def test_read_rows(self):
# Setup Expected Response
last_scanned_row_key = b"-126"
expected_response = {"last_scanned_row_key": last_scanned_row_key}
expected_response = bigtable_pb2.ReadRowsResponse(**expected_response)
# Mock the API response
channel = ChannelStub(responses=[iter([expected_response])])
patch = mock.patch("google.api_core.grpc_helpers.create_channel")
with patch as create_channel:
create_channel.return_value = channel
client = bigtable_v2.BigtableClient()
# Setup Request
table_name = client.table_path("[PROJECT]", "[INSTANCE]", "[TABLE]")
response = client.read_rows(table_name)
resources = list(response)
assert len(resources) == 1
assert expected_response == resources[0]
assert len(channel.requests) == 1
expected_request = bigtable_pb2.ReadRowsRequest(table_name=table_name)
actual_request = channel.requests[0][1]
assert expected_request == actual_request
def build_updated_request(self):
""" Updates the given message request as per last scanned key
"""
r_kwargs = {
"table_name": self.message.table_name,
"filter": self.message.filter,
}
if self.message.rows_limit != 0:
r_kwargs["rows_limit"] = max(
1, self.message.rows_limit - self.rows_read_so_far
)
# if neither RowSet.row_keys nor RowSet.row_ranges currently exist,
# add row_range that starts with last_scanned_key as start_key_open
# to request only rows that have not been returned yet
if not self.message.HasField("rows"):
row_range = data_v2_pb2.RowRange(start_key_open=self.last_scanned_key)
r_kwargs["rows"] = data_v2_pb2.RowSet(row_ranges=[row_range])
else:
row_keys = self._filter_rows_keys()
row_ranges = self._filter_row_ranges()
r_kwargs["rows"] = data_v2_pb2.RowSet(
row_keys=row_keys, row_ranges=row_ranges
)
return data_messages_v2_pb2.ReadRowsRequest(**r_kwargs)
def build_updated_request(self):
""" Updates the given message request as per last scanned key
"""
r_kwargs = {
'table_name': self.message.table_name,
'filter': self.message.filter
}
if self.message.rows_limit != 0:
r_kwargs['rows_limit'] = max(
1, self.message.rows_limit - self.rows_read_so_far)
row_keys = self._filter_rows_keys()
row_ranges = self._filter_row_ranges()
r_kwargs['rows'] = data_v2_pb2.RowSet(row_keys=row_keys,
row_ranges=row_ranges)
return data_messages_v2_pb2.ReadRowsRequest(**r_kwargs)
def test_read_rows(self):
# Setup Expected Response
last_scanned_row_key = b'-126'
expected_response = {'last_scanned_row_key': last_scanned_row_key}
expected_response = bigtable_pb2.ReadRowsResponse(**expected_response)
# Mock the API response
channel = ChannelStub(responses=[iter([expected_response])])
client = bigtable_v2.BigtableClient(channel=channel)
# Setup Request
table_name = client.table_path('[PROJECT]', '[INSTANCE]', '[TABLE]')
response = client.read_rows(table_name)
resources = list(response)
assert len(resources) == 1
assert expected_response == resources[0]
assert len(channel.requests) == 1
expected_request = bigtable_pb2.ReadRowsRequest(table_name=table_name)
actual_request = channel.requests[0][1]
assert expected_request == actual_request
def _ReadRowsRequestPB(*args, **kw):
from google.cloud.bigtable_v2.proto import bigtable_pb2 as messages_v2_pb2
return messages_v2_pb2.ReadRowsRequest(*args, **kw)
def _create_row_request(
table_name,
start_key=None,
end_key=None,
filter_=None,
limit=None,
end_inclusive=False,
app_profile_id=None,
row_set=None,
):
"""Creates a request to read rows in a table.
:type table_name: str
:param table_name: The name of the table to read from.
:type start_key: bytes
:param start_key: (Optional) The beginning of a range of row keys to
read from. The range will include ``start_key``. If
left empty, will be interpreted as the empty string.
:type end_key: bytes
:param end_key: (Optional) The end of a range of row keys to read from.
The range will not include ``end_key``. If left empty,
will be interpreted as an infinite string.
:type filter_: :class:`.RowFilter`
:param filter_: (Optional) The filter to apply to the contents of the
specified row(s). If unset, reads the entire table.
:type limit: int
:param limit: (Optional) The read will terminate after committing to N
rows' worth of results. The default (zero) is to return
all results.
:type end_inclusive: bool
:param end_inclusive: (Optional) Whether the ``end_key`` should be
considered inclusive. The default is False (exclusive).
:type: app_profile_id: str
:param app_profile_id: (Optional) The unique name of the AppProfile.
:type row_set: :class:`row_set.RowSet`
:param row_set: (Optional) The row set containing multiple row keys and
row_ranges.
