/** Check whether the quota is initialized correctly. */
@Test
public void testQuotaInitialization() throws Exception {
final int size = 500;
Path testDir = new Path("/testDir");
long expectedSize = 3 * BLOCKSIZE + BLOCKSIZE / 2;
dfs.mkdirs(testDir);
dfs.setQuota(testDir, size * 4, expectedSize * size * 2);
Path[] testDirs = new Path[size];
for (int i = 0; i < size; i++) {
testDirs[i] = new Path(testDir, "sub" + i);
dfs.mkdirs(testDirs[i]);
dfs.setQuota(testDirs[i], 100, 1000000);
DFSTestUtil.createFile(dfs, new Path(testDirs[i], "a"), expectedSize, (short) 1, 1L);
}
// Directly access the name system to obtain the current cached usage.
INodeDirectory root = fsdir.getRoot();
HashMap<String, Long> nsMap = new HashMap<String, Long>();
HashMap<String, Long> dsMap = new HashMap<String, Long>();
scanDirsWithQuota(root, nsMap, dsMap, false);
fsdir.updateCountForQuota(1);
scanDirsWithQuota(root, nsMap, dsMap, true);
fsdir.updateCountForQuota(2);
scanDirsWithQuota(root, nsMap, dsMap, true);
fsdir.updateCountForQuota(4);
scanDirsWithQuota(root, nsMap, dsMap, true);
}
/** Test truncate over quota does not mark file as UC or create a lease */
@Test(timeout = 60000)
public void testTruncateOverQuota() throws Exception {
final Path dir = new Path("/TestTruncateOverquota");
final Path file = new Path(dir, "file");
// create partial block file
dfs.mkdirs(dir);
DFSTestUtil.createFile(dfs, file, BLOCKSIZE / 2, REPLICATION, seed);
// lower quota to cause exception when appending to partial block
dfs.setQuota(dir, Long.MAX_VALUE - 1, 1);
final INodeDirectory dirNode = fsdir.getINode4Write(dir.toString()).asDirectory();
final long spaceUsed =
dirNode.getDirectoryWithQuotaFeature().getSpaceConsumed().getStorageSpace();
try {
dfs.truncate(file, BLOCKSIZE / 2 - 1);
Assert.fail("truncate didn't fail");
} catch (RemoteException e) {
assertTrue(e.getClassName().contains("DSQuotaExceededException"));
}
// check that the file exists, isn't UC, and has no dangling lease
LeaseManager lm = cluster.getNamesystem().getLeaseManager();
INodeFile inode = fsdir.getINode(file.toString()).asFile();
Assert.assertNotNull(inode);
Assert.assertFalse("should not be UC", inode.isUnderConstruction());
Assert.assertNull("should not have a lease", lm.getLease(inode));
// make sure the quota usage is unchanged
final long newSpaceUsed =
dirNode.getDirectoryWithQuotaFeature().getSpaceConsumed().getStorageSpace();
assertEquals(spaceUsed, newSpaceUsed);
// make sure edits aren't corrupted
dfs.recoverLease(file);
cluster.restartNameNodes();
}
/** Test allow-snapshot operation. */
@Test(timeout = 15000)
public void testAllowSnapshot() throws Exception {
final String pathStr = sub1.toString();
final INode before = fsdir.getINode(pathStr);
// Before a directory is snapshottable
Assert.assertFalse(before.asDirectory().isSnapshottable());
// After a directory is snapshottable
final Path path = new Path(pathStr);
hdfs.allowSnapshot(path);
{
final INode after = fsdir.getINode(pathStr);
Assert.assertTrue(after.asDirectory().isSnapshottable());
}
hdfs.disallowSnapshot(path);
{
final INode after = fsdir.getINode(pathStr);
Assert.assertFalse(after.asDirectory().isSnapshottable());
}
}
/** Test if the quota can be correctly updated when file length is updated through fsync */
@Test(timeout = 60000)
public void testUpdateQuotaForFSync() throws Exception {
final Path foo = new Path("/foo");
final Path bar = new Path(foo, "bar");
DFSTestUtil.createFile(dfs, bar, BLOCKSIZE, REPLICATION, 0L);
dfs.setQuota(foo, Long.MAX_VALUE - 1, Long.MAX_VALUE - 1);
FSDataOutputStream out = dfs.append(bar);
out.write(new byte[BLOCKSIZE / 4]);
