datacontract-cli 1.2.2__tar.gz → 1.2.4__tar.gz

{datacontract_cli-1.2.2/datacontract_cli.egg-info → datacontract_cli-1.2.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datacontract-cli
-Version: 1.2.2
+Version: 1.2.4
 Summary: The datacontract CLI is an open source command-line tool for working with Data Contracts. It uses data contract YAML files to lint the data contract, connect to data sources and execute schema and quality tests, detect breaking changes, and export to different formats. The tool is written in Python. It can be used as a standalone CLI tool, in a CI/CD pipeline, or directly as a Python library.
 Author-email: Jochen Christ <jochen.christ@entropy-data.com>, Stefan Negele <stefan.negele@innoq.com>, Simon Harrer <simon.harrer@entropy-data.com>
 License-Expression: MIT
@@ -40,7 +40,7 @@ Requires-Dist: jsonschema<5.0.0,>=4.23.0
 Requires-Dist: pytz>=2024.1
 Requires-Dist: python-multipart<1.0.0,>=0.0.20
 Requires-Dist: rich<16.0,>=13.7
-Requires-Dist: sqlglot<30.18,>=26.6.0
+Requires-Dist: sqlglot<31.0.0,>=26.6.0
 Requires-Dist: python-dotenv<2.0.0,>=1.0.0
 Requires-Dist: boto3<2.0.0,>=1.34.41
 Requires-Dist: Jinja2<4.0.0,>=3.1.5
@@ -52,6 +52,9 @@ Provides-Extra: avro
 Requires-Dist: avro==1.12.2; extra == "avro"
 Provides-Extra: bigquery
 Requires-Dist: ibis-framework[bigquery]<13.0.0,>=10.0.0; extra == "bigquery"
+Provides-Extra: clickhouse
+Requires-Dist: ibis-framework[clickhouse]<13.0.0,>=10.0.0; extra == "clickhouse"
+Requires-Dist: packaging<27.0,>=21.3; extra == "clickhouse"
 Provides-Extra: csv
 Requires-Dist: datacontract-cli[duckdb]; extra == "csv"
 Provides-Extra: excel
@@ -66,8 +69,8 @@ Requires-Dist: pyarrow-hotfix>=0.4; extra == "dataframe"
 Requires-Dist: rich>=12.4.4; extra == "dataframe"
 Provides-Extra: databricks
 Requires-Dist: ibis-framework[databricks]<13.0.0,>=10.0.0; extra == "databricks"
-Requires-Dist: databricks-sql-connector<4.6.0,>=3.7.0; extra == "databricks"
-Requires-Dist: databricks-sdk<0.140.0; extra == "databricks"
+Requires-Dist: databricks-sql-connector<4.7.0,>=3.7.0; extra == "databricks"
+Requires-Dist: databricks-sdk<0.143.0; extra == "databricks"
 Requires-Dist: packaging<27.0,>=21.3; extra == "databricks"
 Provides-Extra: databricks-runtime
 Requires-Dist: datacontract-cli[databricks]; extra == "databricks-runtime"
@@ -101,7 +104,7 @@ Requires-Dist: duckdb-extension-azure<1.6.0,>=1.5.0; extra == "azure"
 Requires-Dist: azure-identity<1.26,>=1.17.1; extra == "azure"
 Requires-Dist: azure-storage-blob<12.31,>=12.24; extra == "azure"
 Provides-Extra: snowflake
-Requires-Dist: snowflake-connector-python[pandas]<4.8,>=3.6; extra == "snowflake"
+Requires-Dist: snowflake-connector-python[pandas]<4.9,>=3.6; extra == "snowflake"
 Requires-Dist: ibis-framework[snowflake]<13.0.0,>=10.0.0; extra == "snowflake"
 Provides-Extra: sqlserver
 Requires-Dist: ibis-framework[mssql]<13.0.0,>=10.0.0; extra == "sqlserver"
@@ -125,6 +128,9 @@ Requires-Dist: packaging<27.0,>=21.3; extra == "trino"
 Provides-Extra: impala
 Requires-Dist: ibis-framework[impala]<13.0.0,>=10.0.0; extra == "impala"
