def _encode_key(cls, hash_key, range_key=None): dynamizer = Dynamizer() encoded = {cls._get_hash_key().name: dynamizer.encode(hash_key)} if range_key: encoded.update( {cls._get_range_key().name: dynamizer.encode(range_key)}) return encoded
def _encode_key(cls, hash_key, range_key=None): dynamizer = Dynamizer() encoded = {cls._get_hash_key().name: dynamizer.encode(hash_key)} if range_key: encoded.update( {cls._get_range_key().name: dynamizer.encode(range_key)}) return encoded
def update_item(cls, hash_key, range_key=None, attributes_to_set=None, attributes_to_add=None): """Update item attributes. Currently SET and ADD actions are supported.""" primary_key = cls._encode_key(hash_key, range_key) value_names = {} encoded_values = {} dynamizer = Dynamizer() set_expression = '' if attributes_to_set: for i, key in enumerate(attributes_to_set.keys()): value_name = ':s{0}'.format(i) value_names[key] = value_name encoded_values[value_name] = dynamizer.encode(attributes_to_set[key]) set_expression = 'SET {0}'.format( ', '.join( '{key}={value_name}'.format(key=key, value_name=value_names[key]) for key in attributes_to_set ) ) add_expression = '' if attributes_to_add: for i, key in enumerate(attributes_to_add.keys()): value_name = ':a{0}'.format(i) value_names[key] = value_name encoded_values[value_name] = dynamizer.encode(attributes_to_add[key]) add_expression = 'ADD {0}'.format( ', '.join( '{key} {value_name}'.format(key=key, value_name=value_names[key]) for key in attributes_to_add ) ) update_expression = ' '.join([set_expression, add_expression]) cls._get_connection().update_item( cls.get_table_name(), primary_key, update_expression=update_expression, expression_attribute_values=encoded_values)
class Item(object): """ An object representing the item data within a DynamoDB table. An item is largely schema-free, meaning it can contain any data. The only limitation is that it must have data for the fields in the ``Table``'s schema. This object presents a dictionary-like interface for accessing/storing data. It also tries to intelligently track how data has changed throughout the life of the instance, to be as efficient as possible about updates. """ def __init__(self, table, data=None): """ Constructs an (unsaved) ``Item`` instance. To persist the data in DynamoDB, you'll need to call the ``Item.save`` (or ``Item.partial_save``) on the instance. Requires a ``table`` parameter, which should be a ``Table`` instance. This is required, as DynamoDB's API is focus around all operations being table-level. It's also for persisting schema around many objects. Optionally accepts a ``data`` parameter, which should be a dictionary of the fields & values of the item. Example:: >>> users = Table('users') >>> user = Item(users, data={ ... 'username': '******', ... 'first_name': 'John', ... 'date_joined': 1248o61592, ... }) # Change existing data. >>> user['first_name'] = 'Johann' # Add more data. >>> user['last_name'] = 'Doe' # Delete data. >>> del user['date_joined'] # Iterate over all the data. >>> for field, val in user.items(): ... print "%s: %s" % (field, val) username: johndoe first_name: John date_joined: 1248o61592 """ self.table = table self._data = {} self._orig_data = {} self._is_dirty = False self._dynamizer = Dynamizer() if data: self._data = data self._is_dirty = True for key in list(data.keys()): self._orig_data[key] = NEWVALUE def __getitem__(self, key): return self._data.get(key, None) def __setitem__(self, key, value): # Stow the original value if present, so we can track what's changed. if key in self._data: self._orig_data[key] = self._data[key] else: # Use a marker to indicate we've never seen a value for this key. self._orig_data[key] = NEWVALUE self._data[key] = value self._is_dirty = True def __delitem__(self, key): if not key in self._data: return # Stow the original value, so we can track what's changed. value = self._data[key] del self._data[key] self._orig_data[key] = value self._is_dirty = True def keys(self): return list(self._data.keys()) def values(self): return list(self._data.values()) def items(self): return list(self._data.items()) def get(self, key, default=None): return self._data.get(key, default) def __iter__(self): for key in self._data: yield self._data[key] def __contains__(self, key): return key in self._data def needs_save(self): """ Returns whether or not the data has changed on the ``Item``. Example: >>> user.needs_save() False >>> user['first_name'] = 'Johann' >>> user.needs_save() True """ return self._is_dirty def mark_clean(self): """ Marks an ``Item`` instance as no longer needing to be saved. Example: >>> user.needs_save() False >>> user['first_name'] = 'Johann' >>> user.needs_save() True >>> user.mark_clean() >>> user.needs_save() False """ self._orig_data = {} self._is_dirty = False def mark_dirty(self): """ Marks an ``Item`` instance as needing to be saved. Example: >>> user.needs_save() False >>> user.mark_dirty() >>> user.needs_save() True """ self._is_dirty = True def load(self, data): """ This is only useful when being handed