Skip to content

Don't allow datasets to be created from regex capture groups. #7668

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
labkey-klum wants to merge 2 commits into
base: develop
Choose a base branch
from
+30 −3
Open

Don't allow datasets to be created from regex capture groups. #7668

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2114cda
Don't allow datasets to be created from regex capture groups.
labkey-klum May 14, 2026
8c51c63
Avoid NFE.
labkey-klum May 14, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
33 changes: 30 additions & 3 deletions study/src/org/labkey/study/pipeline/FileAnalysisDatasetTask.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,7 @@
*/
package org.labkey.study.pipeline;

import org.apache.commons.lang3.math.NumberUtils;
import org.jetbrains.annotations.NotNull;
import org.labkey.api.action.BaseViewAction;
import org.labkey.api.action.NullSafeBindException;
Expand Down Expand Up @@ -96,17 +97,43 @@ public RecordedActionSet run() throws PipelineJobException

// guaranteed to only have a single file
assert jobSupport.getInputFiles().size() == 1;
StudyImpl study = getStudy();
for (FileLike file : jobSupport.getInputFiles())
{
if (params.containsKey(DATASET_ID_KEY))
inputDataMap.put(file, new Pair<>(DATASET_ID_KEY, params.get(DATASET_ID_KEY)));
{
int datasetId = NumberUtils.toInt(params.get(DATASET_ID_KEY));
if (StudyManager.getInstance().getDatasetDefinition(study, datasetId) != null)
{
_ctx.getLogger().info("Dataset matching the 'id' capture group was resolved : {}", datasetId);
inputDataMap.put(file, new Pair<>(DATASET_ID_KEY, params.get(DATASET_ID_KEY)));
}
else
{
// don't create new datasets via a capture group id
_ctx.getLogger().error("Dataset matching the 'id' capture group was not resolved : {}", datasetId);
return new RecordedActionSet();
}
}
else if (params.containsKey(DATASET_NAME_KEY))
inputDataMap.put(file, new Pair<>(DATASET_NAME_KEY, params.get(DATASET_NAME_KEY)));
{
String datasetName = params.get(DATASET_NAME_KEY);
if (StudyManager.getInstance().getDatasetDefinitionByName(study, datasetName) != null)
{
_ctx.getLogger().info("Dataset matching the 'name' capture group was resolved : {}", datasetName);
inputDataMap.put(file, new Pair<>(DATASET_NAME_KEY, datasetName));
}
else
{
// don't create new datasets via a capture group name
_ctx.getLogger().error("Dataset matching the 'name' capture group was not resolved : {}", datasetName);
return new RecordedActionSet();
}
}
else if (params.containsKey(DataTransformService.ORIGINAL_SOURCE_PATH))
inputDataMap.put(file, new Pair<>(DataTransformService.ORIGINAL_SOURCE_PATH, params.get(DataTransformService.ORIGINAL_SOURCE_PATH)));
}
List<String> readerErrors = new ArrayList<>();
StudyImpl study = getStudy();
DatasetInferSchemaReader reader = new DatasetInferSchemaReader(getDatasetsDirectory(), getStudy(), _ctx, inputDataMap);
reader.validate(readerErrors);

Expand Down