def connect_to_dynamo(): """ This function gets the connection to dynamodb. The only possibly exception it will throw is IOError and there is not a lot we can do to handle it because dynamo has scaling retry times and in the case that dynamo goes down we will have bigger things to worry about. This is currently not an issue. We discussed serving pages directly from neo in the case that dynamo is down but because we currently use AWS for a lot of our services, if dynamo is down AWS will most likely be down. Also there will be three instances of dynamo on our AWS cloud. :return: """ if settings.DYNAMO_IP is None: conn = DynamoDBConnection( aws_secret_access_key=settings.AWS_SECRET_ACCESS_KEY, aws_access_key_id=settings.AWS_ACCESS_KEY_ID, ) else: conn = DynamoDBConnection( host=settings.DYNAMO_IP, port=8000, aws_secret_access_key='anything', is_secure=False, ) return conn
def __init__(self, aws_access_key, aws_secret_access_key, is_secure, is_remote=False, host=None, port=None, in_memory=False, auth_func=None): if auth_func and not auth_func(): raise self.AuthException() self.host = host self.port = port self.is_secure = is_secure self.is_remote = is_remote self.in_memory = in_memory kwargs = { 'aws_access_key_id': aws_access_key, 'aws_secret_access_key': aws_secret_access_key, 'is_secure': is_secure } if not is_remote: kwargs['host'] = host kwargs['port'] = port self.local_db = LocalDb(port, in_memory) self.connection = DynamoDBConnection(**kwargs)
def getDynamoDBConnection(config=None, endpoint=None, port=None, local=False): if local: db = DynamoDBConnection( host=endpoint, port=port, aws_secret_access_key='ticTacToeSampleApp', aws_access_key_id='ticTacToeSampleApp', is_secure=False) else: if config is not None: params = { 'region': config.get('dynamodb', 'region'), 'host': config.get('dynamodb', 'endpoint'), 'is_secure': True } if endpoint is not None: params['host'] = endpoint del params['region'] if config.has_option('dynamodb', 'aws_access_key_id'): params['aws_access_key_id'] = config.get('dynamodb', 'aws_access_key_id') params['aws_secret_access_key'] = config.get('dynamodb', 'aws_secret_access_key') db = DynamoDBConnection(**params) else: if endpoint: db = DynamoDBConnection(host=endpoint) else: db = DynamoDBConnection() return db
def setUp(self): self.todaysKey = datetime.utcnow().strftime("%Y_%m_%d") conn = DynamoDBConnection(host='localhost', port=8000, aws_access_key_id='unit_test', aws_secret_access_key='unit_test', is_secure=False) try: msg_table = Table.create( db._message_table, schema=[HashKey('date_string'), RangeKey('date')], connection=conn) except JSONResponseError as e: conn.delete_table(db._message_table) #print("Could not create test table: {0}".format(e)) with open('test_data.json') as f: self.test_json = f.readline() with open('test2_data.json', 'w') as f: utc = datetime.utcnow() utc_midnight = datetime(utc.year, utc.month, utc.day) msgs = generateMessageEveryHourSince(utc_midnight) f.write(json.dumps(msgs, cls=MessageEncoder))
class Storage(): def __init__(self, storage_conf): self.conf = storage_conf self.max_results = storage_conf["max_results"] self.publishers = self.conf["publishers"] if self.conf["region"] == "localhost": from boto.dynamodb2.layer1 import DynamoDBConnection self.connection = DynamoDBConnection( host='localhost', port=8000, aws_secret_access_key='anything', is_secure=False) else: self.connection = boto.dynamodb2.connect_to_region(self.conf["region"]) self.tables = dict() for prod in self.publishers: self.tables[prod] = Table(self.connection, max_results=self.max_results, **self.conf[prod]) def close(self): """ Closes the connection. This allows you to use with contextlib's closing. Mostly necessary for the test DB which seems to only allow a single connection. """ self.connection.close()
def _make_table(table_func, tablename, read_throughput, write_throughput): """Private common function to make a table with a table func""" db = DynamoDBConnection() dblist = db.list_tables()["TableNames"] if tablename not in dblist: return table_func(tablename, read_throughput, write_throughput) else: return Table(tablename)
def __init__(self, index_url, access_key, secret_access_key): url = urlparse.urlparse(index_url) self.boto_connection = DynamoDBConnection( host=url.hostname, port=url.port, aws_access_key_id=access_key, aws_secret_access_key=secret_access_key, is_secure=False)
def get_rotating_message_table(prefix="message", delta=0): """Gets the message table for the current month.""" db = DynamoDBConnection() dblist = db.list_tables()["TableNames"] tablename = make_rotating_tablename(prefix, delta) if tablename not in dblist: return create_rotating_message_table(prefix=prefix, delta=delta) else: return Table(tablename)
def getallmissions(): missions = [] conn = DynamoDBConnection() tables = conn.list_tables() table = Table('missions', connection=conn) results = conn.scan('missions') for result in results['Items']: print result return results['Items']
def get_rotating_message_table(prefix="message", delta=0, date=None): """Gets the message table for the current month.""" db = DynamoDBConnection() dblist = db.list_tables()["TableNames"] tablename = make_rotating_tablename(prefix, delta, date) if tablename not in dblist: return create_rotating_message_table(prefix=prefix, delta=delta) else: return Table(tablename)
def test_custom_tablename(self): db = DynamoDBConnection() db_name = "storage_%s" % uuid.uuid4() dblist = db.list_tables()["TableNames"] assert db_name not in dblist create_storage_table(db_name) dblist = db.list_tables()["TableNames"] assert db_name in dblist
def delete_dynamodb(): conn = DynamoDBConnection(aws_access_key_id=AWS_ACCESS_KEY, aws_secret_access_key=AWS_SECRET_ACCESS_KEY, region = RegionInfo(name=REGION, endpoint='dynamodb.{0}.amazonaws.com'.format(REGION))) conn.delete_table(EASY_LIST_TBL) conn.close()
def Init(): """ Connect to DynamoDB Local. If you want to connect to the real DynamoDB set the 'local' variable below to Fals, but make sure either you have a .boto file or you pass both the aws_access_key_id and aws_secret_access_key parameters to the create (this code fetches them from settings.cfg). """ local = True if local: # Connect to local DynamoDB server. Make sure you have that running first. conn = DynamoDBConnection(host='localhost', port=8001, aws_secret_access_key='anything', is_secure=False) else: # Connect to the real DynamoDB. config = ConfigParser.RawConfigParser() config.read("settings.cfg") id = config.get('DynamoDB', 'aws_access_key_id') key = config.get('DynamoDB', 'aws_secret_access_key') conn = boto.dynamodb2.connect_to_region('us-west-2', aws_access_key_id=id, aws_secret_access_key=key) # Get a list of all tables from DynamoDB. tables = conn.list_tables() #print "Tables:", tables """ If there isn't an employees table then create it. The table has a primary key of the employee type and id, allowing you to query them. It has a secondary index on the employee type and title, allowing you to query them as well. """ if 'employees' not in tables['TableNames']: # Create table of employees print "Creating new table" employees = Table.create( 'employees', schema=[HashKey('etype'), RangeKey('id')], indexes=[ AllIndex('TitleIndex', parts=[HashKey('etype'), RangeKey('title')]) ], connection=conn) # Wait for table to be created (DynamoDB has eventual consistency) while True: time.sleep(5) try: conn.describe_table('employees') except Exception, e: print e else: break
def test_dynamodb(self): host = os.getenv('DYNAMODB_PORT_8000_TCP_ADDR') port = int(os.getenv('DYNAMODB_PORT_8000_TCP_PORT')) conn = DynamoDBConnection(host=host, port=port, aws_access_key_id='anything', aws_secret_access_key='anything', is_secure=False) tables = conn.list_tables()
def getuserlast(user): conn = DynamoDBConnection() results = conn.query( 'gpstrack', key_conditions={'user': {'AttributeValueList': [{'S': user}], 'ComparisonOperator': 'EQ'}}, scan_index_forward=False, limit=1 ) #print results conn.close() return results
