"""Strict CSV and run-parameter validation for untrusted uploads.""" from __future__ import annotations from dataclasses import dataclass from pathlib import Path from typing import Any import numpy as np import pandas as pd MAX_FILE_BYTES = 1_000_000 # 1 MB MAX_POINTS = 10_000 MAX_HORIZON = 256 DEFAULT_HORIZON = 24 # Patch size is 32; require enough train context after holdout for a meaningful forecast. MIN_TRAIN_POINTS = 64 class ValidationError(ValueError): """User-facing validation failure (safe message, no server paths).""" @dataclass(frozen=True) class SeriesData: values: np.ndarray timestamps: pd.DatetimeIndex | None value_column: str date_column: str | None n_points: int source_label: str @dataclass(frozen=True) class RunParams: holdout: int future_horizon: int seasonality: int def _as_path(file_obj: Any) -> Path: if file_obj is None: raise ValidationError("Sube un CSV o elige un ejemplo sintético.") if isinstance(file_obj, Path): path = file_obj elif isinstance(file_obj, str): path = Path(file_obj) elif hasattr(file_obj, "name"): path = Path(str(file_obj.name)) else: raise ValidationError("Entrada de archivo no válida.") return path def _assert_safe_csv_path(path: Path) -> Path: try: resolved = path.resolve(strict=True) except (OSError, RuntimeError) as exc: raise ValidationError("No se pudo leer el archivo CSV.") from exc if ".." in Path(path).parts: raise ValidationError("Ruta de archivo no permitida.") if resolved.name.startswith("."): raise ValidationError("Ruta de archivo no permitida.") if resolved.suffix.lower() != ".csv": raise ValidationError("Solo se aceptan archivos CSV (.csv).") try: size = resolved.stat().st_size except OSError as exc: raise ValidationError("No se pudo leer el archivo CSV.") from exc if size <= 0: raise ValidationError("El CSV está vacío.") if size > MAX_FILE_BYTES: raise ValidationError("El archivo supera el límite de 1 MB.") return resolved def parse_series_csv( file_obj: Any, value_column: str | None = None, date_column: str | None = None, source_label: str = "upload", ) -> SeriesData: """Parse a univariate series from CSV with hard safety limits.""" path = _assert_safe_csv_path(_as_path(file_obj)) try: df = pd.read_csv(path) except Exception as exc: # noqa: BLE001 — surface as validation error raise ValidationError("CSV corrupto o ilegible.") from exc if df.empty: raise ValidationError("El CSV está vacío.") if len(df) > MAX_POINTS: raise ValidationError(f"Como máximo {MAX_POINTS} puntos (filas).") numeric_cols = [c for c in df.columns if pd.api.types.is_numeric_dtype(df[c])] # Also try coercing object columns that are mostly numeric. if not numeric_cols: for c in df.columns: coerced = pd.to_numeric(df[c], errors="coerce") if coerced.notna().mean() > 0.9: df[c] = coerced numeric_cols.append(c) value_column = (value_column or "").strip() or None if value_column: if value_column not in df.columns: raise ValidationError( f"Columna '{value_column}' no encontrada. Disponibles: {list(df.columns)}" ) col = value_column else: if not numeric_cols: raise ValidationError("No hay columna numérica en el CSV.") col = str(numeric_cols[-1]) values = pd.to_numeric(df[col], errors="coerce").to_numpy(dtype=np.float64) if values.size == 0: raise ValidationError("La columna objetivo no tiene valores.") if values.size > MAX_POINTS: raise ValidationError(f"Como máximo {MAX_POINTS} puntos.") if not np.isfinite(values).all(): raise ValidationError("La serie contiene NaN o valores no finitos.") timestamps: pd.DatetimeIndex | None = None date_column = (date_column or "").strip() or None if date_column: if date_column not in df.columns: raise ValidationError(f"Columna de fecha '{date_column}' no encontrada.") ts = pd.to_datetime(df[date_column], errors="coerce") if ts.isna().any(): raise ValidationError("La columna de fecha tiene valores inválidos.") timestamps = pd.DatetimeIndex(ts) else: for c in df.columns: if c == col: continue ts = pd.to_datetime(df[c], errors="coerce") if ts.notna().mean() > 0.9 and not ts.isna().any(): timestamps = pd.DatetimeIndex(ts) date_column = str(c) break return SeriesData( values=values.astype(np.float64, copy=False), timestamps=timestamps, value_column=str(col), date_column=date_column, n_points=int(values.size), source_label=source_label, ) def validate_run_params( n_points: int, holdout: int, future_horizon: int, seasonality: int, ) -> RunParams: holdout = int(holdout) future_horizon = int(future_horizon) seasonality = int(seasonality) if holdout < 1 or future_horizon < 1: raise ValidationError("Horizonte / holdout deben ser >= 1.") if holdout > MAX_HORIZON or future_horizon > MAX_HORIZON: raise ValidationError(f"Horizonte máximo: {MAX_HORIZON}.") if seasonality < 1: raise ValidationError("La estacionalidad debe ser >= 1.") train_len = n_points - holdout if train_len < MIN_TRAIN_POINTS: raise ValidationError( f"Se necesitan al menos {MIN_TRAIN_POINTS} puntos de contexto " f"tras el holdout (ahora {train_len})." ) if train_len < seasonality: raise ValidationError( "El contexto de entrenamiento debe cubrir al menos un periodo estacional." ) return RunParams(holdout=holdout, future_horizon=future_horizon, seasonality=seasonality)