[hotfix] Fix typo in docs comments and functions (alibaba#171)

Author: liyubin117

fluss-client/src/main/java/com/alibaba/fluss/client/scanner/snapshot/SnapshotScanner.java

@@ -117,8 +117,8 @@ public SnapshotScanner(
     @Nullable
     public CloseableIterator<ScanRecord> poll(Duration timeout) {
         // note: we don't throw exception if the scanner is closed since in flink access pattern,
-        // the scanner will be closed by source reader thead after finished reading all records,
-        // but the fetcher thead may still calling poll method
+        // the scanner will be closed by source reader thread after finished reading all records,
+        // but the fetcher thread may still calling poll method
         ensureNoException();
         return inLock(
                 lock,

fluss-client/src/test/java/com/alibaba/fluss/client/admin/ClientToServerITCaseBase.java

@@ -101,7 +101,7 @@ private static Configuration initConfig() {
         conf.setInt(ConfigOptions.DEFAULT_REPLICATION_FACTOR, 3);
         // set a shorter interval for testing purpose
         conf.set(ConfigOptions.KV_SNAPSHOT_INTERVAL, Duration.ofSeconds(1));
-        // set a shorter max lag time to to make tests in FlussFailServerTableITCase faster
+        // set a shorter max lag time to make tests in FlussFailServerTableITCase faster
         conf.set(ConfigOptions.LOG_REPLICA_MAX_LAG_TIME, Duration.ofSeconds(10));
 
         conf.set(ConfigOptions.CLIENT_WRITER_BUFFER_MEMORY_SIZE, MemorySize.parse("1mb"));

fluss-client/src/test/java/com/alibaba/fluss/client/scanner/log/FlussLogScannerITCase.java

@@ -140,11 +140,11 @@ void testLogScannerMultiThreadAccess() throws Exception {
 
             LogScanner logScanner = table.getLogScanner(new LogScan());
             ExecutorService executor = Executors.newSingleThreadExecutor();
-            // subscribe in thead1
+            // subscribe in thread1
             executor.submit(() -> logScanner.subscribe(0, LogScanner.EARLIEST_OFFSET)).get();
             // subscribe again in main thread
             logScanner.subscribe(1, LogScanner.EARLIEST_OFFSET);
-            // subscribe again in thead1
+            // subscribe again in thread1
             executor.submit(() -> logScanner.subscribeFromBeginning(2)).get();
 
             // should be able to poll data from all buckets

fluss-client/src/test/java/com/alibaba/fluss/client/scanner/log/LogFetchCollectorTest.java

@@ -146,7 +146,7 @@ void testCollectAfterUnassign() throws Exception {
 
         Map<TableBucket, List<ScanRecord>> bucketAndRecords =
                 logFetchCollector.collectFetch(logFetchBuffer);
-        // should only contains records for bucket 1
+        // should only contain records for bucket 1
         assertThat(bucketAndRecords.keySet()).containsExactly(tb1);
 
         // collect again, should be empty

fluss-client/src/test/java/com/alibaba/fluss/client/table/FlussTableITCase.java

@@ -413,7 +413,7 @@ void testInvalidPartialUpdate() throws Exception {
         createTable(DATA1_TABLE_PATH_PK, tableDescriptor, true);
 
         try (Table table = conn.getTable(DATA1_TABLE_PATH_PK)) {
-            // the target columns doesn't contains the primary column, should
+            // the target columns doesn't contain the primary column, should
             // throw exception
             assertThatThrownBy(
                             () ->

fluss-common/src/main/java/com/alibaba/fluss/config/ConfigOptions.java

@@ -621,7 +621,7 @@ public class ConfigOptions {
                                     + " considering a request complete. This controls the durability of records that "
                                     + "are sent. The following settings are allowed:\n"
                                     + "acks=0: If set to 0, then the writer will not wait for any acknowledgment "
-                                    + "from the server at all. No gurarantee can be mode that the server has received "
+                                    + "from the server at all. No guarantee can be mode that the server has received "
                                     + "the record in this case.\n"
                                     + "acks=1: This will mean the leader will write the record to its local log but "
                                     + "will respond without awaiting full acknowledge the record but before the followers"
@@ -1183,7 +1183,7 @@ public class ConfigOptions {
                                     + "like 9990-9999.");
 
