Examples of UTF8

com.datasalt.pangool.io.Utf8
Main String type for Pangool. Natively supported.
net.nutch.io.UTF8
A WritableComparable for strings that uses the UTF8 encoding.
Also includes utilities for efficiently reading and writing UTF-8. @author Doug Cutting
org.apache.avro.util.Utf8
A Utf8 string. Unlike {@link String}, instances are mutable. This is more efficient than {@link String} when reading or writing a sequence of values,as a single instance may be reused.
org.apache.hadoop.io.UTF8
A WritableComparable for strings that uses the UTF8 encoding.
Also includes utilities for efficiently reading and writing UTF-8. @deprecated replaced by Text
org.apache.harmony.archive.internal.pack200.ConstantPoolEntry.UTF8
TODO Comment -- quite a lot can be nicked from Codec, since this was created from it @author Alex Blewitt
org.apache.nutch.io.UTF8
A WritableComparable for strings that uses the UTF8 encoding.
Also includes utilities for efficiently reading and writing UTF-8. @author Doug Cutting

Examples of com.datasalt.pangool.io.Utf8

    }
  }
  
  protected void readUtf8(DataInputStream input,ITuple tuple,int index) throws IOException {
    //this method is safe because tuple is internal, the tuple is not the final one
    Utf8 t = (Utf8)tuple.get(index); 
    if (t == null){
      t = new Utf8();
      tuple.set(index,t);
    }
    t.readFields(input);
  }

View Full Code Here

Examples of net.nutch.io.UTF8

            LOG.fine(getName() + " got value #" + id);


          Call call = (Call)calls.remove(new Integer(id));
          boolean isError = in.readBoolean();     // read if error
          if (isError) {
            UTF8 utf8 = new UTF8();
            utf8.readFields(in);                  // read error string
            call.error = utf8.toString();
            call.value = null;
          } else {
            Writable value = makeValue();
            value.readFields(in);                 // read value
            call.value = value;

View Full Code Here

Examples of org.apache.avro.util.Utf8

      // now add the metadata
      Iterator<String> keysIter = metadata.keySet().iterator();
      while (keysIter.hasNext()) {
          String keymd = keysIter.next();
          String valuemd = metadata.get(keymd);
          row.putToMetadata(new Utf8(keymd), ByteBuffer.wrap(valuemd.getBytes()));
      }


      if (customScore != -1)
        row.setScore(customScore);
      else

View Full Code Here

Examples of org.apache.avro.util.Utf8

  public NutchDocument filter(NutchDocument doc, String url, WebPage page)
      throws IndexingException {


    // check if LANGUAGE found, possibly put there by HTMLLanguageParser
    String lang = null;
    ByteBuffer blang = page.getFromMetadata(new Utf8(Metadata.LANGUAGE));
    if (blang != null) {
      lang = Bytes.toString(blang.array());
    }


    if (lang == null || lang.length() == 0) {

View Full Code Here

Examples of org.apache.avro.util.Utf8


    if (page.getInlinks() != null) {
      page.getInlinks().clear();
    }
    for (ScoreDatum inlink : inlinkedScoreData) {
      page.putToInlinks(new Utf8(inlink.getUrl()), new Utf8(inlink.getAnchor()));
    }


    try {
      scoringFilters.updateScore(url, page, inlinkedScoreData);
    } catch (ScoringFilterException e) {
      LOG.warn("Scoring filters failed with exception " +
                StringUtils.stringifyException(e));
    }


    // clear markers
    // But only delete when they exist. This is much faster for the underlying
    // store. The markers are on the input anyway.
    if (page.getFromMetadata(FetcherJob.REDIRECT_DISCOVERED) != null) {
      page.removeFromMetadata(FetcherJob.REDIRECT_DISCOVERED);
    }
    Mark.GENERATE_MARK.removeMarkIfExist(page);
    Mark.FETCH_MARK.removeMarkIfExist(page);
    Utf8 mark = Mark.PARSE_MARK.removeMarkIfExist(page);
    if (mark != null) {
      Mark.UPDATEDB_MARK.putMark(page, mark);
    }


    context.write(keyUrl, page);

View Full Code Here

Examples of org.apache.avro.util.Utf8

    case ENUM:
      return s.getEnumOrdinal(o.toString());
    case NULL:
      return 0;
    case STRING:
      return (o instanceof Utf8 ? o : new Utf8(o.toString())).hashCode();
    default:
      return o.hashCode();
    }
  }

View Full Code Here

Examples of org.apache.avro.util.Utf8

        ? compare(o1, o2, s.getTypes().get(i1), equals)
        : i1 - i2;
    case NULL:
      return 0;
    case STRING:
      Utf8 u1 = o1 instanceof Utf8 ? (Utf8)o1 : new Utf8(o1.toString());
      Utf8 u2 = o2 instanceof Utf8 ? (Utf8)o2 : new Utf8(o2.toString());
      return u1.compareTo(u2);
    default:
      return ((Comparable)o1).compareTo(o2);
    }
  }

View Full Code Here

Examples of org.apache.avro.util.Utf8

        // Some CharSequence subclasses are mutable, so we still need to make 
        // a copy
        else if (value instanceof Utf8) {
          // Utf8 copy constructor is more efficient than converting 
          // to string and then back to Utf8
          return (T)new Utf8((Utf8)value);
        }
        return (T)new Utf8(value.toString());
      case UNION:
        return deepCopy(
            schema.getTypes().get(resolveUnion(schema, value)), value);
      default:
        throw new AvroRuntimeException(

View Full Code Here

Examples of org.apache.avro.util.Utf8

  }


  /** Called to create a string from a default value.  Subclasses may override
   * to use a different string representation.  By default, this calls {@link
   * Utf8#Utf8(String)}.*/
  protected Object createString(String value) { return new Utf8(value); }

View Full Code Here

Examples of org.apache.avro.util.Utf8

    fields.add(new Schema.Field("f", TestRecord.SCHEMA$, "", null));
    schema.setFields(fields);


    // create a generic instance of this record
    TestRecord nested = new TestRecord();
    nested.name = new Utf8("foo");
    nested.kind = Kind.BAR;
    nested.hash = new MD5();
    System.arraycopy(new byte[]{0,1,2,3,4,5,6,7,8,9,0,1,2,3,4,5}, 0,
                     nested.hash.bytes(), 0, 16);
    GenericData.Record record = new GenericData.Record(schema);

View Full Code Here

0 1 2 3 4 5

TOP

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.