raw data from DynamoDB directly. If you have a Python datastructure already, use the ``__init__`` or manually set the data instead. Largely internal, unless you know what you're doing or are trying to mix the low-level & high-level APIs. """ self._data = {} for field_name, field_value in list(data.get('Item', {}).items()): self[field_name] = self._dynamizer.decode(field_value) self.mark_clean() def get_keys(self): """ Returns a Python-style dict of the keys/values. Largely internal. """ key_fields = self.table.get_key_fields() key_data = {} for key in key_fields: key_data[key] = self[key] return key_data def get_raw_keys(self): """ Returns a DynamoDB-style dict of the keys/values. Largely internal. """ raw_key_data = {} for key, value in list(self.get_keys().items()): raw_key_data[key] = self._dynamizer.encode(value) return raw_key_data def build_expects(self, fields=None): """ Builds up a list of expecations to hand off to DynamoDB on save. Largely internal. """ expects = {} if fields is None: fields = list(self._data.keys()) + list(self._orig_data.keys()) # Only uniques. fields = set(fields) for key in fields: expects[key] = { 'Exists': True, } value = None # Check for invalid keys. if not key in self._orig_data and not key in self._data: raise ValueError("Unknown key %s provided." % key) # States: # * New field (_data & _orig_data w/ marker) # * Unchanged field (only _data) # * Modified field (_data & _orig_data) # * Deleted field (only _orig_data) if not key in self._orig_data: # Existing field unchanged. value = self._data[key] else: if key in self._data: if self._orig_data[key] is NEWVALUE: # New field. expects[key]['Exists'] = False else: # Existing field modified. value = self._orig_data[key] else: # Existing field deleted. value = self._orig_data[key] if value is not None: expects[key]['Value'] = self._dynamizer.encode(value) return expects def prepare_full(self): """ Runs through all fields & encodes them to be handed off to DynamoDB as part of an ``save`` (``put_item``) call. Largely internal. """ # This doesn't save on it's own. Rather, we prepare the datastructure # and hand-off to the table to handle creation/update. final_data = {} for key, value in list(self._data.items()): final_data[key] = self._dynamizer.encode(value) return final_data def prepare_partial(self): """ Runs through **ONLY** the changed/deleted fields & encodes them to be handed off to DynamoDB as part of an ``partial_save`` (``update_item``) call. Largely internal. """ # This doesn't save on it's own. Rather, we prepare the datastructure # and hand-off to the table to handle creation/update. final_data = {} # Loop over ``_orig_data`` so that we only build up data that's changed. for key, value in list(self._orig_data.items()): if key in self._data: # It changed. final_data[key] = { 'Action': 'PUT', 'Value': self._dynamizer.encode(self._data[key]) } else: # It was deleted. final_data[key] = { 'Action': 'DELETE', } return final_data def partial_save(self): """ Saves only the changed data to DynamoDB. Extremely useful for high-volume/high-write data sets, this allows you to update only a handful of fields rather than having to push entire items. This prevents many accidental overwrite situations as well as saves on the amount of data to transfer over the wire. Returns ``True`` on success, ``False`` if no save was performed or the write failed. Example:: >>> user['last_name'] = 'Doh!' # Only the last name field will be sent to DynamoDB. >>> user.partial_save() """ if not self.needs_save(): return False key = self.get_keys() # Build a new dict of only the data we're changing. final_data = self.prepare_partial() # Build expectations of only the fields we're planning to update. expects = self.build_expects(fields=list(self._orig_data.keys())) returned = self.table._update_item(key, final_data, expects=expects) # Mark the object as clean. self.mark_clean() return returned def save(self, overwrite=False): """ Saves all data to DynamoDB. By default, this attempts to ensure that none of the underlying data has changed. If any fields have changed in between when the ``Item`` was constructed & when it is saved, this call will fail so as not to cause any data loss. If you're sure possibly overwriting data is acceptable, you can pass an ``overwrite=True``. If that's not acceptable, you may be able to use ``Item.partial_save`` to only write the changed field data. Optionally accepts an ``overwrite`` parameter, which should be a boolean. If you provide ``True``, the item will be forcibly overwritten within DynamoDB, even if another process changed the data in the meantime. (Default: ``False``) Returns ``True`` on success, ``False`` if no save was performed. Example:: >>> user['last_name'] = 'Doh!' # All data on the Item is sent to DynamoDB. >>> user.save() # If it fails, you can overwrite. >>> user.save(overwrite=True) """ if not self.needs_save(): return False final_data = self.prepare_full() expects = None if overwrite is False: # Build expectations about *all* of the data. expects = self.build_expects() returned = self.table._put_item(final_data, expects=expects) # Mark the object as clean. self.mark_clean() return returned def delete(self): """ Deletes the item's data to DynamoDB. Returns ``True`` on success. Example:: # Buh-bye now. >>> user.delete() """ key_data = self.get_keys() return self.table.delete_item(**key_data)
