Feature to limit file uploads to datasets

doc/release-notes/11275-add-limit-to-number-of-dataset-files.md

@@ -0,0 +1,5 @@
+### Files attached to a Dataset can now be limited by count
+
+Added the ability to set a limit on the number of files that can be uploaded to a Dataset. Limits can be set globally through a JVM setting or set per Collection or Dataset.
+
+See also [the guides](https://dataverse-guide--11359.org.readthedocs.build/en/11359/api/native-api.html#imposing-a-limit-to-the-number-of-files-allowed-to-be-uploaded-to-a-dataset), #11275, and #11359.

doc/sphinx-guides/source/api/native-api.rst

@@ -2474,7 +2474,7 @@ When adding a file to a dataset, you can optionally specify the following:
 - Whether or not the file is restricted.
 - Whether or not the file skips :doc:`tabular ingest </user/tabulardataingest/index>`. If the ``tabIngest`` parameter is not specified, it defaults to ``true``.
 
-Note that when a Dataverse installation is configured to use S3 storage with direct upload enabled, there is API support to send a file directly to S3. This is more complex and is described in the :doc:`/developers/s3-direct-upload-api` guide.
+Note that when a Dataverse installation is configured to use S3 storage with direct upload enabled, there is API support to send a file directly to S3. This is more complex and is described in the :doc:`/developers/s3-direct-upload-api` guide. Also, see :ref:`set-dataset-file-limit-api`, for limitations to the number of files allowed per Dataset.
 
 In the curl example below, all of the above are specified but they are optional.
 
@@ -2699,6 +2699,58 @@ In some circumstances, it may be useful to move or copy files into Dataverse's s
 Two API calls are available for this use case to add files to a dataset or to replace files that were already in the dataset.
 These calls were developed as part of Dataverse's direct upload mechanism and are detailed in :doc:`/developers/s3-direct-upload-api`.
 
+Imposing a limit to the number of files allowed to be uploaded to a Dataset
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Having thousands of files in a Dataset can cause issues. Most users would be better off with the data repackaged in fewer large bundles. To help curtail these issues, a limit can be set to prevent the number of file uploads from getting out of hand.
+
+The limit can be set via JVM setting :ref:`dataverse.files.default-dataset-file-count-limit` to be installation wide, or, set on each Collection/Dataset.
+
+For Installation wide limit, the limit can be set via JVM. ./asadmin $ASADMIN_OPTS create-jvm-options "-Ddataverse.files.default-dataset-file-count-limit=<limit>"
+
+For Collections, the attribute can be controlled by calling the Create or Update Dataverse API and adding ``datasetFileCountLimit=500`` to the Json body.
+
+For Datasets, the attribute can be set using the `Update Dataset Files Limit <#setting-the-files-count-limit-on-a-dataset>`_ API and passing the qp `fileCountLimit=500`.
+
+Setting a value of -1 will clear the limit for that level. If no limit is found on the Dataset, the hierarchy of parent nodes will be checked until finally the JVM setting is checked.
+
+With this setting set a 400 error response stating that the limit has been reached, including the effective limit, will be returned.
+
+Please note that a superuser will be exempt from this rule.
+
+The check will use the value defined in the Dataset first, and if not set (value <1) the Dataverse/Collection will be checked, and finally the JVM setting.
+
+.. _set-dataset-file-limit-api:
+
+Setting the files count limit on a Dataset
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+In order to update the number of files allowed for a Dataset, without causing a Draft version of the Dataset being created, the following API can be used
+
+.. note:: To clear the limit simply set the limit to -1 or call the DELETE API.
+
+.. code-block:: bash
+
+  export API_TOKEN=xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx
+  export SERVER_URL=https://demo.dataverse.org
+  export ID=24
+  export LIMIT=500
+
+  curl -H "X-Dataverse-key:$API_TOKEN" -X POST "$SERVER_URL/api/datasets/$ID/files/uploadlimit/$LIMIT"
+
+To delete the existing limit:
+
+  curl -H "X-Dataverse-key:$API_TOKEN" -X DELETE "$SERVER_URL/api/datasets/$ID/files/uploadlimit"
+
+The fully expanded example above (without environment variables) looks like this:
+
+.. code-block:: bash
+
+  curl -H "X-Dataverse-key:xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx" -X POST "https://demo.dataverse.org/api/datasets/24/files/uploadlimit/500"
+
+To delete the existing limit:
+
+  curl -H "X-Dataverse-key:xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx" -X DELETE "https://demo.dataverse.org/api/datasets/24/files/uploadlimit"
+
 Report the data (file) size of a Dataset
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 

doc/sphinx-guides/source/installation/config.rst

@@ -2561,6 +2561,20 @@ Notes:
 - During startup, this directory will be checked for existence and write access. It will be created for you
   if missing. If it cannot be created or does not have proper write access, application deployment will fail.
 
