Skip to content

Fix transpose VARCHAR length drift in unpivot/pivot lowering #5479

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
songkant-aws wants to merge 2 commits into
base: main
Choose a base branch
from
+85 −72
Open

Fix transpose VARCHAR length drift in unpivot/pivot lowering #5479

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
35bd92b
Fix transpose VARCHAR length drift in unpivot/pivot lowering
songkant-aws May 28, 2026
8b89df5
Update explain_transpose.yaml expected plan for new lowering shape
songkant-aws May 28, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 13 additions & 6 deletions core/src/main/java/org/opensearch/sql/calcite/CalciteRelNodeVisitor.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -913,6 +913,9 @@ public RelNode visitTranspose(
RelBuilder b = context.relBuilder;
RexBuilder rx = context.rexBuilder;
RelDataType varchar = rx.getTypeFactory().createSqlType(SqlTypeName.VARCHAR);
int axisLiteralLength = fieldNames.stream().mapToInt(String::length).max().orElse(0);
RelDataType axisLiteralType =
rx.getTypeFactory().createSqlType(SqlTypeName.CHAR, axisLiteralLength);

// Step 1: ROW_NUMBER
b.projectPlus(
Expand All @@ -930,18 +933,22 @@ public RelNode visitTranspose(
.map(
f ->
Map.entry(
ImmutableList.of(rx.makeLiteral(f)),
ImmutableList.of(
(RexLiteral) rx.makeLiteral(f, axisLiteralType, false, false)),
ImmutableList.of((RexNode) rx.makeCast(varchar, b.field(f), true))))
.collect(Collectors.toList()));

// Step 3: Trim spaces from columnName column before pivot

RexNode trimmedColumnName =
context.rexBuilder.makeCall(
SqlStdOperatorTable.TRIM,
context.rexBuilder.makeFlag(SqlTrimFunction.Flag.BOTH),
context.rexBuilder.makeLiteral(" "),
b.field(columnName));
context.rexBuilder.makeCast(
varchar,
context.rexBuilder.makeCall(
SqlStdOperatorTable.TRIM,
context.rexBuilder.makeFlag(SqlTrimFunction.Flag.BOTH),
context.rexBuilder.makeLiteral(" "),
b.field(columnName)),
true);

