public abstract class MarkLogicRecordReader<KEYIN,VALUEIN> extends org.apache.hadoop.mapreduce.RecordReader<KEYIN,VALUEIN> implements MarkLogicConstants
Modifier and Type | Field and Description |
---|---|
protected org.apache.hadoop.conf.Configuration |
conf
Job configuration.
|
protected long |
count
Count of records fetched
|
protected int |
curForest
Current Forest to connect for failover
|
protected String[] |
hostNames
Hostnames from the input split
|
protected float |
length
Total expected count of the records in a split.
|
static org.apache.commons.logging.Log |
LOG |
protected int |
maxRetries |
protected int |
maxSleepTime |
protected MarkLogicInputSplit |
mlSplit
Input split for this record reader
|
protected String[] |
redactionRuleCol
Redaction rule collection names.
|
protected List<ForestHost> |
replicas
list of forests for failover
|
protected com.marklogic.xcc.ResultSequence |
result
ResultSequence from the MarkLogic server.
|
protected int |
retry
for failover retry
|
protected com.marklogic.xcc.Session |
session
Session to the MarkLogic server.
|
protected int |
sleepTime |
ADVANCED_MODE, ASSIGNMENT_POLICY, BASIC_MODE, BATCH_SIZE, BIND_SPLIT_RANGE, COLLECTION_FILTER, CONTENT_TYPE, COPY_COLLECTIONS, COPY_METADATA, COPY_QUALITY, DEFAULT_BATCH_SIZE, DEFAULT_CONTENT_TYPE, DEFAULT_LOCAL_MAX_SPLIT_SIZE, DEFAULT_MAX_SPLIT_SIZE, DEFAULT_OUTPUT_CONTENT_ENCODING, DEFAULT_OUTPUT_XML_REPAIR_LEVEL, DEFAULT_PROPERTY_OPERATION_TYPE, DIRECTORY_FILTER, DOCUMENT_SELECTOR, EXECUTION_MODE, EXTRACT_URI, INDENTED, INPUT_DATABASE_NAME, INPUT_HOST, INPUT_KEY_CLASS, INPUT_LEXICON_FUNCTION_CLASS, INPUT_MODE, INPUT_PASSWORD, INPUT_PORT, INPUT_QUERY, INPUT_QUERY_LANGUAGE, INPUT_QUERY_TIMESTAMP, INPUT_RESTRICT_HOSTS, INPUT_SSL_OPTIONS_CLASS, INPUT_SSL_PROTOCOL, INPUT_USE_SSL, INPUT_USERNAME, INPUT_VALUE_CLASS, MAX_SPLIT_SIZE, MIN_NODEUPDATE_VERSION, MODE_DISTRIBUTED, MODE_LOCAL, MR_NAMESPACE, NODE_OPERATION_TYPE, OUTPUT_CLEAN_DIR, OUTPUT_COLLECTION, OUTPUT_CONTENT_ENCODING, OUTPUT_CONTENT_LANGUAGE, OUTPUT_CONTENT_NAMESPACE, OUTPUT_DATABASE_NAME, OUTPUT_DIRECTORY, OUTPUT_FAST_LOAD, OUTPUT_FOREST_HOST, OUTPUT_GRAPH, OUTPUT_HOST, OUTPUT_KEY_TYPE, OUTPUT_KEY_VARNAME, OUTPUT_NAMESPACE, OUTPUT_OVERRIDE_GRAPH, OUTPUT_PARTITION, OUTPUT_PASSWORD, OUTPUT_PERMISSION, OUTPUT_PORT, OUTPUT_PROPERTY_ALWAYS_CREATE, OUTPUT_QUALITY, OUTPUT_QUERY, OUTPUT_QUERY_LANGUAGE, OUTPUT_RESTRICT_HOSTS, OUTPUT_SSL_OPTIONS_CLASS, OUTPUT_SSL_PROTOCOL, OUTPUT_STREAMING, OUTPUT_TOLERATE_ERRORS, OUTPUT_URI_PREFIX, OUTPUT_URI_REPLACE, OUTPUT_URI_SUFFIX, OUTPUT_USE_SSL, OUTPUT_USERNAME, OUTPUT_VALUE_TYPE, OUTPUT_VALUE_VARNAME, OUTPUT_XML_REPAIR_LEVEL, PATH_NAMESPACE, PROPERTY_OPERATION_TYPE, QUERY_FILTER, RECORD_TO_FRAGMENT_RATIO, REDACTION_RULE_COLLECTION, SPLIT_END_VARNAME, SPLIT_QUERY, SPLIT_START_VARNAME, SUBDOCUMENT_EXPRESSION, TEMPORAL_COLLECTION, TXN_SIZE, TYPE_FILTER
Constructor and Description |
---|
MarkLogicRecordReader(org.apache.hadoop.conf.Configuration conf) |
Modifier and Type | Method and Description |
---|---|
protected void |
