mealie-mcp/mealie_mcp/verify.py

"""The 'definition of a finished import' as executable checks.

This exists so an agent cannot report a successful import while the recipe still
has an English title, a missing cover image, or unparsed ingredients. Pure
functions over a recipe dict — see resources/import-pitfalls.md for the field
observations these encode.
"""
from __future__ import annotations

from typing import Any, Literal

from .normalize import (
    find_english_leftovers,
    has_extraction_failure,
    ingredient_display_lines,
    looks_mangled,
)

Status = Literal["pass", "fail", "warn"]


def _check(check_id: str, status: Status, detail: str) -> dict[str, str]:
    return {"check": check_id, "status": status, "detail": detail}


def is_parsed(recipe: dict[str, Any]) -> bool:
    """Whether Mealie will stop showing 'your ingredients aren't parsed yet'.

    Mealie treats ingredients as parsed once they carry structured data; an
    ingredient with only free text keeps the recipe in the 'Click Parse' state.
    """
    ingredients = recipe.get("recipeIngredient") or []
    if not ingredients:
        return False
    return any(
        (item.get("food") or {}).get("id") or (item.get("unit") or {}).get("id")
        for item in ingredients
    )


def verify_recipe(
    recipe: dict[str, Any],
    *,
    image_verified: bool = False,
    taxonomy_skipped_reason: str | None = None,
) -> dict[str, Any]:
    """Run every finished-import check and return a pass/fail report.

    ``image_verified`` should only be set by a caller that actually ran an image
    step, because a non-empty ``image`` field alone does not prove the UI shows a
    cover (verified failure mode on Allrecipes imports).

    ``taxonomy_skipped_reason`` records a deliberate decision to leave a recipe
    uncategorized, which turns that check into a pass instead of a failure.
    """
    checks: list[dict[str, str]] = []

    name = (recipe.get("name") or "").strip()
    checks.append(
        _check("title_present", "pass" if name else "fail", name or "Recipe has no title")
    )

    description = (recipe.get("description") or "").strip()
    checks.append(
        _check(
            "description_present",
            "pass" if description else "fail",
            "Description set" if description else "Description is empty",
        )
    )

    instructions = [
        (step.get("text") or "").strip() for step in recipe.get("recipeInstructions") or []
    ]
    instructions = [step for step in instructions if step]
    checks.append(
        _check(
            "instructions_present",
            "pass" if instructions else "fail",
            f"{len(instructions)} step(s)" if instructions else "No instruction steps",
        )
    )

    leftovers = find_english_leftovers(" ".join([name, description, *instructions]))
    checks.append(
        _check(
            "swedish_prose",
            "pass" if not leftovers else "fail",
            "No English unit/label words found"
            if not leftovers
            else f"English leftovers in title/description/instructions: {', '.join(leftovers)}",
        )
    )

    lines = ingredient_display_lines(recipe)
    empty_lines = [index for index, line in enumerate(lines) if not line.strip()]
    checks.append(
        _check(
            "ingredient_lines_present",
            "pass" if lines and not empty_lines else "fail",
            f"{len(lines)} ingredient line(s)"
            if lines and not empty_lines
            else f"Missing display text at index {empty_lines}"
            if lines
            else "Recipe has no ingredients",
        )
    )

    ingredient_leftovers = find_english_leftovers(" ".join(lines))
    checks.append(
        _check(
            "swedish_ingredients",
            "pass" if not ingredient_leftovers else "fail",
            "Ingredient lines are Swedish"
            if not ingredient_leftovers
            else f"English leftovers in ingredient lines: {', '.join(ingredient_leftovers)}",
        )
    )

    mangled = [line for line in lines if looks_mangled(line)]
    checks.append(
        _check(
            "ingredient_lines_readable",
            "pass" if not mangled else "fail",
            "Display text is clean"
            if not mangled
            else f"Parser-mangled display text: {mangled}",
        )
    )

    parsed = is_parsed(recipe)
    checks.append(
        _check(
            "ingredients_parsed",
            "pass" if parsed else "fail",
            "Structured food/unit data present"
            if parsed
            else "Recipe still shows the 'Click Parse' state",
        )
    )

    checks.append(
        _check(
            "no_extraction_placeholders",
            "fail" if has_extraction_failure(recipe) else "pass",
            "Contains 'Could not detect ...' placeholder text"
            if has_extraction_failure(recipe)
            else "No scraper placeholders",
        )
    )

    has_image_field = bool(recipe.get("image"))
    if image_verified:
        image_status: Status = "pass"
        image_detail = "Image step ran and was verified by the caller"
    elif has_image_field:
        image_status = "warn"
        image_detail = (
            "image field is set but no image step was verified; a non-empty image "
            "does not prove the UI shows a cover"
        )
    else:
        image_status = "fail"
        image_detail = "No cover image"
    checks.append(_check("cover_image", image_status, image_detail))

    categories = recipe.get("recipeCategory") or []
    tags = recipe.get("tags") or []
    if categories or tags:
        checks.append(
            _check(
                "taxonomy",
                "pass",
                f"{len(categories)} category/categories, {len(tags)} tag(s)",
            )
        )
    elif taxonomy_skipped_reason:
        checks.append(_check("taxonomy", "pass", f"Deliberately skipped: {taxonomy_skipped_reason}"))
    else:
        checks.append(_check("taxonomy", "fail", "No categories or tags, and no skip reason given"))

    source = recipe.get("orgURL") or (recipe.get("extras") or {}).get("source")
    checks.append(
        _check(
            "attribution",
            "pass" if source else "warn",
            f"Source recorded: {source}" if source else "No orgURL or extras.source",
        )
    )

    failed = [c for c in checks if c["status"] == "fail"]
    warned = [c for c in checks if c["status"] == "warn"]
    return {
        "recipe": name or recipe.get("slug"),
        "complete": not failed,
        "failed": [c["check"] for c in failed],
        "warnings": [c["check"] for c in warned],
        "checks": checks,
    }