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 lookup(self, *args, **kwargs): """ Look up an entry in DynamoDB. This is mostly backwards compatible with boto.dynamodb. Unlike get_item, it takes hash_key and range_key first, although you may still specify keyword arguments instead. Also unlike the get_item command, if the returned item has no keys (i.e., it does not exist in DynamoDB), a None result is returned, instead of an empty key object. Example:: >>> user = users.lookup(username) >>> user = users.lookup(username, consistent=True) >>> app = apps.lookup('my_customer_id', 'my_app_id') """ if not self.schema: self.describe() for x, arg in enumerate(args): kwargs[self.schema[x].name] = arg ret = self.get_item(**kwargs) if not ret.keys(): return None return ret def new_item(self, *args): """ Returns a new, blank item This is mostly for consistency with boto.dynamodb """ if not self.schema: self.describe() data = {} for x, arg in enumerate(args): data[self.schema[x].name] = arg return Item(self, data=data) 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)
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)
class Item(object): """ An object representing the item data within a DynamoDB table. An item is largely schema-free, meaning it can contain any data. The only limitation is that it must have data for the fields in the ``Table``'s schema. This object presents a dictionary-like interface for accessing/storing data. It also tries to intelligently track how data has changed throughout the life of the instance, to be as efficient as possible about updates. """ def __init__(self, table, data=None): """ Constructs an (unsaved) ``Item`` instance. To persist the data in DynamoDB, you'll need to call the ``Item.save`` (or ``Item.partial_save``) on the instance. Requires a ``table`` parameter, which should be a ``Table`` instance. This is required, as DynamoDB's API is focus around all operations being table-level. It's also for persisting schema around many objects. Optionally accepts a ``data`` parameter, which should be a dictionary of the fields & values of the item. Example:: >>> users = Table('users') >>> user = Item(users, data={ ... 'username': '******', ... 'first_name': 'John', ... 'date_joined': 1248o61592, ... }) # Change existing data. >>> user['first_name'] = 'Johann' # Add more data. >>> user['last_name'] = 'Doe' # Delete data. >>> del user['date_joined'] # Iterate over all the data. >>> for field, val in user.items(): ... print "%s: %s" % (field, val) username: johndoe first_name: John date_joined: 1248o61592 """ self.table = table self._data = {} self._orig_data = {} self._is_dirty = False self._dynamizer = Dynamizer() if data: self._data = data self._is_dirty = True for key in data.keys(): self._orig_data[key] = NEWVALUE def __getitem__(self, key): return self._data.get(key, None) def __setitem__(self, key, value): # Stow the original value if present, so we can track what's changed. if key in self._data: self._orig_data[key] = self._data[key] else: # Use a marker to indicate we've never seen a value for this key. self._orig_data[key] = NEWVALUE self._data[key] = value self._is_dirty = True def __delitem__(self, key): if not key in self._data: return # Stow the original value, so we can track what's changed. value = self._data[key] del self._data[key] self._orig_data[key] = value self._is_dirty = True def keys(self): return self._data.keys() def values(self): return self._data.values() def items(self): return self._data.items() def get(self, key, default=None): return self._data.get(key, default) def __iter__(self): for key in self._data: yield self._data[key] def __contains__(self, key): return key in self._data def needs_save(self): """ Returns whether or not the data has changed on the ``Item``. Example: >>> user.needs_save() False >>> user['first_name'] = 'Johann' >>> user.needs_save() True """ return self._is_dirty def mark_clean(self): """ Marks an ``Item`` instance as no longer needing to be saved. Example: >>> user.needs_save() False >>> user['first_name'] = 'Johann' >>> user.needs_save() True >>> user.mark_clean() >>> user.needs_save() False """ self._orig_data = {} self._is_dirty = False def mark_dirty(self): """ Marks an ``Item`` instance as needing to be saved. Example: >>> user.needs_save() False >>> user.mark_dirty() >>> user.needs_save() True """ self._is_dirty = True def load(self, data): """ This is only useful when being handed raw data from DynamoDB directly. If you have a Python datastructure already, use the ``__init__`` or manually set the data instead. Largely internal, unless you know what you're doing or are trying to mix the low-level & high-level APIs. """ self._data = {} for field_name, field_value in data.get('Item', {}).items(): self[field_name] = self._dynamizer.decode(field_value) self.mark_clean() def get_keys(self): """ Returns a Python-style dict of the keys/values. Largely internal. """ key_fields = self.table.get_key_fields() key_data = {} for key in key_fields: key_data[key] = self[key] return key_data def get_raw_keys(self): """ Returns a DynamoDB-style dict of the keys/values. Largely internal. """ raw_key_data = {} for key, value in self.get_keys().items(): raw_key_data[key] = self._dynamizer.encode(value) return raw_key_data def build_expects(self, fields=None): """ Builds up a list of expecations to hand off to DynamoDB on save. Largely internal. """ expects = {} if fields is None: fields = self._data.keys() + self._orig_data.keys() # Only uniques. fields = set(fields) for key in fields: expects[key] = { 'Exists': True, } value = None # Check for invalid keys. if not key in self._orig_data and not key in self._data: raise ValueError("Unknown key %s provided." % key) # States: # * New field (_data & _orig_data w/ marker) # * Unchanged field (only _data) # * Modified field (_data & _orig_data) # * Deleted field (only _orig_data) if not key in self._orig_data: # Existing field unchanged. value = self._data[key] else: if key in self._data: if self._orig_data[key] is NEWVALUE: # New field. expects[key]['Exists'] = False else: # Existing field modified. value = self._orig_data[key] else: # Existing field deleted. value = self._orig_data[key] if value is not None: expects[key]['Value'] = self._dynamizer.encode(value) return expects def prepare_full(self): """ Runs through all fields & encodes them to be handed off to DynamoDB as part of an ``save`` (``put_item``) call. Largely internal. """ # This doesn't save on it's own. Rather, we prepare the datastructure # and hand-off to the table to handle creation/update. final_data = {} for key, value in self._data.items(): final_data[key] = self._dynamizer.encode(value) return final_data def prepare_partial(self): """ Runs through **ONLY** the changed/deleted fields & encodes them to be handed off to DynamoDB as part of an ``partial_save`` (``update_item``) call. Largely internal. """ # This doesn't save on it's own. Rather, we prepare the datastructure # and hand-off to the table to handle creation/update. final_data = {} # Loop over ``_orig_data`` so that we only build up data that's changed. for key, value in self._orig_data.items(): if key in self._data: # It changed. final_data[key] = { 'Action': 'PUT', 'Value': self._dynamizer.encode(self._data[key]) } else: # It was deleted. final_data[key] = { 'Action': 'DELETE', } return final_data def partial_save(self): """ Saves only the changed data to DynamoDB. Extremely useful for high-volume/high-write data sets, this allows you to update only a handful of fields rather than having to push entire items. This prevents many accidental overwrite situations as well as saves on the amount of data to transfer over the wire. Returns ``True`` on success, ``False`` if no save was performed or the write failed. Example:: >>> user['last_name'] = 'Doh!' # Only the last name field will be sent to DynamoDB. >>> user.partial_save() """ if not self.needs_save(): return False key = self.get_keys() # Build a new dict of only the data we're changing. final_data = self.prepare_partial() # Build expectations of only the fields we're planning to update. expects = self.build_expects(fields=self._orig_data.keys()) returned = self.table._update_item(key, final_data, expects=expects) # Mark the object as clean. self.mark_clean() return returned def save(self, overwrite=False): """ Saves all data to DynamoDB. By default, this attempts to ensure that none of the underlying data has changed. If any fields have changed in between when the ``Item`` was constructed & when it is saved, this call will fail so as not to cause any data loss. If you're sure possibly overwriting data is acceptable, you can pass an ``overwrite=True``. If that's not acceptable, you may be able to use ``Item.partial_save`` to only write the changed field data. Optionally accepts an ``overwrite`` parameter, which should be a boolean. If you provide ``True``, the item will be forcibly overwritten within DynamoDB, even if another process changed the data in the meantime. (Default: ``False``) Returns ``True`` on success, ``False`` if no save was performed. Example:: >>> user['last_name'] = 'Doh!' # All data on the Item is sent to DynamoDB. >>> user.save() # If it fails, you can overwrite. >>> user.save(overwrite=True) """ if not self.needs_save(): return False final_data = self.prepare_full() expects = None if overwrite is False: # Build expectations about *all* of the data. expects = self.build_expects() returned = self.table._put_item(final_data, expects=expects) # Mark the object as clean. self.mark_clean() return returned def delete(self): """ Deletes the item's data to DynamoDB. Returns ``True`` on success. Example:: # Buh-bye now. >>> user.delete() """ key_data = self.get_keys() return self.table.delete_item(**key_data)
