mkpipe-extractor-sqlserver 0.1.0__py3-none-any.whl

mkpipe_extractor_sqlserver/__init__.py

@@ -0,0 +1,436 @@
+import os
+import datetime
+from pathlib import Path
+from urllib.parse import quote_plus
+from pyspark.sql import SparkSession
+from pyspark import SparkConf
+import pyspark.sql.functions as F
+
+from mkpipe.config import load_config
+from mkpipe.utils import log_container, Logger
+from mkpipe.functions_db import get_db_connector
+from mkpipe.utils.base_class import PipeSettings
+from mkpipe.plugins.registry_jar import collect_jars
+
+
+class SqlserverExtractor:
+    def __init__(self, config, settings):
+        if isinstance(settings, dict):
+            self.settings = PipeSettings(**settings)
+        else:
+            self.settings = settings
+        self.connection_params = config['connection_params']
+        self.host = self.connection_params['host']
+        self.port = self.connection_params['port']
+        self.username = self.connection_params['user']
+        # self.password = quote_plus(str(self.connection_params['password']))
+        self.password = str(self.connection_params['password'])
+        self.database = self.connection_params['database']
+
+        self.driver_name = 'sqlserver'
+        self.driver_jdbc = 'com.microsoft.sqlserver.jdbc.SQLServerDriver'
+        self.settings.driver_name = self.driver_name
+        self.jdbc_url = f'jdbc:{self.driver_name}://{self.host}:{self.port};databaseName={self.database};user={self.username};password={self.password};encrypt=false;trustServerCertificate=false'
+
+        config = load_config()
+        connection_params = config['settings']['backend']
+        db_type = connection_params['database_type']
+        self.backend = get_db_connector(db_type)(connection_params)
+
+    def create_spark_session(self):
+        jars = collect_jars()
+        conf = SparkConf()
+        conf.setAppName(__file__)
+        conf.setMaster('local[*]')
+        conf.set('spark.driver.memory', self.settings.spark_driver_memory)
+        conf.set('spark.executor.memory', self.settings.spark_executor_memory)
+        conf.set('spark.jars', jars)
+        conf.set('spark.driver.extraClassPath', jars)
+        conf.set('spark.executor.extraClassPath', jars)
+        conf.set('spark.network.timeout', '600s')
+        conf.set('spark.sql.parquet.datetimeRebaseModeInRead', 'CORRECTED')
+        conf.set('spark.sql.parquet.datetimeRebaseModeInWrite', 'CORRECTED')
+        conf.set('spark.sql.parquet.int96RebaseModeInRead', 'CORRECTED')
+        conf.set('spark.sql.parquet.int96RebaseModeInWrite', 'CORRECTED')
+        conf.set('spark.sql.session.timeZone', self.settings.timezone)
+        conf.set(
+            'spark.driver.extraJavaOptions', f'-Duser.timezone={self.settings.timezone}'
+        )
+        conf.set(
+            'spark.executor.extraJavaOptions',
+            f'-Duser.timezone={self.settings.timezone}',
+        )
+        conf.set(
+            'spark.driver.extraJavaOptions',
+            '-XX:ErrorFile=/tmp/java_error%p.log -XX:HeapDumpPath=/tmp',
+        )
+
+        return SparkSession.builder.config(conf=conf).getOrCreate()
+
+    def extract_incremental(self, t):
+        logger = Logger(__file__)
+        spark = self.create_spark_session()
+
+        try:
+            name = t['name']
+            target_name = t['target_name']
+            iterate_column_type = t['iterate_column_type']
+            iterate_batch_size = t.get(
+                'iterate_batch_size', self.settings.default_iterate_batch_size
+            )
+            iterate_max_loop = t.get(
+                'iterate_max_loop', self.settings.default_iterate_max_loop
+            )
+            custom_query = t.get('custom_query', None)
+            custom_query_file = t.get('custom_query_file', None)
+            if custom_query_file:
+                custom_query_file_path = os.path.abspath(
+                    os.path.join(self.settings.ROOT_DIR, 'sql', custom_query_file)
+                )
+                with open(custom_query_file_path, 'r') as f:
+                    custom_query = f.read()
+
+            custom_partition_count = t.get(
+                'partition_count', self.settings.partitions_count
+            )
+            partitions_column_ = t.get('partitions_column')
+            fetchsize = t.get('fetchsize', 100_000)
+
+            partitions_column = partitions_column_.split(' as ')[0].strip()
+            p_col_name = partitions_column_.split(' as ')[-1].strip()
+            p_col_select = f'{partitions_column} as {p_col_name}'
+
+            message = dict(table_name=target_name, status='extracting')
+            logger.info(message)
+            parquet_path = os.path.abspath(
+                os.path.join(self.settings.ROOT_DIR, 'artifacts', target_name)
+            )
+
+            last_point = self.backend.get_last_point(target_name)
+            if last_point:
+                write_mode = 'append'
+
+                iterate_query = f"""(SELECT {p_col_select} from {name} where {partitions_column} > '{last_point}' ) q"""
+
+                df_itarate_list = (
+                    spark.read.format('jdbc')
+                    .option('url', self.jdbc_url)
+                    .option('dbtable', iterate_query)
+                    .option('driver', self.driver_jdbc)
+                    .option('fetchsize', fetchsize)
+                    .load()
+                )
+
+                min_val = last_point
+                max_val = df_itarate_list.agg(F.max(p_col_name).alias('max')).collect()[
+                    0
+                ][0]
+                df_itarate_list = df_itarate_list.where(F.col(p_col_name) > min_val)
+            else:
+                write_mode = 'overwrite'
+
+                iterate_query = f'(SELECT {p_col_select} from {name}) q'
+                df_itarate_list = (
+                    spark.read.format('jdbc')
+                    .option('url', self.jdbc_url)
+                    .option('dbtable', iterate_query)
+                    .option('driver', self.driver_jdbc)
+                    .option('fetchsize', fetchsize)
