Update app.py

app.py

@@ -3,6 +3,7 @@ from transformers import pipeline
 import spacy
 from gradio_client import Client
 import re
+import httpx
 
 # Initialize models
 nlp = spacy.load("en_core_web_sm")
@@ -14,51 +15,54 @@ def preprocess_capitalization(text: str) -> str:
     processed_words = []
     
     for word in words:
-        # Check if the word is an acronym (all uppercase letters)
         if re.match(r"^[A-Z]+$", word):
             processed_words.append(word)  # Leave acronyms unchanged
-        # Check if the word has mixed capitalization (e.g., "HEllo")
         elif re.search(r"[A-Z]", word) and re.search(r"[a-z]", word):
             processed_words.append(word[0].upper() + word[1:].lower())  # Correct capitalization
         else:
-            processed_words.append(word)  # Leave other words unchanged
+            processed_words.append(word)
     
     return " ".join(processed_words)
 
 def preprocess_text(text: str):
     """Process text and return corrections with position information."""
     result = {
-        "suggestions": []  # Rename to generic "suggestions" for flexibility
+        "suggestions": []
     }
 
-    # Apply capitalization preprocessing (Spell type)
+    # Step 1: Apply capitalization preprocessing (Spell type)
     capitalized_text = preprocess_capitalization(text)
     if capitalized_text != text:
         result["suggestions"].append({
             "original": text,
             "corrected": capitalized_text,
-            "type": "spell"  # Add type
+            "type": "spell"
         })
-        text = capitalized_text
+        text = capitalized_text  # Update text for further processing
 
-    # Transformer spell check (Spell type)
-    spell_checked = spell_checker(text, max_length=512)[0]['generated_text']
-    if spell_checked != text:
+    # Step 2: Transformer spell check (Spell type)
+    spell_checked = spell_checker(text, max_length=512)[0]['generated_text'].strip()
+    # Only add as a spell suggestion if it’s a true spelling change (not just punctuation)
+    if spell_checked != text and spell_checked.rstrip('!.') == text.rstrip('!.'):
+        # If the difference is only punctuation, skip adding it here
+        pass
+    elif spell_checked != text:
         result["suggestions"].append({
             "original": text,
             "corrected": spell_checked,
-            "type": "spell"  # Add type
+            "type": "spell"
         })
+        text = spell_checked  # Update text only for true spell corrections
 
-    # Example "other" suggestion (e.g., adding punctuation)
+    # Step 3: Add "other" suggestion (e.g., punctuation)
     if not text.endswith("!") and text.strip():
         result["suggestions"].append({
             "original": text,
             "corrected": text + "!",
-            "type": "other"  # Add type for non-spell suggestions
+            "type": "other"
         })
 
-    # Add entities and tags (unchanged)
+    # Add entities and tags
     doc = nlp(text)
     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(('#', '@'))]
@@ -66,16 +70,19 @@ def preprocess_text(text: str):
     return text, result
 
 def preprocess_and_forward(text: str):
-    """Process text and forward to translation service."""
+    """Process text and forward to translation service with custom timeout."""
     original_text, preprocessing_result = preprocess_text(text)
-    client = Client("Frenchizer/space_21")
+    
     try:
+        client = Client("Frenchizer/space_21", httpx_timeout=httpx.Timeout(60.0))
         translation = client.predict(original_text)
         return translation, preprocessing_result
+    except httpx.ReadTimeout:
+        return "Error: Translation service timed out after 60 seconds. Please try again later.", preprocessing_result
     except Exception as e:
         return f"Error: {str(e)}", preprocessing_result
 
-# Update Gradio outputs to match
+# Gradio interface
 with gr.Blocks() as demo:
     input_text = gr.Textbox(label="Input Text")
     output_text = gr.Textbox(label="Output Text")