def test_export_blocks_job(tmpdir, batch_size, resource_group):
receipts_output_file = tmpdir.join('actual_receipts.csv')
logs_output_file = tmpdir.join('actual_logs.csv')
job = ExportReceiptsJob(tx_hashes_iterable=[
'0x04cbcb236043d8fb7839e07bbc7f5eed692fb2ca55d897f1101eac3e3ad4fab8',
'0x463d53f0ad57677a3b430a007c1c31d15d62c37fab5eee598551697c297c235c',
'0x05287a561f218418892ab053adfb3d919860988b19458c570c5c30f51c146f02',
'0xcea6f89720cc1d2f46cc7a935463ae0b99dd5fad9c91bb7357de5421511cee49'
],
batch_size=batch_size,
ipc_wrapper=ThreadLocalProxy(
lambda: MockIPCWrapper(
lambda file: read_resource(
resource_group, file))),
max_workers=5,
item_exporter=export_receipts_job_item_exporter(
receipts_output_file, logs_output_file),
export_receipts=receipts_output_file is not None,
export_logs=logs_output_file is not None)
job.run()
compare_lines_ignore_order(
read_resource(resource_group, 'expected_receipts.csv'),
read_file(receipts_output_file))
compare_lines_ignore_order(
read_resource(resource_group, 'expected_logs.csv'),
read_file(logs_output_file))
def test_export_receipts_job(tmpdir, batch_size, transaction_hashes,
output_format, resource_group,
web3_provider_type):
receipts_output_file = tmpdir.join('actual_receipts.' + output_format)
logs_output_file = tmpdir.join('actual_logs.' + output_format)
job = ExportReceiptsJob(
transaction_hashes_iterable=transaction_hashes,
batch_size=batch_size,
batch_web3_provider=ThreadLocalProxy(lambda: get_web3_provider(
web3_provider_type,
lambda file: read_resource(resource_group, file),
batch=True)),
max_workers=5,
item_exporter=receipts_and_logs_item_exporter(receipts_output_file,
logs_output_file),
export_receipts=receipts_output_file is not None,
export_logs=logs_output_file is not None)
job.run()
compare_lines_ignore_order(
read_resource(resource_group, 'expected_receipts.' + output_format),
read_file(receipts_output_file))
compare_lines_ignore_order(
read_resource(resource_group, 'expected_logs.' + output_format),
read_file(logs_output_file))
def export_receipts_and_logs(batch_size, transaction_hashes, provider_uri, max_workers, receipts_output, logs_output,
chain='ethereum'):
"""Exports receipts and logs."""
provider_uri = check_classic_provider_uri(chain, provider_uri)
with smart_open(transaction_hashes, 'r') as transaction_hashes_file:
job = ExportReceiptsJob(
transaction_hashes_iterable=(transaction_hash.strip() for transaction_hash in transaction_hashes_file),
batch_size=batch_size,
batch_web3_provider=ThreadLocalProxy(lambda: get_provider_from_uri(provider_uri, batch=True)),
max_workers=max_workers,
item_exporter=receipts_and_logs_item_exporter(receipts_output, logs_output),
export_receipts=receipts_output is not None,
export_logs=logs_output is not None)
job.run()
def _export_receipts_and_logs(self, transactions):
exporter = InMemoryItemExporter(item_types=['receipt', 'log'])
job = ExportReceiptsJob(
transaction_hashes_iterable=(transaction['hash']
for transaction in transactions),
batch_size=self.batch_size,
batch_web3_provider=self.batch_web3_provider,
max_workers=self.max_workers,
item_exporter=exporter,
export_receipts=self._should_export(EntityType.RECEIPT),
export_logs=self._should_export(EntityType.LOG))
job.run()
receipts = exporter.get_items('receipt')
logs = exporter.get_items('log')
return receipts, logs
def export_receipts_and_logs(
self, transactions: Iterable) -> Tuple[Iterable, Iterable]:
"""Export receipts and logs for specified transaction hashes."""
