#758

Committed 04 Sep 2023 08:37PM UTC coverage: 0.0% (-78.3%) from 78.333%

Build # #758

Build Type

push

circle-ci

Committed by

hershd23

Commit Message

Increased underline length in at line 75 in text_summarization.rst
	modified:   docs/source/benchmarks/text_summarization.rst

Run Details

0 of 11303 relevant lines covered (0.0%)

0.0 hits per line

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

0.0

/evadb/storage/pdf_storage_engine.py

# coding=utf-8
# Copyright 2018-2023 EvaDB
#
# 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 pathlib import Path
from typing import Iterator

from evadb.catalog.models.table_catalog import TableCatalogEntry
from evadb.database import EvaDBDatabase
from evadb.models.storage.batch import Batch
from evadb.readers.pdf_reader import PDFReader
from evadb.storage.abstract_media_storage_engine import AbstractMediaStorageEngine


class PDFStorageEngine(AbstractMediaStorageEngine):
    def __init__(self, db: EvaDBDatabase):
        super().__init__(db)

    def read(self, table: TableCatalogEntry) -> Iterator[Batch]:
        for image_files in self._rdb_handler.read(self._get_metadata_table(table), 12):
            for _, (row_id, file_name) in image_files.iterrows():
                system_file_name = self._xform_file_url_to_file_name(file_name)
                image_file = Path(table.file_url) / system_file_name
                # setting batch_mem_size = 1, we need fix it
                reader = PDFReader(str(image_file), batch_mem_size=1)
                for batch in reader.read():
                    batch.frames[table.columns[0].name] = row_id
                    batch.frames[table.columns[1].name] = str(file_name)
                    yield batch

1	# coding=utf-8
2	# Copyright 2018-2023 EvaDB
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 pathlib import Path	×
16	from typing import Iterator	×
17
18	from evadb.catalog.models.table_catalog import TableCatalogEntry	×
19	from evadb.database import EvaDBDatabase	×
20	from evadb.models.storage.batch import Batch	×
21	from evadb.readers.pdf_reader import PDFReader	×
22	from evadb.storage.abstract_media_storage_engine import AbstractMediaStorageEngine	×
23
24
25	class PDFStorageEngine(AbstractMediaStorageEngine):	×
26	def __init__(self, db: EvaDBDatabase):	×
27	super().__init__(db)	×
28
29	def read(self, table: TableCatalogEntry) -> Iterator[Batch]:	×
30	for image_files in self._rdb_handler.read(self._get_metadata_table(table), 12):	×
31	for _, (row_id, file_name) in image_files.iterrows():	×
32	system_file_name = self._xform_file_url_to_file_name(file_name)	×
33	image_file = Path(table.file_url) / system_file_name	×
34	# setting batch_mem_size = 1, we need fix it
35	reader = PDFReader(str(image_file), batch_mem_size=1)	×
36	for batch in reader.read():	×
37	batch.frames[table.columns[0].name] = row_id	×
38	batch.frames[table.columns[1].name] = str(file_name)	×
39	yield batch	×

georgia-tech-db / eva / #758

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