Autoparts-DB/vehicle_database/scripts/populate_fase2.py

#!/usr/bin/env python3
"""
FASE 2: Populate cross-references and aftermarket parts
This script creates FASE 2 tables and populates them with manufacturers,
aftermarket part alternatives, and cross-references.
"""

import sqlite3
import os
import random
import string
from typing import List, Dict, Tuple, Optional

# Database path configuration
DB_PATH = os.path.join(os.path.dirname(__file__), '..', 'vehicle_database.db')
SCHEMA_PATH = os.path.join(os.path.dirname(__file__), '..', 'sql', 'schema.sql')


class Fase2Manager:
    """Manager for FASE 2 tables: manufacturers, aftermarket_parts, and cross-references"""

    def __init__(self, db_path: str = DB_PATH):
        self.db_path = db_path
        self.connection = None

    def connect(self):
        """Connect to the SQLite database"""
        self.connection = sqlite3.connect(self.db_path)
        self.connection.row_factory = sqlite3.Row
        print(f"Connected to database: {self.db_path}")

    def disconnect(self):
        """Close the database connection"""
        if self.connection:
            self.connection.close()
            print("Disconnected from database")

    def create_fase2_tables(self):
        """Create FASE 2 tables from schema file"""
        if not os.path.exists(SCHEMA_PATH):
            raise FileNotFoundError(f"Schema file not found: {SCHEMA_PATH}")

        with open(SCHEMA_PATH, 'r') as f:
            schema = f.read()

        if self.connection:
            cursor = self.connection.cursor()
            cursor.executescript(schema)
            self.connection.commit()
            print("FASE 2 tables created successfully")

    def get_manufacturer_by_name(self, name: str) -> Optional[int]:
        """Get manufacturer ID by name, returns None if not found"""
        cursor = self.connection.cursor()
        cursor.execute("SELECT id FROM manufacturers WHERE name = ?", (name,))
        result = cursor.fetchone()
        return result[0] if result else None

    def insert_manufacturer(self, name: str, type_: str, quality_tier: str,
                           country: str = None, logo_url: str = None,
                           website: str = None) -> int:
        """Insert a manufacturer if it doesn't exist, return its ID"""
        existing_id = self.get_manufacturer_by_name(name)
        if existing_id:
            print(f"  Manufacturer '{name}' already exists (ID: {existing_id})")
            return existing_id

        cursor = self.connection.cursor()
        cursor.execute(
            """INSERT INTO manufacturers (name, type, quality_tier, country, logo_url, website)
               VALUES (?, ?, ?, ?, ?, ?)""",
            (name, type_, quality_tier, country, logo_url, website)
        )
        self.connection.commit()
        manufacturer_id = cursor.lastrowid
        print(f"  Inserted manufacturer: {name} (ID: {manufacturer_id})")
        return manufacturer_id

    def get_all_parts(self) -> List[Dict]:
        """Get all parts from the parts table"""
        cursor = self.connection.cursor()
        cursor.execute("""
            SELECT p.id, p.oem_part_number, p.name, p.name_es, p.group_id,
                   pg.name as group_name, pc.name as category_name
            FROM parts p
            LEFT JOIN part_groups pg ON p.group_id = pg.id
            LEFT JOIN part_categories pc ON pg.category_id = pc.id
        """)
        return [dict(row) for row in cursor.fetchall()]

    def get_aftermarket_part(self, oem_part_id: int, manufacturer_id: int) -> Optional[int]:
        """Check if an aftermarket part already exists"""
        cursor = self.connection.cursor()
        cursor.execute(
            """SELECT id FROM aftermarket_parts
               WHERE oem_part_id = ? AND manufacturer_id = ?""",
            (oem_part_id, manufacturer_id)
        )
        result = cursor.fetchone()
        return result[0] if result else None

    def insert_aftermarket_part(self, oem_part_id: int, manufacturer_id: int,
                                 part_number: str, name: str = None, name_es: str = None,
                                 quality_tier: str = 'standard', price_usd: float = None,
                                 warranty_months: int = 12, in_stock: bool = True) -> int:
        """Insert an aftermarket part if it doesn't exist"""
        existing_id = self.get_aftermarket_part(oem_part_id, manufacturer_id)
        if existing_id:
            return existing_id