def Init(): """ Connect to DynamoDB Local. If you want to connect to the real DynamoDB set the 'local' variable below to Fals, but make sure either you have a .boto file or you pass both the aws_access_key_id and aws_secret_access_key parameters to the create (this code fetches them from settings.cfg). """ local = True if local: # Connect to local DynamoDB server. Make sure you have that running first. conn = DynamoDBConnection( host='localhost', port=8001, aws_secret_access_key='anything', is_secure=False) else: # Connect to the real DynamoDB. config = ConfigParser.RawConfigParser() config.read("settings.cfg") id = config.get('DynamoDB', 'aws_access_key_id') key = config.get('DynamoDB', 'aws_secret_access_key') conn = boto.dynamodb2.connect_to_region('us-west-2', aws_access_key_id = id, aws_secret_access_key = key) # Get a list of all tables from DynamoDB. tables = conn.list_tables() #print "Tables:", tables """ If there isn't an employees table then create it. The table has a primary key of the employee type and id, allowing you to query them. It has a secondary index on the employee type and title, allowing you to query them as well. """ if 'employees' not in tables['TableNames']: # Create table of employees print "Creating new table" employees = Table.create('employees', schema = [HashKey('etype'), RangeKey('id')], indexes = [AllIndex('TitleIndex', parts = [ HashKey('etype'), RangeKey('title')])], connection = conn) # Wait for table to be created (DynamoDB has eventual consistency) while True: time.sleep(5) try: conn.describe_table('employees') except Exception, e: print e else: break
def test_dynamodb(self): host = os.getenv('DYNAMODB_PORT_8000_TCP_ADDR') port = int(os.getenv('DYNAMODB_PORT_8000_TCP_PORT')) conn = DynamoDBConnection( host=host, port=port, aws_access_key_id='anything', aws_secret_access_key='anything', is_secure=False) tables = conn.list_tables()
def test_init_region(self): dynamodb = DynamoDBConnection( aws_access_key_id='aws_access_key_id', aws_secret_access_key='aws_secret_access_key') self.assertEqual(dynamodb.region.name, 'us-east-1') dynamodb = DynamoDBConnection( region=RegionInfo(name='us-west-2', endpoint='dynamodb.us-west-2.amazonaws.com'), aws_access_key_id='aws_access_key_id', aws_secret_access_key='aws_secret_access_key', ) self.assertEqual(dynamodb.region.name, 'us-west-2')
def pytest_runtest_teardown(): conn = DynamoDBConnection() conn.delete_table(Message.get_table_name()) conn.delete_table(ChannelJoinInfo.get_table_name()) conn.delete_table(ChannelUsageLog.get_table_name()) conn.delete_table(Channel.get_table_name()) conn.delete_table(ChannelWithdrawalLog.get_table_name()) Message.create_table() ChannelWithdrawalLog.create_table() ChannelJoinInfo.create_table() ChannelUsageLog.create_table() Channel.create_table()
def tearDown(self): """Any tear down steps post test run. :returns: TODO """ conn = DynamoDBConnection(host='localhost', port=8000, aws_access_key_id='unit_test', aws_secret_access_key='unit_test', is_secure=False) conn.delete_table(db._message_table)
def setUp(self): self.dynamodb = DynamoDBConnection() self.table_name = 'test-%d' % int(time.time()) self.hash_key_name = 'username' self.hash_key_type = 'S' self.range_key_name = 'date_joined' self.range_key_type = 'N' self.read_units = 5 self.write_units = 5 self.attributes = [ { 'AttributeName': self.hash_key_name, 'AttributeType': self.hash_key_type, }, { 'AttributeName': self.range_key_name, 'AttributeType': self.range_key_type, } ] self.schema = [ { 'AttributeName': self.hash_key_name, 'KeyType': 'HASH', }, { 'AttributeName': self.range_key_name, 'KeyType': 'RANGE', }, ] self.provisioned_throughput = { 'ReadCapacityUnits': self.read_units, 'WriteCapacityUnits': self.write_units, } self.lsi = [ { 'IndexName': 'MostRecentIndex', 'KeySchema': [ { 'AttributeName': self.hash_key_name, 'KeyType': 'HASH', }, { 'AttributeName': self.range_key_name, 'KeyType': 'RANGE', }, ], 'Projection': { 'ProjectionType': 'KEYS_ONLY', } } ]
def init_tables(models_module): models = [getattr(models_module, name) for name in dir(models_module)] models = [model for model in models if inspect.isclass(model) and issubclass(model, Model) and not model == Model] conn = DynamoDBConnection() table_names = conn.list_tables()['TableNames'] for model in models: if getattr(model, 'skip_create', False): continue if model.get_table_name() in table_names: continue model.create_table() [load_fixture(model, fixture) for fixture in getattr(model, '__fixtures__', [])]
def main(): if len(sys.argv) == 2 and sys.argv[1] == 'check': print "*** Checking the table in dynamoDB, create one if not exist..." try: ddbc = DynamoDBConnection() src = ddbc.describe_table(iperf_table_name)['Table'] logs = Table(iperf_table_name, schema=[HashKey('path'),RangeKey('datetime'),]) logs.describe() sys.exit(0) except JSONResponseError: logs = Table.create(iperf_table_name, schema=[HashKey('path'),RangeKey('datetime'),]) while ddbc.describe_table(iperf_table_name)['Table']['TableStatus'] != 'ACTIVE': sleep(3) sys.exit(1) if len(sys.argv) != 4: print "usage: %s <iperf_client_name> <datetime> <iperf_server_name>" % sys.argv[0] sys.exit(2) # Store arg lists iperf_client_name = sys.argv[1] datetime = sys.argv[2] iperf_server_name = sys.argv[3] path = iperf_client_name + '-' + iperf_server_name # Retrieve dynamoDB object try: logs = Table(iperf_table_name, schema=[HashKey('path'),RangeKey('datetime'),]) tmp = logs.describe() except JSONResponseError: print "The table %s doesn't exist!" % iperf_table_name sys.exit(1) # Parse iperf log iperf = {} iperf['path'] = path iperf['datetime'] = datetime line = open(os.path.dirname(os.path.abspath(__file__))+'/log/'+datetime+'.log','r').readlines()[6] m = re.search(r"sec\s+(\d+\s+\w+)\s+(\d+\s+[\w/]+)", line) transfer = m.group(1) bandwidth = m.group(2) iperf['transfer'] = transfer iperf['bandwidth'] = bandwidth # Put the log to the dynamoDB table try: logs.put_item(data=iperf, overwrite=True) except ValidationException: pprint(iperf) except JSONResponseError: pass
def get_storage_table(tablename="storage", read_throughput=5, write_throughput=5): """Get the main storage table object Creates the table if it doesn't already exist, otherwise returns the existing table. """ db = DynamoDBConnection() dblist = db.list_tables()["TableNames"] if tablename not in dblist: return create_storage_table(tablename, read_throughput, write_throughput) else: return Table(tablename)
def get_conn(): """Return a connection to DynamoDB.""" if os.environ.get('DEBUG', False) or os.environ.get('travis', False): # In DEBUG mode - use the local DynamoDB # This also works for travis since we'll be running dynalite conn = DynamoDBConnection(host='localhost', port=8000, aws_access_key_id='TEST', aws_secret_access_key='TEST', is_secure=False) else: # Regular old production conn = DynamoDBConnection() return conn
def setUp(self): self.conn = self.conn = DynamoDBConnection( host='localhost', port=8000, aws_access_key_id='test', aws_secret_access_key='test', is_secure=False)
def test_init_host_override(self): dynamodb = DynamoDBConnection( aws_access_key_id='aws_access_key_id', aws_secret_access_key='aws_secret_access_key', host='localhost', port=8000) self.assertEqual(dynamodb.host, 'localhost') self.assertEqual(dynamodb.port, 8000)
def connect_local_dynamodb(self): self.conn = DynamoDBConnection( host='localhost', port=8010, aws_access_key_id='anything', aws_secret_access_key='anything', is_secure=False)
def __init__(self, uri): (unused, regionPath) = uri.split(':') (region, tableName) = regionPath.split('/') self.log = logging.getLogger("dynamo-fuse-oper ") self.tableName = tableName self.region = region for reg in boto.dynamodb2.regions(): if reg.name == region: self.regionv2 = reg break provider = Provider('aws') self.conn = boto.dynamodb.connect_to_region(region, aws_access_key_id=provider.get_access_key(), aws_secret_access_key=provider.get_secret_key()) connection = DynamoDBConnection(aws_access_key_id=provider.get_access_key(), aws_secret_access_key=provider.get_secret_key(), region=self.regionv2) try: self.table = self.conn.get_table(tableName) self.tablev2 = Table(tableName, connection=connection) self.blockTable = self.conn.get_table(self.tableName + "Blocks") self.blockTablev2 = Table(self.tableName + "Blocks", connection=connection) except: self.createTable() self.counter = itertools.count() self.counter.next() # start from 1 self.__createRoot() print "Ready"
def setUp(self): # Connect to DynamoDB Local self.conn = DynamoDBConnection( host='localhost', port=8000, aws_secret_access_key='anything', is_secure=False) tables = self.conn.list_tables() if 'employees' not in tables['TableNames']: # Create table of employees self.employees = Table.create('employees', schema = [HashKey('etype'), RangeKey('id')], indexes = [AllIndex('TitleIndex', parts = [ HashKey('etype'), RangeKey('title')])], connection = self.conn ) else: self.employees = Table('employees', connection=self.conn) self.employeeData = [{'etype' : 'E', 'first_name' : 'John', 'last_name': 'Doe', 'id' : '123456789', 'title' : 'Head Bottle Washer', 'hiredate' : 'June 5 1986'}, {'etype' : 'E', 'first_name' : 'Alice', 'last_name': 'Kramden', 'id' : '007', 'title' : 'Assistant Bottle Washer', 'hiredate' : 'July 1 1950'}, {'etype' : 'E', 'first_name' : 'Bob', 'last_name': 'Dylan', 'id' : '42', 'title' : 'Assistant Bottle Washer', 'hiredate' : 'January 1 1970'}] for data in self.employeeData: self.employees.put_item(data=data, overwrite=True)
def connect_fake(self): self.conn = DynamoDBConnection( aws_access_key_id='foo', aws_secret_access_key='bar', host='localhost', port=8000, is_secure=False)
