Improve data store handling with thread safety and resource management enhancements

This commit addresses several improvements in the data store processing implementation:

**Thread Safety Improvements:**
- DataStoreFactory: Changed dataStoreMap from LinkedHashMap to ConcurrentHashMap for thread-safe concurrent access
- DataStoreFactory: Made dataStoreNames and lastLoadedTime volatile to ensure visibility across threads
- DataStoreFactory: Made getDataStoreNames() synchronized to prevent race conditions during cache refresh
- AbstractDataStore: Made alive field volatile to ensure proper visibility in multi-threaded scenarios
- FileListIndexUpdateCallbackImpl: Changed deleteUrlList from ArrayList to CopyOnWriteArrayList for thread-safe access from executor threads

**Resource Handling:**
- DataStoreFactory: Added null check for jarFiles array to prevent NullPointerException
- DataStoreFactory: Added existence check for XML configuration files before attempting to read them, reducing unnecessary exception handling

**Code Quality:**
- AbstractDataStore: Moved static logger declaration before instance fields following Java best practices
- FileListIndexUpdateCallbackImpl: Fixed incorrect StringUtil import (was using Apache POI's StringUtil instead of Fess's)

These improvements enhance the reliability and thread safety of the data store processing layer,
particularly important for concurrent crawling operations.

Author: claude

src/main/java/org/codelibs/fess/ds/AbstractDataStore.java

@@ -43,13 +43,6 @@
  */
 public abstract class AbstractDataStore implements DataStore {
 
-    /**
-     * Default constructor.
-     */
-    public AbstractDataStore() {
-        // nothing
-    }
-
     private static final Logger logger = LogManager.getLogger(AbstractDataStore.class);
 
     /**
@@ -64,8 +57,16 @@ public AbstractDataStore() {
 
     /**
      * The flag to check if the data store is alive.
+     * Volatile to ensure visibility across threads.
      */
-    protected boolean alive = true;
+    protected volatile boolean alive = true;
+
+    /**
+     * Default constructor.
+     */
+    public AbstractDataStore() {
+        // nothing
+    }
 
     /**
      * Register this data store.

src/main/java/org/codelibs/fess/ds/DataStoreFactory.java

@@ -27,6 +27,7 @@
 import java.util.Locale;
 import java.util.Map;
 import java.util.Set;
+import java.util.concurrent.ConcurrentHashMap;
 import java.util.stream.Collectors;
 
 import javax.xml.parsers.DocumentBuilder;
@@ -64,20 +65,22 @@ public class DataStoreFactory {
     /**
      * Map containing registered data store instances indexed by their names and class simple names.
      * All keys are stored in lowercase for case-insensitive lookup.
+     * Thread-safe implementation using ConcurrentHashMap for concurrent access.
      */
-    protected Map<String, DataStore> dataStoreMap = new LinkedHashMap<>();
+    protected Map<String, DataStore> dataStoreMap = new ConcurrentHashMap<>();
 
     /**
      * Cached array of available data store names discovered from plugin JAR files.
      * This cache is refreshed periodically based on the lastLoadedTime.
      */
-    protected String[] dataStoreNames = StringUtil.EMPTY_STRINGS;
+    protected volatile String[] dataStoreNames = StringUtil.EMPTY_STRINGS;
 
     /**
      * Timestamp of the last time data store names were loaded from plugin files.
      * Used to implement a time-based cache refresh mechanism.
+     * Volatile to ensure visibility across threads.
      */
-    protected long lastLoadedTime = 0;
+    protected volatile long lastLoadedTime = 0;
 
     /**
      * Creates a new instance of DataStoreFactory.
@@ -130,7 +133,7 @@ public DataStore getDataStore(final String name) {
      *
      * @return array of data store names sorted alphabetically, never null
      */
-    public String[] getDataStoreNames() {
+    public synchronized String[] getDataStoreNames() {
         final long now = ComponentUtil.getSystemHelper().getCurrentTimeAsLong();
         if (now - lastLoadedTime > 60000L) {
             final List<String> nameList = loadDataStoreNameList();
@@ -154,9 +157,18 @@ public String[] getDataStoreNames() {
     protected List<String> loadDataStoreNameList() {
         final Set<String> nameSet = new HashSet<>();
         final File[] jarFiles = ResourceUtil.getPluginJarFiles(PluginHelper.ArtifactType.DATA_STORE.getId());
+        if (jarFiles == null) {
+            return nameSet.stream().sorted().collect(Collectors.toList());
+        }
         for (final File jarFile : jarFiles) {
             try (FileSystem fs = FileSystems.newFileSystem(jarFile.toPath(), ClassLoader.getSystemClassLoader())) {
                 final Path xmlPath = fs.getPath("fess_ds++.xml");
+                if (!Files.exists(xmlPath)) {
+                    if (logger.isDebugEnabled()) {
+                        logger.debug("Configuration file not found in {}", jarFile.getAbsolutePath());
+                    }
+                    continue;
+                }
                 try (InputStream is = Files.newInputStream(xmlPath)) {
                     final DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
                     factory.setFeature(org.codelibs.fess.crawler.Constants.FEATURE_SECURE_PROCESSING, true);

src/main/java/org/codelibs/fess/ds/callback/FileListIndexUpdateCallbackImpl.java

@@ -25,6 +25,7 @@
 import java.util.Map;
 import java.util.Objects;
 import java.util.Set;
+import java.util.concurrent.CopyOnWriteArrayList;
 import java.util.concurrent.ExecutorService;
 import java.util.concurrent.LinkedBlockingQueue;
 import java.util.concurrent.ThreadPoolExecutor;
@@ -34,7 +35,7 @@
 
 import org.apache.logging.log4j.LogManager;
 import org.apache.logging.log4j.Logger;
-import org.apache.poi.util.StringUtil;
+import org.codelibs.core.lang.StringUtil;
 import org.codelibs.fess.Constants;
 import org.codelibs.fess.crawler.builder.RequestDataBuilder;
 import org.codelibs.fess.crawler.client.CrawlerClient;
@@ -89,8 +90,8 @@ public class FileListIndexUpdateCallbackImpl implements IndexUpdateCallback {
     /** Factory for creating crawler clients to handle different URL schemes. */
     protected CrawlerClientFactory crawlerClientFactory;
 
-    /** List of URLs to be deleted, cached for batch processing. */
-    protected List<String> deleteUrlList = new ArrayList<>(100);
+    /** List of URLs to be deleted, cached for batch processing. Thread-safe using CopyOnWriteArrayList. */
+    protected List<String> deleteUrlList = new CopyOnWriteArrayList<>();
 
     /** Maximum size of the delete URL cache before batch deletion is triggered. */
     protected int maxDeleteDocumentCacheSize;