tool
/
starrocks
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[BugFix] Fix SQL syntax error in histogram statistics when MCV contains single quotes (#62853) 

Signed-off-by: stephen <stephen5217@163.com>
This commit is contained in:
stephen 2025-09-09 14:28:27 +08:00 committed by GitHub
parent 806161bca7
commit ad5500f35e
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 39 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
fe/fe-core/src/main/java/com/starrocks/statistic/HistogramStatisticsCollectJob.java
View File

@ -167,7 +167,9 @@ public class HistogramStatisticsCollectJob extends StatisticsCollectJob {
if (mostCommonValues.isEmpty()) {
context.put("mcv", "NULL");
} else {
context.put("mcv", "'[" + Joiner.on(",").join(mcvList) + "]'");
String mcvJson = "[" + Joiner.on(",").join(mcvList) + "]";
String escapedMcvJson = mcvJson.replace("'", "''");
context.put("mcv", "'" + escapedMcvJson + "'");
}
if (!mostCommonValues.isEmpty()) {

41
test/sql/test_analyze_statistics/R/test_histogram
View File

@ -118,15 +118,15 @@ LIMIT 10;
-- !result
[UC] ANALYZE FULL TABLE t1;
-- result:
analyze_test_3ac0a9e0097347afa87ef2b1e2025511.t1 analyze status OK
analyze_test_252a40f00cef40969761819bc6f5e66e.t1 analyze status OK
-- !result
[UC] ANALYZE FULL TABLE t2;
-- result:
analyze_test_3ac0a9e0097347afa87ef2b1e2025511.t2 analyze status OK
analyze_test_252a40f00cef40969761819bc6f5e66e.t2 analyze status OK
-- !result
[UC] ANALYZE FULL TABLE t3;
-- result:
analyze_test_3ac0a9e0097347afa87ef2b1e2025511.t3 analyze status OK
analyze_test_252a40f00cef40969761819bc6f5e66e.t3 analyze status OK
-- !result
SELECT min,max,row_count,hll_cardinality(ndv) FROM _statistics_.column_statistics WHERE table_name = 'analyze_test_${uuid0}.t1' and column_name = 'k1';
-- result:
@ -166,15 +166,15 @@ None
-- !result
[UC] ANALYZE TABLE t1 UPDATE HISTOGRAM ON k1,k2,k3 PROPERTIES('histogram_sample_ratio' = '1.0');
-- result:
analyze_test_3ac0a9e0097347afa87ef2b1e2025511.t1 histogram status OK
analyze_test_252a40f00cef40969761819bc6f5e66e.t1 histogram status OK
-- !result
[UC] ANALYZE TABLE t2 UPDATE HISTOGRAM ON k1,k2,k3 PROPERTIES('histogram_sample_ratio' = '1.0');
-- result:
analyze_test_3ac0a9e0097347afa87ef2b1e2025511.t2 histogram status OK
analyze_test_252a40f00cef40969761819bc6f5e66e.t2 histogram status OK
-- !result
[UC] ANALYZE TABLE t3 UPDATE HISTOGRAM ON k1,k2,k3 PROPERTIES('histogram_sample_ratio' = '1.0', "histogram_mcv_size" = '0');
-- result:
analyze_test_3ac0a9e0097347afa87ef2b1e2025511.t3 histogram status OK
analyze_test_252a40f00cef40969761819bc6f5e66e.t3 histogram status OK
-- !result
set enable_stats_to_optimize_skew_join = false;
-- result:
@ -263,15 +263,15 @@ None
-- !result
[UC] ANALYZE TABLE t1 UPDATE HISTOGRAM ON k1,k2,k3 PROPERTIES('histogram_sample_ratio' = '1.0', "histogram_mcv_size" = '400');
-- result:
analyze_test_3ac0a9e0097347afa87ef2b1e2025511.t1 histogram status OK
analyze_test_252a40f00cef40969761819bc6f5e66e.t1 histogram status OK
-- !result
[UC] ANALYZE TABLE t2 UPDATE HISTOGRAM ON k1,k2,k3 PROPERTIES('histogram_sample_ratio' = '1.0', "histogram_mcv_size" = '400');
-- result:
analyze_test_3ac0a9e0097347afa87ef2b1e2025511.t2 histogram status OK
analyze_test_252a40f00cef40969761819bc6f5e66e.t2 histogram status OK
-- !result
