public void map(LongWritable key, Text value, Context context)
     throws IOException, InterruptedException {
   String cur_file =
       ((FileSplit) context.getInputSplit()).getPath().getParent().getParent().getName();
   String train_file = context.getConfiguration().get("train_file");
   if (cur_file.equals(train_file)) {
     StringTokenizer st = new StringTokenizer(value.toString());
     String word = st.nextToken();
     String f_id = st.nextToken();
     myKey.set(word);
     myVal.set(f_id);
     context.write(myKey, myVal);
   } else {
     StringTokenizer st = new StringTokenizer(value.toString());
     String word = st.nextToken();
     String f_id = st.nextToken();
     StringBuilder builder = new StringBuilder(dlt);
     while (st.hasMoreTokens()) {
       String filename = st.nextToken();
       String tf_idf = st.nextToken();
       builder.append(filename);
       builder.append(dlt);
       builder.append(tf_idf);
       builder.append("\t");
     }
     myKey.set(word);
     myVal.set(builder.toString());
     context.write(myKey, myVal);
   }
 }
 public String toString() {
   StringBuilder result = new StringBuilder();
   result.append(offset);
   result.append(',');
   result.append(length);
   for (String h : hosts) {
     result.append(',');
     result.append(h);
   }
   return result.toString();
 }
示例#3
0
  public void testInputFormat() {

    try {
      JobConf conf = new JobConf();
      String TMP_DIR = System.getProperty("test.build.data", "/tmp");
      Path filename = new Path("file:///" + TMP_DIR + "/tmpSeqFile");
      SequenceFile.Writer sfw =
          SequenceFile.createWriter(
              FileSystem.getLocal(conf),
              conf,
              filename,
              ChukwaArchiveKey.class,
              ChunkImpl.class,
              SequenceFile.CompressionType.NONE,
              Reporter.NULL);

      StringBuilder buf = new StringBuilder();
      int offsets[] = new int[lines.length];
      for (int i = 0; i < lines.length; ++i) {
        buf.append(lines[i]);
        buf.append("\n");
        offsets[i] = buf.length() - 1;
      }
      ChukwaArchiveKey key = new ChukwaArchiveKey(0, "datatype", "sname", 0);
      ChunkImpl val = new ChunkImpl("datatype", "sname", 0, buf.toString().getBytes(), null);
      val.setRecordOffsets(offsets);
      sfw.append(key, val);
      sfw.append(key, val); // write it twice
      sfw.close();

      long len = FileSystem.getLocal(conf).getFileStatus(filename).getLen();
      InputSplit split = new FileSplit(filename, 0, len, (String[]) null);
      ChukwaInputFormat in = new ChukwaInputFormat();
      RecordReader<LongWritable, Text> r = in.getRecordReader(split, conf, Reporter.NULL);

      LongWritable l = r.createKey();
      Text line = r.createValue();
      for (int i = 0; i < lines.length * 2; ++i) {
        boolean succeeded = r.next(l, line);
        assertTrue(succeeded);
        assertEquals(i, l.get());
        assertEquals(lines[i % lines.length], line.toString());
        System.out.println("read line: " + l.get() + " " + line);
      }
      boolean succeeded = r.next(l, line);
      assertFalse(succeeded);

    } catch (IOException e) {
      e.printStackTrace();
      fail("IO exception " + e);
    }
  }
示例#4
0
 public void map(
     Object key, Text value, OutputCollector<IntWritable, Text> output, Reporter reporter)
     throws IOException {
   // id color
   // id color 1/0 "COLOR"
   String[] tokens = value.toString().split("\\s+");
   IntWritable SourceId = new IntWritable(Integer.parseInt(tokens[0]));
   StringBuilder sb = new StringBuilder();
   for (int i = 1; i < tokens.length; i++) {
     if (sb.length() != 0) sb.append(" ");
     sb.append(tokens[i]);
   }
   output.collect(SourceId, new Text(sb.toString()));
 }
示例#5
0
    public void map(
        Object key, Text value, OutputCollector<IntWritable, Text> output, Reporter reporter)
        throws IOException {

      // vid neighbors_num n1 n2 ...
      // vid color 1/0 "COLOR"
      String str = value.toString();
      if (str.endsWith(COLOR)) {
        // color table
        String[] tokens = str.substring(0, str.length() - 5).split("\\s+");
        int change = Integer.parseInt(tokens[2]);
        if (change == 1) {
          IntWritable SourceId = new IntWritable(Integer.parseInt(tokens[0]));
          StringBuilder sb = new StringBuilder();
          sb.append(tokens[1]);
          sb.append(" ");
          sb.append(tokens[2]);
          sb.append(COLOR);
          output.collect(SourceId, new Text(sb.toString()));
        }
      } else {
        // edge table
        String[] tokens = value.toString().split("\\s+");
        IntWritable SourceId = new IntWritable(Integer.parseInt(tokens[0]));
        StringBuilder sb = new StringBuilder();
        for (int i = 1; i < tokens.length; i++) {
          if (sb.length() != 0) sb.append(" ");
          sb.append(tokens[i]);
        }
        output.collect(SourceId, new Text(sb.toString()));
      }
    }
示例#6
0
 public String toString() {
   StringBuilder buffer = new StringBuilder();
   buffer.append(methodName);
   buffer.append("(");
   for (int i = 0; i < parameters.length; i++) {
     if (i != 0) buffer.append(", ");
     buffer.append(parameters[i]);
   }
   buffer.append(")");
   buffer.append(", rpc version=" + rpcVersion);
   buffer.append(", client version=" + clientVersion);
   buffer.append(", methodsFingerPrint=" + clientMethodsHash);
   return buffer.toString();
 }
示例#7
0
  /**
   * Make a path relative with respect to a root path. absPath is always assumed to descend from
   * root. Otherwise returned path is null.
   */
  static String makeRelative(Path root, Path absPath) {
    if (!absPath.isAbsolute()) {
      throw new IllegalArgumentException("!absPath.isAbsolute(), absPath=" + absPath);
    }
    String p = absPath.toUri().getPath();

    StringTokenizer pathTokens = new StringTokenizer(p, "/");
    for (StringTokenizer rootTokens = new StringTokenizer(root.toUri().getPath(), "/");
        rootTokens.hasMoreTokens(); ) {
      if (!rootTokens.nextToken().equals(pathTokens.nextToken())) {
        return null;
      }
    }
    StringBuilder sb = new StringBuilder();
    for (; pathTokens.hasMoreTokens(); ) {
      sb.append(pathTokens.nextToken());
      if (pathTokens.hasMoreTokens()) {
        sb.append(Path.SEPARATOR);
      }
    }
    return sb.length() == 0 ? "." : sb.toString();
  }
示例#8
0
  public static String readHDFSFile(String path, Configuration conf) throws IOException {
    Path pt = new Path(path);
    FileSystem fs = FileSystem.get(pt.toUri(), conf);
    FSDataInputStream file = fs.open(pt);
    BufferedReader buffIn = new BufferedReader(new InputStreamReader(file));

    StringBuilder everything = new StringBuilder();
    String line;
    while ((line = buffIn.readLine()) != null) {
      everything.append(line);
      everything.append("\n");
    }
    return everything.toString();
  }
    public void reduce(Text key, Iterable<Text> values, Context context)
        throws IOException, InterruptedException {

      String[] pair = new String[2];
      int count = 0;
      for (Text txt : values) {
        pair[count] = txt.toString();
        count++;
      }

      // word exists in training
      if (count == 2) {
        StringTokenizer st_one, st_two;
        if (pair[0].contains(dlt)) {
          st_one = new StringTokenizer(pair[1]);
          st_two = new StringTokenizer(pair[0]);
        } else {
          st_one = new StringTokenizer(pair[0]);
          st_two = new StringTokenizer(pair[1]);
        }

        // outputting the data
        String f_id = st_one.nextToken();

        StringBuilder builder = new StringBuilder(dlt);
        builder.append(f_id);
        builder.append(dlt);
        while (st_two.hasMoreTokens()) {
          String filename = st_two.nextToken();
          String tf_idf = st_two.nextToken();
          builder.append(filename);
          builder.append(dlt);
          builder.append(tf_idf);
          builder.append("\t");
        }
        myVal.set(builder.toString());
        context.write(key, myVal);
      }
    }
    public void map(Text key, Text value, Context context)
        throws InterruptedException, IOException {