+                    .load()
+                )
+
+                min_max_vals = df_itarate_list.agg(
+                    F.min(p_col_name).alias('min'), F.max(p_col_name).alias('max')
+                ).collect()[0]
+                min_val = min_max_vals[0]
+                max_val = min_max_vals[1]
+                df_itarate_list = df_itarate_list.where(F.col(p_col_name) >= min_val)
+
+            key_list = (
+                df_itarate_list.select(p_col_name)
+                .distinct()
+                .rdd.flatMap(lambda x: x)
+                .collect()
+            )
+            key_list.sort()
+
+            chunks = [
+                key_list[x : x + iterate_batch_size]
+                for x in range(0, len(key_list), iterate_batch_size)
+            ]
+
+            min_max_tuple = [(min(x), max(x)) for x in chunks]
+
+            if not min_max_tuple:
+                if not last_point:
+                    # Empty table, need schema fetc
+                    return self.extract_full(t)
+                else:
+                    # Not empt, but no new data, all fetched before
+                    data = {
+                        'table_name': target_name,
+                        'status': 'extracted',
+                        'replication_method': 'incremental',
+                    }
+                    return data
+
+            data = {
+                'table_name': target_name,
+                'write_mode': write_mode,
+                'file_type': 'parquet',
+                'partition_count': custom_partition_count,
+                'fetchsize': fetchsize,
+                'last_point_value': None,  # Initialize as None or the starting value
+                'iterate_column_type': iterate_column_type,
+                'loop': None,  # This will be updated each loop
+                'path': parquet_path,
+                'number_of_columns': None,
+                'number_of_rows': 0,  # Start with 0 and add to it in each loop
+                'pass_on_error': self.pass_on_error,
+                'status': 'extracted',
+                'replication_method': 'incremental',
+            }
+
+            for index, chunk in enumerate(min_max_tuple):
+                if iterate_max_loop == index:
+                    break
+
+                if index == 0:
+                    p_write_mode = 'overwrite'
+                else:
+                    p_write_mode = 'append'
+
+                if iterate_column_type == 'int':
+                    min_filter = int(chunk[0])
+                    max_filter = int(chunk[-1])
+                    if custom_query:
+                        updated_query = custom_query.replace(
+                            '{query_filter}',
+                            f""" where {partitions_column} between {min_filter} and {max_filter} """,
+                        )
+                    else:
+                        updated_query = f'(SELECT * from {name} where  {partitions_column} between {min_filter} and {max_filter}) q'
+                else:
+                    min_filter = str(chunk[0])
+                    max_filter = str(chunk[-1])
+                    if custom_query:
+                        updated_query = custom_query.replace(
+                            '{query_filter}',
+                            f""" where {partitions_column} between '{min_filter}' and '{max_filter}' """,
+                        )
+                    else:
+                        updated_query = f"""(SELECT * from {name} where  {partitions_column} between '{min_filter}' and '{max_filter}') q"""
+
+                df = (
+                    spark.read.format('jdbc')
+                    .option('url', self.jdbc_url)
+                    .option('dbtable', updated_query)
+                    .option('driver', self.driver_jdbc)
+                    .option('numPartitions', custom_partition_count)
+                    .option('partitionColumn', p_col_name)
+                    .option('lowerBound', min_val)
+                    .option('upperBound', max_val)
+                    .option('fetchsize', fetchsize)
+                    .load()
+                )
+
+                # df.filter(df.cust_ord_id == 285708).select("udate").show(truncate=False)
+                # df = df.dropDuplicates() # this process affecting the partition_count be careful
+                (
+                    df.write.option('compression', self.settings.compression_codec)
+                    .mode(p_write_mode)
+                    .parquet(parquet_path)
+                )
+                count_col = len(df.columns)
+                count_row = df.count()
+                last_point_value = max_filter
+
+                # Update `data` for this iteration
+                data['last_point_value'] = last_point_value  # update with the new max
+                data['loop'] = index  # update loop index
+                data['number_of_columns'] = count_col
+                data['number_of_rows'] += (
+                    count_row  # add current loop's row count to the cumulative total
+                )
+
+                message = dict(
+                    table_name=target_name,
+                    status='iterrated',
+                    meta_data=data,
+                )
+                logger.info(message)
+            logger.info(data)
+            return data
+        finally:
+            # Ensure Spark session is closed
+            spark.stop()
+
+    def extract_full(self, t):
+        logger = Logger(__file__)
+        spark = self.create_spark_session()
+        try:
+            name = t['name']
+            target_name = t['target_name']
+            message = dict(table_name=target_name, status='extracting')
+            logger.info(message)
+            custom_partition_count = t.get(
+                'partition_count', self.settings.partitions_count
+            )
+            fetchsize = t.get('fetchsize', 100_000)
+            partitions_column_ = t.get('partitions_column', None)
+
+            custom_query = t.get('custom_query', None)
+            custom_query_file = t.get('custom_query_file', None)