def process_record(self, data, partition_key, sequence_number): ''' Called for each record that is passed to process_records. :type data: str :param data: The blob of data that was contained in the record. :type partition_key: str :param partition_key: The key associated with this recod. :type sequence_number: int :param sequence_number: The sequence number associated with this record. ''' #################################### # Insert your processing logic here #################################### wrote_index = False try: self.logger.info("processing record %d:%s" % (sequence_number, partition_key)) self.logger.info("putting data:%s" % (data)) index = Index(conn=DynamoDBConnection(), table_name=self.table_name) index.put(data) wrote_index = True except Exception as e: self.logger.error("error putting index in dynamodb %s" % e.message) if wrote_index: try: self.logger.info("posting to s3 s3://%s/%s/%s" % (self.s3bucket, self.s3path, sequence_number)) self.store.put(uuid=uuid.uuid4(), data=data) self.logger.info("posted data:%s" % (data)) except Exception as e: self.logger.error("error posting to s3 %s" % e.message)
def setUp(self): # Connect to DynamoDB Local self.conn = DynamoDBConnection(host='localhost', port=8000, aws_secret_access_key='anything', is_secure=False) tables = self.conn.list_tables() if 'employees' not in tables['TableNames']: # Create table of employees self.employees = Table.create( 'employees', schema=[HashKey('etype'), RangeKey('id')], indexes=[ AllIndex('TitleIndex', parts=[HashKey('etype'), RangeKey('title')]) ], connection=self.conn) else: self.employees = Table('employees', connection=self.conn) self.employeeData = [{ 'etype': 'E', 'first_name': 'John', 'last_name': 'Doe', 'id': '123456789', 'title': 'Head Bottle Washer', 'hiredate': 'June 5 1986' }, { 'etype': 'E', 'first_name': 'Alice', 'last_name': 'Kramden', 'id': '007', 'title': 'Assistant Bottle Washer', 'hiredate': 'July 1 1950' }, { 'etype': 'E', 'first_name': 'Bob', 'last_name': 'Dylan', 'id': '42', 'title': 'Assistant Bottle Washer', 'hiredate': 'January 1 1970' }] for data in self.employeeData: self.employees.put_item(data=data, overwrite=True)
def local_db(): from boto.dynamodb2.layer1 import DynamoDBConnection conn = DynamoDBConnection(host="localhost", port=8000, aws_access_key_id="kiwi", aws_secret_access_key="kiwi", is_secure=False) return conn
def test_init_provider_override(self): alt_provider = Mock(spec=boto.provider.Provider) alt_provider.host = None alt_provider.host_header = None alt_provider.port = None alt_provider.secret_key = 'alt_secret_key' dynamodb = DynamoDBConnection(provider=alt_provider) self.assertEqual(dynamodb.provider, alt_provider)
def getDynamoDBConnection(config=None, endpoint=None, port=None, local=False, use_instance_metadata=False): if local: db = DynamoDBConnection(host=endpoint, port=port, aws_secret_access_key='ticTacToeSampleApp', aws_access_key_id='ticTacToeSampleApp', is_secure=False) else: params = {'is_secure': True} # Read from config file, if provided if config is not None: if config.has_option('dynamodb', 'region'): params['region'] = config.get('dynamodb', 'region') if config.has_option('dynamodb', 'endpoint'): params['host'] = config.get('dynamodb', 'endpoint') if config.has_option('dynamodb', 'aws_access_key_id'): params['aws_access_key_id'] = config.get( 'dynamodb', 'aws_access_key_id') params['aws_secret_access_key'] = config.get( 'dynamodb', 'aws_secret_access_key') # Use the endpoint specified on the command-line to trump the config file if endpoint is not None: params['host'] = endpoint if 'region' in params: del params['region'] # Only auto-detect the DynamoDB endpoint if the endpoint was not specified through other config if 'host' not in params and use_instance_metadata: response = urlopen( 'http://169.254.169.254/latest/dynamic/instance-identity/document' ).read() doc = json.loads(response) params['host'] = 'dynamodb.%s.amazonaws.com' % (doc['region']) if 'region' in params: del params['region'] db = DynamoDBConnection(**params) return db
def getDynamoDBConnection(config=None, endpoint=None, port=None, local=False, use_instance_metadata=False): if local: db = DynamoDBConnection( host=endpoint, port=port, aws_secret_access_key='AKIAIZ2NKAVOD4UIJNVQ', aws_access_key_id='7W5NMo91HGR7cuojCx0kPizKtk65btiB6co315qt', is_secure=False) print "===============" print db.list_tables() print "===============" else: params = { 'is_secure': True } # Read from config file, if provided if config is not None: if config.has_option('dynamodb', 'region'): params['region'] = config.get('dynamodb', 'region') if config.has_option('dynamodb', 'endpoint'): params['host'] = config.get('dynamodb', 'endpoint') if config.has_option('dynamodb', 'aws_access_key_id'): params['aws_access_key_id'] = config.get('dynamodb', 'aws_access_key_id') params['aws_secret_access_key'] = config.get('dynamodb', 'aws_secret_access_key') # Use the endpoint specified on the command-line to trump the config file if endpoint is not None: params['host'] = endpoint if 'region' in params: del params['region'] # Only auto-detect the DynamoDB endpoint if the endpoint was not specified through other config if 'host' not in params and use_instance_metadata: response = urllib2.urlopen('http://169.254.169.254/latest/dynamic/instance-identity/document').read() doc = json.loads(response); params['host'] = 'dynamodb.%s.amazonaws.com' % (doc['region']) if 'region' in params: del params['region'] db = DynamoDBConnection(**params) return db
def test_custom_tablename(self): db = DynamoDBConnection() db_name = "router_%s" % uuid.uuid4() dblist = db.list_tables()["TableNames"] ok_(db_name not in dblist) create_router_table(db_name) dblist = db.list_tables()["TableNames"] ok_(db_name in dblist)
def __init__(self, env): if env == 'development': self.conn = DynamoDBConnection(host='localhost', port=8000, aws_access_key_id='development', aws_secret_access_key='development', is_secure=False) elif env == 'test': self.conn = DynamoDBConnection(host='localhost', port=8000, aws_access_key_id='test', aws_secret_access_key='test', is_secure=False) elif env == 'production': self.conn = boto.connect_dynamodb() else: logging.error("Invalid environment") self.conn = None
def init_connection(): host = "localhost" port = 8040 return DynamoDBConnection(aws_access_key_id='foo', aws_secret_access_key='bar', host=host, port=port, is_secure=False)
def getLocalConnection(): """ returns the Boto DynamoDB connection object """ return DynamoDBConnection(host='localhost', port=SessionTable.LOCAL_PORT, aws_access_key_id='a', aws_secret_access_key='a', is_secure=False)
def init_connection(self): logging.info('Region: %s' % (self.region)) if self.region == 'local': logging.info('using 127.0.0.1') self.conn = DynamoDBConnection(host='127.0.0.1', port=k_default_local_port, is_secure=False) if not self.table_exists(): logging.info('Creating Table %s' % self.table) self.create_my_table() else: self.conn = boto.dynamodb2.connect_to_region( self.region, aws_access_key_id=self.aws_id, aws_secret_access_key=self.aws_key)
def __init__(self): aws_access_key_id = os.environ['S3_KEY'] # I AM OPS U NO GET MY KEYS aws_secret_access_key = os.environ['S3_SECRET'] # DIS IS MY JOB self._conn = DynamoDBConnection( aws_access_key_id=aws_access_key_id, aws_secret_access_key=aws_secret_access_key) self.works_table = Table('ao3rdr-works', connection=self._conn) self.immutable_fields = ['work_id', 'user_id']
class MixinTestCase(unittest.TestCase): def __init__(self, *args, **kwargs): super(MixinTestCase, self).__init__(*args, **kwargs) self.tables = dict() def connect_local_dynamodb(self): self.conn = DynamoDBConnection( host='localhost', port=8010, aws_access_key_id='anything', aws_secret_access_key='anything', is_secure=False) def connect_local_s3(self): self.s3_conn = S3Connection('anything', 'anything', is_secure=False, port=4567, host='localhost', calling_format=OrdinaryCallingFormat()) def create_bucket(self): self.s3_conn.create_bucket(S3_BUCKET_NAME) def delete_bucket(self): bucket = self.s3_conn.get_bucket(S3_BUCKET_NAME) for key in bucket.list(): key.delete() self.s3_conn.delete_bucket(S3_BUCKET_NAME) def create_table(self, table_name, hashkey_name): logger.debug("creating table : table_name=%s, hashkey_name=%s", table_name, hashkey_name) if table_name in self.conn.list_tables()["TableNames"]: Table(table_name, connection=self.conn).delete() table = Table.create(table_name, schema=[HashKey(hashkey_name, data_type=NUMBER)], connection=self.conn) self.tables[table_name] = table def delete_tables(self): for table_name in self.conn.list_tables()["TableNames"]: Table(table_name, connection=self.conn).delete() def load_fixtures(self, table_name): fixture_name = 'tests/fixtures/%s.json' % table_name if os.path.isfile(fixture_name): with open(fixture_name) as f: rs = json.loads(f.read()) for r in rs: self.tables[table_name].put_item(data=r)
