Compute multiple intersections and set the difference between two files using hadoop

Question

Sorry to cross-mail this message on the hadoop user mailing list here too, but this is becoming an urgent issue for me.

My problem is this: I have two input files and I want to define

• a) The number of lines that are found only in file 1
• b) The number of lines that are found only in file 2
• c) The number of rows common to both (e.g. regarding row equality)

Example:

File 1:
a
b
c

File 2:
a
d

Desired conclusion for each case:

lines_only_in_1: 2         (b, c)
lines_only_in_2: 1         (d)
lines_in_both:   1         (a)

, : LineRecordReader, , () , (0 1). Mapper , . ,

Map<Line, Iterable<SourceId>>

( SourceId - 0 1).

, . , (a, b, c) ( 1)

"" ( ?). , :

lines_only_in_1   2531
lines_only_in_2   3190
lines_in_both      901

. ( , , ).

, , (, sourceId)//sourceId 0, 1

, . , , " " - - . .

,

1:

public static class SourceCombiner
    extends Reducer<Text, ByteWritable, Text, LongWritable> {

    private long countA = 0;
    private long countB = 0;
    private long countC = 0; // C = lines (c)ommon to both sources

    @Override
    public void reduce(Text key, Iterable<ByteWritable> values, Context context) throws IOException, InterruptedException {
        Set<Byte> fileIds = new HashSet<Byte>();
        for (ByteWritable val : values) {
            byte fileId = val.get();

            fileIds.add(fileId);
        }

        if(fileIds.contains((byte)0)) { ++countA; }
        if(fileIds.contains((byte)1)) { ++countB; }
        if(fileIds.size() >= 2) { ++countC; }
    }

    protected void cleanup(Context context)
            throws java.io.IOException, java.lang.InterruptedException
    {
        context.write(new Text("in_a_distinct_count_total"), new LongWritable(countA));
        context.write(new Text("in_b_distinct_count_total"), new LongWritable(countB));
        context.write(new Text("out_common_distinct_count_total"), new LongWritable(countC));
    }
}

Answer 1

, , , , , .

filemapper. .

    public class FileMapper extends Mapper<LongWritable, Text, Text, Text> {

        static Text fileName;

        @Override
        protected void map(LongWritable key, Text value, Context context)
                throws IOException, InterruptedException {
            context.write(value, fileName);
        }

        @Override
        protected void setup(Context context) throws IOException,
                InterruptedException {

            String name = ((FileSplit) context.getInputSplit()).getPath().getName();
            fileName = new Text(name);
        }
    }

/, ( )

    a File 1
    b File 1
    c File 1

    a File 2
    d File 2

, :

    a File 1,File 2
    b File 1
    c File 1
    d File 2

, :

public class FileReducer extends Reducer<Text, Text, Text, Text> {

    enum Counter {
        LINES_IN_COMMON, LINES_IN_FIRST, LINES_IN_SECOND
    }

    @Override
    protected void reduce(Text key, Iterable<Text> values, Context context)
            throws IOException, InterruptedException {
        HashSet<String> set = new HashSet<String>();
        for (Text t : values) {
            set.add(t.toString());
        }

        // if we have only two files and we have just two records in our hashset
        // the line is contained in both files
        if (set.size() == 2) {
            context.getCounter(Counter.LINES_IN_COMMON).increment(1);
        } else {
            // sorry this is a bit dirty...
            String t = set.iterator().next();
            // determine which file it was by checking for the name:
            if(t.toString().equals("YOUR_FIRST_FILE_NAME")){
                context.getCounter(Counter.LINES_IN_FIRST).increment(1);
            } else {
                context.getCounter(Counter.LINES_IN_SECOND).increment(1);
            }
        }
    }

}

if .

, , . , :

Job job = new Job(new Configuration());
//setup stuff etc omitted..
job.waitForCompletion(true);
// do the same line with the other enums
long linesInCommon = job.getCounters().findCounter(Counter.LINES_IN_COMMON).getValue();

, .. HDFS, .

, .