def _start(self):
self.blocks_output_file = get_file_handle(self.blocks_output,
binary=True)
self.transactions_output_file = get_file_handle(
self.transactions_output, binary=True)
self.blocks_exporter = CsvItemExporter(self.blocks_output_file)
self.transactions_exporter = CsvItemExporter(
self.transactions_output_file)
def _start(self):
super()._start()
self.blocks_output_file = get_file_handle(self.blocks_output, binary=True)
self.blocks_exporter = CsvItemExporter(
self.blocks_output_file, fields_to_export=self.block_fields_to_export)
self.transactions_output_file = get_file_handle(self.transactions_output, binary=True)
self.transactions_exporter = CsvItemExporter(
self.transactions_output_file, fields_to_export=self.transaction_fields_to_export)
def get_item_sink(output_file):
fh = get_file_handle(output_file, 'w')
if output_file.endswith('.csv'):
set_max_field_size_limit()
writer = None
def sink(item):
nonlocal writer
if writer is None:
fields = list(six.iterkeys(item))
writer = csv.DictWriter(fh,
fieldnames=fields,
extrasaction='ignore')
writer.writeheader()
writer.writerow(item)
else:
def sink(item):
fh.write(json.dumps(item) + '\n')
try:
yield sink
finally:
fh.close()
def open(self):
for item_type, filename in self.filename_mapping.items():
self.file_mapping[item_type] = get_file_handle(filename,
binary=True)
self.exporter_mapping[item_type] = CsvItemExporter(
self.file_mapping[item_type],
fields_to_export=self.field_mapping[item_type])
def _start(self):
# Using bounded executor prevents unlimited queue growth
# and allows monitoring in-progress futures and failing fast in case of errors.
self.executor = FailSafeExecutor(BoundedExecutor(1, self.max_workers))
self.blocks_output_file = get_file_handle(self.blocks_output,
binary=True)
self.blocks_exporter = CsvItemExporter(
self.blocks_output_file,
fields_to_export=self.block_fields_to_export)
self.transactions_output_file = get_file_handle(
self.transactions_output, binary=True)
self.transactions_exporter = CsvItemExporter(
self.transactions_output_file,
fields_to_export=self.transaction_fields_to_export)
def _start(self):
super()._start()
self.output_file = get_file_handle(self.output,
binary=True,
create_parent_dirs=True)
self.exporter = CsvItemExporter(self.output_file,
fields_to_export=self.fields_to_export)
def open(self):
for item_type, filename in self.filename_mapping.items():
file = get_file_handle(filename, binary=True)
fields = self.field_mapping[item_type]
self.file_mapping[item_type] = file
if str(filename).endswith('.json'):
item_exporter = JsonLinesItemExporter(file, fields_to_export=fields)
else:
item_exporter = CsvItemExporter(file, fields_to_export=fields)
self.exporter_mapping[item_type] = item_exporter
self.counter_mapping[item_type] = AtomicCounter()
def get_item_iterable(input_file):
fh = get_file_handle(input_file, 'r')
if input_file.endswith('.csv'):
set_max_field_size_limit()
reader = csv.DictReader(fh)
else:
reader = (json.loads(line) for line in fh)
try:
yield reader
finally:
fh.close()
def _start(self):
self.output_file = get_file_handle(self.output, binary=True)
self.exporter = CsvItemExporter(self.output_file)
def _start(self):
super()._start()
self.output_file = get_file_handle(self.output,
binary=True,
create_parent_dirs=True)
