<!> Solr1.3
The AnalysisRequestHandler is a RequestHandler designed to take in documents as input and return the tokens as output.
Input is very similar to UpdateXmlMessages in that a post can be one or more <doc>s, as in
<docs>
<doc>
<field name="employeeId">05991</field>
<field name="office">Bridgewater</field>
<field name="skills">Perl</field>
<field name="skills">Java</field>
</doc>
[<doc> ... </doc>[<doc> ... </doc>]]
</docs>
The docs tag can actually be any value, it need not be docs. This allows one to use the same Solr XML input that is used for indexing.
$ cd example/exampledocs $ curl 'http://localhost:8983/solr/analysis/document?wt=json&indent=true' --data-binary @monitor.xml -H 'Content-type:text/xml; charset=utf-8'
The output will look something like:
{
"responseHeader":{
"status":0,
"QTime":8},
"analysis":{
"3007WFP":{
"name":{
"index":{
"Dell Widescreen UltraSharp 3007WFP":{
"org.apache.lucene.analysis.WhitespaceTokenizer":[{
"text":"Dell",
"type":"word",
"start":0,
"end":4,
"position":1},
{
"text":"Widescreen",
"type":"word",
"start":5,
"end":15,
"position":2},
{
"text":"UltraSharp",
"type":"word",
"start":16,
"end":26,
"position":3},
{
"text":"3007WFP",
"type":"word",
"start":27,
"end":34,
"position":4}],
"org.apache.lucene.analysis.StopFilter":[{
"text":"Dell",
"type":"word",
"start":0,
"end":4,
"position":1},
{
"text":"Widescreen",
"type":"word",
"start":5,
"end":15,
"position":2},
{
"text":"UltraSharp",
"type":"word",
"start":16,
"end":26,
"position":3},
{
"text":"3007WFP",
"type":"word",
"start":27,
"end":34,
"position":4}],
"org.apache.solr.analysis.WordDelimiterFilter":[{
"text":"Dell",
"type":"word",
"start":0,
"end":4,
"position":1},
{
"text":"Widescreen",
"type":"word",
"start":5,
"end":15,
"position":2},
{
"text":"UltraSharp",
"type":"word",
"start":16,
"end":26,
"position":3},
{
"text":"3007",
"type":"word",
"start":27,
"end":31,
"position":4},
{
"text":"WFP",
"type":"word",
"start":31,
"end":34,
"position":5}],
"org.apache.lucene.analysis.LowerCaseFilter":[{
"text":"dell",
"type":"word",
"start":0,
"end":4,
"position":1},
{
"text":"widescreen",
"type":"word",
"start":5,
"end":15,
"position":2},
{
"text":"ultrasharp",
"type":"word",
"start":16,
"end":26,
"position":3},
{
"text":"3007",
"type":"word",
"start":27,
"end":31,
"position":4},
{
"text":"wfp",
"type":"word",
"start":31,
"end":34,
"position":5}]} } },
[...]