public void testFormat() throws Exception {
localFs = FileSystem.getLocal(defaultConf);
localFs.delete(workDir, true);
Job job = new Job(new Configuration(defaultConf));
Path file = new Path(workDir, "test.txt");
int seed = new Random().nextInt();
Random random = new Random(seed);
// for a variety of lengths
for (int length = 0; length < MAX_LENGTH; length += random.nextInt(MAX_LENGTH / 10) + 1) {
// create a file with length entries
Writer writer = new OutputStreamWriter(localFs.create(file));
try {
MyClass mc = new MyClass();
for (int i = 0; i < length; i++) {
mc.s = Integer.toString(i);
mc.v = i;
byte[] raw = MessagePack.pack(mc);
byte[] b64e = base64_.encodeBase64(raw);
byte[] b64d = base64_.decode(b64e);
MyClass mc2 = MessagePack.unpack(b64d, mc.getClass());
assertEquals(mc.s, mc2.s);
assertEquals(mc.v, mc2.v);
writer.write(base64_.encodeToString(raw));
}
} finally {
writer.close();
}
checkFormat(job);
}
}
public void inject(Path crawlDb, Path urlDir) throws IOException {
SimpleDateFormat sdf = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss");
long start = System.currentTimeMillis();
if (LOG.isInfoEnabled()) {
LOG.info("Injector: starting at " + sdf.format(start));
LOG.info("Injector: crawlDb: " + crawlDb);
LOG.info("Injector: urlDir: " + urlDir);
}
Path tempDir =
new Path(
getConf().get("mapred.temp.dir", ".")
+ "/inject-temp-"
+ Integer.toString(new Random().nextInt(Integer.MAX_VALUE)));
// map text input file to a <url,CrawlDatum> file
if (LOG.isInfoEnabled()) {
LOG.info("Injector: Converting injected urls to crawl db entries.");
}
JobConf sortJob = new NutchJob(getConf());
sortJob.setJobName("inject " + urlDir);
FileInputFormat.addInputPath(sortJob, urlDir);
sortJob.setMapperClass(InjectMapper.class);
FileOutputFormat.setOutputPath(sortJob, tempDir);
sortJob.setOutputFormat(SequenceFileOutputFormat.class);
sortJob.setOutputKeyClass(Text.class);
sortJob.setOutputValueClass(CrawlDatum.class);
sortJob.setLong("injector.current.time", System.currentTimeMillis());
RunningJob mapJob = JobClient.runJob(sortJob);
long urlsInjected = mapJob.getCounters().findCounter("injector", "urls_injected").getValue();
long urlsFiltered = mapJob.getCounters().findCounter("injector", "urls_filtered").getValue();
LOG.info("Injector: total number of urls rejected by filters: " + urlsFiltered);
LOG.info(
"Injector: total number of urls injected after normalization and filtering: "
+ urlsInjected);
// merge with existing crawl db
if (LOG.isInfoEnabled()) {
LOG.info("Injector: Merging injected urls into crawl db.");
}
JobConf mergeJob = CrawlDb.createJob(getConf(), crawlDb);
FileInputFormat.addInputPath(mergeJob, tempDir);
mergeJob.setReducerClass(InjectReducer.class);
JobClient.runJob(mergeJob);
CrawlDb.install(mergeJob, crawlDb);
// clean up
FileSystem fs = FileSystem.get(getConf());
fs.delete(tempDir, true);
long end = System.currentTimeMillis();
LOG.info(
"Injector: finished at "
+ sdf.format(end)
+ ", elapsed: "
+ TimingUtil.elapsedTime(start, end));
}
private void setupProcedureStore() throws IOException {
Path testDir = UTIL.getDataTestDir();
FileSystem fs = testDir.getFileSystem(conf);
Path logDir = new Path(testDir, "proc-logs");
System.out.println("Logs directory : " + logDir.toString());
fs.delete(logDir, true);
if ("nosync".equals(syncType)) {
store = new NoSyncWalProcedureStore(conf, fs, logDir);
} else {
store = ProcedureTestingUtility.createWalStore(conf, fs, logDir);
}
store.start(numThreads);
store.recoverLease();
store.load(new ProcedureTestingUtility.LoadCounter());
System.out.println(
"Starting new log : " + store.getActiveLogs().get(store.getActiveLogs().size() - 1));
}
public void testFormat() throws Exception {
JobConf job = new JobConf(conf);
FileSystem fs = FileSystem.getLocal(conf);
Path dir = new Path(System.getProperty("test.build.data", ".") + "/mapred");
Path file = new Path(dir, "test.seq");
Reporter reporter = Reporter.NULL;
int seed = new Random().nextInt();
// LOG.info("seed = "+seed);
Random random = new Random(seed);
fs.delete(dir, true);
FileInputFormat.setInputPaths(job, dir);
// for a variety of lengths
for (int length = 0; length < MAX_LENGTH; length += random.nextInt(MAX_LENGTH / 10) + 1) {
// LOG.info("creating; entries = " + length);
// create a file with length entries
SequenceFile.Writer writer =
SequenceFile.createWriter(fs, conf, file, IntWritable.class, BytesWritable.class);
try {
for (int i = 0; i < length; i++) {
IntWritable key = new IntWritable(i);
byte[] data = new byte[random.nextInt(10)];
random.nextBytes(data);
BytesWritable value = new BytesWritable(data);
writer.append(key, value);
}
} finally {
writer.close();
}
// try splitting the file in a variety of sizes
InputFormat<IntWritable, BytesWritable> format =
new SequenceFileInputFormat<IntWritable, BytesWritable>();
IntWritable key = new IntWritable();
BytesWritable value = new BytesWritable();
for (int i = 0; i < 3; i++) {
int numSplits = random.nextInt(MAX_LENGTH / (SequenceFile.SYNC_INTERVAL / 20)) + 1;
// LOG.info("splitting: requesting = " + numSplits);
InputSplit[] splits = format.getSplits(job, numSplits);
// LOG.info("splitting: got = " + splits.length);
// check each split
BitSet bits = new BitSet(length);
for (int j = 0; j < splits.length; j++) {
RecordReader<IntWritable, BytesWritable> reader =
format.getRecordReader(splits[j], job, reporter);
try {
int count = 0;
while (reader.next(key, value)) {
// if (bits.get(key.get())) {
// LOG.info("splits["+j+"]="+splits[j]+" : " +
// key.get());
// LOG.info("@"+reader.getPos());
// }
assertFalse("Key in multiple partitions.", bits.get(key.get()));
bits.set(key.get());
count++;
}
// LOG.info("splits["+j+"]="+splits[j]+" count=" +
// count);
} finally {
reader.close();
}
}
assertEquals("Some keys in no partition.", length, bits.cardinality());
}
}
}
