def __init__(
self,
datasource: Dict,
queries: List[Dict],
):
self.datasource = ConnectorRegistry.get_datasource(datasource.get('type'),
int(datasource.get('id')),
db.session)
self.queries = list(map(lambda query_obj: QueryObject(**query_obj), queries))
def __init__(
self,
datasource: Dict,
queries: List[Dict],
force: bool = False,
custom_cache_timeout: int = None,
):
self.datasource = ConnectorRegistry.get_datasource(datasource.get('type'),
int(datasource.get('id')),
db.session)
self.queries = list(map(lambda query_obj: QueryObject(**query_obj), queries))
self.force = force
self.custom_cache_timeout = custom_cache_timeout
self.enforce_numerical_metrics = True
def save(self):
datasource = json.loads(request.form.get('data'))
datasource_id = datasource.get('id')
datasource_type = datasource.get('type')
orm_datasource = ConnectorRegistry.get_datasource(
datasource_type, datasource_id, db.session)
if not check_ownership(orm_datasource, raise_if_false=False):
return json_error_response(
__(
'You are not authorized to modify '
'this data source configuration'),
status='401',
)
orm_datasource.update_from_object(datasource)
data = orm_datasource.data
db.session.commit()
return self.json_response(data)
def get_viz(
slice_id=None,
form_data=None,
datasource_type=None,
datasource_id=None,
force=False,
):
if slice_id:
slc = (db.session.query(models.Slice).filter_by(id=slice_id).one())
return slc.get_viz()
else:
viz_type = form_data.get('viz_type', 'table')
datasource = ConnectorRegistry.get_datasource(datasource_type,
datasource_id,
db.session)
viz_obj = viz.viz_types[viz_type](
datasource,
form_data=form_data,
force=force,
)
return viz_obj
def __init__( # pylint: disable=too-many-arguments
self,
datasource: DatasourceDict,
queries: List[Dict[str, Any]],
force: bool = False,
custom_cache_timeout: Optional[int] = None,
result_type: Optional[ChartDataResultType] = None,
result_format: Optional[ChartDataResultFormat] = None,
) -> None:
self.datasource = ConnectorRegistry.get_datasource(
str(datasource["type"]), int(datasource["id"]), db.session)
self.queries = [QueryObject(**query_obj) for query_obj in queries]
self.force = force
self.custom_cache_timeout = custom_cache_timeout
self.result_type = result_type or ChartDataResultType.FULL
self.result_format = result_format or ChartDataResultFormat.JSON
self.cache_values = {
"datasource": datasource,
"queries": queries,
"result_type": self.result_type,
"result_format": self.result_format,
}
def save(self):
datasource = json.loads(request.form.get('data'))
datasource_id = datasource.get('id')
datasource_type = datasource.get('type')
orm_datasource = ConnectorRegistry.get_datasource(
datasource_type, datasource_id, db.session)
if not check_ownership(orm_datasource, raise_if_false=False):
return json_error_response(
__(
'You are not authorized to modify '
'this data source configuration'),
status='401',
)
if 'owners' in datasource:
datasource['owners'] = db.session.query(orm_datasource.owner_class).filter(
orm_datasource.owner_class.id.in_(datasource['owners'])).all()
orm_datasource.update_from_object(datasource)
data = orm_datasource.data
db.session.commit()
return self.json_response(data)
def external_metadata(
self, datasource_type: str, datasource_id: int
) -> FlaskResponse:
"""Gets column info from the source system"""
if datasource_type == "druid":
datasource = ConnectorRegistry.get_datasource(
datasource_type, datasource_id, db.session
)
elif datasource_type == "table":
database = (
db.session.query(Database).filter_by(id=request.args.get("db_id")).one()
)
table_class = ConnectorRegistry.sources["table"]
datasource = table_class(
database=database,
table_name=request.args.get("table_name"),
schema=request.args.get("schema") or None,
)
else:
raise Exception(f"Unsupported datasource_type: {datasource_type}")
external_metadata = datasource.external_metadata()
return self.json_response(external_metadata)
def save(self) -> FlaskResponse:
data = request.form.get("data")
if not isinstance(data, str):
return json_error_response("Request missing data field.", status=500)