// Step 4: PIVOT
b.pivot(
Expand Down
13 changes: 7 additions & 6 deletions integ-test/src/test/resources/expectedOutput/calcite/explain_transpose.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,20 +3,21 @@ calcite:
LogicalSystemLimit(fetch=[10000], type=[QUERY_SIZE_LIMIT])
LogicalProject(column_names=[$0], row 1=[$1], row 2=[$2], row 3=[$3], row 4=[$4])
LogicalAggregate(group=[{1}], row 1_null=[MAX($0) FILTER $2], row 2_null=[MAX($0) FILTER $3], row 3_null=[MAX($0) FILTER $4], row 4_null=[MAX($0) FILTER $5])
LogicalProject(_value_transpose_=[CAST($19):VARCHAR NOT NULL], $f20=[TRIM(FLAG(BOTH), ' ', $18)], $f21=[=($17, 1)], $f22=[=($17, 2)], $f23=[=($17, 3)], $f24=[=($17, 4)])
LogicalProject(_value_transpose_=[CAST($19):VARCHAR NOT NULL], $f20=[CAST(TRIM(FLAG(BOTH), ' ', $18)):VARCHAR NOT NULL], $f21=[=($17, 1)], $f22=[=($17, 2)], $f23=[=($17, 3)], $f24=[=($17, 4)])
LogicalFilter(condition=[IS NOT NULL($19)])
LogicalProject(account_number=[$0], firstname=[$1], address=[$2], balance=[$3], gender=[$4], city=[$5], employer=[$6], state=[$7], age=[$8], email=[$9], lastname=[$10], _id=[$11], _index=[$12], _score=[$13], _maxscore=[$14], _sort=[$15], _routing=[$16], _row_number_transpose_=[$17], column_names=[$18], _value_transpose_=[CASE(=($18, 'account_number'), CAST($0):VARCHAR NOT NULL, =($18, 'firstname'), CAST($1):VARCHAR NOT NULL, =($18, 'address'), CAST($2):VARCHAR NOT NULL, =($18, 'balance'), CAST($3):VARCHAR NOT NULL, =($18, 'gender'), CAST($4):VARCHAR NOT NULL, =($18, 'city'), CAST($5):VARCHAR NOT NULL, =($18, 'employer'), CAST($6):VARCHAR NOT NULL, =($18, 'state'), CAST($7):VARCHAR NOT NULL, =($18, 'age'), CAST($8):VARCHAR NOT NULL, =($18, 'email'), CAST($9):VARCHAR NOT NULL, =($18, 'lastname'), CAST($10):VARCHAR NOT NULL, null:NULL)])
LogicalProject(account_number=[$0], firstname=[$1], address=[$2], balance=[$3], gender=[$4], city=[$5], employer=[$6], state=[$7], age=[$8], email=[$9], lastname=[$10], _id=[$11], _index=[$12], _score=[$13], _maxscore=[$14], _sort=[$15], _routing=[$16], _row_number_transpose_=[$17], column_names=[$18], _value_transpose_=[CASE(=($18, 'account_number'), CAST($0):VARCHAR NOT NULL, =($18, 'firstname '), CAST($1):VARCHAR NOT NULL, =($18, 'address '), CAST($2):VARCHAR NOT NULL, =($18, 'balance '), CAST($3):VARCHAR NOT NULL, =($18, 'gender '), CAST($4):VARCHAR NOT NULL, =($18, 'city '), CAST($5):VARCHAR NOT NULL, =($18, 'employer '), CAST($6):VARCHAR NOT NULL, =($18, 'state '), CAST($7):VARCHAR NOT NULL, =($18, 'age '), CAST($8):VARCHAR NOT NULL, =($18, 'email '), CAST($9):VARCHAR NOT NULL, =($18, 'lastname '), CAST($10):VARCHAR NOT NULL, null:NULL)])
LogicalJoin(condition=[true], joinType=[inner])
LogicalProject(account_number=[$0], firstname=[$1], address=[$2], balance=[$3], gender=[$4], city=[$5], employer=[$6], state=[$7], age=[$8], email=[$9], lastname=[$10], _id=[$11], _index=[$12], _score=[$13], _maxscore=[$14], _sort=[$15], _routing=[$16], _row_number_transpose_=[ROW_NUMBER() OVER ()])
LogicalSort(fetch=[5])
CalciteLogicalIndexScan(table=[[OpenSearch, opensearch-sql_test_index_account]])
LogicalValues(tuples=[[{ 'account_number' }, { 'firstname' }, { 'address' }, { 'balance' }, { 'gender' }, { 'city' }, { 'employer' }, { 'state' }, { 'age' }, { 'email' }, { 'lastname' }]])
LogicalValues(tuples=[[{ 'account_number' }, { 'firstname ' }, { 'address ' }, { 'balance ' }, { 'gender ' }, { 'city ' }, { 'employer ' }, { 'state ' }, { 'age ' }, { 'email ' }, { 'lastname ' }]])
physical: |
EnumerableLimit(fetch=[10000])
EnumerableAggregate(group=[{1}], row 1_null=[MAX($0) FILTER $2], row 2_null=[MAX($0) FILTER $3], row 3_null=[MAX($0) FILTER $4], row 4_null=[MAX($0) FILTER $5])
