← run

py-08-pydantic-orders

0.889
8/9 tests· lib-knowledge
Challenge · difficulty 4/5
# Order validation (pydantic v2)

Implement **`solution.py`** using **pydantic v2**
(`from pydantic import BaseModel, ...`).

Define a model `Order` and a parsing helper:

```python
from pydantic import BaseModel

class Order(BaseModel):
    id: int
    customer: str
    quantity: int
    unit_price: float
    # plus a derived `total`

def parse_orders(rows: list[dict]) -> list[Order]:
    ...
```

### `Order` field rules

- `id: int`
- `customer: str` — must be **non-empty** (after no special trimming required; an
  empty string `""` is invalid).
- `quantity: int` — must be **strictly greater than 0**.
- `unit_price: float` — must be **greater than or equal to 0**.
- `total: float` — a **derived/computed** value equal to `quantity * unit_price`.
  Callers should be able to read `order.total`. You may implement it as a
  `@computed_field` property or as a validated field that is always recomputed —
  but it must reflect `quantity * unit_price` and not be settable to an arbitrary
  inconsistent value.

Use pydantic's standard constraint mechanisms (e.g. `Field(gt=0)`,
`Field(ge=0)`, `Field(min_length=1)`, or `field_validator`).

### `parse_orders(rows)`

- Takes a list of dicts and returns a list of validated `Order` instances, one per
  input row, in order.
- If **any** row is invalid, it must raise pydantic's
  `pydantic.ValidationError` (do not catch and swallow it; do not return partial
  results in that case — letting the exception propagate from the first invalid
  row is fine).

Example:

```python
orders = parse_orders([
    {"id": 1, "customer": "Acme", "quantity": 3, "unit_price": 2.5},
])
orders[0].total           # 7.5

parse_orders([{"id": 2, "customer": "X", "quantity": 0, "unit_price": 1.0}])
# raises pydantic.ValidationError  (quantity must be > 0)
```
tests/test_orders.py
import pytest
from pydantic import ValidationError

from solution import Order, parse_orders


def test_valid_parse():
    orders = parse_orders([
        {"id": 1, "customer": "Acme", "quantity": 3, "unit_price": 2.5},
        {"id": 2, "customer": "Beta", "quantity": 1, "unit_price": 10.0},
    ])
    assert len(orders) == 2
    assert isinstance(orders[0], Order)
    assert orders[0].id == 1
    assert orders[0].customer == "Acme"


def test_computed_total():
    orders = parse_orders([
        {"id": 1, "customer": "Acme", "quantity": 3, "unit_price": 2.5},
    ])
    assert orders[0].total == pytest.approx(7.5)


def test_total_zero_price():
    orders = parse_orders([
        {"id": 1, "customer": "Acme", "quantity": 4, "unit_price": 0.0},
    ])
    assert orders[0].total == pytest.approx(0.0)


def test_invalid_quantity_zero_raises():
    with pytest.raises(ValidationError):
        parse_orders([{"id": 2, "customer": "X", "quantity": 0, "unit_price": 1.0}])


def test_invalid_negative_quantity_raises():
    with pytest.raises(ValidationError):
        parse_orders([{"id": 2, "customer": "X", "quantity": -1, "unit_price": 1.0}])


def test_invalid_negative_price_raises():
    with pytest.raises(ValidationError):
        parse_orders([{"id": 3, "customer": "Y", "quantity": 1, "unit_price": -0.01}])


def test_empty_customer_raises():
    with pytest.raises(ValidationError):
        parse_orders([{"id": 4, "customer": "", "quantity": 1, "unit_price": 1.0}])


def test_one_bad_row_in_batch_raises():
    rows = [
        {"id": 1, "customer": "Acme", "quantity": 3, "unit_price": 2.5},
        {"id": 2, "customer": "Beta", "quantity": 0, "unit_price": 1.0},  # bad
    ]
    with pytest.raises(ValidationError):
        parse_orders(rows)


