src/share/classes/com/sun/tools/javac/util/Convert.java

changeset 0
959103a6100f
child 2525
2eb010b6cb22
     1.1 --- /dev/null	Thu Jan 01 00:00:00 1970 +0000
     1.2 +++ b/src/share/classes/com/sun/tools/javac/util/Convert.java	Wed Apr 27 01:34:52 2016 +0800
     1.3 @@ -0,0 +1,338 @@
     1.4 +/*
     1.5 + * Copyright (c) 1999, 2013, Oracle and/or its affiliates. All rights reserved.
     1.6 + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
     1.7 + *
     1.8 + * This code is free software; you can redistribute it and/or modify it
     1.9 + * under the terms of the GNU General Public License version 2 only, as
    1.10 + * published by the Free Software Foundation.  Oracle designates this
    1.11 + * particular file as subject to the "Classpath" exception as provided
    1.12 + * by Oracle in the LICENSE file that accompanied this code.
    1.13 + *
    1.14 + * This code is distributed in the hope that it will be useful, but WITHOUT
    1.15 + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
    1.16 + * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
    1.17 + * version 2 for more details (a copy is included in the LICENSE file that
    1.18 + * accompanied this code).
    1.19 + *
    1.20 + * You should have received a copy of the GNU General Public License version
    1.21 + * 2 along with this work; if not, write to the Free Software Foundation,
    1.22 + * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
    1.23 + *
    1.24 + * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
    1.25 + * or visit www.oracle.com if you need additional information or have any
    1.26 + * questions.
    1.27 + */
    1.28 +
    1.29 +package com.sun.tools.javac.util;
    1.30 +
    1.31 +/** Utility class for static conversion methods between numbers
    1.32 + *  and strings in various formats.
    1.33 + *
    1.34 + *  <p>Note regarding UTF-8.
    1.35 + *  The JVMS defines its own version of the UTF-8 format so that it
    1.36 + *  contains no zero bytes (modified UTF-8). This is not actually the same
    1.37 + *  as Charset.forName("UTF-8").
    1.38 + *
    1.39 + *  <p>
    1.40 + *  See also:
    1.41 + *  <ul>
    1.42 + *  <li><a href="http://docs.oracle.com/javase/specs/jvms/se7/html/jvms-4.html#jvms-4.4.7">
    1.43 + *    JVMS 4.4.7 </a></li>
    1.44 + *  <li><a href="http://docs.oracle.com/javase/7/docs/api/java/io/DataInput.html#modified-utf-8">
    1.45 +      java.io.DataInput: Modified UTF-8 </a></li>
    1.46 +    <li><a href="https://en.wikipedia.org/wiki/UTF-8#Modified_UTF-8">
    1.47 +      Modified UTF-8 (wikipedia) </a></li>
    1.48 + *  </ul>
    1.49 + *
    1.50 + *  The methods here support modified UTF-8.
    1.51 + *
    1.52 + *  <p><b>This is NOT part of any supported API.
    1.53 + *  If you write code that depends on this, you do so at your own risk.
    1.54 + *  This code and its internal interfaces are subject to change or
    1.55 + *  deletion without notice.</b>
    1.56 + */
    1.57 +public class Convert {
    1.58 +
    1.59 +    /** Convert string to integer.
    1.60 +     */
    1.61 +    public static int string2int(String s, int radix)
    1.62 +        throws NumberFormatException {
    1.63 +        if (radix == 10) {
    1.64 +            return Integer.parseInt(s, radix);
    1.65 +        } else {
    1.66 +            char[] cs = s.toCharArray();
    1.67 +            int limit = Integer.MAX_VALUE / (radix/2);
    1.68 +            int n = 0;
    1.69 +            for (int i = 0; i < cs.length; i++) {
    1.70 +                int d = Character.digit(cs[i], radix);
    1.71 +                if (n < 0 ||
    1.72 +                    n > limit ||
    1.73 +                    n * radix > Integer.MAX_VALUE - d)
    1.74 +                    throw new NumberFormatException();
    1.75 +                n = n * radix + d;
    1.76 +            }
    1.77 +            return n;
    1.78 +        }
    1.79 +    }
    1.80 +
    1.81 +    /** Convert string to long integer.