+            if custom_query_file:
+                custom_query_file_path = os.path.abspath(
+                    os.path.join(self.settings.ROOT_DIR, 'sql', custom_query_file)
+                )
+                with open(custom_query_file_path, 'r') as f:
+                    custom_query = f.read()
+
+            write_mode = 'overwrite'
+            parquet_path = os.path.abspath(
+                os.path.join(self.settings.ROOT_DIR, 'artifacts', target_name)
+            )
+
+            if not custom_query:
+                updated_query = f'(SELECT * from {name}) q'
+            else:
+                updated_query = custom_query.replace(
+                    '{query_filter}',
+                    ' where 1=1 ',
+                )
+
+            if partitions_column_:
+                partitions_column = partitions_column_.split(' as ')[0]
+                p_col_name = partitions_column_.split(' as ')[-1]
+                query_min_max = f'(SELECT min({partitions_column}), max({partitions_column}) from {name}) q'
+                df_min_max = (
+                    spark.read.format('jdbc')
+                    .option('url', self.jdbc_url)
+                    .option('dbtable', query_min_max)
+                    .option('driver', self.driver_jdbc)
+                    .option('fetchsize', fetchsize)
+                    .load()
+                )
+
+                min_val = df_min_max.first()['min']
+                max_val = df_min_max.first()['max']
+
+                if min_val:
+                    # which means table not empt
+                    df = (
+                        spark.read.format('jdbc')
+                        .option('url', self.jdbc_url)
+                        .option('dbtable', updated_query)
+                        .option('driver', self.driver_jdbc)
+                        .option('numPartitions', custom_partition_count)
+                        .option('partitionColumn', p_col_name)
+                        .option('lowerBound', min_val)
+                        .option('upperBound', max_val)
+                        .option('fetchsize', fetchsize)
+                        .load()
+                    )
+                else:
+                    # empty df, we need schema
+                    df = (
+                        spark.read.format('jdbc')
+                        .option('url', self.jdbc_url)
+                        .option('dbtable', updated_query)
+                        .option('driver', self.driver_jdbc)
+                        .option('fetchsize', fetchsize)
+                        .load()
+                    )
+
+            else:
+                df = (
+                    spark.read.format('jdbc')
+                    .option('url', self.jdbc_url)
+                    .option('dbtable', updated_query)
+                    .option('driver', self.driver_jdbc)
+                    .option('fetchsize', fetchsize)
+                    .load()
+                ).repartition(custom_partition_count)
+
+            df.write.parquet(parquet_path, mode=write_mode)
+
+            count_col = len(df.columns)
+            count_row = df.count()
+
+            data = {
+                'table_name': target_name,
+                'path': parquet_path,
+                'file_type': 'parquet',
+                'number_of_columns': count_col,
+                'number_of_rows': count_row,
+                'write_mode': write_mode,
+                'partition_count': custom_partition_count,
+                'fetchsize': fetchsize,
+                'pass_on_error': self.pass_on_error,
+                'replication_method': 'full',
+            }
+            message = dict(
+                table_name=target_name,
+                status='extracted',
+                meta_data=data,
+            )
+            logger.info(message)
+            return data
+        finally:
+            # Ensure Spark session is closed
+            spark.stop()
+
+    @log_container(__file__)
+    def extract(self):
+        extract_start_time = datetime.datetime.now()
+        logger = Logger(__file__)
+        logger.info({'message': 'Extracting data from SQLserver...'})
+        t = self.table
+        try:
+            target_name = t['target_name']
+            replication_method = t.get('replication_method', None)
+            if self.backend.get_table_status(target_name) in ['extracting', 'loading']:
+                logger.info(
+                    {'message': f'Skipping {target_name}, already in progress...'}
+                )
+                data = {
+                    'table_name': target_name,
+                    'status': 'completed',
+                    'replication_method': 'full',
+                }
+                return data
+
+            self.backend.manifest_table_update(
+                name=target_name,
+                value=None,  # Last point remains unchanged
+                value_type=None,  # Type remains unchanged
+                status='extracting',  # ('completed', 'failed', 'extracting', 'loading')
+                replication_method=replication_method,  # ('incremental', 'full')
+                error_message='',
+            )
+            if replication_method == 'incremental':
+                return self.extract_incremental(t)
+            else:
+                return self.extract_full(t)
+
+        except Exception as e:
+            message = dict(
+                table_name=target_name,
+                status='failed',
+                type='pipeline',
+                error_message=str(e),
+                etl_start_time=str(extract_start_time),
+            )
+            self.backend.manifest_table_update(
+                target_name,
+                None,
+                None,
+                status='failed',
+                replication_method=replication_method,
+                error_message=str(e),
+            )
+            if self.pass_on_error:
+                logger.warning(message)
+                return None
+            else:
+                raise Exception(message) from e

