Example usage for java.util.zip GZIPInputStream GZIPInputStream

Introduction

In this page you can find the example usage for java.util.zip GZIPInputStream GZIPInputStream.

Prototype

public GZIPInputStream(InputStream in) throws IOException

Source Link

Document

Creates a new input stream with a default buffer size.

Usage

From source file:com.act.utils.parser.GenbankInterpreter.java

/**
 * Parses every sequence object from the Genbank File
 * @throws Exception//from  w  w  w  .  ja v  a 2s  .c  om
 */
public void init() throws Exception {
    if (seq_type.equals(PROTEIN)) {
        Map<String, ProteinSequence> sequences;

        if (protFile.getName().endsWith(".gz")) {
            try (InputStream is = new GZIPInputStream(new FileInputStream(protFile))) {
                sequences = GenbankReaderHelper.readGenbankProteinSequence(is);
            }
        } else {
            sequences = GenbankReaderHelper.readGenbankProteinSequence(protFile);
        }

        for (AbstractSequence sequence : sequences.values()) {
            this.sequences.add(sequence);
        }

    } else if (seq_type.equals(DNA)) {
        Map<String, DNASequence> sequences;

        if (protFile.getName().endsWith(".gz")) {
            try (InputStream is = new GZIPInputStream(new FileInputStream(protFile))) {
                /* the AmbiguityDNACompoundSet is necessary due to the presence of ambiguous nucleotide (non-ATCG) compounds
                in the parsed DNA sequences */
                GenbankReader genbankReader = new GenbankReader(is, new GenericGenbankHeaderParser<>(),
                        new DNASequenceCreator(AmbiguityDNACompoundSet.getDNACompoundSet()));

                sequences = genbankReader.process();
            }
        } else {
            /* the AmbiguityDNACompoundSet is necessary due to the presence of ambiguous nucleotide (non-ATCG) compounds
              in the parsed DNA sequences */
            GenbankReader genbankReader = new GenbankReader(protFile, new GenericGenbankHeaderParser<>(),
                    new DNASequenceCreator(AmbiguityDNACompoundSet.getDNACompoundSet()));

            sequences = genbankReader.process();
        }

        for (AbstractSequence sequence : sequences.values()) {
            this.sequences.add(sequence);
        }

    } else {
        String msg = "No proper sequence type given; must be either DNA or Protein";
        LOGGER.error(msg);
        throw new RuntimeException(msg);
    }
}

From source file:it.unimi.dsi.sux4j.mph.VLLcpMonotoneMinimalPerfectHashFunction.java

public static void main(final String[] arg) throws NoSuchMethodException, IOException, JSAPException {

    final SimpleJSAP jsap = new SimpleJSAP(VLLcpMonotoneMinimalPerfectHashFunction.class.getName(),
            "Builds a variable-length LCP-based monotone minimal perfect hash function reading a newline-separated list of strings.",
            new Parameter[] {
                    new FlaggedOption("encoding", ForNameStringParser.getParser(Charset.class), "UTF-8",
                            JSAP.NOT_REQUIRED, 'e', "encoding", "The string file encoding."),
                    new Switch("huTucker", 'h', "hu-tucker", "Use Hu-Tucker coding to reduce string length."),
                    new Switch("iso", 'i', "iso",
                            "Use ISO-8859-1 coding internally (i.e., just use the lower eight bits of each character)."),
                    new Switch("utf32", JSAP.NO_SHORTFLAG, "utf-32",
                            "Use UTF-32 internally (handles surrogate pairs)."),
                    new Switch("zipped", 'z', "zipped", "The string list is compressed in gzip format."),
                    new UnflaggedOption("function", JSAP.STRING_PARSER, JSAP.NO_DEFAULT, JSAP.REQUIRED,
                            JSAP.NOT_GREEDY,
                            "The filename for the serialised monotone minimal perfect hash function."),
                    new UnflaggedOption("stringFile", JSAP.STRING_PARSER, "-", JSAP.NOT_REQUIRED,
                            JSAP.NOT_GREEDY,
                            "The name of a file containing a newline-separated list of strings, or - for standard input; in the first case, strings will not be loaded into core memory."), });

