Update app.py

app.py

@@ -26,61 +26,57 @@ def preprocess_capitalization(text: str) -> str:
     
     return " ".join(processed_words)
 
-def find_differences(original: str, corrected: str):
-    """Find differences between original and corrected text."""
-    differences = []
-    for i, (orig_char, corr_char) in enumerate(zip(original, corrected)):
-        if orig_char != corr_char:
-            differences.append({
-                "position": i,
-                "original": orig_char,
-                "corrected": corr_char
-            })
-    return differences
-
 def preprocess_text(text: str):
     """Process text and return corrections with position information."""
     result = {
-        "corrected_text": "",
-        "differences": [],
-        "entities": []
+        "spell_suggestions": [],
+        "entities": [],
+        "tags": []
     }
 
     # Apply capitalization preprocessing
     capitalized_text = preprocess_capitalization(text)
     if capitalized_text != text:
-        result["corrected_text"] = capitalized_text
-        result["differences"] = find_differences(text, capitalized_text)
+        result["spell_suggestions"].append({
+            "original": text,
+            "corrected": capitalized_text
+        })
         text = capitalized_text  # Update text for further processing
 
-    # TextBlob spell check
+    # Find and record positions of corrections
+    doc = nlp(text)
+    
+    # TextBlob spell check with position tracking
     blob = TextBlob(text)
     corrected = str(blob.correct())
     if corrected != text:
-        result["corrected_text"] = corrected
-        result["differences"] = find_differences(text, corrected)
-        text = corrected  # Update text for further processing
-
+        result["spell_suggestions"].append({
+            "original": text,
+            "corrected": corrected
+        })
+    
     # Transformer spell check
     spell_checked = spell_checker(text, max_length=512)[0]['generated_text']
     if spell_checked != text and spell_checked != corrected:
-        result["corrected_text"] = spell_checked
-        result["differences"] = find_differences(text, spell_checked)
+        result["spell_suggestions"].append({
+            "original": text,
+            "corrected": spell_checked
+        })
 
-    # Add entities
-    doc = nlp(text)
+    # Add entities and tags
     result["entities"] = [{"text": ent.text, "label": ent.label_} for ent in doc.ents]
+    result["tags"] = [token.text for token in doc if token.text.startswith(('#', '@'))]
 
-    return result
+    return text, result
 
 def preprocess_and_forward(text: str):
     """Process text and forward to translation service."""
-    preprocessing_result = preprocess_text(text)
+    original_text, preprocessing_result = preprocess_text(text)
     
-    # Forward corrected text to translation service
+    # Forward original text to translation service
     client = Client("Frenchizer/space_17")
     try:
-        translation = client.predict(preprocessing_result["corrected_text"])
+        translation = client.predict(original_text)
         return translation, preprocessing_result
     except Exception as e:
         return f"Error: {str(e)}", preprocessing_result