        cursor = self.connection.cursor()
        cursor.execute(
            """INSERT INTO aftermarket_parts
               (oem_part_id, manufacturer_id, part_number, name, name_es,
                quality_tier, price_usd, warranty_months, in_stock)
               VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)""",
            (oem_part_id, manufacturer_id, part_number, name, name_es,
             quality_tier, price_usd, warranty_months, in_stock)
        )
        self.connection.commit()
        return cursor.lastrowid

    def get_cross_reference(self, part_id: int, cross_reference_number: str) -> Optional[int]:
        """Check if a cross-reference already exists"""
        cursor = self.connection.cursor()
        cursor.execute(
            """SELECT id FROM part_cross_references
               WHERE part_id = ? AND cross_reference_number = ?""",
            (part_id, cross_reference_number)
        )
        result = cursor.fetchone()
        return result[0] if result else None

    def insert_cross_reference(self, part_id: int, cross_reference_number: str,
                                reference_type: str, source: str = None,
                                notes: str = None) -> int:
        """Insert a cross-reference if it doesn't exist"""
        existing_id = self.get_cross_reference(part_id, cross_reference_number)
        if existing_id:
            return existing_id

        cursor = self.connection.cursor()
        cursor.execute(
            """INSERT INTO part_cross_references
               (part_id, cross_reference_number, reference_type, source, notes)
               VALUES (?, ?, ?, ?, ?)""",
            (part_id, cross_reference_number, reference_type, source, notes)
        )
        self.connection.commit()
        return cursor.lastrowid

    def get_manufacturers_by_tier(self, quality_tier: str) -> List[Dict]:
        """Get all manufacturers of a specific quality tier"""
        cursor = self.connection.cursor()
        cursor.execute(
            "SELECT * FROM manufacturers WHERE quality_tier = ?",
            (quality_tier,)
        )
        return [dict(row) for row in cursor.fetchall()]


# Manufacturer data
MANUFACTURERS_DATA = {
    # OEM manufacturers
    'oem': [
        {'name': 'Toyota', 'country': 'Japan', 'website': 'https://www.toyota.com'},
        {'name': 'Honda', 'country': 'Japan', 'website': 'https://www.honda.com'},
        {'name': 'Ford', 'country': 'USA', 'website': 'https://www.ford.com'},
        {'name': 'GM/ACDelco', 'country': 'USA', 'website': 'https://www.acdelco.com'},
        {'name': 'Volkswagen', 'country': 'Germany', 'website': 'https://www.vw.com'},
        {'name': 'Nissan', 'country': 'Japan', 'website': 'https://www.nissan.com'},
        {'name': 'Hyundai/Kia', 'country': 'South Korea', 'website': 'https://www.hyundai.com'},
    ],
    # Premium aftermarket
    'premium': [
        {'name': 'Bosch', 'country': 'Germany', 'website': 'https://www.bosch.com'},
        {'name': 'Denso', 'country': 'Japan', 'website': 'https://www.denso.com'},
        {'name': 'NGK', 'country': 'Japan', 'website': 'https://www.ngk.com'},
        {'name': 'Akebono', 'country': 'Japan', 'website': 'https://www.akebono.com'},
        {'name': 'Brembo', 'country': 'Italy', 'website': 'https://www.brembo.com'},
        {'name': 'KYB', 'country': 'Japan', 'website': 'https://www.kyb.com'},
        {'name': 'Moog', 'country': 'USA', 'website': 'https://www.moogparts.com'},
        {'name': 'Continental', 'country': 'Germany', 'website': 'https://www.continental.com'},
    ],
    # Standard aftermarket
    'standard': [
        {'name': 'Monroe', 'country': 'USA', 'website': 'https://www.monroe.com'},
        {'name': 'Raybestos', 'country': 'USA', 'website': 'https://www.raybestos.com'},
        {'name': 'Wagner', 'country': 'USA', 'website': 'https://www.wagnerbrake.com'},
        {'name': 'Cardone', 'country': 'USA', 'website': 'https://www.cardone.com'},
        {'name': 'Standard Motor Products', 'country': 'USA', 'website': 'https://www.smpcorp.com'},
    ],
    # Economy aftermarket
    'economy': [
        {'name': 'Fram', 'country': 'USA', 'website': 'https://www.fram.com'},
        {'name': 'WIX', 'country': 'USA', 'website': 'https://www.wixfilters.com'},
        {'name': 'Duralast', 'country': 'USA', 'website': 'https://www.autozone.com'},
        {'name': 'AutoZone Valucraft', 'country': 'USA', 'website': 'https://www.autozone.com'},
    ],
}