((DFSOutputStream) out.getWrappedStream())
.hsync(EnumSet.of(HdfsDataOutputStream.SyncFlag.UPDATE_LENGTH));
INodeDirectory fooNode = fsdir.getINode4Write(foo.toString()).asDirectory();
QuotaCounts quota = fooNode.getDirectoryWithQuotaFeature().getSpaceConsumed();
long ns = quota.getNameSpace();
long ds = quota.getStorageSpace();
assertEquals(2, ns); // foo and bar
assertEquals(BLOCKSIZE * 2 * REPLICATION, ds); // file is under construction
out.write(new byte[BLOCKSIZE / 4]);
out.close();
fooNode = fsdir.getINode4Write(foo.toString()).asDirectory();
quota = fooNode.getDirectoryWithQuotaFeature().getSpaceConsumed();
ns = quota.getNameSpace();
ds = quota.getStorageSpace();
assertEquals(2, ns);
assertEquals((BLOCKSIZE + BLOCKSIZE / 2) * REPLICATION, ds);
// append another block
DFSTestUtil.appendFile(dfs, bar, BLOCKSIZE);
quota = fooNode.getDirectoryWithQuotaFeature().getSpaceConsumed();
ns = quota.getNameSpace();
ds = quota.getStorageSpace();
assertEquals(2, ns); // foo and bar
assertEquals((BLOCKSIZE * 2 + BLOCKSIZE / 2) * REPLICATION, ds);
}
/**
* Test append over a specific type of storage quota does not mark file as UC or create a lease
*/
@Test(timeout = 60000)
public void testAppendOverTypeQuota() throws Exception {
final Path dir = new Path("/TestAppendOverTypeQuota");
final Path file = new Path(dir, "file");
// create partial block file
dfs.mkdirs(dir);
// set the storage policy on dir
dfs.setStoragePolicy(dir, HdfsConstants.ONESSD_STORAGE_POLICY_NAME);
DFSTestUtil.createFile(dfs, file, BLOCKSIZE / 2, REPLICATION, seed);
// set quota of SSD to 1L
dfs.setQuotaByStorageType(dir, StorageType.SSD, 1L);
final INodeDirectory dirNode = fsdir.getINode4Write(dir.toString()).asDirectory();
final long spaceUsed =
dirNode.getDirectoryWithQuotaFeature().getSpaceConsumed().getStorageSpace();
try {
DFSTestUtil.appendFile(dfs, file, BLOCKSIZE);
Assert.fail("append didn't fail");
} catch (QuotaByStorageTypeExceededException e) {
// ignore
}
// check that the file exists, isn't UC, and has no dangling lease
LeaseManager lm = cluster.getNamesystem().getLeaseManager();
INodeFile inode = fsdir.getINode(file.toString()).asFile();
Assert.assertNotNull(inode);
Assert.assertFalse("should not be UC", inode.isUnderConstruction());
Assert.assertNull("should not have a lease", lm.getLease(inode));
// make sure the quota usage is unchanged
final long newSpaceUsed =
dirNode.getDirectoryWithQuotaFeature().getSpaceConsumed().getStorageSpace();
assertEquals(spaceUsed, newSpaceUsed);
// make sure edits aren't corrupted
dfs.recoverLease(file);
cluster.restartNameNodes();
}
/** Test if the quota can be correctly updated for create file */
@Test(timeout = 60000)
public void testQuotaUpdateWithFileCreate() throws Exception {
final Path foo = new Path(dir, "foo");
Path createdFile = new Path(foo, "created_file.data");
dfs.mkdirs(foo);
dfs.setQuota(foo, Long.MAX_VALUE - 1, Long.MAX_VALUE - 1);
long fileLen = BLOCKSIZE * 2 + BLOCKSIZE / 2;
DFSTestUtil.createFile(dfs, createdFile, BLOCKSIZE / 16, fileLen, BLOCKSIZE, REPLICATION, seed);
INode fnode = fsdir.getINode4Write(foo.toString());
assertTrue(fnode.isDirectory());
assertTrue(fnode.isQuotaSet());
QuotaCounts cnt = fnode.asDirectory().getDirectoryWithQuotaFeature().getSpaceConsumed();
assertEquals(2, cnt.getNameSpace());
assertEquals(fileLen * REPLICATION, cnt.getStorageSpace());
}
/** Test if the quota can be correctly updated for append */
@Test(timeout = 60000)
public void testUpdateQuotaForAppend() throws Exception {
final Path foo = new Path(dir, "foo");
final Path bar = new Path(foo, "bar");
long currentFileLen = BLOCKSIZE;
