[hudi] branch master updated: [MINOR] Fix the hudi-cli export command (#8608)

[danny0405]

This is an automated email from the ASF dual-hosted git repository.

danny0405 pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/hudi.git


The following commit(s) were added to refs/heads/master by this push:
     new f3ddcd97625 [MINOR] Fix the hudi-cli export command (#8608)
f3ddcd97625 is described below

commit f3ddcd97625631f91488da745164bbe7809ecc76
Author: Prashant Wason <pwa...@uber.com>
AuthorDate: Sat Apr 29 20:07:29 2023 -0700

    [MINOR] Fix the hudi-cli export command (#8608)
    
    1. Removed the hardcoded location of archives
    2. Handle the case where the metadata from an archive entry may be null 
(seen in very old archives)
---
 .../java/org/apache/hudi/cli/commands/ExportCommand.java  | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git 
a/hudi-cli/src/main/java/org/apache/hudi/cli/commands/ExportCommand.java 
b/hudi-cli/src/main/java/org/apache/hudi/cli/commands/ExportCommand.java
index 54227a613e4..e81a532f2a8 100644
--- a/hudi-cli/src/main/java/org/apache/hudi/cli/commands/ExportCommand.java
+++ b/hudi-cli/src/main/java/org/apache/hudi/cli/commands/ExportCommand.java
@@ -44,6 +44,8 @@ import org.apache.hudi.common.table.timeline.HoodieTimeline;
 import org.apache.hudi.common.table.timeline.TimelineMetadataUtils;
 import org.apache.hudi.common.util.collection.ClosableIterator;
 import org.apache.hudi.exception.HoodieException;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
 import org.springframework.shell.standard.ShellComponent;
 import org.springframework.shell.standard.ShellMethod;
 import org.springframework.shell.standard.ShellOption;
@@ -67,6 +69,8 @@ import java.util.stream.Collectors;
 @ShellComponent
 public class ExportCommand {
 
+  private static final Logger LOG = 
LoggerFactory.getLogger(ExportCommand.class);
+
   @ShellMethod(key = "export instants", value = "Export Instants and their 
metadata from the Timeline")
   public String exportInstants(
       @ShellOption(value = {"--limit"}, help = "Limit Instants", defaultValue 
= "-1") final Integer limit,
@@ -77,7 +81,7 @@ public class ExportCommand {
       throws Exception {
 
     final String basePath = HoodieCLI.getTableMetaClient().getBasePath();
-    final Path archivePath = new Path(basePath + 
"/.hoodie/.commits_.archive*");
+    final Path archivePath = new 
Path(HoodieCLI.getTableMetaClient().getArchivePath());
     final Set<String> actionSet = new 
HashSet<String>(Arrays.asList(filter.split(",")));
     int numExports = limit == -1 ? Integer.MAX_VALUE : limit;
     int numCopied = 0;
@@ -121,7 +125,7 @@ public class ExportCommand {
       Reader reader = HoodieLogFormat.newReader(fileSystem, new 
HoodieLogFile(fs.getPath()), HoodieArchivedMetaEntry.getClassSchema());
 
       // read the avro blocks
-      while (reader.hasNext() && copyCount < limit) {
+      while (reader.hasNext() && copyCount++ < limit) {
         HoodieAvroDataBlock blk = (HoodieAvroDataBlock) reader.next();
         try (ClosableIterator<HoodieRecord<IndexedRecord>> recordItr = 
blk.getRecordIterator(HoodieRecordType.AVRO)) {
           while (recordItr.hasNext()) {
@@ -158,11 +162,12 @@ public class ExportCommand {
             }
 
             final String instantTime = 
archiveEntryRecord.get("commitTime").toString();
+            if (metadata == null) {
+              LOG.error("Could not load metadata for action " + action + " at 
instant time " + instantTime);
+              continue;
+            }
             final String outPath = localFolder + Path.SEPARATOR + instantTime 
+ "." + action;
             writeToFile(outPath, HoodieAvroUtils.avroToJson(metadata, true));
-            if (++copyCount == limit) {
-              break;
-            }
           }
         }
       }