Meal-Planner/backend/app/services/recipe_import_review.py

from __future__ import annotations

from datetime import datetime, timezone
from typing import Any, Mapping
from uuid import UUID

from sqlalchemy import select
from sqlalchemy.dialects.postgresql import insert as pg_insert
from sqlalchemy.orm import Session

from app.models import (
    Ingredient,
    Recipe,
    RecipeCatalogStatus,
    RecipeImportStaging,
    RecipeImportStatus,
)
from app.services.wikibooks_import import (
    WIKIBOOKS_SOURCE,
    WikibooksImportService,
    canonical_json_sha256,
)


class RecipeImportNotFoundError(LookupError):
    """Raised when a staged recipe does not exist."""


class RecipeImportConflictError(ValueError):
    """Raised when a review transition or publication is unsafe."""


def approve_recipe_import(
    db: Session, import_id: UUID, reviewed_by: str
) -> tuple[RecipeImportStaging, bool]:
    """Atomically publish one pending Wikibooks candidate."""
    staged = _locked_import(db, import_id)
    if staged.status == RecipeImportStatus.APPROVED:
        if staged.recipe_id and db.get(Recipe, staged.recipe_id):
            return staged, False
    elif staged.status != RecipeImportStatus.PENDING:
        raise RecipeImportConflictError(
            f"Only pending imports can be approved; current status is {staged.status.value}"
        )
    if staged.source != WIKIBOOKS_SOURCE:
        raise RecipeImportConflictError(f"Unsupported recipe source: {staged.source}")

    raw_payload = _mapping(staged.raw_payload, "raw_payload")
    if canonical_json_sha256(raw_payload) != staged.payload_sha256:
        raise RecipeImportConflictError("Raw payload checksum does not match provenance")

    normalizer = WikibooksImportService("MealPlanner recipe review")
    normalized = normalizer.normalize_page(raw_payload)
    validation_report = normalizer.validate_recipe(normalized)
    if not validation_report["valid"]:
        raise RecipeImportConflictError("Candidate no longer passes publication validation")

    existing = (
        db.query(Recipe)
        .filter(
            Recipe.external_source == staged.source,
            Recipe.external_id == staged.external_id,
        )
        .first()
    )
    if existing:
        raise RecipeImportConflictError(
            "A recipe from this source page is already published"
        )

    ingredient_refs = _ingredient_refs(db, normalized["ingredients"])
    cook_time = (normalized.get("cook_time_minutes") or 0) + (
        normalized.get("baking_time_minutes") or 0
    )
    recipe = Recipe(
        family_profile_id=None,
        name=normalized["name"],
        description=normalized.get("description"),
        image_url=None,
        image_source=None,
        prep_time_minutes=normalized.get("prep_time_minutes"),
        cook_time_minutes=cook_time or None,
        servings=normalized["servings"],
        cuisine_tags=[],
        dietary_tags=[],
        protein_type=None,
        spice_level=None,
        calories_per_serving=None,
        ingredients=ingredient_refs,
        side_dishes=[],
        instructions=list(normalized["instructions"]),
        source_url=staged.source_url,
        scraped_at=staged.acquired_at,
        is_manually_added=False,
        external_source=staged.source,
        external_id=staged.external_id,
        discovery_reason=f"Approved import from revision {staged.source_revision}",
        catalog_status=RecipeCatalogStatus.ACTIVE,
        catalog_findings=[],
    )
    db.add(recipe)
    db.flush()

    staged.normalized_recipe = normalized
    staged.validation_report = validation_report
    staged.status = RecipeImportStatus.APPROVED
    staged.rejection_reason = None
    staged.recipe_id = recipe.id
    staged.reviewed_at = datetime.now(timezone.utc)
    staged.reviewed_by = reviewed_by[:300]
    db.commit()
    db.refresh(staged)
    return staged, True


def reject_recipe_import(
    db: Session, import_id: UUID, reason: str, reviewed_by: str
) -> RecipeImportStaging:
    """Atomically reject a pending or quarantined candidate."""
    staged = _locked_import(db, import_id)
    if staged.status == RecipeImportStatus.APPROVED:
        raise RecipeImportConflictError("Approved imports cannot be rejected")
    if staged.status == RecipeImportStatus.REJECTED:
        if staged.rejection_reason == reason:
            return staged
        raise RecipeImportConflictError("Import was already rejected with another reason")

    staged.status = RecipeImportStatus.REJECTED
    staged.rejection_reason = reason
    staged.reviewed_at = datetime.now(timezone.utc)
    staged.reviewed_by = reviewed_by[:300]
    db.commit()
    db.refresh(staged)
    return staged


def _locked_import(db: Session, import_id: UUID) -> RecipeImportStaging:
    staged = db.execute(
        select(RecipeImportStaging)
        .where(RecipeImportStaging.id == import_id)
        .with_for_update()
    ).scalar_one_or_none()
    if staged is None:
        raise RecipeImportNotFoundError("Recipe import not found")
    return staged


def _ingredient_refs(
    db: Session, ingredients: list[Mapping[str, Any]]
) -> list[dict[str, Any]]:
    prepared: list[tuple[str, str, float, str | None, str | None]] = []
    for item in ingredients:
        name = " ".join(str(item.get("name", "")).split())
        name_lower = name.casefold()
        quantity = item.get("quantity")
        unit = item.get("unit")
        source_text = item.get("source_text")
        if not name or len(name) > 200:
            raise RecipeImportConflictError("Ingredient name is invalid")
        if not isinstance(quantity, (int, float)) or isinstance(quantity, bool) or quantity <= 0:
            raise RecipeImportConflictError("Ingredient quantity is invalid")
        if unit is not None and (not isinstance(unit, str) or len(unit) > 50):
            raise RecipeImportConflictError("Ingredient unit is invalid")
        prepared.append((name, name_lower, float(quantity), unit, source_text))

    for name, name_lower, _, unit, _ in prepared:
        db.execute(
            pg_insert(Ingredient.__table__)
            .values(name=name, name_lower=name_lower, unit=unit, aliases=[])
            .on_conflict_do_nothing(index_elements=[Ingredient.name_lower])
        )

    canonical = {
        row.name_lower: row
        for row in db.query(Ingredient)
        .filter(Ingredient.name_lower.in_([item[1] for item in prepared]))
        .all()
    }
    if len(canonical) != len({item[1] for item in prepared}):
        raise RecipeImportConflictError("Canonical ingredient creation failed")

    return [
        {
            "ingredient_id": str(canonical[name_lower].id),
            "qty": quantity,
            "unit": unit,
            "notes": source_text,
        }
        for _, name_lower, quantity, unit, source_text in prepared
    ]


def _mapping(value: Any, field: str) -> Mapping[str, Any]:
    if not isinstance(value, Mapping):
        raise RecipeImportConflictError(f"{field} must be an object")
    return value