DFSTestUtil.createFile(dfs, bar, currentFileLen, REPLICATION, seed);
dfs.setQuota(foo, Long.MAX_VALUE - 1, Long.MAX_VALUE - 1);
// append half of the block data, the previous file length is at block
// boundary
DFSTestUtil.appendFile(dfs, bar, BLOCKSIZE / 2);
currentFileLen += (BLOCKSIZE / 2);
INodeDirectory fooNode = fsdir.getINode4Write(foo.toString()).asDirectory();
assertTrue(fooNode.isQuotaSet());
QuotaCounts quota = fooNode.getDirectoryWithQuotaFeature().getSpaceConsumed();
long ns = quota.getNameSpace();
long ds = quota.getStorageSpace();
assertEquals(2, ns); // foo and bar
assertEquals(currentFileLen * REPLICATION, ds);
ContentSummary c = dfs.getContentSummary(foo);
assertEquals(c.getSpaceConsumed(), ds);
// append another block, the previous file length is not at block boundary
DFSTestUtil.appendFile(dfs, bar, BLOCKSIZE);
currentFileLen += BLOCKSIZE;
quota = fooNode.getDirectoryWithQuotaFeature().getSpaceConsumed();
ns = quota.getNameSpace();
ds = quota.getStorageSpace();
assertEquals(2, ns); // foo and bar
assertEquals(currentFileLen * REPLICATION, ds);
c = dfs.getContentSummary(foo);
assertEquals(c.getSpaceConsumed(), ds);
// append several blocks
DFSTestUtil.appendFile(dfs, bar, BLOCKSIZE * 3 + BLOCKSIZE / 8);
currentFileLen += (BLOCKSIZE * 3 + BLOCKSIZE / 8);
quota = fooNode.getDirectoryWithQuotaFeature().getSpaceConsumed();
ns = quota.getNameSpace();
ds = quota.getStorageSpace();
assertEquals(2, ns); // foo and bar
assertEquals(currentFileLen * REPLICATION, ds);
c = dfs.getContentSummary(foo);
assertEquals(c.getSpaceConsumed(), ds);
}
/** modified by tony */
@SuppressWarnings("deprecation")
int loadEditRecords(int logVersion, DataInputStream in, boolean closeOnExit) throws IOException {
FSNamesystem.LOG.info("logversion: " + logVersion);
FSDirectory fsDir = fsNamesys.dir;
int numEdits = 0;
String clientName = null;
String clientMachine = null;
String path = null;
int numOpAdd = 0,
numOpClose = 0,
numOpDelete = 0,
numOpRenameOld = 0,
numOpSetRepl = 0,
numOpMkDir = 0,
numOpSetPerm = 0,
numOpSetOwner = 0,
numOpSetGenStamp = 0,
numOpTimes = 0,
numOpRename = 0,
numOpConcatDelete = 0,
numOpSymlink = 0,
numOpGetDelegationToken = 0,
numOpRenewDelegationToken = 0,
numOpCancelDelegationToken = 0,
numOpUpdateMasterKey = 0,
numOpOther = 0;
try {
while (true) {
long timestamp = 0;
long mtime = 0;
long atime = 0;
long blockSize = 0;
byte opcode = -1;
try {
in.mark(1);
opcode = in.readByte();
if (opcode == Ops.OP_INVALID) {
in.reset(); // reset back to end of file if somebody reads it again
break; // no more transactions
}
} catch (EOFException e) {
break; // no more transactions
}
numEdits++;
switch (opcode) {
case Ops.OP_ADD:
case Ops.OP_CLOSE:
{
// versions > 0 support per file replication
// get name and replication
int length = in.readInt();
// modified by tony
if (-7 == logVersion && length != 3
|| -17 < logVersion && logVersion < -7 && length != 4
|| logVersion <= -17 && length != 7) {
throw new IOException(
"Incorrect data format."
+ " logVersion is "
+ logVersion
+ " but writables.length is "
+ length
+ ". ");
}
path = FSImageSerialization.readString(in);
short replication = fsNamesys.adjustReplication(readShort(in));
mtime = readLong(in);
if (LayoutVersion.supports(Feature.FILE_ACCESS_TIME, logVersion)) {
atime = readLong(in);
}
if (logVersion < -7) {
blockSize = readLong(in);
}
long fileSize = readLong(in);
byte type = (byte) readLong(in);
// get blocks
boolean isFileUnderConstruction = (opcode == Ops.OP_ADD);
BlockInfo blocks[] = readBlocks(in, logVersion, isFileUnderConstruction, replication);
// Older versions of HDFS does not store the block size in inode.
