feat: Enhance CSV cleaning service with new endpoints for CSV analysis and preview functionality. Introduce support for job management linked to extraction batches, and update the cleaning rules structure. Add new utility functions for handling CSV data and improve documentation for clarity on usage and available endpoints.

This commit is contained in:
erik
2026-07-11 00:27:05 -05:00
parent cf0ebc72ba
commit b770761832
73 changed files with 7614 additions and 2671 deletions
@@ -0,0 +1,73 @@
"""Extracción de documento y autorización desde notas de texto."""
from __future__ import annotations
import re
from typing import Any, Optional
import pandas as pd
from .nullish import _is_nullish_scalar
def _normalize_nota_text(raw: Any) -> str:
if _is_nullish_scalar(raw):
return ""
try:
if pd.isna(raw):
return ""
except TypeError:
pass
s = str(raw).strip()
if not s or s.lower() in ("nan", "none", "nat", "<na>"):
return ""
return re.sub(r"\s+", " ", s)
def extract_paciente_documento_nota(raw: Any) -> Optional[str]:
"""Número de documento tras ``Paciente:`` y antes del guión del nombre."""
t = _normalize_nota_text(raw)
if not t:
return None
m = _PACIENTE_DOC_NOTA_RE.search(t)
return m.group(1) if m else None
def extract_autorizacion_nota(raw: Any) -> Optional[str]:
"""Número tras ``Autorización No.`` (opcional por fila)."""
t = _normalize_nota_text(raw)
if not t:
return None
m = _AUTORIZACION_NOTA_RE.search(t)
return m.group(1) if m else None
def _alloc_nota_extract_column_names(
col_name: str, existing: set[str]
) -> tuple[str, str]:
"""Nombres únicos para documento paciente y autorización."""
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 ""
dcol, acol = f"{base}{suf}_nota_paciente_doc", f"{base}{suf}_nota_autorizacion"
if dcol not in existing and acol not in existing:
return dcol, acol
raise ValueError("No se pudieron asignar nombres de columnas únicos.")
def _apply_nota_extract_columns(result: pd.DataFrame, col: str, log: list[str]) -> None:
"""Añade columnas con documento (Paciente:) y número de autorización si existe."""
dcol, acol = _alloc_nota_extract_column_names(str(col), set(result.columns))
docs: list[Any] = []
auths: list[Any] = []
for v in result[col].tolist():
dd = extract_paciente_documento_nota(v)
aa = extract_autorizacion_nota(v)
docs.append(dd if dd is not None else pd.NA)
auths.append(aa if aa is not None else pd.NA)
result[dcol] = docs
result[acol] = auths
log.append(
f"[OK] '{str(col)}' -> columnas '{dcol}' y '{acol}' <- Extraer datos de notas"
)