private String getCollectionFromNamespace(String namespace) {
if (namespace.startsWith(definition.getMongoDb())
&& CharMatcher.is('.').countIn(namespace) == 1) {
return namespace.substring(definition.getMongoDb().length() + 1);
}
logger.info("Cannot get collection from namespace [{}]", namespace);
return null;
}
private DBObject applyFieldFilter(DBObject object) {
if (object instanceof GridFSFile) {
GridFSFile file = (GridFSFile) object;
DBObject metadata = file.getMetaData();
if (metadata != null) {
file.setMetaData(applyFieldFilter(metadata));
}
} else {
object = MongoDBHelper.applyExcludeFields(object, definition.getExcludeFields());
object = MongoDBHelper.applyIncludeFields(object, definition.getIncludeFields());
}
return object;
}
private void isRiverStale(DBCursor cursor, Timestamp<?> time) throws SlurperException {
if (cursor == null || time == null) {
return;
}
if (definition.getInitialTimestamp() != null && time.equals(definition.getInitialTimestamp())) {
return;
}
DBObject entry = cursor.next();
Timestamp<?> oplogTimestamp = Timestamp.on(entry);
if (!time.equals(oplogTimestamp)) {
MongoDBRiverHelper.setRiverStatus(client, definition.getRiverName(), Status.RIVER_STALE);
throw new SlurperException("River out of sync with oplog.rs collection");
}
}
private void processAdminCommandOplogEntry(
final DBObject entry, final Timestamp<?> startTimestamp) throws InterruptedException {
if (logger.isTraceEnabled()) {
logger.trace("processAdminCommandOplogEntry - [{}]", entry);
}
DBObject object = (DBObject) entry.get(MongoDBRiver.OPLOG_OBJECT);
if (definition.isImportAllCollections()) {
if (object.containsField(MongoDBRiver.OPLOG_RENAME_COLLECTION_COMMAND_OPERATION)
&& object.containsField(MongoDBRiver.OPLOG_TO)) {
String to = object.get(MongoDBRiver.OPLOG_TO).toString();
if (to.startsWith(definition.getMongoDb())) {
String newCollection = getCollectionFromNamespace(to);
DBCollection coll = slurpedDb.getCollection(newCollection);
doInitialImport(coll);
}
}
}
}
private void addToStream(
final Operation operation,
final Timestamp<?> currentTimestamp,
final DBObject data,
final String collection)
throws InterruptedException {
if (logger.isTraceEnabled()) {
logger.trace(
"addToStream - operation [{}], currentTimestamp [{}], data [{}], collection [{}]",
operation,
currentTimestamp,
data,
collection);
}
if (operation == Operation.DROP_DATABASE) {
if (definition.isImportAllCollections()) {
for (String name : slurpedDb.getCollectionNames()) {
context
.getStream()
.put(
new MongoDBRiver.QueueEntry(
currentTimestamp, Operation.DROP_COLLECTION, data, name));
}
} else {
context
.getStream()
.put(
new MongoDBRiver.QueueEntry(
currentTimestamp, Operation.DROP_COLLECTION, data, collection));
}
} else {
context
.getStream()
.put(new MongoDBRiver.QueueEntry(currentTimestamp, operation, data, collection));
}
}
public Slurper(
List<ServerAddress> mongoServers,
MongoDBRiverDefinition definition,
SharedContext context,
Client client) {
this.definition = definition;
this.context = context;
this.client = client;
this.mongo = new MongoClient(mongoServers, definition.getMongoClientOptions());
this.findKeys = new BasicDBObject();
this.gridfsOplogNamespace =
definition.getMongoOplogNamespace() + MongoDBRiver.GRIDFS_FILES_SUFFIX;
this.cmdOplogNamespace = definition.getMongoDb() + "." + MongoDBRiver.OPLOG_NAMESPACE_COMMAND;
if (definition.getExcludeFields() != null) {
for (String key : definition.getExcludeFields()) {
findKeys.put(key, 0);
}
} else if (definition.getIncludeFields() != null) {
for (String key : definition.getIncludeFields()) {
