public int run(String[] args) throws Exception {
Configuration argConf = getConf();
// JobConf conf = new JobConf(diffdb.class);
Configuration config = HBaseConfiguration.create();
HBaseAdmin hbAdmin = new HBaseAdmin(config);
dbutil db_util = new dbutil(config);
HTable runTable = new HTable(config, "gestore_runs");
Get runGet = new Get(argConf.get("id").getBytes());
Result pipeline = runTable.get(runGet);
NavigableMap<byte[], byte[]> pipeMap = pipeline.getFamilyMap("d".getBytes());
Map.Entry<byte[], byte[]> results = pipeMap.pollFirstEntry();
HashMap<String, HashMap<String, String>> resultMap =
new HashMap<String, HashMap<String, String>>();
while (results != null) {
String resultKey = new String(results.getKey());
String resultValue = new String(results.getValue());
String field = "type";
HashMap<String, String> tempMap = new HashMap<String, String>();
String entry = resultKey;
if (resultKey.endsWith("_db_timestamp")) {
field = "db_timestamp";
entry = resultKey.substring(0, resultKey.lastIndexOf("_db_timestamp"));
} else if (resultKey.endsWith("_filename")) {
field = "filename";
entry = resultKey.substring(0, resultKey.lastIndexOf("_filename"));
} else if (resultKey.endsWith("_regex")) {
field = "regex";
entry = resultKey.substring(0, resultKey.lastIndexOf("_regex"));
}
if (resultMap.containsKey(entry)) {
tempMap = resultMap.get(entry);
}
tempMap.put(field, resultValue);
resultMap.put(entry, tempMap);
// System.out.println("Key: " + resultKey + " Value: " + resultValue);
results = pipeMap.pollFirstEntry();
}
for (String key : resultMap.keySet()) {
System.out.println("File ID: " + key);
for (String subKey : resultMap.get(key).keySet()) {
// System.out.println("\t " + subKey + "\t\t" + resultMap.get(key).get(subKey));
System.out.format(" %1$-20s %2$s\n", subKey, resultMap.get(key).get(subKey));
}
}
return 0;
}
/**
* Add a file path to the current set of classpath entries. It adds the file to cache as well.
* Intended to be used by user code.
*
* @param file Path of the file to be added
* @param conf Configuration that contains the classpath setting
* @param fs FileSystem with respect to which {@code archivefile} should be interpreted.
*/
public static void addFileToClassPath(Path file, Configuration conf, FileSystem fs)
throws IOException {
String filepath = file.toUri().getPath();
String classpath = conf.get("mapred.job.classpath.files");
conf.set(
"mapred.job.classpath.files",
classpath == null ? filepath : classpath + System.getProperty("path.separator") + filepath);
URI uri = fs.makeQualified(file).toUri();
addCacheFile(uri, conf);
}
/**
* Add an archive path to the current set of classpath entries. It adds the archive to cache as
* well. Intended to be used by user code.
*
* @param archive Path of the archive to be added
* @param conf Configuration that contains the classpath setting
* @param fs FileSystem with respect to which {@code archive} should be interpreted.
*/
public static void addArchiveToClassPath(Path archive, Configuration conf, FileSystem fs)
throws IOException {
String archivepath = archive.toUri().getPath();
String classpath = conf.get("mapred.job.classpath.archives");
conf.set(
"mapred.job.classpath.archives",
classpath == null
? archivepath
: classpath + System.getProperty("path.separator") + archivepath);
URI uri = fs.makeQualified(archive).toUri();
addCacheArchive(uri, conf);
}
private static URI addArchiveToClassPathHelper(Path archive, Configuration conf)
throws IOException {
String classpath = conf.get("mapred.job.classpath.archives");
// the scheme/authority use ':' as separator. put the unqualified path in classpath
String archivePath = archive.toUri().getPath();
conf.set(
"mapred.job.classpath.archives",
classpath == null
? archivePath
: classpath + System.getProperty("path.separator") + archivePath);
return archive.makeQualified(archive.getFileSystem(conf)).toUri();
}
/**
* This method checks to see if symlinks are to be create for the localized cache files in the
* current working directory
*
* @param conf the jobconf
* @return true if symlinks are to be created- else return false
*/
public static boolean getSymlink(Configuration conf) {
String result = conf.get("mapred.create.symlink");
if ("yes".equals(result)) {
return true;
}
return false;
}
/**
* This method checks to see if symlinks are to be create for the localized cache files in the
* current working directory Used by internal DistributedCache code.
