datacontract-cli 1.1.3__tar.gz → 1.2.1__tar.gz

{datacontract_cli-1.1.3 → datacontract_cli-1.2.1}/MANIFEST.in

@@ -1,5 +1,5 @@
 include datacontract/templates/style/output.css
-include datacontract/templates/excel/odcs-template.xlsx
+include datacontract/templates/excel/*.xlsx
 recursive-include datacontract/templates/ **/*.html
 recursive-include datacontract/schemas/ **/*.json **/*.yaml
 recursive-include datacontract/editor_assets/ *

{datacontract_cli-1.1.3/datacontract_cli.egg-info → datacontract_cli-1.2.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datacontract-cli
-Version: 1.1.3
+Version: 1.2.1
 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
@@ -40,20 +40,20 @@ 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<31.0.0,>=26.6.0
+Requires-Dist: sqlglot<30.18,>=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
 Requires-Dist: jinja_partials<1.0.0,>=0.2.1
 Requires-Dist: datacontract-specification<2.0.0,>=1.2.3
-Requires-Dist: open-data-contract-standard<3.2.0,>=3.1.2
+Requires-Dist: open-data-contract-standard<3.3.0,>=3.2.0
 Requires-Dist: deepdiff<10.0.0,>=6.0.0
 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: csv
-Requires-Dist: pandas>=2.0.0; extra == "csv"
+Requires-Dist: datacontract-cli[duckdb]; extra == "csv"
 Provides-Extra: excel
 Requires-Dist: openpyxl<4.0.0,>=3.1.5; extra == "excel"
 Provides-Extra: dataframe
@@ -66,13 +66,14 @@ 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<4.5.0,>=3.7.0; extra == "databricks"
-Requires-Dist: databricks-sdk<0.134.0; 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: packaging<27.0,>=21.3; extra == "databricks"
 Provides-Extra: databricks-runtime
 Requires-Dist: datacontract-cli[databricks]; extra == "databricks-runtime"
 Provides-Extra: iceberg
-Requires-Dist: pyiceberg==0.11.1; extra == "iceberg"
+Requires-Dist: pyiceberg[pyarrow,rest-sigv4]==0.12.0; extra == "iceberg"
+Requires-Dist: datacontract-cli[duckdb]; extra == "iceberg"
 Provides-Extra: kafka
 Requires-Dist: datacontract-cli[duckdb,parquet]; extra == "kafka"
 Requires-Dist: confluent-kafka<3.0.0,>=2.6.0; extra == "kafka"
@@ -111,6 +112,13 @@ Requires-Dist: packaging<27.0,>=21.3; extra == "oracle"
 Provides-Extra: athena
 Requires-Dist: ibis-framework[athena]<13.0.0,>=10.0.0; extra == "athena"
 Requires-Dist: packaging<27.0,>=21.3; extra == "athena"
+Provides-Extra: hana
+Requires-Dist: hdbcli<3.0.0,>=2.20.0; extra == "hana"
+Provides-Extra: exasol
+Requires-Dist: ibis-framework[exasol]<13.0.0,>=10.0.0; extra == "exasol"
+Requires-Dist: pyexasol>=1.1.0; extra == "exasol"
+Requires-Dist: packaging<27.0,>=21.3; extra == "exasol"
+Requires-Dist: sqlglot>=26.31.0; extra == "exasol"
 Provides-Extra: trino
 Requires-Dist: ibis-framework[trino]<13.0.0,>=10.0.0; extra == "trino"
 Requires-Dist: packaging<27.0,>=21.3; extra == "trino"
@@ -128,11 +136,11 @@ 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<0.53.0,>=0.44.0; extra == "api"
+Requires-Dist: uvicorn<0.54.0,>=0.44.0; extra == "api"
 Provides-Extra: protobuf
 Requires-Dist: proto-schema-parser<3.0,>=1.0; extra == "protobuf"
 Provides-Extra: all
-Requires-Dist: datacontract-cli[api,athena,avro,azure,bigquery,csv,databricks,dataframe,dbml,duckdb,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,csv,databricks,dataframe,dbml,duckdb,exasol,excel,gcs,iceberg,impala,kafka,mysql,oracle,parquet,postgres,protobuf,rdf,redshift,s3,snowflake,sqlserver,trino]; extra == "all"
 Provides-Extra: dev
 Requires-Dist: datacontract-cli[all]; extra == "dev"
 Requires-Dist: httpx==0.28.1; extra == "dev"
@@ -145,10 +153,10 @@ 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==2.3.13; extra == "dev"
+Requires-Dist: pymssql==2.4.1; 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==0.16.5; extra == "dev"
+Requires-Dist: ruff==0.16.8; 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
@@ -411,7 +419,7 @@ Released images are signed with [cosign](https://docs.sigstore.dev/cosign/signin
 ## Optional Dependencies (Extras)
 
