wgtmac commented on code in PR #1026: URL: https://github.com/apache/parquet-mr/pull/1026#discussion_r1128833713
########## parquet-hadoop/src/main/java/org/apache/parquet/hadoop/rewrite/ParquetRewriter.java: ########## @@ -183,12 +189,69 @@ public ParquetRewriter(TransParquetFileReader reader, } } + // Open all input files to validate their schemas are compatible to merge + private void openInputFiles(List<Path> inputFiles, Configuration conf) { + Preconditions.checkArgument(inputFiles != null && !inputFiles.isEmpty(), "No input files"); + + for (Path inputFile : inputFiles) { + try { + TransParquetFileReader reader = new TransParquetFileReader( + HadoopInputFile.fromPath(inputFile, conf), HadoopReadOptions.builder(conf).build()); + MessageType inputFileSchema = reader.getFooter().getFileMetaData().getSchema(); + if (this.schema == null) { + this.schema = inputFileSchema; + } else { + // Now we enforce equality of schemas from input files for simplicity. + if (!this.schema.equals(inputFileSchema)) { + LOG.error("Input files have different schemas, expect: {}, input: {}, current file: {}", + this.schema, inputFileSchema, inputFile); + throw new InvalidSchemaException("Input files have different schemas, current file: " + inputFile); + } + } + this.allOriginalCreatedBys.add(reader.getFooter().getFileMetaData().getCreatedBy()); + this.inputFiles.add(reader); + } catch (IOException e) { + throw new IllegalArgumentException("Failed to open input file: " + inputFile, e); Review Comment: That sounds reasonable. Would you like to create a PR with your proposed change? @vectorijk -- 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: dev-unsubscr...@parquet.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org