findKeys.put(key, 1);
}
}
}
@Override
public void run() {
while (context.getStatus() == Status.RUNNING) {
try {
if (!assignCollections()) {
break; // failed to assign oplogCollection or
// slurpedCollection
}
Timestamp<?> startTimestamp = null;
if (!definition.isSkipInitialImport()) {
if (!riverHasIndexedFromOplog() && definition.getInitialTimestamp() == null) {
if (!isIndexEmpty()) {
MongoDBRiverHelper.setRiverStatus(
client, definition.getRiverName(), Status.INITIAL_IMPORT_FAILED);
break;
}
if (definition.isImportAllCollections()) {
for (String name : slurpedDb.getCollectionNames()) {
DBCollection collection = slurpedDb.getCollection(name);
startTimestamp = doInitialImport(collection);
}
} else {
DBCollection collection = slurpedDb.getCollection(definition.getMongoCollection());
startTimestamp = doInitialImport(collection);
}
}
} else {
logger.info("Skip initial import from collection {}", definition.getMongoCollection());
}
// Slurp from oplog
DBCursor cursor = null;
try {
cursor = oplogCursor(startTimestamp);
if (cursor == null) {
cursor = processFullOplog();
}
while (cursor.hasNext()) {
DBObject item = cursor.next();
startTimestamp = processOplogEntry(item, startTimestamp);
}
logger.debug("Before waiting for 500 ms");
Thread.sleep(500);
} catch (MongoException.CursorNotFound e) {
logger.info(
"Cursor {} has been closed. About to open a new cusor.", cursor.getCursorId());
logger.debug("Total document inserted [{}]", totalDocuments.get());
} catch (SlurperException sEx) {
logger.warn("Exception in slurper", sEx);
break;
} catch (Exception ex) {
logger.warn("Exception while looping in cursor", ex);
Thread.currentThread().interrupt();
break;
} finally {
if (cursor != null) {
logger.trace("Closing oplog cursor");
cursor.close();
}
}
} catch (MongoInterruptedException mIEx) {
logger.warn("Mongo driver has been interrupted", mIEx);
if (mongo != null) {
mongo.close();
mongo = null;
}
Thread.currentThread().interrupt();
break;
} catch (MongoException e) {
logger.error("Mongo gave an exception", e);
try {
Thread.sleep(5000);
} catch (InterruptedException iEx) {
}
} catch (NoSuchElementException e) {
logger.warn("A mongoDB cursor bug ?", e);
} catch (InterruptedException e) {
logger.info("river-mongodb slurper interrupted");
Thread.currentThread().interrupt();
break;
}
}
}
private String addInsertToStream(final Timestamp<?> currentTimestamp, final DBObject data)
throws InterruptedException {
return addInsertToStream(currentTimestamp, data, definition.getMongoCollection());
}
private boolean isValidOplogEntry(final DBObject entry, final Timestamp<?> startTimestamp) {
if (MongoDBRiver.OPLOG_NOOP_OPERATION.equals(entry.get(MongoDBRiver.OPLOG_OPERATION))) {
logger.debug("[No-op Oplog Entry] - can be ignored. {}", entry);
return false;
}
String namespace = (String) entry.get(MongoDBRiver.OPLOG_NAMESPACE);
// Initial support for sharded collection -
// https://jira.mongodb.org/browse/SERVER-4333
// Not interested in operation from migration or sharding
if (entry.containsField(MongoDBRiver.OPLOG_FROM_MIGRATE)
&& ((BasicBSONObject) entry).getBoolean(MongoDBRiver.OPLOG_FROM_MIGRATE)) {
logger.debug(
"[Invalid Oplog Entry] - from migration or sharding operation. Can be ignored. {}",
entry);
return false;
}
// Not interested by chunks - skip all
if (namespace.endsWith(MongoDBRiver.GRIDFS_CHUNKS_SUFFIX)) {
return false;
}
if (startTimestamp != null) {
Timestamp<?> oplogTimestamp = Timestamp.on(entry);
if (Timestamp.compare(oplogTimestamp, startTimestamp) < 0) {
logger.debug(
"[Invalid Oplog Entry] - entry timestamp [{}] before startTimestamp [{}]",
