stevenzwu commented on a change in pull request #4060:
URL: https://github.com/apache/iceberg/pull/4060#discussion_r803294093
##########
File path:
flink/v1.14/flink/src/main/java/org/apache/iceberg/flink/source/DataIterator.java
##########
@@ -41,16 +42,49 @@
private final FileScanTaskReader<T> fileScanTaskReader;
private final InputFilesDecryptor inputFilesDecryptor;
- private Iterator<FileScanTask> tasks;
+ private final CombinedScanTask combinedTask;
+
+ private Iterator<FileScanTask> fileTasksIterator;
private CloseableIterator<T> currentIterator;
+ private int fileOffset;
+ private long recordOffset;
public DataIterator(FileScanTaskReader<T> fileScanTaskReader,
CombinedScanTask task,
FileIO io, EncryptionManager encryption) {
this.fileScanTaskReader = fileScanTaskReader;
this.inputFilesDecryptor = new InputFilesDecryptor(task, io, encryption);
- this.tasks = task.files().iterator();
+ this.combinedTask = task;
+
+ this.fileTasksIterator = task.files().iterator();
this.currentIterator = CloseableIterator.empty();
+
+ // fileOffset starts at -1 because we started
+ // from an empty iterator that is not from the split files.
+ this.fileOffset = -1;
+ this.recordOffset = 0L;
+ }
+
+ public void seek(int startingFileOffset, long startingRecordOffset) {
+ // skip files
+ Preconditions.checkArgument(startingFileOffset <
combinedTask.files().size(),
+ "Checkpointed file offset is %d, while CombinedScanTask has %d files",
Review comment:
will update to `"Invalid startingFileOffset %d for CombinedScanTask with
%d files: %s",
startingFileOffset, combinedTask.files().size(), combinedTask`
##########
File path:
flink/v1.14/flink/src/main/java/org/apache/iceberg/flink/source/DataIterator.java
##########
@@ -41,16 +42,49 @@
private final FileScanTaskReader<T> fileScanTaskReader;
private final InputFilesDecryptor inputFilesDecryptor;
- private Iterator<FileScanTask> tasks;
+ private final CombinedScanTask combinedTask;
+
+ private Iterator<FileScanTask> fileTasksIterator;
private CloseableIterator<T> currentIterator;
+ private int fileOffset;
+ private long recordOffset;
public DataIterator(FileScanTaskReader<T> fileScanTaskReader,
CombinedScanTask task,
FileIO io, EncryptionManager encryption) {
this.fileScanTaskReader = fileScanTaskReader;
this.inputFilesDecryptor = new InputFilesDecryptor(task, io, encryption);
- this.tasks = task.files().iterator();
+ this.combinedTask = task;
+
+ this.fileTasksIterator = task.files().iterator();
this.currentIterator = CloseableIterator.empty();
+
+ // fileOffset starts at -1 because we started
+ // from an empty iterator that is not from the split files.
+ this.fileOffset = -1;
+ this.recordOffset = 0L;
+ }
+
+ public void seek(int startingFileOffset, long startingRecordOffset) {
+ // skip files
+ Preconditions.checkArgument(startingFileOffset <
combinedTask.files().size(),
+ "Checkpointed file offset is %d, while CombinedScanTask has %d files",
+ startingFileOffset, combinedTask.files().size());
+ for (long i = 0L; i < startingFileOffset; ++i) {
+ fileTasksIterator.next();
+ }
+ updateCurrentIterator();
Review comment:
will fix
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
