public boolean nextKeyValue() throws IOException { if (key == null) { key = new LongWritable(); } key.set(pos); if (value == null) { value = new Text(); } int newSize = 0; // We always read one extra line, which lies outside the upper // split limit i.e. (end - 1) while (getFilePosition() <= end || in.needAdditionalRecordAfterSplit()) { if (pos == 0) { newSize = skipUtfByteOrderMark(); } else { newSize = in.readLine(value, maxLineLength, maxBytesToConsume(pos)); pos += newSize; } if ((newSize == 0) || (newSize < maxLineLength)) { break; } // line too long. try again LOG.info("Skipped line of size " + newSize + " at pos " + (pos - newSize)); } if (newSize == 0) { key = null; value = null; return false; } else { return true; } }
private int skipUtfByteOrderMark() throws IOException { // Strip BOM(Byte Order Mark) // Text only support UTF-8, we only need to check UTF-8 BOM // (0xEF,0xBB,0xBF) at the start of the text stream. int newMaxLineLength = (int) Math.min(3L + (long) maxLineLength, Integer.MAX_VALUE); int newSize = in.readLine(value, newMaxLineLength, maxBytesToConsume(pos)); // Even we read 3 extra bytes for the first line, // we won't alter existing behavior (no backwards incompat issue). // Because the newSize is less than maxLineLength and // the number of bytes copied to Text is always no more than newSize. // If the return size from readLine is not less than maxLineLength, // we will discard the current line and read the next line. pos += newSize; int textLength = value.getLength(); byte[] textBytes = value.getBytes(); if ((textLength >= 3) && (textBytes[0] == (byte) 0xEF) && (textBytes[1] == (byte) 0xBB) && (textBytes[2] == (byte) 0xBF)) { // find UTF-8 BOM, strip it. LOG.info("Found UTF-8 BOM and skipped it"); textLength -= 3; newSize -= 3; if (textLength > 0) { // It may work to use the same buffer and not do the copyBytes textBytes = value.copyBytes(); value.set(textBytes, 3, textLength); } else { value.clear(); } } return newSize; }
public void initialize(InputSplit genericSplit, TaskAttemptContext context) throws IOException { FileSplit split = (FileSplit) genericSplit; Configuration job = context.getConfiguration(); this.maxLineLength = job.getInt(MAX_LINE_LENGTH, Integer.MAX_VALUE); start = split.getStart(); end = start + split.getLength(); final Path file = split.getPath(); // open the file and seek to the start of the split final FileSystem fs = file.getFileSystem(job); fileIn = fs.open(file); CompressionCodec codec = new CompressionCodecFactory(job).getCodec(file); if (null != codec) { isCompressedInput = true; decompressor = CodecPool.getDecompressor(codec); if (codec instanceof SplittableCompressionCodec) { final SplitCompressionInputStream cIn = ((SplittableCompressionCodec) codec) .createInputStream( fileIn, decompressor, start, end, SplittableCompressionCodec.READ_MODE.BYBLOCK); in = new CompressedSplitLineReader(cIn, job, this.recordDelimiterBytes); start = cIn.getAdjustedStart(); end = cIn.getAdjustedEnd(); filePosition = cIn; } else { in = new SplitLineReader( codec.createInputStream(fileIn, decompressor), job, this.recordDelimiterBytes); filePosition = fileIn; } } else { fileIn.seek(start); in = new SplitLineReader(fileIn, job, this.recordDelimiterBytes); filePosition = fileIn; } // If this is not the first split, we always throw away first record // because we always (except the last split) read one extra line in // next() method. if (start != 0) { start += in.readLine(new Text(), 0, maxBytesToConsume(start)); } this.pos = start; }