def header_row_offset(self) -> Optional[int]:
index = None
if self.header_row_index is not None:
index = self.header_row_index
elif self.first_data_row_index:
index = self.first_data_row_index - 1
if index is not None and index < 0:
raise StopParsing('Invalid row index.')
return index
def validate_worksheet_headers(self, worksheet: Worksheet) -> None:
expected_headers = {
column.index: column.header.lower()
for column in self.columns
if column.header and column.validate_header
}
if expected_headers and self.header_row_offset is not None:
for row in worksheet.iter_rows(min_row=self.header_row_offset + 1):
columns = {
idx: col.value.strip().lower() if isinstance(
col.value, str) else col.value
for idx, col in enumerate(row) if idx in expected_headers
}
if columns != expected_headers:
file_path = self.file_path or 'file'
raise StopParsing(
(f'Incorrect column names in the file: {file_path}. '
f'Columns in file: {columns}. '
f'Expected columns: {expected_headers}.'))
break
def validate_headers(self, reader: Iterator[List[str]]) -> None:
expected_headers = {
column.index: column.header.lower()
for column in self.columns
if column.header and column.validate_header
}
if expected_headers and self.header_row_offset is not None:
for row_index, row in enumerate(reader):
if row_index >= self.header_row_offset:
columns = {
idx:
col.strip().lower() if isinstance(col, str) else col
for idx, col in enumerate(row)
if idx in expected_headers
}
if columns != expected_headers:
file_path = self.file_path or 'file'
raise StopParsing((
f'Incorrect column names in the file: {file_path}. '
f'Columns in file: {columns}. '
f'Expected columns: {expected_headers}.'))
break