#725

pending completion

Build # #725

Build Type

push

circle-ci

Committed by

web-flow

Commit Message

chore: reducing coverage loss (#619)

* adding delete operation

* Adding Insert Statement

* checkpoint

* supporting multiple entries

* implemented for structured data error

* adding parser visitor for delete

* delete executor

* delete plan and rules

* adding delete to plan executor

* change position of LogicalDelete

* logical delimeter

* delete test case

* adding test case

* adding test case

* adding delete testcase

* adding predicate to delete executor

* adding delete to Image storage

* bug fix in delete

* fixing testcase

* adding test case for insert statement

* remove order_by from statement_binder.py

* better variable names, using Batch

* error message for insert

* removing order_by and limit from delete

* remove order_by and limit

* use f-string

* adding to changelog

* removing commit messages

* formatting

* fixing comments

* formatting

* eva insert f32 values

* fix: should delete range

* delete multiple rows

* udf bootstrap

* try to run tests in parallel

* minor fix for ray to work

* ray fixes

---------

Co-authored-by: Aryan-Rajoria <aryanrajoria1003@gmail.com>
Co-authored-by: Gaurav <gaurav21776@gmail.com>

Run Details

236 of 236 new or added lines in 53 files covered. (100.0%)

7003 of 9005 relevant lines covered (77.77%)

0.78 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

48.39

/eva/executor/delete_executor.py

# coding=utf-8
# Copyright 2018-2022 EVA
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from typing import Iterator

import pandas as pd

from eva.catalog.catalog_manager import CatalogManager
from eva.catalog.catalog_type import TableType
from eva.executor.abstract_executor import AbstractExecutor
from eva.executor.executor_utils import apply_predicate
from eva.models.storage.batch import Batch
from eva.plan_nodes.project_plan import ProjectPlan
from eva.storage.storage_engine import StorageEngine


class DeleteExecutor(AbstractExecutor):
    """ """

    def __init__(self, node: ProjectPlan):
        super().__init__(node)
        self.predicate = node.where_clause
        self.catalog = CatalogManager()

    def exec(self, *args, **kwargs) -> Iterator[Batch]:
        table_catalog = self.node.table_ref.table.table_obj
        storage_engine = StorageEngine.factory(table_catalog)
        del_batch = Batch()

        assert (
            table_catalog.table_type == TableType.STRUCTURED_DATA
        ), "DELETE only implemented for structured data"

        del_batch = storage_engine.read(table_catalog)
        del_batch = list(del_batch)[0]

        # Added because of inconsistency in col_alias
        # in structured data Batch project function
        original_column_names = list(del_batch.frames.columns)
        column_names = [
            f"{table_catalog.name.lower()}.{name}"
            for name in original_column_names
            if not name == "_row_id"
        ]
        column_names.insert(0, "_row_id")
        del_batch.frames.columns = column_names
        del_batch = apply_predicate(del_batch, self.predicate)

        # All the batches that need to be deleted
        del_batch.frames.columns = original_column_names
        table_needed = del_batch.frames[[f"{self.predicate.children[0].col_name}"]]
        for num in range(len(del_batch)):
            storage_engine.delete(table_catalog, table_needed.iloc[num])

        yield Batch(pd.DataFrame(["Deleted row"]))

1	# coding=utf-8
2	# Copyright 2018-2022 EVA
3	#
4	# Licensed under the Apache License, Version 2.0 (the "License");
5	# you may not use this file except in compliance with the License.
6	# You may obtain a copy of the License at
7	#
8	# http://www.apache.org/licenses/LICENSE-2.0
9	#
10	# Unless required by applicable law or agreed to in writing, software
11	# distributed under the License is distributed on an "AS IS" BASIS,
12	# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13	# See the License for the specific language governing permissions and
14	# limitations under the License.
15	from typing import Iterator	1✔
16
17	import pandas as pd	1✔
18
19	from eva.catalog.catalog_manager import CatalogManager	1✔
20	from eva.catalog.catalog_type import TableType	1✔
21	from eva.executor.abstract_executor import AbstractExecutor	1✔
22	from eva.executor.executor_utils import apply_predicate	1✔
23	from eva.models.storage.batch import Batch	1✔
24	from eva.plan_nodes.project_plan import ProjectPlan	1✔
25	from eva.storage.storage_engine import StorageEngine	1✔
26
27
28	class DeleteExecutor(AbstractExecutor):	1✔
29	""" """
30
31	def __init__(self, node: ProjectPlan):	1✔
32	super().__init__(node)	1✔
33	self.predicate = node.where_clause	1✔
34	self.catalog = CatalogManager()	1✔
35
36	def exec(self, args, *kwargs) -> Iterator[Batch]:	1✔
37	table_catalog = self.node.table_ref.table.table_obj	×
38	storage_engine = StorageEngine.factory(table_catalog)	×
39	del_batch = Batch()	×
40
41	assert (	×
42	table_catalog.table_type == TableType.STRUCTURED_DATA
43	), "DELETE only implemented for structured data"
44
45	del_batch = storage_engine.read(table_catalog)	×
46	del_batch = list(del_batch)[0]	×
47
48	# Added because of inconsistency in col_alias
49	# in structured data Batch project function
50	original_column_names = list(del_batch.frames.columns)	×
51	column_names = [	×
52	f"{table_catalog.name.lower()}.{name}"
53	for name in original_column_names
54	if not name == "_row_id"
55	]
56	column_names.insert(0, "_row_id")	×
57	del_batch.frames.columns = column_names	×
58	del_batch = apply_predicate(del_batch, self.predicate)	×
59
60	# All the batches that need to be deleted
61	del_batch.frames.columns = original_column_names	×
62	table_needed = del_batch.frames[[f"{self.predicate.children[0].col_name}"]]	×
63	for num in range(len(del_batch)):	×
64	storage_engine.delete(table_catalog, table_needed.iloc[num])	×
65
66	yield Batch(pd.DataFrame(["Deleted row"]))	×

georgia-tech-db / eva / #725

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous