[Hotfix]nullsCount in columnStatistic should marked as not present in… #11549
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -331,31 +331,31 @@ public static HiveColumnStatistics fromMetastoreApiColumnStatistics(ColumnStatis | |
| LongColumnStatsData longStatsData = columnStatistics.getStatsData().getLongStats(); | ||
| OptionalLong min = longStatsData.isSetLowValue() ? OptionalLong.of(longStatsData.getLowValue()) : OptionalLong.empty(); | ||
| OptionalLong max = longStatsData.isSetHighValue() ? OptionalLong.of(longStatsData.getHighValue()) : OptionalLong.empty(); | ||
| OptionalLong nullsCount = longStatsData.isSetNumNulls() ? fromMetastoreNullsCount(longStatsData.getNumNulls()) : OptionalLong.empty(); | ||
| OptionalLong distinctValuesCount = longStatsData.isSetNumDVs() ? OptionalLong.of(longStatsData.getNumDVs()) : OptionalLong.empty(); | ||
| return createIntegerColumnStatistics(min, max, nullsCount, fromMetastoreDistinctValuesCount(distinctValuesCount, nullsCount, rowCount)); | ||
| } | ||
| if (columnStatistics.getStatsData().isSetDoubleStats()) { | ||
| DoubleColumnStatsData doubleStatsData = columnStatistics.getStatsData().getDoubleStats(); | ||
| OptionalDouble min = doubleStatsData.isSetLowValue() ? OptionalDouble.of(doubleStatsData.getLowValue()) : OptionalDouble.empty(); | ||
| OptionalDouble max = doubleStatsData.isSetHighValue() ? OptionalDouble.of(doubleStatsData.getHighValue()) : OptionalDouble.empty(); | ||
| OptionalLong nullsCount = doubleStatsData.isSetNumNulls() ? fromMetastoreNullsCount(doubleStatsData.getNumNulls()) : OptionalLong.empty(); | ||
|
||
| OptionalLong distinctValuesCount = doubleStatsData.isSetNumDVs() ? OptionalLong.of(doubleStatsData.getNumDVs()) : OptionalLong.empty(); | ||
| return createDoubleColumnStatistics(min, max, nullsCount, fromMetastoreDistinctValuesCount(distinctValuesCount, nullsCount, rowCount)); | ||
| } | ||
| if (columnStatistics.getStatsData().isSetDecimalStats()) { | ||
| DecimalColumnStatsData decimalStatsData = columnStatistics.getStatsData().getDecimalStats(); | ||
| Optional<BigDecimal> min = decimalStatsData.isSetLowValue() ? fromMetastoreDecimal(decimalStatsData.getLowValue()) : Optional.empty(); | ||
| Optional<BigDecimal> max = decimalStatsData.isSetHighValue() ? fromMetastoreDecimal(decimalStatsData.getHighValue()) : Optional.empty(); | ||
| OptionalLong nullsCount = decimalStatsData.isSetNumNulls() ? fromMetastoreNullsCount(decimalStatsData.getNumNulls()) : OptionalLong.empty(); | ||
| OptionalLong distinctValuesCount = decimalStatsData.isSetNumDVs() ? OptionalLong.of(decimalStatsData.getNumDVs()) : OptionalLong.empty(); | ||
| return createDecimalColumnStatistics(min, max, nullsCount, fromMetastoreDistinctValuesCount(distinctValuesCount, nullsCount, rowCount)); | ||
| } | ||
| if (columnStatistics.getStatsData().isSetDateStats()) { | ||
| DateColumnStatsData dateStatsData = columnStatistics.getStatsData().getDateStats(); | ||
| Optional<LocalDate> min = dateStatsData.isSetLowValue() ? fromMetastoreDate(dateStatsData.getLowValue()) : Optional.empty(); | ||
| Optional<LocalDate> max = dateStatsData.isSetHighValue() ? fromMetastoreDate(dateStatsData.getHighValue()) : Optional.empty(); | ||
| OptionalLong nullsCount = dateStatsData.isSetNumNulls() ? fromMetastoreNullsCount(dateStatsData.getNumNulls()) : OptionalLong.empty(); | ||
| OptionalLong distinctValuesCount = dateStatsData.isSetNumDVs() ? OptionalLong.of(dateStatsData.getNumDVs()) : OptionalLong.empty(); | ||
| return createDateColumnStatistics(min, max, nullsCount, fromMetastoreDistinctValuesCount(distinctValuesCount, nullsCount, rowCount)); | ||