    JSAPResult jsapResult = jsap.parse(arg);
    if (jsap.messagePrinted())
        return;//from  w ww  .  ja  va  2s  .c om

    final String functionName = jsapResult.getString("function");
    final String stringFile = jsapResult.getString("stringFile");
    final Charset encoding = (Charset) jsapResult.getObject("encoding");
    final boolean zipped = jsapResult.getBoolean("zipped");
    final boolean iso = jsapResult.getBoolean("iso");
    final boolean utf32 = jsapResult.getBoolean("utf32");
    final boolean huTucker = jsapResult.getBoolean("huTucker");

    final Collection<MutableString> collection;
    if ("-".equals(stringFile)) {
        final ProgressLogger pl = new ProgressLogger(LOGGER);
        pl.displayLocalSpeed = true;
        pl.displayFreeMemory = true;
        pl.start("Loading strings...");
        collection = new LineIterator(
                new FastBufferedReader(
                        new InputStreamReader(zipped ? new GZIPInputStream(System.in) : System.in, encoding)),
                pl).allLines();
        pl.done();
    } else
        collection = new FileLinesCollection(stringFile, encoding.toString(), zipped);
    final TransformationStrategy<CharSequence> transformationStrategy = huTucker
            ? new HuTuckerTransformationStrategy(collection, true)
            : iso ? TransformationStrategies.prefixFreeIso()
                    : utf32 ? TransformationStrategies.prefixFreeUtf32()
                            : TransformationStrategies.prefixFreeUtf16();

    BinIO.storeObject(
            new VLLcpMonotoneMinimalPerfectHashFunction<CharSequence>(collection, transformationStrategy),
            functionName);
    LOGGER.info("Completed.");
}

From source file:de.tudarmstadt.ukp.dkpro.core.clearnlp.ClearNlpParser.java

@Override
public void initialize(UimaContext context) throws ResourceInitializationException {
    super.initialize(context);

    parserProvider = new ModelProviderBase<AbstractDEPParser>(this, "clearnlp", "parser") {
        @Override//w  w w  .  ja  v  a 2 s .  c o  m
        protected AbstractDEPParser produceResource(URL aUrl) throws IOException {
            InputStream is = null;
            BufferedInputStream bis = null;
            ObjectInputStream ois = null;
            GZIPInputStream gis = null;

            try {
                is = aUrl.openStream();
                String language = getAggregatedProperties().getProperty(LANGUAGE);
                gis = new GZIPInputStream(is);
                bis = new BufferedInputStream(gis);
                ois = new ObjectInputStream(bis);
                AbstractDEPParser parser = NLPGetter.getDEPParser(ois, language);
                Properties metadata = getResourceMetaData();

                SingletonTagset depTags = new SingletonTagset(Dependency.class,
                        metadata.getProperty("dependency.tagset"));

                try {
                    for (StringModel model : parser.getModels()) {
                        for (String label : model.getLabels()) {
                            String[] fields = label.split("_");
                            if (fields.length == 3) {
                                depTags.add(fields[2]);
                            }
                            // else {
                            // getContext().getLogger().log(WARNING,
                            // "Unknown label format: [" + label + "]");
                            // }
                        }
                    }
                } catch (Exception e) {
                    getContext().getLogger().log(WARNING, "Unable to find tagset information.");
                }

                addTagset(depTags);

                if (printTagSet) {
                    getContext().getLogger().log(INFO, getTagset().toString());
                }

                return parser;
            } catch (Exception e) {
                throw new IOException(e);
            } finally {
                closeQuietly(ois);
                closeQuietly(bis);
                closeQuietly(gis);
                closeQuietly(is);
            }
        }
    };
}

From source file:edu.umn.cs.spatialHadoop.visualization.FrequencyMap.java

@Override
public void readFields(DataInput in) throws IOException {
    super.readFields(in);
    int length = in.readInt();
    byte[] serializedData = new byte[length];
    in.readFully(serializedData);/* ww  w  . j  a  v  a 2  s .com*/
    ByteArrayInputStream bais = new ByteArrayInputStream(serializedData);
    GZIPInputStream gzis = new GZIPInputStream(bais);

    byte[] buffer = new byte[8];
    gzis.read(buffer);
    ByteBuffer bbuffer = ByteBuffer.wrap(buffer);
    int width = bbuffer.getInt();
    int height = bbuffer.getInt();
    // Reallocate memory only if needed
    if (width != this.getWidth() || height != this.getHeight())
        frequencies = new float[width][height];
    buffer = new byte[getHeight() * 4];
    for (int x = 0; x < getWidth(); x++) {
        int size = 0;
        while (size < buffer.length) {
            size += gzis.read(buffer, size, buffer.length - size);
        }
        bbuffer = ByteBuffer.wrap(buffer);
        for (int y = 0; y < getHeight(); y++) {
            frequencies[x][y] = bbuffer.getFloat();
        }
    }
}