 The CLI tool defines several optional dependencies (also known as extras) that can be installed for using with specific servers types.
-With _all_, all server dependencies are included.
+With _all_, all server dependencies except `hana` are included.
 
 ```bash
 uv tool install --python python3.11 --upgrade 'datacontract-cli[all]'
@@ -419,35 +427,35 @@ uv tool install --python python3.11 --upgrade 'datacontract-cli[all]'
 
 A list of available extras:
 
-| Dependency                               | Installation Command                       |
-|------------------------------------------|--------------------------------------------|
-| Amazon Athena                            | `pip install datacontract-cli[athena]`     |
-| Avro Support                             | `pip install datacontract-cli[avro]`       |
-| Azure Integration                        | `pip install datacontract-cli[azure]`      |
-| Google BigQuery                          | `pip install datacontract-cli[bigquery]`   |
-| CSV                                      | `pip install datacontract-cli[csv]`        |
-| Databricks Integration                   | `pip install datacontract-cli[databricks]` |
-| Databricks Runtime                       | `pip install datacontract-cli[databricks]` (also inside Databricks, using the cluster's own Spark session) |
-| DataFrame (Spark)                        | `pip install datacontract-cli[dataframe]` (PySpark not included — you supply the Spark session) |
-| DBML                                     | `pip install datacontract-cli[dbml]`       |
-| DuckDB (local/S3/GCS/Azure file testing) | `pip install datacontract-cli[duckdb]`     |
-| Excel                                    | `pip install datacontract-cli[excel]`      |
-| GCS Integration                          | `pip install datacontract-cli[gcs]`        |
-| Iceberg                                  | `pip install datacontract-cli[iceberg]`    |
-| Impala                                   | `pip install datacontract-cli[impala]`     |
-| Kafka Integration                        | `pip install datacontract-cli[kafka]`      |
-| MySQL Integration                        | `pip install datacontract-cli[mysql]`      |
-| Oracle                                   | `pip install datacontract-cli[oracle]`     |
-| Parquet                                  | `pip install datacontract-cli[parquet]`    |
-| PostgreSQL Integration                   | `pip install datacontract-cli[postgres]`   |
-| protobuf                                 | `pip install datacontract-cli[protobuf]`   |
-| RDF                                      | `pip install datacontract-cli[rdf]`        |
-| Amazon Redshift                          | `pip install datacontract-cli[redshift]`   |
-| S3 Integration                           | `pip install datacontract-cli[s3]`         |
-| Snowflake Integration                    | `pip install datacontract-cli[snowflake]`  |
-| Microsoft SQL Server                     | `pip install datacontract-cli[sqlserver]`  |
-| Trino                                    | `pip install datacontract-cli[trino]`      |
-| API (run as web server)                  | `pip install datacontract-cli[api]`        |
+| Dependency | Installation command |
+|---|---|
+| API (run as web server) | `pip install datacontract-cli[api]` |
+| Amazon Athena | `pip install datacontract-cli[athena]` |
+| Avro | `pip install datacontract-cli[avro]` |
+| Azure | `pip install datacontract-cli[azure]` |
+| Google BigQuery | `pip install datacontract-cli[bigquery]` |
+| Databricks | `pip install datacontract-cli[databricks]` (also inside a Databricks Runtime, using the cluster's own Spark session) |
+| DataFrame (Spark) | `pip install datacontract-cli[dataframe]` (PySpark not included — you supply the Spark session) |
+| DBML | `pip install datacontract-cli[dbml]` |
+| DuckDB (local file, CSV import and API response testing) | `pip install datacontract-cli[duckdb]` |
+| Exasol | `pip install datacontract-cli[exasol]` |
+| Excel | `pip install datacontract-cli[excel]` |
+| GCS | `pip install datacontract-cli[gcs]` |
+| SAP HANA / Datasphere | `pip install datacontract-cli[hana]` (not part of `all`: `hdbcli` is proprietary) |
+| Apache Iceberg (schema import and export, REST catalog testing) | `pip install datacontract-cli[iceberg]` |
+| Impala | `pip install datacontract-cli[impala]` |
+| Kafka | `pip install datacontract-cli[kafka]` |
+| MySQL | `pip install datacontract-cli[mysql]` |
+| Oracle | `pip install datacontract-cli[oracle]` |
+| Parquet | `pip install datacontract-cli[parquet]` |
+| PostgreSQL | `pip install datacontract-cli[postgres]` |
+| Protobuf | `pip install datacontract-cli[protobuf]` |
+| RDF | `pip install datacontract-cli[rdf]` |
+| Amazon Redshift | `pip install datacontract-cli[redshift]` |
+| S3 | `pip install datacontract-cli[s3]` |
+| Snowflake | `pip install datacontract-cli[snowflake]` |
+| Microsoft SQL Server | `pip install datacontract-cli[sqlserver]` |
+| Trino | `pip install datacontract-cli[trino]` |
 
 
 ## Documentation

{datacontract_cli-1.1.3 → datacontract_cli-1.2.1}/README.md

@@ -256,7 +256,7 @@ Released images are signed with [cosign](https://docs.sigstore.dev/cosign/signin
 ## Optional Dependencies (Extras)
 
 The CLI tool defines several optional dependencies (also known as extras) that can be installed for using with specific servers types.
-With _all_, all server dependencies are included.
+With _all_, all server dependencies except `hana` are included.
 
