Update app.py

app.py

@@ -25,7 +25,7 @@ def extract_text_from_file(file_obj):
             text = f"Error processing DOCX file: {e}"
     elif ext == ".doc":
         try:
-            # textract requires a filename, so create a temporary file.
+            # textract requires a filename; solve this using a temporary file.
             with tempfile.NamedTemporaryFile(delete=False, suffix=".doc") as tmp:
                 tmp.write(file_obj.read())
                 tmp.flush()
@@ -51,15 +51,18 @@ def extract_basic_resume_info(text):
     Parse the extracted text to summarize basic info:
     - Name
     - Age
-    - Work Experience
-    - Expected Industry/Direction
-    Returns a dictionary of extracted data.
+    - Job Experience (years or descriptive)
+    - Skills
+    - Education
+
+    Returns a dictionary with the extracted elements.
     """
     info = {
         "Name": None,
         "Age": None,
-        "Work Experience": None,
-        "Expected Industry/Direction": None,
+        "Job Experience": None,
+        "Skills": None,
+        "Education": None,
     }
 
     # Extract Name (e.g., "Name: John Doe")
@@ -67,7 +70,7 @@ def extract_basic_resume_info(text):
     if name_match:
         info["Name"] = name_match.group(1).strip()
     else:
-        # Heuristic: search for a line with two or three capitalized words.
+        # Fallback: heuristic, assume the first two or three capitalized words are the candidate name.
         potential_names = re.findall(r"\b[A-Z][a-z]+(?:\s+[A-Z][a-z]+){1,2}\b", text)
         if potential_names:
             info["Name"] = potential_names[0]
@@ -76,21 +79,30 @@ def extract_basic_resume_info(text):
     age_match = re.search(r"[Aa]ge[:\-]\s*(\d{1,2})", text)
     if age_match:
         info["Age"] = age_match.group(1)
-
-    # Extract Work Experience (e.g., "5 years of experience")
+        
+    # Extract Job Experience (e.g., "5 years of experience")
     exp_match = re.search(r"(\d+)\s+(years|yrs)\s+(?:of\s+)?experience", text, re.IGNORECASE)
     if exp_match:
-        info["Work Experience"] = f"{exp_match.group(1)} {exp_match.group(2)}"
+        info["Job Experience"] = f"{exp_match.group(1)} {exp_match.group(2)}"
     else:
-        # Fallback: look for overall experience information.
-        exp_line = re.search(r"(Experience|Background)[:\-]\s*(.*)", text, re.IGNORECASE)
+        # Attempt to capture a descriptive work experience line via a labeled section.
+        exp_line = re.search(r"(Experience|Work History)[:\-]\s*(.+)", text, re.IGNORECASE)
         if exp_line:
-            info["Work Experience"] = exp_line.group(2).strip()
-
-    # Extract Expected Industry/Direction
-    industry_match = re.search(r"(Industry|Interest|Direction)[:\-]\s*(.+)", text, re.IGNORECASE)
-    if industry_match:
-        info["Expected Industry/Direction"] = industry_match.group(2).strip()
+            info["Job Experience"] = exp_line.group(2).strip()
+
+    # Extract Skills (e.g., "Skills: Python, Java, SQL")
+    # This is a simple pattern and might require refinement for your resume formats.
+    skills_match = re.search(r"(Skills|Technical Skills)[:\-]\s*(.+)", text, re.IGNORECASE)
+    if skills_match:
+        # Cleanup skills by removing any trailing or extra characters.
+        skills_str = skills_match.group(2).strip()
+        info["Skills"] = skills_str.rstrip(".")
+        
+    # Extract Education (e.g., "Education: B.Sc in Computer Science")
+    edu_match = re.search(r"Education[:\-]\s*(.+)", text, re.IGNORECASE)
+    if edu_match:
+        edu_str = edu_match.group(1).strip()
+        info["Education"] = edu_str.rstrip(".")
 
     return info
 
@@ -99,22 +111,28 @@ def extract_basic_resume_info(text):
 #####################################
 def summarize_basic_info(info):
     """
-    Create a paragraph summary from the basic resume information.
+    Combine the extracted basic resume information into a cohesive paragraph.
     """
     parts = []
+
     if info.get("Name"):
-        parts.append(f"{info['Name']}")
+        parts.append(f"Candidate {info['Name']}")
+    else:
+        parts.append("The candidate")
+    
     if info.get("Age"):
         parts.append(f"aged {info['Age']}")
-    if info.get("Work Experience"):
-        parts.append(f"with {info['Work Experience']} of work experience")
-    if info.get("Expected Industry/Direction"):
-        parts.append(f"seeking opportunities in {info['Expected Industry/Direction']}")
-
-    if parts:
-        summary_paragraph = "The candidate is " + ", ".join(parts) + "."
-    else:
-        summary_paragraph = "Basic information could not be extracted from the resume."
+    
+    if info.get("Job Experience"):
+        parts.append(f"with {info['Job Experience']} of work experience")
+    
+    if info.get("Skills"):
+        parts.append(f"skilled in {info['Skills']}")
+    
+    if info.get("Education"):
+        parts.append(f"and educated with a background in {info['Education']}")
+    
+    summary_paragraph = ", ".join(parts) + "."
     return summary_paragraph
 
 #####################################
@@ -123,22 +141,21 @@ def summarize_basic_info(info):
 def process_resume(file_obj):
     if file_obj is None:
         return None, None
-    
-    # Extract text content from the file.
+    # Extract the full resume text.
     resume_text = extract_text_from_file(file_obj)
-    # Extract and summarize basic info.
+    # Extract basic info from the text.
     basic_info = extract_basic_resume_info(resume_text)
+    # Create a summary paragraph from the extracted info.
     summary_paragraph = summarize_basic_info(basic_info)
-    
     return resume_text, summary_paragraph
 
 #####################################
 # Streamlit Interface
 #####################################
-st.title("Resume Basic Info Summary")
+st.title("Resume Basic Information Summary")
 st.markdown("""
-Upload your resume file in **.doc** or **.docx** format. The app will extract the content and generate a summary paragraph
-that highlights the candidate's basic information (name, age, work experience, and expected industry/direction).
+Upload your resume file in **.doc** or **.docx** format. The app will extract the document's content and generate a summary paragraph
+highlighting the candidate’s name, age, job experience, skills, and education.
 """)
 
 uploaded_file = st.file_uploader("Upload Resume", type=["doc", "docx"])
@@ -151,4 +168,7 @@ if st.button("Process Resume"):
             resume_text, summary_paragraph = process_resume(uploaded_file)
 
         st.subheader("Summary of Basic Information")
-        st.markdown(summary_paragraph)
+        st.markdown(summary_paragraph)
+
+        st.subheader("Full Extracted Resume Text")
+        st.text_area("", resume_text, height=300)