@ngocsangairvds/vsaf 3.2.14 → 3.2.16

package/tools/vds-scripts/excel_orchestrator/research_based_updates.py

@@ -1,457 +0,0 @@
-"""
-Research-Based Updates to Estimation
-
-Based on MCP research, this script:
-1. Identifies missing non-functional requirements tasks
-2. Adds comprehensive testing coverage
-3. Enhances infrastructure and DevOps tasks
-4. Adds security and compliance tasks
-5. Improves BRD coverage further
-"""
-
-import re
-from pathlib import Path
-
-from openpyxl import load_workbook
-from openpyxl.styles import Alignment, Border, Side
-
-EXCEL_PATH = Path(
-    "../../insurance-document/projects/INSURANCE/analysis/reference/vietin/estimation/Estimation_HTBH.xlsx"
-)
-BRD_PATH = Path("../../insurance-document/projects/INSURANCE/analysis/reference/BRD/BRD_NTBH_2.0.md")
-
-# Additional tasks based on research findings
-RESEARCH_BASED_TASKS = {
-    # Non-functional requirements that might be missing
-    "performance_testing": {
-        "services": ["Platform Infrastructure & Testing"],
-        "tasks": [
-            {
-                "category": "Kiểm thử",
-                "name": "Performance Testing: Load testing, stress testing, và capacity planning",
-                "complexity": "Phức tạp",
-                "base_effort": 10,
-                "brd_ref": "NFR",
-                "multiplier": "1.59x (base) × 1.05x (performance)",
-            },
-            {
-                "category": "Kiểm thử",
-                "name": "Performance Optimization: Database query optimization, caching strategy",
-                "complexity": "Phức tạp",
-                "base_effort": 8,
-                "brd_ref": "NFR",
-                "multiplier": "1.59x (base) × 1.05x (performance)",
-            },
-        ],
-    },
-    "security_testing": {
-        "services": ["Platform Infrastructure & Testing", "Security Gateway"],
-        "tasks": [
-            {
-                "category": "Kiểm thử",
-                "name": "Security Testing: Penetration testing, vulnerability scanning",
-                "complexity": "Phức tạp",
-                "base_effort": 8,
-                "brd_ref": "NFR",
-                "multiplier": "1.59x (base) × 1.05x (compliance)",
-            },
-            {
-                "category": "Bảo mật",
-                "name": "Security Audit: Code review, dependency scanning, OWASP compliance",
-                "complexity": "Trung bình",
-                "base_effort": 5,
-                "brd_ref": "NFR",
-                "multiplier": "1.59x (base) × 1.05x (compliance)",
-            },
-        ],
-    },
-    "accessibility_testing": {
-        "services": ["Customer Interface"],
-        "tasks": [
-            {
-                "category": "Kiểm thử",
-                "name": "Accessibility Testing: WCAG 2.1 AA compliance testing",
-                "complexity": "Trung bình",
-                "base_effort": 5,
-                "brd_ref": "NFR",
-                "multiplier": "1.59x (base)",
-            }
-        ],
-    },
-    "disaster_recovery": {
-        "services": ["Platform Infrastructure & Testing"],
-        "tasks": [
-            {
-                "category": "Triển khai",
-                "name": "Disaster Recovery Planning: Backup strategy, failover procedures",
-                "complexity": "Phức tạp",
-                "base_effort": 8,
-                "brd_ref": "NFR",
-                "multiplier": "1.59x (base)",
-            },
-            {
-                "category": "Triển khai",
-                "name": "Disaster Recovery Testing: DR drills và recovery time validation",
-                "complexity": "Trung bình",
-                "base_effort": 5,
-                "brd_ref": "NFR",
-                "multiplier": "1.59x (base)",
-            },
-        ],
-    },
-    "monitoring_observability": {
-        "services": ["Observability", "Platform Infrastructure & Testing"],
-        "tasks": [
-            {
-                "category": "Phát triển",
-                "name": "Distributed Tracing: Implement tracing across microservices",
-                "complexity": "Phức tạp",
-                "base_effort": 8,
-                "brd_ref": "NFR",
-                "multiplier": "1.59x (base)",
-            },
-            {
-                "category": "Phát triển",
-                "name": "Business Metrics Dashboard: KPI tracking và business intelligence",
-                "complexity": "Trung bình",
-                "base_effort": 6,
-                "brd_ref": "4.10",
-                "multiplier": "1.59x (base)",
-            },
-        ],
-    },
-    "compliance_testing": {
-        "services": ["Platform Infrastructure & Testing"],
-        "tasks": [
-            {
-                "category": "Kiểm thử",
-                "name": "Compliance Testing: GDPR, PCI-DSS, local regulatory compliance",
-                "complexity": "Phức tạp",
-                "base_effort": 10,
-                "brd_ref": "NFR",
-                "multiplier": "1.59x (base) × 1.05x (compliance)",
-            }
-        ],
-    },
-}
-
-
-def calculate_final_effort(base_effort: float, multiplier_str: str) -> tuple:
-    """Calculate final effort from base effort and multiplier string."""
