IPSExtractor/services/cleaning/domain/csv_cleaning/documents.py

"""Homologación y división de tipo/número de documento."""
from __future__ import annotations

import re
import unicodedata
from typing import Any, Optional

import pandas as pd

from .nullish import _is_nullish_scalar


_DOC_TYPE_ALIASES: dict[str, tuple[str, ...]] = {
  "CC": ("CC", "Cedula", "CD", "C", "C.C", "C C", "CCC"),
  "TI": ("TI", "Tarjeta", "Tarjeta Identidad", "T1", "T", "TL"),
  "CN": ("CN", "Certificado", "Nacido Vivo", "Certificado Nacido Vivo"),
  "CE": ("CE", "Cedula de Extranjeria", "Extranjera"),
  "ME": ("ME", "Menor sin Identificacion"),
  "PS": ("PS", "Pasaporte"),
  "PT": ("PT", "Permiso por proteccion Temporal"),
  "RC": ("RC", "Registro Civil", "Registro", "TC"),
  "SC": ("SC", "Salvo Conducto", "Salvoconducto"),
  "PE": ("PE", "Permiso especial de permanencia", "Permiso"),
}


def _ascii_upper(value: Any) -> str:
  text = unicodedata.normalize("NFKD", str(value or ""))
  text = "".join(c for c in text if not unicodedata.combining(c))
  return text.upper()


def _normalize_doc_type_key(value: Any) -> str:
  """Clave comparable: sin acentos, espacios, puntos ni símbolos."""
  return re.sub(r"[^A-Z0-9]", "", _ascii_upper(value))


def _clean_doc_type_text(value: Any) -> Optional[str]:
  cleaned = re.sub(r"[^A-Z0-9]+", " ", _ascii_upper(value)).strip()
  cleaned = re.sub(r"\s+", " ", cleaned)
  return cleaned or None


_DOC_TYPE_ALIAS_BY_KEY: dict[str, str] = {
  _normalize_doc_type_key(alias): canonical
  for canonical, aliases in _DOC_TYPE_ALIASES.items()
  for alias in aliases
}

_DOC_TYPE_ALIAS_DISPLAY_BY_KEY: dict[str, str] = {}
for _canonical, _aliases in _DOC_TYPE_ALIASES.items():
  for _alias in _aliases:
    _alias_key = _normalize_doc_type_key(_alias)
    _alias_display = _clean_doc_type_text(_alias)
    if _alias_key and _alias_display:
      _DOC_TYPE_ALIAS_DISPLAY_BY_KEY.setdefault(_alias_key, _alias_display)

_DOC_TYPE_ALIAS_KEYS_SORTED: list[str] = sorted(
  _DOC_TYPE_ALIAS_BY_KEY,
  key=lambda k: (len(k), k),
  reverse=True,
)


def homologate_doc_type(value: Any) -> Optional[str]:
  """Homologa un tipo documental a sigla; si no existe, conserva texto limpio."""
  if _is_nullish_scalar(value):
    return None
  key = _normalize_doc_type_key(value)
  if not key or key.lower() in ("nan", "none", "nat"):
    return None
  return _DOC_TYPE_ALIAS_BY_KEY.get(key) or _clean_doc_type_text(value)


def _compact_doc_text(value: Any) -> str:
  return _normalize_doc_type_key(value)


def _looks_like_short_alias_prefix(compact: str, alias_key: str) -> bool:
  """Evita que alias de 1-2 chars capturen palabras como CODIGO o TOTAL."""
  if not compact.startswith(alias_key):
    return False
  rest = compact[len(alias_key):]
  if not rest:
    return True
  return bool(rest[0].isdigit())


def _match_known_doc_type_prefix(compact: str) -> Optional[tuple[str, str]]:
  for alias_key in _DOC_TYPE_ALIAS_KEYS_SORTED:
    if len(alias_key) <= 2:
      if not _looks_like_short_alias_prefix(compact, alias_key):
        continue
    elif not compact.startswith(alias_key):
      continue
    return _DOC_TYPE_ALIAS_BY_KEY[alias_key], alias_key
  return None


def split_doc_tipo_y_numero_texto(
  raw: Any,
  *,
  homologate: bool = True,
) -> tuple[Optional[str], Optional[str]]:
  """Separa tipo documental y número, tolerando nombres largos y símbolos.

  Si `homologate` es True, tipos conocidos se devuelven como sigla (CC, TI,
  etc.). Los tipos desconocidos se conservan limpios en mayúsculas.
  """
  if _is_nullish_scalar(raw) and not (isinstance(raw, str) and not str(raw).strip()):
    return (None, None)
  t = str(raw).strip()
  if t.lower() in ("nan", "none", "nat", "<na>"):
    return (None, None)
  if t and t[0].isdigit():
    return (None, None)

  compact = _compact_doc_text(t)
  if not compact:
    return (None, None)

  match = _match_known_doc_type_prefix(compact)
  if match is not None:
    canonical, alias_key = match
    rest = compact[len(alias_key):]
    nums = re.sub(r"[^\d]", "", rest)
    if homologate:
      return (canonical, nums if nums else None)
    raw_type = _DOC_TYPE_ALIAS_DISPLAY_BY_KEY.get(alias_key) or canonical
    return (raw_type, nums if nums else None)

  m = re.match(
    r"^([^\d]+?)\s*([0-9].*)\s*$",
    t,
  )
  if m:
    to_t = _clean_doc_type_text(m.group(1))
    nums = re.sub(r"[^\d]", "", m.group(2))
    return (homologate_doc_type(to_t) if homologate else to_t, nums if nums else None)

  if not re.search(r"\d", t):
    to_t = homologate_doc_type(t) if homologate else _clean_doc_type_text(t)
    return (to_t, None)
  return (None, None)


def _alloc_doc_split_column_names(
  col_name: str, existing: set[str]
) -> tuple[str, str]:
  """Nombres únicos para las dos columnas derivadas."""
  base = re.sub(r"[^\w]+", "_", str(col_name).strip(), flags=re.ASCII) or "col"
  for i in range(0, 200):
    suf = f"_{i}" if i else ""
    t, n = f"{base}{suf}_doc_tipo", f"{base}{suf}_doc_numeros"
    if t not in existing and n not in existing:
      return t, n
  raise ValueError("No se pudieron asignar nombres de columnas únicos.")


def _apply_doc_id_split_columns(
  result: pd.DataFrame, col: str, log: list[str], *, homologate_type: bool = True
) -> None:
  tcol, ncol = _alloc_doc_split_column_names(str(col), set(result.columns))
  st_tipo: list[Optional[str]] = []
  st_num: list[Any] = []
  for v in result[col].tolist():
    tt, nn = split_doc_tipo_y_numero_texto(v, homologate=homologate_type)
    st_tipo.append(tt)
    st_num.append(nn if nn is not None else pd.NA)
  result[tcol] = st_tipo
  result[ncol] = st_num
  log.append(
    f"[OK] '{str(col)}' -> columnas '{tcol}' y '{ncol}' <- Dividir tipo y número (documento)"
  )