duke@1: /* jjg@1770: * Copyright (c) 1999, 2013, Oracle and/or its affiliates. All rights reserved. duke@1: * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. duke@1: * duke@1: * This code is free software; you can redistribute it and/or modify it duke@1: * under the terms of the GNU General Public License version 2 only, as ohair@554: * published by the Free Software Foundation. Oracle designates this duke@1: * particular file as subject to the "Classpath" exception as provided ohair@554: * by Oracle in the LICENSE file that accompanied this code. duke@1: * duke@1: * This code is distributed in the hope that it will be useful, but WITHOUT duke@1: * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or duke@1: * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License duke@1: * version 2 for more details (a copy is included in the LICENSE file that duke@1: * accompanied this code). duke@1: * duke@1: * You should have received a copy of the GNU General Public License version duke@1: * 2 along with this work; if not, write to the Free Software Foundation, duke@1: * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. duke@1: * ohair@554: * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA ohair@554: * or visit www.oracle.com if you need additional information or have any ohair@554: * questions. duke@1: */ duke@1: duke@1: package com.sun.tools.javac.util; duke@1: duke@1: /** Utility class for static conversion methods between numbers duke@1: * and strings in various formats. duke@1: * jjg@1770: *
Note regarding UTF-8. jjg@1770: * The JVMS defines its own version of the UTF-8 format so that it jjg@1770: * contains no zero bytes (modified UTF-8). This is not actually the same jjg@1770: * as Charset.forName("UTF-8"). jjg@1770: * jjg@1770: *
jjg@1770: * See also: jjg@1770: *
This is NOT part of any supported API.
jjg@581: * If you write code that depends on this, you do so at your own risk.
duke@1: * This code and its internal interfaces are subject to change or
duke@1: * deletion without notice.
duke@1: */
duke@1: public class Convert {
duke@1:
duke@1: /** Convert string to integer.
duke@1: */
duke@1: public static int string2int(String s, int radix)
duke@1: throws NumberFormatException {
duke@1: if (radix == 10) {
duke@1: return Integer.parseInt(s, radix);
duke@1: } else {
duke@1: char[] cs = s.toCharArray();
duke@1: int limit = Integer.MAX_VALUE / (radix/2);
duke@1: int n = 0;
duke@1: for (int i = 0; i < cs.length; i++) {
duke@1: int d = Character.digit(cs[i], radix);
duke@1: if (n < 0 ||
duke@1: n > limit ||
duke@1: n * radix > Integer.MAX_VALUE - d)
duke@1: throw new NumberFormatException();
duke@1: n = n * radix + d;
duke@1: }
duke@1: return n;
duke@1: }
duke@1: }
duke@1:
duke@1: /** Convert string to long integer.
duke@1: */
duke@1: public static long string2long(String s, int radix)
duke@1: throws NumberFormatException {
duke@1: if (radix == 10) {
duke@1: return Long.parseLong(s, radix);
duke@1: } else {
duke@1: char[] cs = s.toCharArray();
duke@1: long limit = Long.MAX_VALUE / (radix/2);
duke@1: long n = 0;
duke@1: for (int i = 0; i < cs.length; i++) {
duke@1: int d = Character.digit(cs[i], radix);
duke@1: if (n < 0 ||
duke@1: n > limit ||
duke@1: n * radix > Long.MAX_VALUE - d)
duke@1: throw new NumberFormatException();
duke@1: n = n * radix + d;
duke@1: }
duke@1: return n;
duke@1: }
duke@1: }
duke@1:
duke@1: /* Conversion routines between names, strings, and byte arrays in Utf8 format
duke@1: */
duke@1:
duke@1: /** Convert `len' bytes from utf8 to characters.
duke@1: * Parameters are as in System.arraycopy
duke@1: * Return first index in `dst' past the last copied char.
duke@1: * @param src The array holding the bytes to convert.
duke@1: * @param sindex The start index from which bytes are converted.
duke@1: * @param dst The array holding the converted characters..
duke@1: * @param dindex The start index from which converted characters
duke@1: * are written.
duke@1: * @param len The maximum number of bytes to convert.
