solrctl instancedir --create /root/config/

<field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" />
<field name="serialnumber" type="string" indexed="true" stored="true" required="true" multiValued="false" />
<field name="fulltext" type="text_ch" indexed="true" stored="true" required="true" multiValued="false" />
<field name="_version_" type="long" indexed="true" stored="true"/>

<fieldType name="text_ch" class="solr.TextField" positionIncrementGap="100"><analyzer type="index"><tokenizer class="solr.SmartChineseSentenceTokenizerFactory"/><filter class="solr.SmartChineseWordTokenFilterFactory"/></analyzer>
</fieldType>

solrctl instancedir --create hbase-collection /root/config/
solrctl collection --create hbase-collection

<?xml version="1.0"?>
<indexer table="allDoc" mapper="com.ngdata.hbaseindexer.morphline.MorphlineResultToSolrMapper"><param name="morphlineFile" value="morphlines.conf"/>
</indexer>

morphlines : [{id : morphlineimportCommands : ["org.kitesdk.**","com.ngdata.**"]commands : [{extractHBaseCells {mappings : [{inputColumn : "fulltext:fulltext"outputField : "fulltext"type : stringsource : value},{inputColumn : "fileInfo:serialNumber"outputField : "serialnumber"type : stringsource : value}]}}{ logDebug { format : "output record: {}", args : ["@{}"]}}]}
]

hbase-indexer delete-indexer -n docIndex
hbase-indexer add-indexer -n docIndex -c /root/morphline-hbase-mapper.xml -cp solr.zk=gs-server-5002:2181,gs-server-5001:2181,gs-server-5000:2181/solr -cp solr.collection=hbase-collection8 -z gs-server-5002:2181,gs-server-5001:2181,gs-server-5000:2181
hbase-indexer list-indexers   #查看是否正常运行

COLLECTION='hbase-collection'
ZK='gs-server-5002:2181,gs-server-5001:2181,gs-server-5000:2181'
echo 'Delete previous docs...'
solrctl collection --deletedocs $COLLECTION
echo 'Lily HBase MapReduce indexing...'
config="/etc/hadoop/conf.cloudera.yarn"
parcel="/opt/cloudera/parcels/CDH"
jar="$parcel/lib/hbase-solr/tools/hbase-indexer-mr-*-job.jar"
hbase_conf="/etc/hbase/conf/hbase-site.xml"
opts="'mapred.child.java.opts=-Xmx1024m'"
log4j="$parcel/share/doc/search*/examples/solr-nrt/log4j.properties"
zk="$ZK/solr"
libjars="lucene-analyzers-smartcn-4.10.3-cdh5.12.1.jar"
export HADOOP_OPTS="-Djava.security.auth.login.config=conf/jaas.conf"
hadoop --config $config jar $jar --conf $hbase_conf --libjars $libjars -D $opts --log4j $log4j --hbase-indexer-file morphline-hbase-mapper.xml --verbose --go-live --zk-host $zk --collection $COLLECTION

 public static String stripNonCharCodepoints(String input) {StringBuilder retval = new StringBuilder();char ch;for (int i = 0; i < input.length(); i++) {ch = input.charAt(i);// Strip all non-characters// http://unicode.org/cldr/utility/list-unicodeset.jsp?a=[:Noncharacter_Code_Point=True:]// and non-printable control characters except tabulator, new line and// carriage returnif (ch % 0x10000 != 0xffff && // 0xffff - 0x10ffff range step 0x10000ch % 0x10000 != 0xfffe && // 0xfffe - 0x10fffe range(ch <= 0xfdd0 || ch >= 0xfdef) && // 0xfdd0 - 0xfdef(ch > 0x1F || ch == 0x9 || ch == 0xa || ch == 0xd)) {retval.append(ch);}}return retval.toString();}