datacontract-cli 0.12.1__tar.gz → 0.12.2__tar.gz

{datacontract_cli-0.12.1/datacontract_cli.egg-info → datacontract_cli-0.12.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datacontract-cli
-Version: 0.12.1
+Version: 0.12.2
 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
@@ -11,7 +11,7 @@ Classifier: Operating System :: OS Independent
 Requires-Python: <3.13,>=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: typer<0.25,>=0.18.0
+Requires-Dist: typer<0.26,>=0.18.0
 Requires-Dist: pydantic<2.14.0,>=2.8.2
 Requires-Dist: pyyaml~=6.0.1
 Requires-Dist: requests<2.34,>=2.31
@@ -21,7 +21,6 @@ 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: setuptools>=60
 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
@@ -29,6 +28,7 @@ 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<4.0.0,>=3.1.2
 Requires-Dist: deepdiff<10.0.0,>=6.0.0
+Requires-Dist: setuptools>=70
 Provides-Extra: avro
 Requires-Dist: avro==1.12.1; extra == "avro"
 Provides-Extra: bigquery
@@ -41,7 +41,7 @@ Provides-Extra: databricks
 Requires-Dist: soda-core-spark-df<3.6.0,>=3.3.20; extra == "databricks"
 Requires-Dist: soda-core-spark[databricks]<3.6.0,>=3.3.20; extra == "databricks"
 Requires-Dist: databricks-sql-connector<4.3.0,>=3.7.0; extra == "databricks"
-Requires-Dist: databricks-sdk<0.104.0; extra == "databricks"
+Requires-Dist: databricks-sdk<0.106.0; extra == "databricks"
 Requires-Dist: pyspark<5.0.0,>=3.5.0; extra == "databricks"
 Provides-Extra: iceberg
 Requires-Dist: pyiceberg==0.11.1; extra == "iceberg"
@@ -51,12 +51,12 @@ Requires-Dist: soda-core-spark-df<3.6.0,>=3.3.20; extra == "kafka"
 Requires-Dist: pyspark<5.0.0,>=3.5.0; extra == "kafka"
 Provides-Extra: mysql
 Requires-Dist: soda-core-mysql<3.6.0,>=3.3.20; extra == "mysql"
-Requires-Dist: mysql-connector-python<10.0.0,>=8.0.30; extra == "mysql"
+Requires-Dist: mysql-connector-python<9.7.0,>=8.0.30; extra == "mysql"
 Provides-Extra: postgres
 Requires-Dist: soda-core-postgres<3.6.0,>=3.3.20; extra == "postgres"
 Provides-Extra: s3
 Requires-Dist: s3fs<2027.0.0,>=2025.2.0; extra == "s3"
-Requires-Dist: aiobotocore<3.5.0,>=2.17.0; extra == "s3"
+Requires-Dist: aiobotocore<3.6.0,>=2.17.0; extra == "s3"
 Provides-Extra: snowflake
 Requires-Dist: snowflake-connector-python[pandas]<4.5,>=3.6; extra == "snowflake"
 Requires-Dist: soda-core-snowflake<3.6.0,>=3.3.20; extra == "snowflake"
@@ -68,8 +68,8 @@ Provides-Extra: athena
 Requires-Dist: soda-core-athena<3.6.0,>=3.3.20; extra == "athena"
 Provides-Extra: trino
 Requires-Dist: soda-core-trino<3.6.0,>=3.3.20; extra == "trino"
-Provides-Extra: dbt
-Requires-Dist: dbt-core>=1.8.0; extra == "dbt"
+Provides-Extra: impala