datasource_dict = json.loads(data)
datasource_id = datasource_dict.get("id")
datasource_type = datasource_dict.get("type")
database_id = datasource_dict["database"].get("id")
orm_datasource = ConnectorRegistry.get_datasource(
datasource_type, datasource_id, db.session
)
orm_datasource.database_id = database_id
if "owners" in datasource_dict and orm_datasource.owner_class is not None:
datasource_dict["owners"] = (
db.session.query(orm_datasource.owner_class)
.filter(orm_datasource.owner_class.id.in_(datasource_dict["owners"]))
.all()
)
duplicates = [
name
for name, count in Counter(
[col["column_name"] for col in datasource_dict["columns"]]
).items()
if count > 1
]
if duplicates:
return json_error_response(
f"Duplicate column name(s): {','.join(duplicates)}", status=409
)
orm_datasource.update_from_object(datasource_dict)
data = orm_datasource.data
db.session.commit()
return self.json_response(data)
def test_query_cache_key_changes_when_metric_is_updated(self):
self.login(username="******")
payload = get_query_context("birth_names")
# make temporary change and revert it to refresh the changed_on property
datasource = ConnectorRegistry.get_datasource(
datasource_type=payload["datasource"]["type"],
datasource_id=payload["datasource"]["id"],
session=db.session,
)
datasource.metrics.append(
SqlMetric(metric_name="foo", expression="select 1;"))
db.session.commit()
# construct baseline query_cache_key
query_context = ChartDataQueryContextSchema().load(payload)
query_object = query_context.queries[0]
cache_key_original = query_context.query_cache_key(query_object)
# wait a second since mysql records timestamps in second granularity
time.sleep(1)
datasource.metrics[0].expression = "select 2;"
db.session.commit()
# create new QueryContext with unchanged attributes, extract new query_cache_key
query_context = ChartDataQueryContextSchema().load(payload)
query_object = query_context.queries[0]
cache_key_new = query_context.query_cache_key(query_object)
datasource.metrics = []
db.session.commit()
# the new cache_key should be different due to updated datasource
self.assertNotEqual(cache_key_original, cache_key_new)
def get_viz(
slice_id=None,
form_data=None,
datasource_type=None,
datasource_id=None,
force=False,
):
if slice_id:
slc = (
db.session.query(models.Slice)
.filter_by(id=slice_id)
.one()
)
return slc.get_viz()
else:
viz_type = form_data.get('viz_type', 'table')
datasource = ConnectorRegistry.get_datasource(
datasource_type, datasource_id, db.session)
viz_obj = viz.viz_types[viz_type](
datasource,
form_data=form_data,
force=force,
)
return viz_obj
def _convert_to_model(self, datasource: DatasourceDict) -> BaseDatasource:
return ConnectorRegistry.get_datasource(str(datasource["type"]),
int(datasource["id"]),
db.session)
def get(self, datasource_type: str, datasource_id: int) -> FlaskResponse:
datasource = ConnectorRegistry.get_datasource(datasource_type,
datasource_id,
db.session)
return self.json_response(datasource.data)
def __init__(
self,
datasource: Optional[DatasourceDict] = None,
result_type: Optional[ChartDataResultType] = None,
annotation_layers: Optional[List[Dict[str, Any]]] = None,
applied_time_extras: Optional[Dict[str, str]] = None,
apply_fetch_values_predicate: bool = False,
granularity: Optional[str] = None,
metrics: Optional[List[Union[Dict[str, Any], str]]] = None,
groupby: Optional[List[str]] = None,
filters: Optional[List[Dict[str, Any]]] = None,
time_range: Optional[str] = None,
time_shift: Optional[str] = None,
is_timeseries: Optional[bool] = None,
timeseries_limit: int = 0,
row_limit: Optional[int] = None,
row_offset: Optional[int] = None,
timeseries_limit_metric: Optional[Metric] = None,
order_desc: bool = True,
extras: Optional[Dict[str, Any]] = None,
columns: Optional[List[str]] = None,
orderby: Optional[List[OrderBy]] = None,
post_processing: Optional[List[Optional[Dict[str, Any]]]] = None,
is_rowcount: bool = False,
**kwargs: Any,
):
columns = columns or []
groupby = groupby or []
extras = extras or {}
annotation_layers = annotation_layers or []
