Gets Nodes containing the Search snippet in a document

Question

Is there a way to get the node that contains the search snippet for eg:-

I have a sample xml doc

<pdf2xml>
  <page pageNo="1">xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx</page>
  <page pageNo="2">xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx</page>
  <page pageNo="3">xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx</page>
  <page pageNo="4">xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx</page>
</pdf2xml>

How do I get the pageNo for a given search result ? I tried the following

search:snippet(fn:doc($uri), 
  cts:query(search:parse($q, $options)),  
    <transform-results apply="snippet" xmlns="http://marklogic.com/appservices/search">
      <per-match-tokens>30</per-match-tokens> 
      <max-matches>1000</max-matches> 
      <max-snippet-chars>2000</max-snippet-chars>
      <preferred-matches>
        <element name="page" ns=""/>
      </preferred-matches>
    </transform-results>)

This does not give all the snippets as well ... what is a good a way of doing what I want to do ?

Answer 1

Looking for all of the snippets in a document, returning the containing element and highlighting them can be done with cts:walk and cts:snippet

xquery version "1.0-ml";


let $content := <pdf2xml>
  <page pageNo="1">xxxxxxxxxxxxxx 1 xxxxxxxxx</page>
  <page pageNo="2">xxxxxxxxxxxxxx 2 xxxxx foo xxxxxxxx</page>
  <page pageNo="3">xxxxxxxxxxxxxxx 3 xxxxxxxxxxxxxxxxxxxxxxx</page>
  <page pageNo="4">xxxxxxxxxxxxxxxxx 4 xxxxxxxxxxx foo xxxxxxxxxx</page>
</pdf2xml>

let $q := cts:word-query("foo")

return <results> 
{cts:walk($content, $q , 
  <result>
    <original-node>{$cts:node/parent::*}</original-node>
    <highlighted-content>{cts:highlight($cts:node/parent::*, $q, <matched>{$cts:text}</matched>)}</highlighted-content>
  </result>
  )}
</results>

Results in:

<results>
  <result>
    <original-node>
      <page pageNo="2">xxxxxxxxxxxxxx 2 xxxxx foo xxxxxxxx</page>
    </original-node>
    <highlighted-content>
      <page pageNo="2">xxxxxxxxxxxxxx 2 xxxxx <matched>foo</matched> xxxxxxxx</page>
    </highlighted-content>
  </result>
  <result>
    <original-node>
      <page pageNo="4">xxxxxxxxxxxxxxxxx 4 xxxxxxxxxxx foo xxxxxxxxxx</page>
    </original-node>
      <highlighted-content>
        <page pageNo="4">xxxxxxxxxxxxxxxxx 4 xxxxxxxxxxx <matched>foo</matched> xxxxxxxxxx</page>
      </highlighted-content>
    </result>
</results>

This may not be what you want, but I still offer it up as an example of some of the power you have available to you for manipulating your results (or in the example, extracting and highlighting content as a result of search or not)