Update app.py

app.py

@@ -27,7 +27,7 @@ def preprocess_text(text: str, is_spell_corrected: bool = False):
     """Process text and return corrections with position information."""
     result = {
         "spell_suggestions": [],
-        "other_suggestions": [],  # Added to distinguish style suggestions
+        "other_suggestions": [],  # For NLP-based style/grammar suggestions
         "entities": [],
         "tags": []
     }
@@ -51,17 +51,29 @@ def preprocess_text(text: str, is_spell_corrected: bool = False):
             })
             text = spell_checked  # Update text after spell correction
 
-    # Add style suggestions (other_suggestions)
-    words = text.split()
-    for word in words:
-        if not word.endswith(('.', '?', '!')):  # Skip if already punctuated
-            result["other_suggestions"].append({
-                "original": word,
-                "corrected": word + "!"
-            })
+    # Add NLP-based "other" suggestions using spaCy
+    doc = nlp(text)
+    for token in doc:
+        # Example: Suggest adding an article before a noun if missing
+        if token.pos_ == "NOUN" and token.dep_ != "compound" and token.i > 0:
+            prev_token = doc[token.i - 1]
+            if prev_token.pos_ not in ("DET", "PRON") and not prev_token.text.endswith("'s"):
+                suggested = f"{text[:token.idx]}the {text[token.idx:]}"
+                result["other_suggestions"].append({
+                    "original": text,
+                    "corrected": suggested
+                })
+        # Example: Suggest "is" for subject-verb agreement (rudimentary)
+        elif token.pos_ == "NOUN" and token.dep_ == "nsubj" and token.i + 1 < len(doc):
+            next_token = doc[token.i + 1]
+            if next_token.pos_ != "VERB":
+                suggested = f"{text[:next_token.idx]}is {text[next_token.idx:]}"
+                result["other_suggestions"].append({
+                    "original": text,
+                    "corrected": suggested
+                })
 
     # 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(('#', '@'))]