dist.edu.umd.cloud9.io.WritableComparatorUtils Maven / Gradle / Ivy

Show more of this group Show more artifacts with this name
Show all versions of cloud9 Show documentation

University of Maryland's Hadoop Library

There is a newer version: 2.0.1

package edu.umd.cloud9.io;

import java.io.UTFDataFormatException;

import org.apache.hadoop.io.WritableComparator;

public class WritableComparatorUtils {
	public static String readUTF(byte[] bytes, int s) {
		try {
			int utflen = WritableComparator.readUnsignedShort(bytes, s);

			byte[] bytearr = new byte[utflen];
			char[] chararr = new char[utflen];

			int c, char2, char3;
			int count = 0;
			int chararr_count = 0;

			System.arraycopy(bytes, s + 2, bytearr, 0, utflen);
			// in.readFully(bytearr, 0, utflen);

			while (count < utflen) {
				c = (int) bytearr[count] & 0xff;
				if (c > 127)
					break;
				count++;
				chararr[chararr_count++] = (char) c;
			}

			while (count < utflen) {
				c = (int) bytearr[count] & 0xff;
				switch (c >> 4) {
				case 0:
				case 1:
				case 2:
				case 3:
				case 4:
				case 5:
				case 6:
				case 7:
					/* 0xxxxxxx */
					count++;
					chararr[chararr_count++] = (char) c;
					break;
				case 12:
				case 13:
					/* 110x xxxx 10xx xxxx */
					count += 2;
					if (count > utflen)
						throw new UTFDataFormatException("malformed input: partial character at end");
					char2 = (int) bytearr[count - 1];
					if ((char2 & 0xC0) != 0x80)
						throw new UTFDataFormatException("malformed input around byte " + count);
					chararr[chararr_count++] = (char) (((c & 0x1F) << 6) | (char2 & 0x3F));
					break;
				case 14:
					/* 1110 xxxx 10xx xxxx 10xx xxxx */
					count += 3;
					if (count > utflen)
						throw new UTFDataFormatException("malformed input: partial character at end");
					char2 = (int) bytearr[count - 2];
					char3 = (int) bytearr[count - 1];
					if (((char2 & 0xC0) != 0x80) || ((char3 & 0xC0) != 0x80))
						throw new UTFDataFormatException("malformed input around byte "
								+ (count - 1));
					chararr[chararr_count++] = (char) (((c & 0x0F) << 12)
							| ((char2 & 0x3F) << 6) | ((char3 & 0x3F) << 0));
					break;
				default:
					/* 10xx xxxx, 1111 xxxx */
					throw new UTFDataFormatException("malformed input around byte " + count);
				}
			}
			// The number of chars produced may be less than utflen
			return new String(chararr, 0, chararr_count);

		} catch (Exception e) {
			e.printStackTrace();
		}

		return null;
	}
}