This is an automated email from the ASF dual-hosted git repository.
englefly pushed a commit to branch skew-stats-poc
in repository https://gitbox.apache.org/repos/asf/doris.git
The following commit(s) were added to refs/heads/skew-stats-poc by this push:
new 525404113af add hotvalues attribute for column statistics
525404113af is described below
commit 525404113afe96ab8421f061204cd869a42dbe2a
Author: minghong <[email protected]>
AuthorDate: Wed Jun 4 11:47:08 2025 +0800
add hotvalues attribute for column statistics
---
.../src/main/java/org/apache/doris/statistics/ColumnStatistic.java | 6 ++++++
1 file changed, 6 insertions(+)
diff --git
a/fe/fe-core/src/main/java/org/apache/doris/statistics/ColumnStatistic.java
b/fe/fe-core/src/main/java/org/apache/doris/statistics/ColumnStatistic.java
index e0e99fcdfad..e27111d70a6 100644
--- a/fe/fe-core/src/main/java/org/apache/doris/statistics/ColumnStatistic.java
+++ b/fe/fe-core/src/main/java/org/apache/doris/statistics/ColumnStatistic.java
@@ -22,6 +22,7 @@ import org.apache.doris.catalog.Column;
import org.apache.doris.catalog.Type;
import org.apache.doris.common.AnalysisException;
import org.apache.doris.datasource.InternalCatalog;
+import org.apache.doris.nereids.trees.expressions.literal.Literal;
import org.apache.doris.nereids.types.DataType;
import org.apache.doris.nereids.types.coercion.CharacterType;
import org.apache.doris.persist.gson.GsonUtils;
@@ -33,6 +34,7 @@ import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.json.JSONObject;
+import java.util.ArrayList;
import java.util.List;
import java.util.Set;
@@ -47,6 +49,8 @@ public class ColumnStatistic {
public static final StatsType MIN_VALUE = StatsType.MIN_VALUE;
public static final StatsType MAX_VALUE = StatsType.MAX_VALUE;
+ public static final double HOT_VALUE_PERCENTAGE = 0.5;
+
private static final Logger LOG =
LogManager.getLogger(ColumnStatistic.class);
public static ColumnStatistic UNKNOWN = new
ColumnStatisticBuilder(1).setAvgSizeByte(1).setNdv(1)
@@ -75,6 +79,8 @@ public class ColumnStatistic {
public final double minValue;
@SerializedName("maxValue")
public final double maxValue;
+ @SerializedName("skewValues")
+ public ArrayList<Literal> hotValues;
@SerializedName("isUnKnown")
public final boolean isUnKnown;
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]