, // Multiple underscores with digits
+            /__+[A-Za-z]*\d+_*/g, // Underscore patterns with letters and digits
+        ];
+        // Apply aggressive cleanup patterns as final pass
+        aggressivePatterns.forEach(pattern => {
+            cleaned = cleaned.replace(pattern, '');
+        });
+        // Remove any double spaces created by removals
+        cleaned = cleaned.replace(/\s{2,}/g, ' ').trim();
+        return cleaned;
+    }
     // Helper function to decode HTML entities
     static decodeHtmlEntities(content) {
         const entityMap = {
@@ -1227,37 +1278,37 @@ class NotionAITool {
         });
         return decoded;
     }
-    // Cleanup function to remove remaining HTML tags and XML_BLOCK artifacts
+    // Cleanup function to remove remaining HTML tags and placeholder artifacts
     static cleanupRemainingHtml(content, placeholderPrefix) {
         let cleaned = content;
-        // Simplified placeholder cleanup - use one consistent pattern
+        // Clean up sequential placeholder format: __BLOCK_N__
+        const sequentialPlaceholderPatterns = [
+            /__BLOCK_\d+__/g, // Standard format: __BLOCK_1__, __BLOCK_2__, etc.
+            /\b\d+__\b/g, // Remnants like "7__"
+            /__\d+__/g, // Alternative format: __1__, __2__, etc.
+        ];
+        sequentialPlaceholderPatterns.forEach(pattern => {
+            cleaned = cleaned.replace(pattern, '');
+        });
+        // Legacy placeholder cleanup (for backwards compatibility)
         if (placeholderPrefix) {
-            // Clean up our specific placeholder format: __XML_{uuid8}_{number}__
             const escapedPrefix = placeholderPrefix.replace(/[.*+?^${}()|[\]\\]/g, '\\$&');
             const placeholderPattern = new RegExp(`${escapedPrefix}\\d+__`, 'g');
             cleaned = cleaned.replace(placeholderPattern, '');
         }
-        // Comprehensive fallback cleanup for all possible placeholder formats
-        const placeholderPatterns = [
+        // Clean up old UUID-based placeholders (for backwards compatibility)
+        const legacyPlaceholderPatterns = [
             /__XML_[a-f0-9]{8}_\d+__/g, // Standard format: __XML_abc12345_1__
             /\b[A-Z]{2}[a-z0-9]{8,12}_+\b/g, // Variations like "MLb82d670450__"
             /\b[A-Za-z]{2,4}[a-f0-9]{6,12}_+\b/g, // More flexible pattern matching
             /_[a-f0-9]{8,12}_\d+_*/g, // Underscore variations
             /[a-f0-9]{8,12}_\d+__/g, // Without prefix
         ];
-        placeholderPatterns.forEach(pattern => {
-            cleaned = cleaned.replace(pattern, '');
-        });
-        // Remove entire lines containing XML content to prevent double processing
-        const xmlContentLines = [
-            /^.*<[^>]+>.*$/gm, // Any line with XML/HTML tags
-            /^.*&lt;[^&]+&gt;.*$/gm, // HTML-encoded tags
-            /^.*<(h[1-6]|p|ul|ol|li|strong|em|b|i|code|blockquote|callout|todo|image|embed|bookmark|equation|toggle|divider|quote|pre)\b[^>]*>.*$/gim, // Specific XML content
-        ];
-        xmlContentLines.forEach(pattern => {
+        legacyPlaceholderPatterns.forEach(pattern => {
             cleaned = cleaned.replace(pattern, '');
         });
-        // Remove common HTML tags that might be left behind
+        // Remove common HTML tags that might be left behind AFTER processing
+        // Note: We don't remove entire lines here - only clean up leftover tags
         const htmlTagsToRemove = [
             /<\/?ul\s*[^>]*>/gi,
             /<\/?ol\s*[^>]*>/gi,

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "n8n-nodes-notion-advanced",
-  "version": "1.2.22-beta",
+  "version": "1.2.24-beta",
   "description": "Advanced n8n Notion nodes: Full-featured workflow node + AI Agent Tool for intelligent Notion automation with 25+ block types (BETA)",
   "scripts": {},
   "files": [