 Requires-Dist: packaging<27.0,>=21.3; extra == "impala"
+Provides-Extra: hive
+Requires-Dist: ibis-framework[impala]<13.0.0,>=10.0.0; extra == "hive"
+Requires-Dist: packaging<27.0,>=21.3; extra == "hive"
 Provides-Extra: dbml
 Requires-Dist: pydbml>=1.1.1; extra == "dbml"
 Provides-Extra: duckdb
@@ -135,12 +141,14 @@ Requires-Dist: pyarrow>=18.1.0; extra == "parquet"
 Provides-Extra: rdf
 Requires-Dist: rdflib==7.6.0; extra == "rdf"
 Provides-Extra: api
-Requires-Dist: fastapi<0.142.0,>=0.115.0; extra == "api"
-Requires-Dist: uvicorn<0.54.0,>=0.44.0; extra == "api"
+Requires-Dist: fastapi<0.143.0,>=0.115.0; extra == "api"
+Requires-Dist: uvicorn<0.55.0,>=0.44.0; extra == "api"
 Provides-Extra: protobuf
 Requires-Dist: proto-schema-parser<3.0,>=1.0; extra == "protobuf"
+Provides-Extra: xml
+Requires-Dist: xmlschema<5.0,>=4.0; extra == "xml"
 Provides-Extra: all
-Requires-Dist: datacontract-cli[api,athena,avro,azure,bigquery,csv,databricks,dataframe,dbml,duckdb,exasol,excel,gcs,iceberg,impala,kafka,mysql,oracle,parquet,postgres,protobuf,rdf,redshift,s3,snowflake,sqlserver,trino]; extra == "all"
+Requires-Dist: datacontract-cli[api,athena,avro,azure,bigquery,clickhouse,csv,databricks,dataframe,dbml,duckdb,exasol,excel,gcs,hive,iceberg,impala,kafka,mysql,oracle,parquet,postgres,protobuf,rdf,redshift,s3,snowflake,sqlserver,trino,xml]; extra == "all"
 Provides-Extra: dev
 Requires-Dist: datacontract-cli[all]; extra == "dev"
 Requires-Dist: httpx==0.28.1; extra == "dev"
@@ -153,10 +161,10 @@ Requires-Dist: pre-commit<4.7.0,>=3.7.1; extra == "dev"
 Requires-Dist: pytest; extra == "dev"
 Requires-Dist: pytest-cov; extra == "dev"
 Requires-Dist: pytest-xdist; extra == "dev"
-Requires-Dist: pymssql==2.4.1; extra == "dev"
+Requires-Dist: pymssql==2.4.2; extra == "dev"
 Requires-Dist: psycopg2-binary<3.0,>=2.9; extra == "dev"
 Requires-Dist: mysql-connector-python<26.8.0,>=8.0.30; extra == "dev"
-Requires-Dist: ruff==0.16.8; extra == "dev"
+Requires-Dist: ruff==0.16.10; extra == "dev"
 Requires-Dist: testcontainers[kafka,minio,mssql,mysql,postgres]==4.15.0; extra == "dev"
 Requires-Dist: trino==0.339.0; extra == "dev"
 Dynamic: license-file
@@ -186,7 +194,7 @@ It can be used as a standalone CLI tool, in a CI/CD pipeline, or directly as a P
 >
 > Quick links: [Quickstart](https://docs.datacontract.com/quickstart) · [Commands](https://docs.datacontract.com/commands) · [Best Practices](https://docs.datacontract.com/best-practices) · [Custom Export and Import](https://docs.datacontract.com/extending) · [Release Notes](https://docs.datacontract.com/release-notes) · [Development Setup](#development-setup)
 >
-> For LLMs: [cli.datacontract.com/llms.txt](https://cli.datacontract.com/llms.txt) · [docs.datacontract.com/llms.txt](https://docs.datacontract.com/llms.txt) · [docs.datacontract.com/llms-full.txt](https://docs.datacontract.com/llms-full.txt)
+> For LLMs: [docs.datacontract.com/llms.txt](https://docs.datacontract.com/llms.txt) · [docs.datacontract.com/llms-full.txt](https://docs.datacontract.com/llms-full.txt)
 