self.is_rowcount = is_rowcount
self.datasource = None
if datasource:
self.datasource = ConnectorRegistry.get_datasource(
str(datasource["type"]), int(datasource["id"]), db.session)
self.result_type = result_type
self.apply_fetch_values_predicate = apply_fetch_values_predicate or False
self.annotation_layers = [
layer for layer in annotation_layers
# formula annotations don't affect the payload, hence can be dropped
if layer["annotationType"] != "FORMULA"
]
self.applied_time_extras = applied_time_extras or {}
self.granularity = granularity
self.from_dttm, self.to_dttm = get_since_until(
relative_start=extras.get("relative_start",
config["DEFAULT_RELATIVE_START_TIME"]),
relative_end=extras.get("relative_end",
config["DEFAULT_RELATIVE_END_TIME"]),
time_range=time_range,
time_shift=time_shift,
)
# is_timeseries is True if time column is in either columns or groupby
# (both are dimensions)
self.is_timeseries = (is_timeseries if is_timeseries is not None else
DTTM_ALIAS in columns + groupby)
self.time_range = time_range
self.time_shift = parse_human_timedelta(time_shift)
self.post_processing = [
post_proc for post_proc in post_processing or [] if post_proc
]
# Support metric reference/definition in the format of
# 1. 'metric_name' - name of predefined metric
# 2. { label: 'label_name' } - legacy format for a predefined metric
# 3. { expressionType: 'SIMPLE' | 'SQL', ... } - adhoc metric
self.metrics = metrics and [
x if isinstance(x, str) or is_adhoc_metric(x) else
x["label"] # type: ignore
for x in metrics
]
self.row_limit = config["ROW_LIMIT"] if row_limit is None else row_limit
self.row_offset = row_offset or 0
self.filter = filters or []
self.timeseries_limit = timeseries_limit
self.timeseries_limit_metric = timeseries_limit_metric
self.order_desc = order_desc
self.extras = extras
if config["SIP_15_ENABLED"]:
self.extras["time_range_endpoints"] = get_time_range_endpoints(
form_data=self.extras)
self.columns = columns
self.groupby = groupby or []
self.orderby = orderby or []
# rename deprecated fields
for field in DEPRECATED_FIELDS:
if field.old_name in kwargs:
logger.warning(
"The field `%s` is deprecated, please use `%s` instead.",
field.old_name,
field.new_name,
)
value = kwargs[field.old_name]
if value:
if hasattr(self, field.new_name):
logger.warning(
"The field `%s` is already populated, "
"replacing value with contents from `%s`.",
field.new_name,
field.old_name,
)
setattr(self, field.new_name, value)
# move deprecated extras fields to extras
for field in DEPRECATED_EXTRAS_FIELDS:
if field.old_name in kwargs:
logger.warning(
"The field `%s` is deprecated and should "
"be passed to `extras` via the `%s` property.",
field.old_name,
field.new_name,
)
value = kwargs[field.old_name]
if value:
if hasattr(self.extras, field.new_name):
logger.warning(
"The field `%s` is already populated in "
"`extras`, replacing value with contents "
"from `%s`.",
field.new_name,
field.old_name,
)
self.extras[field.new_name] = value
from superset.connectors.connector_registry import ConnectorRegistry
from flask_appbuilder.security.sqla.models import User
from superset.viz import TableViz
from superset import db
from flask import g
import json
f = open('d:\\home\\pivot_viz\\form_data.json')
form_data_json = f.read()
f.close()
g.user = db.session.query(User).filter(User.id == 2).one()
form_data = json.loads(form_data_json)
datasource_type = form_data.get('viz_type', 'table')
datasource_id = form_data['datasource'].split('__')[0]
datasource = ConnectorRegistry.get_datasource(datasource_type, datasource_id,
db.session)
viz = TableViz(datasource, form_data)
res = viz.get_payload(force=True)
# print(res)
with open('d:\\home\\pivot_viz\\response.json', 'w', encoding='utf8') as f:
f.write(viz.json_dumps(res))
def __init__( # pylint: disable=too-many-arguments,too-many-locals
self,
query_context: "QueryContext",
annotation_layers: Optional[List[Dict[str, Any]]] = None,
applied_time_extras: Optional[Dict[str, str]] = None,
apply_fetch_values_predicate: bool = False,
columns: Optional[List[str]] = None,
datasource: Optional[DatasourceDict] = None,
