datacheck-cli 2.0.2__tar.gz → 2.1.0__tar.gz

{datacheck_cli-2.0.2 → datacheck_cli-2.1.0}/PKG-INFO

@@ -1,32 +1,33 @@
 Metadata-Version: 2.4
 Name: datacheck-cli
-Version: 2.0.2
-Summary: CLI-first data validation tool for data engineers. Catch bad data before it breaks pipelines.
+Version: 2.1.0
+Summary: A linter for data pipelines. Enforce deterministic validation rules in CI/CD, Airflow, and beyond.
 License: Apache-2.0
 License-File: LICENSE
-Keywords: data-validation,cli,data-engineering,pipeline,ci-cd,data-quality,yaml,testing,csv,parquet,postgres,data-testing
+Keywords: data-validation,data-linter,cli,data-engineering,pipeline,ci-cd,yaml,testing,csv,parquet,postgres,data-testing,great-expectations-alternative,soda-alternative,dbt-testing,data-contracts,airflow,snowflake,bigquery,redshift,schema-contracts,schema-validation,data-pipeline,etl-testing
 Author: Squrtech
 Author-email: contact@squrtech.com
 Requires-Python: >=3.10,<4.0
 Classifier: Development Status :: 5 - Production/Stable
+Classifier: Environment :: Console
 Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: Intended Audience :: System Administrators
 Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Operating System :: OS Independent
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
 Classifier: Programming Language :: Python :: 3.14
+Classifier: Topic :: Database :: Database Engines/Servers
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Classifier: Topic :: Software Development :: Quality Assurance
 Provides-Extra: all
-Provides-Extra: avro
-Provides-Extra: azure
 Provides-Extra: bigquery
 Provides-Extra: cloud
 Provides-Extra: databases
-Provides-Extra: deltalake
-Provides-Extra: duckdb
-Provides-Extra: formats
-Provides-Extra: gcs
 Provides-Extra: mssql
 Provides-Extra: mysql
 Provides-Extra: postgres
@@ -37,21 +38,14 @@ Provides-Extra: snowflake
 Provides-Extra: statistical
 Provides-Extra: validation
 Provides-Extra: warehouses
-Requires-Dist: azure-storage-blob (>=12.19.0,<13.0.0) ; extra == "azure" or extra == "cloud" or extra == "all"
 Requires-Dist: boto3 (>=1.34.0,<2.0.0) ; extra == "s3" or extra == "cloud" or extra == "redshift" or extra == "warehouses" or extra == "all"
 Requires-Dist: click (>=8.1.0,<9.0.0)
-Requires-Dist: deltalake (>=1.4.1,<2.0.0) ; extra == "deltalake" or extra == "formats" or extra == "all"
-Requires-Dist: duckdb (>=0.8.1,<2.0.0) ; (platform_system != "Windows") and (extra == "duckdb" or extra == "databases" or extra == "formats" or extra == "all")
-Requires-Dist: email-validator (>=2.1.0,<3.0.0)
-Requires-Dist: fastavro (>=1.12.1,<2.0.0) ; extra == "avro" or extra == "formats" or extra == "all"
-Requires-Dist: google-auth (>=2.0.0,<3.0.0) ; extra == "gcs" or extra == "cloud" or extra == "bigquery" or extra == "warehouses" or extra == "all"
+Requires-Dist: google-auth (>=2.0.0,<3.0.0) ; extra == "bigquery" or extra == "warehouses" or extra == "all"
 Requires-Dist: google-cloud-bigquery (>=3.0.0,<4.0.0) ; extra == "bigquery" or extra == "warehouses" or extra == "all"
-Requires-Dist: google-cloud-storage (>=2.14.0,<3.0.0) ; extra == "gcs" or extra == "cloud" or extra == "all"
 Requires-Dist: jsonschema (>=4.17.0,<5.0.0) ; extra == "validation" or extra == "all"
 Requires-Dist: mysql-connector-python (>=8.2.0,<10.0.0) ; extra == "mysql" or extra == "databases" or extra == "all"
 Requires-Dist: numpy (>=1.24.0,<3.0.0)
 Requires-Dist: pandas (>=2.0.0,<3.0.0)
-Requires-Dist: phonenumbers (>=8.13.0,<10.0.0)
 Requires-Dist: psycopg2-binary (>=2.9.9,<3.0.0) ; extra == "postgresql" or extra == "postgres" or extra == "databases" or extra == "redshift" or extra == "warehouses" or extra == "all"
 Requires-Dist: pyarrow (>=14.0.0,<24.0.0)
 Requires-Dist: pyodbc (>=5.0.1,<6.0.0) ; extra == "mssql" or extra == "databases" or extra == "all"
@@ -65,23 +59,27 @@ Project-URL: Homepage, https://github.com/squrtech/datacheck
 Project-URL: Repository, https://github.com/squrtech/datacheck
 Description-Content-Type: text/markdown
 