duke@1: */
duke@1: public static int utf2chars(byte[] src, int sindex,
duke@1: char[] dst, int dindex,
duke@1: int len) {
duke@1: int i = sindex;
duke@1: int j = dindex;
duke@1: int limit = sindex + len;
duke@1: while (i < limit) {
duke@1: int b = src[i++] & 0xFF;
duke@1: if (b >= 0xE0) {
duke@1: b = (b & 0x0F) << 12;
duke@1: b = b | (src[i++] & 0x3F) << 6;
duke@1: b = b | (src[i++] & 0x3F);
duke@1: } else if (b >= 0xC0) {
duke@1: b = (b & 0x1F) << 6;
duke@1: b = b | (src[i++] & 0x3F);
duke@1: }
duke@1: dst[j++] = (char)b;
duke@1: }
duke@1: return j;
duke@1: }
duke@1:
duke@1: /** Return bytes in Utf8 representation as an array of characters.
duke@1: * @param src The array holding the bytes.
duke@1: * @param sindex The start index from which bytes are converted.
duke@1: * @param len The maximum number of bytes to convert.
duke@1: */
duke@1: public static char[] utf2chars(byte[] src, int sindex, int len) {
duke@1: char[] dst = new char[len];
duke@1: int len1 = utf2chars(src, sindex, dst, 0, len);
duke@1: char[] result = new char[len1];
duke@1: System.arraycopy(dst, 0, result, 0, len1);
duke@1: return result;
duke@1: }
duke@1:
duke@1: /** Return all bytes of a given array in Utf8 representation
duke@1: * as an array of characters.
duke@1: * @param src The array holding the bytes.
duke@1: */
duke@1: public static char[] utf2chars(byte[] src) {
duke@1: return utf2chars(src, 0, src.length);
duke@1: }
duke@1:
duke@1: /** Return bytes in Utf8 representation as a string.
duke@1: * @param src The array holding the bytes.
duke@1: * @param sindex The start index from which bytes are converted.
duke@1: * @param len The maximum number of bytes to convert.
duke@1: */
duke@1: public static String utf2string(byte[] src, int sindex, int len) {
duke@1: char dst[] = new char[len];
duke@1: int len1 = utf2chars(src, sindex, dst, 0, len);
duke@1: return new String(dst, 0, len1);
duke@1: }
duke@1:
duke@1: /** Return all bytes of a given array in Utf8 representation
duke@1: * as a string.
duke@1: * @param src The array holding the bytes.
duke@1: */
duke@1: public static String utf2string(byte[] src) {
duke@1: return utf2string(src, 0, src.length);
duke@1: }
duke@1:
duke@1: /** Copy characters in source array to bytes in target array,
duke@1: * converting them to Utf8 representation.
duke@1: * The target array must be large enough to hold the result.
duke@1: * returns first index in `dst' past the last copied byte.
duke@1: * @param src The array holding the characters to convert.
duke@1: * @param sindex The start index from which characters are converted.
duke@1: * @param dst The array holding the converted characters..
duke@1: * @param dindex The start index from which converted bytes
duke@1: * are written.
duke@1: * @param len The maximum number of characters to convert.
duke@1: */
duke@1: public static int chars2utf(char[] src, int sindex,
duke@1: byte[] dst, int dindex,
duke@1: int len) {
duke@1: int j = dindex;
duke@1: int limit = sindex + len;
duke@1: for (int i = sindex; i < limit; i++) {
duke@1: char ch = src[i];
duke@1: if (1 <= ch && ch <= 0x7F) {
duke@1: dst[j++] = (byte)ch;
duke@1: } else if (ch <= 0x7FF) {
duke@1: dst[j++] = (byte)(0xC0 | (ch >> 6));
duke@1: dst[j++] = (byte)(0x80 | (ch & 0x3F));
duke@1: } else {
duke@1: dst[j++] = (byte)(0xE0 | (ch >> 12));
duke@1: dst[j++] = (byte)(0x80 | ((ch >> 6) & 0x3F));
duke@1: dst[j++] = (byte)(0x80 | (ch & 0x3F));
duke@1: }
duke@1: }
duke@1: return j;
duke@1: }
duke@1:
duke@1: /** Return characters as an array of bytes in Utf8 representation.
duke@1: * @param src The array holding the characters.
duke@1: * @param sindex The start index from which characters are converted.
duke@1: * @param len The maximum number of characters to convert.
duke@1: */
duke@1: public static byte[] chars2utf(char[] src, int sindex, int len) {
duke@1: byte[] dst = new byte[len * 3];
duke@1: int len1 = chars2utf(src, sindex, dst, 0, len);
duke@1: byte[] result = new byte[len1];
duke@1: System.arraycopy(dst, 0, result, 0, len1);
duke@1: return result;
duke@1: }
duke@1:
duke@1: /** Return all characters in given array as an array of bytes
duke@1: * in Utf8 representation.