-    multipliers = {
-        "base": 1.59,
-        "performance": 1.05,
-        "compliance": 1.05,
-        "renewal": 1.3,
-        "logic": 1.3,
-        "dynamic pricing": 1.2,
-        "workflow": 1.25,
-        "ai": 1.4,
-    }
-
-    total_multiplier = 1.0
-    for key, value in multipliers.items():
-        if key in multiplier_str.lower():
-            total_multiplier *= value
-
-    final_days = base_effort * total_multiplier
-    final_hours = final_days * 8
-
-    return final_days, final_hours, f"{total_multiplier:.2f}x"
-
-
-def get_service_id_by_name(excel_path: Path, service_name: str) -> int:
-    """Get service ID by service name."""
-    wb = load_workbook(excel_path, data_only=True)
-    ws = wb["VDS_Est_Detail_Services_Total"]
-
-    for row in range(2, 60):
-        name = ws.cell(row, 2).value
-        service_id = ws.cell(row, 1).value
-
-        if name and service_id:
-            name_clean = str(name).split(":")[0].strip()
-            if service_name.lower() in name_clean.lower() or name_clean.lower() in service_name.lower():
-                return int(service_id)
-
-    return None
-
-
-def get_next_task_id(excel_path: Path, service_id: int) -> str:
-    """Get next task ID for a service."""
-    wb = load_workbook(excel_path, data_only=False)
-    ws = wb["VDS_Task_Breakdown_Detailed"]
-
-    max_task_num = 0
-    for row in range(9, ws.max_row + 1):
-        row_service_id = ws.cell(row, 1).value
-        task_id = ws.cell(row, 5).value
-
-        if row_service_id and isinstance(row_service_id, (int, float)) and int(row_service_id) == service_id:
-            if task_id and isinstance(task_id, str):
-                match = re.search(r"T(\d+)", str(task_id))
-                if match:
-                    task_num = int(match.group(1))
-                    max_task_num = max(max_task_num, task_num)
-
-    next_task_num = max_task_num + 1
-    return f"S{service_id}-T{next_task_num:03d}"
-
-
-def check_if_task_exists(excel_path: Path, service_id: int, task_name: str) -> bool:
-    """Check if a similar task already exists."""
-    wb = load_workbook(excel_path, data_only=False)
-    ws = wb["VDS_Task_Breakdown_Detailed"]
-
-    task_normalized = str(task_name).lower().strip()
-    task_normalized = re.sub(r"[^\w\s]", "", task_normalized)
-    task_normalized = " ".join(task_normalized.split())
-
-    for row in range(9, ws.max_row + 1):
-        row_service_id = ws.cell(row, 1).value
-        row_task_name = ws.cell(row, 6).value
-
-        if row_service_id == service_id and row_task_name:
-            row_task_normalized = str(row_task_name).lower().strip()
-            row_task_normalized = re.sub(r"[^\w\s]", "", row_task_normalized)
-            row_task_normalized = " ".join(row_task_normalized.split())
-
-            # Check for similarity (80% match)
-            if task_normalized in row_task_normalized or row_task_normalized in task_normalized:
-                return True
-
-    return False
-
-
-def add_research_based_tasks(excel_path: Path):
-    """Add research-based tasks to estimation."""