     // ------------------------------------------------------------------------
-    //  ConfigOptions for lakehosue storage
+    //  ConfigOptions for lakehouse storage
     // ------------------------------------------------------------------------
     public static final ConfigOption<String> LAKEHOUSE_STORAGE =
             key("lakehouse.storage")

fluss-common/src/main/java/com/alibaba/fluss/metrics/reporter/MetricReporter.java

@@ -39,8 +39,8 @@ public interface MetricReporter {
      * Configures this reporter.
      *
      * <p>If the reporter was instantiated generically and hence parameter-less, this method is the
-     * place where the reporter sets it's basic fields based on configuration values. Otherwise,
-     * this method will typically be a no-op since resources can be acquired in the constructor.
+     * place where the reporter sets its basic fields based on configuration values. Otherwise, this
+     * method will typically be a no-op since resources can be acquired in the constructor.
      *
      * <p>This method is always called first on a newly instantiated reporter.
      *

fluss-common/src/main/java/com/alibaba/fluss/row/BinaryString.java

@@ -393,11 +393,11 @@ public BinaryString trim() {
         if (inFirstSegment()) {
             int s = 0;
             int e = this.sizeInBytes - 1;
-            // skip all of the space (0x20) in the left side
+            // skip all the space (0x20) on the left side
             while (s < this.sizeInBytes && getByteOneSegment(s) == 0x20) {
                 s++;
             }
-            // skip all of the space (0x20) in the right side
+            // skip all the space (0x20) on the right side
             while (e >= s && getByteOneSegment(e) == 0x20) {
                 e--;
             }
@@ -417,13 +417,13 @@ private BinaryString trimMultiSegs() {
         int e = this.sizeInBytes - 1;
         int segSize = segments[0].size();
         BinaryString.SegmentAndOffset front = firstSegmentAndOffset(segSize);
-        // skip all of the space (0x20) in the left side
+        // skip all the space (0x20) on the left side
         while (s < this.sizeInBytes && front.value() == 0x20) {
             s++;
             front.nextByte(segSize);
         }
         BinaryString.SegmentAndOffset behind = lastSegmentAndOffset(segSize);
-        // skip all of the space (0x20) in the right side
+        // skip all the space (0x20) on the right side
         while (e >= s && behind.value() == 0x20) {
             e--;
             behind.previousByte(segSize);

fluss-connectors/fluss-connector-flink/src/main/java/com/alibaba/fluss/connector/flink/lakehouse/LakeSplitGenerator.java

@@ -80,7 +80,7 @@ public LakeSplitGenerator(
     }
 
     public List<SourceSplitBase> generateLakeSplits() throws Exception {
-        // get the file store store
+        // get the file store
         LakeTableSnapshotInfo lakeSnapshotInfo = flussAdmin.getLakeTableSnapshot(tablePath).get();
         FileStoreTable fileStoreTable =
                 getTable(
@@ -145,7 +145,7 @@ private List<SourceSplitBase> generateSplit(
         List<SourceSplitBase> splits = new ArrayList<>();
         FileStoreSourceSplitGenerator splitGenerator = new FileStoreSourceSplitGenerator();
         if (isLogTable) {
-            // it's log table, we don't care about bucket and we can't get bucket in paimon's
+            // it's log table, we don't care about bucket, and we can't get bucket in paimon's
             // dynamic bucket; so first generate split for the whole paimon snapshot,
             // then generate log split for each bucket paimon snapshot + fluss log
             splits.addAll(

fluss-server/src/main/java/com/alibaba/fluss/server/kv/KvSnapshotResource.java

@@ -102,7 +102,7 @@ public static KvSnapshotResource create(int serverId, Configuration conf) {
                         conf.getInt(ConfigOptions.KV_SNAPSHOT_SCHEDULER_THREAD_NUM),
                         new ExecutorThreadFactory("periodic-snapshot-scheduler-" + serverId));
 