class Item(object): """ An object representing the item data within a DynamoDB table. An item is largely schema-free, meaning it can contain any data. The only limitation is that it must have data for the fields in the ``Table``'s schema. This object presents a dictionary-like interface for accessing/storing data. It also tries to intelligently track how data has changed throughout the life of the instance, to be as efficient as possible about updates. Empty items, or items that have no data, are considered falsey. """ def __init__(self, table, data=None, loaded=False): """ Constructs an (unsaved) ``Item`` instance. To persist the data in DynamoDB, you'll need to call the ``Item.save`` (or ``Item.partial_save``) on the instance. Requires a ``table`` parameter, which should be a ``Table`` instance. This is required, as DynamoDB's API is focus around all operations being table-level. It's also for persisting schema around many objects. Optionally accepts a ``data`` parameter, which should be a dictionary of the fields & values of the item. Optionally accepts a ``loaded`` parameter, which should be a boolean. ``True`` if it was preexisting data loaded from DynamoDB, ``False`` if it's new data from the user. Default is ``False``. Example:: >>> users = Table('users') >>> user = Item(users, data={ ... 'username': '******', ... 'first_name': 'John', ... 'date_joined': 1248o61592, ... }) # Change existing data. >>> user['first_name'] = 'Johann' # Add more data. >>> user['last_name'] = 'Doe' # Delete data. >>> del user['date_joined'] # Iterate over all the data. >>> for field, val in user.items(): ... print "%s: %s" % (field, val) username: johndoe first_name: John date_joined: 1248o61592 """ self.table = table self._loaded = loaded self._orig_data = {} self._data = data self._dynamizer = Dynamizer() if self._data is None: self._data = {} if self._loaded: self._orig_data = deepcopy(self._data) def __getitem__(self, key): return self._data.get(key, None) def __setitem__(self, key, value): self._data[key] = value def __delitem__(self, key): if not key in self._data: return del self._data[key] def keys(self): return self._data.keys() def values(self): return self._data.values() def items(self): return self._data.items() def get(self, key, default=None): return self._data.get(key, default) def __iter__(self): for key in self._data: yield self._data[key] def __contains__(self, key): return key in self._data def __nonzero__(self): return bool(self._data) def _determine_alterations(self): """ Checks the ``-orig_data`` against the ``_data`` to determine what changes to the data are present. Returns a dictionary containing the keys ``adds``, ``changes`` & ``deletes``, containing the updated data. """ alterations = { 'adds': {}, 'changes': {}, 'deletes': [], } orig_keys = set(self._orig_data.keys()) data_keys = set(self._data.keys()) # Run through keys we know are in both for changes. for key in orig_keys.intersection(data_keys): if self._data[key] != self._orig_data[key]: if self._is_storable(self._data[key]): alterations['changes'][key] = self._data[key] else: alterations['deletes'].append(key) # Run through additions. for key in data_keys.difference(orig_keys): if self._is_storable(self._data[key]): alterations['adds'][key] = self._data[key] # Run through deletions. for key in orig_keys.difference(data_keys): alterations['deletes'].append(key) return alterations def needs_save(self, data=None): """ Returns whether or not the data has changed on the ``Item``. Optionally accepts a ``data`` argument, which accepts the output from ``self._determine_alterations()`` if you've already called it. Typically unnecessary to do. Default is ``None``. Example: >>> user.needs_save() False >>> user['first_name'] = 'Johann' >>> user.needs_save() True """ if data is None: data = self._determine_alterations() needs_save = False for kind in ['adds', 'changes', 'deletes']: if len(data[kind]): needs_save = True break return needs_save def mark_clean(self): """ Marks an ``Item`` instance as no longer needing to be saved. Example: >>> user.needs_save() False >>> user['first_name'] = 'Johann' >>> user.needs_save() True >>> user.mark_clean() >>> user.needs_save() False """ self._orig_data = deepcopy(self._data) def mark_dirty(self): """ DEPRECATED: Marks an ``Item`` instance as needing to be saved. This method is no longer necessary, as the state tracking on ``Item`` has been improved to automatically detect proper state. """ return def load(self, data): """ This is only useful when being handed raw data from DynamoDB directly. If you have a Python datastructure already, use the ``__init__`` or manually set the data instead. Largely internal, unless you know what you're doing or are trying to mix the low-level & high-level APIs. """ self._data = {} for field_name, field_value in data.get('Item', {}).items(): self[field_name] = self._dynamizer.decode(field_value) self._loaded = True self._orig_data = deepcopy(self._data) def get_keys(self): """ Returns