Jibing-Li commented on code in PR #24853:
URL: https://github.com/apache/doris/pull/24853#discussion_r1336584266
##########
fe/fe-core/src/main/java/org/apache/doris/statistics/HMSAnalysisTask.java:
##########
@@ -144,27 +173,101 @@ private void getTableColumnStats() throws Exception {
// MAX(`r_regionkey`) AS max,
// 0 AS data_size,
// NOW() FROM `hive`.`tpch100`.`region`
- if (isPartitionOnly) {
- getPartitionNames();
- List<String> partitionAnalysisSQLs = new ArrayList<>();
- for (String partId : this.partitionNames) {
- partitionAnalysisSQLs.add(generateSqlForPartition(partId));
+ StringBuilder sb = new StringBuilder();
+ sb.append(ANALYZE_TABLE_TEMPLATE);
+ Map<String, String> params = buildStatsParams("NULL");
+ params.put("dataSizeFunction", getDataSizeFunction(col));
+ params.put("nullCountExpr", getNullCountExpression());
+ StringSubstitutor stringSubstitutor = new StringSubstitutor(params);
+ String sql = stringSubstitutor.replace(sb.toString());
+ executeInsertSql(sql);
+ }
+
+ private void getPartitionColumnStats() throws Exception {
+ Set<String> partitionNames = table.getPartitionNames();
+ Set<String> ndvPartValues = Sets.newHashSet();
+ long numNulls = 0;
+ long dataSize = 0;
+ String min = null;
+ String max = null;
+ for (String names : partitionNames) {
+ // names is like "date=20230101" for one level partition
+ // and like "date=20230101/hour=12" for two level partition
+ String[] parts = names.split("/");
Review Comment:
Will refactor the code
--
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]
