/*

 * Copyright 1995-2006 Sun Microsystems, Inc.  All Rights Reserved.

 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.

 *

 * This code is free software; you can redistribute it and/or modify it

 * under the terms of the GNU General Public License version 2 only, as

 * published by the Free Software Foundation.  Sun designates this

 * particular file as subject to the "Classpath" exception as provided

 * by Sun in the LICENSE file that accompanied this code.

 *

 * This code is distributed in the hope that it will be useful, but WITHOUT

 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or

 * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License

 * version 2 for more details (a copy is included in the LICENSE file that

 * accompanied this code).

 *

 * You should have received a copy of the GNU General Public License version

 * 2 along with this work; if not, write to the Free Software Foundation,

 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.

 *

 * Please contact Sun Microsystems, Inc., 4150 Network Circle, Santa Clara,

 * CA 95054 USA or visit www.sun.com if you need additional information or

 * have any questions.

 */

package java.util;

import java.io.IOException;

import java.io.PrintStream;

import java.io.PrintWriter;

import java.io.InputStream;

import java.io.OutputStream;

import java.io.Reader;

import java.io.Writer;

import java.io.OutputStreamWriter;

import java.io.BufferedWriter;

/**

 * The <code>Properties</code> class represents a persistent set of

 * properties. The <code>Properties</code> can be saved to a stream

 * or loaded from a stream. Each key and its corresponding value in

 * the property list is a string.

 * <p>

 * A property list can contain another property list as its

 * "defaults"; this second property list is searched if

 * the property key is not found in the original property list.

 * <p>

 * Because <code>Properties</code> inherits from <code>Hashtable</code>, the

 * <code>put</code> and <code>putAll</code> methods can be applied to a

 * <code>Properties</code> object.  Their use is strongly discouraged as they

 * allow the caller to insert entries whose keys or values are not

 * <code>Strings</code>.  The <code>setProperty</code> method should be used

 * instead.  If the <code>store</code> or <code>save</code> method is called

 * on a "compromised" <code>Properties</code> object that contains a

 * non-<code>String</code> key or value, the call will fail. Similarly,

 * the call to the <code>propertyNames</code> or <code>list</code> method

 * will fail if it is called on a "compromised" <code>Properties</code>

 * object that contains a non-<code>String</code> key.

 *

 * <p>

 * The {@link #load(java.io.Reader) load(Reader)} <tt>/</tt>

 * {@link #store(java.io.Writer, java.lang.String) store(Writer, String)}

 * methods load and store properties from and to a character based stream

 * in a simple line-oriented format specified below.

 *

 * The {@link #load(java.io.InputStream) load(InputStream)} <tt>/</tt>

 * {@link #store(java.io.OutputStream, java.lang.String) store(OutputStream, String)}

 * methods work the same way as the load(Reader)/store(Writer, String) pair, except

 * the input/output stream is encoded in ISO 8859-1 character encoding.

 * Characters that cannot be directly represented in this encoding can be written using

 * <a href="http://java.sun.com/docs/books/jls/third_edition/html/lexical.html#3.3">Unicode escapes</a>

 * ; only a single 'u' character is allowed in an escape

 * sequence. The native2ascii tool can be used to convert property files to and

 * from other character encodings.

 *

 * <p> The {@link #loadFromXML(InputStream)} and {@link

 * #storeToXML(OutputStream, String, String)} methods load and store properties

 * in a simple XML format.  By default the UTF-8 character encoding is used,

 * however a specific encoding may be specified if required.  An XML properties

 * document has the following DOCTYPE declaration:

 *

 * <pre>

 * <!DOCTYPE properties SYSTEM "http://java.sun.com/dtd/properties.dtd">

 * </pre>

 * Note that the system URI (http://java.sun.com/dtd/properties.dtd) is

 * <i>not</i> accessed when exporting or importing properties; it merely

 * serves as a string to uniquely identify the DTD, which is:

 * <pre>

 *    <?xml version="1.0" encoding="UTF-8"?>

 *

 *    <!-- DTD for properties -->

 *

 *    <!ELEMENT properties ( comment?, entry* ) >

 *

 *    <!ATTLIST properties version CDATA #FIXED "1.0">

 *

 *    <!ELEMENT comment (#PCDATA) >

 *

 *    <!ELEMENT entry (#PCDATA) >

 *

 *    <!ATTLIST entry key CDATA #REQUIRED>

 * </pre>

 *

 * @see <a href="../../../technotes/tools/solaris/native2ascii.html">native2ascii tool for Solaris</a>

 * @see <a href="../../../technotes/tools/windows/native2ascii.html">native2ascii tool for Windows</a>

 *

 * <p>This class is thread-safe: multiple threads can share a single

 * <tt>Properties</tt> object without the need for external synchronization.