a Python-style dict of the keys/values. Largely internal. """ key_fields = self.table.get_key_fields() key_data = {} for key in key_fields: key_data[key] = self[key] return key_data def get_raw_keys(self): """ Returns a DynamoDB-style dict of the keys/values. Largely internal. """ raw_key_data = {} for key, value in self.get_keys().items(): raw_key_data[key] = self._dynamizer.encode(value) return raw_key_data def build_expects(self, fields=None): """ Builds up a list of expecations to hand off to DynamoDB on save. Largely internal. """ expects = {} if fields is None: fields = self._data.keys() + self._orig_data.keys() # Only uniques. fields = set(fields) for key in fields: expects[key] = { 'Exists': True, } value = None # Check for invalid keys. if not key in self._orig_data and not key in self._data: raise ValueError("Unknown key %s provided." % key) # States: # * New field (only in _data) # * Unchanged field (in both _data & _orig_data, same data) # * Modified field (in both _data & _orig_data, different data) # * Deleted field (only in _orig_data) orig_value = self._orig_data.get(key, NEWVALUE) current_value = self._data.get(key, NEWVALUE) if orig_value == current_value: # Existing field unchanged. value = current_value else: if key in self._data: if not key in self._orig_data: # New field. expects[key]['Exists'] = False else: # Existing field modified. value = orig_value else: # Existing field deleted. value = orig_value if value is not None: expects[key]['Value'] = self._dynamizer.encode(value) return expects def _is_storable(self, value): # We need to prevent ``None``, empty string & empty set from # heading to DDB, but allow false-y values like 0 & False make it. if not value: if not value in (0, 0.0, False): return False return True def prepare_full(self): """ Runs through all fields & encodes them to be handed off to DynamoDB as part of an ``save`` (``put_item``) call. Largely internal. """ # This doesn't save on it's own. Rather, we prepare the datastructure # and hand-off to the table to handle creation/update. final_data = {} for key, value in self._data.items(): if not self._is_storable(value): continue final_data[key] = self._dynamizer.encode(value) return final_data def prepare_partial(self): """ Runs through **ONLY** the changed/deleted fields & encodes them to be handed off to DynamoDB as part of an ``partial_save`` (``update_item``) call. Largely internal. """ # This doesn't save on it's own. Rather, we prepare the datastructure # and hand-off to the table to handle creation/update. final_data = {} fields = set() alterations = self._determine_alterations() for key, value in alterations['adds'].items(): final_data[key] = { 'Action': 'PUT', 'Value': self._dynamizer.encode(self._data[key]) } fields.add(key) for key, value in alterations['changes'].items(): final_data[key] = { 'Action': 'PUT', 'Value': self._dynamizer.encode(self._data[key]) } fields.add(key) for key in alterations['deletes']: final_data[key] = { 'Action': 'DELETE', } fields.add(key) return final_data, fields def partial_save(self): """ Saves only the changed data to DynamoDB. Extremely useful for high-volume/high-write data sets, this allows you to update only a handful of fields rather than having to push entire items. This prevents many accidental overwrite situations as well as saves on the amount of data to transfer over the wire. Returns ``True`` on success, ``False`` if no save was performed or the write failed. Example:: >>> user['last_name'] = 'Doh!' # Only the last name field will be sent to DynamoDB. >>> user.partial_save() """ key = self.get_keys() # Build a new dict of only the data we're changing. final_data, fields = self.prepare_partial() if not final_data: return False # Remove the key(s) from the ``final_data`` if present. # They should only be present if this is a new item, in which # case we shouldn't be sending as part of the data to update. for fieldname, value in key.items(): if fieldname in final_data: del final_data[fieldname] try: # It's likely also in ``fields``, so remove it there too. fields.remove(fieldname) except KeyError: pass # Build expectations of only the fields we're planning to update. expects = self.build_expects(fields=fields) returned = self.table._update_item(key, final_data, expects=expects) # Mark the object as clean. self.mark_clean() return returned def save(self, overwrite=False): """ Saves all data to DynamoDB. By default, this attempts to ensure that none of the underlying data has changed. If any fields have changed in between when the ``Item`` was constructed & when it is saved, this call will fail so as not to cause any data loss. If you're sure possibly overwriting data is acceptable, you can pass an ``overwrite=True``. If that's not acceptable, you may be able to use ``Item.partial_save`` to only write the changed field data. Optionally accepts an ``overwrite`` parameter, which should be a boolean. If you provide ``True``, the item will be forcibly overwritten within DynamoDB, even if another process changed the data in