deniskuzZ commented on code in PR #4520: URL: https://github.com/apache/hive/pull/4520#discussion_r1305472713
########## ql/src/java/org/apache/hadoop/hive/ql/plan/ConditionalResolverMergeFiles.java: ########## @@ -380,32 +432,32 @@ public int getNumFiles() { private AverageSize getAverageSize(FileSystem inpFs, Path dirPath) { AverageSize error = new AverageSize(-1, -1); try { - FileStatus[] fStats = inpFs.listStatus(dirPath); - - long totalSz = 0; - int numFiles = 0; - for (FileStatus fStat : fStats) { - Utilities.FILE_OP_LOGGER.debug("Resolver looking at " + fStat.getPath()); - if (fStat.isDir()) { - AverageSize avgSzDir = getAverageSize(inpFs, fStat.getPath()); - if (avgSzDir.getTotalSize() < 0) { - return error; - } - totalSz += avgSzDir.getTotalSize(); - numFiles += avgSzDir.getNumFiles(); - } - else { - totalSz += fStat.getLen(); - numFiles++; - } - } - - return new AverageSize(totalSz, numFiles); + return getAverageSize(getFileStatus(inpFs, dirPath)); } catch (IOException e) { return error; } } + private List<FileStatus> getFileStatus(FileSystem inputFs, Path path) throws IOException { + FileStatus[] fStats = inputFs.listStatus(path); + List<FileStatus> result = new ArrayList<>(); + for (FileStatus stat : fStats) { + if (stat.isDirectory()) { + result.addAll(getFileStatus(inputFs, stat.getPath())); + } else { + result.add(stat); + } + } + return result; + } + + private AverageSize getAverageSize(List<FileStatus> fileStatusList) { + long totalSize = fileStatusList.stream().filter(FileStatus::isFile) + .mapToLong(FileStatus::getLen).sum(); + int numOfFiles = fileStatusList.size(); Review Comment: that is not accurate as above you have a filter(FileStatus::isFile). do we need this filter? ```` LongSummaryStatistics stats = fileStatusList.stream().filter(FileStatus::isFile) .mapToLong(FileStatus::getLen).summaryStatistics(); return new AverageSize(stats.getSum(), stats.getCount()); ```` -- 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: gitbox-unsubscr...@hive.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: gitbox-unsubscr...@hive.apache.org For additional commands, e-mail: gitbox-h...@hive.apache.org