 *

 * @author  Arthur van Hoff

 * @author  Michael McCloskey

 * @author  Xueming Shen

 * @since   JDK1.0

 */

public

class Properties extends Hashtable<Object,Object> {

    /**

     * use serialVersionUID from JDK 1.1.X for interoperability

     */

     private static final long serialVersionUID = 4112578634029874840L;

    /**

     * A property list that contains default values for any keys not

     * found in this property list.

     *

     * @serial

     */

    protected Properties defaults;

    /**

     * Creates an empty property list with no default values.

     */

    public Properties() {

        this(null);

    }

    /**

     * Creates an empty property list with the specified defaults.

     *

     * @param   defaults   the defaults.

     */

    public Properties(Properties defaults) {

        this.defaults = defaults;

    }

    /**

     * Calls the <tt>Hashtable</tt> method <code>put</code>. Provided for

     * parallelism with the <tt>getProperty</tt> method. Enforces use of

     * strings for property keys and values. The value returned is the

     * result of the <tt>Hashtable</tt> call to <code>put</code>.

     *

     * @param key the key to be placed into this property list.

     * @param value the value corresponding to <tt>key</tt>.

     * @return     the previous value of the specified key in this property

     *             list, or <code>null</code> if it did not have one.

     * @see #getProperty

     * @since    1.2

     */

    public synchronized Object setProperty(String key, String value) {

        return put(key, value);

    }

    /**

     * Reads a property list (key and element pairs) from the input

     * character stream in a simple line-oriented format.

     * <p>

     * Properties are processed in terms of lines. There are two

     * kinds of line, <i>natural lines</i> and <i>logical lines</i>.

     * A natural line is defined as a line of

     * characters that is terminated either by a set of line terminator

     * characters (<code>\n</code> or <code>\r</code> or <code>\r\n</code>)

     * or by the end of the stream. A natural line may be either a blank line,

     * a comment line, or hold all or some of a key-element pair. A logical

     * line holds all the data of a key-element pair, which may be spread

     * out across several adjacent natural lines by escaping

     * the line terminator sequence with a backslash character

     * <code>\</code>.  Note that a comment line cannot be extended

     * in this manner; every natural line that is a comment must have

     * its own comment indicator, as described below. Lines are read from

     * input until the end of the stream is reached.

     *

     * <p>

     * A natural line that contains only white space characters is

     * considered blank and is ignored.  A comment line has an ASCII

     * <code>'#'</code> or <code>'!'</code> as its first non-white

     * space character; comment lines are also ignored and do not

     * encode key-element information.  In addition to line

     * terminators, this format considers the characters space

     * (<code>' '</code>, <code>'&#92;u0020'</code>), tab

     * (<code>'\t'</code>, <code>'&#92;u0009'</code>), and form feed

     * (<code>'\f'</code>, <code>'&#92;u000C'</code>) to be white

     * space.

     *

     * <p>

     * If a logical line is spread across several natural lines, the

     * backslash escaping the line terminator sequence, the line

     * terminator sequence, and any white space at the start of the

     * following line have no affect on the key or element values.

     * The remainder of the discussion of key and element parsing

     * (when loading) will assume all the characters constituting

     * the key and element appear on a single natural line after

     * line continuation characters have been removed.  Note that

     * it is <i>not</i> sufficient to only examine the character

     * preceding a line terminator sequence to decide if the line

     * terminator is escaped; there must be an odd number of

     * contiguous backslashes for the line terminator to be escaped.

     * Since the input is processed from left to right, a

     * non-zero even number of 2<i>n</i> contiguous backslashes

     * before a line terminator (or elsewhere) encodes <i>n</i>

     * backslashes after escape processing.

     *

     * <p>

     * The key contains all of the characters in the line starting

     * with the first non-white space character and up to, but not

     * including, the first unescaped <code>'='</code>,

     * <code>':'</code>, or white space character other than a line

     * terminator. All of these key termination characters may be

     * included in the key by escaping them with a preceding backslash

     * character; for example,<p>

     *

     * <code>\:\=</code><p>

     *

     * would be the two-character key <code>":="</code>.  Line

     * terminator characters can be included using <code>\r</code> and

     * <code>\n</code> escape sequences.  Any white space after the

     * key is skipped; if the first non-white space character after

     * the key is <code>'='</code> or <code>':'</code>, then it is

     * ignored and any white space characters after it are also

     * skipped.  All remaining characters on the line become part of

     * the associated element string; if there are no remaining

     * characters, the element is the empty string

     * <code>&quot;&quot;</code>.  Once the raw character sequences

     * constituting the key and element are identified, escape

     * processing is performed as described above.

