Skip to content

Flink: Fix watermark extractor error message showing field id instead of file #17124

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
anxkhn wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Flink: Fix watermark extractor error message showing field id instead of file #17124

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 0 additions & 1 deletion ...k/src/main/java/org/apache/iceberg/flink/source/reader/ColumnStatsWatermarkExtractor.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -99,7 +99,6 @@ public long extractWatermark(IcebergSourceSplit split) {
&& scanTask.file().lowerBounds().get(eventTimeFieldId) != null,
"Missing statistics for column name = %s in file = %s",

@pvary pvary Jul 7, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could we instead add the id to the message too?

Suggested change
"Missing statistics for column name = %s in file = %s",
"Missing statistics for column name = %s with fieldId = %d in file = %s",

eventTimeFieldName,
eventTimeFieldId,
scanTask.file());
return timeUnit.toMillis(
Conversions.fromByteBuffer(
Expand Down
7 changes: 5 additions & 2 deletions ...c/test/java/org/apache/iceberg/flink/source/reader/TestColumnStatsWatermarkExtractor.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -180,11 +180,14 @@ public void testEmptyStatistics() throws IOException {
assumeThat(columnName).isEqualTo("timestamp_column");

// Create an extractor for a column we do not have statistics
IcebergSourceSplit split = split(0);
ColumnStatsWatermarkExtractor extractor =
new ColumnStatsWatermarkExtractor(10, "missing_field");
assertThatThrownBy(() -> extractor.extractWatermark(split(0)))
assertThatThrownBy(() -> extractor.extractWatermark(split))
.isInstanceOf(IllegalArgumentException.class)
.hasMessageContaining("Missing statistics for column");
.hasMessage(
"Missing statistics for column name = missing_field in file = "
+ split.task().files().iterator().next().file());
}

private IcebergSourceSplit split(int id) throws IOException {
Expand Down
1 change: 0 additions & 1 deletion ...k/src/main/java/org/apache/iceberg/flink/source/reader/ColumnStatsWatermarkExtractor.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -99,7 +99,6 @@ public long extractWatermark(IcebergSourceSplit split) {
&& scanTask.file().lowerBounds().get(eventTimeFieldId) != null,
"Missing statistics for column name = %s in file = %s",
eventTimeFieldName,
eventTimeFieldId,
scanTask.file());
return timeUnit.toMillis(
Conversions.fromByteBuffer(
Expand Down
7 changes: 5 additions & 2 deletions ...c/test/java/org/apache/iceberg/flink/source/reader/TestColumnStatsWatermarkExtractor.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -180,11 +180,14 @@ public void testEmptyStatistics() throws IOException {
assumeThat(columnName).isEqualTo("timestamp_column");

// Create an extractor for a column we do not have statistics
IcebergSourceSplit split = split(0);
ColumnStatsWatermarkExtractor extractor =
new ColumnStatsWatermarkExtractor(10, "missing_field");
assertThatThrownBy(() -> extractor.extractWatermark(split(0)))
assertThatThrownBy(() -> extractor.extractWatermark(split))
.isInstanceOf(IllegalArgumentException.class)
.hasMessageContaining("Missing statistics for column");
.hasMessage(
"Missing statistics for column name = missing_field in file = "
+ split.task().files().iterator().next().file());
}

private IcebergSourceSplit split(int id) throws IOException {
Expand Down
1 change: 0 additions & 1 deletion ...k/src/main/java/org/apache/iceberg/flink/source/reader/ColumnStatsWatermarkExtractor.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -99,7 +99,6 @@ public long extractWatermark(IcebergSourceSplit split) {
&& scanTask.file().lowerBounds().get(eventTimeFieldId) != null,
"Missing statistics for column name = %s in file = %s",
eventTimeFieldName,
eventTimeFieldId,
scanTask.file());
return timeUnit.toMillis(
Conversions.fromByteBuffer(
Expand Down
7 changes: 5 additions & 2 deletions ...c/test/java/org/apache/iceberg/flink/source/reader/TestColumnStatsWatermarkExtractor.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -180,11 +180,14 @@ public void testEmptyStatistics() throws IOException {
assumeThat(columnName).isEqualTo("timestamp_column");

// Create an extractor for a column we do not have statistics
IcebergSourceSplit split = split(0);
ColumnStatsWatermarkExtractor extractor =
new ColumnStatsWatermarkExtractor(10, "missing_field");
assertThatThrownBy(() -> extractor.extractWatermark(split(0)))
assertThatThrownBy(() -> extractor.extractWatermark(split))
.isInstanceOf(IllegalArgumentException.class)
.hasMessageContaining("Missing statistics for column");
.hasMessage(
"Missing statistics for column name = missing_field in file = "
+ split.task().files().iterator().next().file());
}

private IcebergSourceSplit split(int id) throws IOException {
Expand Down
Loading