// If the file has more than one block, use the size of the
// first block as the blocksize. Otherwise use the default
// block size.
if (-8 <= logVersion && blockSize == 0) {
if (blocks.length > 1) {
blockSize = blocks[0].getNumBytes();
} else {
long first = ((blocks.length == 1) ? blocks[0].getNumBytes() : 0);
blockSize = Math.max(fsNamesys.getDefaultBlockSize(), first);
}
}
PermissionStatus permissions = fsNamesys.getUpgradePermission();
if (logVersion <= -11) {
permissions = PermissionStatus.read(in);
}
CodingMatrix codingMatrix = CodingMatrix.getMatrixofCertainType(type);
codingMatrix.readFields(in);
/** added by tony* */
LongWritable offset = new LongWritable();
offset.readFields(in);
long headeroffset = offset.get();
// clientname, clientMachine and block locations of last block.
if (opcode == Ops.OP_ADD && logVersion <= -12) {
clientName = FSImageSerialization.readString(in);
clientMachine = FSImageSerialization.readString(in);
if (-13 <= logVersion) {
readDatanodeDescriptorArray(in);
}
} else {
clientName = "";
clientMachine = "";
}
// The open lease transaction re-creates a file if necessary.
// Delete the file if it already exists.
if (FSNamesystem.LOG.isDebugEnabled()) {
FSNamesystem.LOG.debug(
opcode
+ ": "
+ path
+ " numblocks : "
+ blocks.length
+ " clientHolder "
+ clientName
+ " clientMachine "
+ clientMachine);
}
fsDir.unprotectedDelete(path, mtime);
/** modified by tony add to the file tree */
INodeFile node =
(INodeFile)
fsDir.unprotectedAddFile(
path,
permissions,
codingMatrix,
headeroffset,
fileSize,
blocks,
replication,
mtime,
atime,
blockSize);
if (isFileUnderConstruction) {
numOpAdd++;
//
// Replace current node with a INodeUnderConstruction.
// Recreate in-memory lease record.
//
// INodeFileUnderConstruction cons = new INodeFileUnderConstruction(
// node.getLocalNameBytes(),
// node.getReplication(),
// node.getModificationTime(),
// node.getPreferredBlockSize(),
// node.getBlocks(),
// node.getPermissionStatus(),
// clientName,
// clientMachine,
// null);
// TODO:
INodeFileUnderConstruction cons = null;
fsDir.replaceNode(path, node, cons);
fsNamesys.leaseManager.addLease(cons.getClientName(), path);
}
break;
}
case Ops.OP_SET_REPLICATION:
{
numOpSetRepl++;
path = FSImageSerialization.readString(in);
short replication = fsNamesys.adjustReplication(readShort(in));
fsDir.unprotectedSetReplication(path, replication, null);
break;
}
case Ops.OP_CONCAT_DELETE:
{
numOpConcatDelete++;
int length = in.readInt();
if (length < 3) { // trg, srcs.., timestam
throw new IOException("Incorrect data format. " + "Mkdir operation.");
}
String trg = FSImageSerialization.readString(in);
int srcSize = length - 1 - 1; // trg and timestamp
String[] srcs = new String[srcSize];
for (int i = 0; i < srcSize; i++) {
srcs[i] = FSImageSerialization.readString(in);
}
timestamp = readLong(in);
fsDir.unprotectedConcat(trg, srcs);
break;
}
case Ops.OP_RENAME_OLD:
{
numOpRenameOld++;
int length = in.readInt();
if (length != 3) {
throw new IOException("Incorrect data format. " + "Mkdir operation.");
}
String s = FSImageSerialization.readString(in);
String d = FSImageSerialization.readString(in);
timestamp = readLong(in);
HdfsFileStatus dinfo = fsDir.getFileInfo(d, false);
fsDir.unprotectedRenameTo(s, d, timestamp);
fsNamesys.changeLease(s, d, dinfo);
break;
}
case Ops.OP_DELETE:
{
numOpDelete++;
int length = in.readInt();
if (length != 2) {
throw new IOException("Incorrect data format. " + "delete operation.");
}
path = FSImageSerialization.readString(in);
timestamp = readLong(in);
fsDir.unprotectedDelete(path, timestamp);
break;
}
case Ops.OP_MKDIR:
{
numOpMkDir++;
PermissionStatus permissions = fsNamesys.getUpgradePermission();
int length = in.readInt();
if (-17 < logVersion && length != 2 || logVersion <= -17 && length != 3) {
throw new IOException("Incorrect data format. " + "Mkdir operation.");
}
path = FSImageSerialization.readString(in);
timestamp = readLong(in);
// The disk format stores atimes for directories as well.