def createTable(self): provider = Provider('aws') connection = DynamoDBConnection(aws_access_key_id=provider.get_access_key(), aws_secret_access_key=provider.get_secret_key(), region=self.regionv2) self.blockTablev2 = Table.create(self.tableName + "Blocks", schema=[ HashKey('blockId'), RangeKey('blockNum', data_type=NUMBER) ], throughput={'read': 30, 'write': 10}, connection=connection ) self.tablev2 = Table.create(self.tableName, schema=[ HashKey('path'), RangeKey('name') ], throughput={'read': 30, 'write': 10}, indexes=[ KeysOnlyIndex("Links", parts=[ HashKey('path'), RangeKey('link') ]) ], connection=connection ) description = connection.describe_table(self.tableName) iter = 0 while description["Table"]["TableStatus"] != "ACTIVE": print "Waiting for %s to create %d..." % (self.tableName, iter) iter += 1 sleep(1) description = connection.describe_table(self.tableName) self.table = self.conn.get_table(self.tableName) self.blockTable = self.conn.get_table(self.tableName + "Blocks")
class DynamoDB(Base): def __init__(self, configs): self.local_key = 'dynamodb_local' self.connect(configs) def connect_fake(self): self.conn = DynamoDBConnection( aws_access_key_id='foo', aws_secret_access_key='bar', host='localhost', port=8000, is_secure=False) def connect_real(self, configs): self.conn = dynamo_connect_to_region( configs['aws']['region'], aws_access_key_id=configs['aws']['access_key'], aws_secret_access_key=configs['aws']['secret_key']) def get_table(self, table_name, hash_key='id', range_key='timestamp', throughput={'read': 5, 'write': 15}): if table_name in self.conn.list_tables()['TableNames']: table = Table(table_name, connection=self.conn) table.describe() # Bug: https://github.com/boto/boto/issues/2826 return table schema = [HashKey(hash_key)] if range_key: schema.append(RangeKey(range_key)) table = Table.create( table_name, schema=schema, throughput=throughput, connection=self.conn) self.wait_until_table_is_active(table) return table def update_table(self, table, throughput): if self.conn.host == 'localhost' or throughput == table.throughput: return self.wait_until_table_is_active(table) table.update(throughput=throughput) self.wait_until_table_is_active(table) def wait_until_table_is_active(self, table): while table.describe()['Table']['TableStatus'] != 'ACTIVE': sleep(1)
def __init__(self, storage_conf): self.conf = storage_conf self.max_results = storage_conf["max_results"] self.publishers = self.conf["publishers"] if self.conf["region"] == "localhost": from boto.dynamodb2.layer1 import DynamoDBConnection self.connection = DynamoDBConnection( host='localhost', port=8000, aws_secret_access_key='anything', is_secure=False) else: self.connection = boto.dynamodb2.connect_to_region(self.conf["region"]) self.tables = dict() for prod in self.publishers: self.tables[prod] = Table(self.connection, max_results=self.max_results, **self.conf[prod])
# Author Balbir Singh <*****@*****.**> # Date 13th February 2015 import simplejson from boto.dynamodb2.layer1 import DynamoDBConnection # Connect to Dynamo DB, by default it will connect us-east-1 as mentioned in .boto config ddb2_conn = DynamoDBConnection(profile_name="dhap-test") # Getting the list of the table table = ddb2_conn.list_tables() # Going over each and every table in loop for t in table['TableNames']: table_data_json = ddb2_conn.describe_table(t) table_data_json_dumps = simplejson.dumps(table_data_json) print table_data_json_dumps print "="*90
# coding: utf-8 from boto.dynamodb2.fields import HashKey, RangeKey from boto.dynamodb2.types import STRING, NUMBER from boto.dynamodb2.layer1 import DynamoDBConnection connection_data = {} connection_data["aws_access_key_id"] = "AKIAJ6PJI2SQGES3IDSL" connection_data["aws_secret_access_key"] = "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" connection_data["region"] = "" connection_data["region"] = "us-west-2" conn = DynamoDBConnection(**connection_data) conn = DynamoDBConnection(**connection_data) connection_data["host"] = "dynamodb.us-west-2.amazonaws.com" conn = DynamoDBConnection(**connection_data) conn tables = conn.list_table() tables = conn.list_tables() from boto.dynamodb2.table import Table users = Table.create( "users", schema=[HashKey("name", data_type=STRING), RangeKey("salary", data_type=NUMBER)], connection=conn ) users.put_item(data={"email": "aj", "salary": 1000}) users.put_item(data={"name": "aj", "salary": 1000}) users = Table.create( "users", schema=[HashKey("name", data_type=STRING), RangeKey("salary", data_type=NUMBER)], connection=conn ) conn.list_tables() users.delete() conn.list_tables() conn.list_tables()
class DynamoDBv2Layer1Test(unittest.TestCase): dynamodb = True def setUp(self): self.dynamodb = DynamoDBConnection() self.table_name = 'test-%d' % int(time.time()) self.hash_key_name = 'username' self.hash_key_type = 'S' self.range_key_name = 'date_joined' self.range_key_type = 'N' self.read_units = 5 self.write_units = 5 self.attributes = [ { 'AttributeName': self.hash_key_name, 'AttributeType': self.hash_key_type, }, { 'AttributeName': self.range_key_name, 'AttributeType': self.range_key_type, } ] self.schema = [ { 'AttributeName': self.hash_key_name, 'KeyType': 'HASH', }, { 'AttributeName': self.range_key_name, 'KeyType': 'RANGE', }, ] self.provisioned_throughput = { 'ReadCapacityUnits': self.read_units, 'WriteCapacityUnits': self.write_units, } self.lsi = [ { 'IndexName': 'MostRecentIndex', 'KeySchema': [ { 'AttributeName': self.hash_key_name, 'KeyType': 'HASH', }, { 'AttributeName': self.range_key_name, 'KeyType': 'RANGE', }, ], 'Projection': { 'ProjectionType': 'KEYS_ONLY', } } ] def create_table(self, table_name, attributes, schema, provisioned_throughput, lsi=None, wait=True): # Note: This is a slightly different ordering that makes less sense. result = self.dynamodb.create_table( attributes, table_name, schema, provisioned_throughput, local_secondary_indexes=lsi ) self.addCleanup(self.dynamodb.delete_table, table_name) if wait: while True: description = self.dynamodb.describe_table(table_name) if description['Table']['TableStatus'].lower() == 'active': return result else: time.sleep(5) else: return result def test_integrated(self): result = self.create_table( self.table_name, self.attributes, self.schema, self.provisioned_throughput, self.lsi ) self.assertEqual( result['TableDescription']['TableName'], self.table_name ) description = self.dynamodb.describe_table(self.table_name) self.assertEqual(description['Table']['ItemCount'], 0) # Create some records. record_1_data = { 'username': {'S': 'johndoe'}, 'first_name': {'S': 'John'}, 'last_name': {'S': 'Doe'}, 'date_joined': {'N': '1366056668'}, 'friend_count': {'N': '3'}, 'friends': {'SS': ['alice', 'bob', 'jane']}, } r1_result = self.dynamodb.put_item(self.table_name, record_1_data) # Get the data. record_1 = self.dynamodb.get_item(self.table_name, key={ 'username': {'S': 'johndoe'}, 'date_joined': {'N': '1366056668'}, }, consistent_read=True) self.assertEqual(record_1['Item']['username']['S'], 'johndoe') self.assertEqual(record_1['Item']['first_name']['S'], 'John') self.assertEqual(record_1['Item']['friends']['SS'], [ 'alice', 'bob', 'jane' ]) # Now in a batch. self.dynamodb.batch_write_item({ self.table_name: [ { 'PutRequest': { 'Item': { 'username': {'S': 'jane'}, 'first_name': {'S': 'Jane'}, 'last_name': {'S': 'Doe'}, 'date_joined': {'N': '1366056789'}, 'friend_count': {'N': '1'}, 'friends': {'SS': ['johndoe']}, }, }, }, ] }) # Now a query. lsi_results = self.dynamodb.query( self.table_name, index_name='MostRecentIndex', key_conditions={ 'username': { 'AttributeValueList': [ {'S': 'johndoe'}, ], 'ComparisonOperator': 'EQ', }, }, consistent_read=True ) self.assertEqual(lsi_results['Count'], 1) results = self.dynamodb.query(self.table_name, key_conditions={ 'username': { 'AttributeValueList': [ {'S': 'jane'}, ], 'ComparisonOperator': 'EQ', }, 'date_joined': { 'AttributeValueList': [ {'N': '1366050000'} ], 'ComparisonOperator': 'GT', } }, consistent_read=True) self.assertEqual(results['Count'], 1) # Now a scan. results = self.dynamodb.scan(self.table_name) self.assertEqual(results['Count'], 2) s_items = sorted([res['username']['S'] for res in results['Items']]) self.assertEqual(s_items, ['jane', 'johndoe']) self.dynamodb.delete_item(self.table_name, key={ 'username': {'S': 'johndoe'}, 'date_joined': {'N': '1366056668'}, }) results = self.dynamodb.scan(self.table_name) self.assertEqual(results['Count'], 1) # Parallel scan (minus client-side threading). self.dynamodb.batch_write_item({ self.table_name: [ { 'PutRequest': { 'Item': { 'username': {'S': 'johndoe'}, 'first_name': {'S': 