From source file:it.unimi.dsi.sux4j.mph.ZFastTrieDistributorMonotoneMinimalPerfectHashFunction.java

public static void main(final String[] arg) throws NoSuchMethodException, IOException, JSAPException {

    final SimpleJSAP jsap = new SimpleJSAP(
            ZFastTrieDistributorMonotoneMinimalPerfectHashFunction.class.getName(),
            "Builds a monotone minimal perfect hash using a probabilistic z-fast trie as a distributor reading a newline-separated list of strings.",
            new Parameter[] {
                    new FlaggedOption("encoding", ForNameStringParser.getParser(Charset.class), "UTF-8",
                            JSAP.NOT_REQUIRED, 'e', "encoding", "The string file encoding."),
                    new FlaggedOption("tempDir", FileStringParser.getParser(), JSAP.NO_DEFAULT,
                            JSAP.NOT_REQUIRED, 'T', "temp-dir", "A directory for temporary files."),
                    new Switch("huTucker", 'h', "hu-tucker", "Use Hu-Tucker coding to reduce string length."),
                    new Switch("iso", 'i', "iso",
                            "Use ISO-8859-1 coding internally (i.e., just use the lower eight bits of each character)."),
                    new Switch("utf32", JSAP.NO_SHORTFLAG, "utf-32",
                            "Use UTF-32 internally (handles surrogate pairs)."),
                    new FlaggedOption("signatureWidth", JSAP.INTEGER_PARSER, JSAP.NO_DEFAULT, JSAP.NOT_REQUIRED,
                            's', "signature-width",
                            "If specified, the signature width in bits; if negative, the generated function will be a dictionary."),
                    new Switch("zipped", 'z', "zipped", "The string list is compressed in gzip format."),
                    new FlaggedOption("log2bucket", JSAP.INTEGER_PARSER, "-1", JSAP.NOT_REQUIRED, 'b',
                            "log2bucket", "The base 2 logarithm of the bucket size (mainly for testing)."),
                    new UnflaggedOption("function", JSAP.STRING_PARSER, JSAP.NO_DEFAULT, JSAP.REQUIRED,
                            JSAP.NOT_GREEDY,
                            "The filename for the serialised monotone minimal perfect hash function."),
                    new UnflaggedOption("stringFile", JSAP.STRING_PARSER, "-", JSAP.NOT_REQUIRED,
                            JSAP.NOT_GREEDY,
                            "The name of a file containing a newline-separated list of strings, or - for standard input; in the first case, strings will not be loaded into core memory."), });

    JSAPResult jsapResult = jsap.parse(arg);
    if (jsap.messagePrinted())
        return;//ww w  .ja va2  s. c om

    final String functionName = jsapResult.getString("function");
    final String stringFile = jsapResult.getString("stringFile");
    final int log2BucketSize = jsapResult.getInt("log2bucket");
    final Charset encoding = (Charset) jsapResult.getObject("encoding");
    final File tempDir = jsapResult.getFile("tempDir");
    final boolean zipped = jsapResult.getBoolean("zipped");
    final boolean iso = jsapResult.getBoolean("iso");
    final boolean utf32 = jsapResult.getBoolean("utf32");
    final boolean huTucker = jsapResult.getBoolean("huTucker");
    final int signatureWidth = jsapResult.getInt("signatureWidth", 0);

    final Collection<MutableString> collection;
    if ("-".equals(stringFile)) {
        final ProgressLogger pl = new ProgressLogger(LOGGER);
        pl.displayLocalSpeed = true;
        pl.displayFreeMemory = true;
        pl.start("Loading strings...");
        collection = new LineIterator(
                new FastBufferedReader(
                        new InputStreamReader(zipped ? new GZIPInputStream(System.in) : System.in, encoding)),
                pl).allLines();
        pl.done();
    } else
        collection = new FileLinesCollection(stringFile, encoding.toString(), zipped);
    final TransformationStrategy<CharSequence> transformationStrategy = huTucker
            ? new HuTuckerTransformationStrategy(collection, true)
            : iso ? TransformationStrategies.prefixFreeIso()
                    : utf32 ? TransformationStrategies.prefixFreeUtf32()
                            : TransformationStrategies.prefixFreeUtf16();

    BinIO.storeObject(new ZFastTrieDistributorMonotoneMinimalPerfectHashFunction<CharSequence>(collection,
            transformationStrategy, log2BucketSize, signatureWidth, tempDir), functionName);
    LOGGER.info("Completed.");
}

From source file:co.cask.tigon.sql.internal.StreamBinaryGenerator.java

private void unzipFile(File libZip) throws IOException, ArchiveException {
    String path = libZip.toURI().getPath();
    String outDir = libZip.getParentFile().getPath();
    TarArchiveInputStream archiveInputStream = new TarArchiveInputStream(
            new GZIPInputStream(new FileInputStream(path)));
    try {//w  w  w.j av  a2s  .  c o  m
        TarArchiveEntry entry = archiveInputStream.getNextTarEntry();
        while (entry != null) {
            File destFile = new File(outDir, entry.getName());
            destFile.getParentFile().mkdirs();
            if (!entry.isDirectory()) {
                ByteStreams.copy(archiveInputStream, Files.newOutputStreamSupplier(destFile));
                //TODO: Set executable permission based on entry.getMode()
                destFile.setExecutable(true, false);
            }
            entry = archiveInputStream.getNextTarEntry();
        }
    } finally {
        archiveInputStream.close();
    }
}

