Full-Text Module - Revision history

CG: Text replacement - "" to "

2023-12-01T16:34:49Z

Text replacement - "<syntaxhighlight lang="xquery">" to "<pre lang='xquery'>"

CG: Text replacement - "" to ""

2023-12-01T16:30:29Z

Text replacement - "</syntaxhighlight>" to "</pre>"

CG at 14:53, 9 March 2023

2023-03-09T14:53:28Z

CG at 13:30, 9 March 2023

2023-03-09T13:30:18Z

CG: Text replacement - "'''Signatures'''" to "'''Signature'''"

2023-03-09T13:09:09Z

Text replacement - "'''Signatures'''" to "'''Signature'''"

CG at 11:05, 9 March 2023

2023-03-09T11:05:20Z

CG: Text replacement - "
" to "
"

2023-03-09T08:21:32Z

Text replacement - "<br />" to "<br/>"

CG: /* ft:mark */

2022-10-05T13:20:44Z

ft:mark

CG: /* ft:mark */

2022-10-05T13:19:39Z

ft:mark

CG at 12:18, 20 July 2022

2022-07-20T12:18:11Z

Show changes

@@ Line 46: / Line 46: @@
 * Return all text nodes of the database {{Code|DB}} that contain the numbers {{Code|2010}} and {{Code|2020}}:<br/><code>ft:search("DB", ("2010", "2020"), map { 'mode': 'all' })</code>
 * Return text nodes that contain the terms {{Code|A}} and {{Code|B|}} in a distance of at most 5 words:
-<syntaxhighlight lang="xquery">
+<pre lang='xquery'>
 ft:search("db", ("A", "B"), map {
    "mode": "all words",
@@ Line 56: / Line 56: @@
 </pre>
 * Iterate over three databases and return all elements containing terms similar to {{Code|Hello World}} in the text nodes:
-<syntaxhighlight lang="xquery">
+<pre lang='xquery'>
 let $terms := "Hello Worlds"
 let $fuzzy := true()
@@ Line 83: / Line 83: @@
 | '''Examples'''
 |Returns the number of occurrences for a single, specific index entry:
-<syntaxhighlight lang="xquery">
+<pre lang='xquery'>
 let $term := ft:tokenize($term)
 return number(ft:tokens('db', $term)[. = $term]/@count)
@@ Line 115: / Line 115: @@
+|
 * Checks if {{Code|jack}} or {{Code|john}} occurs in the input string {{Code|John Doe}}:
-<syntaxhighlight lang="xquery">
+<pre lang='xquery'>
 ft:contains("John Doe", ("jack", "john"), map { "mode": "any" })
 </pre>
 * Calls the function with stemming turned on and off:
-<syntaxhighlight lang="xquery">
+<pre lang='xquery'>
 (true(), false()) ! ft:contains("Häuser", "Haus", map { 'stemming': ., 'language':'de' })
 </pre>
@@ Line 219: / Line 219: @@
 | '''Examples'''
 | Returns {{Code|happy}} and {{Code|lucky}}:
-<syntaxhighlight lang="xquery">
+<pre lang='xquery'>
 ft:thesaurus(
    <thesaurus>
@@ Line 254: / Line 254: @@
 | '''Examples'''
 |'''Example 1''': The following query returns {{Code|&lt;XML&gt;&lt;mark&gt;hello&lt;/mark&gt; world&lt;/XML&gt;}}, if one text node of the database {{Code|DB}} has the value "hello world":
-<syntaxhighlight lang="xquery">
+<pre lang='xquery'>
 ft:mark(db:get('DB')//*[text() contains text 'hello'])
 </pre>
 '''Example 2''': The following expression loops through the first ten full-text results and marks the results in a second expression:
-<syntaxhighlight lang="xquery">
+<pre lang='xquery'>
 let $start := 1
 let $end   := 10
@@ Line 267: / Line 267: @@
 </pre>
 '''Example 3''': The following expression returns <code>&lt;xml>hello &lt;b&gt;word&lt;/b&gt;&lt;/xml&gt;</code>:
-<syntaxhighlight lang="xquery">
+<pre lang='xquery'>
 copy $p := <xml>hello world</xml>
 modify ()
@@ Line 291: / Line 291: @@
+|
 * The following query may return {{Code|&lt;XML&gt;...&lt;b&gt;hello&lt;/b&gt;...&lt;XML&gt;}} if a text node of the database {{Code|DB}} contains the string "hello world":
-<syntaxhighlight lang="xquery">
+<pre lang='xquery'>
 ft:extract(db:get('DB')//*[text() contains text 'hello'], 'b', 1)
 </pre>