-    wb = load_workbook(excel_path, data_only=False)
-    ws = wb["VDS_Task_Breakdown_Detailed"]
-
-    # Get service info
-    ws_services = wb["VDS_Est_Detail_Services_Total"]
-    service_info = {}
-    for row in range(2, 60):
-        service_id = ws_services.cell(row, 1).value
-        service_name = ws_services.cell(row, 2).value
-        responsibility = ws_services.cell(row, 6).value
-
-        if service_id and isinstance(service_id, (int, float)) and service_name:
-            name_clean = str(service_name).split(":")[0].strip()
-            service_info[int(service_id)] = {
-                "name": name_clean,
-                "full_name": str(service_name).strip(),
-                "responsibility": responsibility or "Unknown",
-            }
-
-    added_count = 0
-    skipped_count = 0
-
-    print("=" * 80)
-    print("Adding Research-Based Tasks")
-    print("=" * 80)
-
-    # Add tasks for each research area
-    for research_area, area_data in RESEARCH_BASED_TASKS.items():
-        print(f"\n{research_area}:")
-
-        for service_name_pattern in area_data["services"]:
-            # Find matching service
-            service_id = None
-            for sid, info in service_info.items():
-                if service_name_pattern.lower() in info["name"].lower():
-                    service_id = sid
-                    break
-
-            if not service_id:
-                print(f"  ⚠️ Service not found: {service_name_pattern}")
-                continue
-
-            service_data = service_info[service_id]
-            print(f"  ✓ Found service: {service_id} - {service_data['name']}")
-
-            # Add tasks
-            for task_data in area_data["tasks"]:
-                # Check if task already exists
-                if check_if_task_exists(excel_path, service_id, task_data["name"]):
-                    skipped_count += 1
-                    print(f"    ⊘ Skipped (exists): {task_data['name'][:50]}...")
-                    continue
-
-                # Get next task ID
-                task_id = get_next_task_id(excel_path, service_id)
-
-                # Calculate final effort
-                final_days, final_hours, multiplier_applied = calculate_final_effort(
-                    task_data["base_effort"], task_data["multiplier"]
-                )
-
-                # Find next empty row
-                next_row = ws.max_row + 1
-
-                # Set values
-                ws.cell(next_row, 1, service_id)
-                ws.cell(next_row, 2, service_data["full_name"])
-                ws.cell(next_row, 3, service_data["responsibility"])
-                ws.cell(next_row, 4, task_data["category"])
-                ws.cell(next_row, 5, task_id)
-                ws.cell(next_row, 6, task_data["name"])
-                ws.cell(next_row, 7, task_data["brd_ref"])
-                ws.cell(next_row, 8, task_data["complexity"])
-                ws.cell(next_row, 9, task_data["base_effort"])
-                ws.cell(next_row, 10, task_data["multiplier"])
-                ws.cell(next_row, 11, final_days)
-                ws.cell(next_row, 12, final_hours)
-                ws.cell(next_row, 13, "")
-                ws.cell(next_row, 14, f"Added based on research: {research_area}")
-
-                # Apply formatting
-                border = Border(
-                    left=Side(style="thin"),
-                    right=Side(style="thin"),
-                    top=Side(style="thin"),
-                    bottom=Side(style="thin"),
-                )
-
-                for col in range(1, ws.max_column + 1):
-                    cell = ws.cell(next_row, col)
-                    cell.border = border
-
-                    # Apply alignment
-                    if col in [1, 5]:
-                        cell.alignment = Alignment(horizontal="center", vertical="center")
-                    elif col in [9, 11, 12]:
-                        cell.alignment = Alignment(horizontal="right", vertical="center")
-                        if isinstance(cell.value, (int, float)):
-                            if col in [9, 11]:
-                                cell.number_format = "#,##0.00"
-                            elif col == 12:
-                                cell.number_format = "#,##0"
-                    else:
-                        cell.alignment = Alignment(horizontal="left", vertical="center", wrap_text=True)
-
-                added_count += 1
-                print(f"    ✓ Added: {task_id} - {task_data['name'][:50]}...")
-
-    wb.save(excel_path)
-    print(f"\n✅ Added {added_count} research-based tasks")
-    print(f"⊘ Skipped {skipped_count} tasks (already exist)")
-
-    return added_count
-
-
-def improve_brd_references_further(excel_path: Path):
-    """Further improve BRD references based on research."""
