BuyingAgent/backend/scripts/seed_notebook_pilot.py

"""Notebook-pilot metadata only. Not part of the core schema or bootstrap."""

from __future__ import annotations

from sqlalchemy.orm import Session

from app.discovery.definitions import get_definition_by_key, upsert_definition
from app.persistence.models import AttributeDefinitionRecord
from app.services.catalog_service import ensure_product_category, ensure_source_category


NOTEBOOK_ATTRIBUTE_SEEDS = (
    {"key": "ram_gb", "value_type": "number", "canonical_unit": "GB", "minimum": 0},
    {"key": "storage_gb", "value_type": "number", "canonical_unit": "GB", "minimum": 0},
    {"key": "weight_kg", "value_type": "number", "canonical_unit": "kg", "minimum": 0},
    {"key": "battery_score", "value_type": "number", "minimum": 0, "maximum": 100},
    {"key": "display_score", "value_type": "number", "minimum": 0, "maximum": 100},
    {"key": "cpu_score", "value_type": "number", "minimum": 0, "maximum": 100},
)

NOTEBOOK_CRITERION_SEEDS = (
    {
        "key": "ram_gb",
        "origin": "SOURCE",
        "source": "geizhals",
        "product_category_id": "notebook",
        "label": "Arbeitsspeicher",
        "value_type": "number",
        "unit": "GB",
        "semantic": "working_memory",
        "category": "notebook",
        "scoring_attribute_key": "ram_gb",
    },
    {
        "key": "storage_gb",
        "origin": "SOURCE",
        "source": "geizhals",
        "product_category_id": "notebook",
        "label": "SSD",
        "value_type": "number",
        "unit": "GB",
        "semantic": "storage",
        "category": "notebook",
        "scoring_attribute_key": "storage_gb",
    },
    {
        "key": "weight_kg",
        "origin": "SOURCE",
        "source": "geizhals",
        "product_category_id": "notebook",
        "label": "Gewicht",
        "value_type": "number",
        "unit": "kg",
        "semantic": "weight",
        "category": "notebook",
        "scoring_attribute_key": "weight_kg",
    },
    {
        "key": "price_eur",
        "origin": "SOURCE",
        "source": "geizhals",
        "product_category_id": "notebook",
        "label": "Preis",
        "value_type": "number",
        "unit": "EUR",
        "semantic": "price",
        "category": "notebook",
        "scoring_attribute_key": "price_eur",
    },
)


def seed_notebook_pilot(session: Session) -> None:
    ensure_product_category(session, "notebook", "Notebooks")
    ensure_source_category(
        session,
        source_id="geizhals",
        external_category_key="nb",
        product_category_id="notebook",
        name="Notebooks",
        source_url="https://geizhals.de/?cat=nb",
    )
    for item in NOTEBOOK_ATTRIBUTE_SEEDS:
        if session.get(AttributeDefinitionRecord, item["key"]) is None:
            session.add(AttributeDefinitionRecord(**item, description=None))
    for item in NOTEBOOK_CRITERION_SEEDS:
        if get_definition_by_key(session, item["key"]) is None:
            upsert_definition(session, item)
    session.flush()