Update app.py

app.py

@@ -788,6 +788,8 @@ def format_esco_card(esco_data):
     return f"<div class='esco-container'>{card}</div>"    
 
 # ================= Process Analysis =================
+import tempfile
+import json
 from concurrent.futures import ThreadPoolExecutor
 
 def process_pdf(file):
@@ -802,7 +804,8 @@ def process_pdf(file):
             [],
             {},
             {},
-            "No file uploaded."
+            "No file uploaded.",
+            None  # JSON path
         )
 
     try:
@@ -820,19 +823,18 @@ def process_pdf(file):
                 [],
                 {},
                 {},
-                "No responsibilities section found."
+                "No responsibilities section found.",
+                None  # JSON path
             )
 
         # Use ThreadPoolExecutor to parallelize independent tasks
         with ThreadPoolExecutor() as executor:
-            # Submit tasks to the executor
             job_family_future = executor.submit(classify_job_family, responsibilities)
             occ_group_future = executor.submit(classify_occupational_group_by_level, responsibilities)
             esco_occ_future = executor.submit(classify_esco_by_hierarchical_level, responsibilities)
             qualification_future = executor.submit(extract_qualification, responsibilities)
             skills_future = executor.submit(extract_skills, responsibilities)
 
-            # Retrieve results from futures
             job_family = job_family_future.result()
             occ_group = occ_group_future.result()
             esco_occ = esco_occ_future.result()
@@ -850,8 +852,6 @@ def process_pdf(file):
             Level_5_code = esco_occ["Level_5_ESCO_code"]
             skill_esco_extract = review_skills(Level_5_code)
             skill_esco_map = map_proficiency_and_assessment(skill_esco_extract, responsibilities)
-        else:
-            log_debug(f"No Level 5 ESCO code found for {os.path.basename(file.name)}, skipping ESCO skills mapping")
 
         time.sleep(6)
         assessment_lookup = {item['skill_name']: item for item in skill_map}
@@ -870,66 +870,62 @@ def process_pdf(file):
             for skill in skills
         ]
 
-        # Format skills before returning
-        formatted_skills = format_skill_cards(joined_skills)
-        
-        
-        joined_skills_esco = []
-        if has_esco and skill_esco_extract:
-            assessment_esco_lookup = {item['skill_name']: item for item in skill_esco_map}
-            joined_skills_esco = [
-                {
-                    "skill_name": skill["skill_name"],
-                    "skill_description": skill["skill_description"],
-                    "skill_code": skill["skill_code"],
-                    **assessment_esco_lookup.get(skill["skill_name"], {})
-                }
-                for skill in skill_esco_extract
-            ]
-        
-        interview = build_interview(responsibilities, skills)
+        # Prepare all data for JSON output
+        result_data = {
+            "file_name": os.path.basename(file.name),
+            "responsibilities": responsibilities,
+            "job_family": job_family,
+            "qualification": qualification,
+            "ccoq_levels": {f"Level_{i}_CCOG_{field}": occ_group.get(f"Level_{i}_CCOG_{field}")
+                          for i in range(1, 5) for field in ["code", "name", "desc"]},
+            "interview_questions": build_interview(responsibilities, skills),
+            "skills": joined_skills,
+            "esco_levels": {f"Level_{i}_ESCO_{field}": esco_occ.get(f"Level_{i}_ESCO_{field}")
+                          for i in range(1, 6) for field in ["code", "name", "desc"]},
+            "esco_skills": {
+                "skills": [
+                    {
+                        "skill_name": skill["skill_name"],
+                        "skill_description": skill["skill_description"],
+                        "skill_code": skill["skill_code"],
+                        **assessment_esco_lookup.get(skill["skill_name"], {})
+                    }
+                    for skill in (skill_esco_extract if has_esco else [])
+                ]
+            },
+            "processing_time": time.strftime("%Y-%m-%d %H:%M:%S")
+        }
 
-        # Prepare the results for each output component
-        ccoq_levels = {f"Level_{i}_CCOG_{field}": occ_group.get(f"Level_{i}_CCOG_{field}")
-                       for i in range(1, 5) for field in ["code", "name", "desc"]}
-        formatted_ccog = format_ccog_card(ccoq_levels)
-        
-        if has_esco:
-            esco_levels = {f"Level_{i}_ESCO_{field}": esco_occ.get(f"Level_{i}_ESCO_{field}")
-                           for i in range(1, 6) for field in ["code", "name", "desc"]}
-            esco_skills = {
-                "file": os.path.basename(file.name),
-                "classified_job_family": job_family,
-                "skills": joined_skills_esco
-            }
-        else:
-            esco_levels = {f"Level_{i}_ESCO_{field}": None
-                           for i in range(1, 6) for field in ["code", "name", "desc"]}
-            esco_skills = None
+        # Save to temporary JSON file
+        with tempfile.NamedTemporaryFile(suffix=".json", delete=False, mode='w') as f:
+            json.dump(result_data, f, indent=2)
+            json_path = f.name
+            log_debug(f"Results saved to temporary JSON file: {json_path}")
+
+        # Format outputs for display
+        formatted_skills = format_skill_cards(joined_skills)
+        formatted_ccog = format_ccog_card(result_data['ccoq_levels'])
+        formatted_esco_levels = format_esco_card(result_data['esco_levels'])
+        formatted_esco_skills = format_skill_cards(result_data['esco_skills'])
 
-        formatted_esco_levels = format_esco_card(esco_levels)
-        formatted_esco_skills = format_skill_cards(esco_skills)
-        
-        debug_message = "Processing completed successfully."
         return (
             os.path.basename(file.name),
             responsibilities,
             job_family,
             "\n".join(qualification),
-            #ccoq_levels,
             formatted_ccog,
-            "\n".join(interview),
-            #joined_skills,
+            "\n".join(result_data['interview_questions']),
             formatted_skills,
-           # esco_levels,
             formatted_esco_levels,
-            #esco_skills,
             formatted_esco_skills,
-            debug_message if DEBUG else None
+            "Processing completed successfully." if DEBUG else None,
+            json_path  # Return path to JSON file
         )
 
     except Exception as e:
         error_message = f"Error processing PDF: {str(e)}"
+        log_debug(error_message)
+        traceback.print_exc()
         return (
             error_message,
             "",
@@ -940,7 +936,8 @@ def process_pdf(file):
             [],
             {},
             {},
-            error_message
+            error_message,
+            None  # No JSON path on error
         )
 # ================= Build Word Report =================
 from docx import Document
@@ -1765,10 +1762,10 @@ progress::-webkit-progress-value {
     with gr.Row():
         with gr.Column():
             file_input = gr.File(
-                        label="Upload a Post Description PDF file", 
+                        label="Upload a Post Description PDF file - not a scanned file!!!", 
                         file_types=[".pdf"])
             submit_btn = gr.Button(
-                        value="✨ Analyse Post Description",
+                        value="✨ Analyse the Post Description - takes about 90 sec...",
                         variant="primary",
                         elem_classes="btn-primary"
             )
@@ -1858,7 +1855,7 @@ progress::-webkit-progress-value {
             esco_levels_output,
             esco_skills_output
         ],
-        outputs=gr.File(label="Download Word Document")
+        outputs=gr.File(label="Download the corresponding Word report")
     )
 
 if __name__ == "__main__":