 ```bash
 uv tool install --python python3.11 --upgrade 'datacontract-cli[all]'
@@ -264,35 +264,35 @@ uv tool install --python python3.11 --upgrade 'datacontract-cli[all]'
 
 A list of available extras:
 
-| Dependency                               | Installation Command                       |
-|------------------------------------------|--------------------------------------------|
-| Amazon Athena                            | `pip install datacontract-cli[athena]`     |
-| Avro Support                             | `pip install datacontract-cli[avro]`       |
-| Azure Integration                        | `pip install datacontract-cli[azure]`      |
-| Google BigQuery                          | `pip install datacontract-cli[bigquery]`   |
-| CSV                                      | `pip install datacontract-cli[csv]`        |
-| Databricks Integration                   | `pip install datacontract-cli[databricks]` |
-| Databricks Runtime                       | `pip install datacontract-cli[databricks]` (also inside Databricks, using the cluster's own Spark session) |
-| DataFrame (Spark)                        | `pip install datacontract-cli[dataframe]` (PySpark not included — you supply the Spark session) |
-| DBML                                     | `pip install datacontract-cli[dbml]`       |
-| DuckDB (local/S3/GCS/Azure file testing) | `pip install datacontract-cli[duckdb]`     |
-| Excel                                    | `pip install datacontract-cli[excel]`      |
-| GCS Integration                          | `pip install datacontract-cli[gcs]`        |
-| Iceberg                                  | `pip install datacontract-cli[iceberg]`    |
-| Impala                                   | `pip install datacontract-cli[impala]`     |
-| Kafka Integration                        | `pip install datacontract-cli[kafka]`      |
-| MySQL Integration                        | `pip install datacontract-cli[mysql]`      |
-| Oracle                                   | `pip install datacontract-cli[oracle]`     |
-| Parquet                                  | `pip install datacontract-cli[parquet]`    |
-| PostgreSQL Integration                   | `pip install datacontract-cli[postgres]`   |
-| protobuf                                 | `pip install datacontract-cli[protobuf]`   |
-| RDF                                      | `pip install datacontract-cli[rdf]`        |
-| Amazon Redshift                          | `pip install datacontract-cli[redshift]`   |
-| S3 Integration                           | `pip install datacontract-cli[s3]`         |
-| Snowflake Integration                    | `pip install datacontract-cli[snowflake]`  |
-| Microsoft SQL Server                     | `pip install datacontract-cli[sqlserver]`  |
-| Trino                                    | `pip install datacontract-cli[trino]`      |
-| API (run as web server)                  | `pip install datacontract-cli[api]`        |
+| Dependency | Installation command |
+|---|---|
+| API (run as web server) | `pip install datacontract-cli[api]` |
+| Amazon Athena | `pip install datacontract-cli[athena]` |
+| Avro | `pip install datacontract-cli[avro]` |
+| Azure | `pip install datacontract-cli[azure]` |
+| Google BigQuery | `pip install datacontract-cli[bigquery]` |
+| Databricks | `pip install datacontract-cli[databricks]` (also inside a Databricks Runtime, using the cluster's own Spark session) |
+| DataFrame (Spark) | `pip install datacontract-cli[dataframe]` (PySpark not included — you supply the Spark session) |
+| DBML | `pip install datacontract-cli[dbml]` |
+| DuckDB (local file, CSV import and API response testing) | `pip install datacontract-cli[duckdb]` |
+| Exasol | `pip install datacontract-cli[exasol]` |
+| Excel | `pip install datacontract-cli[excel]` |
+| GCS | `pip install datacontract-cli[gcs]` |
+| SAP HANA / Datasphere | `pip install datacontract-cli[hana]` (not part of `all`: `hdbcli` is proprietary) |
+| Apache Iceberg (schema import and export, REST catalog testing) | `pip install datacontract-cli[iceberg]` |
+| Impala | `pip install datacontract-cli[impala]` |
+| Kafka | `pip install datacontract-cli[kafka]` |
+| MySQL | `pip install datacontract-cli[mysql]` |
+| Oracle | `pip install datacontract-cli[oracle]` |
+| Parquet | `pip install datacontract-cli[parquet]` |
+| PostgreSQL | `pip install datacontract-cli[postgres]` |
+| Protobuf | `pip install datacontract-cli[protobuf]` |
+| RDF | `pip install datacontract-cli[rdf]` |
+| Amazon Redshift | `pip install datacontract-cli[redshift]` |
+| S3 | `pip install datacontract-cli[s3]` |
+| Snowflake | `pip install datacontract-cli[snowflake]` |
+| Microsoft SQL Server | `pip install datacontract-cli[sqlserver]` |
+| Trino | `pip install datacontract-cli[trino]` |
 
 
 ## Documentation

{datacontract_cli-1.1.3 → datacontract_cli-1.2.1}/datacontract/api.py

@@ -2,14 +2,12 @@ import json
 import logging
 import os
 import secrets
-import tempfile
 from importlib import metadata
 from typing import Annotated, Optional
 
 import pydantic
-import yaml
 from fastapi import Body, Depends, FastAPI, HTTPException, Query, Request, status
-from fastapi.responses import PlainTextResponse
+from fastapi.responses import JSONResponse, PlainTextResponse
 from fastapi.security.api_key import APIKeyHeader
 from pydantic import BaseModel, Field, ValidationError
 
@@ -20,7 +18,9 @@ from datacontract.model.changelog import ChangelogEntry
 from datacontract.model.exceptions import DataContractException, DefinitionResolutionError
 from datacontract.model.run import Check, ResultEnum, Run
 
-DATA_CONTRACT_EXAMPLE_PAYLOAD = """apiVersion: v3.1.0
+logger = logging.getLogger(__name__)
+
+DATA_CONTRACT_EXAMPLE_PAYLOAD = """apiVersion: v3.2.0
 kind: DataContract
 id: orders
 name: Orders
@@ -335,6 +335,25 @@ app = FastAPI(
     ],
 )
 
+
+@app.exception_handler(pydantic.ValidationError)
+def _validation_error(request: Request, e: pydantic.ValidationError):
+    return JSONResponse(status_code=422, content={"detail": f"Invalid data contract: {e}"})
+
+
+@app.exception_handler(DataContractException)
+def _data_contract_exception(request: Request, e: DataContractException):
+    return JSONResponse(status_code=422, content={"detail": f"Data Contract Validation Failure: {e}"})
+
+
+@app.exception_handler(DefinitionResolutionError)
+def _definition_resolution_error(request: Request, e: DefinitionResolutionError):
+    # The reason names the host that was contacted and what it answered.
+    # Omit for security reasons.
+    logger.warning("Definition resolution failed: %s", e)
+    return JSONResponse(status_code=422, content={"detail": f"Could not resolve authoritative definition '{e.url}'."})
+
+
 _fastapi_openapi = app.openapi
 
