VALUEOUT
-public class ContentOutputFormat<VALUEOUT> extends MarkLogicOutputFormat<DocumentURI,VALUEOUT>
Use this class to store results as content in a MarkLogic Server
database. The text, XML, or binary content is inserted into the
database at the given DocumentURI
.
When using this MarkLogicOutputFormat
,
your key should be the URI of the document to insert into the
database. The value should be the content to insert, in the form of
Text
or MarkLogicNode
.
Several configuration properties exist for controlling the content insertion, including permissions, collections, quality, directory, and content type.
MarkLogicConstants
,
ContentLoader
,
ZipContentLoader
Modifier and Type | Field and Description |
---|---|
protected boolean |
allowFastLoad
whether stats-based policy allows fastload
|
protected AssignmentManager |
am |
protected boolean |
failover |
protected boolean |
fastLoad |
static String |
FOREST_HOST_QUERY |
static String |
FOREST_REPLICA_HOST_QUERY |
static String |
HEADER_QUERY |
static String |
ID_PREFIX |
static String |
INIT_QUERY |
protected String |
initHostName |
protected boolean |
legacy |
static
org.apache.commons.logging.Log |
LOG |
protected AssignmentPolicy.Kind |
policy |
conf,
HOSTS_QUERY
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,
DEFAULT_TXN_SIZE,
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_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 |
---|
ContentOutputFormat() |
Modifier and Type | Method and Description |
---|---|
void |
checkOutputSpecs(org.apache.hadoop.conf.Configuration conf,
com.marklogic.xcc.ContentSource cs) |
protected LinkedMapWritable |
getForestStatusMap(org.apache.hadoop.conf.Configuration conf) |
org.apache.hadoop.mapreduce.RecordWriter<DocumentURI,VALUEOUT> |
getRecordWriter(org.apache.hadoop.mapreduce.TaskAttemptContext context) |
protected Map<String,com.marklogic.xcc.ContentSource> |
getSourceMap(boolean fastLoad,
org.apache.hadoop.mapreduce.TaskAttemptContext context) |
protected boolean |
initialize(com.marklogic.xcc.Session session,
boolean restrictHosts, boolean getForwardHeader)
Initialize initial server host name, assignment
policy and fastload.
|
protected LinkedMapWritable |
queryForestInfo(com.marklogic.xcc.ContentSource cs)
must be attempting or doing fastload when this
method is called.
|
checkOutputSpecs,
getConf,
getHosts,
getOutputCommitter,
queryHosts,
queryHosts,
setConf
public static final org.apache.commons.logging.Log LOG
public static final String ID_PREFIX
public static final String FOREST_HOST_QUERY
public static final String FOREST_REPLICA_HOST_QUERY
public static final String INIT_QUERY
public static final String HEADER_QUERY
protected AssignmentManager am
protected boolean fastLoad
protected boolean allowFastLoad
protected AssignmentPolicy.Kind policy
protected boolean legacy
protected boolean failover
protected String initHostName
public void checkOutputSpecs(org.apache.hadoop.conf.Configuration conf, com.marklogic.xcc.ContentSource cs) throws IOException
checkOutputSpecs
in class MarkLogicOutputFormat<DocumentURI,VALUEOUT>
IOException
protected Map<String,com.marklogic.xcc.ContentSource> getSourceMap(boolean fastLoad, org.apache.hadoop.mapreduce.TaskAttemptContext context) throws IOException
IOException
public org.apache.hadoop.mapreduce.RecordWriter<DocumentURI,VALUEOUT> getRecordWriter(org.apache.hadoop.mapreduce.TaskAttemptContext context) throws IOException, InterruptedException
getRecordWriter
in
class org.apache.hadoop.mapreduce.OutputFormat<DocumentURI,VALUEOUT>
IOException
InterruptedException
protected LinkedMapWritable getForestStatusMap(org.apache.hadoop.conf.Configuration conf) throws IOException
IOException
protected boolean initialize(com.marklogic.xcc.Session session, boolean restrictHosts, boolean getForwardHeader) throws IOException, com.marklogic.xcc.exceptions.RequestException
session
-IOException
com.marklogic.xcc.exceptions.RequestException
protected LinkedMapWritable queryForestInfo(com.marklogic.xcc.ContentSource cs) throws IOException
cs
-IOException
Copyright © 2020 MarkLogic
Corporation. All Rights Reserved.
Complete online documentation for MarkLogic Server,
XQuery and related components may be found at
developer.marklogic.com