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; solve this using a temporary file.
+            # textract requires a file name; save the file temporarily.
             with tempfile.NamedTemporaryFile(delete=False, suffix=".doc") as tmp:
                 tmp.write(file_obj.read())
                 tmp.flush()
@@ -40,7 +40,6 @@ def extract_text_from_file(file_obj):
                 pass
     else:
         text = "Unsupported file type."
-
     return text
 
 #####################################
@@ -48,10 +47,10 @@ def extract_text_from_file(file_obj):
 #####################################
 def extract_basic_resume_info(text):
     """
-    Parse the extracted text to summarize basic info:
+    Parse the extracted text to extract/summarize:
     - Name
     - Age
-    - Job Experience (years or descriptive)
+    - Job Experience (capturing the block under the "experience" section)
     - Skills
     - Education
 
@@ -65,44 +64,50 @@ def extract_basic_resume_info(text):
         "Education": None,
     }
 
-    # Extract Name (e.g., "Name: John Doe")
-    name_match = re.search(r"[Nn]ame[:\-]\s*([A-Za-z\s]+)", text)
+    # Extract Name (e.g., "Name: John Doe" or from heuristics)
+    name_match = re.search(r"[Nn]ame[:\-]\s*([A-Za-z\s,]+)", text)
     if name_match:
         info["Name"] = name_match.group(1).strip()
     else:
-        # Fallback: heuristic, assume the first two or three capitalized words are the candidate name.
+        # Heuristic: Assume the first line or a line with two or three capitalized words is the candidate's 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]
 
     # Extract Age (e.g., "Age: 28")
-    age_match = re.search(r"[Aa]ge[:\-]\s*(\d{1,2})", text)
+    age_match = re.search(r"[Aa]ge[:\-]\s*(\d{1,3})", text)
     if age_match:
         info["Age"] = age_match.group(1)
-        
-    # 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["Job Experience"] = f"{exp_match.group(1)} {exp_match.group(2)}"
+
+    # Extract Job Experience using the "experience" section.
+    # This regex captures everything after the word "experience" until the next section heading (e.g., "additional information" or "skills")
+    experience_match = re.search(r"experience\s*(.*?)(?:\n\s*\n|additional information|$)", text, re.IGNORECASE | re.DOTALL)
+    if experience_match:
+        # Clean up the extracted block by removing any extra whitespace or newlines.
+        job_experience = experience_match.group(1).strip()
+        info["Job Experience"] = " ".join(job_experience.split())
     else:
-        # 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["Job Experience"] = exp_line.group(2).strip()
+        # Fallback if a labeled section isn't found.
+        exp_match = re.search(r"(\d+)\s+(years|yrs)\s+(?:of\s+)?experience", text, re.IGNORECASE)
+        if exp_match:
+            info["Job Experience"] = f"{exp_match.group(1)} {exp_match.group(2)}"
 
     # 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)
+
+    # Extract Education (e.g., "Education: ...")
+    edu_match = re.search(r"education\s*(.*?)(?:\n\s*\n|experience|$)", text, re.IGNORECASE | re.DOTALL)
     if edu_match:
-        edu_str = edu_match.group(1).strip()
-        info["Education"] = edu_str.rstrip(".")
+        education_block = edu_match.group(1).strip()
+        info["Education"] = " ".join(education_block.split())
+    else:
+        # Fallback: search for lines starting with common degree words.
+        edu_match = re.search(r"(Bachelor|Master|B\.Sc|M\.Sc|Ph\.D)[^\n]+", text)
+        if edu_match:
+            info["Education"] = edu_match.group(0)
 
     return info
 
@@ -111,7 +116,7 @@ def extract_basic_resume_info(text):
 #####################################
 def summarize_basic_info(info):
     """
-    Combine the extracted basic resume information into a cohesive paragraph.
+    Combine the extracted resume elements into a concise summary paragraph.
     """
     parts = []
 
@@ -124,13 +129,13 @@ def summarize_basic_info(info):
         parts.append(f"aged {info['Age']}")
     
     if info.get("Job Experience"):
-        parts.append(f"with {info['Job Experience']} of work experience")
+        parts.append(f"with job experience: {info['Job 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']}")
+        parts.append(f"and educated in {info['Education']}")
     
     summary_paragraph = ", ".join(parts) + "."
     return summary_paragraph
@@ -145,7 +150,7 @@ def process_resume(file_obj):
     resume_text = extract_text_from_file(file_obj)
     # Extract basic info from the text.
     basic_info = extract_basic_resume_info(resume_text)
-    # Create a summary paragraph from the extracted info.
+    # Create a summary paragraph from the basic info.
     summary_paragraph = summarize_basic_info(basic_info)
     return resume_text, summary_paragraph
 
@@ -154,8 +159,8 @@ def process_resume(file_obj):
 #####################################
 st.title("Resume Basic Information Summary")
 st.markdown("""
-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.
+Upload your resume file in **.doc** or **.docx** format. The app extracts key details such as name, age, job experience, skills, 
+and education, then summarizes them into a single paragraph.
 """)
 
 uploaded_file = st.file_uploader("Upload Resume", type=["doc", "docx"])
@@ -167,7 +172,7 @@ if st.button("Process Resume"):
         with st.spinner("Processing resume..."):
             resume_text, summary_paragraph = process_resume(uploaded_file)
 
-        st.subheader("Summary of Basic Information")
+        st.subheader("Summary Paragraph")
         st.markdown(summary_paragraph)
 
         st.subheader("Full Extracted Resume Text")