 
@@ -481,6 +500,7 @@ _ENVIRONMENT_CREDENTIAL_TARGETS: dict[str, tuple[str, str | None, tuple[str, ...
     "oracle": ("host", "oracle_host", ("oracle_password",)),
     "impala": ("host", "impala_host", ("impala_password",)),
     "trino": ("host", "trino_host", ("trino_password",)),
+    "exasol": ("host", "exasol_host", ("exasol_password",)),
     "redshift": ("host", "redshift_host", ("redshift_password",)),
     "sqlserver": ("host", "sqlserver_host", ("sqlserver_password",)),
     "snowflake": (
@@ -665,21 +685,21 @@ def _reject_request_platform_host_with_environment_key(config) -> None:
 def check_api_key(api_key_header: str | None):
     correct_api_key = os.getenv("DATACONTRACT_CLI_API_KEY")
     if correct_api_key is None or correct_api_key == "":
-        logging.info("Environment variable DATACONTRACT_CLI_API_KEY is not set. Skip API key check.")
+        logger.info("Environment variable DATACONTRACT_CLI_API_KEY is not set. Skip API key check.")
         return
     if api_key_header is None or api_key_header == "":
-        logging.info("The API key is missing.")
+        logger.warning("The API key is missing.")
         raise HTTPException(
             status_code=status.HTTP_401_UNAUTHORIZED,
             detail="Missing API key. Use Header 'x-api-key' to provide the API key.",
         )
-    if not secrets.compare_digest(api_key_header, correct_api_key):
-        logging.info("The provided API key is not correct.")
+    if not secrets.compare_digest(api_key_header.encode(), correct_api_key.encode()):
+        logger.warning("The provided API key is not correct.")
         raise HTTPException(
             status_code=status.HTTP_403_FORBIDDEN,
             detail="The provided API key is not correct.",
         )
-    logging.info("Request authenticated with API key.")
+    logger.info("Request authenticated with API key.")
     pass
 
 
@@ -777,8 +797,7 @@ async def test(
             status_code=status.HTTP_422_UNPROCESSABLE_ENTITY,
             detail="Use either the filter or the filters parameter, not both.",
         )
-    logging.info("Testing data contract...")
-    logging.info(body)
+    logger.info("Testing data contract...")
     config = config_from_headers(request.headers)
     untrusted_contract = getattr(request.app.state, "untrusted_contracts", False)
     if untrusted_contract:
@@ -857,7 +876,10 @@ async def lint(
 ) -> LintResponse:
     check_api_key(api_key)
     data_contract = DataContract(
-        data_contract_str=body, schema_location=_require_schema_url(schema), all_errors=all_errors
+        data_contract_str=body,
+        schema_location=_require_schema_url(schema),
+        all_errors=all_errors,
+        untrusted_contract=True,
     )
     lint_result = data_contract.lint()
     return LintResponse(result=lint_result.result, checks=lint_result.checks)
@@ -933,30 +955,10 @@ async def changelog_endpoint(
 ) -> ChangelogResponse:
     check_api_key(api_key)
 
-    with tempfile.NamedTemporaryFile(mode="w", suffix=".yaml", delete=False) as f1:
-        f1.write(body.v1)
-        v1_path = f1.name
-    with tempfile.NamedTemporaryFile(mode="w", suffix=".yaml", delete=False) as f2:
-        f2.write(body.v2)
-        v2_path = f2.name
-
-    try:
-        result = DataContract(data_contract_file=v1_path).changelog(DataContract(data_contract_file=v2_path))
-        return ChangelogResponse(summary=result.summary, entries=result.entries)
-    except yaml.YAMLError as e:
-        raise HTTPException(status_code=422, detail=f"Invalid YAML: {e}")
-    except pydantic.ValidationError as e:
-        raise HTTPException(status_code=422, detail=f"Invalid data contract: {e}")
-    except DefinitionResolutionError as e:
-        # The reason names the host that was contacted and what it answered.
-        # Omit for security reasons.
-        logging.warning("Definition resolution failed: %s", e)
-        raise HTTPException(status_code=422, detail=f"Could not resolve authoritative definition '{e.url}'.")
-    except DataContractException as e:
-        raise HTTPException(status_code=422, detail=f"Data Contract Validation Failure: {e}")
-    finally:
-        os.unlink(v1_path)
-        os.unlink(v2_path)
+    result = DataContract(data_contract_str=body.v1, untrusted_contract=True).changelog(
+        DataContract(data_contract_str=body.v2, untrusted_contract=True)
+    )
+    return ChangelogResponse(summary=result.summary, entries=result.entries)
 