 ## Getting started
 
@@ -214,36 +222,41 @@ $ datacontract test https://datacontract.com/orders-v1.odcs.yaml
 # returns:
 Testing https://datacontract.com/orders-v1.odcs.yaml
 Server: production (type=postgres, host=aws-1-eu-central-2.pooler.supabase.com, port=6543, database=postgres, schema=dp_orders_v1)
-╭────────┬──────────────────────────────────────────────────────────┬─────────────────────────┬─────────╮
-│ Result │ Check                                                    │ Field                   │ Details │
-├────────┼──────────────────────────────────────────────────────────┼─────────────────────────┼─────────┤
-│ passed │ Check that field 'line_item_id' is present               │ line_items.line_item_id │         │
-│ passed │ Check that field line_item_id has type UUID              │ line_items.line_item_id │         │
-│ passed │ Check that field line_item_id has no missing values      │ line_items.line_item_id │         │
-│ passed │ Check that field 'order_id' is present                   │ line_items.order_id     │         │
-│ passed │ Check that field order_id has type UUID                  │ line_items.order_id     │         │
-│ passed │ Check that field 'price' is present                      │ line_items.price        │         │
-│ passed │ Check that field price has type INTEGER                  │ line_items.price        │         │
-│ passed │ Check that field price has no missing values             │ line_items.price        │         │
-│ passed │ Check that field 'sku' is present                        │ line_items.sku          │         │
-│ passed │ Check that field sku has type TEXT                       │ line_items.sku          │         │
-│ passed │ Check that field sku has no missing values               │ line_items.sku          │         │
-│ passed │ Check that field 'customer_id' is present                │ orders.customer_id      │         │
-│ passed │ Check that field customer_id has type TEXT               │ orders.customer_id      │         │
-│ passed │ Check that field customer_id has no missing values       │ orders.customer_id      │         │
-│ passed │ Check that field 'order_id' is present                   │ orders.order_id         │         │
-│ passed │ Check that field order_id has type UUID                  │ orders.order_id         │         │
-│ passed │ Check that field order_id has no missing values          │ orders.order_id         │         │
-│ passed │ Check that unique field order_id has no duplicate values │ orders.order_id         │         │
-│ passed │ Check that field 'order_status' is present               │ orders.order_status     │         │
-│ passed │ Check that field order_status has type TEXT              │ orders.order_status     │         │
-│ passed │ Check that field 'order_timestamp' is present            │ orders.order_timestamp  │         │
-│ passed │ Check that field order_timestamp has type TIMESTAMPTZ    │ orders.order_timestamp  │         │
-│ passed │ Check that field 'order_total' is present                │ orders.order_total      │         │
-│ passed │ Check that field order_total has type INTEGER            │ orders.order_total      │         │
-│ passed │ Check that field order_total has no missing values       │ orders.order_total      │         │
-╰────────┴──────────────────────────────────────────────────────────┴─────────────────────────┴─────────╯
-🟢 data contract is valid. Run 25 checks. Took 3.938887 seconds.
+╭────────┬───────────────────────────────────────────────────────────────────┬─────────────────────────┬─────────╮
+│ Result │ Check                                                             │ Field                   │ Details │
+├────────┼───────────────────────────────────────────────────────────────────┼─────────────────────────┼─────────┤
+│ passed │ Check that field 'line_item_id' is present                        │ line_items.line_item_id │         │
+│ passed │ Check that field line_item_id has physical type UUID              │ line_items.line_item_id │         │
+│ passed │ Check that field line_item_id has no missing values               │ line_items.line_item_id │         │
+│ passed │ Check that primary key field line_item_id has no duplicate values │ line_items.line_item_id │         │
+│ passed │ Check that field 'order_id' is present                            │ line_items.order_id     │         │
+│ passed │ Check that field order_id has physical type UUID                  │ line_items.order_id     │         │
+│ passed │ Check that field 'price' is present                               │ line_items.price        │         │
+│ passed │ Check that field price has physical type INTEGER                  │ line_items.price        │         │
+│ passed │ Check that field price has no missing values                      │ line_items.price        │         │
+│ passed │ Check that field 'sku' is present                                 │ line_items.sku          │         │
+│ passed │ Check that field sku has physical type TEXT                       │ line_items.sku          │         │
+│ passed │ Check that field sku has no missing values                        │ line_items.sku          │         │
+│ passed │ Check that model orders has row_count > 100000                    │ orders                  │         │
+│ passed │ Check that field 'customer_id' is present                         │ orders.customer_id      │         │
+│ passed │ Check that field customer_id has physical type TEXT               │ orders.customer_id      │         │
+│ passed │ Check that field customer_id has no missing values                │ orders.customer_id      │         │
+│ passed │ Check that field customer_id has a min length of 10               │ orders.customer_id      │         │
+│ passed │ Check that field customer_id has a max length of 10               │ orders.customer_id      │         │
+│ passed │ Check that field 'order_id' is present                            │ orders.order_id         │         │
+│ passed │ Check that field order_id has physical type UUID                  │ orders.order_id         │         │
+│ passed │ Check that field order_id has no missing values                   │ orders.order_id         │         │
+│ passed │ Check that unique field order_id has no duplicate values          │ orders.order_id         │         │
+│ passed │ Check that field 'order_status' is present                        │ orders.order_status     │         │
+│ passed │ Check that field order_status has physical type TEXT              │ orders.order_status     │         │
+│ passed │ Check that field order_status has invalid_count = 0               │ orders.order_status     │         │
+│ passed │ Check that field 'order_timestamp' is present                     │ orders.order_timestamp  │         │
+│ passed │ Check that field order_timestamp has physical type TIMESTAMPTZ    │ orders.order_timestamp  │         │
+│ passed │ Check that field 'order_total' is present                         │ orders.order_total      │         │
+│ passed │ Check that field order_total has physical type INTEGER            │ orders.order_total      │         │
+│ passed │ Check that field order_total has no missing values                │ orders.order_total      │         │
+╰────────┴───────────────────────────────────────────────────────────────────┴─────────────────────────┴─────────╯
+🟢 Data contract is valid. Ran 30 checks. Took 2.504495 seconds.
 ```
 
 Voilà, the CLI tested that the YAML itself is valid, all records comply with the schema, and all quality attributes are met.
@@ -342,7 +355,7 @@ if not run.has_passed():
 ## How to
 
 - [How to integrate Data Contract CLI in your CI/CD pipeline as a GitHub Action](https://github.com/datacontract/datacontract-action/)
-- [How to run the Data Contract CLI API to test data contracts with POST requests](https://cli.datacontract.com/API)
+- [How to run the Data Contract CLI API to test data contracts with POST requests](https://docs.datacontract.com/api)
 - [How to run Data Contract CLI in a Databricks pipeline](https://www.datamesh-architecture.com/howto/build-a-dataproduct-with-databricks#test-the-data-product)
 
 
@@ -363,11 +376,11 @@ uv tool install --python python3.11 --upgrade 'datacontract-cli[all]'
 If you have [uv](https://docs.astral.sh/uv/) installed, you can run datacontract-cli directly without installing:
 
