Merge cherry-picked commits from upstream 1.22

.github/workflows/cc-build.yml

@@ -29,9 +29,9 @@ jobs:
         os: [ubuntu-latest]
     runs-on: ${{ matrix.os }}
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
       - name: Set up JDK ${{ matrix.java }}
-        uses: actions/setup-java@v4
+        uses: actions/setup-java@v5
         with:
           java-version: ${{ matrix.java }}
           distribution: 'temurin'
@@ -53,5 +53,12 @@ jobs:
       - name: Install recent public suffix list
         run: |
           curl https://publicsuffix.org/list/public_suffix_list.dat -o conf/effective_tld_names.dat
+      - name: Cache Ivy dependencies
+        uses: actions/cache@v4
+        with:
+          path: ~/.ivy2/cache
+          key: ${{ runner.os }}-ivy-${{ hashFiles('ivy/ivy.xml', 'src/plugin/**/ivy.xml') }}
+          restore-keys: |
+            ${{ runner.os }}-ivy-
       - name: Test
         run: ant clean test -buildfile build.xml

.github/workflows/junit-report.yml

@@ -25,30 +25,41 @@ jobs:
   checks:
     runs-on: ubuntu-latest
     steps:
-      - name: Download Test Report
+      - name: Download Test Report (Ubuntu)
         uses: dawidd6/action-download-artifact@v11
         with:
-          name: junit-test-results
+          name: junit-test-results-ubuntu-latest
           workflow: master-build.yml
           run_id: ${{ github.event.workflow_run.id }}
+        continue-on-error: true
       - name: Publish Test Report
-        uses: mikepenz/action-junit-report@v5
+        uses: mikepenz/action-junit-report@v6
         with:
           report_paths: |-
             ./test/TEST-*.xml
             ./**/test/TEST-*.xml
+          check_name: |-
+            JUnit Test Report
+            JUnit Test Report Plugins
           commit: ${{ github.event.workflow_run.head_sha }}
-          comment: true
-          pr_id: ${{ github.event.workflow_run.pull_requests[0].number }}
-          fail_on_failure: true
+          fail_on_failure: false
+          fail_on_parse_error: true
+          require_tests: true
+          require_passed_tests: true
+          include_passed: false
+          include_skipped: true
+          check_annotations: true
+          annotate_notice: true
           job_summary: true
           detailed_summary: true
-          truncate_stack_traces: false
-          fail_on_parse_error: false # temporary while debugging TestMimeUtil
-          require_tests: true
+          flaky_summary: true
+          skip_success_summary: true
           include_time_in_summary: true
-          include_passed: true
+          group_suite: true
+          comment: true
+          updateComment: true
+          skip_comment_without_tests: true
           job_name: tests
-          check_name: |-
-            JUnit Test Report Core
-            JUnit Test Report Plugins
+          truncate_stack_traces: false
+          annotations_limit: 50
+          pr_id: ${{ github.event.workflow_run.pull_requests[0].number || '' }}

.github/workflows/master-build.yml

@@ -24,7 +24,7 @@ jobs:
   javadoc:
     strategy:
       matrix:
-        java: ['11']
+        java: ['17']
         os: [ubuntu-latest]
     runs-on: ${{ matrix.os }}
     steps:
@@ -34,12 +34,19 @@ jobs:
         with:
           java-version: ${{ matrix.java }}
           distribution: 'temurin'
+      - name: Cache Ivy dependencies
+        uses: actions/cache@v4
+        with:
+          path: ~/.ivy2/cache
+          key: ${{ runner.os }}-ivy-${{ hashFiles('ivy/ivy.xml', 'src/plugin/**/ivy.xml') }}
+          restore-keys: |
+            ${{ runner.os }}-ivy-
       - name: Javadoc
         run: ant clean javadoc -buildfile build.xml
   rat:
     strategy:
       matrix:
-        java: ['11']
+        java: ['17']
         os: [ubuntu-latest]
     runs-on: ${{ matrix.os }}
     steps:
@@ -49,6 +56,13 @@ jobs:
         with:
           java-version: ${{ matrix.java }}
           distribution: 'temurin'
+      - name: Cache Ivy dependencies
+        uses: actions/cache@v4
+        with:
+          path: ~/.ivy2/cache
+          key: ${{ runner.os }}-ivy-${{ hashFiles('ivy/ivy.xml', 'src/plugin/**/ivy.xml') }}
+          restore-keys: |
+            ${{ runner.os }}-ivy-
       - name: Run Apache Rat
         run: ant clean run-rat -buildfile build.xml
       - name: Cache unknown licenses
@@ -62,17 +76,24 @@ jobs:
   tests:
     strategy:
       matrix:
-        java: ['11']
+        java: ['17']
         os: [ubuntu-latest, macos-latest]
     runs-on: ${{ matrix.os }}
-    timeout-minutes: 30
+    timeout-minutes: 45
     steps:
       - uses: actions/checkout@v5
       - name: Set up JDK ${{ matrix.java }}
         uses: actions/setup-java@v5
         with:
           java-version: ${{ matrix.java }}
           distribution: 'temurin'
+      - name: Cache Ivy dependencies
+        uses: actions/cache@v4
+        with:
+          path: ~/.ivy2/cache
+          key: ${{ runner.os }}-ivy-${{ hashFiles('ivy/ivy.xml', 'src/plugin/**/ivy.xml') }}
+          restore-keys: |
+            ${{ runner.os }}-ivy-
       - uses: dorny/paths-filter@de90cc6fb38fc0963ad72b210f1f284cd68cea36
         id: filter
         with:
@@ -99,13 +120,23 @@ jobs:
       - name: test plugins
         if: ${{ steps.filter.outputs.plugins == 'true' && steps.filter.outputs.core == 'false' && steps.filter.outputs.buildconf == 'false' }}
         run: ant clean test-plugins -buildfile build.xml
+      - name: Check for test results
+        id: check_tests
+        if: always() && matrix.os == 'ubuntu-latest'
+        run: |
+          shopt -s globstar nullglob
+          files=(./build/test/TEST-*.xml ./build/**/test/TEST-*.xml)
+          if [ ${#files[@]} -gt 0 ]; then
+            echo "has_results=true" >> $GITHUB_OUTPUT
+          else
+            echo "has_results=false" >> $GITHUB_OUTPUT
+          fi
       - name: Upload Test Report
         uses: actions/upload-artifact@v4
-        if: always()
+        if: always() && matrix.os == 'ubuntu-latest' && steps.check_tests.outputs.has_results == 'true'
         with:
-          name: junit-test-results
+          name: junit-test-results-${{ matrix.os }}
           path: |
             ./build/test/TEST-*.xml
             ./build/**/test/TEST-*.xml
-          retention-days: 1
-          overwrite: true
+          retention-days: 1

LICENSE-binary

@@ -245,7 +245,6 @@ com.google.inject.extensions:guice-servlet
 com.google.j2objc:j2objc-annotations
 com.healthmarketscience.jackcess:jackcess
 com.healthmarketscience.jackcess:jackcess-encrypt
-com.intellij:annotations
 com.maxmind.db:maxmind-db
 com.maxmind.geoip2:geoip2
 com.nimbusds:nimbus-jose-jwt
@@ -257,7 +256,12 @@ com.rometools:rome-utils
 com.shapesecurity:salvation2
 com.squareup.okhttp3:okhttp
 com.squareup.okhttp3:okhttp-brotli
+com.squareup.okhttp3:okhttp-jvm
+com.squareup.okhttp3:okhttp-zstd
 com.squareup.okio:okio
+com.squareup.okio:okio-jvm
+com.squareup.zstd:zstd-kmp-jvm
+com.squareup.zstd:zstd-kmp-okio-jvm
 com.tdunning:t-digest
 com.typesafe.netty:netty-reactive-streams
 com.typesafe.scala-logging:scala-logging_2.12
@@ -275,13 +279,14 @@ commons-lang:commons-lang
 commons-logging:commons-logging
 commons-net:commons-net
 commons-validator:commons-validator
+de.l3s.boilerpipe:boilerpipe
 de.vandermeer:ascii-utf-themes
 de.vandermeer:asciitable
 de.vandermeer:char-translation
 de.vandermeer:skb-interfaces
 dev.failsafe:failsafe
+info.picocli:picocli
 io.dropwizard.metrics:metrics-core
-io.netty:netty
 io.netty:netty-all
 io.netty:netty-buffer
 io.netty:netty-codec
@@ -378,7 +383,7 @@ org.apache.hadoop:hadoop-yarn-api
 org.apache.hadoop:hadoop-yarn-client
 org.apache.hadoop:hadoop-yarn-common
 org.apache.hadoop.thirdparty:hadoop-shaded-guava
-org.apache.hadoop.thirdparty:hadoop-shaded-protobuf_3_7
+org.apache.hadoop.thirdparty:hadoop-shaded-protobuf_3_25
 org.apache.httpcomponents:httpasyncclient
 org.apache.httpcomponents:httpclient
 org.apache.httpcomponents:httpcore
@@ -398,21 +403,13 @@ org.apache.kafka:kafka-storage
 org.apache.kafka:kafka-storage-api
 org.apache.kafka:kafka-tools-api
 org.apache.kafka:kafka_2.12
-org.apache.kerby:kerb-admin
-org.apache.kerby:kerb-client
-org.apache.kerby:kerb-common
 org.apache.kerby:kerb-core
 org.apache.kerby:kerb-crypto
-org.apache.kerby:kerb-identity
-org.apache.kerby:kerb-server
-org.apache.kerby:kerb-simplekdc
 org.apache.kerby:kerb-util
 org.apache.kerby:kerby-asn1
 org.apache.kerby:kerby-config
 org.apache.kerby:kerby-pkix
 org.apache.kerby:kerby-util
-org.apache.kerby:kerby-xdr
-org.apache.kerby:token-provider
 org.apache.logging.log4j:log4j-api
 org.apache.logging.log4j:log4j-core
 org.apache.logging.log4j:log4j-slf4j2-impl
@@ -435,6 +432,7 @@ org.apache.pdfbox:fontbox
 org.apache.pdfbox:jbig2-imageio
 org.apache.pdfbox:jempbox
 org.apache.pdfbox:pdfbox
+org.apache.pdfbox:pdfbox-io
 org.apache.pdfbox:pdfbox-tools
 org.apache.pdfbox:xmpbox
 org.apache.poi:poi
@@ -443,6 +441,7 @@ org.apache.poi:poi-ooxml-lite
 org.apache.poi:poi-scratchpad
 org.apache.solr:solr-solrj
 org.apache.tika:tika-core
+org.apache.tika:tika-handler-boilerpipe
 org.apache.tika:tika-langdetect-optimaize
 org.apache.tika:tika-parser-apple-module
 org.apache.tika:tika-parser-audiovideo-module
@@ -476,8 +475,6 @@ org.asynchttpclient:async-http-client
 org.asynchttpclient:async-http-client-netty-utils
 org.bitbucket.b_c:jose4j
 org.ccil.cowan.tagsoup:tagsoup
-org.codehaus.jackson:jackson-core-asl
-org.codehaus.jackson:jackson-mapper-asl
 org.codehaus.jettison:jettison
 org.eclipse.jetty:jetty-alpn-client
 org.eclipse.jetty:jetty-alpn-java-client
@@ -515,9 +512,6 @@ org.gagravarr:vorbis-java-core
 org.gagravarr:vorbis-java-tika
 org.jetbrains:annotations
 org.jetbrains.kotlin:kotlin-stdlib
-org.jetbrains.kotlin:kotlin-stdlib-common
-org.jetbrains.kotlin:kotlin-stdlib-jdk7
-org.jetbrains.kotlin:kotlin-stdlib-jdk8
 org.jspecify:jspecify
 org.littleshoot:littleproxy
 org.locationtech.spatial4j:spatial4j
@@ -595,9 +589,7 @@ BSD 2-Clause
 
 com.barchart.udt:barchart-udt-bundle
 com.github.luben:zstd-jni
-com.google.protobuf:protobuf-java
 dk.brics:automaton
-dnsjava:dnsjava
 org.codehaus.woodstox:stax2-api
 org.jline:jline
 
@@ -609,6 +601,7 @@ BSD 3-Clause
 
 com.adobe.xmp:xmpcore
 com.github.virtuald:curvesapi
+dnsjava:dnsjava
 org.fusesource.leveldbjni:leveldbjni-all
 org.ow2.asm:asm
 
@@ -633,7 +626,7 @@ Bouncy Castle Licence
 
 (licenses-binary/LICENSE-bouncy-castle-licence.txt)
 
-org.bouncycastle:bcmail-jdk18on
+org.bouncycastle:bcjmail-jdk18on
 org.bouncycastle:bcpkix-jdk18on
 org.bouncycastle:bcprov-jdk18on
 org.bouncycastle:bcutil-jdk18on
@@ -717,13 +710,17 @@ jakarta.jws:jakarta.jws-api
 jakarta.xml.bind:jakarta.xml.bind-api
 jakarta.xml.soap:jakarta.xml.soap-api
 jakarta.xml.ws:jakarta.xml.ws-api
+org.eclipse.angus:angus-activation
+org.glassfish.jaxb:jaxb-core
 org.glassfish.jaxb:jaxb-runtime
 org.glassfish.jaxb:txw2
 
 
 Eclipse Public License - Version 2.0
 ------------------------------------
 
+(licenses-binary/LICENSE-eclipse-public-license---version-2.0.txt)
+
 org.eclipse.jetty:jetty-http
 org.eclipse.jetty:jetty-io
 org.eclipse.jetty:jetty-security
@@ -734,6 +731,8 @@ org.eclipse.jetty:jetty-util
 MIT
 ---
 
+(licenses-binary/LICENSE-mit-license.txt)
+
 net.sourceforge.argparse4j:argparse4j
 org.slf4j:slf4j-api
 
@@ -781,7 +780,6 @@ Public Domain
 (licenses-binary/LICENSE-public-domain.txt)
 
 aopalliance:aopalliance
-org.tukaani:xz
 
 
 Public Domain, per Creative Commons CC0