@@ Line 54: / Line 54: @@
+   }
 })
-</syntaxhighlight>
+</pre>
 * Iterate over three databases and return all elements containing terms similar to {{Code|Hello World}} in the text nodes:
 <syntaxhighlight lang="xquery">
@@ Line 62: / Line 62: @@
 let $dbname := 'DB' || $db
 return ft:search($dbname, $terms, map { 'fuzzy': $fuzzy })/..
-</syntaxhighlight>
+</pre>
 |}
@@ Line 86: / Line 86: @@
 let $term := ft:tokenize($term)
 return number(ft:tokens('db', $term)[. = $term]/@count)
-</syntaxhighlight>
+</pre>
 |}
@@ Line 117: / Line 117: @@
 <syntaxhighlight lang="xquery">
 ft:contains("John Doe", ("jack", "john"), map { "mode": "any" })
-</syntaxhighlight>
+</pre>
 * Calls the function with stemming turned on and off:
 <syntaxhighlight lang="xquery">
 (true(), false()) ! ft:contains("Häuser", "Haus", map { 'stemming': ., 'language':'de' })
-</syntaxhighlight>
+</pre>
 |}
@@ Line 232: / Line 232: @@
    'happy'
+)
-</syntaxhighlight>
+</pre>
 |}
@@ Line 256: / Line 256: @@
 <syntaxhighlight lang="xquery">
 ft:mark(db:get('DB')//*[text() contains text 'hello'])
-</syntaxhighlight>
+</pre>
 '''Example 2''': The following expression loops through the first ten full-text results and marks the results in a second expression:
 <syntaxhighlight lang="xquery">
@@ Line 265: / Line 265: @@
 for $ft in (db:get('DB')//*[$test(.)])[position() = $start to $end]
 return ft:mark($ft[$test(.)])
-</syntaxhighlight>
+</pre>
 '''Example 3''': The following expression returns <code>&lt;xml>hello &lt;b&gt;word&lt;/b&gt;&lt;/xml&gt;</code>:
 <syntaxhighlight lang="xquery">
@@ Line 271: / Line 271: @@
 modify ()
 return ft:mark($p[text() contains text 'word'], 'b')
-</syntaxhighlight>
+</pre>
 |}
@@ Line 293: / Line 293: @@
 <syntaxhighlight lang="xquery">
 ft:extract(db:get('DB')//*[text() contains text 'hello'], 'b', 1)
-</syntaxhighlight>
+</pre>
 |}

@@ Line 15: / Line 15: @@
    $db       as xs:string,
    $terms    as item()*,
-   $options  as map(*)?    := ()
+   $options  as map(*)?    := map { }
 ) as text()*</pre>
 |- valign="top"
@@ Line 99: / Line 99: @@
    $input    as item()*,
    $terms    as item()*,
-   $options  as map(*)?  := ()
+   $options  as map(*)?  := map { }
 ) as xs:boolean</pre>
 |- valign="top"
@@ Line 165: / Line 165: @@
 |<pre>ft:tokenize(
    $string   as xs:string?,
-   $options  as map(*)?     := ()
+   $options  as map(*)?     := map { }
 ) as xs:string*</pre>
 |- valign="top"
@@ Line 190: / Line 190: @@
 |<pre>ft:normalize(
    $string   as xs:string?,
-   $options  as map(*)?     := ()
+   $options  as map(*)?     := map { }
 ) as xs:string</pre>
 |- valign="top"
@@ Line 209: / Line 209: @@
    $node     as node(),
    $term     as xs:string,
-   $options  as map(*)?    := ()
+   $options  as map(*)?    := map { }
 ) as xs:string*</pre>
 |- valign="top"