the meantime. (Default: ``False``) Returns ``True`` on success, ``False`` if no save was performed. Example:: >>> user['last_name'] = 'Doh!' # All data on the Item is sent to DynamoDB. >>> user.save() # If it fails, you can overwrite. >>> user.save(overwrite=True) """ if not self.needs_save() and not overwrite: return False final_data = self.prepare_full() expects = None if overwrite is False: # Build expectations about *all* of the data. expects = self.build_expects() returned = self.table._put_item(final_data, expects=expects) # Mark the object as clean. self.mark_clean() return returned def delete(self): """ Deletes the item's data to DynamoDB. Returns ``True`` on success. Example:: # Buh-bye now. >>> user.delete() """ key_data = self.get_keys() return self.table.delete_item(**key_data)
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, global_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 ``global_indexes`` parameter, which should be a list of ``GlobalBaseIndexField`` 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=[ ... HashKey('username') ... RangeKey('date_joined') ... ]), ... ], global_indexes=[ ... GlobalAllIndex('UsersByZipcode', parts=[ ... HashKey('zipcode'), ... RangeKey('username'), ... ], ... throughput={ ... 'read':10, ... 'write":10, ... }), ... ], 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 self.global_indexes = global_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, global_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 ``global_indexes`` parameter, which should be a list of ``GlobalBaseIndexField`` 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') ... ]), global_indexes=[ ... GlobalAllIndex('UsersByZipcode', parts=[ ... HashKey('zipcode'), ... RangeKey('username'), ... ], ... throughput={ ... 'read':10, ... 'write':10, ... }), ... ]) """ 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 if global_indexes is not None: table.global_indexes = global_indexes # Prep the schema. raw_schema = [] attr_defs = [] seen_attrs = set() for field in table.schema: raw_schema.append(field.schema()) # Build the attributes off what we know. seen_attrs.add(field.name) attr_defs.append(field.definition()) raw_throughput = { 'ReadCapacityUnits': int(table.throughput['read']), 'WriteCapacityUnits': int(table.throughput['write']), } kwargs = {} kwarg_map = { 'indexes': 'local_secondary_indexes', 'global_indexes': 'global_secondary_indexes', } for index_attr in ('indexes', 'global_indexes'): table_indexes = getattr(table, index_attr) if table_indexes: raw_indexes = [] for index_field in table_indexes: raw_indexes.append(index_field.schema()) # Make sure all attributes specified in the indexes are # added to the definition for field in index_field.parts: if field.name not in seen_attrs: seen_attrs.add(field.name) attr_defs.append(field.definition()) kwargs[kwarg_map[index_attr]] = raw_indexes 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, raw_attributes=None): """ Given a raw schema structure back from a DynamoDB response, parse out & build the high-level Python objects that represent them. """ schema = [] sane_attributes = {} if raw_attributes: for field in raw_attributes: sane_attributes[field['AttributeName']] = field['AttributeType'] for field in raw_schema: data_type = sane_attributes.get(field['AttributeName'], STRING) if field['KeyType'] == 'HASH': schema.append( HashKey(field['AttributeName'], data_type=data_type) ) elif field['KeyType'] == 'RANGE': schema.append( RangeKey(field['AttributeName'], data_type=data_type) ) 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'], None) 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', []) raw_attributes = result['Table'].get('AttributeDefinitions', []) self.schema = self._introspect_schema(raw_schema, raw_attributes) 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, global_indexes=None): """ 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 # To also update the global index(es) throughput. >>> users.update(throughput={ ... 'read': 20, ... 'write': 10, ... }, ... global_secondary_indexes={ ... 'TheIndexNameHere': { ... 'read': 15, ... 'write': 5, ... } ... }) True """ self.throughput = throughput data = { 'ReadCapacityUnits': int(self.throughput['read']), 'WriteCapacityUnits': int(self.throughput['write']), } gsi_data = None if global_indexes: gsi_data = [] for gsi_name, gsi_throughput in global_indexes.items(): gsi_data.append({ "Update": { "IndexName": gsi_name, "ProvisionedThroughput": { "ReadCapacityUnits": int(gsi_throughput['read']), "WriteCapacityUnits": int(gsi_throughput['write']), }, }, }) self.connection.update_table( self.table_name, provisioned_throughput=data, global_secondary_index_updates=gsi_data ) 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, attributes=None, **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``) Optionally accepts an ``attributes`` parameter, which should be a list of fieldname to fetch. (Default: ``None``, which means all fields should be fetched) 