 
 @app.post(
@@ -986,25 +988,10 @@ def breaking_endpoint(
 ) -> BreakingChangesResponse:
     check_api_key(api_key)
 
-    with tempfile.NamedTemporaryFile(mode="w", suffix=".yaml", delete=False) as f1:
-        f1.write(body.v1)
-        v1_path = f1.name
-    with tempfile.NamedTemporaryFile(mode="w", suffix=".yaml", delete=False) as f2:
-        f2.write(body.v2)
-        v2_path = f2.name
-
-    try:
-        result = DataContract(data_contract_file=v1_path).breaking(DataContract(data_contract_file=v2_path))
-        return BreakingChangesResponse(summary=result.summary, entries=result.entries, is_breaking=result.is_breaking)
-    except yaml.YAMLError as e:
-        raise HTTPException(status_code=422, detail=f"Invalid YAML: {e}")
-    except pydantic.ValidationError as e:
-        raise HTTPException(status_code=422, detail=f"Invalid data contract: {e}")
-    except DataContractException as e:
-        raise HTTPException(status_code=422, detail=f"Data Contract Validation Failure: {e}")
-    finally:
-        os.unlink(v1_path)
-        os.unlink(v2_path)
+    result = DataContract(data_contract_str=body.v1, untrusted_contract=True).breaking(
+        DataContract(data_contract_str=body.v2, untrusted_contract=True)
+    )
+    return BreakingChangesResponse(summary=result.summary, entries=result.entries, is_breaking=result.is_breaking)
 
 
 @app.post(
@@ -1107,21 +1094,9 @@ def export(
     ] = None,
 ):
     check_api_key(api_key)
-    try:
-        return DataContract(data_contract_str=body, server=server).export(
-            export_format=format,
-            model=model,
-            rdf_base=rdf_base,
-            sql_server_type=sql_server_type,
-        )
-    except yaml.YAMLError as e:
-        raise HTTPException(status_code=422, detail=f"Invalid YAML: {e}")
-    except pydantic.ValidationError as e:
-        raise HTTPException(status_code=422, detail=f"Invalid data contract: {e}")
-    except DefinitionResolutionError as e:
-        # The reason names the host that was contacted and what it answered.
-        # Omit for security reasons.
-        logging.warning("Definition resolution failed: %s", e)
-        raise HTTPException(status_code=422, detail=f"Could not resolve authoritative definition '{e.url}'.")
-    except DataContractException as e:
-        raise HTTPException(status_code=422, detail=f"Data Contract Validation Failure: {e}")
+    return DataContract(data_contract_str=body, server=server, untrusted_contract=True).export(
+        export_format=format,
+        model=model,
+        rdf_base=rdf_base,
+        sql_server_type=sql_server_type,
+    )

{datacontract_cli-1.1.3 → datacontract_cli-1.2.1}/datacontract/breaking/detector.py

@@ -22,12 +22,41 @@ class BreakingChangeDetector:
 