 ```
-uv run --with 'datacontract-cli[all]' datacontract --version
+uvx --from 'datacontract-cli[all]' datacontract --version
 ```
 
 ### pip
-Python 3.10, 3.11, and 3.12 are supported. We recommend using Python 3.11.
+Python 3.10–3.14 are supported. We recommend using Python 3.11.
 
 ```bash
 python3 -m pip install 'datacontract-cli[all]'
@@ -456,6 +469,7 @@ A list of available extras:
 | Snowflake | `pip install datacontract-cli[snowflake]` |
 | Microsoft SQL Server | `pip install datacontract-cli[sqlserver]` |
 | Trino | `pip install datacontract-cli[trino]` |
+| XML Schema (import) | `pip install datacontract-cli[xml]` |
 
 
 ## Documentation

{datacontract_cli-1.2.2 → datacontract_cli-1.2.4}/README.md

@@ -23,7 +23,7 @@ It can be used as a standalone CLI tool, in a CI/CD pipeline, or directly as a P
 >
 > Quick links: [Quickstart](https://docs.datacontract.com/quickstart) · [Commands](https://docs.datacontract.com/commands) · [Best Practices](https://docs.datacontract.com/best-practices) · [Custom Export and Import](https://docs.datacontract.com/extending) · [Release Notes](https://docs.datacontract.com/release-notes) · [Development Setup](#development-setup)
 >
-> For LLMs: [cli.datacontract.com/llms.txt](https://cli.datacontract.com/llms.txt) · [docs.datacontract.com/llms.txt](https://docs.datacontract.com/llms.txt) · [docs.datacontract.com/llms-full.txt](https://docs.datacontract.com/llms-full.txt)
+> For LLMs: [docs.datacontract.com/llms.txt](https://docs.datacontract.com/llms.txt) · [docs.datacontract.com/llms-full.txt](https://docs.datacontract.com/llms-full.txt)
 
