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: ==================================================================== */
017:
018: package org.apache.poi.poifs.filesystem;
019:
020: import java.io.*;
021:
022: /**
023: * This class provides methods to read a DocumentEntry managed by a
024: * Filesystem instance.
025: *
026: * @author Marc Johnson (mjohnson at apache dot org)
027: */
028:
029: public class DocumentInputStream extends InputStream {
030:
031: // current offset into the Document
032: private int _current_offset;
033:
034: // current marked offset into the Document (used by mark and
035: // reset)
036: private int _marked_offset;
037:
038: // the Document's size
039: private int _document_size;
040:
041: // have we been closed?
042: private boolean _closed;
043:
044: // the actual Document
045: private POIFSDocument _document;
046:
047: // buffer used to read one byte at a time
048: private byte[] _tiny_buffer;
049:
050: // returned by read operations if we're at end of document
051: static private final int EOD = -1;
052:
053: /**
054: * Create an InputStream from the specified DocumentEntry
055: *
056: * @param document the DocumentEntry to be read
057: *
058: * @exception IOException if the DocumentEntry cannot be opened
059: * (like, maybe it has been deleted?)
060: */
061:
062: public DocumentInputStream(final DocumentEntry document)
063: throws IOException {
064: _current_offset = 0;
065: _marked_offset = 0;
066: _document_size = document.getSize();
067: _closed = false;
068: _tiny_buffer = null;
069: if (document instanceof DocumentNode) {
070: _document = ((DocumentNode) document).getDocument();
071: } else {
072: throw new IOException(
073: "Cannot open internal document storage");
074: }
075: }
076:
077: /**
078: * Create an InputStream from the specified Document
079: *
080: * @param document the Document to be read
081: *
082: * @exception IOException if the DocumentEntry cannot be opened
083: * (like, maybe it has been deleted?)
084: */
085:
086: public DocumentInputStream(final POIFSDocument document)
087: throws IOException {
088: _current_offset = 0;
089: _marked_offset = 0;
090: _document_size = document.getSize();
091: _closed = false;
092: _tiny_buffer = null;
093: _document = document;
094: }
095:
096: /**
097: * Returns the number of bytes that can be read (or skipped over)
098: * from this input stream without blocking by the next caller of a
099: * method for this input stream. The next caller might be the same
100: * thread or or another thread.
101: *
102: * @return the number of bytes that can be read from this input
103: * stream without blocking.
104: *
105: * @exception IOException on error (such as the stream has been
106: * closed)
107: */
108:
109: public int available() throws IOException {
110: dieIfClosed();
111: return _document_size - _current_offset;
112: }
113:
114: /**
115: * Closes this input stream and releases any system resources
116: * associated with the stream.
117: *
118: * @exception IOException
119: */
120:
121: public void close() throws IOException {
122: _closed = true;
123: }
124:
125: /**
126: * Marks the current position in this input stream. A subsequent
127: * call to the reset method repositions this stream at the last
128: * marked position so that subsequent reads re-read the same
129: * bytes.
130: * <p>
131: * The readlimit arguments tells this input stream to allow that
132: * many bytes to be read before the mark position gets
133: * invalidated. This implementation, however, does not care.
134: * <p>
135: * The general contract of mark is that, if the method
136: * markSupported returns true, the stream somehow remembers all
137: * the bytes read after the call to mark and stands ready to
138: * supply those same bytes again if and whenever the method reset
139: * is called. However, the stream is not required to remember any
140: * data at all if more than readlimit bytes are read from the
141: * stream before reset is called. But this stream will.
142: *
143: * @param ignoredReadlimit the maximum limit of bytes that can be
144: * read before the mark position becomes
145: * invalid. Ignored by this
146: * implementation.
147: */
148:
149: public void mark(int ignoredReadlimit) {
150: _marked_offset = _current_offset;
151: }
152:
153: /**
154: * Tests if this input stream supports the mark and reset methods.
155: *
156: * @return true
157: */
158:
159: public boolean markSupported() {
160: return true;
161: }
162:
163: /**
164: * Reads the next byte of data from the input stream. The value
165: * byte is returned as an int in the range 0 to 255. If no byte is
166: * available because the end of the stream has been reached, the
167: * value -1 is returned. The definition of this method in
168: * java.io.InputStream allows this method to block, but it won't.