exporter = InMemoryItemExporter(item_types=["receipt", "log"])
job = ExportReceiptsJob(
transaction_hashes_iterable=(transaction["hash"]
for transaction in transactions),
batch_size=self.batch_size,
batch_web3_provider=self.batch_web3_provider,
max_workers=self.max_workers,
item_exporter=exporter,
export_receipts=True,
export_logs=False,
)
job.run()
receipts = exporter.get_items("receipt")
logs = exporter.get_items("log")
return receipts, logs
def test_export_receipts_job(tmpdir, batch_size, tx_hashes, resource_group):
receipts_output_file = tmpdir.join('actual_receipts.csv')
logs_output_file = tmpdir.join('actual_logs.csv')
job = ExportReceiptsJob(
tx_hashes_iterable=tx_hashes,
batch_size=batch_size,
batch_web3_provider=ThreadLocalProxy(lambda: MockBatchWeb3Provider(lambda file: read_resource(resource_group, file))),
max_workers=5,
item_exporter=export_receipts_job_item_exporter(receipts_output_file, logs_output_file),
export_receipts=receipts_output_file is not None,
export_logs=logs_output_file is not None
)
job.run()
compare_lines_ignore_order(
read_resource(resource_group, 'expected_receipts.csv'), read_file(receipts_output_file)
)
compare_lines_ignore_order(
read_resource(resource_group, 'expected_logs.csv'), read_file(logs_output_file)
)
parser.add_argument(
'--receipts-output',
default=None,
type=str,
help=
'The output file for receipts. If not provided receipts will not be exported. '
'Use "-" for stdout')
parser.add_argument(
'--logs-output',
default=None,
type=str,
help=
'The output file for receipt logs. If not provided receipt logs will not be exported. '
'Use "-" for stdout')
args = parser.parse_args()
with smart_open(args.tx_hashes, 'r') as tx_hashes_file:
job = ExportReceiptsJob(
tx_hashes_iterable=(tx_hash.strip() for tx_hash in tx_hashes_file),
batch_size=args.batch_size,
batch_web3_provider=ThreadLocalProxy(
lambda: get_provider_from_uri(args.provider_uri, batch=True)),
max_workers=args.max_workers,
item_exporter=receipts_and_logs_item_exporter(args.receipts_output,
args.logs_output),
export_receipts=args.receipts_output is not None,
export_logs=args.logs_output is not None)
job.run()
parser.add_argument(
'--receipts-output',
default=None,
type=str,
help=
'The output file for receipts. If not provided receipts will not be exported. '
'Use "-" for stdout')
parser.add_argument(
'--logs-output',
default=None,
type=str,
help=
'The output file for receipt logs. If not provided receipt logs will not be exported. '
'Use "-" for stdout')
args = parser.parse_args()
with smart_open(args.tx_hashes, 'r') as tx_hashes_file:
job = ExportReceiptsJob(
tx_hashes_iterable=(tx_hash.strip() for tx_hash in tx_hashes_file),
batch_size=args.batch_size,
ipc_wrapper=ThreadLocalProxy(
lambda: IPCWrapper(args.ipc_path, timeout=args.ipc_timeout)),
max_workers=args.max_workers,
item_exporter=export_receipts_job_item_exporter(
args.receipts_output, args.logs_output),
export_receipts=args.receipts_output is not None,
export_logs=args.logs_output is not None)
job.run()
def export_all_common(partitions, output_dir, provider_uri, max_workers,
batch_size):
for batch_start_block, batch_end_block, partition_dir in partitions:
# # # start # # #
start_time = time()
padded_batch_start_block = str(batch_start_block).zfill(8)