# Part number prefixes by manufacturer for realistic generation
MANUFACTURER_PREFIXES = {
    'Bosch': ['0 280', '0 986', '1 457', 'F 00M'],
    'Denso': ['234-', '471-', '210-', '950-'],
    'NGK': ['ZFR', 'BKR', 'LFR', 'TR'],
    'Akebono': ['ACT', 'ASP', 'EUR', 'PRO'],
    'Brembo': ['P 85', 'P 06', 'P 23', 'P 50'],
    'KYB': ['332', '334', '343', '344'],
    'Moog': ['K', 'ES', 'RK', 'CK'],
    'Continental': ['49', '50', '51', 'A1'],
    'Monroe': ['32', '33', '34', '37'],
    'Raybestos': ['FRC', 'SGD', 'ATD', 'PGD'],
    'Wagner': ['QC', 'OEX', 'TQ', 'ZD'],
    'Cardone': ['18-', '19-', '20-', '21-'],
    'Standard Motor Products': ['FD', 'TM', 'AC', 'JH'],
    'Fram': ['PH', 'CA', 'TG', 'XG'],
    'WIX': ['51', '57', '46', '33'],
    'Duralast': ['DL', 'BP', 'AF', 'OF'],
    'AutoZone Valucraft': ['VC', 'VB', 'VA', 'VP'],
}


# Price multipliers by quality tier (relative to a base OEM price)
PRICE_MULTIPLIERS = {
    'premium': (0.75, 1.10),  # 75-110% of OEM price
    'standard': (0.50, 0.75),  # 50-75% of OEM price
    'economy': (0.25, 0.50),  # 25-50% of OEM price
}


# Warranty months by quality tier
WARRANTY_MONTHS = {
    'premium': [24, 36, 48],
    'standard': [12, 18, 24],
    'economy': [6, 12],
}


def generate_part_number(manufacturer_name: str, oem_number: str) -> str:
    """Generate a realistic aftermarket part number"""
    prefixes = MANUFACTURER_PREFIXES.get(manufacturer_name, ['XX'])
    prefix = random.choice(prefixes)

    # Extract numeric portion from OEM number or generate random
    numeric_part = ''.join(filter(str.isdigit, oem_number))
    if len(numeric_part) < 4:
        numeric_part = ''.join(random.choices(string.digits, k=5))
    else:
        # Modify slightly to make it different
        numeric_part = numeric_part[:4] + str(random.randint(0, 99)).zfill(2)

    return f"{prefix}{numeric_part}"


def generate_base_price(part_name: str, category_name: str = None) -> float:
    """Generate a realistic base price for a part based on category"""
    # Base price ranges by category/keyword
    price_ranges = {
        'spark plug': (5, 25),
        'filter': (8, 45),
        'oil filter': (5, 20),
        'air filter': (12, 35),
        'brake pad': (25, 80),
        'brake rotor': (40, 150),
        'shock': (50, 200),
        'strut': (80, 250),
        'sensor': (20, 120),
        'alternator': (100, 350),
        'starter': (80, 300),
        'water pump': (30, 120),
        'radiator': (100, 400),
        'thermostat': (10, 40),
        'belt': (15, 60),
        'hose': (10, 50),
        'gasket': (5, 80),
        'bearing': (15, 100),
        'cv joint': (40, 150),
        'tie rod': (25, 80),
        'ball joint': (30, 100),
        'control arm': (60, 200),
        'default': (20, 100),
    }

