Shulou(Shulou.com)06/03 Report--

Now there is a batch of data:

01 | | zs | | 1802 | | ls | | 1903 | | jj | | 10

The delimiter for each row of data is | |, which is a multi-byte delimiter. The default hive only supports a single-byte delimiter. When the data above is | | multibyte, it is not supported.

Solution:

  method01: use RegexSerDe to extract fields through regular expressions

# create table statement create table t_bi_reg (id string,name string,age string) row format serde 'org.apache.hadoop.hive.serde2.RegexSerDe' with serdeproperties (' input.regex'=' ((.\ *)\\ |\ | (.\ *)\ |\ | (.\ *))' 'output.format.string'='%1$ s% 2$ s% 3s') # input.regex: specify the rule of sharding # output.format.string: fields output after sharding # load data load data local inpath'/ Hadoop/data/1.txt' into table t_bi_reg# query select * from t_bi_reg

  method2: modify the source code:

The principle of   is to replace the "multi-byte delimiter" in the data with the hive default delimiter (ctrl+A, that is,\ 001) or the alternative single-character delimiter when inputformat reads rows, so that hive can extract fields according to the default single-byte delimiter during serde operation.

Code

Com.zy.hive.delimit2.BiDelimiterInputFormat:

Package com.zy.hive.delimit2;import java.io.IOException;import org.apache.hadoop.io.LongWritable;import org.apache.hadoop.io.Text;import org.apache.hadoop.mapred.FileSplit;import org.apache.hadoop.mapred.InputSplit;import org.apache.hadoop.mapred.JobConf;import org.apache.hadoop.mapred.RecordReader;import org.apache.hadoop.mapred.Reporter;import org.apache.hadoop.mapred.TextInputFormat Public class BiDelimiterInputFormat extends TextInputFormat {@ Overridepublic RecordReader getRecordReader (InputSplit genericSplit,JobConf job, Reporter reporter) throws IOException {reporter.setStatus (genericSplit.toString ()); BiRecordReader reader = new BiRecordReader (job, (FileSplit) genericSplit); / / MyRecordReader reader = new MyRecordReader (job, (FileSplit) genericSplit); return reader;}}

Com.zy.hive.delimit2.BiRecordReader

Package com.zy.hive.delimit2;import java.io.IOException;import java.io.InputStream;import org.apache.commons.logging.Log;import org.apache.commons.logging.LogFactory;import org.apache.hadoop.conf.Configuration;import org.apache.hadoop.fs.FSDataInputStream;import org.apache.hadoop.fs.FileSystem;import org.apache.hadoop.fs.Path;import org.apache.hadoop.fs.Seekable;import org.apache.hadoop.io.LongWritable;import org.apache.hadoop.io.Text Import org.apache.hadoop.io.compress.CodecPool;import org.apache.hadoop.io.compress.CompressionCodec;import org.apache.hadoop.io.compress.CompressionCodecFactory;import org.apache.hadoop.io.compress.Decompressor;import org.apache.hadoop.io.compress.SplitCompressionInputStream;import org.apache.hadoop.io.compress.SplittableCompressionCodec;import org.apache.hadoop.mapred.FileSplit;import org.apache.hadoop.mapred.LineRecordReader;import org.apache.hadoop.mapred.RecordReader Public class BiRecordReader implements RecordReader {private static final Log LOG = LogFactory.getLog (LineRecordReader.class.getName ()); private CompressionCodecFactory compressionCodecs = null;private long start;private long pos;private long end;private LineReader in;int maxLineLength;private Seekable filePosition;private CompressionCodec codec;private Decompressor decompressor;/*** A class that provides a line reader from an input stream.* @ deprecated Use {@ link org.apache.hadoop.util.LineReader} instead.*/@Deprecatedpublic static class LineReader extends org.apache.hadoop.util.LineReader {LineReader (InputStream in) {super (in) } LineReader (InputStream in, int bufferSize) {super (in, bufferSize);} public LineReader (InputStream in, Configuration conf) throws IOException {Stay hungry Stay foolish-- http://blog.csdn.net/zhongqi2513super(in, conf);}} public BiRecordReader (Configuration job, FileSplit split) throws IOException {this.maxLineLength = job.getInt ("mapred.linerecordreader.maxlength", Integer.MAX_VALUE); start = split.getStart (); end = start + split.getLength (); final Path file = split.getPath (); compressionCodecs = new CompressionCodecFactory (job) Codec = compressionCodecs.getCodec (file); / / open the file and seek to the start of the splitFileSystem fs = file.getFileSystem (job); FSDataInputStream fileIn = fs.open (split.getPath ()); if (isCompressedInput ()) {decompressor = CodecPool.getDecompressor (codec); if (codec instanceof SplittableCompressionCodec) {final SplitCompressionInputStream cIn = ((SplittableCompressionCodec) codec). CreateInputStream (fileIn, decompressor, start, end,SplittableCompressionCodec.READ_MODE.BYBLOCK); in = new LineReader (cIn, job); start = cIn.getAdjustedStart (); end = cIn.getAdjustedEnd (); filePosition = cIn / / take pos from compressed stream} else {in = new LineReader (codec.createInputStream (fileIn,decompressor), job); filePosition = fileIn;}} else {fileIn.seek (start); in = new LineReader (fileIn, job); 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 Stay hungry Stay foolish-- http://blog.csdn.net/zhongqi2513}private boolean isCompressedInput () {return (codec! = null);} private int maxBytesToConsume (long pos) {return isCompressedInput ()? Integer.MAX_VALUE: (int) Math.min (Integer.MAX_VALUE, end-pos);} private long getFilePosition () throws IOException {long retVal;if (isCompressedInput () & & null! = filePosition) {retVal = filePosition.getPos ();} else {retVal = pos;} return retVal;} public BiRecordReader (InputStream in, long offset, long endOffset,int maxLineLength) {this.maxLineLength = maxLineLength;this.in = new LineReader (in); this.start = offset;this.pos = offset;this.end = endOffset;this.filePosition = null } public BiRecordReader (InputStream in, long offset, long endOffset,Configuration job) throws IOException {this.maxLineLength = job.getInt ("mapred.linerecordreader.maxlength", Integer.MAX_VALUE); this.in = new LineReader (in, job); this.start = offset;this.pos = offset;this.end = endOffset;this.filePosition = null;} public LongWritable createKey () {return new LongWritable (); Stay hungry Stay foolish-- http://blog.csdn.net/zhongqi2513}public Text createValue () {return new Text ();} / * * Read a line. * / public synchronized boolean next (LongWritable key, Text value) throws IOException {/ / We always read one extra line, which lies outside the upper// split limit i.e. (end-1) while (getFilePosition ()

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.