Enhance CV parsing functionality in app.py by expanding section header patterns to include more variations and improving line cleaning. Implement a more robust categorization process for unstructured content, extracting contact information, education, experience, and skills based on keywords. Additionally, update text extraction from DOCX files to include table content, ensuring comprehensive CV data retrieval. This change improves the accuracy and completeness of CV parsing, contributing to better email generation based on user inputs.

app.py

@@ -18,32 +18,71 @@ def parse_cv_sections(text: str) -> Dict[str, str]:
         'projects': '',
     }
     
-    # Common section headers in CVs
+    # Common section headers in CVs with more variations
     section_patterns = {
-        'contact': r'(?i)(contact|personal\s+information|profile)',
-        'education': r'(?i)(education|academic|qualification)',
-        'experience': r'(?i)(experience|work|employment|professional)',
-        'skills': r'(?i)(skills|technical skills|competencies)',
-        'projects': r'(?i)(projects|personal projects)',
+        'contact': r'(?i)(contact|personal\s+information|profile|contact\s+details|about\s+me)',
+        'education': r'(?i)(education|academic|qualification|academic\s+background|educational\s+background)',
+        'experience': r'(?i)(experience|work|employment|professional|work\s+history|career|professional\s+experience)',
+        'skills': r'(?i)(skills|technical\s+skills|competencies|expertise|technologies|tools|programming|languages)',
+        'projects': r'(?i)(projects|personal\s+projects|portfolio|work\s+samples)',
     }
     
-    # Split text into lines
-    lines = text.split('\n')
+    # Split text into lines and clean
+    lines = [line.strip() for line in text.split('\n') if line.strip()]
     current_section = None
+    section_content = []
     
-    for line in lines:
-        line = line.strip()
-        if not line:
-            continue
-            
+    # First pass: identify sections
+    for i, line in enumerate(lines):
         # Check if line is a section header
         for section, pattern in section_patterns.items():
             if re.search(pattern, line, re.IGNORECASE):
+                # If we found a section header
+                if current_section:
+                    # Save previous section content
+                    sections[current_section] = '\n'.join(section_content)
                 current_section = section
+                section_content = []
                 break
-                
-        if current_section and line:
-            sections[current_section] += line + '\n'
+        else:
+            # If line is not a header and we have a current section, add to content
+            if current_section:
+                section_content.append(line)
+    
+    # Save the last section
+    if current_section and section_content:
+        sections[current_section] = '\n'.join(section_content)
+    
+    # If no sections were found, try to categorize the content
+    if all(not content for content in sections.values()):
+        lines_text = '\n'.join(lines)
+        
+        # Look for email addresses and phone numbers for contact
+        email_pattern = r'[\w\.-]+@[\w\.-]+'
+        phone_pattern = r'[\+\d]?(\d{2,3}[-\.\s]?){2}\d{4}'
+        
+        emails = re.findall(email_pattern, lines_text)
+        phones = re.findall(phone_pattern, lines_text)
+        if emails or phones:
+            sections['contact'] = '\n'.join(emails + phones)
+        
+        # Look for education keywords
+        edu_keywords = r'(?i)(university|college|school|degree|bachelor|master|phd|diploma)'
+        edu_lines = [l for l in lines if re.search(edu_keywords, l)]
+        if edu_lines:
+            sections['education'] = '\n'.join(edu_lines)
+        
+        # Look for experience keywords
+        exp_keywords = r'(?i)(worked|developer|engineer|manager|consultant|analyst)'
+        exp_lines = [l for l in lines if re.search(exp_keywords, l)]
+        if exp_lines:
+            sections['experience'] = '\n'.join(exp_lines)
+        
+        # Look for skills
+        skill_keywords = r'(?i)(python|java|javascript|react|node|sql|aws|docker|kubernetes|git)'
+        skill_lines = [l for l in lines if re.search(skill_keywords, l)]
+        if skill_lines:
+            sections['skills'] = '\n'.join(skill_lines)
     
     return sections
 
@@ -59,17 +98,27 @@ def extract_cv_text(file):
         if file_ext == '.pdf':
             reader = PdfReader(file)
             for page in reader.pages:
-                text += page.extract_text()
+                text += page.extract_text() + "\n"
         
         elif file_ext == '.docx':
             doc = docx.Document(file)
             for paragraph in doc.paragraphs:
-                text += paragraph.text + '\n'
+                text += paragraph.text + "\n"
+            # Also check tables in docx
+            for table in doc.tables:
+                for row in table.rows:
+                    for cell in row.cells:
+                        text += cell.text + "\n"
         else:
             return "Unsupported file format. Please upload PDF or DOCX files."
         
         # Parse the CV into sections
         sections = parse_cv_sections(text)
+        
+        # Verify that we have content
+        if all(not content.strip() for content in sections.values()):
+            return f"Could not parse CV sections. Raw text:\n{text}"
+            
         return sections
         
     except Exception as e: