Merge branch 'IQSS:develop' into codemeta_structure

Author: doigl

.env

@@ -1,5 +1,5 @@
 APP_IMAGE=gdcc/dataverse:unstable
 POSTGRES_VERSION=17
 DATAVERSE_DB_USER=dataverse
-SOLR_VERSION=9.3.0
-SKIP_DEPLOY=0
+SOLR_VERSION=9.8.0
+SKIP_DEPLOY=0

.github/workflows/codeql.yml

@@ -0,0 +1,104 @@
+# For most projects, this workflow file will not need changing; you simply need
+# to commit it to your repository.
+#
+# You may wish to alter this file to override the set of languages analyzed,
+# or to provide custom queries or build logic.
+#
+# ******** NOTE ********
+# We have attempted to detect the languages in your repository. Please check
+# the `language` matrix defined below to confirm you have the correct set of
+# supported CodeQL languages.
+#
+name: "CodeQL Advanced"
+
+on:
+  push:
+    branches: [ "develop", "master" ]
+  pull_request:
+    branches: [ "develop", "master" ]
+  schedule:
+    - cron: '30 6 * * 4'
+
+jobs:
+  analyze:
+    name: Analyze (${{ matrix.language }})
+    # Runner size impacts CodeQL analysis time. To learn more, please see:
+    #   - https://gh.io/recommended-hardware-resources-for-running-codeql
+    #   - https://gh.io/supported-runners-and-hardware-resources
+    #   - https://gh.io/using-larger-runners (GitHub.com only)
+    # Consider using larger runners or machines with greater resources for possible analysis time improvements.
+    runs-on: ${{ (matrix.language == 'swift' && 'macos-latest') || 'ubuntu-latest' }}
+    permissions:
+      # required for all workflows
+      security-events: write
+
+      # required to fetch internal or private CodeQL packs
+      packages: read
+
+      # only required for workflows in private repositories
+      actions: read
+      contents: read
+
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+        - language: actions
+          build-mode: none
+        - language: java-kotlin
+          build-mode: none # This mode only analyzes Java. Set this to 'autobuild' or 'manual' to analyze Kotlin too.
+        - language: javascript-typescript
+          build-mode: none
+        - language: python
+          build-mode: none
+        # CodeQL supports the following values keywords for 'language': 'actions', 'c-cpp', 'csharp', 'go', 'java-kotlin', 'javascript-typescript', 'python', 'ruby', 'swift'
+        # Use `c-cpp` to analyze code written in C, C++ or both
+        # Use 'java-kotlin' to analyze code written in Java, Kotlin or both
+        # Use 'javascript-typescript' to analyze code written in JavaScript, TypeScript or both
+        # To learn more about changing the languages that are analyzed or customizing the build mode for your analysis,
+        # see https://docs.github.com/en/code-security/code-scanning/creating-an-advanced-setup-for-code-scanning/customizing-your-advanced-setup-for-code-scanning.
+        # If you are analyzing a compiled language, you can modify the 'build-mode' for that language to customize how
+        # your codebase is analyzed, see https://docs.github.com/en/code-security/code-scanning/creating-an-advanced-setup-for-code-scanning/codeql-code-scanning-for-compiled-languages
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v4
+
+    # Add any setup steps before running the `github/codeql-action/init` action.
+    # This includes steps like installing compilers or runtimes (`actions/setup-node`
+    # or others). This is typically only required for manual builds.
+    # - name: Setup runtime (example)
+    #   uses: actions/setup-example@v1
+
+    # Initializes the CodeQL tools for scanning.
+    - name: Initialize CodeQL
+      uses: github/codeql-action/init@v3
+      with:
+        languages: ${{ matrix.language }}
+        build-mode: ${{ matrix.build-mode }}
+        # If you wish to specify custom queries, you can do so here or in a config file.
+        # By default, queries listed here will override any specified in a config file.
+        # Prefix the list here with "+" to use these queries and those in the config file.
+
+        # For more details on CodeQL's query packs, refer to: https://docs.github.com/en/code-security/code-scanning/automatically-scanning-your-code-for-vulnerabilities-and-errors/configuring-code-scanning#using-queries-in-ql-packs
+        # queries: security-extended,security-and-quality
+
+    # If the analyze step fails for one of the languages you are analyzing with
+    # "We were unable to automatically build your code", modify the matrix above
+    # to set the build mode to "manual" for that language. Then modify this step
+    # to build your code.
+    # ℹ️ Command-line programs to run using the OS shell.
+    # 📚 See https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions#jobsjob_idstepsrun
+    - if: matrix.build-mode == 'manual'
+      shell: bash
+      run: |
+        echo 'If you are using a "manual" build mode for one or more of the' \
+          'languages you are analyzing, replace this with the commands to build' \
+          'your code, for example:'
+        echo '  make bootstrap'
+        echo '  make release'
+        exit 1
+
+    - name: Perform CodeQL Analysis
+      uses: github/codeql-action/analyze@v3
+      with:
+        category: "/language:${{matrix.language}}"

.github/workflows/container_base_push.yml

@@ -53,7 +53,7 @@ jobs:
             # Configure a remote ARM64 build host in addition to the local AMD64 in two steps.
             - name: Setup SSH agent
               if: ${{ github.event_name != 'schedule' }}
-              uses: webfactory/ssh-agent@v0.9.0
+              uses: webfactory/ssh-agent@v0.9.1
               with:
                   ssh-private-key: ${{ secrets.BUILDER_ARM64_SSH_PRIVATE_KEY }}
             - name: Provide the known hosts key and the builder config

.github/workflows/copy_labels.yml

@@ -0,0 +1,15 @@
+name: Copy labels from issue to pull request
+
+on:
+  pull_request:
+    types: [opened]
+
+jobs:
+  copy-labels:
+    runs-on: ubuntu-latest
+    name: Copy labels from linked issues
+    steps:
+      - name: copy-labels
+        uses: michalvankodev/copy-issue-labels@v1.3.0
+        with:
+          repo-token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/deploy_beta_testing.yml

@@ -68,7 +68,7 @@ jobs:
           overwrite: true
 
       - name: Execute payara war deployment remotely
-        uses: appleboy/ssh-action@v1.2.0
+        uses: appleboy/ssh-action@v1.2.2
         env:
           INPUT_WAR_FILE: ${{ env.war_file }}
         with:

conf/solr/schema.xml

@@ -38,36 +38,37 @@
     catchall "text" field, and use that for searching.
 -->
 
-<schema name="default-config" version="1.6">
+<schema name="default-config" version="1.7">
     <!-- attribute "name" is the name of this schema and is only used for display purposes.
-       version="x.y" is Solr's version number for the schema syntax and 
+       version="x.y" is Solr's version number for the schema syntax and
        semantics.  It should not normally be changed by applications.
 
-       1.0: multiValued attribute did not exist, all fields are multiValued 
+       1.0: multiValued attribute did not exist, all fields are multiValued
             by nature
-       1.1: multiValued attribute introduced, false by default 
-       1.2: omitTermFreqAndPositions attribute introduced, true by default 
+       1.1: multiValued attribute introduced, false by default
+       1.2: omitTermFreqAndPositions attribute introduced, true by default
             except for text fields.
        1.3: removed optional field compress feature
        1.4: autoGeneratePhraseQueries attribute introduced to drive QueryParser
-            behavior when a single string produces multiple tokens.  Defaults 
+            behavior when a single string produces multiple tokens.  Defaults
             to off for version >= 1.4
-       1.5: omitNorms defaults to true for primitive field types 
+       1.5: omitNorms defaults to true for primitive field types
             (int, float, boolean, string...)
        1.6: useDocValuesAsStored defaults to true.
+       1.7: docValues defaults to true, uninvertible defaults to false.
     -->
 
     <!-- Valid attributes for fields:
      name: mandatory - the name for the field
-     type: mandatory - the name of a field type from the 
+     type: mandatory - the name of a field type from the
        fieldTypes section
      indexed: true if this field should be indexed (searchable or sortable)
      stored: true if this field should be retrievable
      docValues: true if this field should have doc values. Doc Values is
        recommended (required, if you are using *Point fields) for faceting,
        grouping, sorting and function queries. Doc Values will make the index
-       faster to load, more NRT-friendly and more memory-efficient. 
-       They are currently only supported by StrField, UUIDField, all 
+       faster to load, more NRT-friendly and more memory-efficient.
+       They are currently only supported by StrField, UUIDField, all
        *PointFields, and depending on the field type, they might require
        the field to be single-valued, be required or have a default value
        (check the documentation of the field type you're interested in for
@@ -82,9 +83,9 @@
        given field.
        When using MoreLikeThis, fields used for similarity should be
        stored for best performance.
-     termPositions: Store position information with the term vector.  
+     termPositions: Store position information with the term vector.
        This will increase storage costs.
-     termOffsets: Store offset information with the term vector. This 
+     termOffsets: Store offset information with the term vector. This
        will increase storage costs.
      required: The field is required.  It will throw an error if the
        value does not exist
@@ -102,10 +103,10 @@
     <!-- In this _default configset, only four fields are pre-declared:
          id, _version_, and _text_ and _root_. All other fields will be type guessed and added via the
          "add-unknown-fields-to-the-schema" update request processor chain declared in solrconfig.xml.
-         
-         Note that many dynamic fields are also defined - you can use them to specify a 
+
+         Note that many dynamic fields are also defined - you can use them to specify a
          field's type via field naming conventions - see below.
-  
+
          WARNING: The _text_ catch-all field will significantly increase your index size.
          If you don't need it, consider removing it and the corresponding copyField directive."
     -->
@@ -115,12 +116,12 @@
     <field name="_version_" type="plong" indexed="false" stored="false"/>
     <field name="_root_" type="string" indexed="true" stored="false" docValues="false" />
 
-    
-     
-    
-    
-<!-- Start: Dataverse-specific -->    
-    
+
+
+
+
+<!-- Start: Dataverse-specific -->
+
     <!-- catchall field, containing all other searchable text fields (implemented
         via copyField further on in this schema  -->
     <!-- Dataverse solr 7.3.0: for some reason the old text wasn't working so switched to _text_ for copyfields -->
@@ -205,7 +206,8 @@
     <field name="deaccessionReason" type="string" stored="true" indexed="false" multiValued="false"/>
     <field name="fileRestricted" type="boolean" stored="true" indexed="false" multiValued="false"/>
     <field name="canDownloadFile" type="boolean" stored="true" indexed="false" multiValued="false"/>
-
+    <field name="versionNote" type="string" stored="true" indexed="false" multiValued="false"/>
+    
     <!-- Added for Dataverse 4.0 alpha 1. This is a required field so we don't have to go to the database to get the database id of the entity. On cards we use the id in links -->
     <field name="entityId" type="plong" stored="true" indexed="true" multiValued="false"/>
 
@@ -216,7 +218,7 @@
     <!-- https://redmine.hmdc.harvard.edu/issues/3482 -->
     <!-- 'Sorting can be done on the "score" of the document, or on any multiValued="false" indexed="true" field provided that field is either non-tokenized (ie: has no Analyzer) or uses an Analyzer that only produces a single Term (ie: uses the KeywordTokenizer)' http://wiki.apache.org/solr/CommonQueryParameters#sort -->
     <!-- http://stackoverflow.com/questions/13360706/solr-4-0-alphabetical-sorting-trouble/13361226#13361226 -->
-    <field name="nameSort" type="alphaOnlySort" indexed="true" stored="true"/>
+    <field name="nameSort" type="string" indexed="true" stored="true"/>
 
     <field name="dateSort" type="pdate" indexed="true" stored="true"/>
 
@@ -785,7 +787,7 @@
         <filter class="solr.TrimFilterFactory" />
         <!-- The PatternReplaceFilter gives you the flexibility to use
                 Java Regular expression to replace any sequence of characters
-                matching a pattern with an arbitrary replacement string, 
+                matching a pattern with an arbitrary replacement string,
                 which may include back references to portions of the original
                 string matched by the pattern.
 
@@ -798,8 +800,8 @@
         <!-- https://redmine.hmdc.harvard.edu/issues/3482#note-11 -->
         <!-- <filter class="solr.PatternReplaceFilterFactory" pattern="([^a-z])" replacement="" replace="all" /> -->
         </analyzer>
-    </fieldType>   
-    
+    </fieldType>
+
     <!-- The StrField type is not analyzed, but indexed/stored verbatim. -->
     <fieldType name="string" class="solr.StrField" sortMissingLast="true" docValues="true" />
     <fieldType name="strings" class="solr.StrField" sortMissingLast="true" multiValued="true" docValues="true" />