EnumerableCalc(expr#0..12=[{inputs}], expr#13=['account_number'], expr#14=[=($t12, $t13)], expr#15=[CAST($t0):VARCHAR NOT NULL], expr#16=['firstname'], expr#17=[=($t12, $t16)], expr#18=[CAST($t1):VARCHAR NOT NULL], expr#19=['address'], expr#20=[=($t12, $t19)], expr#21=[CAST($t2):VARCHAR NOT NULL], expr#22=['balance'], expr#23=[=($t12, $t22)], expr#24=[CAST($t3):VARCHAR NOT NULL], expr#25=['gender'], expr#26=[=($t12, $t25)], expr#27=[CAST($t4):VARCHAR NOT NULL], expr#28=['city'], expr#29=[=($t12, $t28)], expr#30=[CAST($t5):VARCHAR NOT NULL], expr#31=['employer'], expr#32=[=($t12, $t31)], expr#33=[CAST($t6):VARCHAR NOT NULL], expr#34=['state'], expr#35=[=($t12, $t34)], expr#36=[CAST($t7):VARCHAR NOT NULL], expr#37=['age'], expr#38=[=($t12, $t37)], expr#39=[CAST($t8):VARCHAR NOT NULL], expr#40=['email'], expr#41=[=($t12, $t40)], expr#42=[CAST($t9):VARCHAR NOT NULL], expr#43=['lastname'], expr#44=[=($t12, $t43)], expr#45=[CAST($t10):VARCHAR NOT NULL], expr#46=[null:NULL], expr#47=[CASE($t14, $t15, $t17, $t18, $t20, $t21, $t23, $t24, $t26, $t27, $t29, $t30, $t32, $t33, $t35, $t36, $t38, $t39, $t41, $t42, $t44, $t45, $t46)], expr#48=[CAST($t47):VARCHAR NOT NULL], expr#49=[FLAG(BOTH)], expr#50=[' '], expr#51=[TRIM($t49, $t50, $t12)], expr#52=[1], expr#53=[=($t11, $t52)], expr#54=[2], expr#55=[=($t11, $t54)], expr#56=[3], expr#57=[=($t11, $t56)], expr#58=[4], expr#59=[=($t11, $t58)], _value_transpose_=[$t48], $f20=[$t51], $f21=[$t53], $f22=[$t55], $f23=[$t57], $f24=[$t59])
EnumerableCalc(expr#0..12=[{inputs}], expr#13=['account_number'], expr#14=[=($t12, $t13)], expr#15=[CAST($t0):VARCHAR NOT NULL], expr#16=['firstname '], expr#17=[=($t12, $t16)], expr#18=[CAST($t1):VARCHAR NOT NULL], expr#19=['address '], expr#20=[=($t12, $t19)], expr#21=[CAST($t2):VARCHAR NOT NULL], expr#22=['balance '], expr#23=[=($t12, $t22)], expr#24=[CAST($t3):VARCHAR NOT NULL], expr#25=['gender '], expr#26=[=($t12, $t25)], expr#27=[CAST($t4):VARCHAR NOT NULL], expr#28=['city '], expr#29=[=($t12, $t28)], expr#30=[CAST($t5):VARCHAR NOT NULL], expr#31=['employer '], expr#32=[=($t12, $t31)], expr#33=[CAST($t6):VARCHAR NOT NULL], expr#34=['state '], expr#35=[=($t12, $t34)], expr#36=[CAST($t7):VARCHAR NOT NULL], expr#37=['age '], expr#38=[=($t12, $t37)], expr#39=[CAST($t8):VARCHAR NOT NULL], expr#40=['email '], expr#41=[=($t12, $t40)], expr#42=[CAST($t9):VARCHAR NOT NULL], expr#43=['lastname '], expr#44=[=($t12, $t43)], expr#45=[CAST($t10):VARCHAR NOT NULL], expr#46=[null:NULL], expr#47=[CASE($t14, $t15, $t17, $t18, $t20, $t21, $t23, $t24, $t26, $t27, $t29, $t30, $t32, $t33, $t35, $t36, $t38, $t39, $t41, $t42, $t44, $t45, $t46)], expr#48=[CAST($t47):VARCHAR NOT NULL], expr#49=[FLAG(BOTH)], expr#50=[' '], expr#51=[TRIM($t49, $t50, $t12)], expr#52=[CAST($t51):VARCHAR NOT NULL], expr#53=[1], expr#54=[=($t11, $t53)], expr#55=[2], expr#56=[=($t11, $t55)], expr#57=[3], expr#58=[=($t11, $t57)], expr#59=[4], expr#60=[=($t11, $t59)], _value_transpose_=[$t48], $f20=[$t52], $f21=[$t54], $f22=[$t56], $f23=[$t58], $f24=[$t60])
EnumerableNestedLoopJoin(condition=[true], joinType=[inner])
EnumerableWindow(window#0=[window(rows between UNBOUNDED PRECEDING and CURRENT ROW aggs [ROW_NUMBER()])])
CalciteEnumerableIndexScan(table=[[OpenSearch, opensearch-sql_test_index_account]], PushDownContext=[[PROJECT->[account_number, firstname, address, balance, gender, city, employer, state, age, email, lastname], LIMIT->5], OpenSearchRequestBuilder(sourceBuilder={"from":0,"size":5,"timeout":"1m","_source":{"includes":["account_number","firstname","address","balance","gender","city","employer","state","age","email","lastname"]}}, requestedTotalSize=5, pageSize=null, startFrom=0)])
EnumerableCalc(expr#0=[{inputs}], expr#1=[Sarg['account_number', 'address':CHAR(14), 'age':CHAR(14), 'balance':CHAR(14), 'city':CHAR(14), 'email':CHAR(14), 'employer':CHAR(14), 'firstname':CHAR(14), 'gender':CHAR(14), 'lastname':CHAR(14), 'state':CHAR(14)]:CHAR(14)], expr#2=[SEARCH($t0, $t1)], column_names=[$t0], $condition=[$t2])
EnumerableValues(tuples=[[{ 'account_number' }, { 'firstname' }, { 'address' }, { 'balance' }, { 'gender' }, { 'city' }, { 'employer' }, { 'state' }, { 'age' }, { 'email' }, { 'lastname' }]])
EnumerableCalc(expr#0=[{inputs}], expr#1=[Sarg['account_number', 'address ', 'age ', 'balance ', 'city ', 'email ', 'employer ', 'firstname ', 'gender ', 'lastname ', 'state ']:CHAR(14)], expr#2=[SEARCH($t0, $t1)], column_names=[$t0], $condition=[$t2])
EnumerableValues(tuples=[[{ 'account_number' }, { 'firstname ' }, { 'address ' }, { 'balance ' }, { 'gender ' }, { 'city ' }, { 'employer ' }, { 'state ' }, { 'age ' }, { 'email ' }, { 'lastname ' }]])

Loading
Loading