17d27eeb-d1e1-4c3b-a59c-b789a33e18ef

Build # 17d27eeb-d1e1-4c3b-a59c-b789a33e18ef

Build Type

circle-ci

Committed by jarulraj

Commit Message

checkpoint

Pull Request Pull Request #587: feat: Delete and Insert operators for structured data

Run Details

227 of 227 new or added lines in 22 files covered. (100.0%)

8477 of 9086 relevant lines covered (93.3%)

0.93 hits per line

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

81.63

/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 Generator, 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 ExecutorError, apply_predicate
from eva.models.storage.batch import Batch
from eva.plan_nodes.project_plan import ProjectPlan
from eva.storage.storage_engine import StorageEngine
from eva.utils.logging_manager import logger


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

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

    def validate(self):
        pass

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

            del_batch = Batch()

            if table_catalog.table_type == TableType.VIDEO_DATA:
                raise NotImplementedError("DELETE only implemented for structured data")
            elif table_catalog.table_type == TableType.IMAGE_DATA:
                raise NotImplementedError("DELETE only implemented for structured data")
            elif table_catalog.table_type == TableType.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

            if table_catalog.table_type == TableType.VIDEO_DATA:
                storage_engine.delete(table_catalog, del_batch)
            elif table_catalog.table_type == TableType.IMAGE_DATA:
                storage_engine.delete(table_catalog, del_batch)
            elif table_catalog.table_type == TableType.STRUCTURED_DATA:
                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"]))

        except Exception as e:
            logger.error(e)
            raise ExecutorError(e)

    def __call__(self, **kwargs) -> Generator[Batch, None, None]:
        yield from self.exec(**kwargs)

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 Generator, 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 ExecutorError, 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	from eva.utils.logging_manager import logger	1✔
27
28
29	class DeleteExecutor(AbstractExecutor):	1✔
30	""" """
31
32	def __init__(self, node: ProjectPlan):	1✔
33	super().__init__(node)	1✔
34	self.predicate = node.where_clause	1✔
35	self.catalog = CatalogManager()	1✔
36
37	def validate(self):	1✔
38	pass	×
39
40	def exec(self, **kwargs) -> Iterator[Batch]:	1✔
41	try:	1✔
42	table_catalog = self.node.table_ref.table.table_obj	1✔
43	storage_engine = StorageEngine.factory(table_catalog)	1✔
44
45	del_batch = Batch()	1✔
46
47	if table_catalog.table_type == TableType.VIDEO_DATA:	1✔
48	raise NotImplementedError("DELETE only implemented for structured data")	×
49	elif table_catalog.table_type == TableType.IMAGE_DATA:	1✔
50	raise NotImplementedError("DELETE only implemented for structured data")	×
51	elif table_catalog.table_type == TableType.STRUCTURED_DATA:	1✔
52	del_batch = storage_engine.read(table_catalog)	1✔
53	del_batch = list(del_batch)[0]	1✔
54
55	# Added because of inconsistency in col_alias in Structured data Batch project function
56	original_column_names = list(del_batch.frames.columns)	1✔
57	column_names = [	1✔
58	f"{table_catalog.name.lower()}.{name}"
59	for name in original_column_names
60	if not name == "_row_id"
61	]
62	column_names.insert(0, "_row_id")	1✔
63	del_batch.frames.columns = column_names	1✔
64	del_batch = apply_predicate(del_batch, self.predicate)	1✔
65
66	# All the batches that need to be deleted
67
68	if table_catalog.table_type == TableType.VIDEO_DATA:	1✔
69	storage_engine.delete(table_catalog, del_batch)	×
70	elif table_catalog.table_type == TableType.IMAGE_DATA:	1✔
71	storage_engine.delete(table_catalog, del_batch)	×
72	elif table_catalog.table_type == TableType.STRUCTURED_DATA:	1✔
73	del_batch.frames.columns = original_column_names	1✔
74	table_needed = del_batch.frames[	1✔
75	[f"{self.predicate.children[0].col_name}"]
76	]
77	for num in range(len(del_batch)):	1✔
78	storage_engine.delete(table_catalog, table_needed.iloc[num])	1✔
79	yield Batch(pd.DataFrame(["Deleted row"]))	1✔
80
81	except Exception as e:	×
82	logger.error(e)	×
83	raise ExecutorError(e)	×
84
85	def __call__(self, **kwargs) -> Generator[Batch, None, None]:	1✔
86	yield from self.exec(**kwargs)	×

georgia-tech-db / eva / 17d27eeb-d1e1-4c3b-a59c-b789a33e18ef

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