dcs-sdk 1.7.0__tar.gz

dcs_sdk-1.7.0/PKG-INFO

@@ -0,0 +1,144 @@
+Metadata-Version: 2.4
+Name: dcs-sdk
+Version: 1.7.0
+Summary: SDK for DataChecks
+Author: Waterdip Labs
+Author-email: hello@waterdip.ai
+Requires-Python: >=3.10,<3.13
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Provides-Extra: all-dbs
+Provides-Extra: bigquery
+Provides-Extra: clickhouse
+Provides-Extra: databricks
+Provides-Extra: db2
+Provides-Extra: elasticsearch
+Provides-Extra: impyla
+Provides-Extra: mssql
+Provides-Extra: mysql
+Provides-Extra: opensearch
+Provides-Extra: oracle
+Provides-Extra: postgresql
+Provides-Extra: preql
+Provides-Extra: presto
+Provides-Extra: redshift
+Provides-Extra: snowflake
+Provides-Extra: spark
+Provides-Extra: sybase
+Provides-Extra: trino
+Provides-Extra: vertica
+Requires-Dist: attrs (>=23.1.0)
+Requires-Dist: azure-identity (>=1.25.1,<2.0.0)
+Requires-Dist: azure-storage-blob (>=12.27.1,<13.0.0)
+Requires-Dist: click (>=8.1)
+Requires-Dist: clickhouse-driver (>=0.2.9) ; extra == "clickhouse" or extra == "all-dbs"
+Requires-Dist: cryptography (>=44.0.1) ; extra == "snowflake" or extra == "all-dbs"
+Requires-Dist: databricks-sql-connector (>=3.3.0,<4.0.0) ; extra == "databricks" or extra == "all-dbs"
+Requires-Dist: dsnparse (<0.2.0)
+Requires-Dist: duckdb (>=0.9.0)
+Requires-Dist: elasticsearch (>=9.1.0,<10.0.0) ; extra == "elasticsearch" or extra == "all-dbs"
+Requires-Dist: google-cloud-bigquery (>=3.31.0,<4.0.0) ; extra == "bigquery" or extra == "all-dbs"
+Requires-Dist: h11 (>=0.16.0,<0.17.0)
+Requires-Dist: ibm-db (>=3.2.3,<4.0.0) ; extra == "db2" or extra == "all-dbs"
+Requires-Dist: ibm-db-sa (>=0.4.1,<0.5.0) ; extra == "db2" or extra == "all-dbs"
+Requires-Dist: impyla (>=0.20.0,<0.21.0) ; extra == "impyla" or extra == "all-dbs"
+Requires-Dist: jinja2 (>=3.1.6,<4.0.0)
+Requires-Dist: keyring (>=25.3.0)
+Requires-Dist: loguru (==0.7.2)
+Requires-Dist: mashumaro[msgpack] (>=2.9,<3.11.0)
+Requires-Dist: mysql-connector-python (>=9.0.1) ; extra == "mysql" or extra == "all-dbs"
+Requires-Dist: nltk (>=3.9.1,<4.0.0)
+Requires-Dist: numpy (==1.26.4)
+Requires-Dist: opensearch-py (>=2.2.0,<3.0.0) ; extra == "opensearch" or extra == "all-dbs"
+Requires-Dist: oracledb (>=2.4.1) ; extra == "oracle" or extra == "all-dbs"
+Requires-Dist: packaging (>=24.1,<25.0)
+Requires-Dist: preql (>=0.2.19) ; extra == "preql" or extra == "all-dbs"
+Requires-Dist: presto-python-client (>=0.8.4) ; extra == "presto" or extra == "all-dbs"
+Requires-Dist: protobuf (>=5.29.5,<6.0.0)
+Requires-Dist: psycopg2-binary (>=2.9.9,<3.0.0) ; extra == "postgresql" or extra == "redshift" or extra == "all-dbs"
+Requires-Dist: pydantic (>=1.10.12)
+Requires-Dist: pymysql[rsa] (>=1.1.0,<2.0.0) ; extra == "mysql" or extra == "all-dbs"
+Requires-Dist: pyodbc (>=4.0.39) ; extra == "mssql" or extra == "sybase" or extra == "all-dbs"
+Requires-Dist: pyparsing (>=3.1.1,<4.0.0)
+Requires-Dist: pyspark (>=3.2.1,<4.0.0) ; extra == "spark" or extra == "all-dbs"
+Requires-Dist: python-dateutil (>=2.8.2,<3.0.0)
+Requires-Dist: python-dotenv (>=1.0.1,<2.0.0)
+Requires-Dist: pytz (>=2024.1)
+Requires-Dist: pyyaml (>=6.0.1,<7.0.0)
+Requires-Dist: redis[hiredis] (>=5.2.1,<6.0.0)
+Requires-Dist: requests (>=2.32.4,<3.0.0)
+Requires-Dist: rich (>=13.8.0)
+Requires-Dist: setuptools (>=78.1.1)
+Requires-Dist: snowflake-connector-python (>=3.17.2) ; extra == "snowflake" or extra == "all-dbs"
+Requires-Dist: snowflake-sqlalchemy (>=1.5.3,<2.0.0) ; extra == "snowflake" or extra == "all-dbs"
+Requires-Dist: sqlalchemy (>=2.0.14,<2.1.0)
+Requires-Dist: sqlalchemy-bigquery (>=1.8.0,<2.0.0) ; extra == "bigquery" or extra == "all-dbs"
+Requires-Dist: sqlalchemy-sybase (>=2.0.0,<3.0.0) ; extra == "sybase" or extra == "all-dbs"
+Requires-Dist: tabulate (>=0.9.0)
+Requires-Dist: toml (>=0.10.2)
+Requires-Dist: tornado (>=6.5,<7.0)
