bam-masterdata 0.1.0__tar.gz → 0.2.0__tar.gz

bam_masterdata-0.2.0/.coveragerc

@@ -0,0 +1,6 @@
+[run]
+omit =
+    bam_masterdata/_version.py
+    */__init__.py
+    bam_masterdata/datamodel/*.py
+    bam_masterdata/openbis/*.py

{bam_masterdata-0.1.0 → bam_masterdata-0.2.0}/.vscode/settings.json

@@ -33,6 +33,7 @@
         "type": "debugpy",
         "request": "launch",
         "console": "integratedTerminal",
+        "justMyCode": false,
         "program": "${workspaceFolder}/bam_masterdata/metadata/entities.py",  // path to your entry point Python module
       },
       {
@@ -80,6 +81,18 @@
         "justMyCode": false,
         "args": ["export_to_excel"]
       },
+      {
+        "name": "BM export-to-rdf",
+        "type": "debugpy",
+        "request": "launch",
+        "cwd": "${workspaceFolder}",
+        "program": "${workspaceFolder}/.venv/bin/bam_masterdata",
+        "justMyCode": false,
+        "args": [
+          "export_to_rdf",
+          // "--python-path=${workspaceFolder}/bam_masterdata/datamodel/property_types.py"
+        ]
+      },
     ]
   },
 }

bam_masterdata-0.2.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Bundesanstalt für Materialforschung und -prüfung
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

{bam_masterdata-0.1.0 → bam_masterdata-0.2.0}/PKG-INFO

@@ -1,9 +1,31 @@
 Metadata-Version: 2.2
 Name: bam-masterdata
-Version: 0.1.0
+Version: 0.2.0
 Summary: The BAM Data Store utility tools and masterdata models wrapped in a Python package with a front-end web interface.
 Author-email: BAM Data Store <datastore@bam.de>
 Maintainer-email: "Jose M. Pizarro" <jose.pizarro-blanco@bam.de>
+License: MIT License
+        
+        Copyright (c) 2025 Bundesanstalt für Materialforschung und -prüfung
+        
+        Permission is hereby granted, free of charge, to any person obtaining a copy
+        of this software and associated documentation files (the "Software"), to deal
+        in the Software without restriction, including without limitation the rights
+        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+        copies of the Software, and to permit persons to whom the Software is
+        furnished to do so, subject to the following conditions:
+        
+        The above copyright notice and this permission notice shall be included in all
+        copies or substantial portions of the Software.
+        
+        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+        SOFTWARE.
+        
 Project-URL: Homepage, https://github.com/BAMresearch/bam-masterdata
 Project-URL: Bug Tracker, https://github.com/BAMresearch/bam-masterdata/issues
 Classifier: Natural Language :: English
@@ -16,10 +38,13 @@ Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Requires-Python: >=3.9
 Description-Content-Type: text/markdown
+License-File: LICENSE
 Requires-Dist: pybis~=1.37.1rc4
 Requires-Dist: openpyxl
 Requires-Dist: click
-Requires-Dist: pydantic
+Requires-Dist: pydantic~=2.10.5
+Requires-Dist: rdflib
+Requires-Dist: h5py~=3.12.1
 Provides-Extra: dev
 Requires-Dist: mypy==1.0.1; extra == "dev"
 Requires-Dist: ruff; extra == "dev"
@@ -47,15 +72,22 @@ Requires-Dist: mkdocstrings-python; extra == "docu"
 
 [![CI Status](https://github.com/BAMresearch/bam-masterdata/actions/workflows/actions.yml/badge.svg)](https://github.com/BAMresearch/bam-masterdata/actions/workflows/actions.yml/badge.svg)
 [![Coverage](https://coveralls.io/repos/github/BAMresearch/bam-masterdata/badge.svg?branch=main)](https://coveralls.io/repos/github/BAMresearch/bam-masterdata/badge.svg?branch=main)
+[![PyPI versions](https://img.shields.io/pypi/v/bam-masterdata)](https://img.shields.io/pypi/v/bam-masterdata)
+[![Python supported versions](https://img.shields.io/pypi/pyversions/bam-masterdata)](https://img.shields.io/pypi/pyversions/bam-masterdata)
 
 </h4>
 
 The BAM Masterdata is a repository containing all the masterdata schema defining in BAM, as well as some utility functions to handle the masterdata.
 
