The UTF-8 {@link java.nio.charset.Charset charset} is used to + * decode the entry names. + * + * @param in the actual input stream + */ + public ZipInputStream(InputStream in) { +// this(in, "UTF-8"); + super(new PushbackInputStream(in, 512), new Inflater(true), 512); + //usesDefaultInflater = true; + if(in == null) { + throw new NullPointerException("in is null"); + } + } + + /** + * Creates a new ZIP input stream. + * + * @param in the actual input stream + * + * @param charset + * The {@linkplain java.nio.charset.Charset charset} to be + * used to decode the ZIP entry name (ignored if the + * language + * encoding bit of the ZIP entry's general purpose bit + * flag is set). + * + * @since 1.7 + * + public ZipInputStream(InputStream in, Charset charset) { + super(new PushbackInputStream(in, 512), new Inflater(true), 512); + usesDefaultInflater = true; + if(in == null) { + throw new NullPointerException("in is null"); + } + if (charset == null) + throw new NullPointerException("charset is null"); + this.zc = ZipCoder.get(charset); + } + */ + + /** + * Reads the next ZIP file entry and positions the stream at the + * beginning of the entry data. + * @return the next ZIP file entry, or null if there are no more entries + * @exception ZipException if a ZIP file error has occurred + * @exception IOException if an I/O error has occurred + */ + public ZipEntry getNextEntry() throws IOException { + ensureOpen(); + if (entry != null) { + closeEntry(); + } + crc.reset(); + inf.reset(); + if ((entry = readLOC()) == null) { + return null; + } + if (entry.getMethod() == STORED) { + remaining = entry.getSize(); + } + entryEOF = false; + return entry; + } + + /** + * Closes the current ZIP entry and positions the stream for reading the + * next entry. + * @exception ZipException if a ZIP file error has occurred + * @exception IOException if an I/O error has occurred + */ + public void closeEntry() throws IOException { + ensureOpen(); + while (read(tmpbuf, 0, tmpbuf.length) != -1) ; + entryEOF = true; + } + + /** + * Returns 0 after EOF has reached for the current entry data, + * otherwise always return 1. + *
+ * Programs should not count on this method to return the actual number
+ * of bytes that could be read without blocking.
+ *
+ * @return 1 before EOF and 0 after EOF has reached for current entry.
+ * @exception IOException if an I/O error occurs.
+ *
+ */
+ public int available() throws IOException {
+ ensureOpen();
+ if (entryEOF) {
+ return 0;
+ } else {
+ return 1;
+ }
+ }
+
+ /**
+ * Reads from the current ZIP entry into an array of bytes.
+ * If len is not zero, the method
+ * blocks until some input is available; otherwise, no
+ * bytes are read and 0 is returned.
+ * @param b the buffer into which the data is read
+ * @param off the start offset in the destination array b
+ * @param len the maximum number of bytes read
+ * @return the actual number of bytes read, or -1 if the end of the
+ * entry is reached
+ * @exception NullPointerException if b is null.
+ * @exception IndexOutOfBoundsException if off is negative,
+ * len is negative, or len is greater than
+ * b.length - off
+ * @exception ZipException if a ZIP file error has occurred
+ * @exception IOException if an I/O error has occurred
+ */
+ public int read(byte[] b, int off, int len) throws IOException {
+ ensureOpen();
+ if (off < 0 || len < 0 || off > b.length - len) {
+ throw new IndexOutOfBoundsException();
+ } else if (len == 0) {
+ return 0;
+ }
+
+ if (entry == null) {
+ return -1;
+ }
+ switch (entry.getMethod()) {
+ case DEFLATED:
+ len = super.read(b, off, len);
+ if (len == -1) {
+ readEnd(entry);
+ entryEOF = true;
+ entry = null;
+ } else {
+ crc.update(b, off, len);
+ }
+ return len;
+ case STORED:
+ if (remaining <= 0) {
+ entryEOF = true;
+ entry = null;
+ return -1;
+ }
+ if (len > remaining) {
+ len = (int)remaining;
+ }
+ len = in.read(b, off, len);
+ if (len == -1) {
+ throw new ZipException("unexpected EOF");
+ }
+ crc.update(b, off, len);
+ remaining -= len;
+ if (remaining == 0 && entry.getCrc() != crc.getValue()) {
+ throw new ZipException(
+ "invalid entry CRC (expected 0x" + Long.toHexString(entry.getCrc()) +
+ " but got 0x" + Long.toHexString(crc.getValue()) + ")");
+ }
+ return len;
+ default:
+ throw new ZipException("invalid compression method");
+ }
+ }
+
+ /**
+ * Skips specified number of bytes in the current ZIP entry.
+ * @param n the number of bytes to skip
+ * @return the actual number of bytes skipped
+ * @exception ZipException if a ZIP file error has occurred
+ * @exception IOException if an I/O error has occurred
+ * @exception IllegalArgumentException if n < 0
+ */
+ public long skip(long n) throws IOException {
+ if (n < 0) {
+ throw new IllegalArgumentException("negative skip length");
+ }
+ ensureOpen();
+ int max = (int)Math.min(n, Integer.MAX_VALUE);
+ int total = 0;
+ while (total < max) {
+ int len = max - total;
+ if (len > tmpbuf.length) {
+ len = tmpbuf.length;
+ }
+ len = read(tmpbuf, 0, len);
+ if (len == -1) {
+ entryEOF = true;
+ break;
+ }
+ total += len;
+ }
+ return total;
+ }
+
+ /**
+ * Closes this input stream and releases any system resources associated
+ * with the stream.
+ * @exception IOException if an I/O error has occurred
+ */
+ public void close() throws IOException {
+ if (!closed) {
+ super.close();
+ closed = true;
+ }
+ }
+
+ private byte[] b = new byte[256];
+
+ /*
+ * Reads local file (LOC) header for next entry.
+ */
+ private ZipEntry readLOC() throws IOException {
+ try {
+ readFully(tmpbuf, 0, LOCHDR);
+ } catch (EOFException e) {
+ return null;
+ }
+ if (get32(tmpbuf, 0) != LOCSIG) {
+ return null;
+ }
+ // get flag first, we need check EFS.
+ flag = get16(tmpbuf, LOCFLG);
+ // get the entry name and create the ZipEntry first
+ int len = get16(tmpbuf, LOCNAM);
+ int blen = b.length;
+ if (len > blen) {
+ do
+ blen = blen * 2;
+ while (len > blen);
+ b = new byte[blen];
+ }
+ readFully(b, 0, len);
+ // Force to use UTF-8 if the EFS bit is ON, even the cs is NOT UTF-8
+ ZipEntry e = createZipEntry(((flag & EFS) != 0)
+ ? toStringUTF8(b, len)
+ : toString(b, len));
+ // now get the remaining fields for the entry
+ if ((flag & 1) == 1) {
+ throw new ZipException("encrypted ZIP entry not supported");
+ }
+ e.setMethod(get16(tmpbuf, LOCHOW));
+ e.setTime(get32(tmpbuf, LOCTIM));
+ if ((flag & 8) == 8) {
+ /* "Data Descriptor" present */
+ if (e.getMethod() != DEFLATED) {
+ throw new ZipException(
+ "only DEFLATED entries can have EXT descriptor");
+ }
+ } else {
+ e.setCrc(get32(tmpbuf, LOCCRC));
+ e.setCompressedSize(get32(tmpbuf, LOCSIZ));
+ e.setSize(get32(tmpbuf, LOCLEN));
+ }
+ len = get16(tmpbuf, LOCEXT);
+ if (len > 0) {
+ byte[] bb = new byte[len];
+ readFully(bb, 0, len);
+ e.setExtra(bb);
+ // extra fields are in "HeaderID(2)DataSize(2)Data... format
+ if (e.getCompressedSize() == ZIP64_MAGICVAL || e.getCompressedSize() == ZIP64_MAGICVAL) {
+ int off = 0;
+ while (off + 4 < len) {
+ int sz = get16(bb, off + 2);
+ if (get16(bb, off) == ZIP64_EXTID) {
+ off += 4;
+ // LOC extra zip64 entry MUST include BOTH original and
+ // compressed file size fields
+ if (sz < 16 || (off + sz) > len ) {
+ // Invalid zip64 extra fields, simply skip. Even it's
+ // rare, it's possible the entry size happens to be
+ // the magic value and it "accidnetly" has some bytes
+ // in extra match the id.
+ return e;
+ }
+ e.setSize(get64(bb, off));
+ e.setCompressedSize(get64(bb, off + 8));
+ break;
+ }
+ off += (sz + 4);
+ }
+ }
+ }
+ return e;
+ }
+
+ /**
+ * Creates a new ZipEntry object for the specified
+ * entry name.
+ *
+ * @param name the ZIP file entry name
+ * @return the ZipEntry just created
+ */
+ protected ZipEntry createZipEntry(String name) {
+ return new ZipEntry(name);
+ }
+
+ /*
+ * Reads end of deflated entry as well as EXT descriptor if present.