@@ Line 13: / Line 13: @@
 | width='120' | '''Signature'''
 |<pre>ft:search(
-   $db       as xs:string
+   $db       as xs:string,
-   $terms    as item()*
+   $terms    as item()*,
    $options  as map(*)?    := ()
 ) as text()*</pre>
@@ Line 71: / Line 71: @@
 | width='120' | '''Signature'''
 |<pre>ft:tokens(
-   $db      as xs:string
+   $db      as xs:string,
    $prefix  as xs:string  := ()
 ) as element(value)*</pre>
@@ Line 97: / Line 97: @@
 | width='120' | '''Signature'''
 |<pre>ft:contains(
-   $input    as item()*
+   $input    as item()*,
-   $terms    as item()*
+   $terms    as item()*,
    $options  as map(*)?  := ()
 ) as xs:boolean</pre>
@@ Line 164: / Line 164: @@
 | width='120' | '''Signature'''
 |<pre>ft:tokenize(
-   $string   as xs:string?
+   $string   as xs:string?,
    $options  as map(*)?     := ()
 ) as xs:string*</pre>
@@ Line 189: / Line 189: @@
 | width='120' | '''Signature'''
 |<pre>ft:normalize(
-   $string   as xs:string?
+   $string   as xs:string?,
    $options  as map(*)?     := ()
 ) as xs:string</pre>
@@ Line 207: / Line 207: @@
 | width='120' | '''Signature'''
 |<pre>ft:thesaurus(
-   $node     as node()
+   $node     as node(),
-   $term     as xs:string
+   $term     as xs:string,
    $options  as map(*)?    := ()
 ) as xs:string*</pre>
@@ Line 243: / Line 243: @@
 | width='120' | '''Signature'''
 |<pre>ft:mark(
-   $nodes  as node()*
+   $nodes  as node()*,
    $name   as xs:string  := ()
 ) as node()*</pre>
@@ Line 280: / Line 280: @@
 | width='120' | '''Signature'''
 |<pre>ft:extract(
-   $nodes   as node()*
+   $nodes   as node()*,
-   $name    as xs:string   := ()
+   $name    as xs:string   := (),
    $length  as xs:integer  := ()
 ) as node()*</pre>

@@ Line 11: / Line 11: @@
 {| width='100%'
 |- valign="top"
-| width='120' | '''Signatures'''
+| width='120' | '''Signature'''
 |<pre>ft:search(
    $db       as xs:string
@@ Line 69: / Line 69: @@
 {| width='100%'
 |- valign="top"
-| width='120' | '''Signatures'''
+| width='120' | '''Signature'''
 |<pre>ft:tokens(
    $db      as xs:string
@@ Line 95: / Line 95: @@
 {| width='100%'
 |- valign="top"
-| width='120' | '''Signatures'''
+| width='120' | '''Signature'''
 |<pre>ft:contains(
    $input    as item()*
@@ Line 128: / Line 128: @@
 {| width='100%'
 |- valign="top"
-| width='120' | '''Signatures'''
+| width='120' | '''Signature'''
 |<pre>ft:count(
    $nodes  as node()*
@@ Line 145: / Line 145: @@
 {| width='100%'
 |- valign="top"
-| width='120' | '''Signatures'''
+| width='120' | '''Signature'''
 |<pre>ft:score(
    $item  as item()*
@@ Line 162: / Line 162: @@
 {| width='100%'
 |- valign="top"
-| width='120' | '''Signatures'''
+| width='120' | '''Signature'''
 |<pre>ft:tokenize(
    $string   as xs:string?
@@ Line 187: / Line 187: @@
 {| width='100%'
 |- valign="top"
-| width='120' | '''Signatures'''
+| width='120' | '''Signature'''
 |<pre>ft:normalize(
    $string   as xs:string?
@@ Line 205: / Line 205: @@
 {| width='100%'
 |- valign="top"
-| width='120' | '''Signatures'''
+| width='120' | '''Signature'''
 |<pre>ft:thesaurus(
    $node     as node()
@@ Line 241: / Line 241: @@
 {| width='100%'
 |- valign="top"
-| width='120' | '''Signatures'''
+| width='120' | '''Signature'''
 |<pre>ft:mark(
    $nodes  as node()*
@@ Line 278: / Line 278: @@
 {| width='100%'
 |- valign="top"
-| width='120' | '''Signatures'''
+| width='120' | '''Signature'''
 |<pre>ft:extract(
    $nodes   as node()*