    1.82 +     */
    1.83 +    public static long string2long(String s, int radix)
    1.84 +        throws NumberFormatException {
    1.85 +        if (radix == 10) {
    1.86 +            return Long.parseLong(s, radix);
    1.87 +        } else {
    1.88 +            char[] cs = s.toCharArray();
    1.89 +            long limit = Long.MAX_VALUE / (radix/2);
    1.90 +            long n = 0;
    1.91 +            for (int i = 0; i < cs.length; i++) {
    1.92 +                int d = Character.digit(cs[i], radix);
    1.93 +                if (n < 0 ||
    1.94 +                    n > limit ||
    1.95 +                    n * radix > Long.MAX_VALUE - d)
    1.96 +                    throw new NumberFormatException();
    1.97 +                n = n * radix + d;
    1.98 +            }
    1.99 +            return n;
   1.100 +        }
   1.101 +    }
   1.102 +
   1.103 +/* Conversion routines between names, strings, and byte arrays in Utf8 format
   1.104 + */
   1.105 +
   1.106 +    /** Convert `len' bytes from utf8 to characters.
   1.107 +     *  Parameters are as in System.arraycopy
   1.108 +     *  Return first index in `dst' past the last copied char.
   1.109 +     *  @param src        The array holding the bytes to convert.
   1.110 +     *  @param sindex     The start index from which bytes are converted.
   1.111 +     *  @param dst        The array holding the converted characters..
   1.112 +     *  @param dindex     The start index from which converted characters
   1.113 +     *                    are written.
   1.114 +     *  @param len        The maximum number of bytes to convert.
   1.115 +     */
   1.116 +    public static int utf2chars(byte[] src, int sindex,
   1.117 +                                char[] dst, int dindex,
   1.118 +                                int len) {
   1.119 +        int i = sindex;
   1.120 +        int j = dindex;
   1.121 +        int limit = sindex + len;
   1.122 +        while (i < limit) {
   1.123 +            int b = src[i++] & 0xFF;
   1.124 +            if (b >= 0xE0) {
   1.125 +                b = (b & 0x0F) << 12;
   1.126 +                b = b | (src[i++] & 0x3F) << 6;
   1.127 +                b = b | (src[i++] & 0x3F);
   1.128 +            } else if (b >= 0xC0) {
   1.129 +                b = (b & 0x1F) << 6;
   1.130 +                b = b | (src[i++] & 0x3F);
   1.131 +            }
   1.132 +            dst[j++] = (char)b;
   1.133 +        }
   1.134 +        return j;
   1.135 +    }
   1.136 +
   1.137 +    /** Return bytes in Utf8 representation as an array of characters.
   1.138 +     *  @param src        The array holding the bytes.
   1.139 +     *  @param sindex     The start index from which bytes are converted.
   1.140 +     *  @param len        The maximum number of bytes to convert.
   1.141 +     */
   1.142 +    public static char[] utf2chars(byte[] src, int sindex, int len) {
   1.143 +        char[] dst = new char[len];
   1.144 +        int len1 = utf2chars(src, sindex, dst, 0, len);
   1.145 +        char[] result = new char[len1];
   1.146 +        System.arraycopy(dst, 0, result, 0, len1);
   1.147 +        return result;
   1.148 +    }
   1.149 +
   1.150 +    /** Return all bytes of a given array in Utf8 representation
   1.151 +     *  as an array of characters.
   1.152 +     *  @param src        The array holding the bytes.
   1.153 +     */
   1.154 +    public static char[] utf2chars(byte[] src) {
   1.155 +        return utf2chars(src, 0, src.length);
   1.156 +    }
   1.157 +
   1.158 +    /** Return bytes in Utf8 representation as a string.
   1.159 +     *  @param src        The array holding the bytes.
   1.160 +     *  @param sindex     The start index from which bytes are converted.
   1.161 +     *  @param len        The maximum number of bytes to convert.
