List of usage examples for java.io RandomAccessFile skipBytes
public int skipBytes(int n) throws IOException
From source file:Main.java
public static void main(String[] args) { try {//from w w w . j a va 2 s . com RandomAccessFile raf = new RandomAccessFile("c:/test.txt", "rw"); raf.writeUTF("Hello World from java2s.com"); // set the file pointer at 0 position raf.seek(0); // print the string System.out.println(raf.readUTF()); // set the file pointer at 0 position raf.seek(0); // attempt to skip 10 bytes System.out.println(raf.skipBytes(10)); System.out.println(raf.readLine()); // set the file pointer to position 8 raf.seek(8); // attempt to skip 10 more bytes System.out.println(raf.skipBytes(10)); raf.close(); } catch (IOException ex) { ex.printStackTrace(); } }
From source file:com.sangupta.snowpack.SnowpackRecover.java
/** * Try and recover from a chunk.//from w w w . ja v a 2 s . c o m * * @param chunkID * @param chunkFile * @param metadataDB * @return * @throws IOException */ private static ChunkInfo recoverChunkInfo(final int chunkID, final File chunkFile, SnowpackMetadataDB metadataDB) throws IOException { // open the file for reading RandomAccessFile raf = new RandomAccessFile(chunkFile, "r"); // read the length first int nameLength, length, terminator, headerLength, numFiles = 0; long offset; List<FlakeMetadata> metas = new ArrayList<FlakeMetadata>(); try { while (raf.getFilePointer() < raf.length()) { offset = raf.getFilePointer(); nameLength = raf.readInt(); byte[] name = new byte[nameLength]; raf.readFully(name); length = raf.readInt(); raf.readLong(); raf.skipBytes((int) length); terminator = raf.readByte(); if (terminator != 0) { System.out.print(" invalid descriptor found..."); return null; } headerLength = 4 + name.length + 4 + 8; numFiles++; metas.add(new FlakeMetadata(new String(name), nameLength, chunkID, offset, headerLength)); } } finally { raf.close(); } // all clear for recovery // save all metadata in new DB for (FlakeMetadata meta : metas) { metadataDB.save(meta); } // return chunk info ChunkInfo info = new ChunkInfo(); info.chunkID = chunkID; info.numFiles = numFiles; info.writePointer = -1; return info; }
From source file:TarList.java
public TarEntry(RandomAccessFile is) throws IOException, TarException { fileOffset = is.getFilePointer();/* w w w . ja v a2 s.com*/ // read() returns -1 at EOF if (is.read(name) < 0) throw new EOFException(); // Tar pads to block boundary with nulls. if (name[0] == '\0') throw new EOFException(); // OK, read remaining fields. is.read(mode); is.read(uid); is.read(gid); is.read(size); is.read(mtime); is.read(chksum); type = is.readByte(); is.read(linkName); is.read(magic); is.read(uname); is.read(gname); is.read(devmajor); is.read(devminor); // Since the tar header is < 512, we need to skip it. is.skipBytes((int) (TarFile.RECORDSIZE - (is.getFilePointer() % TarFile.RECORDSIZE))); // TODO if checksum() fails, // throw new TarException("Failed to find next header"); }
From source file:org.commoncrawl.service.crawler.CrawlLog.java
private static void transferLocalCheckpointLog(File crawlLogPath, HDFSCrawlURLWriter writer, long checkpointId) throws IOException { // and open the crawl log file ... RandomAccessFile inputStream = null; IOException exception = null; CRC32 crc = new CRC32(); CustomByteArrayOutputStream buffer = new CustomByteArrayOutputStream(1 << 17); byte[] syncBytesBuffer = new byte[SYNC_BYTES_SIZE]; // save position for potential debug output. long lastReadPosition = 0; try {/*from w w w.j a va2 s.c om*/ inputStream = new RandomAccessFile(crawlLogPath, "rw"); // and a data input stream ... RandomAccessFile reader = inputStream; // seek to zero reader.seek(0L); // read the header ... LogFileHeader header = readLogFileHeader(reader); // read a crawl url from the stream... while (inputStream.getFilePointer() < header._fileSize) { if (seekToNextSyncBytesPos(syncBytesBuffer, reader, header._fileSize)) { try { lastReadPosition = inputStream.getFilePointer(); // skip sync inputStream.skipBytes(SYNC_BYTES_SIZE); // read length ... int urlDataLen = reader.readInt(); long urlDataCRC = reader.readLong(); if (urlDataLen > buffer.getBuffer().length) { buffer = new CustomByteArrayOutputStream(((urlDataLen / 65536) + 1) * 65536); } reader.read(buffer.getBuffer(), 0, urlDataLen); crc.reset(); crc.update(buffer.getBuffer(), 0, urlDataLen); long computedValue = crc.getValue(); // validate crc values ... if (computedValue != urlDataCRC) { LOG.error("CRC Mismatch Detected during HDFS transfer in CrawlLog:" + crawlLogPath.getAbsolutePath() + " Checkpoint Id:" + checkpointId + " FilePosition:" + lastReadPosition); inputStream.seek(lastReadPosition + 1); } else { // allocate a crawl url data structure CrawlURL url = new CrawlURL(); DataInputStream bufferReader = new DataInputStream( new ByteArrayInputStream(buffer.getBuffer(), 0, urlDataLen)); // populate it from the (in memory) data stream url.readFields(bufferReader); try { // and write out appropriate sequence file entries ... writer.writeCrawlURLItem(new Text(url.getUrl()), url); } catch (IOException e) { LOG.error("Failed to write CrawlURL to SequenceFileWriter with Exception:" + CCStringUtils.stringifyException(e)); throw new URLWriterException(); } } } catch (URLWriterException e) { LOG.error("Caught URLRewriter Exception! - Throwing to outer layer!"); throw e; } catch (Exception e) { LOG.error("Ignoring Error Processing CrawlLog Entry at Position:" + lastReadPosition + " Exception:" + CCStringUtils.stringifyException(e)); } } else { break; } } } catch (EOFException e) { LOG.error("Caught EOF Exception during read of local CrawlLog:" + crawlLogPath.getAbsolutePath() + " Checkpoint Id:" + checkpointId + " FilePosition:" + lastReadPosition); } catch (IOException e) { LOG.error(CCStringUtils.stringifyException(e)); exception = e; throw e; } finally { if (inputStream != null) inputStream.close(); } }
From source file:org.commoncrawl.service.crawler.CrawlLog.java
public static void walkCrawlLogFile(File crawlLogPath, long startOffset) throws IOException { // and open the crawl log file ... RandomAccessFile inputStream = null; IOException exception = null; CRC32 crc = new CRC32(); CustomByteArrayOutputStream buffer = new CustomByteArrayOutputStream(1 << 17); byte[] syncBytesBuffer = new byte[SYNC_BYTES_SIZE]; // save position for potential debug output. long lastReadPosition = 0; try {// www . j a v a 2 s .c o m inputStream = new RandomAccessFile(crawlLogPath, "rw"); // and a data input stream ... RandomAccessFile reader = inputStream; // seek to zero reader.seek(0L); // read the header ... LogFileHeader header = readLogFileHeader(reader); System.out.println("Header ItemCount:" + header._itemCount + " FileSize:" + header._fileSize); if (startOffset != 0L) { System.out.println("Preseeking to:" + startOffset); reader.seek(startOffset); } Configuration conf = new Configuration(); // read a crawl url from the stream... long recordCount = 0; while (inputStream.getFilePointer() < header._fileSize) { // System.out.println("PRE-SYNC SeekPos:"+ // inputStream.getFilePointer()); if (seekToNextSyncBytesPos(syncBytesBuffer, reader, header._fileSize)) { // System.out.println("POST-SYNC SeekPos:"+ // inputStream.getFilePointer()); lastReadPosition = inputStream.getFilePointer(); // skip sync inputStream.skipBytes(SYNC_BYTES_SIZE); // read length ... int urlDataLen = reader.readInt(); long urlDataCRC = reader.readLong(); if (urlDataLen > buffer.getBuffer().length) { buffer = new CustomByteArrayOutputStream(((urlDataLen / 65536) + 1) * 65536); } reader.read(buffer.getBuffer(), 0, urlDataLen); crc.reset(); crc.update(buffer.getBuffer(), 0, urlDataLen); long computedValue = crc.getValue(); // validate crc values ... if (computedValue != urlDataCRC) { LOG.error("CRC Mismatch Detected during HDFS transfer in CrawlLog:" + crawlLogPath.getAbsolutePath() + " FilePosition:" + lastReadPosition); inputStream.seek(lastReadPosition + 1); } else { if (recordCount++ % 10000 == 0) { // allocate a crawl url data structure CrawlURL url = new CrawlURL(); DataInputStream bufferReader = new DataInputStream( new ByteArrayInputStream(buffer.getBuffer(), 0, urlDataLen)); // populate it from the (in memory) data stream url.readFields(bufferReader); System.out.println("Record:" + recordCount + " At:" + lastReadPosition + " URL:" + url.getUrl() + " BuffSize:" + urlDataLen + " ContentLen:" + url.getContentRaw().getCount() + " LastModified:" + new Date(url.getLastAttemptTime()).toString()); } } } else { break; } } } catch (EOFException e) { LOG.error("Caught EOF Exception during read of local CrawlLog:" + crawlLogPath.getAbsolutePath() + " FilePosition:" + lastReadPosition); } catch (IOException e) { LOG.error(CCStringUtils.stringifyException(e)); exception = e; throw e; } finally { if (inputStream != null) inputStream.close(); } }
From source file:org.kuali.coeus.sys.framework.controller.interceptor.PerformanceMeasurementFilter.java
private void insertLine(File file, HttpSample httpSample) throws IOException { RandomAccessFile randomAccessFile = null; try {/*from www . j a v a 2 s . c o m*/ randomAccessFile = new RandomAccessFile(file, "rw"); randomAccessFile.skipBytes((int) (file.length() - "\n</httpSamples>".getBytes().length)); randomAccessFile.write("\n".getBytes()); randomAccessFile.write(httpSample.toXML().getBytes()); randomAccessFile.write("\n".getBytes()); randomAccessFile.write("</httpSamples>".getBytes()); } finally { if (randomAccessFile != null) { randomAccessFile.close(); } } }