-        // the parameter to create thread pool is from Flink. todo: may ajust according Fluss's
+        // the parameter to create thread pool is from Flink. todo: may adjust according Fluss's
         // workload
         // create a thread pool for the async part of kv snapshot
         ExecutorService asyncOperationsThreadPool =

fluss-server/src/main/java/com/alibaba/fluss/server/kv/snapshot/CompletedSnapshot.java

@@ -145,7 +145,7 @@ private void disposeSnapshotStorage() throws IOException {
     }
 
     /**
-     * Return the metadata file path that stores all the informations that describes the snapshot.
+     * Return the metadata file path that stores all the information that describes the snapshot.
      */
     public FsPath getMetadataFilePath() {
         return new FsPath(snapshotLocation, SNAPSHOT_METADATA_FILE_NAME);

fluss-server/src/main/java/com/alibaba/fluss/server/kv/snapshot/CompletedSnapshotHandle.java

@@ -34,7 +34,7 @@
 /**
  * A handle to a completed snapshot which contains the metadata file path to the completed snapshot.
  * It is as a wrapper around a {@link CompletedSnapshot} to make the referenced completed snapshot
- * retrievable trough a simple get call.
+ * retrievable through a simple get call.
  */
 public class CompletedSnapshotHandle {
 

fluss-server/src/main/java/com/alibaba/fluss/server/kv/snapshot/PlaceholderKvFileHandler.java

@@ -17,8 +17,8 @@
 package com.alibaba.fluss.server.kv.snapshot;
 
 /**
- * A placeholder handle for shared kv files that will replaced by an original that was created in a
- * previous snapshot. This class is used in the referenced kv files of {@link KvSnapshotHandle}.
+ * A placeholder handle for shared kv files that will be replaced by an original that was created in
+ * a previous snapshot. This class is used in the referenced kv files of {@link KvSnapshotHandle}.
  */
 public class PlaceholderKvFileHandler extends KvFileHandle {
 

fluss-server/src/main/java/com/alibaba/fluss/server/log/LogSegment.java

@@ -377,7 +377,7 @@ public void onBecomeInactiveSegment() throws IOException {
     }
 
     /**
-     * Calculate the offset that would be used for the next message to be append to this segment.
+     * Calculate the offset that would be used for the next message to be appended to this segment.
      * Note that this is expensive.
      */
     public long readNextOffset() throws IOException {
@@ -585,7 +585,7 @@ private void delete(
      *       greater than or equals to the startingOffset.
      * </pre>
      *
-     * <p>This method only returns None when 1) all recordBatch' endOffset < startOffset or 2) the
+     * <p>This method only returns None when 1) all recordBatch's endOffset < startOffset or 2) the
      * log is not empty, but we did not see any recordBatch when scanning the log from the indexed
      * position. The latter could happen if the log is truncated after we get the indexed position
      * but before we scan the log from there. In this case we simply return None and the caller will

fluss-server/src/main/java/com/alibaba/fluss/server/log/remote/DefaultRemoteLogStorage.java

@@ -263,7 +263,7 @@ public void deleteTableBucket(PhysicalTablePath physicalTablePath, TableBucket t
 
     private List<CompletableFuture<Void>> createUploadFutures(
             RemoteLogSegment remoteLogSegment, LogSegmentFiles logSegmentFiles) throws IOException {
-        FsPath rlsPath = creatRemoteLogSegmentDir(remoteLogSegment);
+        FsPath rlsPath = createRemoteLogSegmentDir(remoteLogSegment);
         List<Path> localFiles = logSegmentFiles.getAllPaths();
         List<CompletableFuture<Void>> list = new ArrayList<>();
         for (Path localFile : localFiles) {
@@ -319,7 +319,7 @@ private List<CompletableFuture<Void>> createUploadFutures(
         }
     }
 
-    private FsPath creatRemoteLogSegmentDir(RemoteLogSegment remoteLogSegment) throws IOException {
+    private FsPath createRemoteLogSegmentDir(RemoteLogSegment remoteLogSegment) throws IOException {
         FsPath remoteLogSegmentDir = remoteLogSegmentDir(remoteLogDir, remoteLogSegment);
         fileSystem.mkdirs(remoteLogSegmentDir);
         return remoteLogSegmentDir;

fluss-server/src/main/java/com/alibaba/fluss/server/utils/RpcGatewayManager.java

@@ -92,7 +92,7 @@ public void addServer(ServerNode serverNode) {
      * removed.
      *
      * @param serverId the id of the server to be removed
-     * @return a future to be completed when the the disconnection is complete
+     * @return a future to be completed when the disconnection is complete
      */
     public CompletableFuture<Void> removeServer(int serverId) {
         ServerRpcGateway serverRpcGateway = serverRpcGateways.remove(serverId);

fluss-server/src/main/java/com/alibaba/fluss/server/zk/CuratorFrameworkWithUnhandledErrorListener.java