*
* @param conf the jobconf
* @return true if symlinks are to be created- else return false
*/
public static boolean getSymlink(Configuration conf) {
String result = conf.get(CACHE_SYMLINK);
if ("yes".equals(result)) {
return true;
}
return false;
}
private static String getConfigString(Configuration config) {
String output = "";
Iterator<Map.Entry<String, String>> iterConfig = config.iterator();
while (iterConfig.hasNext()) {
Map.Entry<String, String> curEntry = iterConfig.next();
output = output + "Key: \t" + curEntry.getKey() + "\nValue: \t" + curEntry.getValue() + "\n";
}
return output;
}
public static InetSocketAddress getAddress(Configuration conf) {
String jobTrackerStr = conf.get("mapred.job.tracker", "localhost:8012");
int colon = jobTrackerStr.indexOf(":");
if (colon < 0) {
throw new RuntimeException("Bad mapred.job.tracker: " + jobTrackerStr);
}
String jobTrackerName = jobTrackerStr.substring(0, colon);
int jobTrackerPort = Integer.parseInt(jobTrackerStr.substring(colon + 1));
return new InetSocketAddress(jobTrackerName, jobTrackerPort);
}
/**
* Get the archive entries in classpath as an array of Path
*
* @param conf Configuration that contains the classpath setting
*/
public static Path[] getArchiveClassPaths(Configuration conf) {
String classpath = conf.get("mapred.job.classpath.archives");
if (classpath == null) return null;
ArrayList list =
Collections.list(new StringTokenizer(classpath, System.getProperty("path.separator")));
Path[] paths = new Path[list.size()];
for (int i = 0; i < list.size(); i++) {
paths[i] = new Path((String) list.get(i));
}
return paths;
}
/** An FSDataset has a directory where it loads its data files. */
public FSDataset(DataStorage storage, Configuration conf) throws IOException {
this.maxBlocksPerDir = conf.getInt("dfs.datanode.numblocks", 64);
FSVolume[] volArray = new FSVolume[storage.getNumStorageDirs()];
for (int idx = 0; idx < storage.getNumStorageDirs(); idx++) {
volArray[idx] = new FSVolume(storage.getStorageDir(idx).getCurrentDir(), conf);
}
volumes = new FSVolumeSet(volArray);
volumeMap = new HashMap<Block, DatanodeBlockInfo>();
volumes.getVolumeMap(volumeMap);
registerMBean(storage.getStorageID());
}
FSVolume(File currentDir, Configuration conf) throws IOException {
this.reserved = conf.getLong("dfs.datanode.du.reserved", 0);
boolean supportAppends = conf.getBoolean("dfs.support.append", false);
File parent = currentDir.getParentFile();
this.detachDir = new File(parent, "detach");
if (detachDir.exists()) {
recoverDetachedBlocks(currentDir, detachDir);
}
// Files that were being written when the datanode was last shutdown
// are now moved back to the data directory. It is possible that
// in the future, we might want to do some sort of datanode-local
// recovery for these blocks. For example, crc validation.
//
this.tmpDir = new File(parent, "tmp");
if (tmpDir.exists()) {
if (supportAppends) {
recoverDetachedBlocks(currentDir, tmpDir);
} else {
FileUtil.fullyDelete(tmpDir);
}
}
this.dataDir = new FSDir(currentDir);
if (!tmpDir.mkdirs()) {
if (!tmpDir.isDirectory()) {
throw new IOException("Mkdirs failed to create " + tmpDir.toString());
}
}
if (!detachDir.mkdirs()) {
if (!detachDir.isDirectory()) {
throw new IOException("Mkdirs failed to create " + detachDir.toString());
}
}
this.usage = new DF(parent, conf);
this.dfsUsage = new DU(parent, conf);
this.dfsUsage.start();
}
/**
* Construct in a named directory.
