public void close() throws IOException {
datas.close();
if (sums != null) {
sums.close();
}
set(fs.verifyChecksum, null, 1, 0);
}
/*
* Fetch a file that is in a Hadoop file system. Return a local File.
* Interruptible.
*/
private File hdfsFetch(Path fromPath, Reporter reporter)
throws IOException, InterruptedException {
UUID uniqueId = UUID.randomUUID();
File toFile = new File(tempDir, uniqueId.toString() + "/" + fromPath.getName());
File toDir = new File(toFile.getParent());
if (toDir.exists()) {
FileUtils.deleteDirectory(toDir);
}
toDir.mkdirs();
Path toPath = new Path(toFile.getCanonicalPath());
FileSystem fS = fromPath.getFileSystem(hadoopConf);
FileSystem tofS = FileSystem.getLocal(hadoopConf);
Throttler throttler = new Throttler((double) bytesPerSecThrottle);
try {
for (FileStatus fStatus : fS.globStatus(fromPath)) {
log.info("Copying " + fStatus.getPath() + " to " + toPath);
long bytesSoFar = 0;
FSDataInputStream iS = fS.open(fStatus.getPath());
FSDataOutputStream oS = tofS.create(toPath);
byte[] buffer = new byte[downloadBufferSize];
int nRead;
while ((nRead = iS.read(buffer, 0, buffer.length)) != -1) {
// Needed to being able to be interrupted at any moment.
if (Thread.interrupted()) {
iS.close();
oS.close();
cleanDirNoExceptions(toDir);
throw new InterruptedException();
}
bytesSoFar += nRead;
oS.write(buffer, 0, nRead);
throttler.incrementAndThrottle(nRead);
if (bytesSoFar >= bytesToReportProgress) {
reporter.progress(bytesSoFar);
bytesSoFar = 0l;
}
}
if (reporter != null) {
reporter.progress(bytesSoFar);
}
oS.close();
iS.close();
}
return toDir;
} catch (ClosedByInterruptException e) {
// This can be thrown by the method read.
cleanDirNoExceptions(toDir);
throw new InterruptedIOException();
}
}
public void map(Text key, Text value, Context context)
throws InterruptedException, IOException {
String filename = key.toString();
String json = value.toString();
// Make sure the input is valid
if (!(filename.isEmpty() || json.isEmpty())) {
// Change the json-type feature to Mat-type feature
Mat descriptor = json2mat(json);
if (descriptor != null) {
// Read the query feature from the cache in Hadoop
Mat query_features;
String pathStr = context.getConfiguration().get("featureFilePath");
FileSystem fs = FileSystem.get(context.getConfiguration());
FSDataInputStream fsDataInputStream = fs.open(new Path(pathStr));
StringBuilder sb = new StringBuilder();
// Use a buffer to read the query_feature
int remain = fsDataInputStream.available();
while (remain > 0) {
int read;
byte[] buf = new byte[BUF_SIZE];
read = fsDataInputStream.read(buf, fsDataInputStream.available() - remain, BUF_SIZE);
sb.append(new String(buf, 0, read, StandardCharsets.UTF_8));
remain = remain - read;
System.out.println("remain:" + remain + "\tread:" + read + "\tsb.size:" + sb.length());
}
// Read the query_feature line by line
// Scanner sc = new Scanner(fsDataInputStream, "UTF-8");
// StringBuilder sb = new StringBuilder();
// while (sc.hasNextLine()) {
// sb.append(sc.nextLine());
// }
// String query_json = sb.toString();
// String query_json = new String(buf, StandardCharsets.UTF_8);
String query_json = sb.toString();
fsDataInputStream.close();
query_features = json2mat(query_json);
// Get the similarity of the current database image against the query image
DescriptorMatcher matcher = DescriptorMatcher.create(DescriptorMatcher.FLANNBASED);
MatOfDMatch matches = new MatOfDMatch();
// Ensure the two features have same length of cols (the feature extracted are all 128
// cols(at least in this case))
if (query_features.cols() == descriptor.cols()) {
matcher.match(query_features, descriptor, matches);
DMatch[] dMatches = matches.toArray();
// Calculate the max/min distances
// double max_dist = Double.MAX_VALUE;
// double min_dist = Double.MIN_VALUE;
double max_dist = 0;
double min_dist = 100;
for (int i = 0; i < dMatches.length; i++) {