+.. _dataverse.files.default-dataset-file-count-limit:
+
+dataverse.files.default-dataset-file-count-limit
+++++++++++++++++++++++++++++++++++++++++++++++++
+
+Configure a limit to the maximum number of Datafiles that can be uploaded to a Dataset.
+
+Notes:
+
+- This is a default that can be overwritten in any Dataverse/Collection or Dataset.
+- A value less than 1 will be treated as no limit set.
+- Changing this value will not delete any existing files. It is only intended for preventing new files from being uploaded.
+- Superusers will not be governed by this rule.
+
 .. _dataverse.files.uploads:
 
 dataverse.files.uploads

scripts/search/tests/data/dataset-finch1-fileLimit.json

@@ -0,0 +1,82 @@
+{
+  "datasetVersion": {
+    "license": {
+      "name": "CC0 1.0",
+      "uri": "http://creativecommons.org/publicdomain/zero/1.0"
+    },
+    "metadataBlocks": {
+      "citation": {
+        "fields": [
+          {
+            "value": "Darwin's Finches",
+            "typeClass": "primitive",
+            "multiple": false,
+            "typeName": "title"
+          },
+          {
+            "value": [
+              {
+                "authorName": {
+                  "value": "Finch, Fiona",
+                  "typeClass": "primitive",
+                  "multiple": false,
+                  "typeName": "authorName"
+                },
+                "authorAffiliation": {
+                  "value": "Birds Inc.",
+                  "typeClass": "primitive",
+                  "multiple": false,
+                  "typeName": "authorAffiliation"
+                }
+              }
+            ],
+            "typeClass": "compound",
+            "multiple": true,
+            "typeName": "author"
+          },
+          {
+            "value": [ 
+                { "datasetContactEmail" : {
+                    "typeClass": "primitive",
+                    "multiple": false,
+                    "typeName": "datasetContactEmail",
+                    "value" : "[email protected]"
+                },
+                "datasetContactName" : {
+                    "typeClass": "primitive",
+                    "multiple": false,
+                    "typeName": "datasetContactName",
+                    "value": "Finch, Fiona"
+                }
+            }],
+            "typeClass": "compound",
+            "multiple": true,
+            "typeName": "datasetContact"
+          },
+          {
+            "value": [ {
+               "dsDescriptionValue":{
+                "value":   "Darwin's finches (also known as the Galápagos finches) are a group of about fifteen species of passerine birds.",
+                "multiple":false,
+               "typeClass": "primitive",
+               "typeName": "dsDescriptionValue"
+            }}],
+            "typeClass": "compound",
+            "multiple": true,
+            "typeName": "dsDescription"
+          },
+          {
+            "value": [
+              "Medicine, Health and Life Sciences"
+            ],
+            "typeClass": "controlledVocabulary",
+            "multiple": true,
+            "typeName": "subject"
+          }
+        ],
+        "displayName": "Citation Metadata"
+      }
+    }
+  },
+  "datasetFileCountLimit": 100
+}

src/main/java/edu/harvard/iq/dataverse/Dataset.java

@@ -72,7 +72,9 @@
     @NamedQuery(name = "Dataset.findByReleaseUserId",
                 query = "SELECT o FROM Dataset o WHERE o.releaseUser.id=:releaseUserId"),
     @NamedQuery(name = "Dataset.countAll",
-                query = "SELECT COUNT(ds) FROM Dataset ds")
+                query = "SELECT COUNT(ds) FROM Dataset ds"),
+    @NamedQuery(name = "Dataset.countFilesByOwnerId",
+                query = "SELECT COUNT(dvo) FROM DvObject dvo WHERE dvo.owner.id=:ownerId AND dvo.dtype='DataFile'")
 })
 @NamedNativeQuery(
         name = "Dataset.findAllOrSubsetOrderByFilesOwned",

src/main/java/edu/harvard/iq/dataverse/DatasetPage.java

@@ -4082,7 +4082,16 @@ public String save() {
                     // have been created in the dataset.
                     dataset = datasetService.find(dataset.getId());
 