-# DataCheck — Data Validation Engine
+# DataCheck - A Linter for Data Pipelines
 
+[![PyPI version](https://img.shields.io/pypi/v/datacheck-cli.svg)](https://pypi.org/project/datacheck-cli/)
 [![Python 3.10+](https://img.shields.io/badge/python-3.10%2B-blue.svg)](https://www.python.org/downloads/)
 [![License: Apache 2.0](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
+[![Downloads](https://img.shields.io/pypi/dm/datacheck-cli.svg)](https://pypi.org/project/datacheck-cli/)
 
-DataCheck is a data quality validation engine for data engineers. Define validation rules in a YAML config and data sources inline (files) or in a `sources.yaml` (databases, cloud), then automatically validate data across files, databases, and cloud warehouses.
+**DataCheck enforces deterministic validation rules at the pipeline boundary.** Define rules in YAML. Run in CI. Fail fast on bad data. No servers, no dashboards, no infrastructure.
 
-DataCheck provides the `datacheck` Command-Line Interface (CLI) and a Python API, which you can use to validate data, profile quality, and detect schema changes. These operations can be executed locally during development, embedded programmatically within your data pipelines (Airflow, Dagster, Prefect, etc.), or integrated into CI/CD workflows.
+```
+Your data source  →  [DataCheck rules]  →  exit 0: pipeline continues
+                                        →  exit 1: pipeline stops
+```
 
-### Highlights
+Most teams detect bad data after the fact - broken reports, wrong numbers, angry stakeholders. DataCheck enforces validation rules *before* bad data moves downstream, the same way a linter enforces code quality before bad code ships.
 
-- Define validation rules in YAML config and data sources inline (files) or in a `sources.yaml` (databases, cloud)
-- Run checks on CSV, Parquet, Delta Lake, Avro, PostgreSQL, MySQL, Snowflake, BigQuery, Redshift, and more
-- Use 27+ built-in data quality rules for null checks, numeric ranges, patterns, timestamps, email/phone/URL validation, and cross-column checks
-- Profile data quality with automatic scoring, outlier detection, and rule suggestions
-- Detect schema evolution with compatibility levels (COMPATIBLE, WARNING, BREAKING)
-- Extend with custom rules using the `@custom_rule` plugin decorator
+- **Fail fast** - structured exit codes stop pipelines at the gate, not after the damage is done
+- **Deterministic** - rules are explicit and binary. No heuristics. No anomaly scoring. No statistical guessing.
+- **SQL pushdown** - database checks run as a single aggregate `SELECT`; no data leaves your warehouse
+- **Zero infrastructure** - one `pip install`, one YAML file, runs anywhere
+- **CI-native** - SARIF output to GitHub Security tab, GitHub Action, Apache Airflow operators
 
 ## Installation
 
@@ -97,20 +95,20 @@ pip install datacheck-cli[mysql]         # MySQL
 pip install datacheck-cli[snowflake]     # Snowflake
 pip install datacheck-cli[bigquery]      # BigQuery
 pip install datacheck-cli[redshift]      # Redshift
-pip install datacheck-cli[cloud]         # S3, GCS, Azure Blob
+pip install datacheck-cli[s3]            # S3
 pip install datacheck-cli[all]           # All data sources
 ```
 
 ## Quickstart
 
-Use `datacheck config init` to generate a config from a template. Add `--with-sample-data` to also generate a sample CSV file so you can test validation immediately:
+**Option 1 - Start from a template:**
 