     *

     * <p>

     * As an example, each of the following three lines specifies the key

     * <code>"Truth"</code> and the associated element value

     * <code>"Beauty"</code>:

     * <p>

     * <pre>

     * Truth = Beauty

     *  Truth:Beauty

     * Truth                    :Beauty

     * </pre>

     * As another example, the following three lines specify a single

     * property:

     * <p>

     * <pre>

     * fruits                           apple, banana, pear, \

     *                                  cantaloupe, watermelon, \

     *                                  kiwi, mango

     * </pre>

     * The key is <code>"fruits"</code> and the associated element is:

     * <p>

     * <pre>"apple, banana, pear, cantaloupe, watermelon, kiwi, mango"</pre>

     * Note that a space appears before each <code>\</code> so that a space

     * will appear after each comma in the final result; the <code>\</code>,

     * line terminator, and leading white space on the continuation line are

     * merely discarded and are <i>not</i> replaced by one or more other

     * characters.

     * <p>

     * As a third example, the line:

     * <p>

     * <pre>cheeses

     * </pre>

     * specifies that the key is <code>"cheeses"</code> and the associated

     * element is the empty string <code>""</code>.<p>

     * <p>

     *

     * <a name="unicodeescapes"></a>

     * Characters in keys and elements can be represented in escape

     * sequences similar to those used for character and string literals

     * (see <a

     * href="http://java.sun.com/docs/books/jls/third_edition/html/lexical.html#3.3">&sect;3.3</a>

     * and <a

     * href="http://java.sun.com/docs/books/jls/third_edition/html/lexical.html#3.10.6">&sect;3.10.6</a>

     * of the <i>Java Language Specification</i>).

     *

     * The differences from the character escape sequences and Unicode

     * escapes used for characters and strings are:

     *

     * <ul>

     * <li> Octal escapes are not recognized.

     *

     * <li> The character sequence <code>\b</code> does <i>not</i>

     * represent a backspace character.

     *

     * <li> The method does not treat a backslash character,

     * <code>\</code>, before a non-valid escape character as an

     * error; the backslash is silently dropped.  For example, in a

     * Java string the sequence <code>"\z"</code> would cause a

     * compile time error.  In contrast, this method silently drops

     * the backslash.  Therefore, this method treats the two character

     * sequence <code>"\b"</code> as equivalent to the single

     * character <code>'b'</code>.

     *

     * <li> Escapes are not necessary for single and double quotes;

     * however, by the rule above, single and double quote characters

     * preceded by a backslash still yield single and double quote

     * characters, respectively.

     *

     * <li> Only a single 'u' character is allowed in a Uniocde escape

     * sequence.

     *

     * </ul>

     * <p>

     * The specified stream remains open after this method returns.

     *

     * @param   reader   the input character stream.

     * @throws  IOException  if an error occurred when reading from the

     *          input stream.

     * @throws  IllegalArgumentException if a malformed Unicode escape

     *          appears in the input.

     * @since   1.6

     */

    public synchronized void load(Reader reader) throws IOException {

        load0(new LineReader(reader));

    }

    /**

     * Reads a property list (key and element pairs) from the input

     * byte stream. The input stream is in a simple line-oriented

     * format as specified in

     * {@link #load(java.io.Reader) load(Reader)} and is assumed to use

     * the ISO 8859-1 character encoding; that is each byte is one Latin1

     * character. Characters not in Latin1, and certain special characters,

     * are represented in keys and elements using

     * <a href="http://java.sun.com/docs/books/jls/third_edition/html/lexical.html#3.3">Unicode escapes</a>.

     * <p>

     * The specified stream remains open after this method returns.

     *

     * @param      inStream   the input stream.

     * @exception  IOException  if an error occurred when reading from the

     *             input stream.

     * @throws     IllegalArgumentException if the input stream contains a

     *             malformed Unicode escape sequence.

     * @since 1.2

     */

    public synchronized void load(InputStream inStream) throws IOException {

        load0(new LineReader(inStream));

    }

    private void load0 (LineReader lr) throws IOException {

        char[] convtBuf = new char[1024];

        int limit;

        int keyLen;

        int valueStart;

        char c;

        boolean hasSep;

        boolean precedingBackslash;

        while ((limit = lr.readLine()) >= 0) {

            c = 0;

            keyLen = 0;

            valueStart = limit;

            hasSep = false;

            //System.out.println("line=<" + new String(lineBuf, 0, limit) + ">");

            precedingBackslash = false;

            while (keyLen < limit) {

                c = lr.lineBuf[keyLen];

                //need check if escaped.

