This is an automated email from the ASF dual-hosted git repository.
liaoxin pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/doris.git
The following commit(s) were added to refs/heads/master by this push:
new 6801e069751 [fix](broker-load) fix error in broker-load with
read_json_by_line (#41788)
6801e069751 is described below
commit 6801e0697517519ed8fc725657542ba8e141d0bb
Author: Uniqueyou <[email protected]>
AuthorDate: Fri Oct 18 00:00:21 2024 +0800
[fix](broker-load) fix error in broker-load with read_json_by_line (#41788)
---
.../org/apache/doris/load/BrokerFileGroup.java | 19 ++++++-------
.../broker_load/test_s3_load_properties.out | 18 ++++++++++++
.../broker_load/test_s3_load_properties.groovy | 32 ++++++++++++++++++++++
3 files changed, 59 insertions(+), 10 deletions(-)
diff --git
a/fe/fe-core/src/main/java/org/apache/doris/load/BrokerFileGroup.java
b/fe/fe-core/src/main/java/org/apache/doris/load/BrokerFileGroup.java
index 366983d4139..8605dc59bcc 100644
--- a/fe/fe-core/src/main/java/org/apache/doris/load/BrokerFileGroup.java
+++ b/fe/fe-core/src/main/java/org/apache/doris/load/BrokerFileGroup.java
@@ -184,6 +184,7 @@ public class BrokerFileGroup implements Writable {
if (lineDelimiter == null) {
lineDelimiter = "\n";
}
+
enclose = dataDescription.getEnclose();
escape = dataDescription.getEscape();
@@ -226,16 +227,14 @@ public class BrokerFileGroup implements Writable {
srcTableId = srcTable.getId();
isLoadFromTable = true;
}
- if (fileFormat != null && fileFormat.equalsIgnoreCase("json")) {
- stripOuterArray = dataDescription.isStripOuterArray();
- jsonPaths = dataDescription.getJsonPaths();
- jsonRoot = dataDescription.getJsonRoot();
- fuzzyParse = dataDescription.isFuzzyParse();
- // ATTN: for broker load, we only support reading json format data
line by line,
- // so if this is set to false, it must be stream load.
- readJsonByLine = dataDescription.isReadJsonByLine();
- numAsString = dataDescription.isNumAsString();
- }
+ stripOuterArray = dataDescription.isStripOuterArray();
+ jsonPaths = dataDescription.getJsonPaths();
+ jsonRoot = dataDescription.getJsonRoot();
+ fuzzyParse = dataDescription.isFuzzyParse();
+ // ATTN: for broker load, we only support reading json format data
line by line,
+ // so if this is set to false, it must be stream load.
+ readJsonByLine = dataDescription.isReadJsonByLine();
+ numAsString = dataDescription.isNumAsString();
trimDoubleQuotes = dataDescription.getTrimDoubleQuotes();
skipLines = dataDescription.getSkipLines();
}
diff --git
a/regression-test/data/load_p2/broker_load/test_s3_load_properties.out
b/regression-test/data/load_p2/broker_load/test_s3_load_properties.out
index 022c08cf8f3..8608a3107fe 100644
--- a/regression-test/data/load_p2/broker_load/test_s3_load_properties.out
+++ b/regression-test/data/load_p2/broker_load/test_s3_load_properties.out
@@ -380,6 +380,24 @@
-- !select --
280
+-- !select --
+48
+
+-- !select --
+48
+
+-- !select --
+47
+
+-- !select --
+47
+
+-- !select --
+48
+
+-- !select --
+216
+
-- !select --
18
diff --git
a/regression-test/suites/load_p2/broker_load/test_s3_load_properties.groovy
b/regression-test/suites/load_p2/broker_load/test_s3_load_properties.groovy
index fbb0df3b002..59ad8e67dff 100644
--- a/regression-test/suites/load_p2/broker_load/test_s3_load_properties.groovy
+++ b/regression-test/suites/load_p2/broker_load/test_s3_load_properties.groovy
@@ -418,6 +418,38 @@ suite("test_s3_load_properties", "p2") {
"", "", "", "", ""))
}
+ for (String table : basicTables) {
+ attributesList.add(new
LoadAttributes("s3://${s3BucketName}/regression/load/data/basic_data.json",
+ "${table}", "", "", "",
"(k00,k01,k02,k03,k04,k05,k06,k07,k08,k09,k10,k11,k12,k13,k14,k15,k16,k17,k18)",
+ "", "", "", "", "PROPERTIES(\"strip_outer_array\" = \"true\",
\"fuzzy_parse\" = \"true\")"))
+ }
+
+ attributesList.add(new
LoadAttributes("s3://${s3BucketName}/regression/load/data/basic_data.json",
+ "agg_tbl_basic", "", "", "",
"(k00,k01,k02,k03,k04,k05,k06,k07,k08,k09,k10,k11,k12,k13,k14,k15,k16,k17,k18)",
+ "", "", "SET
(k19=to_bitmap(k04),k20=HLL_HASH(k04),k21=TO_QUANTILE_STATE(k04,1.0),kd19=to_bitmap(k05),kd20=HLL_HASH(k05),kd21=TO_QUANTILE_STATE(k05,1.0))",
"", "PROPERTIES(\"strip_outer_array\" = \"true\", \"fuzzy_parse\" =
\"true\")"))
+
+ for (String table : arrayTables) {
+ attributesList.add(new
LoadAttributes("s3://${s3BucketName}/regression/load/data/basic_array_data.json",
+ "${table}", "", "", "",
"(k00,k01,k02,k03,k04,k05,k06,k07,k08,k09,k10,k11,k12,k13,k14,k15,k16,k17)",
+ "", "", "", "", "PROPERTIES(\"strip_outer_array\" = \"true\",
\"fuzzy_parse\" = \"true\")"))
+ }
+
+ for (String table : basicTables) {
+ attributesList.add(new
LoadAttributes("s3://${s3BucketName}/regression/load/data/basic_data_by_line.json",
+ "${table}", "", "", "",
"(k00,k01,k02,k03,k04,k05,k06,k07,k08,k09,k10,k11,k12,k13,k14,k15,k16,k17,k18)",
+ "", "", "", "", "PROPERTIES(\"read_json_by_line\" =
\"true\")"))
+ }
+
+ attributesList.add(new
LoadAttributes("s3://${s3BucketName}/regression/load/data/basic_data_by_line.json",
+ "agg_tbl_basic", "", "", "",
"(k00,k01,k02,k03,k04,k05,k06,k07,k08,k09,k10,k11,k12,k13,k14,k15,k16,k17,k18)",
+ "", "", "SET
(k19=to_bitmap(k04),k20=HLL_HASH(k04),k21=TO_QUANTILE_STATE(k04,1.0),kd19=to_bitmap(k05),kd20=HLL_HASH(k05),kd21=TO_QUANTILE_STATE(k05,1.0))",
"", "PROPERTIES(\"read_json_by_line\" = \"true\")"))
+
+ for (String table : arrayTables) {
+ attributesList.add(new
LoadAttributes("s3://${s3BucketName}/regression/load/data/basic_array_data_by_line.json",
+ "${table}", "", "", "",
"(k00,k01,k02,k03,k04,k05,k06,k07,k08,k09,k10,k11,k12,k13,k14,k15,k16,k17)",
+ "", "", "", "", "PROPERTIES(\"read_json_by_line\" =
\"true\")"))
+ }
+
attributesList.add(new
LoadAttributes("s3://${s3BucketName}/regression/load/data/basic_data.parq",
"agg_tbl_basic", "", "", "FORMAT AS \"PARQUET\"",
"(k00,k01,k02,k03,k04,k05,k06,k07,k08,k09,k10,k11,k12,k13,k14,k15,k16,k17,k18)",
"", "", "SET
(k19=to_bitmap(k04),k20=HLL_HASH(k04),k21=TO_QUANTILE_STATE(k04,1.0),kd19=to_bitmap(k05),kd20=HLL_HASH(k05),kd21=TO_QUANTILE_STATE(k05,1.0))",
"", ""))
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
