42 * of bytes has been read, an {@code EOFException}
43 * (which is a kind of {@code IOException})
44 * is thrown. If any byte cannot be read for
45 * any reason other than end of file, an {@code IOException}
46 * other than {@code EOFException} is
47 * thrown. In particular, an {@code IOException}
48 * may be thrown if the input stream has been
49 * closed.
50 *
51 * <h3><a id="modified-utf-8">Modified UTF-8</a></h3>
52 * <p>
53 * Implementations of the DataInput and DataOutput interfaces represent
54 * Unicode strings in a format that is a slight modification of UTF-8.
55 * (For information regarding the standard UTF-8 format, see section
56 * <i>3.9 Unicode Encoding Forms</i> of <i>The Unicode Standard, Version
57 * 4.0</i>).
58 * Note that in the following table, the most significant bit appears in the
59 * far left-hand column.
60 *
61 * <blockquote>
62 * <table border="1" cellspacing="0" cellpadding="8"
63 * summary="Bit values and bytes">
64 * <tr>
65 * <th colspan="9"><span style="font-weight:normal">
66 * All characters in the range {@code '\u005Cu0001'} to
67 * {@code '\u005Cu007F'} are represented by a single byte:</span></th>
68 * </tr>
69 * <tr>
70 * <td></td>
71 * <th colspan="8" id="bit_a">Bit Values</th>
72 * </tr>
73 * <tr>
74 * <th id="byte1_a">Byte 1</th>
75 * <td style="text-align:center">0
76 * <td colspan="7" style="text-align:center">bits 6-0
77 * </tr>
78 * <tr>
79 * <th colspan="9"><span style="font-weight:normal">
80 * The null character {@code '\u005Cu0000'} and characters
81 * in the range {@code '\u005Cu0080'} to {@code '\u005Cu07FF'} are
82 * represented by a pair of bytes:</span></th>
83 * </tr>
84 * <tr>
85 * <td></td>
86 * <th colspan="8" id="bit_b">Bit Values</th>
87 * </tr>
88 * <tr>
89 * <th id="byte1_b">Byte 1</th>
90 * <td style="text-align:center">1
91 * <td style="text-align:center">1
92 * <td style="text-align:center">0
93 * <td colspan="5" style="text-align:center">bits 10-6
94 * </tr>
95 * <tr>
96 * <th id="byte2_a">Byte 2</th>
97 * <td style="text-align:center">1
98 * <td style="text-align:center">0
99 * <td colspan="6" style="text-align:center">bits 5-0
100 * </tr>
101 * <tr>
102 * <th colspan="9"><span style="font-weight:normal">
103 * {@code char} values in the range {@code '\u005Cu0800'}
104 * to {@code '\u005CuFFFF'} are represented by three bytes:</span></th>
105 * </tr>
106 * <tr>
107 * <td></td>
108 * <th colspan="8"id="bit_c">Bit Values</th>
109 * </tr>
110 * <tr>
111 * <th id="byte1_c">Byte 1</th>
112 * <td style="text-align:center">1
113 * <td style="text-align:center">1
114 * <td style="text-align:center">1
115 * <td style="text-align:center">0
116 * <td colspan="4" style="text-align:center">bits 15-12
117 * </tr>
118 * <tr>
119 * <th id="byte2_b">Byte 2</th>
120 * <td style="text-align:center">1
121 * <td style="text-align:center">0
122 * <td colspan="6" style="text-align:center">bits 11-6
123 * </tr>
124 * <tr>
125 * <th id="byte3">Byte 3</th>
126 * <td style="text-align:center">1
127 * <td style="text-align:center">0
128 * <td colspan="6" style="text-align:center">bits 5-0
129 * </tr>
130 * </table>
131 * </blockquote>
132 * <p>
133 * The differences between this format and the
134 * standard UTF-8 format are the following:
135 * <ul>
136 * <li>The null byte {@code '\u005Cu0000'} is encoded in 2-byte format
137 * rather than 1-byte, so that the encoded strings never have
138 * embedded nulls.
139 * <li>Only the 1-byte, 2-byte, and 3-byte formats are used.
140 * <li><a href="../lang/Character.html#unicode">Supplementary characters</a>
141 * are represented in the form of surrogate pairs.
142 * </ul>
143 * @author Frank Yellin
144 * @see java.io.DataInputStream
145 * @see java.io.DataOutput
146 * @since 1.0
147 */
148 public
149 interface DataInput {
|
42 * of bytes has been read, an {@code EOFException}
43 * (which is a kind of {@code IOException})
44 * is thrown. If any byte cannot be read for
45 * any reason other than end of file, an {@code IOException}
46 * other than {@code EOFException} is
47 * thrown. In particular, an {@code IOException}
48 * may be thrown if the input stream has been
49 * closed.