// However, currently this is not being updated/used because of
// performance reasons.
if (LayoutVersion.supports(Feature.FILE_ACCESS_TIME, logVersion)) {
atime = readLong(in);
}
if (logVersion <= -11) {
permissions = PermissionStatus.read(in);
}
fsDir.unprotectedMkdir(path, permissions, timestamp);
break;
}
case Ops.OP_SET_GENSTAMP:
{
numOpSetGenStamp++;
long lw = in.readLong();
fsNamesys.setGenerationStamp(lw);
break;
}
case Ops.OP_DATANODE_ADD:
{
numOpOther++;
// Datanodes are not persistent any more.
FSImageSerialization.DatanodeImage.skipOne(in);
break;
}
case Ops.OP_DATANODE_REMOVE:
{
numOpOther++;
DatanodeID nodeID = new DatanodeID();
nodeID.readFields(in);
// Datanodes are not persistent any more.
break;
}
case Ops.OP_SET_PERMISSIONS:
{
numOpSetPerm++;
fsDir.unprotectedSetPermission(
FSImageSerialization.readString(in), FsPermission.read(in));
break;
}
case Ops.OP_SET_OWNER:
{
numOpSetOwner++;
fsDir.unprotectedSetOwner(
FSImageSerialization.readString(in),
FSImageSerialization.readString_EmptyAsNull(in),
FSImageSerialization.readString_EmptyAsNull(in));
break;
}
case Ops.OP_SET_NS_QUOTA:
{
fsDir.unprotectedSetQuota(
FSImageSerialization.readString(in),
readLongWritable(in),
FSConstants.QUOTA_DONT_SET);
break;
}
case Ops.OP_CLEAR_NS_QUOTA:
{
fsDir.unprotectedSetQuota(
FSImageSerialization.readString(in),
FSConstants.QUOTA_RESET,
FSConstants.QUOTA_DONT_SET);
break;
}
case Ops.OP_SET_QUOTA:
fsDir.unprotectedSetQuota(
FSImageSerialization.readString(in), readLongWritable(in), readLongWritable(in));
break;
case Ops.OP_TIMES:
{
numOpTimes++;
int length = in.readInt();
if (length != 3) {
throw new IOException("Incorrect data format. " + "times operation.");
}
path = FSImageSerialization.readString(in);
mtime = readLong(in);
atime = readLong(in);
fsDir.unprotectedSetTimes(path, mtime, atime, true);
break;
}
case Ops.OP_SYMLINK:
{
numOpSymlink++;
int length = in.readInt();
if (length != 4) {
throw new IOException("Incorrect data format. " + "symlink operation.");
}
path = FSImageSerialization.readString(in);
String value = FSImageSerialization.readString(in);
mtime = readLong(in);
atime = readLong(in);
PermissionStatus perm = PermissionStatus.read(in);
fsDir.unprotectedSymlink(path, value, mtime, atime, perm);
break;
}
case Ops.OP_RENAME:
{
numOpRename++;
int length = in.readInt();
if (length != 3) {
throw new IOException("Incorrect data format. " + "Mkdir operation.");
}
String s = FSImageSerialization.readString(in);
String d = FSImageSerialization.readString(in);
timestamp = readLong(in);
Rename[] options = readRenameOptions(in);
HdfsFileStatus dinfo = fsDir.getFileInfo(d, false);
fsDir.unprotectedRenameTo(s, d, timestamp, options);
fsNamesys.changeLease(s, d, dinfo);
break;
}
case Ops.OP_GET_DELEGATION_TOKEN:
{
numOpGetDelegationToken++;
DelegationTokenIdentifier delegationTokenId = new DelegationTokenIdentifier();
delegationTokenId.readFields(in);
long expiryTime = readLong(in);
fsNamesys
.getDelegationTokenSecretManager()
.addPersistedDelegationToken(delegationTokenId, expiryTime);
break;
}
case Ops.OP_RENEW_DELEGATION_TOKEN:
{
numOpRenewDelegationToken++;
DelegationTokenIdentifier delegationTokenId = new DelegationTokenIdentifier();
delegationTokenId.readFields(in);
long expiryTime = readLong(in);
fsNamesys
.getDelegationTokenSecretManager()
.updatePersistedTokenRenewal(delegationTokenId, expiryTime);
break;
}
case Ops.OP_CANCEL_DELEGATION_TOKEN:
{
numOpCancelDelegationToken++;
DelegationTokenIdentifier delegationTokenId = new DelegationTokenIdentifier();
delegationTokenId.readFields(in);
fsNamesys
.getDelegationTokenSecretManager()
.updatePersistedTokenCancellation(delegationTokenId);
break;
}