    # Find matching price range
    part_name_lower = part_name.lower() if part_name else ''
    category_lower = (category_name or '').lower()

    for keyword, (min_price, max_price) in price_ranges.items():
        if keyword in part_name_lower or keyword in category_lower:
            return round(random.uniform(min_price, max_price), 2)

    return round(random.uniform(*price_ranges['default']), 2)


def generate_cross_reference_number(oem_number: str, ref_type: str) -> str:
    """Generate a cross-reference number based on type"""
    if ref_type == 'oem_alternate':
        # Slight variation of OEM number
        chars = list(oem_number)
        if len(chars) > 2:
            idx = random.randint(0, len(chars) - 1)
            if chars[idx].isdigit():
                chars[idx] = str((int(chars[idx]) + 1) % 10)
            elif chars[idx].isalpha():
                chars[idx] = random.choice(string.ascii_uppercase)
        return ''.join(chars)

    elif ref_type == 'supersession':
        # New part number format
        return f"SUP-{oem_number[-6:]}" if len(oem_number) > 6 else f"SUP-{oem_number}"

    elif ref_type == 'interchange':
        # Generic interchange format
        numeric = ''.join(filter(str.isdigit, oem_number))
        return f"INT-{numeric[:6] if len(numeric) > 6 else numeric}"

    elif ref_type == 'competitor':
        # Competitor format
        return f"CMP-{random.choice(string.ascii_uppercase)}{random.randint(1000, 9999)}"

    return oem_number


def populate_manufacturers(manager: Fase2Manager) -> Dict[str, int]:
    """Populate the manufacturers table and return a mapping of name to ID"""
    print("\n=== Populating Manufacturers ===")
    manufacturer_ids = {}

    # Insert OEM manufacturers
    print("\nOEM Manufacturers:")
    for mfr in MANUFACTURERS_DATA['oem']:
        mfr_id = manager.insert_manufacturer(
            name=mfr['name'],
            type_='oem',
            quality_tier='oem',
            country=mfr['country'],
            website=mfr['website']
        )
        manufacturer_ids[mfr['name']] = mfr_id

    # Insert Premium aftermarket
    print("\nPremium Aftermarket Manufacturers:")
    for mfr in MANUFACTURERS_DATA['premium']:
        mfr_id = manager.insert_manufacturer(
            name=mfr['name'],
            type_='aftermarket',
            quality_tier='premium',
            country=mfr['country'],
            website=mfr['website']
        )
        manufacturer_ids[mfr['name']] = mfr_id

    # Insert Standard aftermarket
    print("\nStandard Aftermarket Manufacturers:")
    for mfr in MANUFACTURERS_DATA['standard']:
        mfr_id = manager.insert_manufacturer(
            name=mfr['name'],
            type_='aftermarket',
            quality_tier='standard',
            country=mfr['country'],
            website=mfr['website']
        )
        manufacturer_ids[mfr['name']] = mfr_id

    # Insert Economy aftermarket
    print("\nEconomy Aftermarket Manufacturers:")
    for mfr in MANUFACTURERS_DATA['economy']:
        mfr_id = manager.insert_manufacturer(
            name=mfr['name'],
            type_='aftermarket',
            quality_tier='economy',
            country=mfr['country'],
            website=mfr['website']
        )
        manufacturer_ids[mfr['name']] = mfr_id

    print(f"\nTotal manufacturers: {len(manufacturer_ids)}")
    return manufacturer_ids


def populate_aftermarket_parts(manager: Fase2Manager, manufacturer_ids: Dict[str, int]):
    """Generate aftermarket parts for each OEM part in the database"""
    print("\n=== Generating Aftermarket Parts ===")

    parts = manager.get_all_parts()
    if not parts:
        print("No parts found in the database. Aftermarket parts will be generated when parts are added.")
        return

    total_aftermarket = 0

    for part in parts:
        oem_part_id = part['id']
        oem_number = part['oem_part_number']
        part_name = part['name']
        category_name = part.get('category_name', '')

        # Generate base price for this part
        base_price = generate_base_price(part_name, category_name)

        # Determine how many aftermarket alternatives (2-4)
        num_alternatives = random.randint(2, 4)

        # Select manufacturers from different tiers
        tiers_to_use = ['premium', 'standard', 'economy']
        random.shuffle(tiers_to_use)

        alternatives_created = 0
        for tier in tiers_to_use:
            if alternatives_created >= num_alternatives:
                break

            # Get manufacturers for this tier
            tier_manufacturers = [
                name for name, data in
                [(m['name'], m) for m in (
                    MANUFACTURERS_DATA.get(tier, [])
                )]
            ]

            if not tier_manufacturers:
                continue

            # Pick 1-2 manufacturers from this tier
            selected = random.sample(
                tier_manufacturers,
                min(2, len(tier_manufacturers), num_alternatives - alternatives_created)
            )

            for mfr_name in selected:
                if alternatives_created >= num_alternatives:
                    break

                mfr_id = manufacturer_ids.get(mfr_name)
                if not mfr_id:
                    continue

