[120] | 1 | /** |
---|
| 2 | * Licensed to the Apache Software Foundation (ASF) under one |
---|
| 3 | * or more contributor license agreements. See the NOTICE file |
---|
| 4 | * distributed with this work for additional information |
---|
| 5 | * regarding copyright ownership. The ASF licenses this file |
---|
| 6 | * to you under the Apache License, Version 2.0 (the |
---|
| 7 | * "License"); you may not use this file except in compliance |
---|
| 8 | * with the License. You may obtain a copy of the License at |
---|
| 9 | * |
---|
| 10 | * http://www.apache.org/licenses/LICENSE-2.0 |
---|
| 11 | * |
---|
| 12 | * Unless required by applicable law or agreed to in writing, software |
---|
| 13 | * distributed under the License is distributed on an "AS IS" BASIS, |
---|
| 14 | * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
---|
| 15 | * See the License for the specific language governing permissions and |
---|
| 16 | * limitations under the License. |
---|
| 17 | */ |
---|
| 18 | |
---|
| 19 | package org.apache.hadoop.util; |
---|
| 20 | |
---|
| 21 | public class UTF8ByteArrayUtils { |
---|
| 22 | /** |
---|
| 23 | * Find the first occurrence of the given byte b in a UTF-8 encoded string |
---|
| 24 | * @param utf a byte array containing a UTF-8 encoded string |
---|
| 25 | * @param start starting offset |
---|
| 26 | * @param end ending position |
---|
| 27 | * @param b the byte to find |
---|
| 28 | * @return position that first byte occures otherwise -1 |
---|
| 29 | */ |
---|
| 30 | public static int findByte(byte [] utf, int start, int end, byte b) { |
---|
| 31 | for(int i=start; i<end; i++) { |
---|
| 32 | if (utf[i]==b) { |
---|
| 33 | return i; |
---|
| 34 | } |
---|
| 35 | } |
---|
| 36 | return -1; |
---|
| 37 | } |
---|
| 38 | |
---|
| 39 | /** |
---|
| 40 | * Find the first occurrence of the given bytes b in a UTF-8 encoded string |
---|
| 41 | * @param utf a byte array containing a UTF-8 encoded string |
---|
| 42 | * @param start starting offset |
---|
| 43 | * @param end ending position |
---|
| 44 | * @param b the bytes to find |
---|
| 45 | * @return position that first byte occures otherwise -1 |
---|
| 46 | */ |
---|
| 47 | public static int findBytes(byte [] utf, int start, int end, byte[] b) { |
---|
| 48 | int matchEnd = end - b.length; |
---|
| 49 | for(int i=start; i<=matchEnd; i++) { |
---|
| 50 | boolean matched = true; |
---|
| 51 | for(int j=0; j<b.length; j++) { |
---|
| 52 | if (utf[i+j] != b[j]) { |
---|
| 53 | matched = false; |
---|
| 54 | break; |
---|
| 55 | } |
---|
| 56 | } |
---|
| 57 | if (matched) { |
---|
| 58 | return i; |
---|
| 59 | } |
---|
| 60 | } |
---|
| 61 | return -1; |
---|
| 62 | } |
---|
| 63 | |
---|
| 64 | /** |
---|
| 65 | * Find the nth occurrence of the given byte b in a UTF-8 encoded string |
---|
| 66 | * @param utf a byte array containing a UTF-8 encoded string |
---|
| 67 | * @param start starting offset |
---|
| 68 | * @param length the length of byte array |
---|
| 69 | * @param b the byte to find |
---|
| 70 | * @param n the desired occurrence of the given byte |
---|
| 71 | * @return position that nth occurrence of the given byte if exists; otherwise -1 |
---|
| 72 | */ |
---|
| 73 | public static int findNthByte(byte [] utf, int start, int length, byte b, int n) { |
---|
| 74 | int pos = -1; |
---|
| 75 | int nextStart = start; |
---|
| 76 | for (int i = 0; i < n; i++) { |
---|
| 77 | pos = findByte(utf, nextStart, length, b); |
---|
| 78 | if (pos < 0) { |
---|
| 79 | return pos; |
---|
| 80 | } |
---|
| 81 | nextStart = pos + 1; |
---|
| 82 | } |
---|
| 83 | return pos; |
---|
| 84 | } |
---|
| 85 | |
---|
| 86 | /** |
---|
| 87 | * Find the nth occurrence of the given byte b in a UTF-8 encoded string |
---|
| 88 | * @param utf a byte array containing a UTF-8 encoded string |
---|
| 89 | * @param b the byte to find |
---|
| 90 | * @param n the desired occurrence of the given byte |
---|
| 91 | * @return position that nth occurrence of the given byte if exists; otherwise -1 |
---|
| 92 | */ |
---|
| 93 | public static int findNthByte(byte [] utf, byte b, int n) { |
---|
| 94 | return findNthByte(utf, 0, utf.length, b, n); |
---|
| 95 | } |
---|
| 96 | |
---|
| 97 | } |
---|
| 98 | |
---|