Fix tests org.commoncrawl.* being ignored/skipped

.github/workflows/cc-build.yml

@@ -55,3 +55,21 @@ jobs:
           curl https://publicsuffix.org/list/public_suffix_list.dat -o conf/effective_tld_names.dat
       - name: Test
         run: ant clean test -buildfile build.xml
+      - name: Upload Test Results
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: test-results
+          path: |
+            ./build/test/TEST-*.xml
+            ./build/**/test/TEST-*.xml
+          retention-days: 1
+      - name: Publish Test Results
+        if: always()
+        uses: EnricoMi/publish-unit-test-result-action@v2
+        with:
+          files: |
+            ./build/test/TEST-*.xml
+            ./build/**/test/TEST-*.xml
+          comment_mode: always
+          fail_on: "test failures"

build.xml

@@ -495,7 +495,7 @@
       <testclasses outputDir="${test.build.dir}" unless="testcase">
         <listener type="legacy-plain" sendSysOut="true" sendSysErr="true"/>
         <listener type="legacy-xml" sendSysOut="true" sendSysErr="true"/>
-        <fork>
+        <fork forkMode="perTestClass">
           <jvmarg value="-Xmx1000m"/>
           <sysproperty key="test.build.data" value="${test.build.data}"/>
           <sysproperty key="test.src.dir" value="${test.src.dir}"/>

src/java/org/apache/nutch/tools/CommonCrawlDataDumper.java

@@ -274,7 +274,7 @@ public void dump(File outputDir, File segmentRootDir, File linkdb, boolean gzip,
     if (parts == null || parts.size() == 0) {
       LOG.error( "No segment directories found in {} ",
           segmentRootDir.getAbsolutePath());
-      System.exit(1);
+      return;
     }
     LOG.info("Found {} segment parts", parts.size());
     if (gzip && !warc) {