                # Generate aftermarket part number
                am_part_number = generate_part_number(mfr_name, oem_number)

                # Calculate price based on tier
                price_range = PRICE_MULTIPLIERS.get(tier, (0.5, 0.8))
                price_multiplier = random.uniform(*price_range)
                am_price = round(base_price * price_multiplier, 2)

                # Get warranty for tier
                warranty = random.choice(WARRANTY_MONTHS.get(tier, [12]))

                # Determine quality tier for the part
                quality_tier = tier

                # Insert aftermarket part
                am_id = manager.insert_aftermarket_part(
                    oem_part_id=oem_part_id,
                    manufacturer_id=mfr_id,
                    part_number=am_part_number,
                    name=f"{mfr_name} {part_name}",
                    name_es=part.get('name_es'),
                    quality_tier=quality_tier,
                    price_usd=am_price,
                    warranty_months=warranty,
                    in_stock=random.random() > 0.1  # 90% in stock
                )

                if am_id:
                    alternatives_created += 1
                    total_aftermarket += 1

        print(f"  Part {oem_number}: {alternatives_created} aftermarket alternatives created")

    print(f"\nTotal aftermarket parts created: {total_aftermarket}")


def populate_cross_references(manager: Fase2Manager):
    """Generate cross-references for OEM parts"""
    print("\n=== Generating Cross-References ===")

    parts = manager.get_all_parts()
    if not parts:
        print("No parts found in the database. Cross-references will be generated when parts are added.")
        return

    total_refs = 0
    reference_types = ['oem_alternate', 'supersession', 'interchange', 'competitor']
    sources = ['RockAuto', 'PartsGeek', 'AutoZone', 'OReilly', 'NAPA', 'Manufacturer']

    for part in parts:
        part_id = part['id']
        oem_number = part['oem_part_number']

        # Generate 1-3 cross-references per part
        num_refs = random.randint(1, 3)
        used_types = random.sample(reference_types, min(num_refs, len(reference_types)))

        for ref_type in used_types:
            cross_ref_number = generate_cross_reference_number(oem_number, ref_type)
            source = random.choice(sources)

            notes = None
            if ref_type == 'supersession':
                notes = "New part number supersedes original"
            elif ref_type == 'interchange':
                notes = "Interchangeable with original"

            ref_id = manager.insert_cross_reference(
                part_id=part_id,
                cross_reference_number=cross_ref_number,
                reference_type=ref_type,
                source=source,
                notes=notes
            )

            if ref_id:
                total_refs += 1

        print(f"  Part {oem_number}: {len(used_types)} cross-references created")

    print(f"\nTotal cross-references created: {total_refs}")


def main():
    """Main entry point for FASE 2 population"""
    print("=" * 60)
    print("FASE 2: Cross-References and Aftermarket Parts Population")
    print("=" * 60)

    manager = Fase2Manager()

    try:
        # Connect to database
        manager.connect()

        # Create FASE 2 tables (idempotent)
        manager.create_fase2_tables()

        # Populate manufacturers
        manufacturer_ids = populate_manufacturers(manager)

        # Generate aftermarket parts
        populate_aftermarket_parts(manager, manufacturer_ids)

        # Generate cross-references
        populate_cross_references(manager)

        print("\n" + "=" * 60)
        print("FASE 2 population completed successfully!")
        print("=" * 60)

        # Print summary
        cursor = manager.connection.cursor()
        cursor.execute("SELECT COUNT(*) FROM manufacturers")
        mfr_count = cursor.fetchone()[0]
        cursor.execute("SELECT COUNT(*) FROM aftermarket_parts")
        am_count = cursor.fetchone()[0]
        cursor.execute("SELECT COUNT(*) FROM part_cross_references")
        xref_count = cursor.fetchone()[0]

        print(f"\nSummary:")
        print(f"  Manufacturers: {mfr_count}")
        print(f"  Aftermarket Parts: {am_count}")
        print(f"  Cross-References: {xref_count}")

    except Exception as e:
        print(f"\nError: {e}")
        raise

    finally:
        manager.disconnect()


if __name__ == "__main__":
    main()