*
* @param conf
* @param dir
* @throws IOException
*/
public NutchBean(Configuration conf, Path dir) throws IOException {
this.conf = conf;
this.fs = FileSystem.get(this.conf);
if (dir == null) {
dir = new Path(this.conf.get("searcher.dir", "crawl"));
}
final Path luceneConfig = new Path(dir, "search-servers.txt");
final Path solrConfig = new Path(dir, "solr-servers.txt");
if (fs.exists(luceneConfig) || fs.exists(solrConfig)) {
searchBean = new DistributedSearchBean(conf, luceneConfig, solrConfig);
} else {
final Path indexDir = new Path(dir, "index");
final Path indexesDir = new Path(dir, "indexes");
searchBean = new LuceneSearchBean(conf, indexDir, indexesDir);
}
String tableName = conf.get("table.name", "webtable");
table = new HTable(tableName);
summarizerFactory = new SummarizerFactory(conf);
}
/** Start the JobTracker process, listen on the indicated port */
JobTracker(Configuration conf) throws IOException {
//
// Grab some static constants
//
maxCurrentTasks = conf.getInt("mapred.tasktracker.tasks.maximum", 2);
RETIRE_JOB_INTERVAL = conf.getLong("mapred.jobtracker.retirejob.interval", 24 * 60 * 60 * 1000);
RETIRE_JOB_CHECK_INTERVAL = conf.getLong("mapred.jobtracker.retirejob.check", 60 * 1000);
TASK_ALLOC_EPSILON = conf.getFloat("mapred.jobtracker.taskalloc.loadbalance.epsilon", 0.2f);
PAD_FRACTION = conf.getFloat("mapred.jobtracker.taskalloc.capacitypad", 0.1f);
MIN_SLOTS_FOR_PADDING = 3 * maxCurrentTasks;
// This is a directory of temporary submission files. We delete it
// on startup, and can delete any files that we're done with
this.conf = conf;
JobConf jobConf = new JobConf(conf);
this.systemDir = jobConf.getSystemDir();
this.fs = FileSystem.get(conf);
FileUtil.fullyDelete(fs, systemDir);
fs.mkdirs(systemDir);
// Same with 'localDir' except it's always on the local disk.
jobConf.deleteLocalFiles(SUBDIR);
// Set ports, start RPC servers, etc.
InetSocketAddress addr = getAddress(conf);
this.localMachine = addr.getHostName();
this.port = addr.getPort();
this.interTrackerServer = RPC.getServer(this, addr.getPort(), 10, false, conf);
this.interTrackerServer.start();
Properties p = System.getProperties();
for (Iterator it = p.keySet().iterator(); it.hasNext(); ) {
String key = (String) it.next();
String val = (String) p.getProperty(key);
LOG.info("Property '" + key + "' is " + val);
}
this.infoPort = conf.getInt("mapred.job.tracker.info.port", 50030);
this.infoServer = new JobTrackerInfoServer(this, infoPort);
this.infoServer.start();
this.startTime = System.currentTimeMillis();
new Thread(this.expireTrackers).start();
new Thread(this.retireJobs).start();
new Thread(this.initJobs).start();
}
/**
* Test how IPC cache map works.
*
* @throws Exception If failed.
*/
@SuppressWarnings("unchecked")
public void testIpcCache() throws Exception {
Field cacheField = GridGgfsHadoopIpcIo.class.getDeclaredField("ipcCache");
cacheField.setAccessible(true);
Field activeCntField = GridGgfsHadoopIpcIo.class.getDeclaredField("activeCnt");
activeCntField.setAccessible(true);
Map<String, GridGgfsHadoopIpcIo> cache =
(Map<String, GridGgfsHadoopIpcIo>) cacheField.get(null);
String name = "ggfs:" + getTestGridName(0) + "@";
Configuration cfg = new Configuration();
cfg.addResource(U.resolveGridGainUrl(HADOOP_FS_CFG));
cfg.setBoolean("fs.ggfs.impl.disable.cache", true);
cfg.setBoolean(String.format(GridGgfsHadoopUtils.PARAM_GGFS_ENDPOINT_NO_EMBED, name), true);
// Ensure that existing IO is reused.
FileSystem fs1 = FileSystem.get(new URI("ggfs://" + name + "/"), cfg);
assertEquals(1, cache.size());
GridGgfsHadoopIpcIo io = null;
System.out.println("CACHE: " + cache);
for (String key : cache.keySet()) {
if (key.contains("10500")) {
io = cache.get(key);
break;
}
}
assert io != null;
assertEquals(1, ((AtomicInteger) activeCntField.get(io)).get());
// Ensure that when IO is used by multiple file systems and one of them is closed, IO is not
// stopped.
