Showing the changes to java/pkg/sun/tools/java/ScannerInputReader.java (1 of 18352 files). Show all
Unified · Split
| @@ -0,0 +1,242 @@ | ||
| 1 | +/* | |
| 2 | + * Copyright (c) 1995, 2003, 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 sun.tools.java; | |
| 27 | + | |
| 28 | +import java.io.IOException; | |
| 29 | +import java.io.InputStream; | |
| 30 | +import java.io.InputStreamReader; | |
| 31 | +import java.io.BufferedReader; | |
| 32 | +import java.io.FilterReader; | |
| 33 | +import java.io.UnsupportedEncodingException; | |
| 34 | + | |
| 35 | +/** | |
| 36 | + * An input stream for java programs. The stream treats either "\n", "\r" | |
| 37 | + * or "\r\n" as the end of a line, it always returns \n. It also parses | |
| 38 | + * UNICODE characters expressed as \uffff. However, if it sees "\\", the | |
| 39 | + * second slash cannot begin a unicode sequence. It keeps track of the current | |
| 40 | + * position in the input stream. | |
| 41 | + * | |
| 42 | + * WARNING: The contents of this source file are not part of any | |
| 43 | + * supported API. Code that depends on them does so at its own risk: | |
| 44 | + * they are subject to change or removal without notice. | |
| 45 | + * | |
| 46 | + * @author Arthur van Hoff | |
| 47 | + */ | |
| 48 | + | |
| 49 | +public | |
| 50 | +class ScannerInputReader extends FilterReader implements Constants { | |
| 51 | + // A note. This class does not really properly subclass FilterReader. | |
| 52 | + // Since this class only overrides the single character read method, | |
| 53 | + // and not the multi-character read method, any use of the latter | |
| 54 | + // will not work properly. Any attempt to use this code outside of | |
| 55 | + // the compiler should take that into account. | |
| 56 | + // | |
| 57 | + // For efficiency, it might be worth moving this code to Scanner and | |
| 58 | + // getting rid of this class. | |
| 59 | + | |
| 60 | + Environment env; | |
| 61 | + long pos; | |
| 62 | + | |
| 63 | + private long chpos; | |
| 64 | + private int pushBack = -1; | |
| 65 | + | |
| 66 | + public ScannerInputReader(Environment env, InputStream in) | |
| 67 | + throws UnsupportedEncodingException | |
| 68 | + { | |
| 69 | + // ScannerInputStream has been modified to no longer use | |
| 70 | + // BufferedReader. It now does its own buffering for | |
| 71 | + // performance. | |
| 72 | + super(env.getCharacterEncoding() != null ? | |
| 73 | + new InputStreamReader(in, env.getCharacterEncoding()) : | |
| 74 | + new InputStreamReader(in)); | |
| 75 | + | |
| 76 | + // Start out the buffer empty. | |
| 77 | + currentIndex = 0; | |
| 78 | + numChars = 0; | |
| 79 | + | |
| 80 | + this.env = env; | |
| 81 | + chpos = Scanner.LINEINC; | |
| 82 | + } | |
| 83 | + | |
| 84 | + //------------------------------------------------------------ | |
| 85 | + // Buffering code. | |
| 86 | + | |
| 87 | + // The size of our buffer. | |
| 88 | + private static final int BUFFERLEN = 10 * 1024; | |
| 89 | + | |
| 90 | + // A character buffer. | |
| 91 | + private final char[] buffer = new char[BUFFERLEN]; | |
| 92 | + | |
| 93 | + // The index of the next character to be "read" from the buffer. | |
| 94 | + private int currentIndex; | |
| 95 | + | |
| 96 | + // The number of characters in the buffer. -1 if EOF is reached. | |
| 97 | + private int numChars; | |
| 98 | + | |
| 99 | + /** | |
| 100 | + * Get the next character from our buffer. | |
| 101 | + * Note: this method has been inlined by hand in the `read' method | |
| 102 | + * below. Any changes made to this method should be equally applied | |
| 103 | + * to that code. | |
| 104 | + */ | |
| 105 | + private int getNextChar() throws IOException { | |
| 106 | + // Check to see if we have either run out of characters in our | |
| 107 | + // buffer or gotten to EOF on a previous call. | |
| 108 | + if (currentIndex >= numChars) { | |
| 109 | + numChars = in.read(buffer); | |
| 110 | + if (numChars == -1) { | |
| 111 | + // We have reached EOF. | |
| 112 | + return -1; | |
| 113 | + } | |
| 114 | + | |
| 115 | + // No EOF. currentIndex points to first char in buffer. | |
| 116 | + currentIndex = 0; | |
| 117 | + } | |