-                    List<DataFile> filesAdded = ingestService.saveAndAddFilesToDataset(dataset.getOrCreateEditVersion(), newFiles, null, true);
+                    boolean ignoreUploadFileLimits = this.session.getUser() != null ? this.session.getUser().isSuperuser() : false;
+                    List<DataFile> filesAdded = ingestService.saveAndAddFilesToDataset(dataset.getOrCreateEditVersion(), newFiles, null, true, ignoreUploadFileLimits);
+                    if (filesAdded.size() < nNewFiles) {
+                        // Not all files were saved
+                        Integer limit = dataset.getEffectiveDatasetFileCountLimit();
+                        if (limit != null) {
+                            String msg = BundleUtil.getStringFromBundle("file.add.count_exceeds_limit", List.of(limit.toString()));
+                            JsfHelper.addInfoMessage(msg);
+                        }
+                    }
                     newFiles.clear();
 
                     // and another update command:

src/main/java/edu/harvard/iq/dataverse/DatasetServiceBean.java

@@ -1077,4 +1077,14 @@ public long getDatasetCount() {
         return em.createNamedQuery("Dataset.countAll", Long.class).getSingleResult();
     }
 
+    /**
+     *
+     * @param id - owner id
+     * @return Total number of datafiles for this dataset/owner
+     */
+    public int getDataFileCountByOwner(long id) {
+        Long c = em.createNamedQuery("Dataset.countFilesByOwnerId", Long.class).setParameter("ownerId", id).getSingleResult();
+        return c.intValue(); // ignoring the truncation since the number should never be too large
+    }
+
 }

src/main/java/edu/harvard/iq/dataverse/DvObject.java

@@ -506,7 +506,6 @@ public StorageQuota getStorageQuota() {
     public void setStorageQuota(StorageQuota storageQuota) {
         this.storageQuota = storageQuota;
     }
-
     /**
      * 
      * @param other 

src/main/java/edu/harvard/iq/dataverse/DvObjectContainer.java

@@ -9,11 +9,9 @@
 import edu.harvard.iq.dataverse.util.json.JsonUtil;
 import jakarta.json.JsonObject;
 import jakarta.json.JsonObjectBuilder;
-import jakarta.persistence.CascadeType;
+import jakarta.persistence.*;
+
 import java.util.Optional;
-import jakarta.persistence.MappedSuperclass;
-import jakarta.persistence.OneToOne;
-import jakarta.persistence.Transient;
 
 import org.apache.commons.lang3.StringUtils;
 
@@ -56,6 +54,9 @@ public boolean isEffectivelyPermissionRoot() {
 
     @OneToOne(mappedBy = "dvObjectContainer",cascade={ CascadeType.REMOVE, CascadeType.PERSIST}, orphanRemoval=true)
     private StorageUse storageUse;
+
+    @Column( nullable = true )
+    private Integer datasetFileCountLimit;
 
     public String getEffectiveStorageDriverId() {
         String id = storageDriver;
@@ -260,5 +261,23 @@ public PidProvider getEffectivePidGenerator() {
         }
         return pidGenerator;
     }
+    public Integer getDatasetFileCountLimit() {
+        return datasetFileCountLimit;
+    }
+    public void setDatasetFileCountLimit(Integer datasetFileCountLimit) {
+        this.datasetFileCountLimit = datasetFileCountLimit != null && datasetFileCountLimit < 0 ? null : datasetFileCountLimit;
+    }
 
+    public Integer getEffectiveDatasetFileCountLimit() {
+        if (!isDatasetFileCountLimitSet(getDatasetFileCountLimit()) && getOwner() != null) {
+            return getOwner().getEffectiveDatasetFileCountLimit();
+        } else if (!isDatasetFileCountLimitSet(getDatasetFileCountLimit())) {
+                Optional<Integer> opt = JvmSettings.DEFAULT_DATASET_FILE_COUNT_LIMIT.lookupOptional(Integer.class);
+                return (opt.isPresent()) ? opt.get() : null;
+        }
+        return getDatasetFileCountLimit();
+    }
+    public boolean isDatasetFileCountLimitSet(Integer datasetFileCountLimit) {
+        return datasetFileCountLimit != null && datasetFileCountLimit >= 0;
+    }
 }

src/main/java/edu/harvard/iq/dataverse/EditDatafilesPage.java

@@ -201,7 +201,10 @@ public enum Referrer {
     private Long maxIngestSizeInBytes = null;
     // CSV: 4.8 MB, DTA: 976.6 KB, XLSX: 5.7 MB, etc.
     private String humanPerFormatTabularLimits = null;
-    private Integer multipleUploadFilesLimit = null; 
+    private Integer multipleUploadFilesLimit = null;
+    // Maximum number of files per dataset allowed ot be uploaded
+    private Integer maxFileUploadCount = null;
+    private Integer fileUploadsAvailable = null;
 