:rtype: :class:`data_messages_v2_pb2.ReadRowsRequest`
:returns: The ``ReadRowsRequest`` protobuf corresponding to the inputs.
:raises: :class:`ValueError <exceptions.ValueError>` if both
``row_set`` and one of ``start_key`` or ``end_key`` are set
"""
request_kwargs = {"table_name": table_name}
if (start_key is not None or end_key is not None) and row_set is not None:
raise ValueError("Row range and row set cannot be "
"set simultaneously")
if filter_ is not None:
request_kwargs["filter"] = filter_.to_pb()
if limit is not None:
request_kwargs["rows_limit"] = limit
if app_profile_id is not None:
request_kwargs["app_profile_id"] = app_profile_id
message = data_messages_v2_pb2.ReadRowsRequest(**request_kwargs)
if start_key is not None or end_key is not None:
row_set = RowSet()
row_set.add_row_range(
RowRange(start_key, end_key, end_inclusive=end_inclusive))
if row_set is not None:
row_set._update_message_request(message)
return message
def read_rows(
self,
table_name,
app_profile_id=None,
rows=None,
filter_=None,
rows_limit=None,
retry=google.api_core.gapic_v1.method.DEFAULT,
timeout=google.api_core.gapic_v1.method.DEFAULT,
metadata=None,
):
"""
Streams back the contents of all requested rows in key order, optionally
applying the same Reader filter to each. Depending on their size,
rows and cells may be broken up across multiple responses, but
atomicity of each row will still be preserved. See the
ReadRowsResponse documentation for details.
Example:
>>> from google.cloud import bigtable_v2
>>>
>>> client = bigtable_v2.BigtableClient()
>>>
>>> table_name = client.table_path('[PROJECT]', '[INSTANCE]', '[TABLE]')
>>>
>>> for element in client.read_rows(table_name):
... # process element
... pass
Args:
table_name (str): The unique name of the table from which to read. Values are of the form
``projects/<project>/instances/<instance>/tables/<table>``.
app_profile_id (str): This value specifies routing for replication. If not specified, the
"default" application profile will be used.
rows (Union[dict, ~google.cloud.bigtable_v2.types.RowSet]): The row keys and/or ranges to read. If not specified, reads from all rows.
If a dict is provided, it must be of the same form as the protobuf
message :class:`~google.cloud.bigtable_v2.types.RowSet`
filter_ (Union[dict, ~google.cloud.bigtable_v2.types.RowFilter]): The filter to apply to the contents of the specified row(s). If unset,
reads the entirety of each row.
If a dict is provided, it must be of the same form as the protobuf
message :class:`~google.cloud.bigtable_v2.types.RowFilter`
rows_limit (long): The read will terminate after committing to N rows' worth of results. The
default (zero) is to return all results.
retry (Optional[google.api_core.retry.Retry]): A retry object used
to retry requests. If ``None`` is specified, requests will
be retried using a default configuration.
timeout (Optional[float]): The amount of time, in seconds, to wait
for the request to complete. Note that if ``retry`` is
specified, the timeout applies to each individual attempt.
metadata (Optional[Sequence[Tuple[str, str]]]): Additional metadata
that is provided to the method.
Returns:
Iterable[~google.cloud.bigtable_v2.types.ReadRowsResponse].
Raises:
google.api_core.exceptions.GoogleAPICallError: If the request
failed for any reason.
google.api_core.exceptions.RetryError: If the request failed due
to a retryable error and retry attempts failed.
ValueError: If the parameters are invalid.
"""
# Wrap the transport method to add retry and timeout logic.
if "read_rows" not in self._inner_api_calls:
self._inner_api_calls[
"read_rows"] = google.api_core.gapic_v1.method.wrap_method(
self.transport.read_rows,
default_retry=self._method_configs["ReadRows"].retry,
default_timeout=self._method_configs["ReadRows"].timeout,
client_info=self._client_info,
)
request = bigtable_pb2.ReadRowsRequest(
table_name=table_name,
app_profile_id=app_profile_id,
rows=rows,
filter=filter_,
rows_limit=rows_limit,
)
if metadata is None:
metadata = []
metadata = list(metadata)
try:
routing_header = [("table_name", table_name)]
except AttributeError:
pass
else:
routing_metadata = google.api_core.gapic_v1.routing_header.to_grpc_metadata(
routing_header)
metadata.append(routing_metadata)
return self._inner_api_calls["read_rows"](request,
retry=retry,
timeout=timeout,
metadata=metadata)
def _create_row_request(table_name,
row_key=None,
start_key=None,
end_key=None,
filter_=None,
limit=None,
end_inclusive=False,
app_profile_id=None):
"""Creates a request to read rows in a table.
:type table_name: str
:param table_name: The name of the table to read from.
:type row_key: bytes
:param row_key: (Optional) The key of a specific row to read from.
:type start_key: bytes
:param start_key: (Optional) The beginning of a range of row keys to
read from. The range will include ``start_key``. If
left empty, will be interpreted as the empty string.
