(gravitino) branch main updated: [#8006]Improvement(DorisUtils): fix bucket count parsing in DorisUtils (#8744)

[jmclean]

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

jmclean pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/gravitino.git


The following commit(s) were added to refs/heads/main by this push:
     new e596d822e8 [#8006]Improvement(DorisUtils): fix bucket count parsing in 
DorisUtils (#8744)
e596d822e8 is described below

commit e596d822e845dd532b9cf568e253110d5833854f
Author: Sambhavi Pandey <48976443+pandeysam...@users.noreply.github.com>
AuthorDate: Fri Oct 3 12:39:25 2025 +0530

    [#8006]Improvement(DorisUtils): fix bucket count parsing in DorisUtils 
(#8744)
    
    ### What changes were proposed in this pull request?
    
    updated the Regex Pattern to capture the bucket details.
    
    - Ensure the regex matches both with and without BUCKETS.
    - If the regex matches but BUCKETS is missing, default to 1.
    
    ### Why are the changes needed?
    
    To fix the bucket count parsing in DorisUtils. The current regex expects
    BUCKETS to always be present, but in the absence of BUCKETS, the code
    should default to 1.
    The code already defaults to 1 if [matcher.group(5)] is null, but the
    regex may not always match if BUCKETS is missing, causing the method to
    throw an exception.
    
    Fix: (#8006)
    
    ### Does this PR introduce _any_ user-facing change?
    No
    
    ### How was this patch tested?
    unit testing
---
 .../apache/gravitino/catalog/doris/utils/DorisUtils.java   |  7 ++++---
 .../gravitino/catalog/doris/utils/TestDorisUtils.java      | 14 ++++++++++++++
 2 files changed, 18 insertions(+), 3 deletions(-)

diff --git 
a/catalogs/catalog-jdbc-doris/src/main/java/org/apache/gravitino/catalog/doris/utils/DorisUtils.java
 
b/catalogs/catalog-jdbc-doris/src/main/java/org/apache/gravitino/catalog/doris/utils/DorisUtils.java
index 6d93924416..11b72fb2ce 100644
--- 
a/catalogs/catalog-jdbc-doris/src/main/java/org/apache/gravitino/catalog/doris/utils/DorisUtils.java
+++ 
b/catalogs/catalog-jdbc-doris/src/main/java/org/apache/gravitino/catalog/doris/utils/DorisUtils.java
@@ -49,7 +49,8 @@ public final class DorisUtils {
 
   private static final Pattern DISTRIBUTION_INFO_PATTERN =
       Pattern.compile(
-          "DISTRIBUTED 
BY\\s+(HASH|RANDOM)\\s*(\\(([^)]+)\\))?\\s*(BUCKETS\\s+(\\d+|AUTO))?");
+          "DISTRIBUTED 
BY\\s+(HASH|RANDOM)\\s*(\\(([^)]+)\\))?(?:\\s*BUCKETS\\s+(\\d+|AUTO))?",
+          Pattern.CASE_INSENSITIVE);
 
   private static final String LIST_PARTITION = "LIST";
   private static final String RANGE_PARTITION = "RANGE";
@@ -221,8 +222,8 @@ public final class DorisUtils {
 
   private static int extractBucketNum(Matcher matcher) {
     int bucketNum = 1;
-    if (matcher.group(5) != null) {
-      String bucketValue = matcher.group(5);
+    if (matcher.group(4) != null) {
+      String bucketValue = matcher.group(4);
       // Use -1 to indicate auto bucket.
       bucketNum =
           bucketValue.trim().toUpperCase().equals("AUTO")
diff --git 
a/catalogs/catalog-jdbc-doris/src/test/java/org/apache/gravitino/catalog/doris/utils/TestDorisUtils.java
 
b/catalogs/catalog-jdbc-doris/src/test/java/org/apache/gravitino/catalog/doris/utils/TestDorisUtils.java
index 43c61c29f0..0c9970ddd2 100644
--- 
a/catalogs/catalog-jdbc-doris/src/test/java/org/apache/gravitino/catalog/doris/utils/TestDorisUtils.java
+++ 
b/catalogs/catalog-jdbc-doris/src/test/java/org/apache/gravitino/catalog/doris/utils/TestDorisUtils.java
@@ -191,4 +191,18 @@ public class TestDorisUtils {
         
DorisUtils.extractDistributionInfoFromSql(createTableSqlWithRandomAuto);
     assertEquals(distribution3.number(), -1);
   }
+
+  @Test
+  public void testExtractBucketNumFromSql() {
+    String createTableSql =
+        "CREATE TABLE `testTable` (\n`col1` int NOT NULL\n) ENGINE=OLAP\n 
DISTRIBUTED BY HASH(`col1`) BUCKETS 8";
+    Distribution distribution = 
DorisUtils.extractDistributionInfoFromSql(createTableSql);
+    assertEquals(8, distribution.number());
+
+    String createTableSqlWithoutBucket =
+        "CREATE TABLE `testTable` (\n`col1` int NOT NULL\n) ENGINE=OLAP\n 
DISTRIBUTED BY HASH(`col1`)";
+    Distribution distributionDefault =
+        DorisUtils.extractDistributionInfoFromSql(createTableSqlWithoutBucket);
+    assertEquals(1, distributionDefault.number());
+  }
 }