| } | ||
|
|
@@ -364,13 +364,13 @@ public static HiveColumnStatistics fromMetastoreApiColumnStatistics(ColumnStatis | |
| return createBooleanColumnStatistics( | ||
| booleanStatsData.isSetNumTrues() ? OptionalLong.of(booleanStatsData.getNumTrues()) : OptionalLong.empty(), | ||
| booleanStatsData.isSetNumFalses() ? OptionalLong.of(booleanStatsData.getNumFalses()) : OptionalLong.empty(), | ||
| booleanStatsData.isSetNumNulls() ? fromMetastoreNullsCount(booleanStatsData.getNumNulls()) : OptionalLong.empty()); | ||
| } | ||
| if (columnStatistics.getStatsData().isSetStringStats()) { | ||
| StringColumnStatsData stringStatsData = columnStatistics.getStatsData().getStringStats(); | ||
| OptionalLong maxColumnLength = stringStatsData.isSetMaxColLen() ? OptionalLong.of(stringStatsData.getMaxColLen()) : OptionalLong.empty(); | ||
| OptionalDouble averageColumnLength = stringStatsData.isSetAvgColLen() ? OptionalDouble.of(stringStatsData.getAvgColLen()) : OptionalDouble.empty(); | ||
| OptionalLong nullsCount = stringStatsData.isSetNumNulls() ? fromMetastoreNullsCount(stringStatsData.getNumNulls()) : OptionalLong.empty(); | ||
| OptionalLong distinctValuesCount = stringStatsData.isSetNumDVs() ? OptionalLong.of(stringStatsData.getNumDVs()) : OptionalLong.empty(); | ||
| return createStringColumnStatistics( | ||
| maxColumnLength, | ||
|
|
@@ -382,7 +382,7 @@ public static HiveColumnStatistics fromMetastoreApiColumnStatistics(ColumnStatis | |
| BinaryColumnStatsData binaryStatsData = columnStatistics.getStatsData().getBinaryStats(); | ||
| OptionalLong maxColumnLength = binaryStatsData.isSetMaxColLen() ? OptionalLong.of(binaryStatsData.getMaxColLen()) : OptionalLong.empty(); | ||
| OptionalDouble averageColumnLength = binaryStatsData.isSetAvgColLen() ? OptionalDouble.of(binaryStatsData.getAvgColLen()) : OptionalDouble.empty(); | ||
| OptionalLong nullsCount = binaryStatsData.isSetNumNulls() ? fromMetastoreNullsCount(binaryStatsData.getNumNulls()) : OptionalLong.empty(); | ||
| return createBinaryColumnStatistics( | ||
| maxColumnLength, | ||
| getTotalSizeInBytes(averageColumnLength, rowCount, nullsCount), | ||
|
|
@@ -401,6 +401,18 @@ public static Optional<LocalDate> fromMetastoreDate(Date date) | |
| return Optional.of(LocalDate.ofEpochDay(date.getDaysSinceEpoch())); | ||
| } | ||
|
|
||
| /** | ||
| * Impala `COMPUTE STATS` will write -1 as the null count. | ||
| * @see <a href="https://issues.apache.org/jira/browse/IMPALA-7497">IMPALA-7497</a> | ||
| */ | ||
| public static OptionalLong fromMetastoreNullsCount(long nullsCount) | ||
| { | ||
| if (nullsCount == -1L) { | ||
findepi marked this conversation as resolved.
Outdated
Show resolved
Hide resolved
|
||
| return OptionalLong.empty(); | ||
| } | ||
| return OptionalLong.of(nullsCount); | ||
| } | ||
|
|
||
| public static Optional<BigDecimal> fromMetastoreDecimal(@Nullable Decimal decimal) | ||
| { | ||
| if (decimal == null) { | ||
|
|
||
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
There are other places below that need an update (search for "nullsCount")
Uh oh!
There was an error while loading. Please reload this page.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@findepi , thanks for your correction.
I have add the same conversion for other nullsCounts in method fromMetastoreApiColumnStatistics
I thinks other methods like createDateStatistics which is used to write back the statistics information to Hive, so I should not add this conversion method to it, right?
What your opinion?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
When writing, -1 should by no means be a written value, so no need to change there.