#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

39.39

/eva/executor/insert_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.
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.models.storage.batch import Batch
from eva.plan_nodes.insert_plan import InsertPlan
from eva.storage.storage_engine import StorageEngine
from eva.utils.logging_manager import logger


class InsertExecutor(AbstractExecutor):
    def __init__(self, node: InsertPlan):
        super().__init__(node)
        self.catalog = CatalogManager()

    def exec(self, *args, **kwargs):
        storage_engine = None
        table_catalog_entry = None

        # Get catalog entry
        table_name = self.node.table_ref.table.table_name
        database_name = self.node.table_ref.table.database_name
        table_catalog_entry = self.catalog.get_table_catalog_entry(
            table_name, database_name
        )

        # Implemented only for STRUCTURED_DATA
        assert (
            table_catalog_entry.table_type == TableType.STRUCTURED_DATA
        ), "INSERT only implemented for structured data"

        values_to_insert = []
        for i in self.node.value_list:
            values_to_insert.append(i.value)
        tuple_to_insert = tuple(values_to_insert)
        columns_to_insert = []
        for i in self.node.column_list:
            columns_to_insert.append(i.col_name)

        # Adding all values to Batch for insert
        logger.info(values_to_insert)
        logger.info(columns_to_insert)
        dataframe = pd.DataFrame([tuple_to_insert], columns=columns_to_insert)
        batch = Batch(dataframe)

        storage_engine = StorageEngine.factory(table_catalog_entry)
        storage_engine.write(table_catalog_entry, batch)

        yield Batch(
            pd.DataFrame([f"Number of rows loaded: {str(len(values_to_insert))}"])
        )

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	import pandas as pd	1✔
16
17	from eva.catalog.catalog_manager import CatalogManager	1✔
18	from eva.catalog.catalog_type import TableType	1✔
19	from eva.executor.abstract_executor import AbstractExecutor	1✔
20	from eva.models.storage.batch import Batch	1✔
21	from eva.plan_nodes.insert_plan import InsertPlan	1✔
22	from eva.storage.storage_engine import StorageEngine	1✔
23	from eva.utils.logging_manager import logger	1✔
24
25
26	class InsertExecutor(AbstractExecutor):	1✔
27	def __init__(self, node: InsertPlan):	1✔
28	super().__init__(node)	1✔
29	self.catalog = CatalogManager()	1✔
30
31	def exec(self, args, *kwargs):	1✔
32	storage_engine = None	×
33	table_catalog_entry = None	×
34
35	# Get catalog entry
36	table_name = self.node.table_ref.table.table_name	×
37	database_name = self.node.table_ref.table.database_name	×
38	table_catalog_entry = self.catalog.get_table_catalog_entry(	×
39	table_name, database_name
40	)
41
42	# Implemented only for STRUCTURED_DATA
43	assert (	×
44	table_catalog_entry.table_type == TableType.STRUCTURED_DATA
45	), "INSERT only implemented for structured data"
46
47	values_to_insert = []	×
48	for i in self.node.value_list:	×
49	values_to_insert.append(i.value)	×
50	tuple_to_insert = tuple(values_to_insert)	×
51	columns_to_insert = []	×
52	for i in self.node.column_list:	×
53	columns_to_insert.append(i.col_name)	×
54
55	# Adding all values to Batch for insert
56	logger.info(values_to_insert)	×
57	logger.info(columns_to_insert)	×
58	dataframe = pd.DataFrame([tuple_to_insert], columns=columns_to_insert)	×
59	batch = Batch(dataframe)	×
60
61	storage_engine = StorageEngine.factory(table_catalog_entry)	×
62	storage_engine.write(table_catalog_entry, batch)	×
63
64	yield Batch(	×
65	pd.DataFrame([f"Number of rows loaded: {str(len(values_to_insert))}"])
66	)

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