SOLR-17575: Fixed broken backwards compatibility with the legacy "langid.whitelist" config in Solr Langid

solr/modules/langid/src/java/org/apache/solr/update/processor/LanguageIdentifierUpdateProcessor.java

@@ -111,19 +111,20 @@ private void initParams(SolrParams params) {
       overwrite = params.getBool(OVERWRITE, false);
       langAllowlist = new HashSet<>();
       threshold = params.getDouble(THRESHOLD, DOCID_THRESHOLD_DEFAULT);
-      String legacyAllowList = params.get(LANG_WHITELIST, "");
-      if (legacyAllowList.length() > 0) {
+      final String legacyAllowList = params.get(LANG_WHITELIST, "").trim();
+      if (!legacyAllowList.isEmpty()) {
         // nowarn compile time string concatenation
         log.warn(
             LANG_WHITELIST
                 + " parameter is deprecated; use "
                 + LANG_ALLOWLIST
                 + " instead."); // nowarn
       }
-      if (params.get(LANG_ALLOWLIST, legacyAllowList).length() > 0) {
-        for (String lang : params.get(LANG_ALLOWLIST, "").split(",")) {
-          langAllowlist.add(lang);
-        }
+      if (!params.get(LANG_ALLOWLIST, legacyAllowList).isEmpty()) {
+        Arrays.stream(params.get(LANG_ALLOWLIST, legacyAllowList).split(","))
+            .map(String::trim)
+            .filter(lang -> !lang.isEmpty())
+            .forEach(langAllowlist::add);
       }
 
       // Mapping params (field centric)

solr/modules/langid/src/test/org/apache/solr/update/processor/LanguageIdentifierUpdateProcessorFactoryTestCase.java

@@ -18,6 +18,7 @@
 
 import java.util.ArrayList;
 import java.util.List;
+import java.util.Set;
 import org.apache.solr.SolrTestCaseJ4;
 import org.apache.solr.common.SolrInputDocument;
 import org.apache.solr.common.params.ModifiableSolrParams;
@@ -464,6 +465,31 @@ public void testMapIndividual() throws Exception {
     assertTrue(mappedIndividual.containsKey("text2_ru"));
   }
 
+  @Test
+  public void testAllowlist() throws Exception {
+    ModifiableSolrParams parameters = new ModifiableSolrParams();
+    parameters.add("langid.fl", "name,subject");
+    parameters.add("langid.langField", "language_s");
+    parameters.add("langid.allowlist", "no,en ,,,sv");
+    liProcessor = createLangIdProcessor(parameters);
+
+    // Make sure that empty language codes have been filtered out and others trimmed.
+    assertEquals(Set.of("no", "en", "sv"), liProcessor.langAllowlist);
+  }
+
+  @Test
+  public void testAllowlistBackwardsCompatabilityWithLegacyAllowlist() throws Exception {
+    // The "legacy allowlist" is "langid.whitelist"
+    ModifiableSolrParams parameters = new ModifiableSolrParams();
+    parameters.add("langid.fl", "name,subject");
+    parameters.add("langid.langField", "language_s");
+    parameters.add("langid.whitelist", "no,en ,,,sv");
+    liProcessor = createLangIdProcessor(parameters);
+
+    // Make sure that empty language codes have been filtered out and others trimmed.
+    assertEquals(Set.of("no", "en", "sv"), liProcessor.langAllowlist);
+  }
+
   // Various utility methods
 
   private SolrInputDocument englishDoc() {