Examples of org.elasticsearch.river.wikipedia.bzip2.CBZip2InputStream

Package org.elasticsearch.river.wikipedia.bzip2

Examples of org.elasticsearch.river.wikipedia.bzip2.CBZip2InputStream

org.apache.tools.bzip2.CBZip2InputStream
An input stream that decompresses from the BZip2 format (without the file header chars) to be read as any other stream.

The decompression requires large amounts of memory. Thus you should call the {@link #close() close()} method as soon aspossible, to force CBZip2InputStream to release the allocated memory. See {@link CBZip2OutputStream CBZip2OutputStream} for information about memory usage.

CBZip2InputStream reads bytes from the compressed source stream via the single byte {@link java.io.InputStream#read() read()} method exclusively. Thus you should consider to use abuffered source stream.

Instances of this class are not threadsafe.

    /**
     * Wraps an InputStream with a decompression stream for reading compressed archives.
     */
    private InputStream wrapInputStream(InputStream in) throws IOException {
        if (decompress == USE_BZIP) {
            return new CBZip2InputStream(in);
        }
        if (decompress == USE_GZIP) {
            return new GZIPInputStream(in, BUFFER_SIZE);
        }

View Full Code Here

      return;
    }
    // Read 2 bytes due to bug in BZip library
    compressedStream.read();
    compressedStream.read();
    InputStream stream = new CBZip2InputStream(compressedStream);
    BufferedReader reader = new BufferedReader(new InputStreamReader(stream));


    // Pattern find word name
    Pattern titlePattern = Pattern.compile("<title>([^<]+)</title>");
    // Pattern to find beginning of wiki text

View Full Code Here

        InputStream actualIn =
            new BufferedInputStream(new FileInputStream(actualFile));
        assertEquals((byte) 'B', actualIn.read());
        assertEquals((byte) 'Z', actualIn.read());


        originalIn = new CBZip2InputStream(originalIn);
        actualIn   = new CBZip2InputStream(actualIn);


        while (true) {
            int expected = originalIn.read();
            int actual   = actualIn.read();
            if (expected >= 0) {

View Full Code Here

        for (int i = 0; i < MAGIC.length; i++) {
            if (in.read() != MAGIC[i]) {
                throw new IOException("Invalid bz2 stream.");
            }
        }
        return new CBZip2InputStream(in);
    }

View Full Code Here

        if (source.lastModified() > dest.lastModified()) {
            log("Expanding " + source.getAbsolutePath() + " to "
                + dest.getAbsolutePath());


            FileOutputStream out = null;
            CBZip2InputStream zIn = null;
            InputStream fis = null;
            BufferedInputStream bis = null;
            try {
                out = new FileOutputStream(dest);
                fis = srcResource.getInputStream();
                bis = new BufferedInputStream(fis);
                int b = bis.read();
                if (b != 'B') {
                    throw new BuildException("Invalid bz2 file.", getLocation());
                }
                b = bis.read();
                if (b != 'Z') {
                    throw new BuildException("Invalid bz2 file.", getLocation());
                }
                zIn = new CBZip2InputStream(bis, true);
                byte[] buffer = new byte[BUFFER_SIZE];
                int count = 0;
                do {
                    out.write(buffer, 0, count);
                    count = zIn.read(buffer, 0, buffer.length);
                } while (count != -1);
            } catch (IOException ioe) {
                String msg = "Problem expanding bzip2 " + ioe.getMessage();
                throw new BuildException(msg, ioe, getLocation());
            } finally {

View Full Code Here

                        if (istream.read() != magic[i]) {
                            throw new BuildException(
                                "Invalid bz2 file." + file.toString());
                        }
                    }
                    return new CBZip2InputStream(istream);
                }
            }
            return istream;
        }

View Full Code Here

        InputStream actualIn =
            new BufferedInputStream(new FileInputStream(actualFile));
        assertEquals((byte) 'B', actualIn.read());
        assertEquals((byte) 'Z', actualIn.read());


        originalIn = new CBZip2InputStream(originalIn);
        actualIn   = new CBZip2InputStream(actualIn);


        while (true) {
            int expected = originalIn.read();
            int actual   = actualIn.read();
            if (expected >= 0) {

View Full Code Here

        String fileName = file.getName();
        try {
            if (fileName.endsWith(".tar.gz") || fileName.endsWith(".tgz")) {
                return new TarInputStream(new GZIPInputStream(new FileInputStream(file)));
            } else if (fileName.endsWith(".tar.bz2")) {
                return new TarInputStream(new CBZip2InputStream(new FileInputStream(file)));
            } else if (fileName.endsWith(".tar") || "application/x-tar".equals(contentType)) {
                return new TarInputStream(new FileInputStream(file));
            } else if (fileName.endsWith(".zip") 
                    || "application/x-zip-compressed".equals(contentType)
                    || "application/zip".equals(contentType)

View Full Code Here

                is.mark(4);
                if (!(is.read() == 'B' && is.read() == 'Z')) {
                    // No BZ prefix as appended by command line tools.  Reset and hope for the best
                    is.reset();
                }
                return new CBZip2InputStream(is);
            }
        } catch (IOException e) {
            logger.warn("Something that looked like a compressed file gave an error on open: "+file,e);
        }
        return null;

View Full Code Here

                        if (istream.read() != magic[i]) {
                            throw new BuildException(
                                "Invalid bz2 file." + file.toString());
                        }
                    }
                    return new CBZip2InputStream(istream);
                }
            }
            return istream;
        }

View Full Code Here

0 1 2 3 4 5 6 7

TOP

Related Classes of org.elasticsearch.river.wikipedia.bzip2.CBZip2InputStream

at.molindo.utils.io.StreamUtils

cc.twittertools.index.IndexStatuses

com.endgame.binarypig.util.BuildSequenceFileFromArchive

com.google.gwt.ant.taskdefs.TarCat$UntarCompressionMethod

com.google.refine.importing.ImportingUtilities

com.packetloop.packetpig.loaders.pcap.PcapRecordReader

com.packetloop.packetpig.loaders.pcap.StreamingPcapRecordReader

edu.umd.cloud9.collection.wikipedia.WikipediaPagesBz2InputStream

er.woinstaller.archiver.XarFile

mwt.wow.mpq.BZip2Reader

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.