+Requires-Dist: trino (>=0.314.0) ; extra == "trino" or extra == "all-dbs"
+Requires-Dist: typing-extensions (>=4.0.1)
+Requires-Dist: urllib3 (>=2.5.0,<3.0.0)
+Requires-Dist: vertica-python (>=1.4.0) ; extra == "vertica" or extra == "all-dbs"
+Description-Content-Type: text/markdown
+
+<h1 align="center">
+  DCS SDK v1.7.0
+</h1>
+
+> SDK for DataChecks
+
+## Installation
+
+> Python version `>=3.10,<3.13`
+
+```bash
+
+$ pip install dcs-sdk[all-dbs]
+
+```
+
+## Supported Databases
+
+> Availability Status
+
+| Database          | Code Name    | Supported |
+| ----------------- | ------------ | --------- |
+| PostgreSQL        | `postgres`   | ✅        |
+| Snowflake         | `snowflake`  | ✅        |
+| Trino             | `trino`      | ✅        |
+| Databricks        | `databricks` | ✅        |
+| Oracle            | `oracle`     | ✅        |
+| MSSQL             | `mssql`      | ✅        |
+| MySQL             | `mysql`      | ✅        |
+| SAP Sybase IQ/ASE | `sybase`     | ✅        |
+| File              | `file`       | ✅        |
+| BigQuery          | `bigquery`   | ✅        |
+
+## Available Commands
+
+|    Option     | Short Option | Required |     Default     |                    Description                     |                                                 Example                                                  |
+| :-----------: | :----------: | :------: | :-------------: | :------------------------------------------------: | :------------------------------------------------------------------------------------------------------: |
+| --config-path |      -C      | **Yes**  |      None       |    Specify the file path for the configuration     |                        dcs-sdk run --config-path config.yaml --compare comp_name                         |
+|   --compare   |              | **Yes**  |      None       | Run only specific comparison using comparison name |                        dcs-sdk run --config-path config.yaml --compare comp_name                         |
+|  --save-json  |      -j      |    No    |      False      |           Save the data into a JSON file           |                  dcs-sdk run --config-path config.yaml --compare comp_name --save-json                   |
+|  --json-path  |     -jp      |    No    | dcs_report.json |        Specify the file path for JSON file         |       dcs-sdk run --config-path config.yaml --compare comp_name --save-json --json-path ouput.json       |
+|    --stats    |              |    No    |      False      |            Print stats about data diff             |                    dcs-sdk run --config-path config.yaml --compare comp_name --stats                     |
+|     --url     |              |    No    |      None       |         Specify url to send data to server         |        dcs-sdk run --config-path config.yaml --compare comp_name --url=https://comapre/send/data         |
+| --html-report |              |    No    |      False      |                 Save table as HTML                 |                 dcs-sdk run --config-path config.yaml --compare comp_name --html-report                  |
+| --report-path |              |    No    | dcs_report.html |       Specify the file path for HTML report        |     dcs-sdk run --config-path config.yaml --compare comp_name --html-report --report-path table.html     |
+|    --table    |              |    No    |      False      |         Display Comparison in table format         | dcs-sdk run --config-path config.yaml --compare comp_name --html-report --report-path table.html --table |
+
+### Example Command [CLI]
+
+```sh
+$ dcs-sdk --version
+
+$ dcs-sdk --help
+
+$ dcs-sdk run -C example.yaml --compare comparison_one --stats -j -jp output.json --html-report --report-path result.html --table --url=https://comapre/send/data
+```
+