-    wb = load_workbook(excel_path, data_only=False)
-    ws = wb["VDS_Task_Breakdown_Detailed"]
-
-    # Enhanced keyword mapping
-    brd_enhancements = {
-        "lưu đơn hàng": "3.3.6",
-        "sửa đơn hàng": "3.3.6",
-        "hủy đơn hàng": "3.3.6",
-        "mã giới thiệu": "3.3.7",
-        "referral": "3.3.7",
-        "mã giảm giá": "3.3.8",
-        "voucher": "3.3.8",
-        "thanh toán đơn hàng": "3.3.9",
-        "payment": "3.3.9",
-        "performance": "NFR",
-        "scalability": "NFR",
-        "security": "NFR",
-        "compliance": "NFR",
-        "accessibility": "NFR",
-        "monitoring": "NFR",
-        "observability": "NFR",
-        "disaster recovery": "NFR",
-        "backup": "NFR",
-        "failover": "NFR",
-    }
-
-    updated_count = 0
-
-    for row in range(9, ws.max_row + 1):
-        task_name = ws.cell(row, 6).value
-        current_brd_ref = ws.cell(row, 7).value
-
-        if task_name:
-            task_lower = str(task_name).lower()
-
-            # Find matching BRD references
-            matched_refs = []
-            for keyword, brd_ref in brd_enhancements.items():
-                if keyword in task_lower and brd_ref not in matched_refs:
-                    matched_refs.append(brd_ref)
-
-            # Update if we found references
-            if matched_refs:
-                new_ref = ", ".join(sorted(set(matched_refs))[:3])
-
-                if not current_brd_ref or str(current_brd_ref) == "N/A" or len(str(current_brd_ref)) < 5:
-                    ws.cell(row, 7, new_ref)
-                    updated_count += 1
-                else:
-                    existing_refs = [r.strip() for r in str(current_brd_ref).split(",")]
-                    new_refs_to_add = [r for r in matched_refs if r not in existing_refs]
-
-                    if new_refs_to_add:
-                        combined = sorted(set(existing_refs + new_refs_to_add))
-                        ws.cell(row, 7, ", ".join(combined[:3]))
-                        updated_count += 1
-
-    wb.save(excel_path)
-    print(f"✅ Improved BRD references for {updated_count} tasks")
-    return updated_count
-
-
-def main():
-    """Main execution."""
-    print("=" * 80)
-    print("Research-Based Updates to Estimation")
-    print("=" * 80)
-
-    # Step 1: Add research-based tasks
-    print("\nStep 1: Adding research-based tasks...")
-    added_count = add_research_based_tasks(EXCEL_PATH)
-
-    # Step 2: Improve BRD references
-    print("\nStep 2: Improving BRD references...")
-    brd_updated = improve_brd_references_further(EXCEL_PATH)
-
-    # Step 3: Recalculate task IDs and group by service
-    print("\nStep 3: Recalculating task IDs...")
-    wb = load_workbook(EXCEL_PATH, data_only=False)
-    ws = wb["VDS_Task_Breakdown_Detailed"]
-
-    current_service_id = None
-    task_counter = 1
-
-    for row in range(9, ws.max_row + 1):
-        service_id = ws.cell(row, 1).value
-
-        if service_id and isinstance(service_id, (int, float)):
-            service_id_int = int(service_id)
-
-            if service_id_int != current_service_id:
-                current_service_id = service_id_int
-                task_counter = 1
-
-            task_id = f"S{service_id_int}-T{task_counter:03d}"
-            ws.cell(row, 5, task_id)
-            task_counter += 1
-
-    wb.save(EXCEL_PATH)
-    print("  ✅ Task IDs recalculated")
-
-    # Final summary
-    print("\n" + "=" * 80)
-    print("Research-Based Updates Completed")
-    print("=" * 80)
-    print("\nSummary:")
-    print(f"  Tasks added: {added_count}")
-    print(f"  BRD references improved: {brd_updated}")
-    print(f"  Total tasks: {ws.max_row - 8}")
-
-
-if __name__ == "__main__":
-    main()

package/tools/vds-scripts/excel_orchestrator/restore_e_values.py

@@ -1,172 +0,0 @@
-"""Restore all E values and rebuild D formulas correctly."""
-
-from openpyxl import load_workbook
-
-# Service effort mapping (days) - with complex service multipliers
-SERVICE_EFFORT = {
-    "proposal": 15.6,
-    "policy": 13.0,
-    "customer": 8.0,
-    "claim": 16.8,
-    "agent": 10.0,
-    "billing": 10.0,
-    "promotion": 8.0,
-    "socialized": 10.0,
-    "catalog": 12.0,
-    "rating": 22.5,
-    "underwriting": 13.4,
-    "rules": 10.0,
-    "document": 8.0,
-    "analytics": 10.0,
-    "fraud": 10.0,
-    "ocr": 8.0,
-    "orchestrator": 16.8,
-    "workflow": 22.5,
-    "renewal": 8.0,
-    "timeout": 6.0,
-    "reconcile": 8.0,
-    "payment": 13.0,
-    "payment hub": 15.6,
-    "carrier": 13.0,
-    "migration": 21.0,
-    "sync": 8.0,
-    "user": 8.0,
-    "crm": 10.0,
-    "schedule": 8.0,
-    "content": 10.0,
-    "security": 12.0,
-    "observability": 12.0,
-    "test": 15.0,
-    "cicd": 10.0,
-    "interface": 10.0,
-    "portal": 12.0,
-    "admin portal": 12.0,
-    "bff": 10.0,
-    "gateway": 12.0,
-    "regulator": 10.0,
-}
-
-
-def distribute_hours(total_hours, num_tasks):
-    """Distribute hours across tasks with weights."""
