Refactored input processing

functions/gradio.py

@@ -0,0 +1,119 @@
+"""
+gradio.py
+
+Functions for handling Gradio UI interactions and processing user inputs.
+"""
+
+import logging
+from functions.linkedin_resume import extract_text_from_linkedin_pdf
+from functions.github import get_github_repositories
+
+# Set up logging
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+
+def process_inputs(linkedin_pdf, github_url, job_post_text):
+    """
+    Process the input files and URLs from the Gradio interface.
+    
+    Args:
+        linkedin_pdf: Uploaded LinkedIn resume export PDF file
+        github_url (str): GitHub profile URL  
+        job_post_text (str): Job post text content
+    
+    Returns:
+        str: Formatted output with file and URL information
+    """
+    result = ""
+    logger.info("Processing user inputs from Gradio interface")
+    
+    # Process LinkedIn PDF file
+    if linkedin_pdf is not None:
+        result += "✅ LinkedIn Resume PDF uploaded\n"
+        logger.info(f"Processing LinkedIn PDF: {linkedin_pdf.name}")
+        
+        # Extract and structure text from the PDF
+        extraction_result = extract_text_from_linkedin_pdf(linkedin_pdf.name)
+        
+        if extraction_result["status"] == "success":
+            result += " ✅ Text extraction successful\n\n"
+            logger.info("LinkedIn PDF text extraction successful")
+
+        elif extraction_result["status"] == "warning":
+            result += f" ⚠️  Text extraction: {extraction_result['message']}\n\n"
+            logger.warning(f"LinkedIn PDF extraction warning: {extraction_result['message']}")
+        else:
+            result += f" ❌ Text extraction failed: {extraction_result['message']}\n\n"
+            logger.error(f"LinkedIn PDF extraction failed: {extraction_result['message']}")
+    else:
+        result += "❌ No LinkedIn resume PDF file uploaded\n\n"
+        logger.info("No LinkedIn PDF file provided")
+    
+    # Process GitHub profile
+    if github_url and github_url.strip():
+        result += "✅ GitHub Profile URL provided\n"
+        logger.info(f"Processing GitHub URL: {github_url}")
+        
+        # Retrieve repositories from GitHub
+        github_result = get_github_repositories(github_url)
+        
+        if github_result["status"] == "success":
+            result += "  ✅ GitHub list download successful\n\n"
+            logger.info(f"GitHub repositories retrieved successfully for {github_result['metadata']['username']}")
+            
+        else:
+            result += f"  ❌ GitHub extraction failed: {github_result['message']}\n\n"
+            logger.error(f"GitHub extraction failed: {github_result['message']}")
+    else:
+        result += "❌ No GitHub profile URL provided\n\n"
+        logger.info("No GitHub URL provided")
+    
+    # Process job post text
+    if job_post_text and job_post_text.strip():
+        result += "✅ Job post text provided\n"
+        logger.info(f"Job post text provided ({len(job_post_text)} characters)")
+    else:
+        result += "❌ Job post not provided\n"
+        logger.info("No job post text provided")
+
+    logger.info("Input processing completed")
+    return result
+
+
+def get_processed_data(linkedin_pdf, github_url, job_post_text):
+    """
+    Get structured data from all inputs for further processing.
+    
+    Args:
+        linkedin_pdf: Uploaded LinkedIn resume export PDF file
+        github_url (str): GitHub profile URL  
+        job_post_text (str): Job post text content
+    
+    Returns:
+        dict: Structured data containing all processed information
+    """
+    processed_data = {
+        "linkedin": None,
+        "github": None,
+        "job_post": job_post_text.strip() if job_post_text else None,
+        "errors": []
+    }
+    
+    # Process LinkedIn PDF
+    if linkedin_pdf is not None:
+        extraction_result = extract_text_from_linkedin_pdf(linkedin_pdf.name)
+        if extraction_result["status"] == "success":
+            processed_data["linkedin"] = extraction_result
+        else:
+            processed_data["errors"].append(f"LinkedIn: {extraction_result['message']}")
+    
+    # Process GitHub profile
+    if github_url and github_url.strip():
+        github_result = get_github_repositories(github_url)
+        if github_result["status"] == "success":
+            processed_data["github"] = github_result
+        else:
+            processed_data["errors"].append(f"GitHub: {github_result['message']}")
+    
+    return processed_data

resumate.py

@@ -6,72 +6,16 @@ A simple Gradio UI for collecting user profile and job post information.
 This app provides inputs for:
 - LinkedIn resume export PDF file upload
 - GitHub profile URL
-- LinkedIn job post URL
+- LinkedIn job post text
 
-Upon submission, the input values are displayed in the output box.
+Upon submission, the input values are processed and displayed in the output box.
 
 To run:
     python resumate.py
 """
 
 import gradio as gr
-from functions.linkedin_resume import extract_text_from_linkedin_pdf
-from functions.github import get_github_repositories
-
-
-def process_inputs(linkedin_pdf, github_url, job_post_text):
-    """
-    Process the input files and URLs.
-    
-    Args:
-        linkedin_pdf: Uploaded LinkedIn resume export PDF file
-        github_url (str): GitHub profile URL  
-        job_post_url (str): LinkedIn job post URL
-    
-    Returns:
-        str: Formatted output with file and URL information
-    """
-    result = ""
-    
-    # Process LinkedIn PDF file
-    if linkedin_pdf is not None:
-        result += "✅ LinkedIn Resume PDF uploaded\n"
-        
-        # Extract and structure text from the PDF
-        extraction_result = extract_text_from_linkedin_pdf(linkedin_pdf.name)
-        
-        if extraction_result["status"] == "success":
-            result += " ✅ Text extraction successful\n\n"
-
-        elif extraction_result["status"] == "warning":
-            result += f" ⚠️  Text extraction: {extraction_result['message']}\n\n"
-        else:
-            result += f" ❌ Text extraction failed: {extraction_result['message']}\n\n"
-    else:
-        result += "❌ No LinkedIn resume PDF file uploaded\n\n"
-    
-    # Process GitHub profile
-    if github_url and github_url.strip():
-        result += "✅ GitHub Profile URL provided\n"
-        
-        # Retrieve repositories from GitHub
-        github_result = get_github_repositories(github_url)
-        
-        if github_result["status"] == "success":
-            result += "  ✅ GitHub list download successful\n\n"
-            
-        else:
-            result += f"  ❌ GitHub extraction failed: {github_result['message']}\n\n"
-    else:
-        result += "❌ No GitHub profile URL provided\n\n"
-    
-    # Process other inputs
-    if job_post_text:
-        result += "✅ Job post text provided\n"
-    else:
-        result += f"❌ Job post not provided\n"
-
-    return result
+from functions.gradio import process_inputs
 
 
 with gr.Blocks() as demo: