zhangyue19921010 commented on a change in pull request #4782:
URL: https://github.com/apache/hudi/pull/4782#discussion_r805105044
##########
File path:
hudi-common/src/main/java/org/apache/hudi/common/table/TableSchemaResolver.java
##########
@@ -422,6 +443,55 @@ public MessageType readSchemaFromBaseFile(Path
parquetFilePath) throws IOExcepti
return fileFooter.getFileMetaData().getSchema();
}
+ /**
+ * Read the parquet schema from a HFile.
+ */
+ public MessageType readSchemaFromHFileBaseFile(Path hFilePath) throws
IOException {
+ LOG.info("Reading schema from " + hFilePath);
+
+ FileSystem fs = metaClient.getRawFs();
+ if (!fs.exists(hFilePath)) {
+ throw new IllegalArgumentException(
+ "Failed to read schema from data file " + hFilePath + ". File does
not exist.");
+ }
+
+ CacheConfig cacheConfig = new CacheConfig(fs.getConf());
+ HoodieHFileReader<IndexedRecord> hFileReader = new
HoodieHFileReader<>(fs.getConf(), hFilePath, cacheConfig);
+
+ return convertAvroSchemaToParquet(hFileReader.getSchema());
+ }
+
+
+ /**
+ * Read the parquet schema from a ORC file.
+ */
+ public MessageType readSchemaFromORCBaseFile(Path orcFilePath) throws
IOException {
Review comment:
Nice idea. Changed!
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
