exadata-validator 0.0.1__tar.gz → 1.1.0__tar.gz

{exadata_validator-0.0.1 → exadata_validator-1.1.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: exadata-validator
-Version: 0.0.1
+Version: 1.1.0
 Summary: Validate data-model folders using DuckDB.
 Author: Exaflow Team
 Requires-Python: >=3.10,<3.11
@@ -14,7 +14,7 @@ Description-Content-Type: text/markdown
 
 `exadata-validator` validates data-model folders using DuckDB.
 
-## Install With pip
+## Install with pip
 
 ```bash
 python -m venv .venv
@@ -28,21 +28,21 @@ Validate a data model folder:
 exadata-validator validate-data-model /path/to/data_model_folder
 ```
 
-## Develop With Poetry
-
-From the repository root:
+Run as a Python module:
 
 ```bash
-cd data-validator/exaflow-data-validator
-poetry install
+python -m validator validate-data-model /path/to/data_model_folder
 ```
 
-Then run the same CLI through Poetry:
+Useful options:
 
 ```bash
-poetry run exadata-validator validate-data-model /path/to/data_model_folder
+exadata-validator validate-data-model /path/to/data_model_folder --fail-fast
+exadata-validator validate-data-model /path/to/data_model_folder --format html --output report.html
 ```
 
+By default the command collects and reports all validation errors in text format. If `--format html` is used without `--output`, the report is written under `/tmp`.
+
 Use `exadata-validator validate-data-model --help` for reporting, output, and threading options.
 
 ## Folder Layout

{exadata_validator-0.0.1 → exadata_validator-1.1.0}/README.md

@@ -2,7 +2,7 @@
 
 `exadata-validator` validates data-model folders using DuckDB.
 
-## Install With pip
+## Install with pip
 
 ```bash
 python -m venv .venv
@@ -16,21 +16,21 @@ Validate a data model folder:
 exadata-validator validate-data-model /path/to/data_model_folder
 ```
 
-## Develop With Poetry
-
-From the repository root:
+Run as a Python module:
 
 ```bash
-cd data-validator/exaflow-data-validator
-poetry install
+python -m validator validate-data-model /path/to/data_model_folder
 ```
 
-Then run the same CLI through Poetry:
+Useful options:
 
 ```bash
-poetry run exadata-validator validate-data-model /path/to/data_model_folder
+exadata-validator validate-data-model /path/to/data_model_folder --fail-fast
+exadata-validator validate-data-model /path/to/data_model_folder --format html --output report.html
 ```
 
+By default the command collects and reports all validation errors in text format. If `--format html` is used without `--output`, the report is written under `/tmp`.
+
 Use `exadata-validator validate-data-model --help` for reporting, output, and threading options.
 
 ## Folder Layout

{exadata_validator-0.0.1 → exadata_validator-1.1.0}/pyproject.toml

@@ -1,11 +1,11 @@
 [tool.poetry]
 name = "exadata-validator"
-version = "0.0.1"
+version = "1.1.0"
 description = "Validate data-model folders using DuckDB."
 authors = ["Exaflow Team"]
 readme = "README.md"
 packages = [
-    { include = "data_validator" },
+    { include = "validator" },
 ]
 
 [tool.poetry.dependencies]
@@ -17,7 +17,7 @@ duckdb = "~1.1"
 pytest = "~8.4"
 
 [tool.poetry.scripts]
-exadata-validator = "data_validator.commands:entry"
+exadata-validator = "validator.commands:entry"
 
 [tool.pytest.ini_options]
 testpaths = ["tests"]

exadata_validator-1.1.0/validator/__main__.py

@@ -0,0 +1,4 @@
+from validator.commands import entry
+
+if __name__ == "__main__":
+    entry()

{exadata_validator-0.0.1/data_validator → exadata_validator-1.1.0/validator}/commands.py

@@ -7,11 +7,11 @@ from uuid import uuid4
 
 import click as cl
 
-from data_validator.exceptions import ExitCode
-from data_validator.exceptions import InvalidDatasetError
-from data_validator.exceptions import handle_errors
-from data_validator.reporting import render_report
-from data_validator.usecases import validate_data_model_folder
+from validator.exceptions import ExitCode
+from validator.exceptions import InvalidDatasetError
+from validator.exceptions import handle_errors
+from validator.reporting import render_report
+from validator.usecases import validate_data_model_folder
 
 logging.basicConfig(
     stream=sys.stderr, level=logging.INFO, format="%(levelname)s: %(message)s"
@@ -54,7 +54,7 @@ def _default_html_report_path() -> Path:
 @cl.option(
     "--format",
     "output_format",
-    type=cl.Choice(["text", "json", "ndjson", "html"], case_sensitive=False),
+    type=cl.Choice(["text", "html"], case_sensitive=False),
     default="text",
     show_default=True,
     help="Output format when collecting all validation errors.",

{exadata_validator-0.0.1/data_validator → exadata_validator-1.1.0/validator}/dataelements.py

@@ -1,8 +1,8 @@
 import json
 from dataclasses import dataclass
 
-from data_validator.exceptions import InvalidDataModelError
-from data_validator.exceptions import UserInputError
+from validator.exceptions import InvalidDataModelError
+from validator.exceptions import UserInputError
 