dcs_sdk-1.7.0/README.md

@@ -0,0 +1,56 @@
+<h1 align="center">
+  DCS SDK v1.7.0
+</h1>
+
+> SDK for DataChecks
+
+## Installation
+
+> Python version `>=3.10,<3.13`
+
+```bash
+
+$ pip install dcs-sdk[all-dbs]
+
+```
+
+## Supported Databases
+
+> Availability Status
+
+| Database          | Code Name    | Supported |
+| ----------------- | ------------ | --------- |
+| PostgreSQL        | `postgres`   | ✅        |
+| Snowflake         | `snowflake`  | ✅        |
+| Trino             | `trino`      | ✅        |
+| Databricks        | `databricks` | ✅        |
+| Oracle            | `oracle`     | ✅        |
+| MSSQL             | `mssql`      | ✅        |
+| MySQL             | `mysql`      | ✅        |
+| SAP Sybase IQ/ASE | `sybase`     | ✅        |
+| File              | `file`       | ✅        |
+| BigQuery          | `bigquery`   | ✅        |
+
+## Available Commands
+
+|    Option     | Short Option | Required |     Default     |                    Description                     |                                                 Example                                                  |
+| :-----------: | :----------: | :------: | :-------------: | :------------------------------------------------: | :------------------------------------------------------------------------------------------------------: |
+| --config-path |      -C      | **Yes**  |      None       |    Specify the file path for the configuration     |                        dcs-sdk run --config-path config.yaml --compare comp_name                         |
+|   --compare   |              | **Yes**  |      None       | Run only specific comparison using comparison name |                        dcs-sdk run --config-path config.yaml --compare comp_name                         |
+|  --save-json  |      -j      |    No    |      False      |           Save the data into a JSON file           |                  dcs-sdk run --config-path config.yaml --compare comp_name --save-json                   |
+|  --json-path  |     -jp      |    No    | dcs_report.json |        Specify the file path for JSON file         |       dcs-sdk run --config-path config.yaml --compare comp_name --save-json --json-path ouput.json       |
+|    --stats    |              |    No    |      False      |            Print stats about data diff             |                    dcs-sdk run --config-path config.yaml --compare comp_name --stats                     |
+|     --url     |              |    No    |      None       |         Specify url to send data to server         |        dcs-sdk run --config-path config.yaml --compare comp_name --url=https://comapre/send/data         |
+| --html-report |              |    No    |      False      |                 Save table as HTML                 |                 dcs-sdk run --config-path config.yaml --compare comp_name --html-report                  |
+| --report-path |              |    No    | dcs_report.html |       Specify the file path for HTML report        |     dcs-sdk run --config-path config.yaml --compare comp_name --html-report --report-path table.html     |
+|    --table    |              |    No    |      False      |         Display Comparison in table format         | dcs-sdk run --config-path config.yaml --compare comp_name --html-report --report-path table.html --table |
+
+### Example Command [CLI]
+
+```sh
+$ dcs-sdk --version
+
+$ dcs-sdk --help
+
+$ dcs-sdk run -C example.yaml --compare comparison_one --stats -j -jp output.json --html-report --report-path result.html --table --url=https://comapre/send/data
+```

dcs_sdk-1.7.0/data_diff/__init__.py

@@ -0,0 +1,219 @@
+#  Copyright 2022-present, the Waterdip Labs Pvt. Ltd.
+#
+#  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 Iterator, Optional, Sequence, Tuple, Union
+
+from data_diff.abcs.database_types import DbPath, DbTime
+from data_diff.databases import Database
+from data_diff.databases._connect import connect
+from data_diff.diff_tables import Algorithm
+from data_diff.hashdiff_tables import (
+    DEAFULT_TIMEOUT,
+    DEFAULT_BISECTION_FACTOR,
+    DEFAULT_BISECTION_THRESHOLD,
+    DEFAULT_ENGRESS_LIMIT,
+    DEFAULT_PER_COLUMN_DIFF_LIMIT,
+    HashDiffer,
+)
+from data_diff.joindiff_tables import TABLE_WRITE_LIMIT, JoinDiffer
+from data_diff.table_segment import TableSegment
+from data_diff.utils import Vector, eval_name_template
+
+
+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(db_info, dict):
+        keys_to_remove = [k for k, v in db_info.items() if v is None]
+        for k in keys_to_remove:
+            db_info.pop(k)
+    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,
+    # Type check
+    strict: bool = True,
+    # Maximum number diff per column
+    per_column_diff_limit: int = DEFAULT_PER_COLUMN_DIFF_LIMIT,
+    # Maximum number of rows to download
+    egress_limit: int = DEFAULT_ENGRESS_LIMIT,
+    # Timeout limit in minutes
+    # (used for diffing large tables, to avoid long-running queries)
+    timeout_limit: int = DEAFULT_TIMEOUT,
+    in_memory_diff: 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,
+            strict=strict,
+            t1_row_count=table1.count(),
+            t2_row_count=table2.count(),
+            per_column_diff_limit=per_column_diff_limit,
+            egress_limit=egress_limit,
+            timeout_limit=timeout_limit,
+            in_memory_diff=in_memory_diff,
+        )
+    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)