padded_batch_end_block = str(batch_end_block).zfill(8)
block_range = '{padded_batch_start_block}-{padded_batch_end_block}'.format(
padded_batch_start_block=padded_batch_start_block,
padded_batch_end_block=padded_batch_end_block,
)
file_name_suffix = '{padded_batch_start_block}_{padded_batch_end_block}'.format(
padded_batch_start_block=padded_batch_start_block,
padded_batch_end_block=padded_batch_end_block,
)
# # # blocks_and_transactions # # #
blocks_output_dir = '{output_dir}/blocks{partition_dir}'.format(
output_dir=output_dir,
partition_dir=partition_dir,
)
os.makedirs(os.path.dirname(blocks_output_dir), exist_ok=True)
transactions_output_dir = '{output_dir}/transactions{partition_dir}'.format(
output_dir=output_dir,
partition_dir=partition_dir,
)
os.makedirs(os.path.dirname(transactions_output_dir), exist_ok=True)
blocks_file = '{blocks_output_dir}/blocks_{file_name_suffix}.csv'.format(
blocks_output_dir=blocks_output_dir,
file_name_suffix=file_name_suffix,
)
transactions_file = '{transactions_output_dir}/transactions_{file_name_suffix}.csv'.format(
transactions_output_dir=transactions_output_dir,
file_name_suffix=file_name_suffix,
)
logger.info('Exporting blocks {block_range} to {blocks_file}'.format(
block_range=block_range,
blocks_file=blocks_file,
))
logger.info(
'Exporting transactions from blocks {block_range} to {transactions_file}'
.format(
block_range=block_range,
transactions_file=transactions_file,
))
job = ExportBlocksJob(
start_block=batch_start_block,
end_block=batch_end_block,
batch_size=batch_size,
batch_web3_provider=ThreadLocalProxy(
lambda: get_provider_from_uri(provider_uri, batch=True)),
max_workers=max_workers,
item_exporter=blocks_and_transactions_item_exporter(
blocks_file, transactions_file),
export_blocks=blocks_file is not None,
export_transactions=transactions_file is not None)
job.run()
# # # token_transfers # # #
token_transfers_file = None
if is_log_filter_supported(provider_uri):
token_transfers_output_dir = '{output_dir}/token_transfers{partition_dir}'.format(
output_dir=output_dir,
partition_dir=partition_dir,
)
os.makedirs(os.path.dirname(token_transfers_output_dir),
exist_ok=True)
token_transfers_file = '{token_transfers_output_dir}/token_transfers_{file_name_suffix}.csv'.format(
token_transfers_output_dir=token_transfers_output_dir,
file_name_suffix=file_name_suffix,
)
logger.info(
'Exporting ERC20 transfers from blocks {block_range} to {token_transfers_file}'
.format(
block_range=block_range,
token_transfers_file=token_transfers_file,
))
job = ExportTokenTransfersJob(
start_block=batch_start_block,
end_block=batch_end_block,
batch_size=batch_size,
web3=ThreadLocalProxy(
lambda: Web3(get_provider_from_uri(provider_uri))),
item_exporter=token_transfers_item_exporter(
token_transfers_file),
max_workers=max_workers)
job.run()
# # # receipts_and_logs # # #
cache_output_dir = '{output_dir}/.tmp{partition_dir}'.format(
output_dir=output_dir,
partition_dir=partition_dir,
)
os.makedirs(os.path.dirname(cache_output_dir), exist_ok=True)
transaction_hashes_file = '{cache_output_dir}/transaction_hashes_{file_name_suffix}.csv'.format(
cache_output_dir=cache_output_dir,
file_name_suffix=file_name_suffix,
)
logger.info(
'Extracting hash column from transaction file {transactions_file}'.