duke@1: * @param src The array holding the characters.
duke@1: */
duke@1: public static byte[] chars2utf(char[] src) {
duke@1: return chars2utf(src, 0, src.length);
duke@1: }
duke@1:
duke@1: /** Return string as an array of bytes in in Utf8 representation.
duke@1: */
duke@1: public static byte[] string2utf(String s) {
duke@1: return chars2utf(s.toCharArray());
duke@1: }
duke@1:
duke@1: /**
duke@1: * Escapes each character in a string that has an escape sequence or
duke@1: * is non-printable ASCII. Leaves non-ASCII characters alone.
duke@1: */
duke@1: public static String quote(String s) {
duke@1: StringBuilder buf = new StringBuilder();
duke@1: for (int i = 0; i < s.length(); i++) {
duke@1: buf.append(quote(s.charAt(i)));
duke@1: }
duke@1: return buf.toString();
duke@1: }
duke@1:
duke@1: /**
duke@1: * Escapes a character if it has an escape sequence or is
duke@1: * non-printable ASCII. Leaves non-ASCII characters alone.
duke@1: */
duke@1: public static String quote(char ch) {
duke@1: switch (ch) {
duke@1: case '\b': return "\\b";
duke@1: case '\f': return "\\f";
duke@1: case '\n': return "\\n";
duke@1: case '\r': return "\\r";
duke@1: case '\t': return "\\t";
duke@1: case '\'': return "\\'";
duke@1: case '\"': return "\\\"";
duke@1: case '\\': return "\\\\";
duke@1: default:
darcy@414: return (isPrintableAscii(ch))
duke@1: ? String.valueOf(ch)
darcy@414: : String.format("\\u%04x", (int) ch);
duke@1: }
duke@1: }
duke@1:
duke@1: /**
duke@1: * Is a character printable ASCII?
duke@1: */
duke@1: private static boolean isPrintableAscii(char ch) {
duke@1: return ch >= ' ' && ch <= '~';
duke@1: }
duke@1:
duke@1: /** Escape all unicode characters in string.
duke@1: */
duke@1: public static String escapeUnicode(String s) {
duke@1: int len = s.length();
duke@1: int i = 0;
duke@1: while (i < len) {
duke@1: char ch = s.charAt(i);
duke@1: if (ch > 255) {
jjg@1362: StringBuilder buf = new StringBuilder();
duke@1: buf.append(s.substring(0, i));
duke@1: while (i < len) {
duke@1: ch = s.charAt(i);
duke@1: if (ch > 255) {
duke@1: buf.append("\\u");
duke@1: buf.append(Character.forDigit((ch >> 12) % 16, 16));
duke@1: buf.append(Character.forDigit((ch >> 8) % 16, 16));
duke@1: buf.append(Character.forDigit((ch >> 4) % 16, 16));
duke@1: buf.append(Character.forDigit((ch ) % 16, 16));
duke@1: } else {
duke@1: buf.append(ch);
duke@1: }
duke@1: i++;
duke@1: }
duke@1: s = buf.toString();
duke@1: } else {
duke@1: i++;
duke@1: }
duke@1: }
duke@1: return s;
duke@1: }
duke@1:
duke@1: /* Conversion routines for qualified name splitting
duke@1: */
duke@1: /** Return the last part of a class name.
duke@1: */
duke@1: public static Name shortName(Name classname) {
duke@1: return classname.subName(
jjg@113: classname.lastIndexOf((byte)'.') + 1, classname.getByteLength());
duke@1: }
duke@1:
duke@1: public static String shortName(String classname) {
duke@1: return classname.substring(classname.lastIndexOf('.') + 1);
duke@1: }
duke@1:
duke@1: /** Return the package name of a class name, excluding the trailing '.',
duke@1: * "" if not existent.
duke@1: */
duke@1: public static Name packagePart(Name classname) {
duke@1: return classname.subName(0, classname.lastIndexOf((byte)'.'));
duke@1: }
duke@1:
duke@1: public static String packagePart(String classname) {
duke@1: int lastDot = classname.lastIndexOf('.');
duke@1: return (lastDot < 0 ? "" : classname.substring(0, lastDot));
duke@1: }
duke@1:
duke@1: public static List