问题导读 1、 InputForma新AP提供哪两个功能？ 2、InputFormat有哪两个比较重要的方法？ 3、InputSplit分片信息有哪些特点？
/** An {@link InputFormat} for plain text files. Files are broken into lines.
* Either linefeed or carriage-return are used to signal end of line. Keys are
* the position in the file, and values are the line of text.. */
public class TextInputFormat extends FileInputFormat<LongWritable, Text> {
@Override
public RecordReader<LongWritable, Text>
createRecordReader(InputSplit split,
TaskAttemptContext context) {
return new LineRecordReader();
}
@Override
protected boolean isSplitable(JobContext context, Path file) {
CompressionCodec codec =
new CompressionCodecFactory(context.getConfiguration()).getCodec(file);
return codec == null;
}
} 复制代码 一、getSplits方法，这个方法在FileInputFormat类中，它的子类一般只需要实现TextInputFormat中的两个方法而已，getSplits方法代码如下： /**
* Generate the list of files and make them into FileSplits.
*/
public List<InputSplit> getSplits(JobContext job
) throws IOException {
long minSize = Math.max(getFormatMinSplitSize(), getMinSplitSize(job));
long maxSize = getMaxSplitSize(job); //Long.MAX_VALUE
// generate splits
List<InputSplit> splits = new ArrayList<InputSplit>();
List<FileStatus>files = listStatus(job);
for (FileStatus file: files) {
Path path = file.getPath();
FileSystem fs = path.getFileSystem(job.getConfiguration());
long length = file.getLen(); //整个文件的长度
BlockLocation[] blkLocations = fs.getFileBlockLocations(file, 0, length);
if ((length != 0) && isSplitable(job, path)) { //默认是true，但是如果是压缩的，则是false
long blockSize = file.getBlockSize(); //64M，67108864B
long splitSize = computeSplitSize(blockSize, minSize, maxSize); //计算split大小 Math.max(minSize, Math.min(maxSize, blockSize))
long bytesRemaining = length;
while (((double) bytesRemaining)/splitSize > SPLIT_SLOP) {
int blkIndex = getBlockIndex(blkLocations, length-bytesRemaining);
splits.add(new FileSplit(path, length-bytesRemaining, splitSize,
blkLocations[blkIndex].getHosts())); //hosts是主机名,name是IP
bytesRemaining -= splitSize; //剩余块的大小
}
if (bytesRemaining != 0) { //最后一个
splits.add(new FileSplit(path, length-bytesRemaining, bytesRemaining,
blkLocations[blkLocations.length-1].getHosts()));
}
} else if (length != 0) { //isSplitable(job, path)等于false
splits.add(new FileSplit(path, 0, length, blkLocations[0].getHosts()));
} else {
//Create empty hosts array for zero length files
splits.add(new FileSplit(path, 0, length, new String[0]));
}
}
// Save the number of input files in the job-conf
job.getConfiguration().setLong(NUM_INPUT_FILES, files.size());
LOG.debug("Total # of splits: " + splits.size());
return splits;
} 复制代码 protected int getBlockIndex(BlockLocation[] blkLocations,
long offset) {
for (int i = 0 ; i < blkLocations.length; i++) {
// is the offset inside this block?
if ((blkLocations[i].getOffset() <= offset) &&
(offset < blkLocations[i].getOffset() + blkLocations[i].getLength())){
return i;
}
}
BlockLocation last = blkLocations[blkLocations.length -1];
long fileLength = last.getOffset() + last.getLength() -1;
throw new IllegalArgumentException("Offset " + offset +
" is outside of file (0.." +
fileLength + ")");
} 复制代码 二、createRecordReader方法，该方法返回一个RecordReader对象，实现了类似的迭代器功能，将某个InputSplit解析成一个个key/value对。RecordReader应该注意两点： /**
* Read one line from the InputStream into the given Text. A line
* can be terminated by one of the following: '\n' (LF) , '\r' (CR),
* or '\r\n' (CR+LF). EOF also terminates an otherwise unterminated
* line.
