1 /*
2 * Copyright (c) 2010, 2020, Oracle and/or its affiliates. All rights reserved.
3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
4 *
5 * This code is free software; you can redistribute it and/or modify it
6 * under the terms of the GNU General Public License version 2 only, as
7 * published by the Free Software Foundation. Oracle designates this
8 * particular file as subject to the "Classpath" exception as provided
9 * by Oracle in the LICENSE file that accompanied this code.
10 *
11 * This code is distributed in the hope that it will be useful, but WITHOUT
12 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
13 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
14 * version 2 for more details (a copy is included in the LICENSE file that
15 * accompanied this code).
16 *
17 * You should have received a copy of the GNU General Public License version
18 * 2 along with this work; if not, write to the Free Software Foundation,
19 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
20 *
21 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
22 * or visit www.oracle.com if you need additional information or have any
23 * questions.
24 */
25
26 package build.tools.generatecharacter;
27
28 import java.io.*;
29 import java.nio.*;
30 import java.util.*;
31 import java.util.zip.*;
32
33 public class CharacterName {
34
35 public static void main(String[] args) {
36 FileReader reader = null;
37 try {
38 if (args.length != 2) {
39 System.err.println("Usage: java CharacterName UnicodeData.txt uniName.dat");
40 System.exit(1);
41 }
42 reader = new FileReader(args[0]);
43 BufferedReader bfr = new BufferedReader(reader);
44 String line = null;
45
46 StringBuilder namePool = new StringBuilder();
47 byte[] cpPoolBytes = new byte[0x100000];
48 boolean[] cpBlocks = new boolean[(Character.MAX_CODE_POINT + 1) >> 8];
49 int bkNum = 0;
50 ByteBuffer cpBB = ByteBuffer.wrap(cpPoolBytes);
51 int lastCp = 0;
52 int cpNum = 0;
53
54 while ((line = bfr.readLine()) != null) {
55 if (line.startsWith("#"))
56 continue;
57 UnicodeSpec spec = UnicodeSpec.parse(line);
58 if (spec != null) {
59 int cp = spec.getCodePoint();
60 String name = spec.getName();
61 if (name.equals("<control>") && spec.getOldName() != null) {
62 if (cp == 0x7) // <control>BELL -> BEL; u+1f514 <-> BELL
63 name = "BEL";
64 else if (spec.getOldName().length() != 0)
65 name = spec.getOldName();
66 /*
67 3 "figment" characters from NameAliases.txt
68 Several documented labels for C1 control code points which
69 were never actually approved in any standard...but were
70 implemented in Perl regex.
71 0080;PADDING CHARACTER;figment
72 0081;HIGH OCTET PRESET;figment
73 0099;SINGLE GRAPHIC CHARACTER INTRODUCER;figment
74 */
75 else if (cp == 0x80)
76 name = "PADDING CHARACTER";
77 else if (cp == 0x81)
78 name = "HIGH OCTET PRESET";
79 else if (cp == 0x99)
80 name = "SINGLE GRAPHIC CHARACTER INTRODUCER";
81 else
82 continue;
83 } else if (name.startsWith("<")) {
84 /*
85 3400 <CJK Ideograph Extension A, First>
86 4db5 <CJK Ideograph Extension A, Last>
87 4e00 <CJK Ideograph, First>
88 9fc3 <CJK Ideograph, Last>
89 ac00 <Hangul Syllable, First>
90 d7a3 <Hangul Syllable, Last>
91 d800 <Non Private Use High Surrogate, First>
92 db7f <Non Private Use High Surrogate, Last>
93 db80 <Private Use High Surrogate, First>
94 dbff <Private Use High Surrogate, Last>
95 dc00 <Low Surrogate, First>
96 dfff <Low Surrogate, Last>
97 e000 <Private Use, First>
98 f8ff <Private Use, Last>
99 20000 <CJK Ideograph Extension B, First>
100 2a6d6 <CJK Ideograph Extension B, Last>
101 f0000 <Plane 15 Private Use, First>
102 ffffd <Plane 15 Private Use, Last>
103 */
104 continue;
105 }
106 cpNum++;
107 if (!cpBlocks[cp >> 8]) {
108 cpBlocks[cp >> 8] = true;
109 bkNum++;
110 }
111 if (cp == lastCp + 1) {
112 cpBB.put((byte)name.length());
113 } else {
114 cpBB.put((byte)0); // segment start flag
115 cpBB.putInt((name.length() << 24) | (cp & 0xffffff));
116 }
117 namePool.append(name);
118 lastCp = cp;
119 }
120 }
121
122 byte[] namePoolBytes = namePool.toString().getBytes("ASCII");
123 int cpLen = cpBB.position();
124 int total = cpLen + namePoolBytes.length;
125 DataOutputStream dos = new DataOutputStream(
126 new DeflaterOutputStream(
127 new FileOutputStream(args[1])));
128 dos.writeInt(total); // total
129 dos.writeInt(bkNum); // bkNum;
130 dos.writeInt(cpNum); // cpNum
131 dos.writeInt(cpLen); // nameOff
132 dos.write(cpPoolBytes, 0, cpLen);
133 dos.write(namePoolBytes);
134 dos.close();
135
136 } catch (Throwable e) {
137 System.out.println("Unexpected exception:");
138 e.printStackTrace();
139 } finally {
140 if (reader != null) {
141 try {
142 reader.close();
143 } catch (Throwable ee) { ee.printStackTrace(); }
144 }
145 }
146 }
147 }