-<!--
-## Getting started
+If you want to install it, do:
+```sh
+pip install bam-masterdata
+```
 
- Add here installation instructions once the package is deployed -->
+In order to include the CLI functionalities, you have to add the optional `[dev]` dependencies when pip installing the package:
+```sh
+pip install bam-masterdata[dev]
+```
 
 ## Development
 

{bam_masterdata-0.1.0 → bam_masterdata-0.2.0}/README.md

@@ -12,15 +12,22 @@
 
 [![CI Status](https://github.com/BAMresearch/bam-masterdata/actions/workflows/actions.yml/badge.svg)](https://github.com/BAMresearch/bam-masterdata/actions/workflows/actions.yml/badge.svg)
 [![Coverage](https://coveralls.io/repos/github/BAMresearch/bam-masterdata/badge.svg?branch=main)](https://coveralls.io/repos/github/BAMresearch/bam-masterdata/badge.svg?branch=main)
+[![PyPI versions](https://img.shields.io/pypi/v/bam-masterdata)](https://img.shields.io/pypi/v/bam-masterdata)
+[![Python supported versions](https://img.shields.io/pypi/pyversions/bam-masterdata)](https://img.shields.io/pypi/pyversions/bam-masterdata)
 
 </h4>
 
 The BAM Masterdata is a repository containing all the masterdata schema defining in BAM, as well as some utility functions to handle the masterdata.
 
-<!--
-## Getting started
+If you want to install it, do:
+```sh
+pip install bam-masterdata
+```
 
- Add here installation instructions once the package is deployed -->
+In order to include the CLI functionalities, you have to add the optional `[dev]` dependencies when pip installing the package:
+```sh
+pip install bam-masterdata[dev]
+```
 
 ## Development
 

{bam_masterdata-0.1.0 → bam_masterdata-0.2.0}/bam_masterdata/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '0.1.0'
-__version_tuple__ = version_tuple = (0, 1, 0)
+__version__ = version = '0.2.0'
+__version_tuple__ = version_tuple = (0, 2, 0)

bam_masterdata-0.2.0/bam_masterdata/checker/__init__.py

@@ -0,0 +1 @@
+from .checker import MasterdataChecker

bam_masterdata-0.2.0/bam_masterdata/checker/checker.py

@@ -0,0 +1,45 @@
+from bam_masterdata.checker.datamodel_loader import DataModelLoader
+from bam_masterdata.checker.masterdata_validator import MasterDataValidator
+from bam_masterdata.checker.source_loader import SourceLoader
+
+
+class MasterdataChecker:
+    def __init__(self, validation_rules_path: str):
+        """
+        Initialize the comparator with validation rules.
+        """
+        self.validation_rules = self._load_validation_rules(validation_rules_path)
+        self.current_model = None
+        self.new_entities = None
+
+    def _load_validation_rules(self, path: str) -> dict:
+        """
+        Load validation rules from a JSON file.
+        """
+        pass
+
+    def load_current_model(self, source_path: str):
+        """
+        Load and transform the current data model (Pydantic classes) into JSON.
+        """
+        # loader = DataModelLoader(source_path)
+        # self.current_model = loader.parse_pydantic_models()
+
+    def load_new_entities(self, source: str, source_type: str):
+        """
+        Load new entities from various sources (Python classes, Excel, etc.).
+        """
+        # loader = SourceLoader(source, source_type)
+        # self.new_entities = loader.load()
+
+    def validate(self, mode: str = "all") -> dict:
+        """
+        Run validations. Mode can be:
+        - "self" -> Validate only the new entity structure.
+        - "compare" -> Validate new entities against current model.
+        - "all" -> Run both validation types.
+        """
+        validator = MasterDataValidator(
+            self.new_entities, self.current_model, self.validation_rules
+        )
+        return validator.validate(mode)

bam_masterdata-0.2.0/bam_masterdata/checker/datamodel_loader.py

@@ -0,0 +1,9 @@
+class DataModelLoader:
+    def __init__(self, source_path: str):
+        self.source_path = source_path
+
+    def parse_pydantic_models(self) -> dict:
+        """
+        Read and transform Pydantic classes into JSON format.
+        """
+        pass

