Update process_interview.py

process_interview.py

@@ -35,7 +35,15 @@ import spacy
 import google.generativeai as genai
 import joblib
 from concurrent.futures import ThreadPoolExecutor
-
+# --- Imports to ensure are present at the top of process_interview.py ---
+from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer, Table, TableStyle, PageBreak, Image
+from reportlab.lib.pagesizes import letter
+from reportlab.lib.styles import getSampleStyleSheet, ParagraphStyle
+from reportlab.lib.units import inch
+from reportlab.lib import colors
+import time
+import re
+import io
 # Setup logging
 logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
@@ -495,69 +503,75 @@ def generate_report(analysis_data: Dict) -> str:
         return f"Error generating report: {str(e)}"
 
 
+
+# --- NEW, ENHANCED PDF GENERATION FUNCTION ---
 def create_pdf_report(analysis_data: Dict, output_path: str, gemini_report_text: str):
     try:
-        doc = SimpleDocTemplate(output_path, pagesize=letter)
+        doc = SimpleDocTemplate(output_path, pagesize=letter,
+                                rightMargin=inch/2, leftMargin=inch/2,
+                                topMargin=inch, bottomMargin=inch/2)
+
         styles = getSampleStyleSheet()
-        h1 = ParagraphStyle(name='Heading1', parent=styles['h1'], fontSize=16, spaceAfter=14, alignment=1, textColor=colors.HexColor('#003366'))
-        h2 = ParagraphStyle(name='Heading2', parent=styles['h2'], fontSize=12, spaceBefore=10, spaceAfter=8, textColor=colors.HexColor('#336699'))
-        h3 = ParagraphStyle(name='Heading3', parent=styles['h3'], fontSize=10, spaceBefore=8, spaceAfter=4, textColor=colors.HexColor('#0055AA'))
-        body_text = ParagraphStyle(name='BodyText', parent=styles['Normal'], fontSize=9, leading=12, spaceAfter=4)
+        styles.add(ParagraphStyle(name='Justify', alignment=4)) # TA_JUSTIFY = 4
+        h1 = ParagraphStyle(name='Heading1', fontSize=18, leading=22, spaceAfter=20, alignment=1, textColor=colors.HexColor('#003366'))
+        h2 = ParagraphStyle(name='Heading2', fontSize=14, leading=18, spaceBefore=12, spaceAfter=10, textColor=colors.HexColor('#336699'))
+        body_text = ParagraphStyle(name='BodyText', parent=styles['Normal'], spaceAfter=6)
         bullet_style = ParagraphStyle(name='Bullet', parent=body_text, leftIndent=18, bulletIndent=9)
+
         story = []
-        story.append(Paragraph(f"<b>EvalBot Interview Analysis Report</b>", h1))
-        story.append(Spacer(1, 0.2 * inch))
-        story.append(Paragraph(f"<b>Date:</b> {time.strftime('%Y-%m-%d')}", body_text))
+
+        # --- Header and Footer ---
+        def header_footer(canvas, doc):
+            canvas.saveState()
+            # Footer
+            canvas.setFont('Helvetica', 9)
+            canvas.drawString(inch, 0.5 * inch, f"Page {doc.page} | EvalBot Analysis")
+            # Header line
+            canvas.setStrokeColorRGB(0, 0.2, 0.4)
+            canvas.setLineWidth(1)
+            canvas.line(doc.leftMargin, doc.height + doc.topMargin - inch/2, doc.width + doc.leftMargin, doc.height + doc.topMargin - inch/2)
+            canvas.restoreState()
+
+        # --- First Page: Summary ---
+        story.append(Paragraph("EvalBot Interview Analysis Report", h1))
+        story.append(Spacer(1, 0.1 * inch))
+        story.append(Paragraph(f"Analysis Date: {time.strftime('%Y-%m-%d')}", styles['Normal']))
         story.append(Spacer(1, 0.3 * inch))
+
         acceptance_prob = analysis_data.get('acceptance_probability')
         if acceptance_prob is not None:
-            story.append(Paragraph("<b>Candidate Evaluation Summary</b>", h2))
-            story.append(Spacer(1, 0.1 * inch))
+            story.append(Paragraph("Candidate Evaluation Summary", h2))
             prob_color = colors.green if acceptance_prob >= 70 else (colors.orange if acceptance_prob >= 40 else colors.red)
-            story.append(Paragraph(f"<font size='12' color='{prob_color.hexval()}'><b>Estimated Acceptance Probability: {acceptance_prob:.2f}%</b></font>", ParagraphStyle(name='AcceptanceProbability', parent=styles['Normal'], fontSize=12, spaceAfter=10, alignment=1)))
-            if acceptance_prob >= 80: story.append(Paragraph("This indicates a very strong candidate with high potential. Well done!", body_text))
-            elif acceptance_prob >= 50: story.append(Paragraph("This candidate shows solid potential but has areas for improvement.", body_text))
-            else: story.append(Paragraph("This candidate may require significant development or may not be an ideal fit.", body_text))
-            story.append(Spacer(1, 0.3 * inch))
-        
-        sections = {}
-        current_section = None
-        section_patterns = {
-            r'^\s*\*\*\s*1\.\s*Executive Summary\s*\*\*': 'Executive Summary',
-            r'^\s*\*\*\s*2\.\s*Voice Analysis Insights\s*\*\*': 'Voice Analysis Insights',
-            r'^\s*\*\*\s*3\.\s*Content Analysis & Strengths/Areas for Development\s*\*\*': 'Content Analysis',
-            r'^\s*\*\*\s*4\.\s*Actionable Recommendations\s*\*\*': 'Recommendations'
-        }
-        for line in gemini_report_text.split('\n'):
-            matched_section = False
-            for pattern, section_name in section_patterns.items():
-                if re.match(pattern, line):
-                    current_section = section_name
-                    sections[current_section] = []
-                    matched_section = True
-                    break
-            if not matched_section and current_section:
-                sections[current_section].append(line)
-        
-        story.append(PageBreak()) # Start detailed report on a new page
+            story.append(Paragraph(f"<font size=14>Estimated Acceptance Probability: <b><font color='{prob_color.hexval()}'>{acceptance_prob:.2f}%</font></b></font>",
+                                 ParagraphStyle(name='Prob', fontSize=12, spaceAfter=10)))
+            if acceptance_prob >= 80:
+                story.append(Paragraph("This indicates a very strong candidate with high potential.", body_text))
+            elif acceptance_prob >= 50:
+                story.append(Paragraph("This candidate shows solid potential with areas for improvement.", body_text))
+            else:
+                story.append(Paragraph("This candidate may require significant development or may not be an ideal fit.", body_text))
         
