c17038481baa7676d216838f78a5d948901c4b8c
[vxquery.git] / vxquery-core / src / main / java / org / apache / vxquery / runtime / functions / strings / UTF8StringCharacterIterator.java
1 /*
2 * Licensed to the Apache Software Foundation (ASF) under one or more
3 * contributor license agreements. See the NOTICE file distributed with
4 * this work for additional information regarding copyright ownership.
5 * The ASF licenses this file to You under the Apache License, Version 2.0
6 * (the "License"); you may not use this file except in compliance with
7 * the License. You may obtain a copy of the License at
8 *
9 * http://www.apache.org/licenses/LICENSE-2.0
10 *
11 * Unless required by applicable law or agreed to in writing, software
12 * distributed under the License is distributed on an "AS IS" BASIS,
13 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 * See the License for the specific language governing permissions and
15 * limitations under the License.
16 */
17 package org.apache.vxquery.runtime.functions.strings;
18
19 import java.util.logging.Level;
20 import java.util.logging.Logger;
21
22 import org.apache.hyracks.data.std.primitive.UTF8StringPointable;
23
24 public class UTF8StringCharacterIterator implements ICharacterIterator {
25 private static final Logger LOGGER = Logger.getLogger(UTF8StringCharacterIterator.class.getName());
26
27 private int byteOffset;
28 private final UTF8StringPointable stringp;
29
30 public UTF8StringCharacterIterator(UTF8StringPointable stringp) {
31 this.stringp = stringp;
32 }
33
34 public int getByteOffset() {
35 return byteOffset;
36 }
37
38 @Override
39 public char next() {
40 // Default - no character exists.
41 int c = ICharacterIterator.EOS_CHAR;
42 if (byteOffset < stringp.getLength()) {
43 c = stringp.charAt(byteOffset);
44 if (LOGGER.isLoggable(Level.FINE)) {
45 LOGGER.finer(" UTF8StringCharacterIterator char[" + byteOffset + "] = " + c);
46 }
47 // Increment cursor
48 if ((c >= 0x0001) && (c <= 0x007F)) {
49 ++byteOffset;
50 } else if (c > 0x07FF) {
51 byteOffset += 3;
52 } else {
53 byteOffset += 2;
54 }
55 }
56 if (LOGGER.isLoggable(Level.FINE)) {
57 LOGGER.finer(" END UTF8StringCharacterIterator char[" + byteOffset + "] = " + c);
58 }
59 return (char) c;
60 }
61
62 @Override
63 public void reset() {
64 byteOffset = 2;
65 }
66
67 public void setByteOffset(int byteOffset) {
68 this.byteOffset = byteOffset;
69 }
70
71 }

Copyright 2016, The Apache Software Foundation.