     def detect(self, changelog: ChangelogResult) -> BreakingChangeResult:
         entries = [self._classify(entry) for entry in changelog.entries]
-        # Nothing inside a newly added element can break a consumer: it did not exist before.
-        added = {entry.path for entry in entries if entry.change_type == ChangelogType.added}
+        # Nothing inside an added element can break a consumer: it did not exist before.
+        # Inside a removed one, the element's own entry carries the grade; its former
+        # constraints are gone, which is a relaxation.
+        added_or_removed = {
+            entry.path
+            for entry in entries
+            if entry.change_type in (ChangelogType.added, ChangelogType.removed)
+            and (
+                entry.path.startswith("schema.")
+                and (len(entry.path.split(".")) == 2 or entry.path.split(".")[-2] in ("properties", "quality"))
+            )
+        }
+        removed_enums = {
+            entry.path
+            for entry in entries
+            if entry.change_type == ChangelogType.removed and entry.path.endswith(".enum")
+        }
+        # Stable IDs may change or swap without changing the set of allowed
+        # values. Match removed/updated values against additions in the same enum.
+        added_values = defaultdict(set)
+        for entry in entries:
+            if entry.rule_id == "enum-constraint-changed" and entry.path.endswith(".value"):
+                if entry.change_type in (ChangelogType.added, ChangelogType.updated):
+                    added_values[entry.path.rsplit(".enum.", 1)[0]].add(entry.new_value)
         for entry in entries:
             segments = entry.path.split(".")
-            if any(".".join(segments[:i]) in added for i in range(1, len(segments))):
+            if any(".".join(segments[:i]) in added_or_removed for i in range(1, len(segments))):
                 entry.level = BreakingChangeLevel.INFO
+            if entry.rule_id == "enum-constraint-changed":
+                if any(entry.path.startswith(path + ".") for path in removed_enums):
+                    entry.level = BreakingChangeLevel.INFO
+                elif entry.path.endswith(".value") and entry.old_value in added_values.get(
+                    entry.path.rsplit(".enum.", 1)[0], set()
+                ):
+                    entry.level = BreakingChangeLevel.INFO
         entries_by_prefix = defaultdict(list)
         for entry in entries:
             prefix = ""

{datacontract_cli-1.1.3 → datacontract_cli-1.2.1}/datacontract/breaking/rules.py

@@ -140,6 +140,87 @@ class MetadataFallbackRule(BreakingChangeRule):
         return RuleEvaluation(self.rule_id, BreakingChangeLevel.INFO, _change_message("contract", entry))
 
 
+class EnumConstraintRule(BreakingChangeRule):
+    rule_id = "enum-constraint-changed"
+
+    def evaluate(self, entry: ChangelogEntry) -> RuleEvaluation | None:
+        if not entry.path.startswith("schema.") or ".properties." not in entry.path:
+            return None
+        if entry.path.endswith(".enum"):
+            level = BreakingChangeLevel.ERROR if entry.type == ChangelogType.added else BreakingChangeLevel.INFO
+        elif (
+            ".enum." in entry.path
+            and entry.path.endswith(".value")
+            and ".customProperties." not in entry.path.rsplit(".enum.", 1)[1]
+            and ".authoritativeDefinitions." not in entry.path.rsplit(".enum.", 1)[1]
+        ):
+            level = BreakingChangeLevel.INFO if entry.type == ChangelogType.added else BreakingChangeLevel.ERROR
+        else:
+            return None
+        return RuleEvaluation(self.rule_id, level, _change_message("allowed values", entry))
+
+
+class QualityConstraintRule(BreakingChangeRule):
+    rule_id = "quality-constraint-changed"
+    _thresholds = (
+        ".mustBeLessThan",
+        ".mustBeLessOrEqualTo",
+        ".mustBeGreaterThan",
+        ".mustBeGreaterOrEqualTo",
+    )
+
+    def evaluate(self, entry: ChangelogEntry) -> RuleEvaluation | None:
+        if not entry.path.startswith("schema.") or ".quality." not in entry.path:
+            return None
+        rule_path = entry.path.rsplit(".quality.", 1)[1]
+        if rule_path.endswith(".arguments.validValues"):
+            # The diff emits one entry per list element.
+            level = BreakingChangeLevel.INFO if entry.type == ChangelogType.added else BreakingChangeLevel.ERROR
+        elif rule_path.endswith(".arguments.invalidValues"):
+            level = BreakingChangeLevel.INFO if entry.type == ChangelogType.removed else BreakingChangeLevel.ERROR
+        elif rule_path.endswith(self._thresholds):
+            old = _parse_number(entry.old_value)
+            new = _parse_number(entry.new_value)
+            if entry.type == ChangelogType.removed:
+                level = BreakingChangeLevel.INFO
+            elif old is None or new is None:
+                level = BreakingChangeLevel.WARNING
+            elif _is_tightening(entry.path, old, new):
+                level = BreakingChangeLevel.ERROR
+            else:
+                level = BreakingChangeLevel.INFO
+        elif "." not in rule_path:
+            # A new rule is a constraint existing data may not satisfy; a removed one is a relaxation.
+            level = BreakingChangeLevel.ERROR if entry.type == ChangelogType.added else BreakingChangeLevel.INFO
+        elif rule_path.endswith((".description", ".dimension", ".businessImpact", ".severity")):
+            level = BreakingChangeLevel.INFO
+        elif ".customProperties." in rule_path or ".authoritativeDefinitions." in rule_path or ".tags" in rule_path:
+            level = BreakingChangeLevel.INFO
+        else:
+            # What the rule checks changed (type, metric, query, other arguments, thresholds we cannot order).
+            level = BreakingChangeLevel.WARNING
+        name, _, field = rule_path.partition(".")
+        subject = f"{field} of quality rule '{name}'" if field else "quality rule"
+        return RuleEvaluation(self.rule_id, level, _change_message(subject, entry))
+
+
+class VectorShapeRule(BreakingChangeRule):
+    rule_id = "vector-shape-changed"
+
+    def evaluate(self, entry: ChangelogEntry) -> RuleEvaluation | None:
+        if not entry.path.startswith("schema.") or not entry.path.endswith(
+            (".logicalTypeOptions.dimensions", ".logicalTypeOptions.elementType")
+        ):
+            return None
+        if entry.path.endswith(".elementType"):
+            old = entry.old_value or "float32"
+            new = entry.new_value or "float32"
+            level = BreakingChangeLevel.INFO if old == new else BreakingChangeLevel.ERROR
+        else:
+            level = BreakingChangeLevel.WARNING if entry.type == ChangelogType.removed else BreakingChangeLevel.ERROR
+        return RuleEvaluation(self.rule_id, level, _change_message("vector shape", entry))
+
+
 def _is_schema_property_path(segments: list[str]) -> bool:
     return len(segments) >= 3 and segments[0] == "schema" and segments[-2] == "properties"
 