   1.162 +     */
   1.163 +    public static String utf2string(byte[] src, int sindex, int len) {
   1.164 +        char dst[] = new char[len];
   1.165 +        int len1 = utf2chars(src, sindex, dst, 0, len);
   1.166 +        return new String(dst, 0, len1);
   1.167 +    }
   1.168 +
   1.169 +    /** Return all bytes of a given array in Utf8 representation
   1.170 +     *  as a string.
   1.171 +     *  @param src        The array holding the bytes.
   1.172 +     */
   1.173 +    public static String utf2string(byte[] src) {
   1.174 +        return utf2string(src, 0, src.length);
   1.175 +    }
   1.176 +
   1.177 +    /** Copy characters in source array to bytes in target array,
   1.178 +     *  converting them to Utf8 representation.
   1.179 +     *  The target array must be large enough to hold the result.
   1.180 +     *  returns first index in `dst' past the last copied byte.
   1.181 +     *  @param src        The array holding the characters to convert.
   1.182 +     *  @param sindex     The start index from which characters are converted.
   1.183 +     *  @param dst        The array holding the converted characters..
   1.184 +     *  @param dindex     The start index from which converted bytes
   1.185 +     *                    are written.
   1.186 +     *  @param len        The maximum number of characters to convert.
   1.187 +     */
   1.188 +    public static int chars2utf(char[] src, int sindex,
   1.189 +                                byte[] dst, int dindex,
   1.190 +                                int len) {
   1.191 +        int j = dindex;
   1.192 +        int limit = sindex + len;
   1.193 +        for (int i = sindex; i < limit; i++) {
   1.194 +            char ch = src[i];
   1.195 +            if (1 <= ch && ch <= 0x7F) {
   1.196 +                dst[j++] = (byte)ch;
   1.197 +            } else if (ch <= 0x7FF) {
   1.198 +                dst[j++] = (byte)(0xC0 | (ch >> 6));
   1.199 +                dst[j++] = (byte)(0x80 | (ch & 0x3F));
   1.200 +            } else {
   1.201 +                dst[j++] = (byte)(0xE0 | (ch >> 12));
   1.202 +                dst[j++] = (byte)(0x80 | ((ch >> 6) & 0x3F));
   1.203 +                dst[j++] = (byte)(0x80 | (ch & 0x3F));
   1.204 +            }
   1.205 +        }
   1.206 +        return j;
   1.207 +    }
   1.208 +
   1.209 +    /** Return characters as an array of bytes in Utf8 representation.
   1.210 +     *  @param src        The array holding the characters.
   1.211 +     *  @param sindex     The start index from which characters are converted.
   1.212 +     *  @param len        The maximum number of characters to convert.
   1.213 +     */
   1.214 +    public static byte[] chars2utf(char[] src, int sindex, int len) {
   1.215 +        byte[] dst = new byte[len * 3];
   1.216 +        int len1 = chars2utf(src, sindex, dst, 0, len);
   1.217 +        byte[] result = new byte[len1];
   1.218 +        System.arraycopy(dst, 0, result, 0, len1);
   1.219 +        return result;
   1.220 +    }
   1.221 +
   1.222 +    /** Return all characters in given array as an array of bytes
   1.223 +     *  in Utf8 representation.
   1.224 +     *  @param src        The array holding the characters.
   1.225 +     */
   1.226 +    public static byte[] chars2utf(char[] src) {
   1.227 +        return chars2utf(src, 0, src.length);
   1.228 +    }
   1.229 +
   1.230 +    /** Return string as an array of bytes in in Utf8 representation.
   1.231 +     */
   1.232 +    public static byte[] string2utf(String s) {
   1.233 +        return chars2utf(s.toCharArray());
   1.234 +    }
   1.235 +
   1.236 +    /**
   1.237 +     * Escapes each character in a string that has an escape sequence or
   1.238 +     * is non-printable ASCII.  Leaves non-ASCII characters alone.
   1.239 +     */
   1.240 +    public static String quote(String s) {
   1.241 +        StringBuilder buf = new StringBuilder();
   1.242 +        for (int i = 0; i < s.length(); i++) {
   1.243 +            buf.append(quote(s.charAt(i)));
   1.244 +        }
   1.245 +        return buf.toString();
   1.246 +    }
   1.247 +
   1.248 +    /**
   1.249 +     * Escapes a character if it has an escape sequence or is
   1.250 +     * non-printable ASCII.  Leaves non-ASCII characters alone.