@@ -23,7 +23,7 @@
 import java.io.Closeable;
 
 /**
- * A wrapper for curatorFramework and unHandledErrorListener which should be unregister from
+ * A wrapper for curatorFramework and unHandledErrorListener which should be unregistered from
  * curatorFramework before closing it.
  */
 public class CuratorFrameworkWithUnhandledErrorListener implements Closeable {

fluss-server/src/test/java/com/alibaba/fluss/server/coordinator/TableManagerTest.java

@@ -157,7 +157,7 @@ void testDeleteTable() throws Exception {
         // call method resumeDeletions, should delete the assignments from zk
         tableManager.resumeDeletions();
         assertThat(zookeeperClient.getTableAssignment(tableId)).isEmpty();
-        // the table will also removed from coordinator context
+        // the table will also be removed from coordinator context
         assertThat(coordinatorContext.getAllReplicasForTable(tableId)).isEmpty();
     }
 

fluss-server/src/test/java/com/alibaba/fluss/server/kv/snapshot/SharedKvFileRegistryTest.java

@@ -62,7 +62,7 @@ void testRegistryNormal() throws Exception {
         sharedKvFileRegistry.registerReference(
                 SharedKvFileRegistryKey.fromKvFileHandle(placeHolder), placeHolder, 1);
         sharedKvFileRegistry.unregisterUnusedKvFile(1L);
-        // the handle shoudn't be discarded since snapshot1 is still referring to it
+        // the handle shouldn't be discarded since snapshot1 is still referring to it
         assertThat(testKvHandle.discarded).isFalse();
 
         sharedKvFileRegistry.unregisterUnusedKvFile(2L);

fluss-server/src/test/java/com/alibaba/fluss/server/kv/snapshot/TestCompletedSnapshotHandleStore.java

@@ -25,7 +25,7 @@
 import java.util.List;
 import java.util.Optional;
 
-/** A implementation of {@link CompletedSnapshotStore} for test purpose. */
+/** An implementation of {@link CompletedSnapshotStore} for test purpose. */
 public class TestCompletedSnapshotHandleStore implements CompletedSnapshotHandleStore {
 
     private final SupplierWithException<List<Tuple2<CompletedSnapshotHandle, String>>, Exception>

fluss-server/src/test/java/com/alibaba/fluss/server/metrics/ServerMetricUtilsTest.java

@@ -203,7 +203,7 @@ void testNonHeapMetricUsageNotStatic() throws Exception {
     private static class Dummy {}
 
     /**
-     * Define an new class using {@link Dummy} class's name and bytecode to consume Metaspace and
+     * Define a new class using {@link Dummy} class's name and bytecode to consume Metaspace and
      * NonHeap memory.
      */
     private static Class<?> redefineDummyClass() throws ClassNotFoundException {

fluss-server/src/test/java/com/alibaba/fluss/server/replica/ReplicaTestBase.java

@@ -501,7 +501,7 @@ protected Set<String> listRemoteLogFiles(TableBucket tableBucket) throws IOExcep
                 .collect(Collectors.toSet());
     }
 
