1 package org.apache.lucene.index;
2
3 /**
4 * Licensed to the Apache Software Foundation (ASF) under one or more
5 * contributor license agreements. See the NOTICE file distributed with
6 * this work for additional information regarding copyright ownership.
7 * The ASF licenses this file to You under the Apache License, Version 2.0
8 * (the "License"); you may not use this file except in compliance with
9 * the License. You may obtain a copy of the License at
10 *
11 * http://www.apache.org/licenses/LICENSE-2.0
12 *
13 * Unless required by applicable law or agreed to in writing, software
14 * distributed under the License is distributed on an "AS IS" BASIS,
15 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
16 * See the License for the specific language governing permissions and
17 * limitations under the License.
18 */
19
20 import java.io.IOException;
21 import org.apache.lucene.store.IndexInput;
22 import org.apache.lucene.util.UnicodeUtil;
23
24 final class TermBuffer implements Cloneable {
25
26 private String field;
27 private Term term; // cached
28 private boolean preUTF8Strings; // true if strings are stored in modified UTF8 encoding (LUCENE-510)
29 private boolean dirty; // true if text was set externally (ie not read via UTF8 bytes)
30
31 private UnicodeUtil.UTF16Result text = new UnicodeUtil.UTF16Result();
32 private UnicodeUtil.UTF8Result bytes = new UnicodeUtil.UTF8Result();
33
34 public final int compareTo(TermBuffer other) {
35 if (field == other.field) // fields are interned
36 return compareChars(text.result, text.length, other.text.result, other.text.length);
37 else
38 return field.compareTo(other.field);
39 }
40
41 private static final int compareChars(char[] chars1, int len1,
42 char[] chars2, int len2) {
43 final int end = len1 < len2 ? len1:len2;
44 for (int k = 0; k < end; k++) {
45 char c1 = chars1[k];
46 char c2 = chars2[k];
47 if (c1 != c2) {
48 return c1 - c2;
49 }
50 }
51 return len1 - len2;
52 }
53
54 /** Call this if the IndexInput passed to {@link #read}
55 * stores terms in the "modified UTF8" (pre LUCENE-510)
56 * format. */
57 void setPreUTF8Strings() {
58 preUTF8Strings = true;
59 }
60
61 public final void read(IndexInput input, FieldInfos fieldInfos)
62 throws IOException {
63 this.term = null; // invalidate cache
64 int start = input.readVInt();
65 int length = input.readVInt();
66 int totalLength = start + length;
67 if (preUTF8Strings) {
68 text.setLength(totalLength);
69 input.readChars(text.result, start, length);
70 } else {
71
72 if (dirty) {
73 // Fully convert all bytes since bytes is dirty
74 UnicodeUtil.UTF16toUTF8(text.result, 0, text.length, bytes);
75 bytes.setLength(totalLength);
76 input.readBytes(bytes.result, start, length);
77 UnicodeUtil.UTF8toUTF16(bytes.result, 0, totalLength, text);
78 dirty = false;
79 } else {
80 // Incrementally convert only the UTF8 bytes that are new:
81 bytes.setLength(totalLength);
82 input.readBytes(bytes.result, start, length);
83 UnicodeUtil.UTF8toUTF16(bytes.result, start, length, text);
84 }
85 }
86 this.field = fieldInfos.fieldName(input.readVInt());
87 }
88
89 public final void set(Term term) {
90 if (term == null) {
91 reset();
92 return;
93 }
94 final String termText = term.text();
95 final int termLen = termText.length();
96 text.setLength(termLen);
97 termText.getChars(0, termLen, text.result, 0);
98 dirty = true;
99 field = term.field();
100 this.term = term;
101 }
102
103 public final void set(TermBuffer other) {
104 text.copyText(other.text);
105 dirty = true;
106 field = other.field;
107 term = other.term;
108 }
109
110 public void reset() {
111 field = null;
112 text.setLength(0);
113 term = null;
114 dirty = true;
115 }
116
117 public Term toTerm() {
118 if (field == null) // unset
119 return null;
120
121 if (term == null)
122 term = new Term(field, new String(text.result, 0, text.length), false);
123
124 return term;
125 }
126
127 protected Object clone() {
128 TermBuffer clone = null;
129 try {
130 clone = (TermBuffer)super.clone();
131 } catch (CloneNotSupportedException e) {}
132
133 clone.dirty = true;
134 clone.bytes = new UnicodeUtil.UTF8Result();
135 clone.text = new UnicodeUtil.UTF16Result();
136 clone.text.copyText(text);
137 return clone;
138 }
139 }