Skip to content

branch-4.0: [fix](be) Correct Arrow UTF8/String size limit #63137 #63558

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
github-actions wants to merge 1 commit into
base: branch-4.0
Choose a base branch
from
+43 −3
Open

branch-4.0: [fix](be) Correct Arrow UTF8/String size limit #63137 #63558

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
2 changes: 1 addition & 1 deletion be/src/util/arrow/row_batch.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,7 +39,7 @@ class Schema;

namespace doris {

constexpr size_t MAX_ARROW_UTF8 = (1ULL << 21); // 2G
constexpr size_t MAX_ARROW_UTF8 = (1ULL << 31); // 2G

class RowDescriptor;

Expand Down
8 changes: 7 additions & 1 deletion regression-test/data/arrow_flight_sql_p0/test_select.out
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,4 +5,10 @@
-- !arrow_flight_sql_datetime --
333 plsql333 2024-07-21 12:00:00.123456 2024-07-21 12:00:00.0
222 plsql222 2024-07-20 12:00:00.123456 2024-07-20 12:00:00.0
111 plsql111 2024-07-19 12:00:00.123456 2024-07-19 12:00:00.0
111 plsql111 2024-07-19 12:00:00.123456 2024-07-19 12:00:00.0

-- !arrow_flight_sql_jsonb --
1 {"k1":1,"k2":"v2"}
2 [1,2,{"nested":true}]
3 \N

36 changes: 35 additions & 1 deletion regression-test/suites/arrow_flight_sql_p0/test_select.groovy
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,7 +26,7 @@ suite("test_select", "arrow_flight_sql") {
sql """INSERT INTO ${tableName} VALUES(222, "plsql222")"""
sql """INSERT INTO ${tableName} VALUES(333, "plsql333")"""
sql """INSERT INTO ${tableName} VALUES(111, "plsql333")"""

qt_arrow_flight_sql "select sum(id) as a, count(1) as b from ${tableName}"

tableName = "test_select_datetime"
Expand All @@ -40,4 +40,38 @@ suite("test_select", "arrow_flight_sql") {
sql """INSERT INTO ${tableName} VALUES(333, "plsql333","2024-07-21 12:00:00.123456","2024-07-21 12:00:00")"""

qt_arrow_flight_sql_datetime "select * from ${tableName} order by id desc"

tableName = "test_select_jsonb"
sql "DROP TABLE IF EXISTS ${tableName}"
sql """
create table ${tableName} (id int, payload jsonb) DUPLICATE key(`id`) distributed by hash (`id`) buckets 4
properties ("replication_num"="1");
"""
sql """
INSERT INTO ${tableName} VALUES
(1, '{"k1": 1, "k2": "v2"}'),
(2, '[1, 2, {"nested": true}]'),
(3, NULL)
"""

qt_arrow_flight_sql_jsonb "select id, payload from ${tableName} order by id"

def largeJsonValueSize = 2100000
sql """
INSERT INTO ${tableName}
SELECT 4, CAST(CONCAT('{"large":"', REPEAT('x', ${largeJsonValueSize}), '"}') AS JSONB)
"""

// This row exceeds MAX_ARROW_UTF8 and exercises JSONB -> LargeString serialization.
def largeJsonbResult = arrow_flight_sql """
select payload, length(cast(payload as string)) from ${tableName} where id = 4
"""
assertEquals(1, largeJsonbResult.size())
assertEquals(2, largeJsonbResult[0].size())
def expectedLargeJsonbSize = largeJsonValueSize + '{"large":""}'.length()
def largeJsonb = largeJsonbResult[0][0].toString()
assertEquals(expectedLargeJsonbSize, largeJsonb.length())
assertEquals(expectedLargeJsonbSize, (largeJsonbResult[0][1] as Number).intValue())
assertTrue(largeJsonb.startsWith('{"large":"'))
assertTrue(largeJsonb.endsWith('"}'))
}
Loading