chore: Remove obsolete build and GUI files, and introduce a new Docker Compose setup for microservices architecture. This change streamlines the project structure by eliminating legacy scripts and integrating a PostgreSQL database service alongside extraction and cleaning services.

services/extraction/domain/csv_manager.py

@@ -0,0 +1,52 @@
+"""Gestor de escritura CSV.
+
+Maneja la escritura incremental segura (con lock) en archivos CSV.
+"""
+import csv
+import os
+import re
+import threading
+from typing import Any, Dict, List
+
+_LINE_BREAK_RE = re.compile(r"[\r\n\v\f\x85\u2028\u2029]+")
+
+
+def sanitize_csv_cell_value(value: Any) -> Any:
+  """Reemplaza saltos de línea en valores de celda por un espacio (una fila física por registro).
+
+  Conserva ``None`` y escalares numéricos/booleanos sin tocar. Cadenas y demás
+  tipos se normalizan solo si la representación en texto contiene saltos.
+  """
+  if value is None:
+    return value
+  if isinstance(value, bool):
+    return value
+  if isinstance(value, (int, float)):
+    return value
+  if isinstance(value, str):
+    if not _LINE_BREAK_RE.search(value):
+      return value
+    return _LINE_BREAK_RE.sub(" ", value).strip()
+  s = str(value)
+  if not _LINE_BREAK_RE.search(s):
+    return value
+  return _LINE_BREAK_RE.sub(" ", s).strip()
+
+
+class CSVManager:
+  def __init__(self):
+    self._lock = threading.Lock()
+
+  def append_rows(self, csv_path: str, rows: List[Dict[str, Any]], header: List[str]) -> None:
+    """Anexa filas a un CSV, creando encabezado si el archivo no existe."""
+    os.makedirs(os.path.dirname(csv_path) or ".", exist_ok=True)
+    file_exists = os.path.exists(csv_path) and os.path.getsize(csv_path) > 0
+
+    with self._lock:
+      with open(csv_path, "a", encoding="utf-8-sig", newline="") as f:
+        writer = csv.DictWriter(f, fieldnames=header, extrasaction="ignore", delimiter="|")
+        if not file_exists:
+          writer.writeheader()
+        for r in rows:
+          sanitized = {k: sanitize_csv_cell_value(v) for k, v in r.items()}
+          writer.writerow(sanitized)