'Johann'}, 'last_name': {'S': 'Does'}, 'date_joined': {'N': '1366058000'}, 'friend_count': {'N': '1'}, 'friends': {'SS': ['jane']}, }, }, 'PutRequest': { 'Item': { 'username': {'S': 'alice'}, 'first_name': {'S': 'Alice'}, 'last_name': {'S': 'Expert'}, 'date_joined': {'N': '1366056800'}, 'friend_count': {'N': '2'}, 'friends': {'SS': ['johndoe', 'jane']}, }, }, }, ] }) time.sleep(20) results = self.dynamodb.scan(self.table_name, segment=0, total_segments=2) self.assertTrue(results['Count'] in [1, 2]) results = self.dynamodb.scan(self.table_name, segment=1, total_segments=2) self.assertTrue(results['Count'] in [1, 2]) def test_without_range_key(self): result = self.create_table( self.table_name, [ { 'AttributeName': self.hash_key_name, 'AttributeType': self.hash_key_type, }, ], [ { 'AttributeName': self.hash_key_name, 'KeyType': 'HASH', }, ], self.provisioned_throughput ) self.assertEqual( result['TableDescription']['TableName'], self.table_name ) description = self.dynamodb.describe_table(self.table_name) self.assertEqual(description['Table']['ItemCount'], 0) # Create some records. record_1_data = { 'username': {'S': 'johndoe'}, 'first_name': {'S': 'John'}, 'last_name': {'S': 'Doe'}, 'date_joined': {'N': '1366056668'}, 'friend_count': {'N': '3'}, 'friends': {'SS': ['alice', 'bob', 'jane']}, } r1_result = self.dynamodb.put_item(self.table_name, record_1_data) # Now try a range-less get. johndoe = self.dynamodb.get_item(self.table_name, key={ 'username': {'S': 'johndoe'}, }, consistent_read=True) self.assertEqual(johndoe['Item']['username']['S'], 'johndoe') self.assertEqual(johndoe['Item']['first_name']['S'], 'John') self.assertEqual(johndoe['Item']['friends']['SS'], [ 'alice', 'bob', 'jane' ]) def test_throughput_exceeded_regression(self): tiny_tablename = 'TinyThroughput' tiny = self.create_table( tiny_tablename, self.attributes, self.schema, { 'ReadCapacityUnits': 1, 'WriteCapacityUnits': 1, } ) self.dynamodb.put_item(tiny_tablename, { 'username': {'S': 'johndoe'}, 'first_name': {'S': 'John'}, 'last_name': {'S': 'Doe'}, 'date_joined': {'N': '1366056668'}, }) self.dynamodb.put_item(tiny_tablename, { 'username': {'S': 'jane'}, 'first_name': {'S': 'Jane'}, 'last_name': {'S': 'Doe'}, 'date_joined': {'N': '1366056669'}, }) self.dynamodb.put_item(tiny_tablename, { 'username': {'S': 'alice'}, 'first_name': {'S': 'Alice'}, 'last_name': {'S': 'Expert'}, 'date_joined': {'N': '1366057000'}, }) time.sleep(20) for i in range(100): # This would cause an exception due to a non-existant instance variable. self.dynamodb.scan(tiny_tablename)
from boto.dynamodb2.layer1 import DynamoDBConnection from boto.dynamodb2.table import Table from boto.dynamodb2.fields import HashKey from boto.dynamodb2.types import NUMBER from boto.dynamodb2.items import Item from dal.base import BaseMeta conn = DynamoDBConnection(host='localhost', port=8888, aws_secret_access_key='A', is_secure=False) TABLE_NAMES = set(conn.list_tables()['TableNames']) TABLES = {} def _create_table(cls): kwargs = dict(table_name=cls.__name__, schema=[HashKey('oid', data_type=NUMBER)], connection=conn) if cls.__name__ in TABLE_NAMES: table = Table(**kwargs) else: table = Table.create(**kwargs) TABLES[cls.__name__] = table return table def _get_table(cls): return TABLES.get(cls.__name__, _create_table(cls)) def load(cls, oid): table = _get_table(cls) return dict(table.get_item(oid=oid)) def store(cls, oid, data): table = _get_table(cls)
class Table(object): """ Interacts & models the behavior of a DynamoDB table. The ``Table`` object represents a set (or rough categorization) of records within DynamoDB. The important part is that all records within the table, while largely-schema-free, share the same schema & are essentially namespaced for use in your application. For example, you might have a ``users`` table or a ``forums`` table. """ max_batch_get = 100 def __init__(self, table_name, schema=None, throughput=None, indexes=None, connection=None): """ Sets up a new in-memory ``Table``. This is useful if the table already exists within DynamoDB & you simply want to use it for additional interactions. The only required parameter is the ``table_name``. However, under the hood, the object will call ``describe_table`` to determine the schema/indexes/throughput. You can avoid this extra call by passing in ``schema`` & ``indexes``. **IMPORTANT** - If you're creating a new ``Table`` for the first time, you should use the ``Table.create`` method instead, as it will persist the table structure to DynamoDB. Requires a ``table_name`` parameter, which should be a simple string of the name of the table. Optionally accepts a ``schema`` parameter, which should be a list of ``BaseSchemaField`` subclasses representing the desired schema. Optionally accepts a ``throughput`` parameter, which should be a dictionary. If provided, it should specify a ``read`` & ``write`` key, both of which should have an integer value associated with them. Optionally accepts a ``indexes`` parameter, which should be a list of ``BaseIndexField`` subclasses representing the desired indexes. Optionally accepts a ``connection`` parameter, which should be a ``DynamoDBConnection`` instance (or subclass). This is primarily useful for specifying alternate connection parameters. Example:: # The simple, it-already-exists case. >>> conn = Table('users') # The full, minimum-extra-calls case. >>> from boto import dynamodb2 >>> users = Table('users', schema=[ ... HashKey('username'), ... RangeKey('date_joined', data_type=NUMBER) ... ], throughput={ ... 'read':20, ... 'write': 10, ... }, indexes=[ ... KeysOnlyIndex('MostRecentlyJoined', parts=[ ... RangeKey('date_joined') ... ]), ... ], ... connection=dynamodb2.connect_to_region('us-west-2', ... aws_access_key_id='key', ... aws_secret_access_key='key', ... )) """ self.table_name = table_name self.connection = connection self.throughput = {"read": 5, "write": 5} self.schema = schema self.indexes = indexes if self.connection is None: self.connection = DynamoDBConnection() if throughput is not None: self.throughput = throughput self._dynamizer = Dynamizer() @classmethod def create(cls, table_name, schema, throughput=None, indexes=None, connection=None): """ Creates a new table in DynamoDB & returns an in-memory ``Table`` object. This will setup a brand new table within DynamoDB. The ``table_name`` must be unique for your AWS account. The ``schema`` is also required to define the key structure of the table. **IMPORTANT** - You should consider the usage pattern of your table up-front, as the schema & indexes can **NOT** be modified once the table is created, requiring the creation of a new table & migrating the data should you wish to revise it. **IMPORTANT** - If the table already exists in DynamoDB, additional calls to this method will result in an error. If you just need a ``Table`` object to interact with the existing table, you should just initialize a new ``Table`` object, which requires only the ``table_name``. Requires a ``table_name`` parameter, which should be a simple string of the name of the table. Requires a ``schema`` parameter, which should be a list of ``BaseSchemaField`` subclasses representing the desired schema. Optionally accepts a ``throughput`` parameter, which should be a dictionary. If provided, it should specify a ``read`` & ``write`` key, both of which should have an integer value associated with them. Optionally accepts a ``indexes`` parameter, which should be a list of ``BaseIndexField`` subclasses representing the desired indexes. Optionally accepts a ``connection`` parameter, which should be a ``DynamoDBConnection`` instance (or subclass). This is primarily useful for specifying alternate connection parameters. Example:: >>> users = Table.create('users', schema=[ ... HashKey('username'), ... RangeKey('date_joined', data_type=NUMBER) ... ], throughput={ ... 'read':20, ... 