opengrok/analysis/XrefInputStream.java

/*
 * CDDL HEADER START
 *
 * The contents of this file are subject to the terms of the
 * Common Development and Distribution License (the "License").
 * You may not use this file except in compliance with the License.
 *
 * See LICENSE.txt included in this distribution for the specific
 * language governing permissions and limitations under the License.
 *
 * When distributing Covered Code, include this CDDL HEADER in each
 * file and include the License file at LICENSE.txt.
 * If applicable, add the following below this CDDL HEADER, with the
 * fields enclosed by brackets "[]" replaced with your own identifying
 * information: Portions Copyright [yyyy] [name of copyright owner]
 *
 * CDDL HEADER END
 */

/*
 * Copyright (c) 2012, Oracle and/or its affiliates. All rights reserved.
 * Portions Copyright 2012 Jens Elkner.
 */
package org.opensolaris.opengrok.analysis;

import java.io.BufferedInputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.FilterInputStream;
import java.io.IOException;
import java.io.InputStreamReader;
import java.io.OutputStream;
import java.io.Writer;
import java.util.logging.Level;
import java.util.logging.Logger;
import java.util.zip.GZIPInputStream;

import org.opensolaris.opengrok.analysis.FileAnalyzer.Genre;
import org.opensolaris.opengrok.util.IOUtils;

/**
 * A {@link FilterInputStream} for Opengrok crossfiles.
 * It uses a {@link BufferedInputStream} or {@link GZIPInputStream} as
 * underlying stream to provide the required functionality. So there is usually
 * no need to wrap it into another BufferedInputStream etc. .
 *
 * @see BufferedInputStream
 * @see GZIPInputStream
 *
 * @author  Jens Elkner
 * @version $Revision$
 */
public class XrefInputStream extends FilterInputStream {
    private static final Logger logger = Logger.getLogger(XrefInputStream.class.getName());
    private XrefHeader header;
    private File file;
    private boolean uncompress;
    private boolean canClose;

    /**
     * Create a new InputStream from the given crossfile. The header gets read
     * automatically and thus internal cursor points to the start of the data
     * section of the crossfile, when this method returns.
     *
     * @param file file to read.
     * @param uncompress if {@code true} crossfile data gets uncompressed on
     *  the fly if they are compressed.
     * @throws IOException on read error or if the given file is not a crossfile
     */
    public XrefInputStream(File file, boolean uncompress) throws IOException {
        super(null);
        FileInputStream fis = new FileInputStream(file);
        this.file = file;
        try {
            header = new XrefHeader(fis);
            this.uncompress = uncompress && header.isCompressed();
            in = this.uncompress
                ? new GZIPInputStream(fis, 4096)
                : new BufferedInputStream(fis, header.isCompressed() ? 4096 : 16384);
        } catch (IOException e) {
            if (in != null) {
                IOUtils.close(in);
            } else {
                IOUtils.close(fis);
            }
            throw new IOException(e.getMessage() + "(" + file + ")");
        }
        canClose = true;
    }

    /**
     * Get the header of the crossfile beeing read.
     * @return the crossfile header
     */
    public XrefHeader getHeader() {
        return header;
    }

    /**
     * Convinience method to check, whether the wrapped crossfile contains
     * compressed data.
     * @return {@code true} if data section is compressed.
     * @see XrefHeader#isCompressed()
     * @see #getHeader()
     */
    public boolean isCompressed() {
        return header.isCompressed();
    }

    /**
     * Convinience method to get the Genre of data provided by this stream.
     * @return the data's genre.
     * @see XrefHeader#getGenre()
     * @see #getHeader()
     */
    public Genre getGenre() {
        return header.getGenre();
    }

    /**
     * Get the file from which this stream has been created.
     * @return the origin of this stream
     */
    public File getFile() {
        return file;
    }

    /**
     * Dump all data not yet read to the given output stream.
     * @param out  where to dump remaining data.
     * @throws IOException
     */
    public void dump(OutputStream out) throws IOException {
        if (out == null) {
            throw new IllegalArgumentException("null output stream not allowed");
        }
        byte[] buf =
            new byte[!uncompress && (in instanceof GZIPInputStream) ? 4096 : 16384];
        int len = 0;
        while ((len = in.read(buf)) >= 0) {
            out.write(buf, 0, len);
        }
    }

    /**
     * Dump all data not yet read to the given writer. The constructor for this
     * instance should have been called with on-the-fly uncompression enabled.
     * If not and the data of the stream are compressed, it is tried to switch
     * over to on-the-fly uncompression, but obviously this will fail with an
     * IOException, if any data have been read from this stream already.
     *
     * @param out   where to write data.
     * @throws IOException  on read error
     * @see XrefInputStream#XrefInputStream(File, boolean)
     */
    public void dump(Writer out) throws IOException {
        if (out == null) {
            throw new IllegalArgumentException("null output stream not allowed");
        }
        if (header.isCompressed() && !uncompress) {
            logger.warning("switching over to on-the-fly uncompression for "
                + file + " (wasn't specified in constructor)");
            GZIPInputStream gin = new GZIPInputStream(in, 4096);
            in = gin;
        }
        InputStreamReader isr = new InputStreamReader(in, "UTF-8");
        char[] buf = new char[4096];    // underlying buffers are suffient
        int len = 0;
        canClose = false; // avoid that isr.close() closes in as well
        try {
            while ((len = isr.read(buf)) >= 0) {
                out.write(buf, 0, len);
            }
        } finally {
            IOUtils.close(isr);
            canClose = true;
        }
    }

    /**
     * Convinience method to dump a crossfile to the given writer..
     *
     * @param file  crossfile to dump.
     * @param out   dump destination.
     * @param script if {@code true} the javascript snippet
     *  {@code O.lines=$num; O.createLinenums();} gets emitted to the writer
     *  first.
     * @return {@code true} on success.
     */
    public static boolean dump(File file, Writer out, boolean script) {
        if (out == null) {
            return false;
        }
        XrefInputStream in = null;
        try {
            in = new XrefInputStream(file, true);
            if (script) {
                out.write("<script type='text/javascript'>/* <![CDATA[ */O.lines=");
                out.write(Integer.toString(in.getHeader().getLines()));
                out.write(";O.createLinenums();/* ]]> */</script>");
            }
            in.dump(out);
            return true;
        } catch (Exception e) {
            logger.warning(e.getLocalizedMessage());
            logger.log(Level.FINE, "dump " + file, e);
        } finally {
            IOUtils.close(in);
        }
        return false;
    }

    /**
     * {@inheritDoc}
     */
    @Override
    public void close() throws IOException {
        if (!canClose) {
            return;
        }
        in.close();
    }

    /**
     * Dump an opengrok cross file.
     * @param args  opengrok crossfile name
     */
    public static void main(String[] args) {
        if (args.length == 0) {
            System.out.println("Usage: java ... " + logger.getName() + " xrefFile");
            return;
        }
        XrefInputStream in = null;
        try {
             in = new XrefInputStream(new File(args[0]), true);
             System.out.println(in.getHeader().toString());
             System.out.println();
             in.dump(System.out);
        } catch (IOException e) {
            System.out.println(e.getLocalizedMessage());
        } finally {
            IOUtils.close(in);
        }
    }
}