@@ -169,9 +250,9 @@ def _parse_number(value: str | None) -> float | None:
 
 
 def _is_tightening(path: str, old: float, new: float) -> bool:
-    if path.endswith((".minLength", ".minimum", ".exclusiveMinimum")):
+    if path.endswith((".minLength", ".minimum", ".exclusiveMinimum", ".mustBeGreaterThan", ".mustBeGreaterOrEqualTo")):
         return new > old
-    if path.endswith((".maxLength", ".maximum", ".exclusiveMaximum")):
+    if path.endswith((".maxLength", ".maximum", ".exclusiveMaximum", ".mustBeLessThan", ".mustBeLessOrEqualTo")):
         return new < old
     return True
 
@@ -185,6 +266,7 @@ def _change_message(subject: str, entry: ChangelogEntry) -> str:
 
 
 DEFAULT_RULES: tuple[BreakingChangeRule, ...] = (
+    QualityConstraintRule(),
     RequiredChangedRule(),
     SchemaRemovedRule(),
     FieldRemovedRule(),
@@ -192,5 +274,7 @@ DEFAULT_RULES: tuple[BreakingChangeRule, ...] = (
     UniqueConstraintRule(),
     KeyConstraintRule(),
     ValidationConstraintRule(),
+    EnumConstraintRule(),
+    VectorShapeRule(),
     MetadataFallbackRule(),
 )

{datacontract_cli-1.1.3 → datacontract_cli-1.2.1}/datacontract/catalog/catalog.py

@@ -12,6 +12,8 @@ from datacontract.config import cli_config
 from datacontract.data_contract import DataContract
 from datacontract.export.html_exporter import get_version
 
+logger = logging.getLogger(__name__)
+
 
 def _get_owner(odcs: OpenDataContractStandard) -> Optional[str]:
     """Get the owner from ODCS customProperties or team."""
@@ -25,7 +27,7 @@ def _get_owner(odcs: OpenDataContractStandard) -> Optional[str]:
 
 
 def create_data_contract_html(contracts, file: Path, path: Path, schema: str):
-    logging.debug(f"Creating data contract html for file {file} and schema {schema}")
+    logger.debug(f"Creating data contract html for file {file} and schema {schema}")
     data_contract = DataContract(
         data_contract_file=f"{file.absolute()}", inline_references=True, schema_location=schema, config=cli_config()
     )