FileSystem fs2 = FileSystem.get(new URI("ggfs://" + name + "/abc"), cfg);
assertEquals(1, cache.size());
assertEquals(2, ((AtomicInteger) activeCntField.get(io)).get());
fs2.close();
assertEquals(1, cache.size());
assertEquals(1, ((AtomicInteger) activeCntField.get(io)).get());
Field stopField = GridGgfsHadoopIpcIo.class.getDeclaredField("stopping");
stopField.setAccessible(true);
assert !(Boolean) stopField.get(io);
// Ensure that IO is stopped when nobody else is need it.
fs1.close();
assert cache.isEmpty();
assert (Boolean) stopField.get(io);
}
FileDataGenNew(String HDFSMaster) {
fsConf.set("fs.default.name", HDFSMaster);
}
/**
* Add a file to be localized to the conf
*
* @param uri The uri of the cache to be localized
* @param conf Configuration to add the cache to
*/
public static void addCacheFile(URI uri, Configuration conf) {
String files = conf.get("mapred.cache.files");
conf.set("mapred.cache.files", files == null ? uri.toString() : files + "," + uri.toString());
}
/**
* Add a archives to be localized to the conf
*
* @param uri The uri of the cache to be localized
* @param conf Configuration to add the cache to
*/
public static void addSharedCacheArchive(URI uri, Configuration conf) {
String archives = conf.get("mapred.cache.shared.archives");
conf.set(
"mapred.cache.shared.archives",
archives == null ? uri.toString() : archives + "," + uri.toString());
}
/**
* Set the conf to contain the location for localized files
*
* @param conf The conf to modify to contain the localized caches
* @param str a comma separated list of local files
*/
public static void setLocalSharedFiles(Configuration conf, String str) {
conf.set("mapred.cache.shared.localFiles", str);
}
/**
* Set the conf to contain the location for localized archives
*
* @param conf The conf to modify to contain the localized caches
* @param str a comma separated list of local archives
*/
public static void setLocalArchives(Configuration conf, String str) {
conf.set("mapred.cache.localArchives", str);
}
/**
* Get cache files set in the Configuration
*
* @param conf The configuration which contains the files
* @return A URI array of the files set in the Configuration
* @throws IOException
*/
public static URI[] getSharedCacheFiles(Configuration conf) throws IOException {
return StringUtils.stringToURI(conf.getStrings("mapred.cache.shared.files"));
}
/**
* This is to check the timestamp of the files to be localized
*
* @param conf Configuration which stores the timestamp's
* @param timestamps comma separated list of timestamps of files. The order should be the same as
* the order in which the files are added.
*/
public static void setFileTimestamps(Configuration conf, String timestamps) {
conf.set("mapred.cache.files.timestamps", timestamps);
}
/**
* This is to check the timestamp of the archives to be localized
*
* @param conf Configuration which stores the timestamp's
* @param timestamps comma separated list of timestamps of archives. The order should be the same
* as the order in which the archives are added.
*/
public static void setArchiveTimestamps(Configuration conf, String timestamps) {
conf.set("mapred.cache.archives.timestamps", timestamps);
}
public static String[] getSharedFileLength(Configuration conf) {
return conf.getStrings("mapred.cache.shared.files.length");
}
/**
* Get the timestamps of the files
*
* @param conf The configuration which stored the timestamps
* @return a string array of timestamps
* @throws IOException
*/
public static String[] getFileTimestamps(Configuration conf) {
return conf.getStrings("mapred.cache.files.timestamps");
}
/**
* Get the timestamps of the archives
*
* @param conf The configuration which stored the timestamps
* @return a string array of timestamps
* @throws IOException
*/
public static String[] getArchiveTimestamps(Configuration conf) {
return conf.getStrings("mapred.cache.archives.timestamps");
}
/**
* Set the configuration with the given set of files
*
* @param files The list of files that need to be localized
* @param conf Configuration which will be changed
*/
public static void setCacheFiles(URI[] files, Configuration conf) {
String sfiles = StringUtils.uriToString(files);
conf.set("mapred.cache.files", sfiles);
}
/**
* Return the path array of the localized caches
*
* @param conf Configuration that contains the localized archives
* @return A path array of localized caches
* @throws IOException
*/
public static Path[] getLocalCacheArchives(Configuration conf) throws IOException {
return StringUtils.stringToPath(conf.getStrings("mapred.cache.localArchives"));
}
public static void setSharedFileLength(Configuration conf, String length) {
conf.set("mapred.cache.shared.files.length", length);
}
/**
* Return the path array of the localized files
*
* @param conf Configuration that contains the localized files
* @return A path array of localized files
* @throws IOException
*/
public static Path[] getLocalSharedCacheFiles(Configuration conf) throws IOException {
return StringUtils.stringToPath(conf.getStrings("mapred.cache.shared.localFiles"));
}
/**
* Get cache archives set in the Configuration
*
* @param conf The configuration which contains the archives
* @return A URI array of the caches set in the Configuration
* @throws IOException
*/
public static URI[] getCacheArchives(Configuration conf) throws IOException {
return StringUtils.stringToURI(conf.getStrings("mapred.cache.archives"));
}