     //MutableBoolean so it can be passed from DatasetPage, supporting DatasetPage.cancelCreate()
     private MutableBoolean uploadInProgress = null;
@@ -393,6 +396,10 @@ public String populateHumanPerFormatTabularLimits() {
         return String.join(", ", formatLimits);
     }
 
+    public Integer getFileUploadsAvailable() {
+        return fileUploadsAvailable != null ? fileUploadsAvailable : -1;
+    }
+
     /*
         The number of files the GUI user is allowed to upload in one batch, 
         via drag-and-drop, or through the file select dialog. Now configurable 
@@ -543,17 +550,28 @@ public String initCreateMode(String modeToken, DatasetVersion version, MutableBo
         this.maxIngestSizeInBytes = systemConfig.getTabularIngestSizeLimit();
         this.humanPerFormatTabularLimits = populateHumanPerFormatTabularLimits();
         this.multipleUploadFilesLimit = systemConfig.getMultipleUploadFilesLimit();
-
+        setFileUploadCountLimits(0);
         logger.fine("done");
 
         saveEnabled = true;
 
         return null;
     }
+    private void setFileUploadCountLimits(int preLoaded) {
+        this.maxFileUploadCount = this.maxFileUploadCount == null ? dataset.getEffectiveDatasetFileCountLimit() : this.maxFileUploadCount;
+        Long id = dataset.getId() != null ? dataset.getId() : dataset.getOwner() != null ? dataset.getOwner().getId() : null;
+        this.fileUploadsAvailable = this.maxFileUploadCount != null && id != null ?
+                Math.max(0, this.maxFileUploadCount - datasetService.getDataFileCountByOwner(id) - preLoaded) :
+                -1;
+    }
 
     public boolean isQuotaExceeded() {
         return systemConfig.isStorageQuotasEnforced() && uploadSessionQuota != null && uploadSessionQuota.getRemainingQuotaInBytes() == 0;
     }
+    public boolean isFileUploadCountExceeded() {
+        boolean ignoreLimit = this.session.getUser().isSuperuser();
+        return !ignoreLimit && !isFileReplaceOperation() && fileUploadsAvailable != null && fileUploadsAvailable == 0;
+    }
 
     public String init() {
         // default mode should be EDIT
@@ -604,8 +622,8 @@ public String init() {
         }
         this.maxIngestSizeInBytes = systemConfig.getTabularIngestSizeLimit();
         this.humanPerFormatTabularLimits = populateHumanPerFormatTabularLimits();
-        this.multipleUploadFilesLimit = systemConfig.getMultipleUploadFilesLimit();        
-
+        this.multipleUploadFilesLimit = systemConfig.getMultipleUploadFilesLimit();
+        setFileUploadCountLimits(0);
         hasValidTermsOfAccess = isHasValidTermsOfAccess();
         if (!hasValidTermsOfAccess) {
             PrimeFaces.current().executeScript("PF('blockDatasetForm').show()");
@@ -1103,9 +1121,17 @@ public String save() {
                     }
                 }
             }
-
+            boolean ignoreUploadFileLimits = this.session.getUser() != null ? this.session.getUser().isSuperuser() : false;
             // Try to save the NEW files permanently: 
-            List<DataFile> filesAdded = ingestService.saveAndAddFilesToDataset(workingVersion, newFiles, null, true); 
+            List<DataFile> filesAdded = ingestService.saveAndAddFilesToDataset(workingVersion, newFiles, null, true, ignoreUploadFileLimits);
+            if (filesAdded.size() < nNewFiles) {
+                // Not all files were saved
+                Integer limit = dataset.getEffectiveDatasetFileCountLimit();
+                if (limit != null) {
+                    String msg = BundleUtil.getStringFromBundle("file.add.count_exceeds_limit", List.of(limit.toString()));
+                    JsfHelper.addInfoMessage(msg);
+                }
+            }
 
             // reset the working list of fileMetadatas, as to only include the ones
             // that have been added to the version successfully: