collate-data-diff 0.11.2__tar.gz

collate_data_diff-0.11.2/LICENSE

@@ -0,0 +1,18 @@
+Copyright 2022 DataFold Inc.
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of
+this software and associated documentation files (the "Software"), to deal in
+the Software without restriction, including without limitation the rights to
+use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of
+the Software, and to permit persons to whom the Software is furnished to do so,
+subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS
+FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR
+COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER
+IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

collate_data_diff-0.11.2/PKG-INFO

@@ -0,0 +1,77 @@
+Metadata-Version: 2.1
+Name: collate-data-diff
+Version: 0.11.2
+Summary: Command-line tool and Python library to efficiently diff rows across two different databases.
+Home-page: https://github.com/open-metadata/collate-data-diff
+License: MIT
+Author: Collate
+Requires-Python: >=3.8.0,<4.0
+Classifier: Development Status :: 2 - Pre-Alpha
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Information Technology
+Classifier: Intended Audience :: System Administrators
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Database :: Database Engines/Servers
+Classifier: Typing :: Typed
+Provides-Extra: all-dbs
+Provides-Extra: clickhouse
+Provides-Extra: duckdb
+Provides-Extra: mssql
+Provides-Extra: mysql
+Provides-Extra: oracle
+Provides-Extra: postgresql
+Provides-Extra: preql
+Provides-Extra: presto
+Provides-Extra: redshift
+Provides-Extra: snowflake
+Provides-Extra: trino
+Provides-Extra: vertica
+Requires-Dist: attrs (>=23.1.0)
+Requires-Dist: click (>=8.1)
+Requires-Dist: clickhouse-driver ; extra == "clickhouse" or extra == "all-dbs"
+Requires-Dist: cryptography ; extra == "snowflake" or extra == "all-dbs"
+Requires-Dist: dbt-core (>=1.0.0,<2.0.0)
+Requires-Dist: dsnparse (<0.2.0)
+Requires-Dist: duckdb ; extra == "duckdb" or extra == "all-dbs"
+Requires-Dist: keyring
+Requires-Dist: mashumaro[msgpack] (>=2.9,<3.11.0)
+Requires-Dist: mysql-connector-python (>=8.0.29) ; extra == "mysql" or extra == "all-dbs"
+Requires-Dist: oracledb ; extra == "oracle" or extra == "all-dbs"
+Requires-Dist: preql (>=0.2.19) ; extra == "preql" or extra == "all-dbs"
+Requires-Dist: presto-python-client ; extra == "presto" or extra == "all-dbs"
+Requires-Dist: psycopg2 ; extra == "postgresql" or extra == "redshift" or extra == "all-dbs"
+Requires-Dist: pydantic (>=1.10.12)
+Requires-Dist: pyodbc (>=4.0.39) ; extra == "mssql" or extra == "all-dbs"
+Requires-Dist: rich
+Requires-Dist: snowflake-connector-python (>=3.0.2,<4.0.0) ; extra == "snowflake" or extra == "all-dbs"
+Requires-Dist: tabulate (>=0.9.0)
+Requires-Dist: toml (>=0.10.2)
+Requires-Dist: trino (>=0.314.0) ; extra == "trino" or extra == "all-dbs"
+Requires-Dist: typing-extensions (>=4.0.1)
+Requires-Dist: urllib3 (<2)
+Requires-Dist: vertica-python ; extra == "vertica" or extra == "all-dbs"
+Project-URL: Repository, https://github.com/open-metadata/collate-data-diff
+Description-Content-Type: text/markdown
+
+Forked from the archived repository [datafold/data-diff](https://github.com/datafold/data-diff)
+---
+
+# data-diff: Compare datasets fast, within or across SQL databases
+
+## Contributors
+
+<a href="https://github.com/datafold/data-diff/graphs/contributors">
+  <img src="https://contributors-img.web.app/image?repo=datafold/data-diff" />
+</a>
+
+## License
+
+This project is licensed under the terms of the [MIT License](https://github.com/datafold/data-diff/blob/master/LICENSE).
+

collate_data_diff-0.11.2/README.md

@@ -0,0 +1,14 @@
+Forked from the archived repository [datafold/data-diff](https://github.com/datafold/data-diff)
+---
+
+# data-diff: Compare datasets fast, within or across SQL databases
+
+## Contributors
+
+<a href="https://github.com/datafold/data-diff/graphs/contributors">
+  <img src="https://contributors-img.web.app/image?repo=datafold/data-diff" />
+</a>
+
+## License
+
+This project is licensed under the terms of the [MIT License](https://github.com/datafold/data-diff/blob/master/LICENSE).

collate_data_diff-0.11.2/data_diff/__init__.py

@@ -0,0 +1,180 @@
+from typing import Sequence, Tuple, Iterator, Optional, Union
+
+from data_diff.abcs.database_types import DbTime, DbPath
+from data_diff.databases import Database
+from data_diff.tracking import disable_tracking
+from data_diff.databases._connect import connect
+from data_diff.diff_tables import Algorithm
+from data_diff.hashdiff_tables import HashDiffer, DEFAULT_BISECTION_THRESHOLD, DEFAULT_BISECTION_FACTOR
+from data_diff.joindiff_tables import JoinDiffer, TABLE_WRITE_LIMIT
+from data_diff.table_segment import TableSegment
+from data_diff.utils import eval_name_template, Vector
+
+
+def connect_to_table(
+    db_info: Union[str, dict],
+    table_name: Union[DbPath, str],
+    key_columns: str = ("id",),
+    thread_count: Optional[int] = 1,
+    **kwargs,
+) -> TableSegment:
+    """Connects to the given database, and creates a TableSegment instance
+
+    Parameters:
+        db_info: Either a URI string, or a dict of connection options.
+        table_name: Name of the table as a string, or a tuple that signifies the path.
+        key_columns: Names of the key columns
+        thread_count: Number of threads for this connection (only if using a threadpooled db implementation)
+
+    See Also:
+        :meth:`connect`
+    """
+    if isinstance(key_columns, str):
+        key_columns = (key_columns,)
+
+    db: Database = connect(db_info, thread_count=thread_count)
+
+    if isinstance(table_name, str):
+        table_name = db.dialect.parse_table_name(table_name)
+
+    return TableSegment(db, table_name, key_columns, **kwargs)
+
+
+def diff_tables(
+    table1: TableSegment,
+    table2: TableSegment,
+    *,
+    # Name of the key column, which uniquely identifies each row (usually id)
+    key_columns: Sequence[str] = None,
+    # Name of updated column, which signals that rows changed (usually updated_at or last_update)
+    update_column: str = None,
+    # Extra columns to compare
+    extra_columns: Tuple[str, ...] = None,
+    # Start/end key_column values, used to restrict the segment
+    min_key: Vector = None,
+    max_key: Vector = None,
+    # Start/end update_column values, used to restrict the segment
+    min_update: DbTime = None,
+    max_update: DbTime = None,
+    # Enable/disable threaded diffing. Needed to take advantage of database threads.
+    threaded: bool = True,
+    # Maximum size of each threadpool. None = auto. Only relevant when threaded is True.
+    # There may be many pools, so number of actual threads can be a lot higher.
+    max_threadpool_size: Optional[int] = 1,
+    # Algorithm
+    algorithm: Algorithm = Algorithm.AUTO,
+    # An additional 'where' expression to restrict the search space.
+    where: str = None,
+    # Into how many segments to bisect per iteration (hashdiff only)
+    bisection_factor: int = DEFAULT_BISECTION_FACTOR,
+    # When should we stop bisecting and compare locally (in row count; hashdiff only)
+    bisection_threshold: int = DEFAULT_BISECTION_THRESHOLD,
+    # Enable/disable validating that the key columns are unique. (joindiff only)
+    validate_unique_key: bool = True,
+    # Enable/disable sampling of exclusive rows. Creates a temporary table. (joindiff only)
+    sample_exclusive_rows: bool = False,
+    # Path of new table to write diff results to. Disabled if not provided. (joindiff only)
+    materialize_to_table: Union[str, DbPath] = None,
+    # Materialize every row, not just those that are different. (joindiff only)
+    materialize_all_rows: bool = False,
+    # Maximum number of rows to write when materializing, per thread. (joindiff only)
+    table_write_limit: int = TABLE_WRITE_LIMIT,
+    # Skips diffing any rows with null keys. (joindiff only)
+    skip_null_keys: bool = False,
+) -> Iterator:
+    """Finds the diff between table1 and table2.
+
+    Parameters:
+        key_columns (Tuple[str, ...]): Name of the key column, which uniquely identifies each row (usually id)
+        update_column (str, optional): Name of updated column, which signals that rows changed.
+                                       Usually updated_at or last_update.  Used by `min_update` and `max_update`.
+        extra_columns (Tuple[str, ...], optional): Extra columns to compare
+        min_key (:data:`Vector`, optional): Lowest key value, used to restrict the segment
+        max_key (:data:`Vector`, optional): Highest key value, used to restrict the segment
+        min_update (:data:`DbTime`, optional): Lowest update_column value, used to restrict the segment