                if ((c == '=' ||  c == ':') && !precedingBackslash) {

                    valueStart = keyLen + 1;

                    hasSep = true;

                    break;

                } else if ((c == ' ' || c == '\t' ||  c == '\f') && !precedingBackslash) {

                    valueStart = keyLen + 1;

                    break;

                }

                if (c == '\\') {

                    precedingBackslash = !precedingBackslash;

                } else {

                    precedingBackslash = false;

                }

                keyLen++;

            }

            while (valueStart < limit) {

                c = lr.lineBuf[valueStart];

                if (c != ' ' && c != '\t' &&  c != '\f') {

                    if (!hasSep && (c == '=' ||  c == ':')) {

                        hasSep = true;

                    } else {

                        break;

                    }

                }

                valueStart++;

            }

            String key = loadConvert(lr.lineBuf, 0, keyLen, convtBuf);

            String value = loadConvert(lr.lineBuf, valueStart, limit - valueStart, convtBuf);

            put(key, value);

        }

    }

    /* Read in a "logical line" from an InputStream/Reader, skip all comment

     * and blank lines and filter out those leading whitespace characters

     * (\u0020, \u0009 and \u000c) from the beginning of a "natural line".

     * Method returns the char length of the "logical line" and stores

     * the line in "lineBuf".

     */

    class LineReader {

        public LineReader(InputStream inStream) {

            this.inStream = inStream;

            inByteBuf = new byte[8192];

        }

        public LineReader(Reader reader) {

            this.reader = reader;

            inCharBuf = new char[8192];

        }

        byte[] inByteBuf;

        char[] inCharBuf;

        char[] lineBuf = new char[1024];

        int inLimit = 0;

        int inOff = 0;

        InputStream inStream;

        Reader reader;

        int readLine() throws IOException {

            int len = 0;

            char c = 0;

            boolean skipWhiteSpace = true;

            boolean isCommentLine = false;

            boolean isNewLine = true;

            boolean appendedLineBegin = false;

            boolean precedingBackslash = false;

            boolean skipLF = false;

            while (true) {

                if (inOff >= inLimit) {

                    inLimit = (inStream==null)?reader.read(inCharBuf)

                                              :inStream.read(inByteBuf);

                    inOff = 0;

                    if (inLimit <= 0) {

                        if (len == 0 || isCommentLine) {

                            return -1;

                        }

                        return len;

                    }

                }

                if (inStream != null) {

                    //The line below is equivalent to calling a

                    //ISO8859-1 decoder.

                    c = (char) (0xff & inByteBuf[inOff++]);

                } else {

                    c = inCharBuf[inOff++];

                }

                if (skipLF) {

                    skipLF = false;

                    if (c == '\n') {

                        continue;

                    }

                }

                if (skipWhiteSpace) {

                    if (c == ' ' || c == '\t' || c == '\f') {

                        continue;

                    }

                    if (!appendedLineBegin && (c == '\r' || c == '\n')) {

                        continue;

                    }

                    skipWhiteSpace = false;

                    appendedLineBegin = false;

                }

                if (isNewLine) {

                    isNewLine = false;

                    if (c == '#' || c == '!') {

                        isCommentLine = true;

                        continue;

                    }

                }

                if (c != '\n' && c != '\r') {

                    lineBuf[len++] = c;

                    if (len == lineBuf.length) {

                        int newLength = lineBuf.length * 2;

                        if (newLength < 0) {

                            newLength = Integer.MAX_VALUE;

                        }

                        char[] buf = new char[newLength];

                        System.arraycopy(lineBuf, 0, buf, 0, lineBuf.length);

                        lineBuf = buf;

                    }

                    //flip the preceding backslash flag

                    if (c == '\\') {

                        precedingBackslash = !precedingBackslash;

                    } else {

                        precedingBackslash = false;

                    }

                }

                else {

                    // reached EOL

                    if (isCommentLine || len == 0) {

                        isCommentLine = false;

                        isNewLine = true;

                        skipWhiteSpace = true;

                        len = 0;

                        continue;

                    }

                    if (inOff >= inLimit) {

                        inLimit = (inStream==null)

                                  ?reader.read(inCharBuf)

                                  :inStream.read(inByteBuf);

                        inOff = 0;

                        if (inLimit <= 0) {

                            return len;

                        }

                    }

                    if (precedingBackslash) {

                        len -= 1;

                        //skip the leading whitespace characters in following line

                        skipWhiteSpace = true;

                        appendedLineBegin = true;

                        precedingBackslash = false;

                        if (c == '\r') {

                            skipLF = true;

                        }

                    } else {

                        return len;

                    }

                }

            }

        }

    }