import module namespace kwic="http://exist-db.org/xquery/kwic" at "xmldb:exist:///db/modules/kwic.xql";

declare function local:filter($node as node(), $mode as xs:string) as xs:string? {
  if ($node/parent::SPEAKER or $node/parent::STAGEDIR) then
      ()
  else if ($mode eq 'before') then
      concat($node, ' ')
  else
      concat(' ', $node)
};

(: context scope: number of preceding / following words :)
let $scope := 5
(: determine context width for KWIC results: 10 characters per context word, minimally 40 :)
let $cutoff := max(($scope * 10, xs:int(40)))
let $config := <config width="{$cutoff}"/>
let $hits := doc("/db/shakespeare/plays/hamlet.xml")//SPEECH[ft:query(., "nature king sir")]
let $KWIC := $hits/kwic:summarize(., $config,
            util:function(xs:QName("local:filter"), 2))

(: split up collocations per search term :)
for $term in distinct-values($KWIC//kwic:hit/lower-case(normalize-space(.)))
order by $term
return
  (: prepare entire left / right contexts for tokenization: 
        -lower case
        -normalize whitespace
        -reverse $prev
  :)
  let $prev := for $a in $KWIC[kwic:hit/lower-case(normalize-space(.))) eq $term]/kwic:prev/lower-case(normalize-space(.)) return string-join(reverse(tokenize($a, '\W+')), ' ')
  let $next := $KWIC[kwic:hit/lower-case(normalize-space(.))) eq $term]//kwic:next/lower-case(normalize-space(.))
  
  (: per context position, retrieve all distinct words :)
  (: note: discard numbers :)
  let $prev := 
    for $context in ((0 - $scope) to -1)
    let $words := 
      let $tok := for $a in $prev return tokenize($a, '\W+')[matches(., '[a-zA-Z]')][position() = abs($context)]
      for $b in distinct-values($tok) order by $b return <w>{$b}</w>
    return <context pos="{$context}">{$words}</context>
  let $next := 
    for $context in (1 to $scope)
    let $words := 
      let $tok := for $a in $next return tokenize($a, '\W+')[matches(., '[a-zA-Z]')][$context]
      for $b in distinct-values($tok) order by $b return <w>{$b}</w>
    return <context pos="{$context}">{$words}</context>

  let $max := max(($next|$prev)/count(w))

  (: spread out words-per-context over table rows :)
  return 
    <table border="1">{
      <tr>
        <th/>
        {
          for $a in $prev
          return <th>{$a/@pos/string()}</th>
          ,
          <th>term</th>
          ,
          for $a in $next
          return <th>{$a/@pos/string()}</th>
        }
      </tr>
      ,
      for $i in (1 to $max)
      return 
        <tr>{
          <td>{$i}</td>,
          for $a in $prev
          return
            <td>{$a/w[$i]/text()}</td>
          ,
          <th>{$term}</th>
          ,
          for $a in $next
          return
            <td>{$a/w[$i]/text()}</td>
        }</tr>
    }</table>