from __future__ import annotations

from core.csv_utils import merge_verbatim_long_strings, set_at_path


def test_merge_replaces_truncated_string_same_path() -> None:
  raw = {
    "Notas": (
      "Las retenciones son informativas. Paciente: 1 - NOMBRE "
      "Contrato No. X. Valor en Letras: MIL PESOS Fecha ingreso 01/01/2024"
    ),
  }
  norm = {"Notas": "Las retenciones son informativas. Paciente: 1 - NOMBRE "}
  merge_verbatim_long_strings(raw, norm, ["Notas"])
  assert norm["Notas"] == raw["Notas"]


def test_merge_nested_path() -> None:
  raw = {"cabecera": {"Notas": "A" * 200}}
  norm = {"cabecera": {"Notas": "A" * 40}}
  merge_verbatim_long_strings(raw, norm, ["cabecera/Notas"])
  assert norm["cabecera"]["Notas"] == "A" * 200


def test_merge_resolves_by_unique_last_segment() -> None:
  raw = {"Notas": "texto completo desde raíz cuando el normalizado usa cabecera/Notas"}
  norm = {"cabecera": {"Notas": "texto completo"}}
  merge_verbatim_long_strings(raw, norm, ["cabecera/Notas"])
  assert norm["cabecera"]["Notas"] == raw["Notas"]


def test_merge_skips_ambiguous_same_last_segment() -> None:
  raw = {
    "a": {"Notas": "primera nota " + "x" * 50},
    "b": {"Notas": "segunda nota " + "y" * 50},
  }
  norm = {"cabecera": {"Notas": "primera nota"}}
  merge_verbatim_long_strings(raw, norm, ["cabecera/Notas"])
  assert norm["cabecera"]["Notas"] == "primera nota"


def test_merge_skips_when_normalized_not_prefix_of_raw() -> None:
  raw = {"Notas": "completamente distinto " + "z" * 80}
  norm = {"Notas": "otro texto corto"}
  merge_verbatim_long_strings(raw, norm, ["Notas"])
  assert norm["Notas"] == "otro texto corto"


def test_merge_skips_paths_with_wildcard() -> None:
  raw = {"items": [{"x": "long " * 20}]}
  norm = {"items": [{"x": "long "}]}
  merge_verbatim_long_strings(raw, norm, ["items/*/x"])
  assert norm["items"][0]["x"] == "long "


def test_set_at_path_creates_intermediates() -> None:
  root: dict = {}
  set_at_path(root, "a/b/c", 1)
  assert root == {"a": {"b": {"c": 1}}}