 ```bash
 datacheck config init --with-sample-data
 datacheck config init --template ecommerce --with-sample-data
 ```
 
-Or create a `.datacheck.yaml` config file manually with your data source and validation rules:
+**Option 2 - Write manually.** Create a `.datacheck.yaml` config file with your data source and validation rules:
 
 ```yaml
 data_source:
@@ -131,16 +129,67 @@ checks:
       min: 0
       max: 10000
 
-  - name: email_check
-    column: email
-    rules:
-      email_valid: true
 ```
 
 Run validation:
 
 ```bash
-datacheck validate
+datacheck validate                          # auto-discover config
+datacheck validate data.csv                 # direct file
+datacheck validate --config checks.yaml
+echo $?  # 1 if any error-severity rule fails
+```
+
+## CI/CD Integration
+
+### GitHub Actions (with SARIF to Security tab)
+
+```yaml
+# .github/workflows/data-quality.yml
+name: Data Quality Gate
+on: [push, pull_request]
+
+permissions:
+  contents: read
+  security-events: write
+
+jobs:
+  validate:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: squrtech/datacheck-action@v1
+        with:
+          config: .datacheck.yaml
+```
+
+Or generate SARIF manually and upload to the GitHub Security tab:
+
+```yaml
+      - name: Run data quality gate
+        run: |
+          pip install datacheck-cli
+          datacheck validate -c .datacheck.yaml --format sarif --output results.sarif
+
+      - name: Upload SARIF
+        uses: github/codeql-action/upload-sarif@v3
+        if: always()
+        with:
+          sarif_file: results.sarif
+```
+
+### Apache Airflow
+
+```python
+from airflow_provider_datacheck.operators.datacheck import DataCheckOperator
+
+validate_orders = DataCheckOperator(
+    task_id="validate_orders",
+    config_path="/config/orders.datacheck.yaml",
+    source_name="production_db",
+    table="orders",
+    fail_on_error=True,
+)
 ```
 
 ## Database and Cloud Sources
@@ -185,22 +234,13 @@ source: production_db
 table: orders
 ```
 
-## Profile Data Quality
+## Enforce Schema Contracts
 
 ```bash
-datacheck profile                                              # Auto-discover config
-datacheck profile data.csv                                     # Direct file path
-datacheck profile --source production_db --sources-file sources.yaml  # Named source
-datacheck profile --format json -o profile.json                # Export as JSON
-```
-
-## Detect Schema Changes
-
-```bash
-datacheck schema capture                                        # Auto-discover config
+datacheck schema capture                                        # Save current schema as baseline
 datacheck schema capture data.csv                               # Direct file path
 datacheck schema capture --source production_db --sources-file sources.yaml  # Named source
-datacheck schema compare                                        # Compare against baseline
+datacheck schema compare                                        # Compare against baseline - fails if schema changed
 ```
 