[UC] ANALYZE TABLE t3 UPDATE HISTOGRAM ON k1,k2,k3 PROPERTIES('histogram_sample_ratio' = '1.0', "histogram_mcv_size" = '400');
-- result:
analyze_test_3ac0a9e0097347afa87ef2b1e2025511.t3 histogram status OK
analyze_test_252a40f00cef40969761819bc6f5e66e.t3 histogram status OK
-- !result
function: assert_explain_costs_contains('SELECT COUNT(*) FROM t1 JOIN t2 USING (k1)', 'cardinality: 45150', 'cardinality: 45150', 'cardinality: 4589949')
-- result:
@ -291,15 +291,15 @@ None
-- !result
[UC] ANALYZE TABLE t1 UPDATE HISTOGRAM ON k1,k2,k3 WITH 256 BUCKETS PROPERTIES('histogram_sample_ratio' = '1.0', "histogram_mcv_size" = '100');
-- result:
analyze_test_3ac0a9e0097347afa87ef2b1e2025511.t1 histogram status OK
analyze_test_252a40f00cef40969761819bc6f5e66e.t1 histogram status OK
-- !result
[UC] ANALYZE TABLE t2 UPDATE HISTOGRAM ON k1,k2,k3 WITH 256 BUCKETS PROPERTIES('histogram_sample_ratio' = '1.0', "histogram_mcv_size" = '100');
-- result:
analyze_test_3ac0a9e0097347afa87ef2b1e2025511.t2 histogram status OK
analyze_test_252a40f00cef40969761819bc6f5e66e.t2 histogram status OK
-- !result
[UC] ANALYZE TABLE t3 UPDATE HISTOGRAM ON k1,k2,k3 WITH 256 BUCKETS PROPERTIES('histogram_sample_ratio' = '1.0', "histogram_mcv_size" = '0');
-- result:
analyze_test_3ac0a9e0097347afa87ef2b1e2025511.t3 histogram status OK
analyze_test_252a40f00cef40969761819bc6f5e66e.t3 histogram status OK
-- !result
function: assert_explain_costs_contains('SELECT COUNT(*) FROM t1 JOIN t2 USING (k1)', 'cardinality: 45150', 'cardinality: 45150', 'cardinality: 4562636')
-- result:
@ -316,4 +316,21 @@ None
function: assert_explain_costs_contains('SELECT COUNT(*) FROM (t1 n1 JOIN t2 n2 ON n1.k1 = n2.k1) JOIN t3 n3 ON n1.k3 = n3.k3', 'cardinality: 45150', 'cardinality: 45150', 'cardinality: 90000', 'cardinality: 4562636', 'cardinality: 1446330752')
-- result:
None
-- !result
create table test_escaped_string (k1 string) properties("replication_num"="1");
-- result:
-- !result
insert into test_escaped_string select "aaaaa's";
-- result:
-- !result
insert into test_escaped_string select "bbbbbbb";
-- result:
-- !result
[UC] analyze table test_escaped_string update histogram on k1;
-- result:
analyze_test_252a40f00cef40969761819bc6f5e66e.test_escaped_string histogram status OK
-- !result
function: assert_explain_costs_contains('select k1 from test_escaped_string', 'MCV')
-- result:
None
-- !result

7
test/sql/test_analyze_statistics/T/test_histogram
View File

@ -154,3 +154,10 @@ function: assert_explain_costs_contains('SELECT COUNT(*) FROM t1 JOIN t2 USING (
function: assert_explain_costs_contains('SELECT COUNT(*) FROM (t1 n1 JOIN t2 n2 ON n1.k1 = n2.k1) JOIN t3 n3 ON n1.k1 = n3.k1', 'cardinality: 45150', 'cardinality: 45150', 'cardinality: 90000', 'cardinality: 4562636', 'cardinality: 1173989056')
function: assert_explain_costs_contains('SELECT COUNT(*) FROM (t1 n1 JOIN t2 n2 ON n1.k1 = n2.k1) JOIN t3 n3 ON n1.k3 = n3.k3', 'cardinality: 45150', 'cardinality: 45150', 'cardinality: 90000', 'cardinality: 4562636', 'cardinality: 1446330752')
create table test_escaped_string (k1 string) properties("replication_num"="1");
insert into test_escaped_string select "aaaaa's";
insert into test_escaped_string select "bbbbbbb";
[UC] analyze table test_escaped_string update histogram on k1;
function: assert_explain_costs_contains('select k1 from test_escaped_string', 'MCV')