169: *
170: * @return the next byte of data, or -1 if the end of the stream
171: * is reached.
172: *
173: * @exception IOException
174: */
175:
176: public int read() throws IOException {
177: dieIfClosed();
178: if (atEOD()) {
179: return EOD;
180: }
181: if (_tiny_buffer == null) {
182: _tiny_buffer = new byte[1];
183: }
184: _document.read(_tiny_buffer, _current_offset++);
185: return ((int) _tiny_buffer[0]) & 0x000000FF;
186: }
187:
188: /**
189: * Reads some number of bytes from the input stream and stores
190: * them into the buffer array b. The number of bytes actually read
191: * is returned as an integer. The definition of this method in
192: * java.io.InputStream allows this method to block, but it won't.
193: * <p>
194: * If b is null, a NullPointerException is thrown. If the length
195: * of b is zero, then no bytes are read and 0 is returned;
196: * otherwise, there is an attempt to read at least one byte. If no
197: * byte is available because the stream is at end of file, the
198: * value -1 is returned; otherwise, at least one byte is read and
199: * stored into b.
200: * <p>
201: * The first byte read is stored into element b[0], the next one
202: * into b[1], and so on. The number of bytes read is, at most,
203: * equal to the length of b. Let k be the number of bytes actually
204: * read; these bytes will be stored in elements b[0] through
205: * b[k-1], leaving elements b[k] through b[b.length-1] unaffected.
206: * <p>
207: * If the first byte cannot be read for any reason other than end
208: * of file, then an IOException is thrown. In particular, an
209: * IOException is thrown if the input stream has been closed.
210: * <p>
211: * The read(b) method for class InputStream has the same effect as:
212: * <p>
213: * <code>read(b, 0, b.length)</code>
214: *
215: * @param b the buffer into which the data is read.
216: *
217: * @return the total number of bytes read into the buffer, or -1
218: * if there is no more data because the end of the stream
219: * has been reached.
220: *
221: * @exception IOException
222: * @exception NullPointerException
223: */
224:
225: public int read(final byte[] b) throws IOException,
226: NullPointerException {
227: return read(b, 0, b.length);
228: }
229:
230: /**
231: * Reads up to len bytes of data from the input stream into an
232: * array of bytes. An attempt is made to read as many as len
233: * bytes, but a smaller number may be read, possibly zero. The
234: * number of bytes actually read is returned as an integer.
235: * <p>
236: * The definition of this method in java.io.InputStream allows it
237: * to block, but it won't.
238: * <p>
239: * If b is null, a NullPointerException is thrown.
240: * <p>
241: * If off is negative, or len is negative, or off+len is greater
242: * than the length of the array b, then an
243: * IndexOutOfBoundsException is thrown.
244: * <p>
245: * If len is zero, then no bytes are read and 0 is returned;
246: * otherwise, there is an attempt to read at least one byte. If no
247: * byte is available because the stream is at end of file, the
248: * value -1 is returned; otherwise, at least one byte is read and
249: * stored into b.
250: * <p>
251: * The first byte read is stored into element b[off], the next one
252: * into b[off+1], and so on. The number of bytes read is, at most,
253: * equal to len. Let k be the number of bytes actually read; these
254: * bytes will be stored in elements b[off] through b[off+k-1],
255: * leaving elements b[off+k] through b[off+len-1] unaffected.
256: * <p>
257: * In every case, elements b[0] through b[off] and elements
258: * b[off+len] through b[b.length-1] are unaffected.
259: * <p>
260: * If the first byte cannot be read for any reason other than end
261: * of file, then an IOException is thrown. In particular, an
262: * IOException is thrown if the input stream has been closed.
263: *
264: * @param b the buffer into which the data is read.
265: * @param off the start offset in array b at which the data is
266: * written.
267: * @param len the maximum number of bytes to read.
268: *
269: * @return the total number of bytes read into the buffer, or -1
270: * if there is no more data because the end of the stream
271: * has been reached.
