ALwrity + Wordpress + Wix + GSC integration

backend/alwrity_utils/dependency_manager.py

@@ -91,7 +91,7 @@ class DependencyManager:
         return len(missing_packages) == 0, missing_packages
     
     def setup_spacy_model(self) -> bool:
-        """Set up spaCy English model (production-optimized)."""
+        """Set up spaCy English model."""
         print("🧠 Setting up spaCy model...")
         
         try:
@@ -107,30 +107,42 @@ class DependencyManager:
                     print(f"✅ spaCy model '{model_name}' is available")
                     return True
             except OSError:
-                print(f"⚠️  spaCy model '{model_name}' not found")
-                print("   Skipping spaCy setup in production mode")
-                return True  # Don't fail for missing spaCy in production
+                # Model not found - try to download it
+                print(f"⚠️  spaCy model '{model_name}' not found, downloading...")
+                try:
+                    subprocess.check_call([
+                        sys.executable, "-m", "spacy", "download", model_name
+                    ])
+                    print(f"✅ spaCy model '{model_name}' downloaded successfully")
+                    return True
+                except subprocess.CalledProcessError as e:
+                    print(f"❌ Failed to download spaCy model: {e}")
+                    print("   Please download manually with: python -m spacy download en_core_web_sm")
+                    return False
                 
         except ImportError:
             print("⚠️  spaCy not installed - skipping model setup")
-            return True  # Don't fail for missing spaCy
+            return True  # Don't fail for missing spaCy package
         
         return True
     
     def setup_nltk_data(self) -> bool:
-        """Set up NLTK data (production-optimized)."""
+        """Set up NLTK data."""
         print("📚 Setting up NLTK data...")
         
         try:
             import nltk
             
-            # Only download essential data
-            essential_data = ['punkt', 'stopwords']
+            # Essential NLTK data packages
+            essential_data = [
+                ('punkt_tab', 'tokenizers/punkt_tab'),  # Updated tokenizer
+                ('stopwords', 'corpora/stopwords'),
+                ('averaged_perceptron_tagger', 'taggers/averaged_perceptron_tagger')
+            ]
             
-            for data_package in essential_data:
+            for data_package, path in essential_data:
                 try:
-                    nltk.data.find(f'tokenizers/{data_package}' if data_package == 'punkt' 
-                                  else f'corpora/{data_package}')
+                    nltk.data.find(path)
                     print(f"   ✅ {data_package}")
                 except LookupError:
                     print(f"   ⚠️  {data_package} - downloading...")
@@ -139,12 +151,19 @@ class DependencyManager:
                         print(f"   ✅ {data_package} downloaded")
                     except Exception as e:
                         print(f"   ⚠️  {data_package} download failed: {e}")
+                        # Try fallback for punkt_tab -> punkt
+                        if data_package == 'punkt_tab':
+                            try:
+                                nltk.download('punkt', quiet=True)
+                                print(f"   ✅ punkt (fallback) downloaded")
+                            except:
+                                pass
             
             print("✅ NLTK data setup complete")
             return True
             
         except ImportError:
             print("⚠️  NLTK not installed - skipping data setup")
-            return True  # Don't fail for missing NLTK
+            return True  # Don't fail for missing NLTK package
         
         return True