50 *
51 * <h3><a id="modified-utf-8">Modified UTF-8</a></h3>
52 * <p>
53 * Implementations of the DataInput and DataOutput interfaces represent
54 * Unicode strings in a format that is a slight modification of UTF-8.
55 * (For information regarding the standard UTF-8 format, see section
56 * <i>3.9 Unicode Encoding Forms</i> of <i>The Unicode Standard, Version
57 * 4.0</i>).
58 * Note that in the following table, the most significant bit appears in the
59 * far left-hand column.
60 *
61 * <blockquote>
62 * <table class="plain">
63 * <caption style="display:none">Bit values and bytes</caption>
64 * <tbody>
65 * <tr>
66 * <th colspan="9"><span style="font-weight:normal">
67 * All characters in the range {@code '\u005Cu0001'} to
68 * {@code '\u005Cu007F'} are represented by a single byte:</span></th>
69 * </tr>
70 * <tr>
71 * <td></td>
72 * <th colspan="8" id="bit_a">Bit Values</th>
73 * </tr>
74 * <tr>
75 * <th id="byte1_a" style="text-align:left">Byte 1</th>
76 * <td style="text-align:center">0
77 * <td colspan="7" style="text-align:center">bits 6-0
78 * </tr>
79 * <tr>
80 * <th colspan="9"><span style="font-weight:normal">
81 * The null character {@code '\u005Cu0000'} and characters
82 * in the range {@code '\u005Cu0080'} to {@code '\u005Cu07FF'} are
83 * represented by a pair of bytes:</span></th>
84 * </tr>
85 * <tr>
86 * <td></td>
87 * <th colspan="8" id="bit_b">Bit Values</th>
88 * </tr>
89 * <tr>
90 * <th id="byte1_b" style="text-align:left">Byte 1</th>
91 * <td style="text-align:center">1
92 * <td style="text-align:center">1
93 * <td style="text-align:center">0
94 * <td colspan="5" style="text-align:center">bits 10-6
95 * </tr>
96 * <tr>
97 * <th id="byte2_a" style="text-align:left">Byte 2</th>
98 * <td style="text-align:center">1
99 * <td style="text-align:center">0
100 * <td colspan="6" style="text-align:center">bits 5-0
101 * </tr>
102 * <tr>
103 * <th colspan="9"><span style="font-weight:normal">
104 * {@code char} values in the range {@code '\u005Cu0800'}
105 * to {@code '\u005CuFFFF'} are represented by three bytes:</span></th>
106 * </tr>
107 * <tr>
108 * <td></td>
109 * <th colspan="8"id="bit_c">Bit Values</th>
110 * </tr>
111 * <tr>
112 * <th id="byte1_c" style="text-align:left">Byte 1</th>
113 * <td style="text-align:center">1
114 * <td style="text-align:center">1
115 * <td style="text-align:center">1
116 * <td style="text-align:center">0
117 * <td colspan="4" style="text-align:center">bits 15-12
118 * </tr>
119 * <tr>
120 * <th id="byte2_b" style="text-align:left">Byte 2</th>
121 * <td style="text-align:center">1
122 * <td style="text-align:center">0
123 * <td colspan="6" style="text-align:center">bits 11-6
124 * </tr>
125 * <tr>
126 * <th id="byte3" style="text-align:left">Byte 3</th>
127 * <td style="text-align:center">1
128 * <td style="text-align:center">0
129 * <td colspan="6" style="text-align:center">bits 5-0
130 * </tr>
131 * </tbody>
132 * </table>
133 * </blockquote>
134 * <p>
135 * The differences between this format and the
136 * standard UTF-8 format are the following:
137 * <ul>
138 * <li>The null byte {@code '\u005Cu0000'} is encoded in 2-byte format
139 * rather than 1-byte, so that the encoded strings never have
140 * embedded nulls.
141 * <li>Only the 1-byte, 2-byte, and 3-byte formats are used.
142 * <li><a href="../lang/Character.html#unicode">Supplementary characters</a>
143 * are represented in the form of surrogate pairs.
144 * </ul>
145 * @author Frank Yellin
146 * @see java.io.DataInputStream
147 * @see java.io.DataOutput
148 * @since 1.0
149 */
150 public
151 interface DataInput {
|