 ## Python API
@@ -215,6 +255,9 @@ print(f"Passed: {summary.passed_rules}/{summary.total_rules}")
 
 for result in summary.get_failed_results():
     print(f"  FAIL: {result.rule_name} on {result.column} ({result.failed_rows} rows)")
+
+if not summary.all_passed:
+    raise ValueError("Data quality gate failed - halting pipeline")
 ```
 
 ## Available Rules
@@ -222,12 +265,10 @@ for result in summary.get_failed_results():
 | Category | Rules |
 |----------|-------|
 | Null & Uniqueness | `not_null`, `unique`, `unique_combination` |
-| Numeric | `min`, `max`, `mean_between`, `std_dev_less_than`, `percentile_range`, `z_score_outliers`, `distribution_type` |
+| Numeric | `min`, `max`, `range`, `boolean` |
 | String & Pattern | `regex`, `allowed_values`, `length`, `min_length`, `max_length`, `type` |
-| Temporal | `max_age`, `timestamp_range` (or `date_range`), `no_future_timestamps`, `date_format_valid` (or `date_format`), `business_days_only` |
-| Semantic | `email_valid`, `phone_valid`, `url_valid`, `json_valid` |
+| Temporal | `max_age`, `timestamp_range` (or `date_range`), `no_future_timestamps`, `date_format_valid` (or `date_format`) |
 | Cross-Column | `unique_combination`, `foreign_key_exists` (Python API), `sum_equals` |
-| Custom | `custom` — user-defined functions via `@custom_rule` decorator |
 
 ## Links
 
@@ -238,5 +279,5 @@ for result in summary.get_failed_results():
 
 ## License
 
-Apache License 2.0 — Copyright 2026 Squrtech
+Apache License 2.0 - Copyright 2026 Squrtech
 

{datacheck_cli-2.0.2 → datacheck_cli-2.1.0}/README_PYPI.md

@@ -1,20 +1,24 @@
-# DataCheck — Data Validation Engine
+# DataCheck - A Linter for Data Pipelines
 
+[![PyPI version](https://img.shields.io/pypi/v/datacheck-cli.svg)](https://pypi.org/project/datacheck-cli/)
 [![Python 3.10+](https://img.shields.io/badge/python-3.10%2B-blue.svg)](https://www.python.org/downloads/)
 [![License: Apache 2.0](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
+[![Downloads](https://img.shields.io/pypi/dm/datacheck-cli.svg)](https://pypi.org/project/datacheck-cli/)
 
-DataCheck is a data quality validation engine for data engineers. Define validation rules in a YAML config and data sources inline (files) or in a `sources.yaml` (databases, cloud), then automatically validate data across files, databases, and cloud warehouses.
+**DataCheck enforces deterministic validation rules at the pipeline boundary.** Define rules in YAML. Run in CI. Fail fast on bad data. No servers, no dashboards, no infrastructure.
 
-DataCheck provides the `datacheck` Command-Line Interface (CLI) and a Python API, which you can use to validate data, profile quality, and detect schema changes. These operations can be executed locally during development, embedded programmatically within your data pipelines (Airflow, Dagster, Prefect, etc.), or integrated into CI/CD workflows.
+```
+Your data source  →  [DataCheck rules]  →  exit 0: pipeline continues
+                                        →  exit 1: pipeline stops
+```
 
-### Highlights
+Most teams detect bad data after the fact - broken reports, wrong numbers, angry stakeholders. DataCheck enforces validation rules *before* bad data moves downstream, the same way a linter enforces code quality before bad code ships.
 
-- Define validation rules in YAML config and data sources inline (files) or in a `sources.yaml` (databases, cloud)
-- Run checks on CSV, Parquet, Delta Lake, Avro, PostgreSQL, MySQL, Snowflake, BigQuery, Redshift, and more
-- Use 27+ built-in data quality rules for null checks, numeric ranges, patterns, timestamps, email/phone/URL validation, and cross-column checks
-- Profile data quality with automatic scoring, outlier detection, and rule suggestions
-- Detect schema evolution with compatibility levels (COMPATIBLE, WARNING, BREAKING)
-- Extend with custom rules using the `@custom_rule` plugin decorator
+- **Fail fast** - structured exit codes stop pipelines at the gate, not after the damage is done
+- **Deterministic** - rules are explicit and binary. No heuristics. No anomaly scoring. No statistical guessing.
+- **SQL pushdown** - database checks run as a single aggregate `SELECT`; no data leaves your warehouse
+- **Zero infrastructure** - one `pip install`, one YAML file, runs anywhere
+- **CI-native** - SARIF output to GitHub Security tab, GitHub Action, Apache Airflow operators
 
 ## Installation
 
@@ -30,20 +34,20 @@ pip install datacheck-cli[mysql]         # MySQL
 pip install datacheck-cli[snowflake]     # Snowflake
 pip install datacheck-cli[bigquery]      # BigQuery
 pip install datacheck-cli[redshift]      # Redshift
-pip install datacheck-cli[cloud]         # S3, GCS, Azure Blob
+pip install datacheck-cli[s3]            # S3
 pip install datacheck-cli[all]           # All data sources
 ```
 
