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.

services/cleaning/domain/csv_cleaning/rules/numeric.py

@@ -0,0 +1,57 @@
+"""Reglas numéricas (entero, redondeo)."""
+from __future__ import annotations
+
+import math
+
+import numpy as np
+import pandas as pd
+
+from ..nullish import _is_nullish_scalar
+from ..numbers import _to_numeric_lenient
+
+
+def _rule_to_integer(series: pd.Series) -> pd.Series:
+  """Convierte a entero (Int64 nullable) con parser tolerante."""
+  numeric = _to_numeric_lenient(series.astype(str))
+  return numeric.round().astype("Int64")
+
+
+def _round_to_int_half_tie_le(x: float) -> int:
+  """Fracc. > 0,5 hacia arriba; 0,5 o menos hacia abajo. Banda 1e-9 en 0,5 (float).
+
+  Misma noción que en la descripción de la regla. Trabaja sobre |x| y
+  recompone el signo.
+  """
+  sign = -1 if x < 0 else 1
+  if x == 0.0 or x == -0.0:
+    return 0
+  ax = abs(float(x))
+  ip = math.trunc(ax)
+  frac = ax - ip
+  if frac < 0.5 - 1e-9:
+    out = ip
+  elif frac > 0.5 + 1e-9:
+    out = ip + 1
+  else:
+    out = ip
+  return -out if sign < 0 else out
+
+
+def _rule_round_decimals_custom(series: pd.Series) -> pd.Series:
+  """Mismo parser tolerante que convertir a entero; aprox. con fracc. >0,5 arriba."""
+  numeric = _to_numeric_lenient(series.astype(str))
+
+  def _fn(x):
+    if _is_nullish_scalar(x) or (isinstance(x, (float, np.floating)) and (not np.isfinite(x) or np.isnan(x))):
+      return pd.NA
+    try:
+      f = float(x)
+    except (TypeError, ValueError, OverflowError):
+      return pd.NA
+    if not np.isfinite(f):
+      return pd.NA
+    if f == 0.0 or f == -0.0:
+      return 0
+    return _round_to_int_half_tie_le(f)
+
+  return numeric.map(_fn).astype("Int64")