datacontract-cli 1.0.0__tar.gz → 1.0.2__tar.gz

datacontract_cli-1.0.2/MANIFEST.in

@@ -0,0 +1,4 @@
+include datacontract/templates/style/output.css
+recursive-include datacontract/templates/ **/*.html
+recursive-include datacontract/schemas/ **/*.json **/*.yaml
+recursive-include datacontract/editor_assets/ *

{datacontract_cli-1.0.0/datacontract_cli.egg-info → datacontract_cli-1.0.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datacontract-cli
-Version: 1.0.0
+Version: 1.0.2
 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@innoq.com>, Stefan Negele <stefan.negele@innoq.com>, Simon Harrer <simon.harrer@innoq.com>
 License-Expression: MIT
@@ -39,7 +39,7 @@ Requires-Dist: openpyxl<4.0.0,>=3.1.5; extra == "excel"
 Provides-Extra: databricks
 Requires-Dist: ibis-framework[databricks,pyspark]<13.0.0,>=10.0.0; extra == "databricks"
 Requires-Dist: databricks-sql-connector<4.3.0,>=3.7.0; extra == "databricks"
-Requires-Dist: databricks-sdk<0.112.0; extra == "databricks"
+Requires-Dist: databricks-sdk<0.116.0; extra == "databricks"
 Requires-Dist: pyspark<5.0.0,>=3.5.0; extra == "databricks"
 Provides-Extra: iceberg
 Requires-Dist: pyiceberg==0.11.1; extra == "iceberg"
@@ -51,8 +51,10 @@ Provides-Extra: mysql
 Requires-Dist: datacontract-cli[duckdb]; extra == "mysql"
 Provides-Extra: postgres
 Requires-Dist: ibis-framework[postgres]<13.0.0,>=10.0.0; extra == "postgres"
+Requires-Dist: psycopg[binary]<4.0,>=3.1; extra == "postgres"
 Provides-Extra: redshift
 Requires-Dist: ibis-framework[postgres]<13.0.0,>=10.0.0; extra == "redshift"
+Requires-Dist: psycopg[binary]<4.0,>=3.1; extra == "redshift"
 Provides-Extra: s3
 Requires-Dist: s3fs<2027.0.0,>=2025.2.0; extra == "s3"
 Requires-Dist: duckdb-extension-httpfs<1.6.0,>=1.5.0; extra == "s3"
@@ -64,7 +66,7 @@ Provides-Extra: azure
 Requires-Dist: datacontract-cli[duckdb]; extra == "azure"
 Requires-Dist: duckdb-extension-azure<1.6.0,>=1.5.0; extra == "azure"
 Provides-Extra: snowflake
-Requires-Dist: snowflake-connector-python[pandas]<4.6,>=3.6; extra == "snowflake"
+Requires-Dist: snowflake-connector-python[pandas]<4.7,>=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"
@@ -87,7 +89,7 @@ Provides-Extra: rdf
 Requires-Dist: rdflib==7.6.0; extra == "rdf"
 Provides-Extra: api
 Requires-Dist: fastapi<0.137.0,>=0.115.0; extra == "api"
-Requires-Dist: uvicorn<0.49.0,>=0.44.0; extra == "api"
+Requires-Dist: uvicorn<0.50.0,>=0.44.0; extra == "api"
 Provides-Extra: protobuf
 Requires-Dist: proto-schema-parser<3.0,>=1.0; extra == "protobuf"
 Provides-Extra: all
@@ -97,7 +99,7 @@ Requires-Dist: datacontract-cli[all]; extra == "dev"
 Requires-Dist: httpx==0.28.1; extra == "dev"
 Requires-Dist: kafka-python; extra == "dev"
 Requires-Dist: minio==7.2.20; extra == "dev"
-Requires-Dist: moto==5.2.1; extra == "dev"
+Requires-Dist: moto==5.2.2; extra == "dev"
 Requires-Dist: pandas>=2.1.0; extra == "dev"
 Requires-Dist: pre-commit<4.7.0,>=3.7.1; extra == "dev"
 Requires-Dist: pytest; extra == "dev"
@@ -105,7 +107,7 @@ Requires-Dist: pytest-xdist; extra == "dev"
 Requires-Dist: pymssql==2.3.13; extra == "dev"
 Requires-Dist: psycopg2-binary<3.0,>=2.9; extra == "dev"
 Requires-Dist: mysql-connector-python<9.7.0,>=8.0.30; extra == "dev"
-Requires-Dist: ruff==0.15.14; extra == "dev"
+Requires-Dist: ruff==0.15.16; extra == "dev"
 Requires-Dist: testcontainers[kafka,minio,mssql,mysql,postgres]==4.14.2; extra == "dev"
 Requires-Dist: trino==0.337.0; extra == "dev"
 Dynamic: license-file
@@ -229,6 +231,9 @@ $ datacontract export html --output orders-v1.odcs.html https://datacontract.com
 # create a new data contract from example and write it to odcs.yaml
 $ datacontract init odcs.yaml
 