+ */
+ private void readEnd(ZipEntry e) throws IOException {
+ int n = inf.getRemaining();
+ if (n > 0) {
+ ((PushbackInputStream)in).unread(buf, len - n, n);
+ }
+ if ((flag & 8) == 8) {
+ /* "Data Descriptor" present */
+ if (inf.getBytesWritten() > ZIP64_MAGICVAL ||
+ inf.getBytesRead() > ZIP64_MAGICVAL) {
+ // ZIP64 format
+ readFully(tmpbuf, 0, ZIP64_EXTHDR);
+ long sig = get32(tmpbuf, 0);
+ if (sig != EXTSIG) { // no EXTSIG present
+ e.setCrc(sig);
+ e.setCompressedSize(get64(tmpbuf, ZIP64_EXTSIZ - ZIP64_EXTCRC));
+ e.setSize(get64(tmpbuf, ZIP64_EXTLEN - ZIP64_EXTCRC));
+ ((PushbackInputStream)in).unread(
+ tmpbuf, ZIP64_EXTHDR - ZIP64_EXTCRC - 1, ZIP64_EXTCRC);
+ } else {
+ e.setCrc(get32(tmpbuf, ZIP64_EXTCRC));
+ e.setCompressedSize(get64(tmpbuf, ZIP64_EXTSIZ));
+ e.setSize(get64(tmpbuf, ZIP64_EXTLEN));
+ }
+ } else {
+ readFully(tmpbuf, 0, EXTHDR);
+ long sig = get32(tmpbuf, 0);
+ if (sig != EXTSIG) { // no EXTSIG present
+ e.setCrc(sig);
+ e.setCompressedSize(get32(tmpbuf, EXTSIZ - EXTCRC));
+ e.setSize(get32(tmpbuf, EXTLEN - EXTCRC));
+ ((PushbackInputStream)in).unread(
+ tmpbuf, EXTHDR - EXTCRC - 1, EXTCRC);
+ } else {
+ e.setCrc(get32(tmpbuf, EXTCRC));
+ e.setCompressedSize(get32(tmpbuf, EXTSIZ));
+ e.setSize(get32(tmpbuf, EXTLEN));
+ }
+ }
+ }
+ if (e.getSize() != inf.getBytesWritten()) {
+ throw new ZipException(
+ "invalid entry size (expected " + e.getSize() +
+ " but got " + inf.getBytesWritten() + " bytes)");
+ }
+ if (e.getCompressedSize() != inf.getBytesRead()) {
+ throw new ZipException(
+ "invalid entry compressed size (expected " + e.getCompressedSize() +
+ " but got " + inf.getBytesRead() + " bytes)");
+ }
+ if (e.getCrc() != crc.getValue()) {
+ throw new ZipException(
+ "invalid entry CRC (expected 0x" + Long.toHexString(e.getCrc()) +
+ " but got 0x" + Long.toHexString(crc.getValue()) + ")");
+ }
+ }
+
+ /*
+ * Reads bytes, blocking until all bytes are read.
+ */
+ private void readFully(byte[] b, int off, int len) throws IOException {
+ while (len > 0) {
+ int n = in.read(b, off, len);
+ if (n == -1) {
+ throw new EOFException();
+ }
+ off += n;
+ len -= n;
+ }
+ }
+
+ /*
+ * Fetches unsigned 16-bit value from byte array at specified offset.
+ * The bytes are assumed to be in Intel (little-endian) byte order.
+ */
+ private static final int get16(byte b[], int off) {
+ return (b[off] & 0xff) | ((b[off+1] & 0xff) << 8);
+ }
+
+ /*
+ * Fetches unsigned 32-bit value from byte array at specified offset.
+ * The bytes are assumed to be in Intel (little-endian) byte order.
+ */
+ private static final long get32(byte b[], int off) {
+ return (get16(b, off) | ((long)get16(b, off+2) << 16)) & 0xffffffffL;
+ }
+
+ /*
+ * Fetches signed 64-bit value from byte array at specified offset.
+ * The bytes are assumed to be in Intel (little-endian) byte order.
+ */
+ private static final long get64(byte b[], int off) {
+ return get32(b, off) | (get32(b, off+4) << 32);
+ }
+
+ private static String toStringUTF8(byte[] arr, int len) {
+ return new String(arr, 0, len);
+ }
+
+ private static String toString(byte[] b, int len) {
+ return new String(b, 0, len);
+ }
+}