+Requires-Dist: soda-core-impala<3.6.0,>=3.3.20; extra == "impala"
 Provides-Extra: dbml
 Requires-Dist: pydbml>=1.1.1; extra == "dbml"
 Provides-Extra: duckdb
@@ -80,12 +80,12 @@ 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==0.136.0; extra == "api"
+Requires-Dist: fastapi==0.136.1; extra == "api"
 Requires-Dist: uvicorn==0.44.0; extra == "api"
 Provides-Extra: protobuf
-Requires-Dist: grpcio-tools>=1.53; extra == "protobuf"
+Requires-Dist: protobuf<7.0,>=3.20; extra == "protobuf"
 Provides-Extra: all
-Requires-Dist: datacontract-cli[api,athena,bigquery,csv,databricks,dbml,dbt,duckdb,excel,iceberg,kafka,mysql,oracle,parquet,postgres,protobuf,rdf,s3,snowflake,sqlserver,trino]; extra == "all"
+Requires-Dist: datacontract-cli[api,athena,bigquery,csv,databricks,dbml,duckdb,excel,iceberg,impala,kafka,mysql,oracle,parquet,postgres,protobuf,rdf,s3,snowflake,sqlserver,trino]; extra == "all"
 Provides-Extra: dev
 Requires-Dist: datacontract-cli[all]; extra == "dev"
 Requires-Dist: httpx==0.28.1; extra == "dev"
@@ -97,7 +97,7 @@ Requires-Dist: pre-commit<4.6.0,>=3.7.1; extra == "dev"
 Requires-Dist: pytest; extra == "dev"
 Requires-Dist: pytest-xdist; extra == "dev"
 Requires-Dist: pymssql==2.3.13; extra == "dev"
-Requires-Dist: ruff==0.15.11; extra == "dev"
+Requires-Dist: ruff==0.15.12; 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
@@ -345,23 +345,25 @@ A list of available extras:
 | Amazon Athena           | `pip install datacontract-cli[athena]`     |
 | Avro Support            | `pip install datacontract-cli[avro]`       |
 | Google BigQuery         | `pip install datacontract-cli[bigquery]`   |
+| CSV                     | `pip install datacontract-cli[csv]`        |
 | Databricks Integration  | `pip install datacontract-cli[databricks]` |
+| DBML                    | `pip install datacontract-cli[dbml]`       |
 | DuckDB (local/S3/GCS/Azure file testing) | `pip install datacontract-cli[duckdb]` |
+| Excel                   | `pip install datacontract-cli[excel]`      |
 | 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]`        |
 | 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]`      |
-| Impala                  | `pip install datacontract-cli[impala]` 	   |
-| dbt                     | `pip install datacontract-cli[dbt]`        |
-| DBML                    | `pip install datacontract-cli[dbml]`       |
-| Parquet                 | `pip install datacontract-cli[parquet]`    |
-| RDF                     | `pip install datacontract-cli[rdf]`        |
 | API (run as web server) | `pip install datacontract-cli[api]`        |
-| protobuf                | `pip install datacontract-cli[protobuf]`   |
 