buildDocExprQuery(String docExpr,
Collection<String> nsCol,
String subExpr,
StringBuilder buf) |
protected void |
buildSearchQuery(String docExpr,
String ctsQuery,
Collection<String> nsCol,
StringBuilder buf) |
protected void |
buildSrcInDocExprQuery(String docExpr,
String subExpr,
StringBuilder buf) |
protected void |
buildSrcInSearchQuery(String docExpr,
String ctsQuery,
StringBuilder buf) |
void |
close() |
protected abstract void |
endOfResult() |
org.apache.hadoop.conf.Configuration |
getConf() |
long |
getCount() |
protected abstract float |
getDefaultRatio() |
float |
getProgress() |
void |
initialize(org.apache.hadoop.mapreduce.InputSplit split,
org.apache.hadoop.mapreduce.TaskAttemptContext context) |
boolean |
nextKeyValue() |
protected abstract boolean |
nextResult(com.marklogic.xcc.ResultItem result) |
public static final org.apache.commons.logging.Log LOG
protected MarkLogicInputSplit mlSplit
protected long count
protected com.marklogic.xcc.Session session
protected com.marklogic.xcc.ResultSequence result
protected org.apache.hadoop.conf.Configuration conf
protected float length
protected String[] redactionRuleCol
protected List<ForestHost> replicas
protected int curForest
protected String[] hostNames
protected int retry
protected final int maxRetries
protected int sleepTime
protected final int maxSleepTime
public MarkLogicRecordReader(org.apache.hadoop.conf.Configuration conf)
public void close() throws IOException
close
in interface Closeable
close
in interface AutoCloseable
close
in class org.apache.hadoop.mapreduce.RecordReader<KEYIN,VALUEIN>
IOException
public org.apache.hadoop.conf.Configuration getConf()
public float getProgress() throws IOException, InterruptedException
getProgress
in class org.apache.hadoop.mapreduce.RecordReader<KEYIN,VALUEIN>
IOException
InterruptedException
protected void buildSrcInDocExprQuery(String docExpr, String subExpr, StringBuilder buf)
protected void buildDocExprQuery(String docExpr, Collection<String> nsCol, String subExpr, StringBuilder buf)
protected void buildSrcInSearchQuery(String docExpr, String ctsQuery, StringBuilder buf)
protected void buildSearchQuery(String docExpr, String ctsQuery, Collection<String> nsCol, StringBuilder buf)
public void initialize(org.apache.hadoop.mapreduce.InputSplit split, org.apache.hadoop.mapreduce.TaskAttemptContext context) throws IOException, InterruptedException
initialize
in class org.apache.hadoop.mapreduce.RecordReader<KEYIN,VALUEIN>
IOException
InterruptedException
public boolean nextKeyValue() throws IOException, InterruptedException
nextKeyValue
in class org.apache.hadoop.mapreduce.RecordReader<KEYIN,VALUEIN>
IOException
InterruptedException
protected abstract void endOfResult()
protected abstract boolean nextResult(com.marklogic.xcc.ResultItem result)
protected abstract float getDefaultRatio()
public long getCount()
Copyright © 2020 MarkLogic Corporation. All Rights Reserved.
Complete online documentation for MarkLogic Server, XQuery and related components may be found at developer.marklogic.com