entry,
startTimestamp);
return false;
}
}
boolean validNamespace = false;
if (definition.isMongoGridFS()) {
validNamespace = gridfsOplogNamespace.equals(namespace);
} else {
if (definition.isImportAllCollections()) {
// Skip temp entry generated by map / reduce
if (namespace.startsWith(definition.getMongoDb())
&& !namespace.startsWith(definition.getMongoDb() + ".tmp.mr")) {
validNamespace = true;
}
} else {
if (definition.getMongoOplogNamespace().equals(namespace)) {
validNamespace = true;
}
}
if (cmdOplogNamespace.equals(namespace)) {
validNamespace = true;
}
if (MongoDBRiver.OPLOG_ADMIN_COMMAND.equals(namespace)) {
validNamespace = true;
}
}
if (!validNamespace) {
logger.debug("[Invalid Oplog Entry] - namespace [{}] is not valid", namespace);
return false;
}
String operation = (String) entry.get(MongoDBRiver.OPLOG_OPERATION);
if (!oplogOperations.contains(operation)) {
logger.debug("[Invalid Oplog Entry] - operation [{}] is not valid", operation);
return false;
}
// TODO: implement a better solution
if (definition.getMongoOplogFilter() != null) {
DBObject object = (DBObject) entry.get(MongoDBRiver.OPLOG_OBJECT);
BasicDBObject filter = definition.getMongoOplogFilter();
if (!filterMatch(filter, object)) {
logger.debug(
"[Invalid Oplog Entry] - filter [{}] does not match object [{}]", filter, object);
return false;
}
}
return true;
}
private Timestamp<?> processOplogEntry(final DBObject entry, final Timestamp<?> startTimestamp)
throws InterruptedException {
// To support transactions, TokuMX wraps one or more operations in a single oplog entry, in a
// list.
// As long as clients are not transaction-aware, we can pretty safely assume there will only be
// one operation in the list.
// Supporting genuine multi-operation transactions will require a bit more logic here.
flattenOps(entry);
if (!isValidOplogEntry(entry, startTimestamp)) {
return startTimestamp;
}
Operation operation = Operation.fromString(entry.get(MongoDBRiver.OPLOG_OPERATION).toString());
String namespace = entry.get(MongoDBRiver.OPLOG_NAMESPACE).toString();
String collection = null;
Timestamp<?> oplogTimestamp = Timestamp.on(entry);
DBObject object = (DBObject) entry.get(MongoDBRiver.OPLOG_OBJECT);
if (definition.isImportAllCollections()) {
if (namespace.startsWith(definition.getMongoDb()) && !namespace.equals(cmdOplogNamespace)) {
collection = getCollectionFromNamespace(namespace);
}
} else {
collection = definition.getMongoCollection();
}
if (namespace.equals(cmdOplogNamespace)) {
if (object.containsField(MongoDBRiver.OPLOG_DROP_COMMAND_OPERATION)) {
operation = Operation.DROP_COLLECTION;
if (definition.isImportAllCollections()) {
collection = object.get(MongoDBRiver.OPLOG_DROP_COMMAND_OPERATION).toString();
if (collection.startsWith("tmp.mr.")) {
return startTimestamp;
}
}
}
if (object.containsField(MongoDBRiver.OPLOG_DROP_DATABASE_COMMAND_OPERATION)) {
operation = Operation.DROP_DATABASE;
}
}
logger.trace("namespace: {} - operation: {}", namespace, operation);
if (namespace.equals(MongoDBRiver.OPLOG_ADMIN_COMMAND)) {
if (operation == Operation.COMMAND) {
processAdminCommandOplogEntry(entry, startTimestamp);
return startTimestamp;
}
}
if (logger.isTraceEnabled()) {
logger.trace("MongoDB object deserialized: {}", object.toString());
logger.trace("collection: {}", collection);
logger.trace("oplog entry - namespace [{}], operation [{}]", namespace, operation);
logger.trace("oplog processing item {}", entry);
}
String objectId = getObjectIdFromOplogEntry(entry);
if (operation == Operation.DELETE) {