| 118 | + | |
| 119 | + return buffer[currentIndex++]; | |
| 120 | + } | |
| 121 | + | |
| 122 | + //------------------------------------------------------------ | |
| 123 | + | |
| 124 | + public int read(char[] buffer, int off, int len) { | |
| 125 | + throw new CompilerError( | |
| 126 | + "ScannerInputReader is not a fully implemented reader."); | |
| 127 | + } | |
| 128 | + | |
| 129 | + public int read() throws IOException { | |
| 130 | + pos = chpos; | |
| 131 | + chpos += Scanner.OFFSETINC; | |
| 132 | + | |
| 133 | + int c = pushBack; | |
| 134 | + if (c == -1) { | |
| 135 | + getchar: try { | |
| 136 | + // Here the call... | |
| 137 | + // c = getNextChar(); | |
| 138 | + // has been inlined by hand for performance. | |
| 139 | + | |
| 140 | + if (currentIndex >= numChars) { | |
| 141 | + numChars = in.read(buffer); | |
| 142 | + if (numChars == -1) { | |
| 143 | + // We have reached EOF. | |
| 144 | + c = -1; | |
| 145 | + break getchar; | |
| 146 | + } | |
| 147 | + | |
| 148 | + // No EOF. currentIndex points to first char in buffer. | |
| 149 | + currentIndex = 0; | |
| 150 | + } | |
| 151 | + c = buffer[currentIndex++]; | |
| 152 | + | |
| 153 | + } catch (java.io.CharConversionException e) { | |
| 154 | + env.error(pos, "invalid.encoding.char"); | |
| 155 | + // this is fatal error | |
| 156 | + return -1; | |
| 157 | + } | |
| 158 | + } else { | |
| 159 | + pushBack = -1; | |
| 160 | + } | |
| 161 | + | |
| 162 | + // parse special characters | |
| 163 | + switch (c) { | |
| 164 | + case -2: | |
| 165 | + // -2 is a special code indicating a pushback of a backslash that | |
| 166 | + // definitely isn't the start of a unicode sequence. | |
| 167 | + return '\\'; | |
| 168 | + | |
| 169 | + case '\\': | |
| 170 | + if ((c = getNextChar()) != 'u') { | |
| 171 | + pushBack = (c == '\\' ? -2 : c); | |
| 172 | + return '\\'; | |
| 173 | + } | |
| 174 | + // we have a unicode sequence | |
| 175 | + chpos += Scanner.OFFSETINC; | |
| 176 | + while ((c = getNextChar()) == 'u') { | |
| 177 | + chpos += Scanner.OFFSETINC; | |
| 178 | + } | |
| 179 | + | |
| 180 | + // unicode escape sequence | |
| 181 | + int d = 0; | |
| 182 | + for (int i = 0 ; i < 4 ; i++, chpos += Scanner.OFFSETINC, c = getNextChar()) { | |
| 183 | + switch (c) { | |
| 184 | + case '0': case '1': case '2': case '3': case '4': | |
| 185 | + case '5': case '6': case '7': case '8': case '9': | |
| 186 | + d = (d << 4) + c - '0'; | |
| 187 | + break; | |
| 188 | + | |
| 189 | + case 'a': case 'b': case 'c': case 'd': case 'e': case 'f': | |
| 190 | + d = (d << 4) + 10 + c - 'a'; | |
| 191 | + break; | |
| 192 | + | |
| 193 | + case 'A': case 'B': case 'C': case 'D': case 'E': case 'F': | |
| 194 | + d = (d << 4) + 10 + c - 'A'; | |
| 195 | + break; | |
| 196 | + | |
| 197 | + default: | |
| 198 | + env.error(pos, "invalid.escape.char"); | |
| 199 | + pushBack = c; | |
| 200 | + return d; | |
| 201 | + } | |
| 202 | + } | |
| 203 | + pushBack = c; | |
| 204 | + | |
| 205 | + // To read the following line, switch \ and /... | |
| 206 | + // Handle /u000a, /u000A, /u000d, /u000D properly as | |
| 207 | + // line terminators as per JLS 3.4, even though they are encoded | |
| 208 | + // (this properly respects the order given in JLS 3.2). | |
| 209 | + switch (d) { | |
| 210 | + case '\n': | |
| 211 | + chpos += Scanner.LINEINC; | |
| 212 | + return '\n'; | |
| 213 | + case '\r': | |
| 214 | + if ((c = getNextChar()) != '\n') { | |
| 215 | + pushBack = c; | |
| 216 | + } else { | |
| 217 | + chpos += Scanner.OFFSETINC; | |
| 218 | + } | |
| 219 | + chpos += Scanner.LINEINC; | |
| 220 | + return '\n'; | |
| 221 | + default: | |
| 222 | + return d; | |
| 223 | + } | |
| 224 | + | |
| 225 | + case '\n': | |
| 226 | + chpos += Scanner.LINEINC; | |
| 227 | + return '\n'; | |
| 228 | + | |
| 229 | + case '\r': | |
| 230 | + if ((c = getNextChar()) != '\n') { | |
| 231 | + pushBack = c; | |
| 232 | + } else { | |
| 233 | + chpos += Scanner.OFFSETINC; | |
| 234 | + } | |
| 235 | + chpos += Scanner.LINEINC; | |
| 236 | + return '\n'; | |
| 237 | + | |
| 238 | + default: | |
| 239 | + return c; | |
| 240 | + } | |
| 241 | + } | |
| 242 | +} | |