 ## Getting started
 
@@ -51,36 +51,41 @@ $ datacontract test https://datacontract.com/orders-v1.odcs.yaml
 # returns:
 Testing https://datacontract.com/orders-v1.odcs.yaml
 Server: production (type=postgres, host=aws-1-eu-central-2.pooler.supabase.com, port=6543, database=postgres, schema=dp_orders_v1)
-╭────────┬──────────────────────────────────────────────────────────┬─────────────────────────┬─────────╮
-│ Result │ Check                                                    │ Field                   │ Details │
-├────────┼──────────────────────────────────────────────────────────┼─────────────────────────┼─────────┤
-│ passed │ Check that field 'line_item_id' is present               │ line_items.line_item_id │         │
-│ passed │ Check that field line_item_id has type UUID              │ line_items.line_item_id │         │
-│ passed │ Check that field line_item_id has no missing values      │ line_items.line_item_id │         │
-│ passed │ Check that field 'order_id' is present                   │ line_items.order_id     │         │
-│ passed │ Check that field order_id has type UUID                  │ line_items.order_id     │         │
-│ passed │ Check that field 'price' is present                      │ line_items.price        │         │
-│ passed │ Check that field price has type INTEGER                  │ line_items.price        │         │
-│ passed │ Check that field price has no missing values             │ line_items.price        │         │
-│ passed │ Check that field 'sku' is present                        │ line_items.sku          │         │
-│ passed │ Check that field sku has type TEXT                       │ line_items.sku          │         │
-│ passed │ Check that field sku has no missing values               │ line_items.sku          │         │
-│ passed │ Check that field 'customer_id' is present                │ orders.customer_id      │         │
-│ passed │ Check that field customer_id has type TEXT               │ orders.customer_id      │         │
-│ passed │ Check that field customer_id has no missing values       │ orders.customer_id      │         │
-│ passed │ Check that field 'order_id' is present                   │ orders.order_id         │         │
-│ passed │ Check that field order_id has type UUID                  │ orders.order_id         │         │
-│ passed │ Check that field order_id has no missing values          │ orders.order_id         │         │
-│ passed │ Check that unique field order_id has no duplicate values │ orders.order_id         │         │
-│ passed │ Check that field 'order_status' is present               │ orders.order_status     │         │
-│ passed │ Check that field order_status has type TEXT              │ orders.order_status     │         │
-│ passed │ Check that field 'order_timestamp' is present            │ orders.order_timestamp  │         │
-│ passed │ Check that field order_timestamp has type TIMESTAMPTZ    │ orders.order_timestamp  │         │
-│ passed │ Check that field 'order_total' is present                │ orders.order_total      │         │
-│ passed │ Check that field order_total has type INTEGER            │ orders.order_total      │         │
-│ passed │ Check that field order_total has no missing values       │ orders.order_total      │         │
-╰────────┴──────────────────────────────────────────────────────────┴─────────────────────────┴─────────╯
-🟢 data contract is valid. Run 25 checks. Took 3.938887 seconds.
+╭────────┬───────────────────────────────────────────────────────────────────┬─────────────────────────┬─────────╮
+│ Result │ Check                                                             │ Field                   │ Details │
+├────────┼───────────────────────────────────────────────────────────────────┼─────────────────────────┼─────────┤
+│ passed │ Check that field 'line_item_id' is present                        │ line_items.line_item_id │         │
+│ passed │ Check that field line_item_id has physical type UUID              │ line_items.line_item_id │         │
+│ passed │ Check that field line_item_id has no missing values               │ line_items.line_item_id │         │
+│ passed │ Check that primary key field line_item_id has no duplicate values │ line_items.line_item_id │         │
+│ passed │ Check that field 'order_id' is present                            │ line_items.order_id     │         │
+│ passed │ Check that field order_id has physical type UUID                  │ line_items.order_id     │         │
+│ passed │ Check that field 'price' is present                               │ line_items.price        │         │
+│ passed │ Check that field price has physical type INTEGER                  │ line_items.price        │         │
+│ passed │ Check that field price has no missing values                      │ line_items.price        │         │
+│ passed │ Check that field 'sku' is present                                 │ line_items.sku          │         │
+│ passed │ Check that field sku has physical type TEXT                       │ line_items.sku          │         │
+│ passed │ Check that field sku has no missing values                        │ line_items.sku          │         │
+│ passed │ Check that model orders has row_count > 100000                    │ orders                  │         │
+│ passed │ Check that field 'customer_id' is present                         │ orders.customer_id      │         │
+│ passed │ Check that field customer_id has physical type TEXT               │ orders.customer_id      │         │
+│ passed │ Check that field customer_id has no missing values                │ orders.customer_id      │         │
+│ passed │ Check that field customer_id has a min length of 10               │ orders.customer_id      │         │
+│ passed │ Check that field customer_id has a max length of 10               │ orders.customer_id      │         │
+│ passed │ Check that field 'order_id' is present                            │ orders.order_id         │         │
+│ passed │ Check that field order_id has physical type UUID                  │ orders.order_id         │         │
+│ passed │ Check that field order_id has no missing values                   │ orders.order_id         │         │
+│ passed │ Check that unique field order_id has no duplicate values          │ orders.order_id         │         │
+│ passed │ Check that field 'order_status' is present                        │ orders.order_status     │         │
+│ passed │ Check that field order_status has physical type TEXT              │ orders.order_status     │         │
+│ passed │ Check that field order_status has invalid_count = 0               │ orders.order_status     │         │
+│ passed │ Check that field 'order_timestamp' is present                     │ orders.order_timestamp  │         │
+│ passed │ Check that field order_timestamp has physical type TIMESTAMPTZ    │ orders.order_timestamp  │         │
+│ passed │ Check that field 'order_total' is present                         │ orders.order_total      │         │
+│ passed │ Check that field order_total has physical type INTEGER            │ orders.order_total      │         │
+│ passed │ Check that field order_total has no missing values                │ orders.order_total      │         │
+╰────────┴───────────────────────────────────────────────────────────────────┴─────────────────────────┴─────────╯
+🟢 Data contract is valid. Ran 30 checks. Took 2.504495 seconds.
 ```
 
 Voilà, the CLI tested that the YAML itself is valid, all records comply with the schema, and all quality attributes are met.
@@ -179,7 +184,7 @@ if not run.has_passed():
 ## How to
 
 - [How to integrate Data Contract CLI in your CI/CD pipeline as a GitHub Action](https://github.com/datacontract/datacontract-action/)
-- [How to run the Data Contract CLI API to test data contracts with POST requests](https://cli.datacontract.com/API)
+- [How to run the Data Contract CLI API to test data contracts with POST requests](https://docs.datacontract.com/api)
 - [How to run Data Contract CLI in a Databricks pipeline](https://www.datamesh-architecture.com/howto/build-a-dataproduct-with-databricks#test-the-data-product)
 
 
@@ -200,11 +205,11 @@ uv tool install --python python3.11 --upgrade 'datacontract-cli[all]'
 If you have [uv](https://docs.astral.sh/uv/) installed, you can run datacontract-cli directly without installing:
 