 
 ## Documentation
@@ -1972,7 +1974,17 @@ datacontract import csv --source "test.csv"
 <details markdown="1">
 <summary><strong>protobuf</strong></summary>
 
-Importing from protobuf File. Specify file in `source` parameter. 
+Importing from protobuf File. Specify file in `source` parameter.
+
+Requires the `protoc` compiler installed on the system. Install with:
+
+| Platform       | Command                              |
+|----------------|--------------------------------------|
+| macOS          | `brew install protobuf`              |
+| Debian/Ubuntu  | `sudo apt install protobuf-compiler` |
+| Fedora/RHEL    | `sudo dnf install protobuf-compiler` |
+| Arch           | `sudo pacman -S protobuf`            |
+| Windows        | `choco install protoc` (or [download a release](https://github.com/protocolbuffers/protobuf/releases)) |
 
 Example:
 

{datacontract_cli-0.12.1 → datacontract_cli-0.12.2}/README.md

@@ -241,23 +241,25 @@ A list of available extras:
 | Amazon Athena           | `pip install datacontract-cli[athena]`     |
 | Avro Support            | `pip install datacontract-cli[avro]`       |
 | Google BigQuery         | `pip install datacontract-cli[bigquery]`   |
+| CSV                     | `pip install datacontract-cli[csv]`        |
 | Databricks Integration  | `pip install datacontract-cli[databricks]` |
+| DBML                    | `pip install datacontract-cli[dbml]`       |
 | DuckDB (local/S3/GCS/Azure file testing) | `pip install datacontract-cli[duckdb]` |
+| Excel                   | `pip install datacontract-cli[excel]`      |
 | 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]`        |
 | 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]`      |
-| Impala                  | `pip install datacontract-cli[impala]` 	   |
-| dbt                     | `pip install datacontract-cli[dbt]`        |
-| DBML                    | `pip install datacontract-cli[dbml]`       |
-| Parquet                 | `pip install datacontract-cli[parquet]`    |
-| RDF                     | `pip install datacontract-cli[rdf]`        |
 | API (run as web server) | `pip install datacontract-cli[api]`        |
-| protobuf                | `pip install datacontract-cli[protobuf]`   |
 
 
 ## Documentation
@@ -1868,7 +1870,17 @@ datacontract import csv --source "test.csv"
 <details markdown="1">
 <summary><strong>protobuf</strong></summary>
 
-Importing from protobuf File. Specify file in `source` parameter. 
+Importing from protobuf File. Specify file in `source` parameter.
+
+Requires the `protoc` compiler installed on the system. Install with:
+
+| Platform       | Command                              |
+|----------------|--------------------------------------|
+| macOS          | `brew install protobuf`              |
+| Debian/Ubuntu  | `sudo apt install protobuf-compiler` |
+| Fedora/RHEL    | `sudo dnf install protobuf-compiler` |
+| Arch           | `sudo pacman -S protobuf`            |
+| Windows        | `choco install protoc` (or [download a release](https://github.com/protocolbuffers/protobuf/releases)) |
 
 Example:
 

{datacontract_cli-0.12.1 → datacontract_cli-0.12.2}/datacontract/command_changelog.py

@@ -11,8 +11,8 @@ from datacontract.output.text_changelog_results import write_text_changelog_resu
     epilog="Example: datacontract changelog datacontract-v1.yaml datacontract-v2.yaml",
 )
 def changelog(
-    v1: Annotated[str, typer.Argument(help="The location (path) of the source (before) data contract YAML.")],
-    v2: Annotated[str, typer.Argument(help="The location (path) of the target (after) data contract YAML.")],
+    v1: Annotated[str, typer.Argument(help="The location (url or path) of the source (before) data contract YAML.")],
+    v2: Annotated[str, typer.Argument(help="The location (url or path) of the target (after) data contract YAML.")],
     debug: debug_option = None,
 ):
     """Show a changelog between two data contracts."""

{datacontract_cli-0.12.1 → datacontract_cli-0.12.2}/datacontract/engines/data_contract_checks.py

@@ -1,8 +1,8 @@
+import logging
 import re
 import uuid
 from dataclasses import dataclass
 from typing import List, Optional
-from venv import logger
 
 import yaml
 from open_data_contract_standard.model import (
@@ -16,6 +16,8 @@ from open_data_contract_standard.model import (
 from datacontract.export.sql_type_converter import convert_to_sql_type
 from datacontract.model.run import Check
 
+logger = logging.getLogger(__name__)
+
 
 @dataclass
 class QuotingConfig:
@@ -48,6 +50,28 @@ def _quote_field_name(field_name: str, quoting_config: QuotingConfig) -> str:
     return field_name
 