:type end_key: bytes
:param end_key: (Optional) The end of a range of row keys to read from.
The range will not include ``end_key``. If left empty,
will be interpreted as an infinite string.
:type filter_: :class:`.RowFilter`
:param filter_: (Optional) The filter to apply to the contents of the
specified row(s). If unset, reads the entire table.
:type limit: int
:param limit: (Optional) The read will terminate after committing to N
rows' worth of results. The default (zero) is to return
all results.
:type end_inclusive: bool
:param end_inclusive: (Optional) Whether the ``end_key`` should be
considered inclusive. The default is False (exclusive).
:type: app_profile_id: str
:param app_profile_id: (Optional) The unique name of the AppProfile.
:rtype: :class:`data_messages_v2_pb2.ReadRowsRequest`
:returns: The ``ReadRowsRequest`` protobuf corresponding to the inputs.
:raises: :class:`ValueError <exceptions.ValueError>` if both
``row_key`` and one of ``start_key`` and ``end_key`` are set
"""
request_kwargs = {'table_name': table_name}
if (row_key is not None
and (start_key is not None or end_key is not None)):
raise ValueError('Row key and row range cannot be '
'set simultaneously')
range_kwargs = {}
if start_key is not None or end_key is not None:
if start_key is not None:
range_kwargs['start_key_closed'] = _to_bytes(start_key)
if end_key is not None:
end_key_key = 'end_key_open'
if end_inclusive:
end_key_key = 'end_key_closed'
range_kwargs[end_key_key] = _to_bytes(end_key)
if filter_ is not None:
request_kwargs['filter'] = filter_.to_pb()
if limit is not None:
request_kwargs['rows_limit'] = limit
if app_profile_id is not None:
request_kwargs['app_profile_id'] = app_profile_id
message = data_messages_v2_pb2.ReadRowsRequest(**request_kwargs)
if row_key is not None:
message.rows.row_keys.append(_to_bytes(row_key))
if range_kwargs:
message.rows.row_ranges.add(**range_kwargs)
return message
def read_rows(self,
table_name,
app_profile_id=None,
rows=None,
filter_=None,
rows_limit=None,
retry=google.api_core.gapic_v1.method.DEFAULT,
timeout=google.api_core.gapic_v1.method.DEFAULT):
"""
Streams back the contents of all requested rows in key order, optionally
applying the same Reader filter to each. Depending on their size,
rows and cells may be broken up across multiple responses, but
atomicity of each row will still be preserved. See the
ReadRowsResponse documentation for details.
Example:
>>> from google.cloud import bigtable_v2
>>>
>>> client = bigtable_v2.BigtableClient()
>>>
>>> table_name = client.table_path('[PROJECT]', '[INSTANCE]', '[TABLE]')
>>>
>>> for element in client.read_rows(table_name):
... # process element
... pass
Args:
table_name (str): The unique name of the table from which to read.
Values are of the form
``projects/<project>/instances/<instance>/tables/<table>``.
app_profile_id (str): This is a private alpha release of Cloud Bigtable replication. This feature
is not currently available to most Cloud Bigtable customers. This feature
might be changed in backward-incompatible ways and is not recommended for
production use. It is not subject to any SLA or deprecation policy.
This value specifies routing for replication. If not specified, the
\"default\" application profile will be used.
rows (Union[dict, ~google.cloud.bigtable_v2.types.RowSet]): The row keys and/or ranges to read. If not specified, reads from all rows.
If a dict is provided, it must be of the same form as the protobuf
message :class:`~google.cloud.bigtable_v2.types.RowSet`
filter_ (Union[dict, ~google.cloud.bigtable_v2.types.RowFilter]): The filter to apply to the contents of the specified row(s). If unset,
reads the entirety of each row.
If a dict is provided, it must be of the same form as the protobuf
message :class:`~google.cloud.bigtable_v2.types.RowFilter`
rows_limit (long): The read will terminate after committing to N rows' worth of results. The
default (zero) is to return all results.
retry (Optional[google.api_core.retry.Retry]): A retry object used
to retry requests. If ``None`` is specified, requests will not
be retried.
timeout (Optional[float]): The amount of time, in seconds, to wait
for the request to complete. Note that if ``retry`` is
specified, the timeout applies to each individual attempt.
Returns:
Iterable[~google.cloud.bigtable_v2.types.ReadRowsResponse].
Raises:
google.api_core.exceptions.GoogleAPICallError: If the request
failed for any reason.
google.api_core.exceptions.RetryError: If the request failed due
to a retryable error and retry attempts failed.
ValueError: If the parameters are invalid.
"""
request = bigtable_pb2.ReadRowsRequest(
table_name=table_name,
app_profile_id=app_profile_id,
rows=rows,
filter=filter_,
rows_limit=rows_limit,
)
return self._read_rows(request, retry=retry, timeout=timeout)