 ```
-uv run --with 'datacontract-cli[all]' datacontract --version
+uvx --from 'datacontract-cli[all]' datacontract --version
 ```
 
 ### pip
-Python 3.10, 3.11, and 3.12 are supported. We recommend using Python 3.11.
+Python 3.10–3.14 are supported. We recommend using Python 3.11.
 
 ```bash
 python3 -m pip install 'datacontract-cli[all]'
@@ -293,6 +298,7 @@ A list of available extras:
 | Snowflake | `pip install datacontract-cli[snowflake]` |
 | Microsoft SQL Server | `pip install datacontract-cli[sqlserver]` |
 | Trino | `pip install datacontract-cli[trino]` |
+| XML Schema (import) | `pip install datacontract-cli[xml]` |
 
 
 ## Documentation

{datacontract_cli-1.2.2 → datacontract_cli-1.2.4}/datacontract/api.py

@@ -449,7 +449,8 @@ def config_from_headers(headers) -> "Config | None":
     → ``DATACONTRACT_SNOWFLAKE_PASSWORD``, ``entropy-data-api-key`` →
     ``ENTROPY_DATA_API_KEY``. Returns None when no config headers are present,
     so env-var-configured deployments behave exactly as before. Unknown
-    ``datacontract-*`` option names are rejected with a 400.
+    ``datacontract-*`` option names are rejected with a 400, and so is the
+    custom quality checks folder.
     """
     known = known_env_names()
     values = {}
@@ -457,6 +458,12 @@ def config_from_headers(headers) -> "Config | None":
         lowered = name.lower()
         env = lowered.upper().replace("-", "_")
         if lowered.startswith(_CONFIG_HEADER_PREFIX) or env in known:
+            if env == "DATACONTRACT_CUSTOM_QUALITY_CHECKS":
+                # A folder on the server's disk is the operator's to choose, never the caller's.
+                raise HTTPException(
+                    status_code=status.HTTP_400_BAD_REQUEST,
+                    detail="The custom quality checks folder is configured by the API server, not per request.",
+                )
             values[env] = value
     if not values:
         return None
@@ -502,6 +509,8 @@ _ENVIRONMENT_CREDENTIAL_TARGETS: dict[str, tuple[str, str | None, tuple[str, ...
     "impala": ("host", "impala_host", ("impala_password",)),
     "trino": ("host", "trino_host", ("trino_password",)),
     "exasol": ("host", "exasol_host", ("exasol_password",)),
+    "clickhouse": ("host", "clickhouse_host", ("clickhouse_password",)),
+    "hive": ("host", "hive_host", ("hive_password",)),
     "redshift": ("host", "redshift_host", ("redshift_password",)),
     "sqlserver": ("host", "sqlserver_host", ("sqlserver_password",)),
     "snowflake": (

{datacontract_cli-1.2.2 → datacontract_cli-1.2.4}/datacontract/cli.py

@@ -15,7 +15,7 @@ from rich.markup import escape
 from typer.core import TyperGroup
 from typing_extensions import Annotated
 
-from datacontract.config import Config, set_cli_config
+from datacontract.config import Config, cli_config, set_cli_config
 from datacontract.output.output_format import OutputFormat
 
 console = Console()
@@ -31,6 +31,23 @@ inline_references_option = Annotated[
     ),
 ]
 
+custom_quality_checks_option = Annotated[
+    Optional[Path],
+    typer.Option(
+        metavar="DIR",
+        help="Folder with the custom quality checks the contract's quality rules use, one YAML file per check. "
+        "Defaults to DATACONTRACT_CUSTOM_QUALITY_CHECKS.",
+    ),
+]
+
+
+def config_with_custom_quality_checks(custom_quality_checks: Optional[Path]) -> Config | None:
+    """The --config-file config, with the --custom-quality-checks folder if one was given."""
+    config = cli_config()
+    if custom_quality_checks is None:
+        return config
+    return Config.resolve(config).model_copy(update={"custom_quality_checks": str(custom_quality_checks)})
+
 
