def test_fails_on_ods_from_excel(self):
excel_path = dev_test.path_to_test_data('valid_customers.xls')
try:
list(rowio.ods_rows(excel_path))
self.fail()
except errors.DataFormatError as anticipated_error:
dev_test.assert_fnmatches(self, str(anticipated_error), '*: cannot uncompress ODS spreadsheet: *')
def test_fails_on_ods_without_content_xml(self):
broken_ods_path = dev_test.path_to_test_data('broken_without_content_xml.ods')
try:
list(rowio.ods_rows(broken_ods_path))
self.fail('expected DataFormatError')
except errors.DataFormatError as error:
error_message = '%s' % error
self.assertTrue(
'cannot extract content.xml' in error_message, 'error_message=%r' % error_message)
def test_fails_on_ods_from_csv(self):
broken_ods_path = dev_test.path_to_test_data('customers.csv')
try:
list(rowio.ods_rows(broken_ods_path))
self.fail('expected DataFormatError')
except errors.DataFormatError as error:
error_message = '%s' % error
self.assertTrue(
'cannot uncompress ODS spreadsheet:' in error_message, 'error_message=%r' % error_message)
def test_fails_on_non_existent_ods_sheet(self):
ods_path = dev_test.path_to_test_data('valid_customers.ods')
try:
list(rowio.ods_rows(ods_path, 123))
self.fail('expected DataFormatError')
except errors.DataFormatError as error:
error_message = '%s' % error
self.assertTrue(
'ODS must contain at least' in error_message, 'error_message=%r' % error_message)
def to_csv(ods_source_path, csv_target_path, dialect='excel', sheet=1):
"""
Convert ODS file in `odsFilePath` to CSV using `dialect` and store the result in `csvTargetPath`.
"""
assert ods_source_path is not None
assert csv_target_path is not None
assert dialect is not None
assert sheet is not None
assert sheet >= 1
with io.open(csv_target_path, 'w', newline='', encoding='utf-8') as csv_target_file:
csv_writer = _compat.csv_writer(csv_target_file, dialect)
csv_writer.writerows(rowio.ods_rows(ods_source_path, sheet))
def toCsv(odsFilePath, csvTargetPath, dialect="excel", sheet=1):
"""
Convert ODS file in `odsFilePath` to CSV using `dialect` and store the result in `csvTargetPath`.
"""
assert odsFilePath is not None
assert csvTargetPath is not None
assert dialect is not None
assert sheet is not None
assert sheet >= 1
with io.open(csvTargetPath, 'w', newline='',
encoding='utf-8') as csvTargetFile:
csv_writer = _compat.csv_writer(csvTargetFile, dialect)
csv_writer.writerows(rowio.ods_rows(odsFilePath, sheet))
def _raw_rows(self):
data_format = self.cid.data_format
format = data_format.format
if format == data.FORMAT_EXCEL:
return rowio.excel_rows(self._source_data_stream_or_path, data_format.sheet)
elif format == data.FORMAT_DELIMITED:
return rowio.delimited_rows(self._source_data_stream_or_path, data_format)
elif format == data.FORMAT_FIXED:
return rowio.fixed_rows(
self._source_data_stream_or_path, data_format.encoding, interface.field_names_and_lengths(self.cid),
data_format.line_delimiter)
elif format == data.FORMAT_ODS:
return rowio.ods_rows(self._source_data_stream_or_path, data_format.sheet)
else:
assert False, 'format=%r' % format
def _raw_rows(self):
data_format = self.cid.data_format
format = data_format.format
if format == data.FORMAT_EXCEL:
return rowio.excel_rows(self._source_data_stream_or_path, data_format.sheet)
elif format == data.FORMAT_DELIMITED:
return rowio.delimited_rows(self._source_data_stream_or_path, data_format)
elif format == data.FORMAT_FIXED:
return rowio.fixed_rows(
self._source_data_stream_or_path, data_format.encoding, interface.field_names_and_lengths(self.cid),
data_format.line_delimiter)
elif format == data.FORMAT_ODS:
return rowio.ods_rows(self._source_data_stream_or_path, data_format.sheet)
else:
assert False, 'format=%r' % format
def to_rst(ods_source_path,
rst_target_path,
first_row_is_heading=True,
sheet=1):
"""
Convert ODS file in `odsFilePath` to reStructuredText and store the result in `rstTargetPath`.
"""
assert ods_source_path is not None
assert rst_target_path is not None
assert sheet >= 1
rows = list(rowio.ods_rows(ods_source_path, sheet))
# Find out the length of each column.
lengths = []
is_first_row = True
for row in rows:
for column_index in range(len(row)):
item = row[column_index]
item_length = len(item)
if is_first_row or (column_index == len(lengths)):
lengths.append(item_length)
is_first_row = False
elif lengths[column_index] < item_length:
lengths[column_index] = item_length
if not lengths:
raise ValueError("file must contain columns: \"%s\"" % ods_source_path)
for column_index in range(len(lengths)):
if lengths[column_index] == 0:
raise ValueError("column %d in file %r must not always be empty" %
(column_index + 1, ods_source_path))
with io.open(rst_target_path, "w", encoding='utf-8') as rst_target_file:
is_first_row = first_row_is_heading
_write_rst_separator_line(rst_target_file, lengths, "-")
for row in rows:
_write_rst_row(rst_target_file, lengths, row)
if is_first_row:
line_separator = "="
is_first_row = False
else:
line_separator = "-"
_write_rst_separator_line(rst_target_file, lengths, line_separator)
def to_rst(ods_source_path, rst_target_path, first_row_is_heading=True, sheet=1):
"""
Convert ODS file in `odsFilePath` to reStructuredText and store the result in `rstTargetPath`.
"""
assert ods_source_path is not None
assert rst_target_path is not None
assert sheet >= 1
rows = list(rowio.ods_rows(ods_source_path, sheet))
# Find out the length of each column.
lengths = []
is_first_row = True
for row in rows:
for column_index in range(len(row)):
item = row[column_index]
item_length = len(item)
if is_first_row or (column_index == len(lengths)):
lengths.append(item_length)
is_first_row = False
elif lengths[column_index] < item_length:
lengths[column_index] = item_length
if not lengths:
raise ValueError("file must contain columns: \"%s\"" % ods_source_path)
for column_index in range(len(lengths)):
if lengths[column_index] == 0:
raise ValueError("column %d in file %r must not always be empty" % (column_index + 1, ods_source_path))
with io.open(rst_target_path, "w", encoding='utf-8') as rst_target_file:
is_first_row = first_row_is_heading
_write_rst_separator_line(rst_target_file, lengths, "-")
for row in rows:
_write_rst_row(rst_target_file, lengths, row)
if is_first_row:
line_separator = "="
is_first_row = False
else:
line_separator = "-"
_write_rst_separator_line(rst_target_file, lengths, line_separator)
def test_can_read_ods_rows(self):
ods_path = dev_test.path_to_test_data('valid_customers.ods')
self._assert_rows_contain_data(rowio.ods_rows(ods_path))
