Add __init__.py to output/ to fix import error and include output/ in repo

output/pdf_generator.py

@@ -0,0 +1,82 @@
+
+from reportlab.lib.pagesizes import letter
+from reportlab.pdfgen import canvas
+from reportlab.lib import colors
+from reportlab.platypus import SimpleDocTemplate, Table, TableStyle, Paragraph, Spacer
+from reportlab.lib.styles import getSampleStyleSheet
+from .output.pdf_generator import generate_pdf_report
+import io
+
+def generate_pdf_report(results):
+    """
+    Generates a PDF report from analysis results.
+    Args:
+        results: List of dictionaries containing analysis findings.
+    Returns:
+        bytes: PDF file content.
+    """
+    buffer = io.BytesIO()
+    doc = SimpleDocTemplate(buffer, pagesize=letter)
+    elements = []
+    
+    styles = getSampleStyleSheet()
+    title_style = styles['Title']
+    heading_style = styles['Heading2']
+    normal_style = styles['Normal']
+
+    # Title
+    elements.append(Paragraph("Semantic Integrity Analysis Report", title_style))
+    elements.append(Spacer(1, 12))
+
+    if not results:
+        elements.append(Paragraph("No integrity issues detected.", normal_style))
+    else:
+        # Summary
+        elements.append(Paragraph(f"Total Potential Issues Found: {len(results)}", normal_style))
+        elements.append(Spacer(1, 12))
+
+        # Table Header
+        data = [['S.No', 'Label', 'Loc', 'Reason']]
+        
+        # Table Data
+        for idx, r in enumerate(results):
+            # Text wrapping for table cells needs explicit Paragraph usage usually, 
+            # but for simplicity we truncate or just list them.
+            # To make it robust, we'll list details below the table or keep table simple.
+            row = [
+                str(idx + 1),
+                r.get('Label', 'N/A'),
+                r.get('Location 1', '').replace('Pg ', 'P').replace('Ln ', 'L'),
+                r.get('Reason', 'N/A')
+            ]
+            data.append(row)
+
+        # Create Table
+        t = Table(data, colWidths=[30, 90, 60, 320])
+        t.setStyle(TableStyle([
+            ('BACKGROUND', (0, 0), (-1, 0), colors.grey),
+            ('TEXTCOLOR', (0, 0), (-1, 0), colors.whitesmoke),
+            ('ALIGN', (0, 0), (-1, -1), 'LEFT'),
+            ('FONTNAME', (0, 0), (-1, 0), 'Helvetica-Bold'),
+            ('BOTTOMPADDING', (0, 0), (-1, 0), 12),
+            ('BACKGROUND', (0, 1), (-1, -1), colors.beige),
+            ('GRID', (0, 0), (-1, -1), 1, colors.black),
+        ]))
+        elements.append(t)
+        
+        elements.append(Spacer(1, 24))
+        
+        # Detailed Findings
+        elements.append(Paragraph("Detailed Findings", heading_style))
+        for idx, r in enumerate(results):
+            elements.append(Paragraph(f"<b>Issue #{idx + 1}: {r.get('Label')}</b>", normal_style))
+            elements.append(Paragraph(f"<i>Reason:</i> {r.get('Reason')}", normal_style))
+            elements.append(Paragraph(f"<i>Clause 1:</i> {r.get('Clause 1')}", normal_style))
+            elements.append(Paragraph(f"<i>Clause 2:</i> {r.get('Clause 2')}", normal_style))
+            elements.append(Spacer(1, 12))
+            elements.append(Paragraph("-" * 60, normal_style))
+            elements.append(Spacer(1, 12))
+
+    doc.build(elements)
+    buffer.seek(0)
+    return buffer.getvalue()

output/report.json

@@ -0,0 +1,23 @@
+[
+    {
+        "type": "Duplication",
+        "clause_1": "The organization retains all user data for a period of five (5) years from the date of collection.",
+        "clause_2": "The organization retains all user data for a period of five (5) years from the date of collection.",
+        "confidence": 1.0,
+        "explanation": "High semantic similarity (>90%)"
+    },
+    {
+        "type": "Contradiction",
+        "clause_1": "All cloud storage providers must comply with ISO 27001 security standards.",
+        "clause_2": "Cloud vendors are encouraged, but not required, to follow ISO 27001 standards.",
+        "confidence": 0.71,
+        "explanation": "Logical opposition (Assertion vs Negation)"
+    },
+    {
+        "type": "Contradiction",
+        "clause_1": "Users shall have full access to modify or delete their personal data at any time.",
+        "clause_2": "Users are not permitted to modify or delete their personal data once it has been submitted.",
+        "confidence": 0.67,
+        "explanation": "Logical opposition (Assertion vs Negation)"
+    }
+]

output/report_generator.py

@@ -0,0 +1,5 @@
+import json
+
+def generate_report(results, path="output/report.json"):
+    with open(path, "w") as f:
+        json.dump(results, f, indent=4)