Skip to content
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

Jump to bottom

[Spark Load]fix min_value of GlobalDict will be negative number in spark load #9436

Merged
merged 1 commit into from
May 19, 2022
Merged

[Spark Load]fix min_value of GlobalDict will be negative number in spark load #9436

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
9 changes: 6 additions & 3 deletions fe/spark-dpp/src/main/java/org/apache/doris/load/loadv2/dpp/GlobalDictBuilder.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -309,8 +309,9 @@ private String getSplitBuildGlobalDictSql(Map<String, Long> distinctKeyMap, Stri
sql.append("insert overwrite table ").append(globalDictTableName).append(" partition(dict_column='").append(distinctColumnName).append("') ")
.append(" select dict_key,dict_value from ").append(globalDictTableName).append(" where dict_column='").append(distinctColumnName).append("' ");
for (Map.Entry<String, Long> entry : distinctKeyMap.entrySet()) {
sql.append(" union all select dict_key, (row_number() over(order by dict_key)) ")
.append(String.format(" +(%s) as dict_value from %s", entry.getValue(), entry.getKey()));
sql.append(" union all select dict_key, CAST((row_number() over(order by dict_key)) as BIGINT) ")
.append(String.format("+ CAST(%s as BIGINT) as dict_value from %s",
entry.getValue(), entry.getKey()));
}
return sql.toString();
}
Expand All @@ -334,7 +335,9 @@ private double[] getRandomSplitWeights() {
private String getBuildGlobalDictSql(long maxGlobalDictValue, String distinctColumnName) {
return "insert overwrite table " + globalDictTableName + " partition(dict_column='" + distinctColumnName + "') "
+ " select dict_key,dict_value from " + globalDictTableName + " where dict_column='" + distinctColumnName + "' "
+ " union all select t1.dict_key as dict_key,(row_number() over(order by t1.dict_key)) + (" + maxGlobalDictValue + ") as dict_value from "
+ " union all select t1.dict_key as dict_key,"
+ "CAST((row_number() over(order by t1.dict_key)) as BIGINT) + "
+ "CAST(" + maxGlobalDictValue + " as BIGINT) as dict_value from "
+ "(select dict_key from " + distinctKeyTableName + " where dict_column='" + distinctColumnName + "' and dict_key is not null)t1 left join "
+ " (select dict_key,dict_value from " + globalDictTableName + " where dict_column='" + distinctColumnName + "' )t2 " +
"on t1.dict_key = t2.dict_key where t2.dict_value is null";
Expand Down