updated api

app/routers/analyze.py

@@ -10,7 +10,16 @@ router = APIRouter()
 
 # Load the spaCy English language model for natural language processing tasks,
 # such as dependency parsing for active/passive voice detection.
-nlp = spacy.load("en_core_web_sm")
+# IMPORTANT: If you get an OSError: [E050] Can't find model 'en_core_web_sm',
+# you need to run: python -m spacy download en_core_web_sm in your terminal.
+try:
+    nlp = spacy.load("en_core_web_sm")
+except OSError:
+    print("SpaCy model 'en_core_web_sm' not found. Please run: python -m spacy download en_core_web_sm")
+    # You might want to raise an HTTPException or provide a dummy NLP object
+    # if the model is crucial for the application to function.
+    # For now, we'll let it fail if not installed, as it's a critical dependency.
+    raise
 
 # Initialize LanguageTool for grammar, spelling, and style checking.
 # 'en-US' specifies the English (United States) language.
@@ -23,18 +32,20 @@ class AnalyzeInput(BaseModel):
     """
     text: str
 
-@router.post("/analyze")
-def analyze_text(payload: AnalyzeInput, request: Request = Depends(verify_api_key)):
+# Apply the verify_api_key dependency at the router level for this endpoint.
+# The Request object is now correctly handled without being wrapped by Depends.
+@router.post("/analyze", dependencies=[Depends(verify_api_key)])
+def analyze_text(payload: AnalyzeInput):
     """
     Analyzes the provided text for grammar, punctuation, sentence correctness,
     tone, active/passive voice, and inclusive pronoun suggestions.
 
     Args:
         payload (AnalyzeInput): The request body containing the text to be analyzed.
-        request (Request): The FastAPI Request object (dependency injected for API key verification).
+        (dependencies=[Depends(verify_api_key)]): Ensures the API key is verified before execution.
 
     Returns:
-        dict: A dictionary containing various analysis results.
+        dict: A dictionary containing various analysis results structured as per requirements.
     """
     text = payload.text
 
@@ -42,11 +53,11 @@ def analyze_text(payload: AnalyzeInput, request: Request = Depends(verify_api_ke
     # Get the grammatically corrected version of the original text.
     corrected_grammar = models.run_grammar_correction(text)
     
+    grammar_changes = []
     # Use difflib to find differences between the original and corrected text.
-    # difflib.SequenceMatcher compares sequences and can identify insertions, deletions, and substitutions.
+    # We split by words to get word-level diffs, which are easier to interpret.
     s = difflib.SequenceMatcher(None, text.split(), corrected_grammar.split())
     
-    grammar_changes = []
     # Iterate through the operations (opcodes) generated by SequenceMatcher.
     # 'equal', 'replace', 'delete', 'insert' are the types of operations.
     for opcode, i1, i2, j1, j2 in s.get_opcodes():
@@ -72,7 +83,7 @@ def analyze_text(payload: AnalyzeInput, request: Request = Depends(verify_api_ke
     sentence_correctness_feedback = []
     
     for m in matches:
-        # Check if the rule ID contains "PUNCTUATION" to categorize it.
+        # Check if the rule ID (from LanguageTool) contains "PUNCTUATION" to categorize it.
         if 'PUNCTUATION' in m.ruleId.upper():
             punctuation_issues.append(m.message)
         else:
@@ -80,36 +91,41 @@ def analyze_text(payload: AnalyzeInput, request: Request = Depends(verify_api_ke
             sentence_correctness_feedback.append(m.message)
 
     # --- 4. Tone Detection and Suggestion ---
-    # Classify the tone of the original text using the fine-tuned model.
+    # Classify the tone of the original text using the fine-tuned emotion classifier.
     detected_tone = models.classify_tone(text)
     
     tone_suggestion_text = ""
     # Provide a simple tone suggestion based on the detected tone.
-    # This logic can be expanded for more sophisticated suggestions.
-    if detected_tone in ["neutral", "joy"]: # Example condition for suggesting a formal tone
+    # This logic can be expanded for more sophisticated suggestions based on context or user goals.
+    if detected_tone in ["neutral", "joy"]: # Example: if text is neutral or joyful, suggest a formal alternative
         # Generate a formal tone version using FLAN-T5.
         tone_suggestion_text = models.run_flan_prompt(prompts.tone_prompt(text, "formal"))
+    elif detected_tone == "anger":
+        tone_suggestion_text = models.run_flan_prompt(prompts.tone_prompt(text, "calm and professional"))
+    elif detected_tone == "sadness":
+        tone_suggestion_text = models.run_flan_prompt(prompts.tone_prompt(text, "more uplifting"))
     else:
+        # If no specific suggestion, indicate that the detected tone is generally fine.
         tone_suggestion_text = f"The detected tone '{detected_tone}' seems appropriate for general communication."
 
 
     # --- 5. Active/Passive Voice Detection and Suggestion ---
-    doc = nlp(text) # Process the text with spaCy
+    doc = nlp(text) # Process the text with spaCy for linguistic analysis
     voice_detected = "active"
-    voice_suggestion = "None \u2014 active voice is fine here." # Using Unicode em dash
+    voice_suggestion = "None \u2014 active voice is fine here." # Using Unicode em dash for better readability
 
-    # Iterate through tokens to find passive auxiliary verbs (e.g., "is", "was" in passive constructions).
-    # A simple heuristic: if any token's dependency is 'auxpass', it's likely passive.
+    # Iterate through tokens to find passive auxiliary verbs (e.g., "is", "was", "been" when followed by a past participle).
+    # A simple heuristic: if any token's dependency is 'auxpass', it's likely part of a passive construction.
     for token in doc:
         if token.dep_ == "auxpass":
             voice_detected = "passive"
-            # If passive, ask FLAN-T5 to rewrite it in active voice.
+            # If passive voice is detected, ask FLAN-T5 to rewrite it in active voice.
             better_voice_prompt = prompts.active_voice_prompt(text)
             voice_suggestion = models.run_flan_prompt(better_voice_prompt)
-            break # Exit loop once passive voice is detected
+            break # Exit loop once passive voice is detected, no need to check further
 
     # --- 6. Inclusive Pronoun Suggestion ---
-    # Use FLAN-T5 with a specific prompt to suggest inclusive language.
+    # Use FLAN-T5 with a specific prompt to suggest more inclusive language.
     inclusive_pronouns_suggestion = models.run_flan_prompt(prompts.pronoun_friendly_prompt(text))
 
     # --- Construct the final response matching the example output structure ---