OLD | NEW |
| (Empty) |
1 // Protocol Buffers - Google's data interchange format | |
2 // Copyright 2008 Google Inc. All rights reserved. | |
3 // http://code.google.com/p/protobuf/ | |
4 // | |
5 // Redistribution and use in source and binary forms, with or without | |
6 // modification, are permitted provided that the following conditions are | |
7 // met: | |
8 // | |
9 // * Redistributions of source code must retain the above copyright | |
10 // notice, this list of conditions and the following disclaimer. | |
11 // * Redistributions in binary form must reproduce the above | |
12 // copyright notice, this list of conditions and the following disclaimer | |
13 // in the documentation and/or other materials provided with the | |
14 // distribution. | |
15 // * Neither the name of Google Inc. nor the names of its | |
16 // contributors may be used to endorse or promote products derived from | |
17 // this software without specific prior written permission. | |
18 // | |
19 // THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS | |
20 // "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT | |
21 // LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR | |
22 // A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT | |
23 // OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, | |
24 // SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT | |
25 // LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, | |
26 // DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY | |
27 // THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT | |
28 // (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE | |
29 // OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. | |
30 | |
31 package com.google.protobuf; | |
32 | |
33 import java.io.UnsupportedEncodingException; | |
34 | |
35 /** | |
36 * The classes contained within are used internally by the Protocol Buffer | |
37 * library and generated message implementations. They are public only because | |
38 * those generated messages do not reside in the {@code protobuf} package. | |
39 * Others should not use this class directly. | |
40 * | |
41 * @author kenton@google.com (Kenton Varda) | |
42 */ | |
43 public class Internal { | |
44 /** | |
45 * Helper called by generated code to construct default values for string | |
46 * fields. | |
47 * <p> | |
48 * The protocol compiler does not actually contain a UTF-8 decoder -- it | |
49 * just pushes UTF-8-encoded text around without touching it. The one place | |
50 * where this presents a problem is when generating Java string literals. | |
51 * Unicode characters in the string literal would normally need to be encoded | |
52 * using a Unicode escape sequence, which would require decoding them. | |
53 * To get around this, protoc instead embeds the UTF-8 bytes into the | |
54 * generated code and leaves it to the runtime library to decode them. | |
55 * <p> | |
56 * It gets worse, though. If protoc just generated a byte array, like: | |
57 * new byte[] {0x12, 0x34, 0x56, 0x78} | |
58 * Java actually generates *code* which allocates an array and then fills | |
59 * in each value. This is much less efficient than just embedding the bytes | |
60 * directly into the bytecode. To get around this, we need another | |
61 * work-around. String literals are embedded directly, so protoc actually | |
62 * generates a string literal corresponding to the bytes. The easiest way | |
63 * to do this is to use the ISO-8859-1 character set, which corresponds to | |
64 * the first 256 characters of the Unicode range. Protoc can then use | |
65 * good old CEscape to generate the string. | |
66 * <p> | |
67 * So we have a string literal which represents a set of bytes which | |
68 * represents another string. This function -- stringDefaultValue -- | |
69 * converts from the generated string to the string we actually want. The | |
70 * generated code calls this automatically. | |
71 */ | |
72 public static String stringDefaultValue(String bytes) { | |
73 try { | |
74 return new String(bytes.getBytes("ISO-8859-1"), "UTF-8"); | |
75 } catch (UnsupportedEncodingException e) { | |
76 // This should never happen since all JVMs are required to implement | |
77 // both of the above character sets. | |
78 throw new IllegalStateException( | |
79 "Java VM does not support a standard character set.", e); | |
80 } | |
81 } | |
82 | |
83 /** | |
84 * Helper called by generated code to construct default values for bytes | |
85 * fields. | |
86 * <p> | |
87 * This is a lot like {@link #stringDefaultValue}, but for bytes fields. | |
88 * In this case we only need the second of the two hacks -- allowing us to | |
89 * embed raw bytes as a string literal with ISO-8859-1 encoding. | |
90 */ | |
91 public static ByteString bytesDefaultValue(String bytes) { | |
92 try { | |
93 return ByteString.copyFrom(bytes.getBytes("ISO-8859-1")); | |
94 } catch (UnsupportedEncodingException e) { | |
95 // This should never happen since all JVMs are required to implement | |
96 // ISO-8859-1. | |
97 throw new IllegalStateException( | |
98 "Java VM does not support a standard character set.", e); | |
99 } | |
100 } | |
101 | |
102 /** | |
103 * Helper called by generated code to determine if a byte array is a valid | |
104 * UTF-8 encoded string such that the original bytes can be converted to | |
105 * a String object and then back to a byte array round tripping the bytes | |
106 * without loss. More precisely, returns {@code true} whenever: | |
107 * <pre> {@code | |
108 * Arrays.equals(byteString.toByteArray(), | |
109 * new String(byteString.toByteArray(), "UTF-8").getBytes("UTF-8")) | |
110 * }</pre> | |
111 * | |
112 * <p>This method rejects "overlong" byte sequences, as well as | |
113 * 3-byte sequences that would map to a surrogate character, in | |
114 * accordance with the restricted definition of UTF-8 introduced in | |
115 * Unicode 3.1. Note that the UTF-8 decoder included in Oracle's | |
116 * JDK has been modified to also reject "overlong" byte sequences, | |
117 * but currently (2011) still accepts 3-byte surrogate character | |
118 * byte sequences. | |
119 * | |
120 * <p>See the Unicode Standard,</br> | |
121 * Table 3-6. <em>UTF-8 Bit Distribution</em>,</br> | |
122 * Table 3-7. <em>Well Formed UTF-8 Byte Sequences</em>. | |
123 * | |
124 * <p>As of 2011-02, this method simply returns the result of {@link | |
125 * ByteString#isValidUtf8()}. Calling that method directly is preferred. | |
126 * | |
127 * @param byteString the string to check | |
128 * @return whether the byte array is round trippable | |
129 */ | |
130 public static boolean isValidUtf8(ByteString byteString) { | |
131 return byteString.isValidUtf8(); | |
132 } | |
133 | |
134 /** | |
135 * Interface for an enum value or value descriptor, to be used in FieldSet. | |
136 * The lite library stores enum values directly in FieldSets but the full | |
137 * library stores EnumValueDescriptors in order to better support reflection. | |
138 */ | |
139 public interface EnumLite { | |
140 int getNumber(); | |
141 } | |
142 | |
143 /** | |
144 * Interface for an object which maps integers to {@link EnumLite}s. | |
145 * {@link Descriptors.EnumDescriptor} implements this interface by mapping | |
146 * numbers to {@link Descriptors.EnumValueDescriptor}s. Additionally, | |
147 * every generated enum type has a static method internalGetValueMap() which | |
148 * returns an implementation of this type that maps numbers to enum values. | |
149 */ | |
150 public interface EnumLiteMap<T extends EnumLite> { | |
151 T findValueByNumber(int number); | |
152 } | |
153 } | |
OLD | NEW |