 # Order in which top-level commands appear in `datacontract --help` (cf. README.md)
 COMMAND_ORDER = [
@@ -130,6 +147,8 @@ app = typer.Typer(
     cls=OrderedCommandsWithMigrationHints,
     no_args_is_help=True,
     add_completion=False,
+    # the locals of a --debug traceback can hold credentials
+    pretty_exceptions_show_locals=False,
     help="CLI to manage data contracts. Documentation: https://docs.datacontract.com",
     epilog="Read the full documentation at https://docs.datacontract.com",
 )

{datacontract_cli-1.2.2 → datacontract_cli-1.2.4}/datacontract/command_ci.py

@@ -10,14 +10,15 @@ from datacontract.cli import (
     _print_logs,
     _print_publish_failure,
     app,
+    config_with_custom_quality_checks,
     console,
+    custom_quality_checks_option,
     debug_option,
     enable_debug_logging,
     inline_references_option,
     resolve_output_format,
     validate_publish_url,
 )
-from datacontract.config import cli_config
 from datacontract.data_contract import DataContract
 from datacontract.output.ci_output import write_ci_output, write_ci_summary, write_json_results
 from datacontract.output.output_format import OutputFormat
@@ -80,6 +81,7 @@ def ci(
         bool,
         typer.Option(help="SSL verification when publishing the data contract."),
     ] = True,
+    custom_quality_checks: custom_quality_checks_option = None,
     inline_references: inline_references_option = True,
     debug: debug_option = None,
 ):
@@ -104,6 +106,7 @@ def ci(
     # Plain text output for CI logs; --json sends human output to stderr.
     out = Console(stderr=True, no_color=True) if json_output else Console(no_color=True)
 
+    config = config_with_custom_quality_checks(custom_quality_checks)
     results = []
     fail_results = {
         "warning": {"warning", "failed", "error"},
@@ -115,7 +118,7 @@ def ci(
     for location in locations:
         out.print(f"Testing {location}")
         run = DataContract(
-            config=cli_config(),
+            config=config,
             data_contract_file=location,
             schema_location=schema,
             publish_url=publish,

{datacontract_cli-1.2.2 → datacontract_cli-1.2.4}/datacontract/command_edit.py

@@ -336,7 +336,7 @@ def edit(
     The server also acts as the editor's test runner: "Run test" in the editor executes
     the data contract tests locally against the servers defined in the data contract.
     Credentials for the data sources must be provided as environment variables, see
-    https://cli.datacontract.com/#test
+    https://docs.datacontract.com/testing
     """
     enable_debug_logging(debug)
 

{datacontract_cli-1.2.2 → datacontract_cli-1.2.4}/datacontract/command_export.py

@@ -306,6 +306,24 @@ def export_jsonschema(
     _export(ExportFormat.jsonschema, location, output, server, schema_name, schema, inline_references=inline_references)
 
 
+@export_app.command(
+    name="xsd",
+    epilog="Example: datacontract export xsd datacontract.yaml --output schema.xsd",
+)
+def export_xsd(
+    location: location_arg = "datacontract.yaml",
+    output: output_option = None,
+    server: server_option = None,
+    schema_name: schema_name_option = "all",
+    schema: schema_option = None,
+    inline_references: inline_references_option = True,
+    debug: debug_option = None,
+):
+    """Export a data contract to an XML Schema (XSD)."""
+    enable_debug_logging(debug)
+    _export(ExportFormat.xsd, location, output, server, schema_name, schema, inline_references=inline_references)
+
+
 @export_app.command(
     name="pydantic-model",
     epilog="Example: datacontract export pydantic-model datacontract.yaml --output models.py",

{datacontract_cli-1.2.2 → datacontract_cli-1.2.4}/datacontract/command_import.py

@@ -316,6 +316,26 @@ def import_jsonschema(
     _write_result(result, output)
 
 
+@import_app.command(
+    name="xsd",
+    epilog="Example: datacontract import xsd --source schema.xsd --output datacontract.yaml",
+)
+def import_xsd(
+    source: Annotated[Optional[str], typer.Option(help="Path to the XML Schema (XSD) file.")] = None,
+    output: output_option = None,
+    schema: schema_option = None,
+    owner: owner_option = None,
+    id: id_option = None,
+    debug: debug_option = None,
+):
+    """Import a data contract from an XML Schema (XSD) file."""
+    enable_debug_logging(debug)
+    result = DataContract.import_from_source(
+        config=cli_config(), format="xsd", source=source, schema=schema, owner=owner, id=id
+    )
+    _write_result(result, output)
+
+
 @import_app.command(
     name="json",
     epilog="Example: datacontract import json --source data.json --output datacontract.yaml",
@@ -835,6 +855,70 @@ def import_mysql(
     _write_result(result, output)
 