-        story.append(Paragraph("<b>1. Detailed Voice Analysis</b>", h2))
+        story.append(PageBreak())
+
+        # --- Second Page and beyond: Detailed Analysis ---
+        story.append(Paragraph("1. Detailed Voice Analysis", h2))
         voice_analysis = analysis_data.get('voice_analysis', {})
         if voice_analysis and 'error' not in voice_analysis:
+            # Table for voice metrics
             table_data = [
                 ['Metric', 'Value', 'Interpretation'],
-                ['Speaking Rate', f"{voice_analysis['speaking_rate']:.2f} words/sec", 'Average rate'],
-                ['Filler Words', f"{voice_analysis['filler_ratio'] * 100:.1f}%", '% of total words'],
-                ['Repetition Score', f"{voice_analysis['repetition_score']:.3f}", 'Lower is better'],
-                ['Anxiety Level', voice_analysis['interpretation']['anxiety_level'].upper(), f"Score: {voice_analysis['composite_scores']['anxiety']:.3f}"],
-                ['Confidence Level', voice_analysis['interpretation']['confidence_level'].upper(), f"Score: {voice_analysis['composite_scores']['confidence']:.3f}"],
-                ['Fluency', voice_analysis['interpretation']['fluency_level'].upper(), 'Overall speech flow']
+                ['Speaking Rate', f"{voice_analysis.get('speaking_rate', 0):.2f} words/sec", 'Average rate'],
+                ['Filler Words', f"{voice_analysis.get('filler_ratio', 0) * 100:.1f}%", '% of total words'],
+                ['Anxiety Level', voice_analysis.get('interpretation', {}).get('anxiety_level', 'N/A').upper(), f"Score: {voice_analysis.get('composite_scores', {}).get('anxiety', 0):.3f}"],
+                ['Confidence Level', voice_analysis.get('interpretation', {}).get('confidence_level', 'N/A').upper(), f"Score: {voice_analysis.get('composite_scores', {}).get('confidence', 0):.3f}"],
+                ['Fluency', voice_analysis.get('interpretation', {}).get('fluency_level', 'N/A').upper(), 'Overall speech flow']
             ]
             table = Table(table_data, colWidths=[1.5*inch, 1.5*inch, 3*inch])
             table.setStyle(TableStyle([
                 ('BACKGROUND', (0,0), (-1,0), colors.HexColor('#4682B4')),
                 ('TEXTCOLOR',(0,0),(-1,0),colors.whitesmoke),
                 ('ALIGN', (0,0), (-1,-1), 'CENTER'),
+                ('VALIGN', (0,0), (-1,-1), 'MIDDLE'),
                 ('FONTNAME', (0, 0), (-1, 0), 'Helvetica-Bold'),
                 ('BOTTOMPADDING', (0, 0), (-1, 0), 12),
                 ('BACKGROUND', (0, 1), (-1, -1), colors.HexColor('#F0F8FF')),
@@ -566,31 +580,78 @@ def create_pdf_report(analysis_data: Dict, output_path: str, gemini_report_text:
             story.append(table)
             story.append(Spacer(1, 0.2 * inch))
 
