rcv.parse_csv: add parse_rcv_compra_X_csv_file

cl_sii/dte/parse.py

@@ -131,7 +131,7 @@ def parse_dte_xml(xml_doc: XmlElement) -> data_models.DteDataL2:
     # TODO: change response type to a dataclass like 'DteXmlData'.
     # TODO: separate the XML parsing stage from the deserialization stage, which could be
     #   performed by XML-agnostic code (perhaps using Marshmallow or data clacases?).
-    #   See :class:`cl_sii.rcv.parse.RcvCsvRowSchema`.
+    #   See :class:`cl_sii.rcv.parse_csv.RcvVentaCsvRowSchema`.
 
     if not isinstance(xml_doc, (XmlElement, XmlElementTree)):
         raise TypeError("'xml_doc' must be an 'XmlElement'.")

cl_sii/rcv/__init__.py

@@ -9,64 +9,3 @@
     http://www.sii.cl/preguntas_frecuentes/catastro/001_012_6971.htm
 
 """
-import csv
-import io
-from typing import Callable
-
-from . import parse
-
-
-def process_rcv_csv_file(
-    text_stream: io.TextIOBase,
-    rcv_owner_rut: str,
-    row_data_handler: Callable,
-    max_data_rows: int = None,
-) -> int:
-    """
-    Process a RCV CSV file.
-
-    Processing steps:
-    - Create a CSV reader, with auto-detection of header names (first row).
-    - Instantiate an schema to parse and deserialize each row.
-    - For each data row:
-        - Using an appropriate schema, deserialize the raw data.
-        - Apply ``row_data_handler`` to the deserialization output.
-
-    :param text_stream: a file-like object, not necessarily a real file
-    :param rcv_owner_rut: RCV file owner's RUT
-    :param row_data_handler: function be called with parsed row data
-    :param max_data_rows: max number of data rows to process (raise exception if exceeded);
-        ``None`` means no limit
-    :return: number of data rows processed
-
-    """
-    # TODO: convert to iterator. That way we do not need the 'row_data_handler' and we can also use
-    #   the same function to retrieve the collection of deserialized rows.
-
-    csv_reader = parse.create_rcv_csv_reader(text_stream, expected_fields_strict=True)
-    schema = parse.RcvCsvRowSchema(context=dict(receptor_rut=rcv_owner_rut))
-
-    try:
-        for row_ix, row_data in enumerate(csv_reader, start=1):
-            if max_data_rows is not None and row_ix > max_data_rows:
-                # TODO: custom exception
-                raise Exception("Exceeded 'max_data_rows' value: {}.".format(max_data_rows))
-
-            try:
-                deserialized_row_data = schema.deserialize_csv_row(row_data)
-            except Exception as exc:
-                exc_msg = "Error deserializing row {} of CSV file: {}".format(row_ix, exc)
-                raise Exception(exc_msg) from exc
-            try:
-                row_data_handler(row_ix, deserialized_row_data)
-            except Exception as exc:
-                exc_msg = "Error in row_data_handler for row {} of CSV file: {}".format(row_ix, exc)
-                raise Exception(exc_msg) from exc
-
-        # The first row in the CSV file is not a data row; it is the headers row.
-        rows_processed = csv_reader.line_num - 1
-    except csv.Error as exc:
-        exc_msg = "CSV error for line {} of CSV file: {}".format(csv_reader.line_num, exc)
-        raise Exception(exc_msg) from exc
-
-    return rows_processed