From source file:org.grameenfoundation.consulteca.utils.HttpHelpers.java

private static InputStream getInputStream(HttpResponse httpResponse) throws IllegalStateException, IOException {
    InputStream inputStream = httpResponse.getEntity().getContent();
    Header contentEncoding = httpResponse.getFirstHeader("Content-Encoding");
    if (contentEncoding != null && contentEncoding.getValue().equalsIgnoreCase("gzip")) {
        inputStream = new GZIPInputStream(inputStream);
    }// w w  w. j a v a2s.co  m
    return inputStream;
}

From source file:com.t3.model.AssetLoader.java

protected List<String> decode(byte[] indexData) throws IOException {
    BufferedReader reader = new BufferedReader(
            new InputStreamReader(new GZIPInputStream(new ByteArrayInputStream(indexData))));

    List<String> list = new ArrayList<String>();

    String line = null;//from  w  w w  . j a v  a 2 s .c  o m
    while ((line = reader.readLine()) != null) {
        list.add(line);
    }
    return list;
}

From source file:com.googlecode.android_scripting.ZipExtractorTask.java

private long unzip() throws Exception {
    long extractedSize = 0l;
    Enumeration<? extends ZipEntry> entries;
    if (mInput.isFile() && mInput.getName().contains(".gz")) {
        InputStream stream = new FileInputStream(mInput);
        GZIPInputStream gzipStream = new GZIPInputStream(stream);
        InputSource is = new InputSource(gzipStream);
        InputStream input = new BufferedInputStream(is.getByteStream());
        File destination = new File(mOutput, "php");
        ByteArrayBuffer baf = new ByteArrayBuffer(255000);
        int current = 0;
        while ((current = input.read()) != -1) {
            baf.append((byte) current);
        }//from  ww w  .j  av a 2 s .  c  o  m

        FileOutputStream output = new FileOutputStream(destination);
        output.write(baf.toByteArray());
        output.close();
        Log.d("written!");
        return baf.toByteArray().length;
    }
    ZipFile zip = new ZipFile(mInput);
    long uncompressedSize = getOriginalSize(zip);

    publishProgress(0, (int) uncompressedSize);

    entries = zip.entries();

    try {
        while (entries.hasMoreElements()) {
            ZipEntry entry = entries.nextElement();
            if (entry.isDirectory()) {
                // Not all zip files actually include separate directory entries.
                // We'll just ignore them
                // and create them as necessary for each actual entry.
                continue;
            }
            File destination = new File(mOutput, entry.getName());
            if (!destination.getParentFile().exists()) {
                destination.getParentFile().mkdirs();
            }
            if (destination.exists() && mContext != null && !mReplaceAll) {
                Replace answer = showDialog(entry.getName());
                switch (answer) {
                case YES:
                    break;
                case NO:
                    continue;
                case YESTOALL:
                    mReplaceAll = true;
                    break;
                default:
                    return extractedSize;
                }
            }
            ProgressReportingOutputStream outStream = new ProgressReportingOutputStream(destination);
            extractedSize += IoUtils.copy(zip.getInputStream(entry), outStream);
            outStream.close();
        }
    } finally {
        try {
            zip.close();
        } catch (Exception e) {
            // swallow this exception, we are only interested in the original one
        }
    }
    Log.v("Extraction is complete.");
    return extractedSize;
}

From source file:com.slytechs.capture.StreamFactory.java

public <T extends InputCapture<? extends FilePacket>> T newInput(final Class<T> t, final File file,
        Filter<ProtocolFilterTarget> filter) throws IOException {

    final BufferedInputStream b = new BufferedInputStream(new FileInputStream(file));
    b.mark(1024); // Buffer first 1K of stream so we can rewind

    /*/* w w  w .ja  v a  2  s .c  o  m*/
     * Check the stream, without decompression first
     */
    if (formatType(Channels.newChannel(b)) != null) {
        b.close();

        /*
         * This is a plain uncompressed file, open up a FileChannel. It will be
         * much faster
         */
        return newInput(t, new RandomAccessFile(file, "rw").getChannel(), filter);
    }

    /*
     * Try with gunziped stream, second
     */
    b.reset(); // Rewind
    if (formatType(Channels.newChannel(new GZIPInputStream(b))) != null) {
        b.close();

        /*
         * Now reopen the same file, but this time without the buffered
         * inputstream in the middle. Try to make things as efficient as possible.
         * TODO: implement much faster channel based GZIP decompression algorithm
         */
        return newInput(t, Channels.newChannel(new GZIPInputStream(new FileInputStream(file))), filter);
    }

    throw new IllegalArgumentException(
            "File is not any compressed or decompressed known format [" + file.getName() + "]");

}