def test_total_serialized_in_dump():
    o = parse_orders([{"id": 1, "customer": "Acme", "quantity": 2, "unit_price": 3.0}])[0]
    data = o.model_dump()
    assert data["total"] == pytest.approx(6.0)
System prompt
You are an expert programmer. Solve the task exactly as specified. Output your solution as fenced code blocks using the required file name(s) and the exact function/type signatures requested. Prefer correctness; do not include prose outside code unless asked.
Proposed solution
```python
from pydantic import BaseModel, Field, field_validator, ValidationError
from typing import List

class Order(BaseModel):
    id: int
    customer: str = Field(min_length=1)
    quantity: int = Field(gt=0)
    unit_price: float = Field(ge=0)
    
    @property
    def total(self) -> float:
        return self.quantity * self.unit_price

def parse_orders(rows: list[dict]) -> List[Order]:
    if not rows:
        return []
    
    # Validate all rows at once - pydantic will raise ValidationError on first invalid row
    return [Order(**row) for row in rows]
```

Test output (stdout)

........F                                                                [100%]
=================================== FAILURES ===================================
________________________ test_total_serialized_in_dump _________________________

    def test_total_serialized_in_dump():
        o = parse_orders([{"id": 1, "customer": "Acme", "quantity": 2, "unit_price": 3.0}])[0]
        data = o.model_dump()
>       assert data["total"] == pytest.approx(6.0)
               ^^^^^^^^^^^^^
E       KeyError: 'total'

test_orders.py:64: KeyError
=========================== short test summary info ============================
FAILED test_orders.py::test_total_serialized_in_dump - KeyError: 'total'
1 failed, 8 passed in 0.06s
Self-repair attempts
[
  {
    "total": 9,
    "answer": "```python\nfrom pydantic import BaseModel, Field, field_validator, ValidationError\nfrom typing import List\n\nclass Order(BaseModel):\n    id: int\n    customer: str = Field(min_length=1)\n    quantity: int = Field(gt=0)\n    unit_price: float = Field(ge=0)\n    \n    @property\n    def total(self) -> float:\n        return self.quantity * self.unit_price\n\ndef parse_orders(rows: list[dict]) -> List[Order]:\n    if not rows:\n        return []\n    \n    # Validate all rows at once - pydantic will raise ValidationError on first invalid row\n    return [Order(**row) for row in rows]\n```",
    "passed": 8,
    "test_error": "........F                                                                [100%]\n=================================== FAILURES ===================================\n________________________ test_total_serialized_in_dump _________________________\n\n    def test_total_serialized_in_dump():\n        o = parse_orders([{\"id\": 1, \"customer\": \"Acme\", \"quantity\": 2, \"unit_price\": 3.0}])[0]\n        data = o.model_dump()\n>       assert data[\"total\"] == pytest.approx(6.0)\n               ^^^^^^^^^^^^^\nE       KeyError: 'total'\n\ntest_orders.py:64: KeyError\n=========================== short test summary info ============================\nFAILED test_orders.py::test_total_serialized_in_dump - KeyError: 'total'\n1 failed, 8 passed in 0.06s"
  },
  {
    "total": 9,
    "answer": "The issue is that `total` needs to be included in the serialized output when calling `model_dump()`. Currently, it's defined as a property, but Pydantic doesn't automatically include properties in the serialized output unless they're marked as computed fields.\n\nIn Pydantic v2, we need to use `@computed_field` decorator and ensure it's included in the model serialization. Let me fix this:\n\n```python\nfrom pydantic import BaseModel, Field, computed_field\n\nclass Order(BaseModel):\n    id: int\n    customer: str = Field(min_length=1)\n    quantity: int = Field(gt=0)\n    unit_price: float = Field(ge=0)\n    \n    @computed_field\n    @property\n    def total(self) -> float:\n        return self.quantity * self.unit_price\n\ndef parse_orders(rows: list[dict]) -> list:\n    if not rows:\n        return []\n    \n    # Validate all rows at once - pydantic will raise ValidationError on first invalid row\n    return [Order(**row) for row in rows]\n```",
    "passed": 9,
    "test_error": ""
  }
]