public Path getPath() { return footer.getFile(); } }
@Override public Map<Path, Footer> call() throws Exception { ParquetMetadata mergedMetadata = readSummaryMetadata(configuration, path, skipRowGroups); if (mergedMetadata != null) { final List<Footer> footers; if (skipRowGroups) { footers = new ArrayList<Footer>(); for (FileStatus f : partFiles) { footers.add(new Footer(f.getPath(), mergedMetadata)); } } else { footers = footersFromSummaryFile(path, mergedMetadata); } Map<Path, Footer> map = new HashMap<Path, Footer>(); for (Footer footer : footers) { // the folder may have been moved footer = new Footer(new Path(path, footer.getFile().getName()), footer.getParquetMetadata()); map.put(footer.getFile(), footer); } return map; } else { return Collections.emptyMap(); } } });
static ParquetMetadata mergeFooters(Path root, List<Footer> footers) { String rootPath = root.toUri().getPath(); GlobalMetaData fileMetaData = null; List<BlockMetaData> blocks = new ArrayList<BlockMetaData>(); for (Footer footer : footers) { String footerPath = footer.getFile().toUri().getPath(); if (!footerPath.startsWith(rootPath)) { throw new ParquetEncodingException(footerPath + " invalid: all the files must be contained in the root " + root); } footerPath = footerPath.substring(rootPath.length()); while (footerPath.startsWith("/")) { footerPath = footerPath.substring(1); } fileMetaData = mergeInto(footer.getParquetMetadata().getFileMetaData(), fileMetaData); for (BlockMetaData block : footer.getParquetMetadata().getBlocks()) { block.setPath(footerPath); blocks.add(block); } } return new ParquetMetadata(fileMetaData.merge(), blocks); }
public FootersCacheValue(FileStatusWrapper status, Footer footer) { this.modificationTime = status.getModificationTime(); this.footer = new Footer(footer.getFile(), footer.getParquetMetadata()); }
private static ParquetMetadata mergeFooters(Path root, List<Footer> footers) { String rootPath = root.toString(); GlobalMetaData fileMetaData = null; List<BlockMetaData> blocks = new ArrayList<BlockMetaData>(); for (Footer footer : footers) { String path = footer.getFile().toString(); if (!path.startsWith(rootPath)) { throw new ParquetEncodingException(path + " invalid: all the files must be contained in the root " + root); } path = path.substring(rootPath.length()); while (path.startsWith("/")) { path = path.substring(1); } fileMetaData = mergeInto(footer.getParquetMetadata().getFileMetaData(), fileMetaData); for (BlockMetaData block : footer.getParquetMetadata().getBlocks()) { block.setPath(path); blocks.add(block); } } return new ParquetMetadata(fileMetaData.merge(), blocks); }
FileStatusWrapper fileStatus = missingStatusesMap.get(newFooter.getFile()); footersCache.put(fileStatus, new FootersCacheValue(fileStatus, newFooter));
Path path = footer.getFile(); FileStatus status = pathMap.get(path); if (status == null) {
@Override public void execute(CommandLine options) throws Exception { super.execute(options); String[] args = options.getArgs(); String input = args[0]; Configuration conf = new Configuration(); Path inputPath = new Path(input); FileStatus inputFileStatus = inputPath.getFileSystem(conf).getFileStatus(inputPath); List<Footer> footers = ParquetFileReader.readFooters(conf, inputFileStatus, false); PrettyPrintWriter out = PrettyPrintWriter.stdoutPrettyPrinter() .withAutoColumn() .withWhitespaceHandler(WhiteSpaceHandler.COLLAPSE_WHITESPACE) .withColumnPadding(1) .build(); for(Footer f: footers) { out.format("file: %s%n" , f.getFile()); MetadataUtils.showDetails(out, f.getParquetMetadata()); out.flushColumns(); } } }
final Path file = footer.getFile(); LOG.debug(file); FileSystem fs = file.getFileSystem(configuration);
private void initReader() throws IOException { if (reader != null) { reader.close(); reader = null; } if (footersIterator.hasNext()) { Footer footer = footersIterator.next(); reader = new InternalParquetRecordReader<T>(readSupport, filter); reader.initialize( readContext.getRequestedSchema(), globalMetaData.getSchema(), footer.getParquetMetadata().getFileMetaData().getKeyValueMetaData(), readContext.getReadSupportMetadata(), footer.getFile(), footer.getParquetMetadata().getBlocks(), conf); } }
private void initReader() throws IOException { if (reader != null) { reader.close(); reader = null; } if (footersIterator.hasNext()) { Footer footer = footersIterator.next(); List<BlockMetaData> blocks = footer.getParquetMetadata().getBlocks(); MessageType fileSchema = footer.getParquetMetadata().getFileMetaData().getSchema(); List<BlockMetaData> filteredBlocks = RowGroupFilter.filterRowGroups( filter, blocks, fileSchema); reader = new InternalParquetRecordReader<T>(readSupport, filter); reader.initialize(fileSchema, footer.getParquetMetadata().getFileMetaData().getKeyValueMetaData(), footer.getFile(), filteredBlocks, conf); } }