-    /** A implementation of {@link SnapshotContext} for test purpose. */
+    /** An implementation of {@link SnapshotContext} for test purpose. */
     protected class TestSnapshotContext implements SnapshotContext {
 
         private final FsPath remoteKvTabletDir;

fluss-server/src/test/java/com/alibaba/fluss/server/testutils/KvTestUtils.java

@@ -93,11 +93,11 @@ public static void checkSnapshotIncrementWithNewlyFiles(
             int expectedNewFileNum) {
         Set<String> previousNewlyFiles =
                 toNewlyLocalFiles(previousSnapshotHandle.getSharedKvFileHandles());
-        // get the newly upload files from the currently snapshot
+        // get the new upload files from the current snapshot
         int newlyUploadedFiles = 0;
         for (KvFileHandleAndLocalPath handle : currentSnapshotHandle.getSharedKvFileHandles()) {
             if (handle.getKvFileHandle() instanceof PlaceholderKvFileHandler) {
-                // if it's a place holder, it should be file in previous snapshot
+                // if it's a placeholder, it should be file in previous snapshot
                 assertThat(previousNewlyFiles).contains(handle.getLocalPath());
             } else {
                 newlyUploadedFiles += 1;

fluss-test-utils/src/main/java/com/alibaba/fluss/testutils/common/CheckedThread.java

@@ -21,7 +21,7 @@
  * exceptions.
  *
  * <p>Rather than overriding {@link Thread#run()} (or supplying a {@link Runnable}), one needs to
- * extends this class and implement the {@link #go()} method. That method may throw exceptions.
+ * extend this class and implement the {@link #go()} method. That method may throw exceptions.
  *
  * <p>Exception from the {@link #go()} method are caught and re-thrown when joining this thread via
  * the {@link #sync()} method.

fluss-test-utils/src/main/java/com/alibaba/fluss/testutils/common/ContextClassLoaderExtension.java

@@ -34,7 +34,7 @@
 import java.util.List;
 import java.util.function.Function;
 
-/** JUnit extension to customize the classloader that a test is run with. */
+/** JUnit's extension to customize the classloader that a test is run with. */
 public class ContextClassLoaderExtension implements BeforeAllCallback, AfterAllCallback {
 
     private File tempDir;

website/docs/dev/building.md

@@ -10,7 +10,7 @@ This page covers how to build Fluss 0.6.0-SNAPSHOT from sources.
 
 In order to build Fluss you need to get the source code by [clone the git repository](https://github.com/alibaba/fluss).
 
-In addition you need **Maven 3.8.6** and a **JDK** (Java Development Kit). Fluss requires **Java 8 or Java 11** to build.
+In addition, you need **Maven 3.8.6** and a **JDK** (Java Development Kit). Fluss requires **Java 8 or Java 11** to build.
 
 To clone from git, enter:
 

website/docs/install-deploy/deploying-distributed-cluster.md

@@ -13,11 +13,11 @@ This page provides instructions on how to deploy a *distributed cluster* for Flu
 
 Fluss runs on all *UNIX-like environments*, e.g. **Linux**, **Mac OS X**.
 To build a distributed cluster, you need to have at least two nodes.
-This docs provides a simple example of how to deploy a distributed cluster on three nodes.
+This doc provides a simple example of how to deploy a distributed cluster on three nodes.
 
 ### Software Requirements
 
-Before you start to setup the system, make sure you have the following software installed **on each node**:
+Before you start to set up the system, make sure you have the following software installed **on each node**:
 - **Java 17** or higher (Java 8 and Java 11 are not recommended)
 - **Zookeeper 3.6.0** or higher (It is not recommended to use zookeeper versions below 3.6.0)
 

website/docs/intro.md

@@ -12,7 +12,7 @@ Fluss is a streaming storage built for real-time analytics which can serve as th
 It bridges the gap between **streaming data** and the data **Lakehouse** by enabling low-latency, high-throughput data ingestion and processing while seamlessly integrating with popular compute engines like **Apache Flink**, while **Apache Spark**, and **StarRocks** are coming soon.
 
 Fluss supports `streaming reads` and `writes` with sub-second latency and stores data in a columnar format, enhancing query performance and reducing storage costs. 
-It offers flexible table types, including append-only **Log Tables** and updateable **PrimaryKey Tables**, to accommodate diverse real-time analytics and processing needs.
+It offers flexible table types, including append-only **Log Tables** and updatable **PrimaryKey Tables**, to accommodate diverse real-time analytics and processing needs.
 
 With built-in replication for fault tolerance, horizontal scalability, and advanced features like high-QPS lookup joins and bulk read/write operations, Fluss is ideal for powering **real-time analytics**, **AI/ML pipelines**, and **streaming data warehouses**.