*
* @param str the object to store the given line (without newline)
* @param maxLineLength the maximum number of bytes to store into str;
* the rest of the line is silently discarded.
* @param maxBytesToConsume the maximum number of bytes to consume
* in this call. This is only a hint, because if the line cross
* this threshold, we allow it to happen. It can overshoot
* potentially by as much as one buffer length.
*
* @return the number of bytes read including the (longest) newline
* found.
*
* @throws IOException if the underlying stream throws
*/
public int readLine(Text str, int maxLineLength,
int maxBytesToConsume) throws IOException {
/* We're reading data from in, but the head of the stream may be
* already buffered in buffer, so we have several cases:
* 1. No newline characters are in the buffer, so we need to copy
* everything and read another buffer from the stream.
* 2. An unambiguously terminated line is in buffer, so we just
* copy to str.
* 3. Ambiguously terminated line is in buffer, i.e. buffer ends
* in CR. In this case we copy everything up to CR to str, but
* we also need to see what follows CR: if it's LF, then we
* need consume LF as well, so next call to readLine will read
* from after that.
* We use a flag prevCharCR to signal if previous character was CR
* and, if it happens to be at the end of the buffer, delay
* consuming it until we have a chance to look at the char that
* follows.
*/
str.clear();
int txtLength = 0; //tracks str.getLength(), as an optimization
int newlineLength = 0; //length of terminating newline
boolean prevCharCR = false; //true of prev char was CR
long bytesConsumed = 0;
do {
int startPosn = bufferPosn; //starting from where we left off the last time
if (bufferPosn >= bufferLength) {
startPosn = bufferPosn = 0;
if (prevCharCR)
++bytesConsumed; //account for CR from previous read
bufferLength = in.read(buffer); //从输入流中读取一定数量的字节，并将其存储在缓冲区数组 b 中。以整数形式返回实际读取的字节数。
if (bufferLength <= 0) //结束了，没数据了
break; // EOF
}
//'\n'，ASCII码：10，意义：换行NL；；；；'\r' ，ASCII码：13，意义： 回车CR
for (; bufferPosn < bufferLength; ++bufferPosn) { //search for newline
if (buffer[bufferPosn] == LF) { //如果是换行字符\n
newlineLength = (prevCharCR) ? 2 : 1;
++bufferPosn; // at next invocation proceed from following byte，越过换行字符
break;
}
if (prevCharCR) { //CR + notLF, we are at notLF，如果是回车字符\r
newlineLength = 1;
break;
}
prevCharCR = (buffer[bufferPosn] == CR);
}
int readLength = bufferPosn - startPosn;
if (prevCharCR && newlineLength == 0) //表示还没遇到换行，有回车字符，且缓存最后一个是\r
--readLength; //CR at the end of the buffer
bytesConsumed += readLength;
int appendLength = readLength - newlineLength; //newlineLength换行符个数
if (appendLength > maxLineLength - txtLength) {
appendLength = maxLineLength - txtLength;
}
if (appendLength > 0) {
str.append(buffer, startPosn, appendLength); //将数据加入str
txtLength += appendLength;
}
} while (newlineLength == 0 && bytesConsumed < maxBytesToConsume);//循环条件没有换行并且没超过上限
if (bytesConsumed > (long)Integer.MAX_VALUE)
throw new IOException("Too many bytes before newline: " + bytesConsumed);
return (int)bytesConsumed;
} 复制代码 public boolean nextKeyValue() throws IOException {
if (key == null) {
key = new LongWritable();
}
key.set(pos);
if (value == null) {
value = new Text();
}
int newSize = 0;
while (pos < end) {
newSize = in.readLine(value, maxLineLength,
Math.max((int)Math.min(Integer.MAX_VALUE, end-pos),
maxLineLength));
if (newSize == 0) {
break;
}
pos += newSize;
if (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;
}
} 复制代码 
/2 
京ICP备2020039040号
简书网举报电话：021-34700000
提升卡
置顶卡
沉默卡
喧嚣卡
变色卡
千斤顶
显身卡
