gsoc26 : merging gsoc 2026 branch to main branch

.github/workflows/docker-publish.yml

@@ -40,12 +40,3 @@ jobs:
           tags: |
             dbpedia/databus-python-client:latest
             dbpedia/databus-python-client:${{ steps.package.outputs.version }}
-
-      - name: Update Docker Hub overview
-        uses: peter-evans/dockerhub-description@v5
-        with:
-          username: ${{ secrets.DBP_DOCKERHUB_CREDENTIAL_USERNAME }}
-          password: ${{ secrets.DBP_DOCKERHUB_CREDENTIAL_TOKEN_PUSHIMAGES }}
-          repository: dbpedia/databus-python-client
-          short-description: Command-line and Python client for downloading, deploying and deleting datasets on DBpedia Databus.
-          readme-filepath: ./doc/docker/README.md

.gitignore

@@ -35,6 +35,12 @@ share/python-wheels/
 *.egg
 MANIFEST
 
+# Windows-specific: MANIFEST above matches databusclient/manifest/ case-insensitively
+# on Windows, preventing the manifest module from being committed.
+!databusclient/manifest/
+!databusclient/manifest/**
+databusclient/manifest/__pycache__/
+
 # PyInstaller
 #  Usually these files are written by a python script from a template
 #  before PyInstaller builds the exe, so as to inject date/other infos into it.
@@ -167,4 +173,4 @@ cython_debug/
 #  and can be added to the global gitignore or merged into this file.  For a more nuclear
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
 .idea/
-
+workflow-output/

databusclient/__init__.py

@@ -5,31 +5,11 @@
 ``python -m databusclient``.
 """
 
-from importlib.metadata import PackageNotFoundError, version
-from pathlib import Path
-import tomllib
-
 from databusclient import cli
 from databusclient.api.deploy import create_dataset, create_distribution, deploy
+from databusclient.version import __version__
 
-
-# Source checkouts do not always have current package metadata installed, so
-# prefer pyproject.toml locally and fall back to installed metadata for wheels
-def _get_version() -> str:
-    pyproject = Path(__file__).resolve().parent.parent / "pyproject.toml"
-    if pyproject.exists():
-        with pyproject.open("rb") as f:
-            return tomllib.load(f)["tool"]["poetry"]["version"]
-
-    try:
-        return version("databusclient")
-    except PackageNotFoundError:
-        return "0.0.0"
-
-
-__version__ = _get_version()
-
-__all__ = ["create_dataset", "deploy", "create_distribution"]
+__all__ = ["__version__", "create_dataset", "deploy", "create_distribution"]
 
 
 def run():

databusclient/api/convert.py

@@ -0,0 +1,48 @@
+from databusclient.filehandling.format import convert_file, get_converted_filename
+from databusclient.filehandling import mapping as _mapping
+
+from databusclient.filehandling.format import (
+    QuadHandler,
+    TSDHandler,
+    TripleHandler,
+    _quad_handler,
+    _tsd_handler,
+    _triple_handler,
+)
+
+__all__ = [
+    "convert_file",
+    "get_converted_filename",
+    "QuadHandler",
+    "TSDHandler",
+    "TripleHandler",
+]
+
+convert_rdf_to_csv = _mapping.convert_rdf_to_csv
+
+
+def convert_rdf_triple_format(
+    source: str,
+    target: str,
+    input_format: str,
+    output_format: str,
+) -> None:
+    _triple_handler.convert(source, target, input_format, output_format)
+
+
+def convert_rdf_quad_format(
+    source: str,
+    target: str,
+    input_format: str,
+    output_format: str,
+) -> None:
+    _quad_handler.convert(source, target, input_format, output_format)
+
+
+def convert_tabular_format(
+    source: str,
+    target: str,
+    input_format: str,
+    output_format: str,
+) -> None:
+    _tsd_handler.convert(source, target, input_format, output_format)

databusclient/api/delete.py

@@ -23,13 +23,16 @@ class DeleteQueue:
     Allows adding multiple databus URIs to a queue and executing their deletion in batch.
     """
 
-    def __init__(self, databus_key: str):
+    def __init__(self, databus_key: str, manifest_context=None):
         """Create a DeleteQueue bound to a given Databus API key.
 
         Args:
             databus_key: API key used to authenticate deletion requests.
+            manifest_context: Optional ManifestContext to record deletion
+                outcomes into. Passed through to _delete_list on execute().
         """
         self.databus_key = databus_key
+        self.manifest_context = manifest_context
         self.queue: set[str] = set()
 
     def add_uri(self, databusURI: str):
@@ -69,11 +72,13 @@ def execute(self):
         """Execute all queued deletions.
 
         Each queued URI will be deleted using `_delete_resource`.
+        Passes manifest_context through so deletions are recorded.
         """
         _delete_list(
             list(self.sorted_queue()),
             self.databus_key,
             force=True,
+            manifest_context=self.manifest_context,
         )
 
 
@@ -116,6 +121,7 @@ def _delete_resource(
     dry_run: bool = False,
     force: bool = False,
     queue: DeleteQueue = None,
+    manifest_context=None,
 ):
     """Delete a single Databus resource (version, artifact, group).
 
@@ -144,6 +150,8 @@ def _delete_resource(
 
     if dry_run:
         print(f"[DRY RUN] Would delete: {databusURI}")
+        if manifest_context is not None:
+            manifest_context.record_file(url=databusURI, status="dry_run")
         return
 
     if queue is not None:
@@ -156,6 +164,8 @@ def _delete_resource(
 
     if response.status_code in (200, 204):
         print(f"Successfully deleted: {databusURI}")
+        if manifest_context is not None:
+            manifest_context.record_file(url=databusURI, status="success")
     else:
         raise Exception(
             f"Failed to delete {databusURI}: {response.status_code} - {response.text}"
@@ -168,6 +178,7 @@ def _delete_list(
     dry_run: bool = False,
     force: bool = False,
     queue: DeleteQueue = None,
+    manifest_context=None,
 ):
     """Delete a list of Databus resources.
 