 
 @dataclass

{exadata_validator-0.0.1/data_validator → exadata_validator-1.1.0/validator}/duckdb_validator.py

@@ -9,13 +9,13 @@ from typing import Callable
 
 import duckdb
 
-from data_validator.dataelements import flatten_cdes
-from data_validator.dataelements import get_cdes_with_enumerations
-from data_validator.dataelements import get_cdes_with_min_max
-from data_validator.dataelements import get_dataset_enums
-from data_validator.dataelements import get_sql_type_per_column
-from data_validator.exceptions import InvalidDatasetError
-from data_validator.reporting import ValidationIssue
+from validator.dataelements import flatten_cdes
+from validator.dataelements import get_cdes_with_enumerations
+from validator.dataelements import get_cdes_with_min_max
+from validator.dataelements import get_dataset_enums
+from validator.dataelements import get_sql_type_per_column
+from validator.exceptions import InvalidDatasetError
+from validator.reporting import ValidationIssue
 
 
 def _quote_identifier(value: str) -> str:
@@ -247,10 +247,7 @@ class DuckDBDatasetValidator:
                         f"{quoted_column} IS NOT NULL AND {quoted_column} NOT IN ({in_list})"
                     ),
                     sample_expression_sql=quoted_column,
-                    message_factory=lambda count,
-                    sample,
-                    c=column,
-                    allowed=allowed_display: (
+                    message_factory=lambda count, sample, c=column, allowed=allowed_display: (
                         f"Column '{c}' has invalid categorical value(s). "
                         f"Allowed values: [{allowed}]. "
                         f"Found {count} invalid row(s), example invalid value: {sample!r}."
@@ -268,9 +265,7 @@ class DuckDBDatasetValidator:
                     column="dataset",
                     condition_sql=f"dataset IS NOT NULL AND dataset NOT IN ({in_list})",
                     sample_expression_sql="dataset",
-                    message_factory=lambda count,
-                    sample,
-                    allowed=dataset_allowed_display: (
+                    message_factory=lambda count, sample, allowed=dataset_allowed_display: (
                         "Column 'dataset' has value(s) not declared in CDEsMetadata "
                         f"enumerations. Allowed values: [{allowed}]. "
                         f"Found {count} invalid row(s), example invalid value: {sample!r}."

{exadata_validator-0.0.1/data_validator → exadata_validator-1.1.0/validator}/reporting.py

@@ -1,6 +1,5 @@
 from __future__ import annotations
 
-import json
 from dataclasses import dataclass
 from dataclasses import field
 from datetime import datetime
@@ -61,10 +60,6 @@ class ValidationReport:
 def render_report(report: ValidationReport, output_format: str) -> str:
     if output_format == "text":
         return _render_text(report)
-    if output_format == "json":
-        return json.dumps(report.to_dict(), indent=2)
-    if output_format == "ndjson":
-        return _render_ndjson(report)
     if output_format == "html":
         return _render_html(report)
     raise ValueError(f"Unsupported report format: {output_format}")
@@ -119,31 +114,6 @@ def _render_text(report: ValidationReport) -> str:
     return "\n".join(lines)
 
 
-def _render_ndjson(report: ValidationReport) -> str:
-    lines = [
-        json.dumps(
-            {
-                "type": "summary",
-                "folder": report.folder,
-                "generated_at": report.generated_at,
-                "files_checked": len(report.files_checked),
-                "error_count": len(report.issues),
-            }
-        )
-    ]
-    for issue in report.issues:
-        lines.append(
-            json.dumps(
-                {
-                    "type": "issue",
-                    "folder": report.folder,
-                    **issue.to_dict(),
-                }
-            )
-        )
-    return "\n".join(lines)
-
-
 def _render_html(report: ValidationReport) -> str:
     grouped_sections: list[str] = []
     grouped_issues = _group_issues_by_file(report)

{exadata_validator-0.0.1/data_validator → exadata_validator-1.1.0/validator}/usecases.py

@@ -6,18 +6,16 @@ from pathlib import Path
 
 import duckdb
 
-from data_validator.dataelements import flatten_cdes
-from data_validator.dataelements import (
-    validate_dataset_present_on_cdes_with_proper_format,
-)
-from data_validator.dataelements import validate_longitudinal_data_model
-from data_validator.duckdb_validator import DuckDBDatasetValidator
-from data_validator.exceptions import FileContentError
-from data_validator.exceptions import InvalidDataModelError
-from data_validator.exceptions import InvalidDatasetError
-from data_validator.exceptions import UserInputError
-from data_validator.reporting import ValidationIssue
-from data_validator.reporting import ValidationReport
+from validator.dataelements import flatten_cdes
+from validator.dataelements import validate_dataset_present_on_cdes_with_proper_format
+from validator.dataelements import validate_longitudinal_data_model
+from validator.duckdb_validator import DuckDBDatasetValidator
+from validator.exceptions import FileContentError
+from validator.exceptions import InvalidDataModelError
+from validator.exceptions import InvalidDatasetError
+from validator.exceptions import UserInputError
+from validator.reporting import ValidationIssue
+from validator.reporting import ValidationReport
 
 LONGITUDINAL = "longitudinal"
 

exadata_validator-0.0.1/data_validator/__main__.py

@@ -1,4 +0,0 @@
-from data_validator.commands import entry
-
-if __name__ == "__main__":
-    entry()