+# edit the data contract in the Data Contract Editor (web UI)
+$ datacontract edit odcs.yaml
+
 # lint the odcs.yaml and stop after the first validation error (default).
 $ datacontract lint odcs.yaml
 
@@ -385,6 +390,7 @@ A list of available extras:
 Commands
 
 - [init](#init)
+- [edit](#edit)
 - [lint](#lint)
 - [changelog](#changelog)
 - [test](#test)
@@ -417,6 +423,52 @@ Usage: datacontract init [OPTIONS] [LOCATION]
  Example: datacontract init datacontract.yaml
 ```
 
+### edit
+```
+Usage: datacontract edit [OPTIONS] [LOCATION]                                                      
+                                                                                                    
+ Edit a data contract file in the Data Contract Editor (web UI).                                    
+                                                                                                    
+ Starts a local web server that opens the Data Contract Editor for the given file.                  
+ The editor is bundled with the CLI, so no internet access is required.                             
+ Saving in the editor writes directly back to the local file.                                       
+ If a URL is given, you are asked whether to download a local copy, which is then edited.           
+ 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                                                                 
+                                                                                                    
+╭─ Arguments ──────────────────────────────────────────────────────────────────────────────────────╮
+│   location      [LOCATION]  The path of the data contract yaml to edit. If the file does not     │
+│                             exist, you are asked whether to initialize a new data contract. If a │
+│                             URL is given, you are asked whether to download a local copy to      │
+│                             edit.                                                                │
+│                             [default: datacontract.yaml]                                         │
+╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
+╭─ Options ────────────────────────────────────────────────────────────────────────────────────────╮
+│ --port                               INTEGER  Bind socket to this port. [default: 4243]          │
+│ --host                               TEXT     Bind socket to this host. Hint: For running in     │
+│                                               docker, set it to 0.0.0.0                          │
+│                                               [default: 127.0.0.1]                               │
+│ --editor-version                     TEXT     Version of the datacontract-editor npm package to  │
+│                                               load from the CDN, e.g. '0.1.9' or 'latest'. By    │
+│                                               default, the editor version bundled with the CLI   │
+│                                               is used (works offline).                           │
+│ --editor-assets-url                  TEXT     Base URL to load the Data Contract Editor assets   │
+│                                               (JS/CSS) from, e.g. a self-hosted editor build.    │
+│                                               Takes precedence over --editor-version.            │
+│ --open                 --no-open              Open the editor in the default browser.            │
+│                                               [default: open]                                    │
+│ --debug                --no-debug             Enable debug logging                               │
+│ --help                                        Show this message and exit.                        │
+╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
+                                                                                                    
+ Example: datacontract edit datacontract.yaml
+```
+
+Requires the `api` extra (`pip install 'datacontract-cli[api]'`).
+The [Data Contract Editor](https://github.com/datacontract/datacontract-editor) assets are loaded from a CDN by default; use `--editor-version` to pin a specific editor version or `--editor-assets-url` to point to a self-hosted build.
+
 ### lint
 ```
 Usage: datacontract lint [OPTIONS] [LOCATION]                                                      
@@ -437,7 +489,8 @@ Usage: datacontract lint [OPTIONS] [LOCATION]
 │                                                                If no path is provided, the       │
 │                                                                output will be printed to stdout. │
 │ --output-format                                  [json|junit]  The target format for the test    │
-│                                                                results.                          │
+│                                                                results. Accepted values: json,   │
+│                                                                junit.                            │
 │ --all-errors                                                   Report all JSON Schema validation │
 │                                                                errors instead of stopping after  │
 │                                                                the first one.                    │
@@ -497,59 +550,76 @@ Usage: datacontract test [OPTIONS] [LOCATION]
 │                             [default: datacontract.yaml]                                         │
 ╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
 ╭─ Options ────────────────────────────────────────────────────────────────────────────────────────╮
-│ --json-schema                                          TEXT          The location (url or path)  │
-│                                                                      of the ODCS JSON Schema     │
-│ --server                                               TEXT          The server configuration to │
-│                                                                      run the schema and quality  │
-│                                                                      tests. Use the key of the   │
-│                                                                      server object in the data   │
-│                                                                      contract yaml file to refer │
-│                                                                      to a server, e.g.,          │
-│                                                                      `production`, or `all` for  │
-│                                                                      all servers (default).      │
-│                                                                      [default: all]              │
-│ --schema-name                                          TEXT          Which schema to test, e.g., │
-│                                                                      `orders`, or `all` for all  │
-│                                                                      schemas (default).          │
-│                                                                      [default: all]              │
-│ --publish-test-results    --no-publish-test-results                  Deprecated. Use publish     │
-│                                                                      parameter. Publish the      │
-│                                                                      results after the test      │
-│                                                                      [default:                   │
-│                                                                      no-publish-test-results]    │
-│ --publish                                              TEXT          The url to publish the      │
-│                                                                      results after the test.     │
-│ --output                                               PATH          Specify the file path where │
-│                                                                      the test results should be  │
-│                                                                      written to (e.g.,           │
-│                                                                      './test-results/TEST-datac… │
-│ --output-format                                        [json|junit]  The target format for the   │
-│                                                                      test results.               │
-│ --checks                                               TEXT          Comma-separated list of     │
-│                                                                      check categories to run     │
-│                                                                      (available: schema,         │
-│                                                                      quality, servicelevel,      │
-│                                                                      custom). Omit to enable     │
-│                                                                      all.                        │