@@ -180,7 +191,7 @@ def _delete_list(
     """
     for databusURI in databusURIs:
         _delete_resource(
-            databusURI, databus_key, dry_run=dry_run, force=force, queue=queue
+            databusURI, databus_key, dry_run=dry_run, force=force, queue=queue, manifest_context=manifest_context
         )
 
 
@@ -190,6 +201,7 @@ def _delete_artifact(
     dry_run: bool = False,
     force: bool = False,
     queue: DeleteQueue = None,
+    manifest_context=None,
 ):
     """Delete an artifact and all its versions.
 
@@ -223,11 +235,11 @@ def _delete_artifact(
         else:
             # Delete all versions
             _delete_list(
-                version_uris, databus_key, dry_run=dry_run, force=force, queue=queue
+                version_uris, databus_key, dry_run=dry_run, force=force, queue=queue, manifest_context=manifest_context
             )
 
     # Finally, delete the artifact itself
-    _delete_resource(databusURI, databus_key, dry_run=dry_run, force=force, queue=queue)
+    _delete_resource(databusURI, databus_key, dry_run=dry_run, force=force, queue=queue,manifest_context=manifest_context)
 
 
 def _delete_group(
@@ -236,6 +248,7 @@ def _delete_group(
     dry_run: bool = False,
     force: bool = False,
     queue: DeleteQueue = None,
+    manifest_context=None,
 ):
     """Delete a group and all its artifacts and versions.
 
@@ -266,14 +279,14 @@ def _delete_group(
     # Delete all artifacts (which deletes their versions)
     for artifact_uri in artifact_uris:
         _delete_artifact(
-            artifact_uri, databus_key, dry_run=dry_run, force=force, queue=queue
+            artifact_uri, databus_key, dry_run=dry_run, force=force, queue=queue, manifest_context=manifest_context
         )
 
     # Finally, delete the group itself
-    _delete_resource(databusURI, databus_key, dry_run=dry_run, force=force, queue=queue)
+    _delete_resource(databusURI, databus_key, dry_run=dry_run, force=force, queue=queue,manifest_context=manifest_context)
 
 
-def delete(databusURIs: List[str], databus_key: str, dry_run: bool, force: bool):
+def delete(databusURIs: List[str], databus_key: str, dry_run: bool, force: bool, manifest_context=None):
     """Delete a dataset from the databus.
 
     Delete a group, artifact, or version identified by the given databus URI.
@@ -286,7 +299,7 @@ def delete(databusURIs: List[str], databus_key: str, dry_run: bool, force: bool)
         force: If True, skip confirmation prompt and proceed with deletion.
     """
 
-    queue = DeleteQueue(databus_key)
+    queue = DeleteQueue(databus_key, manifest_context=manifest_context)
 
     for databusURI in databusURIs:
         _host, _account, group, artifact, version, file = (
@@ -296,24 +309,24 @@ def delete(databusURIs: List[str], databus_key: str, dry_run: bool, force: bool)
         if group == "collections" and artifact is not None:
             print(f"Deleting collection: {databusURI}")
             _delete_resource(
-                databusURI, databus_key, dry_run=dry_run, force=force, queue=queue
+                databusURI, databus_key, dry_run=dry_run, force=force, queue=queue, manifest_context=manifest_context
             )
         elif file is not None:
             print(f"Deleting file is not supported via API: {databusURI}")
         elif version is not None:
             print(f"Deleting version: {databusURI}")
             _delete_resource(
-                databusURI, databus_key, dry_run=dry_run, force=force, queue=queue
+                databusURI, databus_key, dry_run=dry_run, force=force, queue=queue, manifest_context=manifest_context
             )
         elif artifact is not None:
             print(f"Deleting artifact and all its versions: {databusURI}")
             _delete_artifact(
-                databusURI, databus_key, dry_run=dry_run, force=force, queue=queue
+                databusURI, databus_key, dry_run=dry_run, force=force, queue=queue, manifest_context=manifest_context
             )
         elif group is not None and group != "collections":
             print(f"Deleting group and all its artifacts and versions: {databusURI}")
             _delete_group(
-                databusURI, databus_key, dry_run=dry_run, force=force, queue=queue
+                databusURI, databus_key, dry_run=dry_run, force=force, queue=queue, manifest_context=manifest_context
             )
         else:
             print(f"Deleting {databusURI} is not supported.")

databusclient/api/deploy.py

@@ -249,7 +249,7 @@ def create_distribution(
     return f"{url}|{meta_string}"
 
 
-def _create_distributions_from_metadata(
+def create_distributions_from_metadata(
     metadata: List[Dict[str, Union[str, int]]],
 ) -> List[str]:
     """
@@ -524,7 +524,7 @@ def deploy_from_metadata(
     Parameters
     ----------
     metadata : List[Dict[str, Union[str, int]]]
-        List of file metadata entries (see _create_distributions_from_metadata)
+        List of file metadata entries (see create_distributions_from_metadata)
     version_id : str
         Dataset version ID in the form $DATABUS_BASE/$ACCOUNT/$GROUP/$ARTIFACT/$VERSION
     artifact_version_title : str
@@ -538,7 +538,7 @@ def deploy_from_metadata(
     apikey : str
         API key for authentication
     """
-    distributions = _create_distributions_from_metadata(metadata)
+    distributions = create_distributions_from_metadata(metadata)
 
     dataset = create_dataset(
         version_id=version_id,