   1.251 +     */
   1.252 +    public static String quote(char ch) {
   1.253 +        switch (ch) {
   1.254 +        case '\b':  return "\\b";
   1.255 +        case '\f':  return "\\f";
   1.256 +        case '\n':  return "\\n";
   1.257 +        case '\r':  return "\\r";
   1.258 +        case '\t':  return "\\t";
   1.259 +        case '\'':  return "\\'";
   1.260 +        case '\"':  return "\\\"";
   1.261 +        case '\\':  return "\\\\";
   1.262 +        default:
   1.263 +            return (isPrintableAscii(ch))
   1.264 +                ? String.valueOf(ch)
   1.265 +                : String.format("\\u%04x", (int) ch);
   1.266 +        }
   1.267 +    }
   1.268 +
   1.269 +    /**
   1.270 +     * Is a character printable ASCII?
   1.271 +     */
   1.272 +    private static boolean isPrintableAscii(char ch) {
   1.273 +        return ch >= ' ' && ch <= '~';
   1.274 +    }
   1.275 +
   1.276 +    /** Escape all unicode characters in string.
   1.277 +     */
   1.278 +    public static String escapeUnicode(String s) {
   1.279 +        int len = s.length();
   1.280 +        int i = 0;
   1.281 +        while (i < len) {
   1.282 +            char ch = s.charAt(i);
   1.283 +            if (ch > 255) {
   1.284 +                StringBuilder buf = new StringBuilder();
   1.285 +                buf.append(s.substring(0, i));
   1.286 +                while (i < len) {
   1.287 +                    ch = s.charAt(i);
   1.288 +                    if (ch > 255) {
   1.289 +                        buf.append("\\u");
   1.290 +                        buf.append(Character.forDigit((ch >> 12) % 16, 16));
   1.291 +                        buf.append(Character.forDigit((ch >>  8) % 16, 16));
   1.292 +                        buf.append(Character.forDigit((ch >>  4) % 16, 16));
   1.293 +                        buf.append(Character.forDigit((ch      ) % 16, 16));
   1.294 +                    } else {
   1.295 +                        buf.append(ch);
   1.296 +                    }
   1.297 +                    i++;
   1.298 +                }
   1.299 +                s = buf.toString();
   1.300 +            } else {
   1.301 +                i++;
   1.302 +            }
   1.303 +        }
   1.304 +        return s;
   1.305 +    }
   1.306 +
   1.307 +/* Conversion routines for qualified name splitting
   1.308 + */
   1.309 +    /** Return the last part of a class name.
   1.310 +     */
   1.311 +    public static Name shortName(Name classname) {
   1.312 +        return classname.subName(
   1.313 +            classname.lastIndexOf((byte)'.') + 1, classname.getByteLength());
   1.314 +    }
   1.315 +
   1.316 +    public static String shortName(String classname) {
   1.317 +        return classname.substring(classname.lastIndexOf('.') + 1);
   1.318 +    }
   1.319 +
   1.320 +    /** Return the package name of a class name, excluding the trailing '.',
   1.321 +     *  "" if not existent.
   1.322 +     */
   1.323 +    public static Name packagePart(Name classname) {
   1.324 +        return classname.subName(0, classname.lastIndexOf((byte)'.'));
   1.325 +    }
   1.326 +
   1.327 +    public static String packagePart(String classname) {
   1.328 +        int lastDot = classname.lastIndexOf('.');
   1.329 +        return (lastDot < 0 ? "" : classname.substring(0, lastDot));
   1.330 +    }
   1.331 +
   1.332 +    public static List<Name> enclosingCandidates(Name name) {
   1.333 +        List<Name> names = List.nil();
   1.334 +        int index;
   1.335 +        while ((index = name.lastIndexOf((byte)'$')) > 0) {
   1.336 +            name = name.subName(0, index);
   1.337 +            names = names.prepend(name);
   1.338 +        }
   1.339 +        return names;
   1.340 +    }
   1.341 +}

mercurial