Classes in this File | Line Coverage | Branch Coverage | Complexity | ||||
NativeAsciiReader |
|
| 11.666666666666666;11.667 |
1 | /* | |
2 | * Copyright (C) 1998-2000 Semiotek Inc. All Rights Reserved. | |
3 | * | |
4 | * Redistribution and use in source and binary forms, with or without | |
5 | * modification, are permitted under the terms of either of the following | |
6 | * Open Source licenses: | |
7 | * | |
8 | * The GNU General Public License, version 2, or any later version, as | |
9 | * published by the Free Software Foundation | |
10 | * (http://www.fsf.org/copyleft/gpl.html); | |
11 | * | |
12 | * or | |
13 | * | |
14 | * The Semiotek Public License (http://webmacro.org/LICENSE.) | |
15 | * | |
16 | * This software is provided "as is", with NO WARRANTY, not even the | |
17 | * implied warranties of fitness to purpose, or merchantability. You | |
18 | * assume all risks and liabilities associated with its use. | |
19 | * | |
20 | * See www.webmacro.org for more information on the WebMacro project. | |
21 | */ | |
22 | ||
23 | package org.webmacro.util; | |
24 | ||
25 | import java.io.BufferedReader; | |
26 | import java.io.IOException; | |
27 | import java.io.Reader; | |
28 | ||
29 | /** | |
30 | * Reads a file that has been encoded with Java's unicode escape syntax, | |
31 | * typically converted with native2ascii. | |
32 | * | |
33 | * All character sequences like \\uxxxx will be converted to a single unicode | |
34 | * character. Other '\' escaped characters will be passed unchanged. An | |
35 | * error will be thrown if the \\u is not followed by 4 hexadecimal characters | |
36 | * | |
37 | * | |
38 | */ | |
39 | public class NativeAsciiReader extends BufferedReader | |
40 | { | |
41 | ||
42 | /* | |
43 | The constructors simply echo those in the super-class | |
44 | */ | |
45 | 0 | private static int defaultCharBufferSize = 8192; |
46 | public static final String RCS = "$Id: org.webmacro.util.NativeAsciiReader.html,v 1.1 2010/03/04 23:00:06 timp Exp $"; | |
47 | ||
48 | public NativeAsciiReader (Reader in, int sz) | |
49 | { | |
50 | 0 | super(in, sz); |
51 | 0 | } |
52 | ||
53 | public NativeAsciiReader (Reader in) | |
54 | { | |
55 | 0 | this(in, defaultCharBufferSize); |
56 | 0 | } |
57 | ||
58 | /** | |
59 | * Read a sequence of characters into the given buffer. Since we're | |
60 | * extending BufferedReader, it is efficient enough to read one character | |
61 | * at a time | |
62 | */ | |
63 | public int read (char cbuf[], int off, int len) throws IOException | |
64 | { | |
65 | 0 | int i = 0; |
66 | 0 | while (i < len) |
67 | { | |
68 | 0 | int c = read(); |
69 | 0 | if (i == 0 && c == -1) return -1; |
70 | 0 | if (c == -1) return i; |
71 | 0 | if (c == '\\') |
72 | { | |
73 | 0 | mark(1); |
74 | 0 | if (read() != 'u') |
75 | { | |
76 | 0 | reset(); |
77 | } | |
78 | 0 | int value = 0; |
79 | int a; | |
80 | ||
81 | 0 | for (int j = 0; j < 4; j++) |
82 | { | |
83 | 0 | a = read(); |
84 | 0 | switch (a) |
85 | { | |
86 | case '0': | |
87 | case '1': | |
88 | case '2': | |
89 | case '3': | |
90 | case '4': | |
91 | case '5': | |
92 | case '6': | |
93 | case '7': | |
94 | case '8': | |
95 | case '9': | |
96 | 0 | value = (value << 4) + a - '0'; |
97 | 0 | break; |
98 | case 'a': | |
99 | case 'b': | |
100 | case 'c': | |
101 | case 'd': | |
102 | case 'e': | |
103 | case 'f': | |
104 | 0 | value = (value << 4) + 10 + a - 'a'; |
105 | 0 | break; |
106 | case 'A': | |
107 | case 'B': | |
108 | case 'C': | |
109 | case 'D': | |
110 | case 'E': | |
111 | case 'F': | |
112 | 0 | value = (value << 4) + 10 + a - 'A'; |
113 | 0 | break; |
114 | default: | |
115 | 0 | throw new IllegalArgumentException( |
116 | "Malformed \\uxxxx encoding."); | |
117 | } | |
118 | } | |
119 | 0 | c = (char) value; |
120 | } | |
121 | 0 | cbuf[i + off] = (char) c; |
122 | 0 | i++; |
123 | 0 | } |
124 | 0 | return i; |
125 | } | |
126 | ||
127 | } |