This is an automated email from the ASF dual-hosted git repository. kxiao pushed a commit to branch branch-2.0 in repository https://gitbox.apache.org/repos/asf/doris.git
commit 9a9e56bd90074a26c30b44444ec44bb332956a70 Author: gnehil <adamlee...@gmail.com> AuthorDate: Tue Sep 5 12:14:07 2023 +0800 [fix](spark load) not setting the file format cause null pointer exception (#16202) --- .../src/main/java/org/apache/doris/load/loadv2/dpp/SparkDpp.java | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fe/spark-dpp/src/main/java/org/apache/doris/load/loadv2/dpp/SparkDpp.java b/fe/spark-dpp/src/main/java/org/apache/doris/load/loadv2/dpp/SparkDpp.java index e6c9bf5528..33ca13cb0e 100644 --- a/fe/spark-dpp/src/main/java/org/apache/doris/load/loadv2/dpp/SparkDpp.java +++ b/fe/spark-dpp/src/main/java/org/apache/doris/load/loadv2/dpp/SparkDpp.java @@ -627,7 +627,7 @@ public final class SparkDpp implements java.io.Serializable { srcColumnsWithColumnsFromPath.addAll(fileGroup.columnsFromPath); } - if (fileGroup.fileFormat.equalsIgnoreCase("parquet")) { + if ("parquet".equalsIgnoreCase(fileGroup.fileFormat)) { // parquet had its own schema, just use it; perhaps we could add some validation in future. Dataset<Row> dataFrame = spark.read().parquet(fileUrl); if (!CollectionUtils.isEmpty(columnValueFromPath)) { @@ -639,7 +639,7 @@ public final class SparkDpp implements java.io.Serializable { return dataFrame; } - if (fileGroup.fileFormat.equalsIgnoreCase("orc")) { + if ("orc".equalsIgnoreCase(fileGroup.fileFormat)) { Dataset<Row> dataFrame = spark.read().orc(fileUrl); if (!CollectionUtils.isEmpty(columnValueFromPath)) { for (int k = 0; k < columnValueFromPath.size(); k++) { --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@doris.apache.org For additional commands, e-mail: commits-h...@doris.apache.org