-│ --logs                    --no-logs                                  Print logs                  │
-│                                                                      [default: no-logs]          │
-│ --ssl-verification        --no-ssl-verification                      SSL verification when       │
-│                                                                      publishing the data         │
-│                                                                      contract.                   │
-│                                                                      [default: ssl-verification] │
-│ --inline-references       --no-inline-references                     Resolve external references │
-│                                                                      (currently:                 │
-│                                                                      authoritativeDefinitions[t… │
-│                                                                      in {definition,             │
-│                                                                      semantics}]) in the         │
-│                                                                      contract and inline the     │
-│                                                                      fetched content from the    │
-│                                                                      configured entropy-data     │
-│                                                                      host.                       │
-│                                                                      [default:                   │
-│                                                                      inline-references]          │
-│ --debug                   --no-debug                                 Enable debug logging        │
-│ --help                                                               Show this message and exit. │
+│ --json-schema                                            TEXT          The location (url or      │
+│                                                                        path) of the ODCS JSON    │
+│                                                                        Schema                    │
+│ --server                                                 TEXT          The server configuration  │
+│                                                                        to run the schema and     │
+│                                                                        quality tests. Use the    │
+│                                                                        key of the server object  │
+│                                                                        in the data contract yaml │
+│                                                                        file to refer to a        │
+│                                                                        server, e.g.,             │
+│                                                                        `production`, or `all`    │
+│                                                                        for all servers           │
+│                                                                        (default).                │
+│                                                                        [default: all]            │
+│ --schema-name                                            TEXT          Which schema to test,     │
+│                                                                        e.g., `orders`, or `all`  │
+│                                                                        for all schemas           │
+│                                                                        (default).                │
+│                                                                        [default: all]            │
+│ --publish-test-results      --no-publish-test-results                  Deprecated. Use publish   │
+│                                                                        parameter. Publish the    │
+│                                                                        results after the test    │
+│                                                                        [default:                 │
+│                                                                        no-publish-test-results]  │
+│ --publish                                                TEXT          The url to publish the    │
+│                                                                        results after the test.   │
+│ --output                                                 PATH          Specify the file path     │
+│                                                                        where the test results    │
+│                                                                        should be written to      │
+│                                                                        (e.g.,                    │
+│                                                                        './test-results/TEST-dat… │
+│ --output-format                                          [json|junit]  The target format for the │
+│                                                                        test results. Accepted    │
+│                                                                        values: json, junit.      │
+│ --checks                                                 TEXT          Comma-separated list of   │
+│                                                                        check categories to run   │
+│                                                                        (available: schema,       │
+│                                                                        quality, servicelevel,    │
+│                                                                        custom). Omit to enable   │
+│                                                                        all.                      │
+│ --include-failed-samples    --no-include-failed-samp…                  Collect a small sample of │
+│                                                                        rows that failed each     │
+│                                                                        missing/invalid/duplicate │
+│                                                                        check (identifier +       │
+│                                                                        offending columns;        │
+│                                                                        sensitive columns         │
+│                                                                        omitted). Off by default. │
+│                                                                        [default:                 │
+│                                                                        no-include-failed-sample… │
+│ --logs                      --no-logs                                  Print logs                │
+│                                                                        [default: no-logs]        │
+│ --ssl-verification          --no-ssl-verification                      SSL verification when     │
+│                                                                        publishing the data       │
+│                                                                        contract.                 │
+│                                                                        [default:                 │
+│                                                                        ssl-verification]         │
+│ --inline-references         --no-inline-references                     Resolve external          │
+│                                                                        references (currently:    │
+│                                                                        authoritativeDefinitions… │
+│                                                                        in {definition,           │
+│                                                                        semantics}]) in the       │
+│                                                                        contract and inline the   │
+│                                                                        fetched content from the  │
+│                                                                        configured entropy-data   │
+│                                                                        host.                     │
+│                                                                        [default:                 │
+│                                                                        inline-references]        │
+│ --debug                     --no-debug                                 Enable debug logging      │
+│ --help                                                                 Show this message and     │
+│                                                                        exit.                     │
 ╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
                                                                                                     