      String filename = key.toString();
      String json = value.toString();

      // Make sure the input is valid
      if (!(filename.isEmpty() || json.isEmpty())) {

        // Change the json-type feature to Mat-type feature
        Mat descriptor = json2mat(json);
        if (descriptor != null) {
          // Read the query feature from the cache in Hadoop
          Mat query_features;
          String pathStr = context.getConfiguration().get("featureFilePath");
          FileSystem fs = FileSystem.get(context.getConfiguration());
          FSDataInputStream fsDataInputStream = fs.open(new Path(pathStr));
          StringBuilder sb = new StringBuilder();

          // Use a buffer to read the query_feature
          int remain = fsDataInputStream.available();
          while (remain > 0) {
            int read;
            byte[] buf = new byte[BUF_SIZE];
            read = fsDataInputStream.read(buf, fsDataInputStream.available() - remain, BUF_SIZE);
            sb.append(new String(buf, 0, read, StandardCharsets.UTF_8));
            remain = remain - read;
            System.out.println("remain:" + remain + "\tread:" + read + "\tsb.size:" + sb.length());
          }

          // Read the query_feature line by line
          //                    Scanner sc = new Scanner(fsDataInputStream, "UTF-8");
          //                    StringBuilder sb = new StringBuilder();
          //                    while (sc.hasNextLine()) {
          //                        sb.append(sc.nextLine());
          //                    }
          //                    String query_json = sb.toString();
          //                    String query_json = new String(buf, StandardCharsets.UTF_8);

          String query_json = sb.toString();
          fsDataInputStream.close();
          query_features = json2mat(query_json);

          // Get the similarity of the current database image against the query image
          DescriptorMatcher matcher = DescriptorMatcher.create(DescriptorMatcher.FLANNBASED);
          MatOfDMatch matches = new MatOfDMatch();

          // Ensure the two features have same length of cols (the feature extracted are all 128
          // cols(at least in this case))
          if (query_features.cols() == descriptor.cols()) {

            matcher.match(query_features, descriptor, matches);
            DMatch[] dMatches = matches.toArray();

            // Calculate the max/min distances
            //                    double max_dist = Double.MAX_VALUE;
            //                    double min_dist = Double.MIN_VALUE;
            double max_dist = 0;
            double min_dist = 100;
            for (int i = 0; i < dMatches.length; i++) {
              double dist = dMatches[i].distance;
              if (min_dist > dist) min_dist = dist;
              if (max_dist < dist) max_dist = dist;
            }
            // Only distances ≤ threshold are good matches
            double threshold = max_dist * THRESHOLD_FACTOR;
            //                    double threshold = min_dist * 2;
            LinkedList<DMatch> goodMatches = new LinkedList<DMatch>();

            for (int i = 0; i < dMatches.length; i++) {
              if (dMatches[i].distance <= threshold) {
                goodMatches.addLast(dMatches[i]);
              }
            }

            // Get the ratio of good_matches to all_matches
            double ratio = (double) goodMatches.size() / (double) dMatches.length;

            System.out.println("*** current_record_filename:" + filename + " ***");
            System.out.println("feature:" + descriptor + "\nquery_feature:" + query_features);
            System.out.println(
                "min_dist of keypoints:" + min_dist + "  max_dist of keypoints:" + max_dist);
            System.out.println(
                "total_matches:" + dMatches.length + "\tgood_matches:" + goodMatches.size());
            //                    System.out.println("type:" + descriptor.type() + " channels:" +
            // descriptor.channels() + " rows:" + descriptor.rows() + " cols:" + descriptor.cols());
            //                    System.out.println("qtype:" + query_features.type() + "
            // qchannels:" + query_features.channels() + " qrows:" + query_features.rows() + "
            // qcols:" + query_features.cols());
            System.out.println();

            if (ratio > PERCENTAGE_THRESHOLD) {
              // Key:1        Value:filename|ratio
              context.write(ONE, new Text(filename + "|" + ratio));
              //                        context.write(ONE, new Text(filename + "|" +
              // String.valueOf(goodMatches.size())));
            }
          } else {
            System.out.println("The size of the features are not equal");
          }
        } else {
          // a null pointer, do nothing
          System.out.println("A broken/null feature:" + filename);
          System.out.println();
        }
      }
    }