 
+@import_app.command(
+    name="clickhouse",
+    epilog="Example: datacontract import clickhouse --source localhost --database default --output datacontract.yaml",
+)
+def import_clickhouse(
+    source: Annotated[Optional[str], typer.Option(help="The host of the ClickHouse server.")] = None,
+    port: Annotated[Optional[int], typer.Option(help="The ClickHouse HTTP port (default 8123).")] = None,
+    database: database_option = None,
+    table: Annotated[
+        Optional[List[str]],
+        typer.Option(help="Name of a table to import (repeat for multiple tables, omit for all tables)."),
+    ] = None,
+    output: output_option = None,
+    owner: owner_option = None,
+    id: id_option = None,
+    debug: debug_option = None,
+):
+    """Import a data contract from a ClickHouse database."""
+    enable_debug_logging(debug)
+    result = DataContract.import_from_source(
+        config=cli_config(),
+        format="clickhouse",
+        source=source,
+        port=port,
+        database=database,
+        clickhouse_table=table,
+        owner=owner,
+        id=id,
+    )
+    _write_result(result, output)
+
+
+@import_app.command(
+    name="hive",
+    epilog="Example: datacontract import hive --source localhost --database default --output datacontract.yaml",
+)
+def import_hive(
+    source: Annotated[Optional[str], typer.Option(help="The host of the HiveServer2.")] = None,
+    port: Annotated[Optional[int], typer.Option(help="The HiveServer2 port (default 10000).")] = None,
+    database: database_option = None,
+    table: Annotated[
+        Optional[List[str]],
+        typer.Option(help="Name of a table to import (repeat for multiple tables, omit for all tables)."),
+    ] = None,
+    output: output_option = None,
+    owner: owner_option = None,
+    id: id_option = None,
+    debug: debug_option = None,
+):
+    """Import a data contract from a Hive database."""
+    enable_debug_logging(debug)
+    result = DataContract.import_from_source(
+        config=cli_config(),
+        format="hive",
+        source=source,
+        port=port,
+        database=database,
+        hive_table=table,
+        owner=owner,
+        id=id,
+    )
+    _write_result(result, output)
+
+
 @import_app.command(
     name="s3",
     epilog="Example: datacontract import s3 --source s3://my-bucket/orders/*.json --output datacontract.yaml",
@@ -958,3 +1042,29 @@ def import_odata(
         id=id,
     )
     _write_result(result, output)
+
+
+@import_app.command(
+    name="openapi",
+    epilog="Example: datacontract import openapi --source openapi.yaml --operation listOrders --output datacontract.yaml",
+)
+def import_openapi(
+    source: Annotated[Optional[str], typer.Option(help="Path to the OpenAPI 3.x document (YAML or JSON).")] = None,
+    operation: Annotated[
+        Optional[str],
+        typer.Option(
+            help="The GET operation to import, by operationId or path (e.g. listOrders or /orders). "
+            "Required when the document has more than one GET operation."
+        ),
+    ] = None,
+    output: output_option = None,
+    owner: owner_option = None,
+    id: id_option = None,
+    debug: debug_option = None,
+):
+    """Import a data contract from the response of a GET operation in an OpenAPI 3.x document."""
+    enable_debug_logging(debug)
+    result = DataContract.import_from_source(
+        config=cli_config(), format="openapi", source=source, openapi_operation=operation, owner=owner, id=id
+    )
+    _write_result(result, output)

{datacontract_cli-1.2.2 → datacontract_cli-1.2.4}/datacontract/command_test.py

@@ -10,7 +10,9 @@ from datacontract.cli import (
     _print_logs,
     _print_publish_failure,
     app,
+    config_with_custom_quality_checks,
     console,
+    custom_quality_checks_option,
     debug_option,
     enable_debug_logging,
     inline_references_option,
@@ -200,6 +202,7 @@ def test(
         bool,
         typer.Option(help="SSL verification when publishing the data contract."),
     ] = True,
+    custom_quality_checks: custom_quality_checks_option = None,
     inline_references: inline_references_option = True,
     debug: debug_option = None,
 ):
@@ -231,7 +234,7 @@ def test(
     if server == "all":
         server = None
     run = DataContract(
-        config=cli_config(),
+        config=config_with_custom_quality_checks(custom_quality_checks),
         data_contract_file=location,
         schema_location=schema,
         publish_test_results=publish_test_results,