-    if num_tasks <= 3:
-        return [total_hours / num_tasks] * num_tasks
-    weights = []
-    for i in range(num_tasks):
-        if i == 0:  # API
-            weights.append(1.3)
-        elif i < 4:  # Core logic
-            weights.append(1.2)
-        elif i < 7:  # Integration
-            weights.append(1.0)
-        else:  # Testing
-            weights.append(0.8)
-    total_weight = sum(weights)
-    return [total_hours * w / total_weight for w in weights]
-
-
-if __name__ == "__main__":
-    wb = load_workbook(
-        "../../docs-nttc/projects/INSURANCE/analysis/reference/vietin/estimation/Estimation_HTBH.xlsx",
-        read_only=False,
-    )
-    detail = wb["VDS_Est_Detail_Target_State"]
-
-    print("=== Restoring E Values ===")
-
-    # Read services and tasks
-    services = []
-    current_service = None
-    current_tasks = []
-
-    for row in range(10, 450):
-        col2 = detail.cell(row, 2).value
-        col3 = detail.cell(row, 3).value
-
-        if not col3:
-            continue
-
-        if isinstance(col2, (int, float)):
-            # Save previous service
-            if current_service:
-                services.append(
-                    {
-                        "row": current_service["row"],
-                        "name": current_service["name"],
-                        "total_days": current_service["total_days"],
-                        "tasks": current_tasks.copy(),
-                    }
-                )
-
-            # New service - determine effort
-            service_name_lower = str(col3).lower()
-            total_days = 10.0  # Default
-
-            for key, days in SERVICE_EFFORT.items():
-                if key in service_name_lower:
-                    total_days = days
-                    break
-
-            current_service = {"row": row, "name": str(col3), "total_days": total_days}
-            current_tasks = []
-        else:
-            # Task
-            if current_service:
-                current_tasks.append(row)
-
-    # Save last service
-    if current_service:
-        services.append(
-            {
-                "row": current_service["row"],
-                "name": current_service["name"],
-                "total_days": current_service["total_days"],
-                "tasks": current_tasks.copy(),
-            }
-        )
-
-    print(f"Found {len(services)} services")
-
-    # Restore E values and rebuild D formulas
-    restored = 0
-    for svc in services:
-        if len(svc["tasks"]) > 0:
-            task_hours = distribute_hours(svc["total_days"] * 8, len(svc["tasks"]))
-            for i, task_row in enumerate(svc["tasks"]):
-                days = round(task_hours[i] / 8, 1)
-                detail.cell(task_row, 5).value = days
-                detail.cell(task_row, 4).value = f"=E{task_row}*8"
-                restored += 1
-
-    print(f"Restored {restored} E values and D formulas")
-
-    # Fix totals
-    last_data_row = 449
-    detail.cell(9, 4).value = f"=SUM(D10:D{last_data_row})"
-    detail.cell(9, 5).value = "=D9/8"
-    detail.cell(527, 4).value = f"=SUM(D10:D{last_data_row})"
-    detail.cell(527, 5).value = "=D527/8"
-    detail.cell(5, 4).value = "=D527"
-    detail.cell(5, 5).value = "=E527"
-
-    # Update summary
-    summary = wb["VDS_Summary_Target_State"]
-    summary.cell(10, 4).value = "='VDS_Est_Detail_Target_State'!D527"
-    summary.cell(10, 5).value = "='VDS_Est_Detail_Target_State'!D527"
-
-    wb.save("../../docs-nttc/projects/INSURANCE/analysis/reference/vietin/estimation/Estimation_HTBH.xlsx")
-    print("\\n✅ All E values restored and D formulas rebuilt!")
-
-    # Verification
-    print("\\n=== Verification ===")
-    tasks_with_e = 0
-    for row in range(10, 50):
-        col5 = detail.cell(row, 5).value
-        col3 = detail.cell(row, 3).value
-        col2 = detail.cell(row, 2).value
-        if col3 and not isinstance(col2, (int, float)) and col5:
-            tasks_with_e += 1
-
-    print(f"Tasks with E values: {tasks_with_e}")
-    if tasks_with_e > 0:
-        print("✅ E values restored successfully!")

package/tools/vds-scripts/excel_orchestrator/src/vds_excel_orchestrator/__init__.py

@@ -1,5 +0,0 @@
-"""VDS Excel Orchestrator - Excel (.xlsx) file manipulation."""
-
-__version__ = "0.1.0"
-
-__all__ = ["__version__"]