 
+_BACKTICK_DIALECTS = {"databricks", "bigquery", "mysql", "impala", "dataframe", "kafka"}
+_ANSI_QUOTING_DIALECTS = {"postgres", "sqlserver", "snowflake", "azure", "s3", "gcs", "local"}
+
+_BARE_IDENTIFIER_STRICT = re.compile(r"^[A-Za-z_][A-Za-z0-9_]*$")
+_BARE_IDENTIFIER_PERMISSIVE = re.compile(r"^[A-Za-z_][A-Za-z0-9_$]*$")
+_PERMISSIVE_BARE_DIALECTS = {"postgres", "snowflake", "oracle", "sqlserver"}
+
+
+def _quote_identifier_if_needed(identifier: str, server: Optional[Server]) -> str:
+    """Quote an identifier only when the target dialect would reject it bare.
+
+    Avoids unnecessary quoting, because quoting leads to case-sensitivity.
+    """
+    if identifier is None:
+        return identifier
+    server_type = server.type if server and server.type else None
+    pattern = _BARE_IDENTIFIER_PERMISSIVE if server_type in _PERMISSIVE_BARE_DIALECTS else _BARE_IDENTIFIER_STRICT
+    if pattern.match(identifier):
+        return identifier
+    return f"`{identifier}`" if server_type in _BACKTICK_DIALECTS else f'"{identifier}"'
+
+
 def _get_logical_type_option(prop: SchemaProperty, key: str):
     """Get a logical type option value."""
     if prop.logicalTypeOptions is None:
@@ -84,7 +108,7 @@ def create_checks(data_contract: OpenDataContractStandard, server: Server, schem
             continue
         schema_checks = to_schema_checks(schema_obj, server)
         checks.extend(schema_checks)
-    checks.extend(to_servicelevel_checks(data_contract))
+    checks.extend(to_servicelevel_checks(data_contract, server))
     return [check for check in checks if check is not None]
 
 
@@ -98,21 +122,21 @@ def to_schema_checks(schema_object: SchemaObject, server: Server) -> List[Check]
 
     type1 = server.type if server and server.type else None
     config = QuotingConfig(
-        quote_field_name=type1 in ["postgres", "sqlserver", "snowflake", "azure", "s3", "gcs", "local"],
-        quote_field_name_with_backticks=type1 in ["databricks", "bigquery", "mysql"],
-        quote_model_name=type1 in ["postgres", "sqlserver", "snowflake", "azure", "s3", "gcs", "local"],
-        quote_model_name_with_backticks=type1 in ["databricks", "bigquery", "mysql"],
+        quote_field_name=type1 in _ANSI_QUOTING_DIALECTS,
+        quote_field_name_with_backticks=type1 in _BACKTICK_DIALECTS,
+        quote_model_name=type1 in _ANSI_QUOTING_DIALECTS,
+        quote_model_name_with_backticks=type1 in _BACKTICK_DIALECTS,
     )
     quoting_config = config
 
     for prop in properties:
         property_name = prop.name
-        logical_type = prop.logicalType
 
         checks.append(check_property_is_present(schema_name, property_name, quoting_config))
-        if check_types and logical_type is not None:
+        if check_types and (prop.physicalType is not None or prop.logicalType is not None):
             sql_type: str = convert_to_sql_type(prop, server_type)
-            checks.append(check_property_type(schema_name, property_name, sql_type, quoting_config))
+            if sql_type is not None:
+                checks.append(check_property_type(schema_name, property_name, sql_type, quoting_config))
         if prop.required:
             checks.append(check_property_required(schema_name, property_name, quoting_config))
         if prop.unique:
@@ -224,6 +248,9 @@ def check_property_is_present(model_name, field_name, quoting_config: QuotingCon
 def check_property_type(
     model_name: str, field_name: str, expected_type: str, quoting_config: QuotingConfig = QuotingConfig()
 ):
+    if expected_type is None:
+        logger.warning(f"Cannot build type check for {model_name}.{field_name}: expected_type is None.")
+        return None
     check_type = "field_type"
     check_key = f"{model_name}__{field_name}__{check_type}"
     sodacl_check_dict = {
@@ -750,10 +777,10 @@ def check_quality_list(
         elif quality.type == "sql":
             if property_name is None:
                 check_key = f"{schema_name}__quality_sql_{count}"
-                check_type = "field_quality_sql"
+                check_type = "model_quality_sql"
             else:
                 check_key = f"{schema_name}__{property_name}__quality_sql_{count}"
-                check_type = "model_quality_sql"
+                check_type = "field_quality_sql"
             threshold = to_sodacl_threshold(quality)
             query = prepare_query(quality, schema_name, property_name, quoting_config, server)
             if query is None:
@@ -869,6 +896,7 @@ def prepare_query(
 