extras: Optional[Dict[str, Any]] = None,
filters: Optional[List[QueryObjectFilterClause]] = None,
granularity: Optional[str] = None,
is_rowcount: bool = False,
is_timeseries: Optional[bool] = None,
metrics: Optional[List[Metric]] = None,
order_desc: bool = True,
orderby: Optional[List[OrderBy]] = None,
post_processing: Optional[List[Optional[Dict[str, Any]]]] = None,
result_type: Optional[ChartDataResultType] = None,
row_limit: Optional[int] = None,
row_offset: Optional[int] = None,
series_columns: Optional[List[str]] = None,
series_limit: int = 0,
series_limit_metric: Optional[Metric] = None,
time_range: Optional[str] = None,
time_shift: Optional[str] = None,
**kwargs: Any,
):
columns = columns or []
extras = extras or {}
annotation_layers = annotation_layers or []
self.time_offsets = kwargs.get("time_offsets", [])
self.inner_from_dttm = kwargs.get("inner_from_dttm")
self.inner_to_dttm = kwargs.get("inner_to_dttm")
if series_columns:
self.series_columns = series_columns
elif is_timeseries and metrics:
self.series_columns = columns
else:
self.series_columns = []
self.is_rowcount = is_rowcount
self.datasource = None
if datasource:
self.datasource = ConnectorRegistry.get_datasource(
str(datasource["type"]), int(datasource["id"]), db.session)
self.result_type = result_type or query_context.result_type
self.apply_fetch_values_predicate = apply_fetch_values_predicate or False
self.annotation_layers = [
layer for layer in annotation_layers
# formula annotations don't affect the payload, hence can be dropped
if layer["annotationType"] != "FORMULA"
]
self.applied_time_extras = applied_time_extras or {}
self.granularity = granularity
self.from_dttm, self.to_dttm = get_since_until(
relative_start=extras.get("relative_start",
config["DEFAULT_RELATIVE_START_TIME"]),
relative_end=extras.get("relative_end",
config["DEFAULT_RELATIVE_END_TIME"]),
time_range=time_range,
time_shift=time_shift,
)
# is_timeseries is True if time column is in either columns or groupby
# (both are dimensions)
self.is_timeseries = (is_timeseries if is_timeseries is not None else
DTTM_ALIAS in columns)
self.time_range = time_range
self.time_shift = parse_human_timedelta(time_shift)
self.post_processing = [
post_proc for post_proc in post_processing or [] if post_proc
]
# Support metric reference/definition in the format of
# 1. 'metric_name' - name of predefined metric
# 2. { label: 'label_name' } - legacy format for a predefined metric
# 3. { expressionType: 'SIMPLE' | 'SQL', ... } - adhoc metric
self.metrics = metrics and [
x if isinstance(x, str) or is_adhoc_metric(x) else
x["label"] # type: ignore
for x in metrics
]
default_row_limit = (config["SAMPLES_ROW_LIMIT"]
if self.result_type == ChartDataResultType.SAMPLES
else config["ROW_LIMIT"])
self.row_limit = apply_max_row_limit(row_limit or default_row_limit)
self.row_offset = row_offset or 0
self.filter = filters or []
self.series_limit = series_limit
self.series_limit_metric = series_limit_metric
self.order_desc = order_desc
self.extras = extras
if config["SIP_15_ENABLED"]:
self.extras["time_range_endpoints"] = get_time_range_endpoints(
form_data=self.extras)
self.columns = columns
self.orderby = orderby or []
self._rename_deprecated_fields(kwargs)
self._move_deprecated_extra_fields(kwargs)
def external_metadata(self, datasource_type=None, datasource_id=None):
"""Gets column info from the source system"""
orm_datasource = ConnectorRegistry.get_datasource(
datasource_type, datasource_id, db.session)
return self.json_response(orm_datasource.external_metadata())
def get_datasource_by_id(datasource_id: int,
datasource_type: str) -> BaseDatasource:
try:
return ConnectorRegistry.get_datasource(datasource_type, datasource_id)
except (NoResultFound, KeyError):
raise DatasourceNotFoundValidationError()
def external_metadata(self, datasource_type=None, datasource_id=None):
"""Gets column info from the source system"""
orm_datasource = ConnectorRegistry.get_datasource(
datasource_type, datasource_id, db.session)
return self.json_response(orm_datasource.external_metadata())
