001/*
002 * Licensed to the Apache Software Foundation (ASF) under one or more
003 * contributor license agreements.  See the NOTICE file distributed with
004 * this work for additional information regarding copyright ownership.
005 * The ASF licenses this file to You under the Apache License, Version 2.0
006 * (the "License"); you may not use this file except in compliance with
007 * the License.  You may obtain a copy of the License at
008 *
009 *      http://www.apache.org/licenses/LICENSE-2.0
010 *
011 * Unless required by applicable law or agreed to in writing, software
012 * distributed under the License is distributed on an "AS IS" BASIS,
013 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
014 * See the License for the specific language governing permissions and
015 * limitations under the License.
016 */
017package org.apache.commons.io.input;
018
019import static org.apache.commons.io.IOUtils.EOF;
020
021import java.io.Reader;
022import java.io.Serializable;
023import java.util.Objects;
024
025/**
026 * {@link Reader} implementation that can read from String, StringBuffer,
027 * StringBuilder or CharBuffer.
028 * <p>
029 * <strong>Note:</strong> Supports {@link #mark(int)} and {@link #reset()}.
030 * </p>
031 * <h2>Deprecating Serialization</h2>
032 * <p>
033 * <em>Serialization is deprecated and will be removed in 3.0.</em>
034 * </p>
035 *
036 * @since 1.4
037 */
038public class CharSequenceReader extends Reader implements Serializable {
039
040    private static final long serialVersionUID = 3724187752191401220L;
041    private final CharSequence charSequence;
042    private int idx;
043    private int mark;
044
045    /**
046     * The start index in the character sequence, inclusive.
047     * <p>
048     * When de-serializing a CharSequenceReader that was serialized before
049     * this fields was added, this field will be initialized to 0, which
050     * gives the same behavior as before: start reading from the start.
051     * </p>
052     *
053     * @see #start()
054     * @since 2.7
055     */
056    private final int start;
057
058    /**
059     * The end index in the character sequence, exclusive.
060     * <p>
061     * When de-serializing a CharSequenceReader that was serialized before
062     * this fields was added, this field will be initialized to {@code null},
063     * which gives the same behavior as before: stop reading at the
064     * CharSequence's length.
065     * If this field was an int instead, it would be initialized to 0 when the
066     * CharSequenceReader is de-serialized, causing it to not return any
067     * characters at all.
068     * </p>
069     *
070     * @see #end()
071     * @since 2.7
072     */
073    private final Integer end;
074
075    /**
076     * Constructs a new instance with the specified character sequence.
077     *
078     * @param charSequence The character sequence, may be {@code null}
079     */
080    public CharSequenceReader(final CharSequence charSequence) {
081        this(charSequence, 0);
082    }
083
084    /**
085     * Constructs a new instance with a portion of the specified character sequence.
086     * <p>
087     * The start index is not strictly enforced to be within the bounds of the
088     * character sequence. This allows the character sequence to grow or shrink
089     * in size without risking any {@link IndexOutOfBoundsException} to be thrown.
090     * Instead, if the character sequence grows smaller than the start index, this
091     * instance will act as if all characters have been read.
092     * </p>
093     *
094     * @param charSequence The character sequence, may be {@code null}
095     * @param start The start index in the character sequence, inclusive
096     * @throws IllegalArgumentException if the start index is negative
097     * @since 2.7
098     */
099    public CharSequenceReader(final CharSequence charSequence, final int start) {
100        this(charSequence, start, Integer.MAX_VALUE);
101    }
102
103    /**
104     * Constructs a new instance with a portion of the specified character sequence.
105     * <p>
106     * The start and end indexes are not strictly enforced to be within the bounds
107     * of the character sequence. This allows the character sequence to grow or shrink
108     * in size without risking any {@link IndexOutOfBoundsException} to be thrown.
109     * Instead, if the character sequence grows smaller than the start index, this
110     * instance will act as if all characters have been read; if the character sequence
111     * grows smaller than the end, this instance will use the actual character sequence
112     * length.
113     * </p>
114     *
115     * @param charSequence The character sequence, may be {@code null}
116     * @param start The start index in the character sequence, inclusive
117     * @param end The end index in the character sequence, exclusive
118     * @throws IllegalArgumentException if the start index is negative, or if the end index is smaller than the start index
119     * @since 2.7
120     */
121    public CharSequenceReader(final CharSequence charSequence, final int start, final int end) {
122        if (start < 0) {
123            throw new IllegalArgumentException("Start index is less than zero: " + start);
124        }
125        if (end < start) {
126            throw new IllegalArgumentException("End index is less than start " + start + ": " + end);
127        }
128        // Don't check the start and end indexes against the CharSequence,
129        // to let it grow and shrink without breaking existing behavior.