bam_masterdata-0.2.0/bam_masterdata/checker/masterdata_validator.py

@@ -0,0 +1,34 @@
+class MasterDataValidator:
+    def __init__(self, new_entities: dict, current_model: dict, validation_rules: dict):
+        self.new_entities = new_entities
+        self.current_model = current_model
+        self.validation_rules = validation_rules
+
+    def validate(self, mode: str = "all") -> dict:
+        """
+        Run validations based on mode:
+        - "self": Validate new entity JSON structure.
+        - "compare": Validate new entities against the current model.
+        - "all": Run both.
+        """
+        results = {}
+
+        if mode in ["self", "all"]:
+            results["self_validation"] = self._validate_new_entities()
+
+        if mode in ["compare", "all"]:
+            results["comparison"] = self._compare_with_current_model()
+
+        return results
+
+    def _validate_new_entities(self) -> dict:
+        """
+        Check structure, ordering, and internal consistency of new entity JSON.
+        """
+        pass
+
+    def _compare_with_current_model(self) -> dict:
+        """
+        Compare new entities against the current model using validation rules.
+        """
+        pass

bam_masterdata-0.2.0/bam_masterdata/checker/source_loader.py

@@ -0,0 +1,27 @@
+class SourceLoader:
+    def __init__(self, source: str, source_type: str):
+        self.source = source
+        self.source_type = source_type
+
+    def load(self) -> dict:
+        """
+        Read and transform the new entity data into JSON.
+        """
+        if self.source_type == "python":
+            return self._parse_python_classes()
+        elif self.source_type == "excel":
+            return self._parse_excel()
+        else:
+            raise NotImplementedError(f"Source type {self.source_type} not supported.")
+
+    def _parse_python_classes(self) -> dict:
+        """
+        Parse new entities defined as Python classes.
+        """
+        pass
+
+    def _parse_excel(self) -> dict:
+        """
+        Parse new entities stored in an Excel file.
+        """
+        pass

{bam_masterdata-0.1.0 → bam_masterdata-0.2.0}/bam_masterdata/cli/cli.py

@@ -6,18 +6,40 @@ from pathlib import Path
 import click
 from decouple import config as environ
 from openpyxl import Workbook
+from rdflib import Graph
 
 from bam_masterdata.cli.entities_to_excel import entities_to_excel
 from bam_masterdata.cli.entities_to_json import entities_to_json
+from bam_masterdata.cli.entities_to_rdf import entities_to_rdf
 from bam_masterdata.cli.fill_masterdata import MasterdataCodeGenerator
 from bam_masterdata.logger import logger
 from bam_masterdata.utils import (
     delete_and_create_dir,
+    duplicated_property_types,
     import_module,
     listdir_py_modules,
 )
 
-DATAMODEL_DIR = os.path.join(".", "bam_masterdata", "datamodel")
+
+def find_datamodel_dir():
+    """Search for 'datamodel/' in possible locations and return its absolute path."""
+    possible_locations = [
+        # Case: Running from a project with `datamodel/`
+        Path.cwd() / "datamodel",
+        # Case: Running inside bam-masterdata
+        Path.cwd() / "bam_masterdata" / "datamodel",
+        # Case: Running inside installed package
+        Path(__file__).parent / "datamodel",
+    ]
+
+    for path in possible_locations:
+        if path.exists():
+            return str(path.resolve())
+
+    raise FileNotFoundError("Could not find a valid 'datamodel/' directory.")
+
+
+DATAMODEL_DIR = find_datamodel_dir()
 
 
 @click.group(help="Entry point to run `bam_masterdata` CLI commands.")
@@ -129,11 +151,20 @@ def fill_masterdata(url, excel_file):
     Default is `./bam_masterdata/datamodel/`.
     """,
 )
-def export_to_json(force_delete, python_path):
-    # Get the directories from the Python modules and the export directory for the static artifacts
-    export_dir = os.path.join(".", "artifacts")
-
+@click.option(
+    "--export-dir",
+    type=str,
+    required=False,
+    default="./artifacts",
+    help="The directory where the JSON files will be exported. Default is `./artifacts`.",
+)
+def export_to_json(force_delete, python_path, export_dir):
     # Delete and create the export directory
+    if force_delete:
+        click.confirm(
+            f"Are you sure you want to delete the directory {export_dir}?",
+            abort=True,
+        )
     delete_and_create_dir(
         directory_path=export_dir,
         logger=logger,
@@ -145,6 +176,12 @@ def export_to_json(force_delete, python_path):
 