// Include only _id in data, as vanilla MongoDB does, so transformation scripts won't be
// broken by Toku
if (object.containsField(MongoDBRiver.MONGODB_ID_FIELD)) {
if (object.keySet().size() > 1) {
entry.put(
MongoDBRiver.OPLOG_OBJECT,
object = new BasicDBObject(MongoDBRiver.MONGODB_ID_FIELD, objectId));
}
} else {
throw new NullPointerException(MongoDBRiver.MONGODB_ID_FIELD);
}
}
if (definition.isMongoGridFS()
&& namespace.endsWith(MongoDBRiver.GRIDFS_FILES_SUFFIX)
&& (operation == Operation.INSERT || operation == Operation.UPDATE)) {
if (objectId == null) {
throw new NullPointerException(MongoDBRiver.MONGODB_ID_FIELD);
}
GridFS grid = new GridFS(mongo.getDB(definition.getMongoDb()), collection);
GridFSDBFile file = grid.findOne(new ObjectId(objectId));
if (file != null) {
logger.info("Caught file: {} - {}", file.getId(), file.getFilename());
object = file;
} else {
logger.warn("Cannot find file from id: {}", objectId);
}
}
if (object instanceof GridFSDBFile) {
if (objectId == null) {
throw new NullPointerException(MongoDBRiver.MONGODB_ID_FIELD);
}
if (logger.isTraceEnabled()) {
logger.trace("Add attachment: {}", objectId);
}
addToStream(operation, oplogTimestamp, applyFieldFilter(object), collection);
} else {
if (operation == Operation.UPDATE) {
DBObject update = (DBObject) entry.get(MongoDBRiver.OPLOG_UPDATE);
logger.debug("Updated item: {}", update);
addQueryToStream(operation, oplogTimestamp, update, collection);
} else {
if (operation == Operation.INSERT) {
addInsertToStream(oplogTimestamp, applyFieldFilter(object), collection);
} else {
addToStream(operation, oplogTimestamp, applyFieldFilter(object), collection);
}
}
}
return oplogTimestamp;
}
protected boolean assignCollections() {
DB adminDb = mongo.getDB(MongoDBRiver.MONGODB_ADMIN_DATABASE);
oplogDb = mongo.getDB(MongoDBRiver.MONGODB_LOCAL_DATABASE);
if (!definition.getMongoAdminUser().isEmpty()
&& !definition.getMongoAdminPassword().isEmpty()) {
logger.info(
"Authenticate {} with {}",
MongoDBRiver.MONGODB_ADMIN_DATABASE,
definition.getMongoAdminUser());
CommandResult cmd =
adminDb.authenticateCommand(
definition.getMongoAdminUser(), definition.getMongoAdminPassword().toCharArray());
if (!cmd.ok()) {
logger.error(
"Autenticatication failed for {}: {}",
MongoDBRiver.MONGODB_ADMIN_DATABASE,
cmd.getErrorMessage());
// Can still try with mongoLocal credential if provided.
// return false;
}
oplogDb = adminDb.getMongo().getDB(MongoDBRiver.MONGODB_LOCAL_DATABASE);
}
if (!definition.getMongoLocalUser().isEmpty()
&& !definition.getMongoLocalPassword().isEmpty()
&& !oplogDb.isAuthenticated()) {
logger.info(
"Authenticate {} with {}",
MongoDBRiver.MONGODB_LOCAL_DATABASE,
definition.getMongoLocalUser());
CommandResult cmd =
oplogDb.authenticateCommand(
definition.getMongoLocalUser(), definition.getMongoLocalPassword().toCharArray());
if (!cmd.ok()) {
logger.error(
"Autenticatication failed for {}: {}",
MongoDBRiver.MONGODB_LOCAL_DATABASE,
cmd.getErrorMessage());
return false;
}
}
Set<String> collections = oplogDb.getCollectionNames();
if (!collections.contains(MongoDBRiver.OPLOG_COLLECTION)) {
logger.error(
"Cannot find "
+ MongoDBRiver.OPLOG_COLLECTION
+ " collection. Please check this link: http://goo.gl/2x5IW");
return false;
}
oplogCollection = oplogDb.getCollection(MongoDBRiver.OPLOG_COLLECTION);
slurpedDb = mongo.getDB(definition.getMongoDb());
if (!definition.getMongoAdminUser().isEmpty()
&& !definition.getMongoAdminPassword().isEmpty()
&& adminDb.isAuthenticated()) {
slurpedDb = adminDb.getMongo().getDB(definition.getMongoDb());
}
// Not necessary as local user has access to all databases.