'write': 10, ... }, indexes=[ ... KeysOnlyIndex('MostRecentlyJoined', parts=[ ... RangeKey('date_joined') ... ]), ... ]) """ table = cls(table_name=table_name, connection=connection) table.schema = schema if throughput is not None: table.throughput = throughput if indexes is not None: table.indexes = indexes # Prep the schema. raw_schema = [] attr_defs = [] for field in table.schema: raw_schema.append(field.schema()) # Build the attributes off what we know. attr_defs.append(field.definition()) raw_throughput = { "ReadCapacityUnits": int(table.throughput["read"]), "WriteCapacityUnits": int(table.throughput["write"]), } kwargs = {} if table.indexes: # Prep the LSIs. raw_lsi = [] for index_field in table.indexes: raw_lsi.append(index_field.schema()) # Again, build the attributes off what we know. # HOWEVER, only add attributes *NOT* already seen. attr_define = index_field.definition() for part in attr_define: attr_names = [attr["AttributeName"] for attr in attr_defs] if not part["AttributeName"] in attr_names: attr_defs.append(part) kwargs["local_secondary_indexes"] = raw_lsi table.connection.create_table( table_name=table.table_name, attribute_definitions=attr_defs, key_schema=raw_schema, provisioned_throughput=raw_throughput, **kwargs ) return table def _introspect_schema(self, raw_schema): """ Given a raw schema structure back from a DynamoDB response, parse out & build the high-level Python objects that represent them. """ schema = [] for field in raw_schema: if field["KeyType"] == "HASH": schema.append(HashKey(field["AttributeName"])) elif field["KeyType"] == "RANGE": schema.append(RangeKey(field["AttributeName"])) else: raise exceptions.UnknownSchemaFieldError( "%s was seen, but is unknown. Please report this at " "https://github.com/boto/boto/issues." % field["KeyType"] ) return schema def _introspect_indexes(self, raw_indexes): """ Given a raw index structure back from a DynamoDB response, parse out & build the high-level Python objects that represent them. """ indexes = [] for field in raw_indexes: index_klass = AllIndex kwargs = {"parts": []} if field["Projection"]["ProjectionType"] == "ALL": index_klass = AllIndex elif field["Projection"]["ProjectionType"] == "KEYS_ONLY": index_klass = KeysOnlyIndex elif field["Projection"]["ProjectionType"] == "INCLUDE": index_klass = IncludeIndex kwargs["includes"] = field["Projection"]["NonKeyAttributes"] else: raise exceptions.UnknownIndexFieldError( "%s was seen, but is unknown. Please report this at " "https://github.com/boto/boto/issues." % field["Projection"]["ProjectionType"] ) name = field["IndexName"] kwargs["parts"] = self._introspect_schema(field["KeySchema"]) indexes.append(index_klass(name, **kwargs)) return indexes def describe(self): """ Describes the current structure of the table in DynamoDB. This information will be used to update the ``schema``, ``indexes`` and ``throughput`` information on the ``Table``. Some calls, such as those involving creating keys or querying, will require this information to be populated. It also returns the full raw datastructure from DynamoDB, in the event you'd like to parse out additional information (such as the ``ItemCount`` or usage information). Example:: >>> users.describe() { # Lots of keys here... } >>> len(users.schema) 2 """ result = self.connection.describe_table(self.table_name) # Blindly update throughput, since what's on DynamoDB's end is likely # more correct. raw_throughput = result["Table"]["ProvisionedThroughput"] self.throughput["read"] = int(raw_throughput["ReadCapacityUnits"]) self.throughput["write"] = int(raw_throughput["WriteCapacityUnits"]) if not self.schema: # Since we have the data, build the schema. raw_schema = result["Table"].get("KeySchema", []) self.schema = self._introspect_schema(raw_schema) if not self.indexes: # Build the index information as well. raw_indexes = result["Table"].get("LocalSecondaryIndexes", []) self.indexes = self._introspect_indexes(raw_indexes) # This is leaky. return result def update(self, throughput): """ Updates table attributes in DynamoDB. Currently, the only thing you can modify about a table after it has been created is the throughput. Requires a ``throughput`` parameter, which should be a dictionary. If provided, it should specify a ``read`` & ``write`` key, both of which should have an integer value associated with them. Returns ``True`` on success. Example:: # For a read-heavier application... >>> users.update(throughput={ ... 'read': 20, ... 'write': 10, ... }) True """ self.throughput = throughput self.connection.update_table( self.table_name, {"ReadCapacityUnits": int(self.throughput["read"]), "WriteCapacityUnits": int(self.throughput["write"])}, ) return True def delete(self): """ Deletes a table in DynamoDB. **IMPORTANT** - Be careful when using this method, there is no undo. Returns ``True`` on success. Example:: >>> users.delete() True """ self.connection.delete_table(self.table_name) return True def _encode_keys(self, keys): """ Given a flat Python dictionary of keys/values, converts it into the nested dictionary DynamoDB expects. Converts:: { 'username': '******', 'tags': [1, 2, 5], } ...to...:: { 'username': {'S': 'john'}, 'tags': {'NS': ['1', '2', '5']}, } """ raw_key = {} for key, value in keys.items(): raw_key[key] = self._dynamizer.encode(value) return raw_key def get_item(self, consistent=False, **kwargs): """ Fetches an item (record) from a table in DynamoDB. To specify the key of the item you'd like to get, you can specify the key attributes as kwargs. Optionally accepts a ``consistent`` parameter, which should be a boolean. If you provide ``True``, it will perform a consistent (but more expensive) read from DynamoDB. (Default: ``False``) Returns an ``Item`` instance containing all the data for that record. Example:: # A simple hash key. >>> john = users.get_item(username='******') >>> john['first_name'] 'John' # A complex hash+range key. >>> john = users.get_item(username='******', last_name='Doe') >>> john['first_name'] 'John' # A consistent read (assuming the data might have just changed). >>> john = users.get_item(username='******', consistent=True) >>> john['first_name'] 'Johann' # With a key that is an invalid variable name in Python. # Also, assumes a different schema than previous examples. >>> john = users.get_item(**{ ... 'date-joined': 127549192, ... }) >>> john['first_name'] 'John' """ raw_key = self._encode_keys(kwargs) item_data = self.connection.get_item(self.table_name, raw_key, consistent_read=consistent) item = Item(self) item.load(item_data) return item def put_item(self, data, overwrite=False): """ Saves an entire item to DynamoDB. By default, if any part of the ``Item``'s original data doesn't match what's currently in DynamoDB, this request will fail. This prevents other processes from updating the data in between when you read the item & when your request to update the item's data is processed, which would typically result in some data loss. Requires a ``data`` parameter, which should be a dictionary of the data you'd like to store in DynamoDB. Optionally accepts an ``overwrite`` parameter, which should be a boolean. If you provide ``True``, this will tell DynamoDB to blindly overwrite whatever data is present, if any. Returns ``True`` on success. Example:: >>> users.put_item(data={ ... 'username': '******', ... 'first_name': 'Jane', ... 'last_name': 'Doe', ... 'date_joined': 126478915, ... }) True """ item = Item(self, data=data) return item.save(overwrite=overwrite) def _put_item(self, item_data, expects=None): """ The internal variant of ``put_item`` (full data). This is used by the ``Item`` objects, since that operation is represented at the table-level by the API, but conceptually maps better to telling an individual ``Item`` to save itself. """ kwargs = {} if expects is not None: kwargs["expected"] = expects self.connection.put_item(self.table_name, item_data, **kwargs) return True def _update_item(self, key, item_data, expects=None): """ The internal variant of ``put_item`` (partial data). This is used by the ``Item`` objects, since that operation is represented at the table-level by the API, but conceptually maps better to telling an individual ``Item`` to save itself. """ raw_key = self._encode_keys(key) kwargs = {} if expects is not None: kwargs["expected"] = expects self.connection.update_item(self.table_name, raw_key, item_data, **kwargs) return True def delete_item(self, **kwargs): """ Deletes an item in DynamoDB. **IMPORTANT** - Be careful when using this method, there is no undo. To specify the key of the item you'd like to get, you can specify the key attributes as kwargs. Returns ``True`` on success. Example:: # A simple hash key. >>> users.delete_item(username='******') True # A complex hash+range key. >>> users.delete_item(username='******', last_name='Doe') True # With a key that is an invalid variable name in Python. # Also, assumes a different schema than previous examples. >>> users.delete_item(**{ ... 