+            # Chart generation
             chart_buffer = io.BytesIO()
-            generate_anxiety_confidence_chart(voice_analysis['composite_scores'], chart_buffer)
+            generate_anxiety_confidence_chart(voice_analysis.get('composite_scores', {}), chart_buffer)
             chart_buffer.seek(0)
             img = Image(chart_buffer, width=4*inch, height=2.5*inch)
             story.append(img)
         else:
-            story.append(Paragraph("Voice analysis not available.", body_text))
+            story.append(Paragraph("Voice analysis data not available.", body_text))
 
         story.append(PageBreak())
-        
-        for section_title, key in [("2. Content Analysis", "Content Analysis"), ("3. Recommendations", "Recommendations")]:
-            story.append(Paragraph(f"<b>{section_title}</b>", h2))
-            if key in sections:
-                for line in sections[key]:
-                    if line.strip():
-                        story.append(Paragraph(line.strip().lstrip('-').strip(), bullet_style if line.strip().startswith('-') else body_text))
-            story.append(Spacer(1, 0.2*inch))
-        
-        doc.build(story)
+
+        # --- Parse and display Gemini report sections ---
+        sections = {}
+        current_section = None
+        # Simplified patterns to find sections
+        section_patterns = {
+            'Executive Summary': r'executive summary',
+            'Voice Analysis Insights': r'voice analysis insights',
+            'Content Analysis & Strengths/Areas for Development': r'content analysis|strengths/areas for development',
+            'Actionable Recommendations': r'actionable recommendations'
+        }
+        # Pre-populate sections to maintain order
+        for name in section_patterns.keys():
+            sections[name] = []
+
+        # Parse text into sections based on keywords
+        for line in gemini_report_text.split('\n'):
+            line_lower = line.lower()
+            matched = False
+            for name, pattern in section_patterns.items():
+                if re.search(pattern, line_lower):
+                    current_section = name
+                    matched = True
+                    break
+            if not matched and current_section:
+                sections[current_section].append(line)
+
+        # Display Content Analysis and Recommendations
+        story.append(Paragraph("2. Content Analysis", h2))
+        if sections['Content Analysis & Strengths/Areas for Development']:
+            for line in sections['Content Analysis & Strengths/Areas for Development']:
+                line = line.strip()
+                if not line: continue
+                if line.startswith(('-', '•', '*')):
+                    story.append(Paragraph(line.lstrip('-•* ').strip(), bullet_style))
+                else:
+                    story.append(Paragraph(line, body_text))
+        else:
+            story.append(Paragraph("Content analysis not provided in the report.", body_text))
+
+        story.append(Spacer(1, 0.2*inch))
+
+        story.append(Paragraph("3. Recommendations", h2))
+        if sections['Actionable Recommendations']:
+            for line in sections['Actionable Recommendations']:
+                line = line.strip()
+                if not line: continue
+                if line.startswith(('-', '•', '*')):
+                    story.append(Paragraph(line.lstrip('-•* ').strip(), bullet_style))
+                else:
+                    story.append(Paragraph(line, body_text))
+        else:
+            story.append(Paragraph("Recommendations not provided in the report.", body_text))
+
+        doc.build(story, onFirstPage=header_footer, onLaterPages=header_footer)
         return True
     except Exception as e:
-        logger.error(f"PDF creation failed: {str(e)}", exc_info=True)
+        logger.error(f"Enhanced PDF creation failed: {str(e)}", exc_info=True)
         return False
 
 
+
 def convert_to_serializable(obj):
     if isinstance(obj, np.generic): return obj.item()
     if isinstance(obj, dict): return {k: convert_to_serializable(v) for k, v in obj.items()}