// http://docs.mongodb.org/manual/reference/local-database/
// if (!mongoDbUser.isEmpty() && !mongoDbPassword.isEmpty()
// && !slurpedDb.isAuthenticated()) {
// logger.info("Authenticate {} with {}", mongoDb, mongoDbUser);
// CommandResult cmd = slurpedDb.authenticateCommand(mongoDbUser,
// mongoDbPassword.toCharArray());
// if (!cmd.ok()) {
// logger.error("Authentication failed for {}: {}",
// mongoDb, cmd.getErrorMessage());
// return false;
// }
// }
// slurpedCollection =
// slurpedDb.getCollection(definition.getMongoCollection());
// if (definition.isImportAllCollections()) {
// for (String collection : slurpedDb.getCollectionNames()) {
// slurpedCollections.put(collection,
// slurpedDb.getCollection(collection));
// }
// } else {
// slurpedCollections.put(definition.getMongoCollection(),
// slurpedDb.getCollection(definition.getMongoCollection()));
// }
return true;
}
/**
* Does an initial sync the same way MongoDB does. https://groups.google.com/
* forum/?fromgroups=#!topic/mongodb-user/sOKlhD_E2ns
*
* @return the last oplog timestamp before the import began
* @throws InterruptedException if the blocking queue stream is interrupted while waiting
*/
protected Timestamp<?> doInitialImport(DBCollection collection) throws InterruptedException {
// TODO: ensure the index type is empty
// DBCollection slurpedCollection =
// slurpedDb.getCollection(definition.getMongoCollection());
logger.info("MongoDBRiver is beginning initial import of " + collection.getFullName());
Timestamp<?> startTimestamp = getCurrentOplogTimestamp();
boolean inProgress = true;
String lastId = null;
while (inProgress) {
DBCursor cursor = null;
try {
if (definition.isDisableIndexRefresh()) {
updateIndexRefresh(definition.getIndexName(), -1L);
}
if (!definition.isMongoGridFS()) {
logger.info("Collection {} - count: {}", collection.getName(), collection.count());
long count = 0;
cursor =
collection.find(
getFilterForInitialImport(definition.getMongoCollectionFilter(), lastId));
while (cursor.hasNext()) {
DBObject object = cursor.next();
count++;
if (cursor.hasNext()) {
lastId = addInsertToStream(null, applyFieldFilter(object), collection.getName());
} else {
logger.debug("Last entry for initial import - add timestamp: {}", startTimestamp);
lastId =
addInsertToStream(startTimestamp, applyFieldFilter(object), collection.getName());
}
}
inProgress = false;
logger.info("Number documents indexed: {}", count);
} else {
// TODO: To be optimized.
// https://github.com/mongodb/mongo-java-driver/pull/48#issuecomment-25241988
// possible option: Get the object id list from .fs
// collection
// then call GriDFS.findOne
GridFS grid =
new GridFS(mongo.getDB(definition.getMongoDb()), definition.getMongoCollection());
cursor = grid.getFileList();
while (cursor.hasNext()) {
DBObject object = cursor.next();
if (object instanceof GridFSDBFile) {
GridFSDBFile file =
grid.findOne(new ObjectId(object.get(MongoDBRiver.MONGODB_ID_FIELD).toString()));
if (cursor.hasNext()) {
lastId = addInsertToStream(null, file);
} else {
logger.debug("Last entry for initial import - add timestamp: {}", startTimestamp);
lastId = addInsertToStream(startTimestamp, file);
}
}
}
inProgress = false;
}
} catch (MongoException.CursorNotFound e) {
logger.info(
"Initial import - Cursor {} has been closed. About to open a new cusor.",
cursor.getCursorId());
logger.debug("Total document inserted [{}]", totalDocuments.get());
} finally {
if (cursor != null) {
logger.trace("Closing initial import cursor");
cursor.close();
}
if (definition.isDisableIndexRefresh()) {
updateIndexRefresh(definition.getIndexName(), TimeValue.timeValueSeconds(1));
}
}
}
return startTimestamp;
}