'date-joined': 127549192, ... }) True """ raw_key = self._encode_keys(kwargs) self.connection.delete_item(self.table_name, raw_key) return True def get_key_fields(self): """ Returns the fields necessary to make a key for a table. If the ``Table`` does not already have a populated ``schema``, this will request it via a ``Table.describe`` call. Returns a list of fieldnames (strings). Example:: # A simple hash key. >>> users.get_key_fields() ['username'] # A complex hash+range key. >>> users.get_key_fields() ['username', 'last_name'] """ if not self.schema: # We don't know the structure of the table. Get a description to # populate the schema. self.describe() return [field.name for field in self.schema] def batch_write(self): """ Allows the batching of writes to DynamoDB. Since each write/delete call to DynamoDB has a cost associated with it, when loading lots of data, it makes sense to batch them, creating as few calls as possible. This returns a context manager that will transparently handle creating these batches. The object you get back lightly-resembles a ``Table`` object, sharing just the ``put_item`` & ``delete_item`` methods (which are all that DynamoDB can batch in terms of writing data). DynamoDB's maximum batch size is 25 items per request. If you attempt to put/delete more than that, the context manager will batch as many as it can up to that number, then flush them to DynamoDB & continue batching as more calls come in. Example:: # Assuming a table with one record... >>> with users.batch_write() as batch: ... batch.put_item(data={ ... 'username': '******', ... 'first_name': 'John', ... 'last_name': 'Doe', ... 'owner': 1, ... }) ... # Nothing across the wire yet. ... batch.delete_item(username='******') ... # Still no requests sent. ... batch.put_item(data={ ... 'username': '******', ... 'first_name': 'Jane', ... 'last_name': 'Doe', ... 'date_joined': 127436192, ... }) ... # Nothing yet, but once we leave the context, the ... # put/deletes will be sent. """ # PHENOMENAL COSMIC DOCS!!! itty-bitty code. return BatchTable(self) def _build_filters(self, filter_kwargs, using=QUERY_OPERATORS): """ An internal method for taking query/scan-style ``**kwargs`` & turning them into the raw structure DynamoDB expects for filtering. """ filters = {} for field_and_op, value in filter_kwargs.items(): field_bits = field_and_op.split("__") fieldname = "__".join(field_bits[:-1]) try: op = using[field_bits[-1]] except KeyError: raise exceptions.UnknownFilterTypeError( "Operator '%s' from '%s' is not recognized." % (field_bits[-1], field_and_op) ) lookup = {"AttributeValueList": [], "ComparisonOperator": op} # Special-case the ``NULL/NOT_NULL`` case. if field_bits[-1] == "null": del lookup["AttributeValueList"] if value is False: lookup["ComparisonOperator"] = "NOT_NULL" else: lookup["ComparisonOperator"] = "NULL" # Special-case the ``BETWEEN`` case. elif field_bits[-1] == "between": if len(value) == 2 and isinstance(value, (list, tuple)): lookup["AttributeValueList"].append(self._dynamizer.encode(value[0])) lookup["AttributeValueList"].append(self._dynamizer.encode(value[1])) else: # Fix up the value for encoding, because it was built to only work # with ``set``s. if isinstance(value, (list, tuple)): value = set(value) lookup["AttributeValueList"].append(self._dynamizer.encode(value)) # Finally, insert it into the filters. filters[fieldname] = lookup return filters def query(self, limit=None, index=None, reverse=False, consistent=False, attributes=None, **filter_kwargs): """ Queries for a set of matching items in a DynamoDB table. Queries can be performed against a hash key, a hash+range key or against any data stored in your local secondary indexes. **Note** - You can not query against arbitrary fields within the data stored in DynamoDB. To specify the filters of the items you'd like to get, you can specify the filters as kwargs. Each filter kwarg should follow the pattern ``<fieldname>__<filter_operation>=<value_to_look_for>``. Optionally accepts a ``limit`` parameter, which should be an integer count of the total number of items to return. (Default: ``None`` - all results) Optionally accepts an ``index`` parameter, which should be a string of name of the local secondary index you want to query against. (Default: ``None``) Optionally accepts a ``reverse`` parameter, which will present the results in reverse order. (Default: ``None`` - normal order) Optionally accepts a ``consistent`` parameter, which should be a boolean. If you provide ``True``, it will force a consistent read of the data (more expensive). (Default: ``False`` - use eventually consistent reads) Optionally accepts a ``attributes`` parameter, which should be a tuple. If you provide any attributes only these will be fetched from DynamoDB. This uses the ``AttributesToGet`` and set's ``Select`` to ``SPECIFIC_ATTRIBUTES`` API. Returns a ``ResultSet``, which transparently handles the pagination of results you get back. Example:: # Look for last names equal to "Doe". >>> results = users.query(last_name__eq='Doe') >>> for res in results: ... print res['first_name'] 'John' 'Jane' # Look for last names beginning with "D", in reverse order, limit 3. >>> results = users.query( ... last_name__beginswith='D', ... reverse=True, ... limit=3 ... ) >>> for res in results: ... print res['first_name'] 'Alice' 'Jane' 'John' # Use an LSI & a consistent read. >>> results = users.query( ... date_joined__gte=1236451000, ... owner__eq=1, ... index='DateJoinedIndex', ... consistent=True ... ) >>> for res in results: ... print res['first_name'] 'Alice' 'Bob' 'John' 'Fred' """ if self.schema: if len(self.schema) == 1 and len(filter_kwargs) <= 1: raise exceptions.QueryError("You must specify more than one key to filter on.") if attributes is not None: select = "SPECIFIC_ATTRIBUTES" else: select = None results = ResultSet() kwargs = filter_kwargs.copy() kwargs.update( { "limit": limit, "index": index, "reverse": reverse, "consistent": consistent, "select": select, "attributes_to_get": attributes, } ) results.to_call(self._query, **kwargs) return results def query_count(self, index=None, consistent=False, **filter_kwargs): """ Queries the exact count of matching items in a DynamoDB table. Queries can be performed against a hash key, a hash+range key or against any data stored in your local secondary indexes. To specify the filters of the items you'd like to get, you can specify the filters as kwargs. Each filter kwarg should follow the pattern ``<fieldname>__<filter_operation>=<value_to_look_for>``. Optionally accepts an ``index`` parameter, which should be a string of name of the local secondary index you want to query against. (Default: ``None``) Optionally accepts a ``consistent`` parameter, which should be a boolean. If you provide ``True``, it will force a consistent read of the data (more expensive). (Default: ``False`` - use eventually consistent reads) Returns an integer which represents the exact amount of matched items. Example:: # Look for last names equal to "Doe". >>> users.query_count(last_name__eq='Doe') 5 # Use an LSI & a consistent read. >>> users.query_count( ... date_joined__gte=1236451000, ... owner__eq=1, ... index='DateJoinedIndex', ... consistent=True ... ) 2 """ key_conditions = self._build_filters(filter_kwargs, using=QUERY_OPERATORS) raw_results = self.connection.query( self.table_name, index_name=index, consistent_read=consistent, select="COUNT", key_conditions=key_conditions ) return int(raw_results.get("Count", 0)) def _query( self, limit=None, index=None, reverse=False, consistent=False, exclusive_start_key=None, select=None, attributes_to_get=None, **filter_kwargs ): """ The internal method that performs the actual queries. Used extensively by ``ResultSet`` to perform each (paginated) request. """ kwargs = { "limit": limit, "index_name": index, "scan_index_forward": reverse, "consistent_read": consistent, "select": select, "attributes_to_get": attributes_to_get, } if exclusive_start_key: kwargs["exclusive_start_key"] = {} for key, value in exclusive_start_key.items(): kwargs["exclusive_start_key"][key] = self._dynamizer.encode(value) # Convert the filters into something we can actually use. kwargs["key_conditions"] = self._build_filters(filter_kwargs, using=QUERY_OPERATORS) raw_results = self.connection.query(self.table_name, **kwargs) results = [] last_key = None for raw_item in raw_results.get("Items", []): item = Item(self) item.load({"Item": raw_item}) results.append(item) if raw_results.get("LastEvaluatedKey", None): last_key = {} for key, value in raw_results["LastEvaluatedKey"].items(): last_key[key] = self._dynamizer.decode(value) return {"results": results, "last_key": last_key} def scan(self, limit=None, segment=None, total_segments=None, **filter_kwargs): """ Scans across all items within a DynamoDB table. Scans can be performed against a hash key or a hash+range key. You can additionally filter the results after the table has been read but before the response is returned. To specify the filters of the items you'd like to get, you can specify the filters as kwargs. Each filter kwarg should follow the pattern ``<fieldname>__<filter_operation>=<value_to_look_for>``. Optionally accepts a ``limit`` parameter, which should be an integer count of the total number of items to return. (Default: ``None`` - all results) Returns a ``ResultSet``, which transparently handles the pagination of results you get back. Example:: # All results. >>> everything = users.scan() # Look for last names beginning with "D". >>> results = users.scan(last_name__beginswith='D') >>> for res in results: ... print res['first_name'] 'Alice' 'John' 'Jane' # Use an ``IN`` filter & limit. >>> results = users.scan( ... age__in=[25, 26, 27, 28, 29], ... limit=1 ... ) >>> for res in results: ... print res['first_name'] 'Alice' """ results = ResultSet() kwargs = filter_kwargs.copy() kwargs.update({"limit": limit, "segment": segment, "total_segments": total_segments}) results.to_call(self._scan, **kwargs) return results def _scan(self, limit=None, exclusive_start_key=None, segment=None, total_segments=None, **filter_kwargs): """ The internal method that performs the actual scan. Used extensively by ``ResultSet`` to perform each (paginated) request. """ kwargs = {"limit": limit, "segment": segment, "total_segments": total_segments} if exclusive_start_key: kwargs["exclusive_start_key"] = {} for key, value in exclusive_start_key.items(): kwargs["exclusive_start_key"][key] = self._dynamizer.encode(value) # Convert the filters into something we can actually use. kwargs["scan_filter"] = self._build_filters(filter_kwargs, using=FILTER_OPERATORS) raw_results = self.connection.scan(self.table_name, **kwargs) results = [] last_key = None for raw_item in raw_results.get("Items", []): item = Item(self) item.load({"Item": raw_item}) results.append(item) if raw_results.get("LastEvaluatedKey", None): last_key = {} for key, value in raw_results["LastEvaluatedKey"].items(): last_key[key] = self._dynamizer.decode(value) return {"results": results, "last_key": last_key} def batch_get(self, keys, consistent=False): """ Fetches many specific items in batch from a table. Requires a ``keys`` parameter, which should be a list of dictionaries. Each dictionary should consist of the keys values to specify. Optionally accepts a ``consistent`` parameter, which should be a boolean. If you provide ``True``, a strongly consistent read will be used. (Default: False) Returns a ``ResultSet``, which transparently handles the pagination of results you get back. Example:: >>> results = users.batch_get(keys=[ ... { ... 'username': '******', ... }, ... { ... 'username': '******', ... }, ... { ... 'username': '******', ... }, ... ]) >>> for res in results: ... print res['first_name'] 'John' 'Jane' 'Fred' """ # We pass the keys to the constructor instead, so it can maintain it's # own internal state as to what keys have been processed. results = BatchGetResultSet(keys=keys, max_batch_get=self.max_batch_get) results.to_call(self._batch_get, consistent=False) return results def _batch_get(self, keys, consistent=False): """ The internal method that performs the actual batch get. Used extensively by ``BatchGetResultSet`` to perform each (paginated) request. """ items = {self.table_name: {"Keys": []}} if consistent: items[self.table_name]["ConsistentRead"] = True for key_data in keys: raw_key = {} for key, value in key_data.items(): raw_key[key] = self._dynamizer.encode(value) items[self.table_name]["Keys"].append(raw_key) raw_results = self.connection.batch_get_item(request_items=items) results = [] unprocessed_keys = [] for raw_item in raw_results["Responses"].get(self.table_name, []): item = Item(self) item.load({"Item": raw_item}) results.append(item) raw_unproccessed = raw_results.get("UnprocessedKeys", {}) for raw_key in raw_unproccessed.get("Keys", []): py_key = {} for key, value in raw_key.items(): py_key[key] = self._dynamizer.decode(value) unprocessed_keys.append(py_key) return { "results": results, # NEVER return a ``last_key``. Just in-case any part of # ``ResultSet`` peeks through, since much of the # original underlying implementation is based on this key. "last_key": None, "unprocessed_keys": unprocessed_keys, } def count(self): """ Returns a (very) eventually consistent count of the number of items in a table. Lag time is about 6 hours, so don't expect a high degree of accuracy. Example:: >>> users.count() 6 """ info = self.describe() return info["Table"].get("ItemCount", 0)
def __init__(self, table_name, schema=None, throughput=None, indexes=None, connection=None): """ Sets up a new in-memory ``Table``. This is useful if the table already exists within DynamoDB & you simply want to use it for additional interactions. The only required parameter is the ``table_name``. However, under the hood, the object will call ``describe_table`` to determine the schema/indexes/throughput. You can avoid this extra call by passing in ``schema`` & ``indexes``. **IMPORTANT** - If you're creating a new ``Table`` for the first time, you should use the ``Table.create`` method instead, as it will persist the table structure to DynamoDB. Requires a ``table_name`` parameter, which should be a simple string of the name of the table. Optionally accepts a ``schema`` parameter, which should be a list of ``BaseSchemaField`` subclasses representing the desired schema. Optionally accepts a ``throughput`` parameter, which should be a dictionary. If provided, it should specify a ``read`` & ``write`` key, both of which should have an integer value associated with them. Optionally accepts a ``indexes`` parameter, which should be a list of ``BaseIndexField`` subclasses representing the desired indexes. Optionally accepts a ``connection`` parameter, which should be a ``DynamoDBConnection`` instance (or subclass). This is primarily useful for specifying alternate connection parameters. Example:: # The simple, it-already-exists case. >>> conn = Table('users') # The full, minimum-extra-calls case. >>> from boto import dynamodb2 >>> users = Table('users', schema=[ ... HashKey('username'), ... RangeKey('date_joined', data_type=NUMBER) ... ], throughput={ ... 'read':20, ... 'write': 10, ... }, indexes=[ ... KeysOnlyIndex('MostRecentlyJoined', parts=[ ... RangeKey('date_joined') ... ]), ... ], ... connection=dynamodb2.connect_to_region('us-west-2', ... aws_access_key_id='key', ... aws_secret_access_key='key', ... )) """ self.table_name = table_name self.connection = connection self.throughput = {"read": 5, "write": 5} self.schema = schema self.indexes = indexes if self.connection is None: self.connection = DynamoDBConnection() if throughput is not None: self.throughput = throughput self._dynamizer = Dynamizer()
# This is a python 3.4 test script using boto to connect to the localhost dynamodb-local instance # # First install boto: # - pip install boto from boto.dynamodb2.layer1 import DynamoDBConnection connection = DynamoDBConnection( aws_access_key_id="foo", # Dummy access key aws_secret_access_key="bar", # Dummy secret key host="localhost", # Host where DynamoDB Local resides port=8000, # DynamoDB Local port (8000 is the default) is_secure=False, ) # Disable secure connections print(connection.list_tables())
# https://github.com/techgaun/dynamodb-copy-table # Usage: python dyndb-kopier.py src_region src_table dst_region dst_table if len(sys.argv) != 5: print 'Usage: %s <source_region> <source_table_name>' \ ' <destination_region> <destination_table_name>' % sys.argv[0] sys.exit(1) src_region = sys.argv[1] src_table = sys.argv[2] dst_region = sys.argv[3] dst_table = sys.argv[4] source_hostname = 'dynamodb.{}.amazonaws.com'.format(src_region) destination_hostname = 'dynamodb.{}.amazonaws.com'.format(dst_region) source_ddbc = DynamoDBConnection(is_secure=False, region=src_region, host=source_hostname) destination_ddbc = DynamoDBConnection(is_secure=False, region=dst_region, host=destination_hostname) # 1. Try to connect to the source table try: src_logs = Table(src_table, connection=source_ddbc) print "Connected to source table %s in region %s" % (src_table, src_region) except JSONResponseError: print "Source table %s in region %s does not exist" % (src_table, src_region) sys.exit(1)(src_table, src_region) print 'Reading source key schema from %s in %s' % (src_table, src_region) src_table_describe = source_ddbc.describe_table(src_table)['Table'] src_hash_key = '' src_range_key = '' for schema in src_table_describe['KeySchema']:
#parsing our access config = ConfigParser.RawConfigParser() config.read("settings.cfg") aws_access_key_id = config.get('Twitter', 'aws_access_key_id') aws_secret_access_key = config.get('Twitter', 'aws_secret_access_key') region = config.get("Twitter", 'region') local = config.get('Twitter', 'local') ########### Connect to DynamoDB if local == 'True': # Connect to DynamoDB Local conn = DynamoDBConnection( host='localhost', port=8000, aws_secret_access_key='foo', is_secure=False) else: conn = connect_to_region(region, aws_access_key_id=aws_access_key_id, aws_secret_access_key=aws_secret_access_key) ############################################# ###########Try to connect in our table. Otherwise, it creates one####### tables = conn.list_tables() #print tables if 'twitter' not in tables['TableNames']: # Create table of employees twitter = Table.create('twitter',