@@ Line 217: / Line 217: @@
 |- valign="top"
 | width='120' | '''Signatures'''
-|{{Func|ft:mark|$nodes as node()*|node()*}}<br />{{Func|ft:mark|$nodes as node()*, $name as xs:string|node()*}}
+|{{Func|ft:mark|$nodes as node()*|node()*}}<br/>{{Func|ft:mark|$nodes as node()*, $name as xs:string|node()*}}
 |- valign="top"
 | '''Summary'''
-|Puts a marker element around the resulting {{Code|$nodes}} of a full-text request.<br />The default name of the marker element is {{Code|mark}}. An alternative name can be chosen via the optional {{Code|$name}} argument.<br />Please note that:
+|Puts a marker element around the resulting {{Code|$nodes}} of a full-text request.<br/>The default name of the marker element is {{Code|mark}}. An alternative name can be chosen via the optional {{Code|$name}} argument.<br/>Please note that:
 * The full-text expression that computes the token positions must be specified as argument of the <code>ft:mark()</code> function, as all position information is lost in subsequent processing steps. You may need to specify more than one full-text expression if you want to use the function in a FLWOR expression, as shown in Example 2.
 * The supplied node must be a [[Database Module#Database Node|Database Node]]. As shown in Example 3, {{Code|update}} or {{Code|transform}} can be utilized to convert a fragment to the required internal representation.
@@ Line 251: / Line 251: @@
 |- valign="top"
 | width='120' | '''Signatures'''
-|{{Func|ft:extract|$nodes as node()*|node()*}}<br />{{Func|ft:extract|$nodes as node()*, $name as xs:string|node()*}}<br />{{Func|ft:extract|$nodes as node()*, $name as xs:string, $length as xs:integer|node()*}}
+|{{Func|ft:extract|$nodes as node()*|node()*}}<br/>{{Func|ft:extract|$nodes as node()*, $name as xs:string|node()*}}<br/>{{Func|ft:extract|$nodes as node()*, $name as xs:string, $length as xs:integer|node()*}}
 |- valign="top"
 | '''Summary'''
-|Extracts and returns relevant parts of full-text results. It puts a marker element around the resulting {{Code|$nodes}} of a full-text index request and chops irrelevant sections of the result.<br />The default element name of the marker element is {{Code|mark}}. An alternative element name can be chosen via the optional {{Code|$name}} argument.<br />The default length of the returned text is {{Code|150}} characters. An alternative length can be specified via the optional {{Code|$length}} argument. Note that the effective text length may differ from the specified text due to formatting and readibility issues.<br />For more details on this function, please have a look at {{Function||ft:mark}}.
+|Extracts and returns relevant parts of full-text results. It puts a marker element around the resulting {{Code|$nodes}} of a full-text index request and chops irrelevant sections of the result.<br/>The default element name of the marker element is {{Code|mark}}. An alternative element name can be chosen via the optional {{Code|$name}} argument.<br/>The default length of the returned text is {{Code|150}} characters. An alternative length can be specified via the optional {{Code|$length}} argument. Note that the effective text length may differ from the specified text due to formatting and readibility issues.<br/>For more details on this function, please have a look at {{Function||ft:mark}}.
 |- valign="top"
 | '''Examples'''

@@ Line 234: / Line 234: @@
 let $end   := 10
 let $term  := 'welcome'
-for $ft in (db:get('DB')//*[text() contains text { $term }])[position() = $start to $end]
+let $test  := function($node) { $node/text() contains text { $term } }
 return element hit {
-   ft:mark($ft[text() contains text { $term }])
+   ft:mark($ft[$test(.)])
+}
 </syntaxhighlight>