 ## Quickstart
 
-Use `datacheck config init` to generate a config from a template. Add `--with-sample-data` to also generate a sample CSV file so you can test validation immediately:
+**Option 1 - Start from a template:**
 
 ```bash
 datacheck config init --with-sample-data
 datacheck config init --template ecommerce --with-sample-data
 ```
 
-Or create a `.datacheck.yaml` config file manually with your data source and validation rules:
+**Option 2 - Write manually.** Create a `.datacheck.yaml` config file with your data source and validation rules:
 
 ```yaml
 data_source:
@@ -64,16 +68,67 @@ checks:
       min: 0
       max: 10000
 
-  - name: email_check
-    column: email
-    rules:
-      email_valid: true
 ```
 
 Run validation:
 
 ```bash
-datacheck validate
+datacheck validate                          # auto-discover config
+datacheck validate data.csv                 # direct file
+datacheck validate --config checks.yaml
+echo $?  # 1 if any error-severity rule fails
+```
+
+## CI/CD Integration
+
+### GitHub Actions (with SARIF to Security tab)
+
+```yaml
+# .github/workflows/data-quality.yml
+name: Data Quality Gate
+on: [push, pull_request]
+
+permissions:
+  contents: read
+  security-events: write
+
+jobs:
+  validate:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: squrtech/datacheck-action@v1
+        with:
+          config: .datacheck.yaml
+```
+
+Or generate SARIF manually and upload to the GitHub Security tab:
+
+```yaml
+      - name: Run data quality gate
+        run: |
+          pip install datacheck-cli
+          datacheck validate -c .datacheck.yaml --format sarif --output results.sarif
+
+      - name: Upload SARIF
+        uses: github/codeql-action/upload-sarif@v3
+        if: always()
+        with:
+          sarif_file: results.sarif
+```
+
+### Apache Airflow
+
+```python
+from airflow_provider_datacheck.operators.datacheck import DataCheckOperator
+
+validate_orders = DataCheckOperator(
+    task_id="validate_orders",
+    config_path="/config/orders.datacheck.yaml",
+    source_name="production_db",
+    table="orders",
+    fail_on_error=True,
+)
 ```
 
 ## Database and Cloud Sources
@@ -118,22 +173,13 @@ source: production_db
 table: orders
 ```
 
-## Profile Data Quality
+## Enforce Schema Contracts
 
 ```bash
-datacheck profile                                              # Auto-discover config
-datacheck profile data.csv                                     # Direct file path
-datacheck profile --source production_db --sources-file sources.yaml  # Named source
-datacheck profile --format json -o profile.json                # Export as JSON
-```
-
-## Detect Schema Changes
-
-```bash
-datacheck schema capture                                        # Auto-discover config
+datacheck schema capture                                        # Save current schema as baseline
 datacheck schema capture data.csv                               # Direct file path
 datacheck schema capture --source production_db --sources-file sources.yaml  # Named source
-datacheck schema compare                                        # Compare against baseline
+datacheck schema compare                                        # Compare against baseline - fails if schema changed
 ```
 
 ## Python API
@@ -148,6 +194,9 @@ print(f"Passed: {summary.passed_rules}/{summary.total_rules}")
 
 for result in summary.get_failed_results():
     print(f"  FAIL: {result.rule_name} on {result.column} ({result.failed_rows} rows)")
+
+if not summary.all_passed:
+    raise ValueError("Data quality gate failed - halting pipeline")
 ```
 