130
131        this.charSequence = charSequence != null ? charSequence : "";
132        this.start = start;
133        this.end = end;
134
135        this.idx = start;
136        this.mark = start;
137    }
138
139    /**
140     * Close resets the file back to the start and removes any marked position.
141     */
142    @Override
143    public void close() {
144        idx = start;
145        mark = start;
146    }
147
148    /**
149     * Returns the index in the character sequence to end reading at, taking into account its length.
150     *
151     * @return The end index in the character sequence (exclusive).
152     */
153    private int end() {
154        /*
155         * end == null for de-serialized instances that were serialized before start and end were added.
156         * Use Integer.MAX_VALUE to get the same behavior as before - use the entire CharSequence.
157         */
158        return Math.min(charSequence.length(), end == null ? Integer.MAX_VALUE : end);
159    }
160
161    /**
162     * Mark the current position.
163     *
164     * @param readAheadLimit ignored
165     */
166    @Override
167    public void mark(final int readAheadLimit) {
168        mark = idx;
169    }
170
171    /**
172     * Mark is supported (returns true).
173     *
174     * @return {@code true}
175     */
176    @Override
177    public boolean markSupported() {
178        return true;
179    }
180
181    /**
182     * Read a single character.
183     *
184     * @return the next character from the character sequence
185     * or -1 if the end has been reached.
186     */
187    @Override
188    public int read() {
189        if (idx >= end()) {
190            return EOF;
191        }
192        return charSequence.charAt(idx++);
193    }
194
195    /**
196     * Read the specified number of characters into the array.
197     *
198     * @param array The array to store the characters in
199     * @param offset The starting position in the array to store
200     * @param length The maximum number of characters to read
201     * @return The number of characters read or -1 if there are
202     * no more
203     */
204    @Override
205    public int read(final char[] array, final int offset, final int length) {
206        if (idx >= end()) {
207            return EOF;
208        }
209        Objects.requireNonNull(array, "array");
210        if (length < 0 || offset < 0 || offset + length > array.length) {
211            throw new IndexOutOfBoundsException("Array Size=" + array.length +
212                    ", offset=" + offset + ", length=" + length);
213        }
214
215        if (charSequence instanceof String) {
216            final int count = Math.min(length, end() - idx);
217            ((String) charSequence).getChars(idx, idx + count, array, offset);
218            idx += count;
219            return count;
220        }
221        if (charSequence instanceof StringBuilder) {
222            final int count = Math.min(length, end() - idx);
223            ((StringBuilder) charSequence).getChars(idx, idx + count, array, offset);
224            idx += count;
225            return count;
226        }
227        if (charSequence instanceof StringBuffer) {
228            final int count = Math.min(length, end() - idx);
229            ((StringBuffer) charSequence).getChars(idx, idx + count, array, offset);
230            idx += count;
231            return count;
232        }
233
234        int count = 0;
235        for (int i = 0; i < length; i++) {
236            final int c = read();
237            if (c == EOF) {
238                return count;
239            }
240            array[offset + i] = (char)c;
241            count++;
242        }
243        return count;
244    }
245
246    /**
247     * Tells whether this stream is ready to be read.
248     *
249     * @return {@code true} if more characters from the character sequence are available, or {@code false} otherwise.
250     */
251    @Override
252    public boolean ready() {
253        return idx < end();
254    }
255
256    /**
257     * Reset the reader to the last marked position (or the beginning if
258     * mark has not been called).
259     */
260    @Override
261    public void reset() {
262        idx = mark;
263    }
264
265    /**
266     * Skip the specified number of characters.
267     *
268     * @param n The number of characters to skip
269     * @return The actual number of characters skipped
270     */
271    @Override
272    public long skip(final long n) {
273        if (n < 0) {
274            throw new IllegalArgumentException("Number of characters to skip is less than zero: " + n);
275        }
276        if (idx >= end()) {
277            return 0;
278        }
279        final int dest = (int) Math.min(end(), idx + n);
280        final int count = dest - idx;
281        idx = dest;
282        return count;
283    }
284
285    /**
286     * Returns the index in the character sequence to start reading from, taking into account its length.
287     *
288     * @return The start index in the character sequence (inclusive).
289     */
290    private int start() {
291        return Math.min(charSequence.length(), start);
292    }
293
294    /**
295     * Return a String representation of the underlying
296     * character sequence.
297     *
298     * @return The contents of the character sequence
299     */
300    @Override
301    public String toString() {
302        final CharSequence subSequence = charSequence.subSequence(start(), end());
303        return subSequence.toString();
304    }
305}