272: *
273: * @exception IOException
274: * @exception NullPointerException
275: * @exception IndexOutOfBoundsException
276: */
277:
278: public int read(final byte[] b, final int off, final int len)
279: throws IOException, NullPointerException,
280: IndexOutOfBoundsException {
281: dieIfClosed();
282: if (b == null) {
283: throw new NullPointerException("buffer is null");
284: }
285: if ((off < 0) || (len < 0) || (b.length < (off + len))) {
286: throw new IndexOutOfBoundsException(
287: "can't read past buffer boundaries");
288: }
289: if (len == 0) {
290: return 0;
291: }
292: if (atEOD()) {
293: return EOD;
294: }
295: int limit = Math.min(available(), len);
296:
297: if ((off == 0) && (limit == b.length)) {
298: _document.read(b, _current_offset);
299: } else {
300: byte[] buffer = new byte[limit];
301:
302: _document.read(buffer, _current_offset);
303: System.arraycopy(buffer, 0, b, off, limit);
304: }
305: _current_offset += limit;
306: return limit;
307: }
308:
309: /**
310: * Repositions this stream to the position at the time the mark
311: * method was last called on this input stream.
312: * <p>
313: * The general contract of reset is:
314: * <p>
315: * <ul>
316: * <li>
317: * If the method markSupported returns true, then:
318: * <ul>
319: * <li>
320: * If the method mark has not been called since the
321: * stream was created, or the number of bytes read
322: * from the stream since mark was last called is
323: * larger than the argument to mark at that last
324: * call, then an IOException might be thrown.
325: * </li>
326: * <li>
327: * If such an IOException is not thrown, then the
328: * stream is reset to a state such that all the
329: * bytes read since the most recent call to mark
330: * (or since the start of the file, if mark has not
331: * been called) will be resupplied to subsequent
332: * callers of the read method, followed by any
333: * bytes that otherwise would have been the next
334: * input data as of the time of the call to reset.
335: * </li>
336: * </ul>
337: * </li>
338: * <li>
339: * If the method markSupported returns false, then:
340: * <ul>
341: * <li>
342: * The call to reset may throw an IOException.
343: * </li>
344: * <li>
345: * If an IOException is not thrown, then the
346: * stream is reset to a fixed state that depends
347: * on the particular type of the input and how it
348: * was created. The bytes that will be supplied to
349: * subsequent callers of the read method depend on
350: * the particular type of the input stream.
351: * </li>
352: * </ul>
353: * </li>
354: * </ul>
355: * <p>
356: * All well and good ... this class's markSupported method returns
357: * true and this method does not care whether you've called mark
358: * at all, or whether you've exceeded the number of bytes
359: * specified in the last call to mark. We're basically walking a
360: * byte array ... mark and reset to your heart's content.
361: */
362:
363: public void reset() {
364: _current_offset = _marked_offset;
365: }
366:
367: /**
368: * Skips over and discards n bytes of data from this input
369: * stream. The skip method may, for a variety of reasons, end up
370: * skipping over some smaller number of bytes, possibly 0. This
371: * may result from any of a number of conditions; reaching end of
372: * file before n bytes have been skipped is only one
373: * possibility. The actual number of bytes skipped is returned. If
374: * n is negative, no bytes are skipped.
375: *
376: * @param n the number of bytes to be skipped.
377: *
378: * @return the actual number of bytes skipped.
379: *
380: * @exception IOException
381: */
382:
383: public long skip(final long n) throws IOException {
384: dieIfClosed();
385: if (n < 0) {
386: return 0;
387: }
388: int new_offset = _current_offset + (int) n;
389:
390: if (new_offset < _current_offset) {
391:
392: // wrap around in converting a VERY large long to an int
393: new_offset = _document_size;
394: } else if (new_offset > _document_size) {
395: new_offset = _document_size;
396: }
397: long rval = new_offset - _current_offset;
398:
399: _current_offset = new_offset;
400: return rval;
401: }
402:
403: private void dieIfClosed() throws IOException {
404: if (_closed) {
405: throw new IOException(
406: "cannot perform requested operation on a closed stream");
407: }
408: }
409:
410: private boolean atEOD() {
411: return _current_offset == _document_size;
412: }
413: } // end public class DocumentInputStream
|