format(transactions_file=transactions_file, ))
extract_csv_column_unique(transactions_file, transaction_hashes_file,
'hash')
receipts_output_dir = '{output_dir}/receipts{partition_dir}'.format(
output_dir=output_dir,
partition_dir=partition_dir,
)
os.makedirs(os.path.dirname(receipts_output_dir), exist_ok=True)
logs_output_dir = '{output_dir}/logs{partition_dir}'.format(
output_dir=output_dir,
partition_dir=partition_dir,
)
os.makedirs(os.path.dirname(logs_output_dir), exist_ok=True)
receipts_file = '{receipts_output_dir}/receipts_{file_name_suffix}.csv'.format(
receipts_output_dir=receipts_output_dir,
file_name_suffix=file_name_suffix,
)
logs_file = '{logs_output_dir}/logs_{file_name_suffix}.csv'.format(
logs_output_dir=logs_output_dir,
file_name_suffix=file_name_suffix,
)
logger.info(
'Exporting receipts and logs from blocks {block_range} to {receipts_file} and {logs_file}'
.format(
block_range=block_range,
receipts_file=receipts_file,
logs_file=logs_file,
))
with smart_open(transaction_hashes_file, 'r') as transaction_hashes:
job = ExportReceiptsJob(
transaction_hashes_iterable=(
transaction_hash.strip()
for transaction_hash in transaction_hashes),
batch_size=batch_size,
batch_web3_provider=ThreadLocalProxy(
lambda: get_provider_from_uri(provider_uri, batch=True)),
max_workers=max_workers,
item_exporter=receipts_and_logs_item_exporter(
receipts_file, logs_file),
export_receipts=receipts_file is not None,
export_logs=logs_file is not None)
job.run()
# # # contracts # # #
contract_addresses_file = '{cache_output_dir}/contract_addresses_{file_name_suffix}.csv'.format(
cache_output_dir=cache_output_dir,
file_name_suffix=file_name_suffix,
)
logger.info(
'Extracting contract_address from receipt file {receipts_file}'.
format(receipts_file=receipts_file))
extract_csv_column_unique(receipts_file, contract_addresses_file,
'contract_address')
contracts_output_dir = '{output_dir}/contracts{partition_dir}'.format(
output_dir=output_dir,
partition_dir=partition_dir,
)
os.makedirs(os.path.dirname(contracts_output_dir), exist_ok=True)
contracts_file = '{contracts_output_dir}/contracts_{file_name_suffix}.csv'.format(
contracts_output_dir=contracts_output_dir,
file_name_suffix=file_name_suffix,
)
logger.info(
'Exporting contracts from blocks {block_range} to {contracts_file}'
.format(
block_range=block_range,
contracts_file=contracts_file,
))
with smart_open(contract_addresses_file,
'r') as contract_addresses_file:
contract_addresses = (
contract_address.strip()
for contract_address in contract_addresses_file
if contract_address.strip())
job = ExportContractsJob(
contract_addresses_iterable=contract_addresses,
batch_size=batch_size,
batch_web3_provider=ThreadLocalProxy(
lambda: get_provider_from_uri(provider_uri, batch=True)),
item_exporter=contracts_item_exporter(contracts_file),
max_workers=max_workers)
job.run()
# # # tokens # # #
if token_transfers_file is not None:
token_addresses_file = '{cache_output_dir}/token_addresses_{file_name_suffix}'.format(
cache_output_dir=cache_output_dir,
file_name_suffix=file_name_suffix,
)
logger.info(
'Extracting token_address from token_transfers file {token_transfers_file}'
.format(token_transfers_file=token_transfers_file, ))
extract_csv_column_unique(token_transfers_file,
token_addresses_file, 'token_address')
tokens_output_dir = '{output_dir}/tokens{partition_dir}'.format(
output_dir=output_dir,
partition_dir=partition_dir,
)
os.makedirs(os.path.dirname(tokens_output_dir), exist_ok=True)
tokens_file = '{tokens_output_dir}/tokens_{file_name_suffix}.csv'.format(
tokens_output_dir=tokens_output_dir,
file_name_suffix=file_name_suffix,
)
logger.info(
'Exporting tokens from blocks {block_range} to {tokens_file}'.
format(
block_range=block_range,
tokens_file=tokens_file,
))
with smart_open(token_addresses_file, 'r') as token_addresses:
job = ExportTokensJob(
token_addresses_iterable=(
token_address.strip()
for token_address in token_addresses),
web3=ThreadLocalProxy(
lambda: Web3(get_provider_from_uri(provider_uri))),
item_exporter=tokens_item_exporter(tokens_file),
max_workers=max_workers)
job.run()
# # # finish # # #
shutil.rmtree(os.path.dirname(cache_output_dir))
end_time = time()
time_diff = round(end_time - start_time, 5)
logger.info(
'Exporting blocks {block_range} took {time_diff} seconds'.format(
block_range=block_range,
time_diff=time_diff,
))