  Example: datacontract test datacontract.yaml --server production
@@ -571,6 +641,14 @@ Internally, it connects with DuckDB, Spark, or a native connection and executes
 The `server` block in the datacontract.yaml is used to set up the connection.
 In addition, credentials, such as username and passwords, are provided with environment variables.
 
+Environment variables are also loaded from a `.env` file in the current working directory (or the nearest parent directory containing one, so you can run the CLI from a subfolder of your project). Already-set environment variables take precedence over values from the `.env` file.
+
+```bash
+# .env
+DATACONTRACT_POSTGRES_USERNAME=postgres
+DATACONTRACT_POSTGRES_PASSWORD=postgres
+```
+
 Feel free to create an [issue](https://github.com/datacontract/datacontract-cli/issues), if you need support for additional types and formats.
 
 <details markdown="1">
@@ -718,6 +796,7 @@ models:
 |----------------------------------------------|---------------------------|---------------------------------------------------------|
 | `DATACONTRACT_BIGQUERY_ACCOUNT_INFO_JSON_PATH` | `~/service-access-key.json` | Service Account key JSON file. If not set, ADC/WIF is used automatically. |
 | `DATACONTRACT_BIGQUERY_IMPERSONATION_ACCOUNT` | `sa@project.iam.gserviceaccount.com` | Optional. Service account to impersonate. Works with both key file and ADC auth. |
+| `DATACONTRACT_BIGQUERY_BILLING_PROJECT` | `my-compute-project` | Optional. Google Cloud project ID to bill query jobs to. Use when the data lives in an external project and you want charges routed to your own project. Requires `bigquery.jobUser` on the billing project and `bigquery.dataViewer` on the data project. |
 