double dist = dMatches[i].distance;
if (min_dist > dist) min_dist = dist;
if (max_dist < dist) max_dist = dist;
}
// Only distances ≤ threshold are good matches
double threshold = max_dist * THRESHOLD_FACTOR;
// double threshold = min_dist * 2;
LinkedList<DMatch> goodMatches = new LinkedList<DMatch>();
for (int i = 0; i < dMatches.length; i++) {
if (dMatches[i].distance <= threshold) {
goodMatches.addLast(dMatches[i]);
}
}
// Get the ratio of good_matches to all_matches
double ratio = (double) goodMatches.size() / (double) dMatches.length;
System.out.println("*** current_record_filename:" + filename + " ***");
System.out.println("feature:" + descriptor + "\nquery_feature:" + query_features);
System.out.println(
"min_dist of keypoints:" + min_dist + " max_dist of keypoints:" + max_dist);
System.out.println(
"total_matches:" + dMatches.length + "\tgood_matches:" + goodMatches.size());
// System.out.println("type:" + descriptor.type() + " channels:" +
// descriptor.channels() + " rows:" + descriptor.rows() + " cols:" + descriptor.cols());
// System.out.println("qtype:" + query_features.type() + "
// qchannels:" + query_features.channels() + " qrows:" + query_features.rows() + "
// qcols:" + query_features.cols());
System.out.println();
if (ratio > PERCENTAGE_THRESHOLD) {
// Key:1 Value:filename|ratio
context.write(ONE, new Text(filename + "|" + ratio));
// context.write(ONE, new Text(filename + "|" +
// String.valueOf(goodMatches.size())));
}
} else {
System.out.println("The size of the features are not equal");
}
} else {
// a null pointer, do nothing
System.out.println("A broken/null feature:" + filename);
System.out.println();
}
}
}
/**
* Check how prefetch override works.
*
* @throws Exception IF failed.
*/
public void testOpenPrefetchOverride() throws Exception {
create(igfsSecondary, paths(DIR, SUBDIR), paths(FILE));
// Write enough data to the secondary file system.
final int blockSize = IGFS_BLOCK_SIZE;
IgfsOutputStream out = igfsSecondary.append(FILE, false);
int totalWritten = 0;
while (totalWritten < blockSize * 2 + chunk.length) {
out.write(chunk);
totalWritten += chunk.length;
}
out.close();
awaitFileClose(igfsSecondary.asSecondary(), FILE);
// Instantiate file system with overridden "seq reads before prefetch" property.
Configuration cfg = new Configuration();
cfg.addResource(U.resolveIgniteUrl(PRIMARY_CFG));
int seqReads = SEQ_READS_BEFORE_PREFETCH + 1;
cfg.setInt(String.format(PARAM_IGFS_SEQ_READS_BEFORE_PREFETCH, "igfs:grid@"), seqReads);
FileSystem fs = FileSystem.get(new URI(PRIMARY_URI), cfg);
// Read the first two blocks.
Path fsHome = new Path(PRIMARY_URI);
Path dir = new Path(fsHome, DIR.name());
Path subdir = new Path(dir, SUBDIR.name());
Path file = new Path(subdir, FILE.name());
FSDataInputStream fsIn = fs.open(file);
final byte[] readBuf = new byte[blockSize * 2];
fsIn.readFully(0, readBuf, 0, readBuf.length);
// Wait for a while for prefetch to finish (if any).
IgfsMetaManager meta = igfs.context().meta();
IgfsFileInfo info = meta.info(meta.fileId(FILE));
IgfsBlockKey key = new IgfsBlockKey(info.id(), info.affinityKey(), info.evictExclude(), 2);
IgniteCache<IgfsBlockKey, byte[]> dataCache =
igfs.context().kernalContext().cache().jcache(igfs.configuration().getDataCacheName());
for (int i = 0; i < 10; i++) {
if (dataCache.containsKey(key)) break;
else U.sleep(100);
}
fsIn.close();
// Remove the file from the secondary file system.
igfsSecondary.delete(FILE, false);
// Try reading the third block. Should fail.
GridTestUtils.assertThrows(
log,
new Callable<Object>() {
@Override
public Object call() throws Exception {
IgfsInputStream in0 = igfs.open(FILE);
in0.seek(blockSize * 2);
try {
in0.read(readBuf);
} finally {
U.closeQuiet(in0);
}
return null;
}
},
IOException.class,
"Failed to read data due to secondary file system exception: /dir/subdir/file");
}