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

DENG-2598: adding support for select * except #9

Merged
merged 1 commit into from
May 29, 2024
Merged

DENG-2598: adding support for select * except #9

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
26 changes: 26 additions & 0 deletions ...utilities/src/main/java/org/apache/hudi/utilities/transform/SqlQueryBasedTransformer.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,6 +31,8 @@
import org.slf4j.LoggerFactory;

import java.util.UUID;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

import static org.apache.hudi.common.util.ConfigUtils.getStringWithAltKeys;

Expand Down Expand Up @@ -59,6 +61,24 @@ public Dataset<Row> apply(JavaSparkContext jsc, SparkSession sparkSession, Datas
return rowDataset;
}

// Extract except clause into formattedColumns if found
Pattern pattern = Pattern.compile("(?i)(.*\\*) except\\(([^)]*)\\)(.*)");
Matcher matcher = pattern.matcher(transformerSQL);
String[] formattedColumns = {};
boolean dropColumns = false;
if (matcher.find()) {
String columnString = matcher.group(2);
String[] columns = columnString.split(",", 0);
formattedColumns = new String[columns.length];
for (int i = 0; i < columns.length; i++) {
formattedColumns[i] = columns[i].trim();
}
LOG.info("Found 'except' clause in SQL query transform for columns: " + String.join(", ", formattedColumns));
dropColumns = true;
transformerSQL = matcher.group(1) + matcher.group(3);
LOG.info("Generated new SQL query transform: " + transformerSQL);
}

try {
// tmp table name doesn't like dashes
String tmpTable = TMP_TABLE.concat(UUID.randomUUID().toString().replace("-", "_"));
Expand All @@ -68,6 +88,12 @@ public Dataset<Row> apply(JavaSparkContext jsc, SparkSession sparkSession, Datas
LOG.debug("SQL Query for transformation : (" + sqlStr + ")");
Dataset<Row> transformed = sparkSession.sql(sqlStr);
sparkSession.catalog().dropTempView(tmpTable);
if (dropColumns) {
LOG.info("Dropping columns: " + String.join(", ", formattedColumns));
for (String column : formattedColumns) {
transformed = transformed.drop(column);
}
}
return transformed;
} catch (Exception e) {
throw new HoodieTransformExecutionException("Failed to apply sql query based transformer", e);
Expand Down