+        max_update (:data:`DbTime`, optional): Highest update_column value, used to restrict the segment
+        threaded (bool): Enable/disable threaded diffing. Needed to take advantage of database threads.
+        max_threadpool_size (int): Maximum size of each threadpool. ``None`` means auto.
+                                   Only relevant when `threaded` is ``True``.
+                                   There may be many pools, so number of actual threads can be a lot higher.
+        where (str, optional): An additional 'where' expression to restrict the search space.
+        algorithm (:class:`Algorithm`): Which diffing algorithm to use (`HASHDIFF` or `JOINDIFF`. Default=`AUTO`)
+        bisection_factor (int): Into how many segments to bisect per iteration. (Used when algorithm is `HASHDIFF`)
+        bisection_threshold (Number): Minimal row count of segment to bisect, otherwise download
+                                      and compare locally. (Used when algorithm is `HASHDIFF`).
+        validate_unique_key (bool): Enable/disable validating that the key columns are unique. (used for `JOINDIFF`. default: True)
+                                    Single query, and can't be threaded, so it's very slow on non-cloud dbs.
+                                    Future versions will detect UNIQUE constraints in the schema.
+        sample_exclusive_rows (bool): Enable/disable sampling of exclusive rows. Creates a temporary table. (used for `JOINDIFF`. default: False)
+        materialize_to_table (Union[str, DbPath], optional): Path of new table to write diff results to. Disabled if not provided. Used for `JOINDIFF`.
+        materialize_all_rows (bool): Materialize every row, not just those that are different. (used for `JOINDIFF`. default: False)
+        table_write_limit (int): Maximum number of rows to write when materializing, per thread.
+        skip_null_keys (bool): Skips diffing any rows with null PKs (displays a warning if any are null) (used for `JOINDIFF`. default: False)
+
+    Note:
+        The following parameters are used to override the corresponding attributes of the given :class:`TableSegment` instances:
+        `key_columns`, `update_column`, `extra_columns`, `min_key`, `max_key`, `where`.
+        If different values are needed per table, it's possible to omit them here, and instead set
+        them directly when creating each :class:`TableSegment`.
+
+    Example:
+        >>> table1 = connect_to_table('postgresql:///', 'Rating', 'id')
+        >>> list(diff_tables(table1, table1))
+        []
+
+    See Also:
+        :class:`TableSegment`
+        :class:`HashDiffer`
+        :class:`JoinDiffer`
+
+    """
+    if isinstance(key_columns, str):
+        key_columns = (key_columns,)
+
+    tables = [table1, table2]
+    override_attrs = {
+        k: v
+        for k, v in dict(
+            key_columns=key_columns,
+            update_column=update_column,
+            extra_columns=extra_columns,
+            min_key=min_key,
+            max_key=max_key,
+            min_update=min_update,
+            max_update=max_update,
+            where=where,
+        ).items()
+        if v is not None
+    }
+
+    segments = [t.new(**override_attrs) for t in tables] if override_attrs else tables
+
+    algorithm = Algorithm(algorithm)
+    if algorithm == Algorithm.AUTO:
+        algorithm = Algorithm.JOINDIFF if table1.database is table2.database else Algorithm.HASHDIFF
+
+    if algorithm == Algorithm.HASHDIFF:
+        differ = HashDiffer(
+            bisection_factor=bisection_factor,
+            bisection_threshold=bisection_threshold,
+            threaded=threaded,
+            max_threadpool_size=max_threadpool_size,
+        )
+    elif algorithm == Algorithm.JOINDIFF:
+        if isinstance(materialize_to_table, str):
+            table_name = eval_name_template(materialize_to_table)
+            materialize_to_table = table1.database.dialect.parse_table_name(table_name)
+        differ = JoinDiffer(
+            threaded=threaded,
+            max_threadpool_size=max_threadpool_size,
+            validate_unique_key=validate_unique_key,
+            sample_exclusive_rows=sample_exclusive_rows,
+            materialize_to_table=materialize_to_table,
+            materialize_all_rows=materialize_all_rows,
+            table_write_limit=table_write_limit,
+            skip_null_keys=skip_null_keys,
+        )
+    else:
+        raise ValueError(f"Unknown algorithm: {algorithm}")
+
+    return differ.diff_tables(*segments)