 </details>
 
@@ -1003,17 +1082,22 @@ models:
 ```
 
 ##### Environment Variables
-Any `DATACONTRACT_SNOWFLAKE_`-prefixed variable is passed (lowercased, prefix stripped) as a connection parameter to the [snowflake-connector-python](https://docs.snowflake.com/en/developer-guide/python-connector/python-connector-api#connect) driver that the ibis Snowflake backend uses.
+Any `DATACONTRACT_SNOWFLAKE_`-prefixed variable is passed (lowercased, prefix stripped) as a connection parameter to the [snowflake-connector-python](https://docs.snowflake.com/en/developer-guide/python-connector/python-connector-api#connect) driver.
+Depending on the `authenticator` mode required by your Snowflake workspace, please set your environment variables accordingly.
 For example:
 
-| Connection parameter | Environment Variable                        |
-|----------------------|---------------------------------------------|
-| `user`               | `DATACONTRACT_SNOWFLAKE_USERNAME` or `DATACONTRACT_SNOWFLAKE_USER` |
-| `password`           | `DATACONTRACT_SNOWFLAKE_PASSWORD`           |
-| `warehouse`          | `DATACONTRACT_SNOWFLAKE_WAREHOUSE`          |
-| `role`               | `DATACONTRACT_SNOWFLAKE_ROLE`               |
+| Soda parameter           | Environment Variable                            |
+|--------------------------|-------------------------------------------------|
+| `username`               | `DATACONTRACT_SNOWFLAKE_USERNAME`               |
+| `password`               | `DATACONTRACT_SNOWFLAKE_PASSWORD`               |
+| `warehouse`              | `DATACONTRACT_SNOWFLAKE_WAREHOUSE`              |
+| `role`                   | `DATACONTRACT_SNOWFLAKE_ROLE`                   |
+| `connection_timeout`     | `DATACONTRACT_SNOWFLAKE_CONNECTION_TIMEOUT`     |
+| `authenticator`          | `DATACONTRACT_SNOWFLAKE_AUTHENTICATOR`          |
+| `private_key`            | `DATACONTRACT_SNOWFLAKE_PRIVATE_KEY`            |
+| `private_key_passphrase` | `DATACONTRACT_SNOWFLAKE_PRIVATE_KEY_PASSPHRASE` |
+| `private_key_path`       | `DATACONTRACT_SNOWFLAKE_PRIVATE_KEY_PATH`       |
 
-(`DATACONTRACT_SNOWFLAKE_USERNAME` is accepted as an alias for the connector's `user` parameter.)
 
 Beware, that parameters:
 * `account`
@@ -1419,6 +1503,8 @@ Usage: datacontract ci [OPTIONS] [LOCATIONS]...
 │                                                                         './test-results/TEST-da… │
 │ --output-format                                  [json|junit]           The target format for    │
 │                                                                         the test results.        │
+│                                                                         Accepted values: json,   │
+│                                                                         junit.                   │
 │ --logs                 --no-logs                                        Print logs               │
 │                                                                         [default: no-logs]       │
 │ --json                                                                  Print test results as    │
@@ -1931,6 +2017,7 @@ Usage: datacontract import [OPTIONS] COMMAND [ARGS]...
 │ spark       Import a data contract from a Spark schema.                                          │
 │ iceberg     Import a data contract from an Iceberg schema.                                       │
 │ excel       Import a data contract from an Excel file.                                           │
+│ snowflake   Import a data contract from a Snowflake workspace.                                   │
 ╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
                                                                                                     
  Example: datacontract import sql --source ddl.sql --dialect postgres --output datacontract.yaml
@@ -2159,6 +2246,21 @@ datacontract import protobuf --source "test.proto"
 
 </details>
 
+<details markdown="1">
+<summary><strong>snowflake</strong></summary>
+
+Importing from snowflake schema. Specify snowflake workspace account in `source` parameter, database name `database` and schema in `schema`. 
+Multiple authentification are supported, 
+login/password using the `DATACONTRACT_SNOWFLAKE_ ...` test environement variable are setup,
+MFA using external browser is selected when `DATACONTRACT_SNOWFLAKE_PASSWORD` is missing
+TOML file authentification using the default profile when `SNOWFLAKE_DEFAULT_CONNECTION_NAME` environment variable is defined
+
+Example:
+
+```bash
+datacontract import snowflake --source account.canada-central.azure --database databaseName --schema schemaName
+```
+</details>
 
 ### catalog
 ```