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, attributes_to_get=attributes, consistent_read=consistent ) if 'Item' not in item_data: raise exceptions.ItemNotFound("Item %s couldn't be found." % kwargs) item = Item(self) item.load(item_data) return item def has_item(self, **kwargs): """ Return whether an item (record) exists within 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``) Optionally accepts an ``attributes`` parameter, which should be a list of fieldnames to fetch. (Default: ``None``, which means all fields should be fetched) Returns ``True`` if an ``Item`` is present, ``False`` if not. Example:: # Simple, just hash-key schema. >>> users.has_item(username='******') True # Complex schema, item not present. >>> users.has_item( ... username='******', ... date_joined='2014-01-07' ... ) False """ try: self.get_item(**kwargs) except (JSONResponseError, exceptions.ItemNotFound): return False return True def lookup(self, *args, **kwargs): """ Look up an entry in DynamoDB. This is mostly backwards compatible with boto.dynamodb. Unlike get_item, it takes hash_key and range_key first, although you may still specify keyword arguments instead. Also unlike the get_item command, if the returned item has no keys (i.e., it does not exist in DynamoDB), a None result is returned, instead of an empty key object. Example:: >>> user = users.lookup(username) >>> user = users.lookup(username, consistent=True) >>> app = apps.lookup('my_customer_id', 'my_app_id') """ if not self.schema: self.describe() for x, arg in enumerate(args): kwargs[self.schema[x].name] = arg ret = self.get_item(**kwargs) if not ret.keys(): return None return ret def new_item(self, *args): """ Returns a new, blank item This is mostly for consistency with boto.dynamodb """ if not self.schema: self.describe() data = {} for x, arg in enumerate(args): data[self.schema[x].name] = arg return Item(self, data=data) 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]) ) # Special-case the ``IN`` case elif field_bits[-1] == 'in': for val in value: lookup['AttributeValueList'].append(self._dynamizer.encode(val)) 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, max_page_size=None, **filter_kwargs): """ **WARNING:** This method is provided **strictly** for backward-compatibility. It returns results in an incorrect order. If you are writing new code, please use ``Table.query_2``. """ reverse = not reverse return self.query_2(limit=limit, index=index, reverse=reverse, consistent=consistent, attributes=attributes, max_page_size=max_page_size, **filter_kwargs) def query_2(self, limit=None, index=None, reverse=False, consistent=False, attributes=None, max_page_size=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: ``False`` - 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. Optionally accepts a ``max_page_size`` parameter, which should be an integer count of the maximum number of items to retrieve **per-request**. This is useful in making faster requests & prevent the scan from drowning out other queries. (Default: ``None`` - fetch as many as DynamoDB will return) 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: if len(filter_kwargs) <= 1: if not self.global_indexes or not len(self.global_indexes): # If the schema only has one field, there's <= 1 filter # param & no Global Secondary Indexes, this is user # error. Bail early. 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( max_page_size=max_page_size ) 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, 'consistent_read': consistent, 'select': select, 'attributes_to_get': attributes_to_get, } if reverse: kwargs['scan_index_forward'] = False 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, max_page_size=None, attributes=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) Optionally accepts a ``segment`` parameter, which should be an integer of the segment to retrieve on. Please see the documentation about Parallel Scans (Default: ``None`` - no segments) Optionally accepts a ``total_segments`` parameter, which should be an integer count of number of segments to divide the table into. Please see the documentation about Parallel Scans (Default: ``None`` - no segments) Optionally accepts a ``max_page_size`` parameter, which should be an integer count of the maximum number of items to retrieve **per-request**. This is useful in making faster requests & prevent the scan from drowning out other queries. (Default: ``None`` - fetch as many as DynamoDB will return) Optionally accepts an ``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:: # 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( max_page_size=max_page_size ) kwargs = filter_kwargs.copy() kwargs.update({ 'limit': limit, 'segment': segment, 'total_segments': total_segments, 'attributes': attributes, }) results.to_call(self._scan, **kwargs) return results def _scan(self, limit=None, exclusive_start_key=None, segment=None, total_segments=None, attributes=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, 'attributes_to_get': attributes, } 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)