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

[HUDI-4003] Try to read all the log file to parse schema #5473

Merged
merged 3 commits into from
May 10, 2022
+19 −9
Merged

[HUDI-4003] Try to read all the log file to parse schema #5473

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
8997ecf
[HUDI-4003] Try to read all the log file to parse schema
lanyuanxiaoyao Apr 30, 2022
b4fa0ff
[HUDI-4003] Unify the data file schema scan across both MOR/COW
lanyuanxiaoyao May 5, 2022
842f311
addressing minor feedback
nsivabalan May 10, 2022
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
28 changes: 19 additions & 9 deletions hudi-common/src/main/java/org/apache/hudi/common/table/TableSchemaResolver.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -61,6 +61,7 @@
import java.io.IOException;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.Iterator;
import java.util.List;

import static org.apache.hudi.avro.AvroSchemaUtils.appendFieldsToSchema;
Expand Down Expand Up @@ -98,8 +99,8 @@ private MessageType getTableParquetSchemaFromDataFile() {
// For COW table, the file has data written must be in parquet or orc format currently.
if (instantAndCommitMetadata.isPresent()) {
HoodieCommitMetadata commitMetadata = instantAndCommitMetadata.get().getRight();
String filePath = commitMetadata.getFileIdAndFullPaths(metaClient.getBasePath()).values().stream().findAny().get();
return readSchemaFromBaseFile(filePath);
Iterator<String> filePaths = commitMetadata.getFileIdAndFullPaths(metaClient.getBasePath()).values().iterator();
return fetchSchemaFromFiles(filePaths);
} else {
throw new IllegalArgumentException("Could not find any data file written for commit, "
+ "so could not get schema for table " + metaClient.getBasePath());
Expand All @@ -109,13 +110,8 @@ private MessageType getTableParquetSchemaFromDataFile() {
// Determine the file format based on the file name, and then extract schema from it.
if (instantAndCommitMetadata.isPresent()) {
HoodieCommitMetadata commitMetadata = instantAndCommitMetadata.get().getRight();
String filePath = commitMetadata.getFileIdAndFullPaths(metaClient.getBasePath()).values().stream().findAny().get();
if (filePath.contains(HoodieFileFormat.HOODIE_LOG.getFileExtension())) {
// this is a log file
return readSchemaFromLogFile(new Path(filePath));
} else {
return readSchemaFromBaseFile(filePath);
}
Iterator<String> filePaths = commitMetadata.getFileIdAndFullPaths(metaClient.getBasePath()).values().iterator();
return fetchSchemaFromFiles(filePaths);
} else {
throw new IllegalArgumentException("Could not find any data file written for commit, "
+ "so could not get schema for table " + metaClient.getBasePath());
Expand All @@ -129,6 +125,20 @@ private MessageType getTableParquetSchemaFromDataFile() {
}
}

private MessageType fetchSchemaFromFiles(Iterator<String> filePaths) throws IOException {
MessageType type = null;
while (filePaths.hasNext() && type == null) {
String filePath = filePaths.next();
if (filePath.contains(HoodieFileFormat.HOODIE_LOG.getFileExtension())) {
// this is a log file
type = readSchemaFromLogFile(new Path(filePath));
} else {
type = readSchemaFromBaseFile(filePath);
}
}
return type;
}

private MessageType readSchemaFromBaseFile(String filePath) throws IOException {
if (filePath.contains(HoodieFileFormat.PARQUET.getFileExtension())) {
// this is a parquet file
Expand Down