     query = re.sub(r'["\']?\$?\{model}["\']?', model_name_for_soda, query)
     query = re.sub(r'["\']?\$?\{table}["\']?', model_name_for_soda, query)
+    query = re.sub(r'["\']?\$?\{object}["\']?', model_name_for_soda, query)
 
     if server and server.schema_:
         if quoting_config.quote_model_name:
@@ -926,14 +954,14 @@ def _get_schema_by_name(data_contract: OpenDataContractStandard, name: str) -> O
     return next((s for s in data_contract.schema_ if s.name == name), None)
 
 
-def to_servicelevel_checks(data_contract: OpenDataContractStandard) -> List[Check]:
+def to_servicelevel_checks(data_contract: OpenDataContractStandard, server: Optional[Server] = None) -> List[Check]:
     checks: List[Check] = []
     if data_contract.slaProperties is None:
         return checks
 
     for sla in data_contract.slaProperties:
         if sla.property == "freshness":
-            check = to_sla_freshness_check(data_contract, sla)
+            check = to_sla_freshness_check(data_contract, sla, server)
             if check is not None:
                 checks.append(check)
         elif sla.property == "retention":
@@ -944,7 +972,9 @@ def to_servicelevel_checks(data_contract: OpenDataContractStandard) -> List[Chec
     return checks
 
 
-def to_sla_freshness_check(data_contract: OpenDataContractStandard, sla) -> Check | None:
+def to_sla_freshness_check(
+    data_contract: OpenDataContractStandard, sla, server: Optional[Server] = None
+) -> Check | None:
     """Create a freshness check from an ODCS latency SLA property."""
     if sla.element is None:
         logger.info("slaProperties.latency.element is not defined, skipping freshness check")
@@ -990,10 +1020,11 @@ def to_sla_freshness_check(data_contract: OpenDataContractStandard, sla) -> Chec
 
     check_type = "servicelevel_freshness"
     check_key = "servicelevel_freshness"
+    quoted_field = _quote_identifier_if_needed(field_name, server)
     sodacl_check_dict = {
         f"checks for {model_name}": [
             {
-                f"freshness({field_name}) < {threshold}": {
+                f"freshness({quoted_field}) < {threshold}": {
                     "name": check_key,
                 },
             }

{datacontract_cli-0.12.1 → datacontract_cli-0.12.2}/datacontract/engines/soda/check_soda_execute.py

@@ -191,13 +191,14 @@ def check_soda_execute(
         )
 
     if scan.has_error_logs():
-        run.log_warn("Engine soda-core has errors. See the logs for details.")
+        reason = _first_error_message(scan_results) or "Engine soda-core has errors. See the logs for details."
+        run.log_error(f"Engine soda-core has errors: {reason}")
         run.checks.append(
             Check(
                 type="general",
                 name="Data Contract Tests",
-                result=ResultEnum.warning,
-                reason="Engine soda-core has errors. See the logs for details.",
+                result=ResultEnum.failed,
+                reason=reason,
                 engine="soda-core",
             )
         )
@@ -212,6 +213,15 @@ def get_check(run, scan_result) -> Check | None:
     return None
 
 
+def _first_error_message(scan_results: dict) -> str | None:
+    for log in scan_results.get("logs") or []:
+        if log.get("level") == "ERROR":
+            message = log.get("message")
+            if message:
+                return message.strip().splitlines()[0]
+    return None
+
+
 def to_result(c) -> ResultEnum:
     soda_outcome = c.get("outcome")
     if soda_outcome == "pass":