 ## Available Rules
@@ -155,12 +204,10 @@ for result in summary.get_failed_results():
 | Category | Rules |
 |----------|-------|
 | Null & Uniqueness | `not_null`, `unique`, `unique_combination` |
-| Numeric | `min`, `max`, `mean_between`, `std_dev_less_than`, `percentile_range`, `z_score_outliers`, `distribution_type` |
+| Numeric | `min`, `max`, `range`, `boolean` |
 | String & Pattern | `regex`, `allowed_values`, `length`, `min_length`, `max_length`, `type` |
-| Temporal | `max_age`, `timestamp_range` (or `date_range`), `no_future_timestamps`, `date_format_valid` (or `date_format`), `business_days_only` |
-| Semantic | `email_valid`, `phone_valid`, `url_valid`, `json_valid` |
+| Temporal | `max_age`, `timestamp_range` (or `date_range`), `no_future_timestamps`, `date_format_valid` (or `date_format`) |
 | Cross-Column | `unique_combination`, `foreign_key_exists` (Python API), `sum_equals` |
-| Custom | `custom` — user-defined functions via `@custom_rule` decorator |
 
 ## Links
 
@@ -171,4 +218,4 @@ for result in summary.get_failed_results():
 
 ## License
 
-Apache License 2.0 — Copyright 2026 Squrtech
+Apache License 2.0 - Copyright 2026 Squrtech

{datacheck_cli-2.0.2 → datacheck_cli-2.1.0}/datacheck/__init__.py

@@ -1,4 +1,4 @@
-"""DataCheck - Lightweight data quality validation CLI tool."""
+"""DataCheck - A linter for data pipelines."""
 
 from datacheck.engine import ValidationEngine
 from datacheck.exceptions import (
@@ -12,11 +12,9 @@ from datacheck.exceptions import (
     ValidationError,
 )
 from datacheck.loader import (
-    AvroLoader,
     CSVLoader,
     DataLoader,
-    DeltaLakeLoader,
-    DuckDBLoader,
+    DatabaseLoader,
     LoaderFactory,
     ParquetLoader,
 )
@@ -26,18 +24,8 @@ from datacheck.schema import (
     SchemaComparator,
     SchemaDetector,
 )
-from datacheck.profiling import DataProfiler
-from datacheck.profiling.models import ColumnProfile, DatasetProfile
-from datacheck.profiling.outliers import OutlierDetector, OutlierMethod
-from datacheck.profiling.quality import QualityScorer
-from datacheck.profiling.suggestions import RuleSuggester
-from datacheck.profiling.formatters import (
-    JsonFormatter,
-    MarkdownFormatter,
-    TerminalFormatter,
-)
 
-__version__ = "2.0.2"
+__version__ = "2.1.0"
 __author__ = "Squrtech"
 __email__ = "contact@squrtech.com"
 
@@ -58,9 +46,7 @@ __all__ = [
     "DataLoader",
     "CSVLoader",
     "ParquetLoader",
-    "DuckDBLoader",
-    "DeltaLakeLoader",
-    "AvroLoader",
+    "DatabaseLoader",
     "LoaderFactory",
     # Engine
     "ValidationEngine",
@@ -71,15 +57,4 @@ __all__ = [
     "SchemaDetector",
     "SchemaComparator",
     "BaselineManager",
-    # Profiling
-    "DataProfiler",
-    "ColumnProfile",
-    "DatasetProfile",
-    "OutlierDetector",
-    "OutlierMethod",
-    "QualityScorer",
-    "RuleSuggester",
-    "JsonFormatter",
-    "MarkdownFormatter",
-    "TerminalFormatter",
 ]

{datacheck_cli-2.0.2 → datacheck_cli-2.1.0}/datacheck/airflow/__init__.py

@@ -1,10 +1,10 @@
 """Airflow integration for DataCheck.
 
-Provides two operators for integrating DataCheck data quality
-validation into Airflow pipelines:
+Provides two operators for enforcing DataCheck validation rules
+in Airflow pipelines:
 
-- DataCheckOperator: Validate data against configured rules
-- DataCheckSchemaOperator: Detect schema changes against baselines
+- DataCheckOperator: Enforce validation rules against configured data sources
+- DataCheckSchemaOperator: Enforce schema contracts against saved baselines
 
 For complex workflows, you can also use the CLI via BashOperator.
 """