     # Process each module using the `model_to_json` method of each entity
     for module_path in py_modules:
+        if module_path.endswith("property_types.py"):
+            if duplicated_property_types(module_path=module_path, logger=logger):
+                click.echo(
+                    "Please fix the duplicated property types before exporting to RDF/XML."
+                )
+                return
         entities_to_json(module_path=module_path, export_dir=export_dir, logger=logger)
 
     click.echo(f"All entity artifacts have been generated and saved to {export_dir}")
@@ -173,11 +210,20 @@ def export_to_json(force_delete, python_path):
     Default is `./bam_masterdata/datamodel/`.
     """,
 )
-def export_to_excel(force_delete, python_path):
-    # Get the directories from the Python modules and the export directory for the static artifacts
-    export_dir = os.path.join(".", "artifacts")
-
+@click.option(
+    "--export-dir",
+    type=str,
+    required=False,
+    default="./artifacts",
+    help="The directory where the Excel file will be exported. Default is `./artifacts`.",
+)
+def export_to_excel(force_delete, python_path, export_dir):
     # Delete and create the export directory
+    if force_delete:
+        click.confirm(
+            f"Are you sure you want to delete the directory {export_dir}?",
+            abort=True,
+        )
     delete_and_create_dir(
         directory_path=export_dir,
         logger=logger,
@@ -188,14 +234,19 @@ def export_to_excel(force_delete, python_path):
     py_modules = listdir_py_modules(directory_path=python_path, logger=logger)
 
     # Load the definitions module classes
-    definitions_module = import_module(
-        module_path="./bam_masterdata/metadata/definitions.py"
-    )
+    definitions_path = Path(__file__).parent / ".." / "metadata" / "definitions.py"
+    definitions_module = import_module(module_path=str(definitions_path.resolve()))
 
     # Process the modules and save the entities to the openBIS masterdata Excel file
-    masterdata_file = os.path.join(".", "artifacts", "masterdata.xlsx")
+    masterdata_file = os.path.join(export_dir, "masterdata.xlsx")
     wb = Workbook()
     for i, module_path in enumerate(py_modules):
+        if module_path.endswith("property_types.py"):
+            if duplicated_property_types(module_path=module_path, logger=logger):
+                click.echo(
+                    "Please fix the duplicated property types before exporting to RDF/XML."
+                )
+                return
         if i == 0:
             ws = wb.active
         else:
@@ -216,5 +267,77 @@ def export_to_excel(force_delete, python_path):
     click.echo(f"All masterdata have been generated and saved to {masterdata_file}")
 
 
+@cli.command(
+    name="export_to_rdf",
+    help="Export entities to a RDF/XML file in the path `./artifacts/bam_masterdata.owl`.",
+)
+@click.option(
+    "--force-delete",
+    type=bool,
+    required=False,
+    default=False,
+    help="""
+    (Optional) If set to `True`, it will delete the current `./artifacts/` folder and create a new one. Default is `False`.
+    """,
+)
+@click.option(
+    "--python-path",
+    type=str,
+    required=False,
+    default=DATAMODEL_DIR,
+    help="""
+    (Optional) The path to the individual Python module or the directory containing the Python modules to process the datamodel.
+    Default is `./bam_masterdata/datamodel/`.
+    """,
+)
+@click.option(
+    "--export-dir",
+    type=str,
+    required=False,
+    default="./artifacts",
+    help="The directory where the RDF/XML file will be exported. Default is `./artifacts`.",
+)
+def export_to_rdf(force_delete, python_path, export_dir):
+    # Delete and create the export directory
+    if force_delete:
+        click.confirm(
+            f"Are you sure you want to delete the directory {export_dir}?",
+            abort=True,
+        )
+    delete_and_create_dir(
+        directory_path=export_dir,
+        logger=logger,
+        force_delete=force_delete,
+    )
+
+    # Get the Python modules to process the datamodel
+    py_modules = listdir_py_modules(directory_path=python_path, logger=logger)
+    # ! Remove the module containing 'vocabulary_types.py'
+    py_modules = [
+        module for module in py_modules if "vocabulary_types.py" not in module
+    ]
+
+    # Process each module using the `model_to_rdf` method of each entity
+    graph = Graph()
+    for module_path in py_modules:
+        if module_path.endswith("property_types.py"):
+            if duplicated_property_types(module_path=module_path, logger=logger):
+                click.echo(
+                    "Please fix the duplicated property types before exporting to RDF/XML."
+                )
+                return
+        entities_to_rdf(graph=graph, module_path=module_path, logger=logger)
+
+    # Saving RDF/XML to file
+    rdf_output = graph.serialize(format="pretty-xml")
+    masterdata_file = os.path.join(export_dir, "masterdata.owl")
+    with open(masterdata_file, "w", encoding="utf-8") as f:
+        f.write(rdf_output)
+
+    click.echo(
+        f"All masterdata has been generated in RDF/XML format and saved to {masterdata_file}"
+    )
+
+
 if __name__ == "__main__":
     cli()