mkpipe_extractor_sqlserver-0.1.0.dist-info/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2023-2024 Metin Karakus
+
+   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.

mkpipe_extractor_sqlserver-0.1.0.dist-info/METADATA

@@ -0,0 +1,42 @@
+Metadata-Version: 2.1
+Name: mkpipe-extractor-sqlserver
+Version: 0.1.0
+Summary: SQLserver extractor for mkpipe.
+Author: Metin Karakus
+Author-email: metin_karakus@yahoo.com
+License: Apache License 2.0
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: Apache Software License
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: mkpipe
+
+# MkPipe
+
+**MkPipe** is a modular, open-source ETL (Extract, Transform, Load) tool that allows you to integrate various data sources and sinks easily. It is designed to be extensible with a plugin-based architecture that supports extractors, transformers, and loaders.  
+
+## Documentation
+
+For more detailed documentation, please visit the [GitHub repository](https://github.com/mkpipe-etl/mkpipe).
+
+## License
+
+This project is licensed under the Apache 2.0 License - see the [LICENSE](LICENSE) file for details.
+
+
+## mkpipe_project.yaml Variables
+```yaml
+...
+  connections:
+    source:
+      host: 'XXX'
+      port: 'XXX'
+      database: 'XXX'
+      user: 'XXX'
+      password: 'XXX'
+...
+```
+
+
+

mkpipe_extractor_sqlserver-0.1.0.dist-info/RECORD

@@ -0,0 +1,8 @@
+mkpipe_extractor_sqlserver/__init__.py,sha256=7m47U5O7-2zna15iTygyWMMFNAjmSpvmMaS5xQ3UKew,17838
+mkpipe_extractor_sqlserver/jars/com.microsoft.sqlserver_mssql-jdbc-12.8.1.jre11.jar,sha256=5pM8BxHlmKIkBg5S7TE5L3IKSnZk6F2K43xSqFtn67A,1476685
+mkpipe_extractor_sqlserver-0.1.0.dist-info/LICENSE,sha256=6G5XWHq2ng2Te_IpVeOKvDabtRBPwqaImM7vpke0HOE,11348
+mkpipe_extractor_sqlserver-0.1.0.dist-info/METADATA,sha256=nMoO_wTzZTwqJecWS8qciHuxh59onXBbswQhCoIfpBA,1114
+mkpipe_extractor_sqlserver-0.1.0.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
+mkpipe_extractor_sqlserver-0.1.0.dist-info/entry_points.txt,sha256=YWQKQYSCQl8IVRMiRhLNDIqgf13BuH-L0zKXKSbfpGg,78
+mkpipe_extractor_sqlserver-0.1.0.dist-info/top_level.txt,sha256=z3qdgAYGXAl11etde_yqlXRFJ5xzNl_1Jl-3dVdi0jY,27
+mkpipe_extractor_sqlserver-0.1.0.dist-info/RECORD,,

mkpipe_extractor_sqlserver-0.1.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (75.6.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

mkpipe_extractor_sqlserver-0.1.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[mkpipe.extractors]
+sqlserver = mkpipe_extractor_sqlserver:SqlserverExtractor

mkpipe_extractor_sqlserver-0.1.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+mkpipe_extractor_sqlserver