case Ops.OP_UPDATE_MASTER_KEY:
{
numOpUpdateMasterKey++;
DelegationKey delegationKey = new DelegationKey();
delegationKey.readFields(in);
fsNamesys.getDelegationTokenSecretManager().updatePersistedMasterKey(delegationKey);
break;
}
default:
{
throw new IOException("Never seen opcode " + opcode);
}
}
}
} catch (IOException ex) {
check203UpgradeFailure(logVersion, ex);
} finally {
if (closeOnExit) in.close();
}
if (FSImage.LOG.isDebugEnabled()) {
FSImage.LOG.debug(
"numOpAdd = "
+ numOpAdd
+ " numOpClose = "
+ numOpClose
+ " numOpDelete = "
+ numOpDelete
+ " numOpRenameOld = "
+ numOpRenameOld
+ " numOpSetRepl = "
+ numOpSetRepl
+ " numOpMkDir = "
+ numOpMkDir
+ " numOpSetPerm = "
+ numOpSetPerm
+ " numOpSetOwner = "
+ numOpSetOwner
+ " numOpSetGenStamp = "
+ numOpSetGenStamp
+ " numOpTimes = "
+ numOpTimes
+ " numOpConcatDelete = "
+ numOpConcatDelete
+ " numOpRename = "
+ numOpRename
+ " numOpGetDelegationToken = "
+ numOpGetDelegationToken
+ " numOpRenewDelegationToken = "
+ numOpRenewDelegationToken
+ " numOpCancelDelegationToken = "
+ numOpCancelDelegationToken
+ " numOpUpdateMasterKey = "
+ numOpUpdateMasterKey
+ " numOpOther = "
+ numOpOther);
}
return numEdits;
}
SingleIndex(String directoryName, String fileName, String indexPath) {
try {
Directory dir = FSDirectory.open(new File(indexPath)); // write to an directory for checking
Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_48);
IndexWriterConfig iwc = new IndexWriterConfig(Version.LUCENE_48, analyzer);
IndexWriter writer = new IndexWriter(dir, iwc);
String[] files = directoryName.list();
FileInputStream fis;
try {
fis = new FileInputStream(fileName);
} catch (FileNotFoundException fnfe) {
// at least on windows, some temporary files raise this exception with an "access denied"
// message
// checking if the file can be read doesn't help
return;
}
try {
// make a new, empty document
Document doc = new Document();
// Add the path of the file as a field named "path". Use a
// field that is indexed (i.e. searchable), but don't tokenize
// the field into separate words and don't index term frequency
// or positional information:
Field pathField = new StringField("path", file.getPath(), Field.Store.YES);
doc.add(pathField);
// Add the last modified date of the file a field named "modified".
// Use a LongField that is indexed (i.e. efficiently filterable with
// NumericRangeFilter). This indexes to milli-second resolution, which
// is often too fine. You could instead create a number based on
// year/month/day/hour/minutes/seconds, down the resolution you require.
// For example the long value 2011021714 would mean
// February 17, 2011, 2-3 PM.
doc.add(new LongField("modified", file.lastModified(), Field.Store.NO));
// Add the contents of the file to a field named "contents". Specify a Reader,
// so that the text of the file is tokenized and indexed, but not stored.
// Note that FileReader expects the file to be in UTF-8 encoding.
// If that's not the case searching for special characters will fail.
doc.add(
new TextField(
"contents",
new BufferedReader(new InputStreamReader(fis, StandardCharsets.UTF_8))));
if (writer.getConfig().getOpenMode() == OpenMode.CREATE) {
// New index, so we just add the document (no old document can be there):
System.out.println("adding " + file);
writer.addDocument(doc);
} else {
// Existing index (an old copy of this document may have been indexed) so
// we use updateDocument instead to replace the old one matching the exact
// path, if present:
System.out.println("updating " + file);
writer.updateDocument(new Term("path", file.getPath()), doc);
}
} finally {
fis.close();
}
writer.close();
} catch (Exception e) {
e.printStackTrace();
}
}