In between search:parse and search:resolve, *you* are in control of the query.
You can do anything you like. To pick one possibility at random, you can
rewrite the query to be more efficient. Depending on the situation you might
need to transform the query in fairly complex ways, but you have the right
tools to do that.
You may find it helpful to know how to convert back and forth between cts:query
items and cts:query XML using 'document { ... }' in one direction, and
'cts:query(...xml...)/*' in the other. If you prefer you can work with queries
entirely as XML, but I usually stick with the cts:query API.
Here is a crude example, which could be improved and extended:
import module namespace search = "http://marklogic.com/appservices/search";
at "/MarkLogic/appservices/search/search.xqy";
import module namespace dls = "http://marklogic.com/xdmp/dls";
at "/MarkLogic/dls.xqy";
declare namespace ft="http://thecompany/facet"; ;
declare function local:rewrite(
$q as cts:query)
as cts:query
{
typeswitch ($q)
case cts:or-query return cts:or-query(
local:rewrite(cts:or-query-queries($q)))
case cts:word-query return cts:element-word-query(
xs:QName('ft:author'),
cts:word-query-text($q),
cts:word-query-options($q))
default return $q
};
<cts:and-query xmlns:cts="http://marklogic.com/cts";>
{ dls:documents-query() }
<cts:not-query>
<cts:collection-query>
<cts:uri>error</cts:uri>
<cts:uri>collection-A</cts:uri>
<cts:uri>collection-B</cts:uri>
</cts:collection-query>
</cts:not-query>
<cts:collection-query>
<cts:uri>collection-C</cts:uri>
<cts:uri>collection-D</cts:uri>
</cts:collection-query>
<cts:properties-query>
{
document { local:rewrite(cts:query(search:parse('foo OR bar'))) }/*
}
</cts:properties-query>
</cts:and-query>
=>
<cts:and-query xmlns:cts="http://marklogic.com/cts";>
<cts:properties-query>
<cts:registered-query>
<cts:id>3813349421842441358</cts:id>
</cts:registered-query>
</cts:properties-query>
<cts:not-query>
<cts:collection-query>
<cts:uri>error</cts:uri>
<cts:uri>collection-A</cts:uri>
<cts:uri>collection-B</cts:uri>
</cts:collection-query>
</cts:not-query>
<cts:collection-query>
<cts:uri>collection-C</cts:uri>
<cts:uri>collection-D</cts:uri>
</cts:collection-query>
<cts:properties-query>
<cts:or-query>
<cts:element-word-query>
<cts:element xmlns:ft="http://thecompany/facet";>ft:author</cts:element>
<cts:text xml:lang="en">foo</cts:text>
</cts:element-word-query>
<cts:element-word-query>
<cts:element xmlns:ft="http://thecompany/facet";>ft:author</cts:element>
<cts:text xml:lang="en">bar</cts:text>
</cts:element-word-query>
</cts:or-query>
</cts:properties-query>
</cts:and-query>
-- Mike
On 16 May 2013, at 14:51 , Mauricio Valderrama Fonseca <[email protected]>
wrote:
> I forgot to say the version, I'm using 5.0-5
>
> Sorry for the confusion, from the initial $query:
>
> let $query := <cts:and-query xmlns:cts="http://marklogic.com/cts";>
> { dls:documents-query() }
> <cts:not-query>
> <cts:collection-query>
> <cts:uri>error</cts:uri>
> <cts:uri>collection-A</cts:uri>
> <cts:uri>collection-B</cts:uri>
> </cts:collection-query>
> </cts:not-query>
> <cts:collection-query>
> <cts:uri>collection-C</cts:uri>
> <cts:uri>collection-D</cts:uri>
> </cts:collection-query>
> <cts:properties-query>
> <cts:element-query>
> <cts:element xmlns:ft="http://thecompany/facet";>ft:author</cts:element>
> <cts:word-query qtextref="cts:text"
> xmlns:xs="http://www.w3.org/2001/XMLSchema";>
> <cts:text>fiber</cts:text>
> <cts:option>case-insensitive</cts:option>
> <cts:option>diacritic-insensitive</cts:option>
> <cts:option>punctuation-insensitive</cts:option>
> <cts:option>whitespace-insensitive</cts:option>
> <cts:option>stemmed</cts:option>
> <cts:option>wildcarded</cts:option>
> </cts:word-query>
> </cts:element-query>
> </cts:properties-query>
> </cts:and-query>
>
> The bolded part (the word-query) is the result of a search:parse, like this:
>
> let $options := <options xmlns="http://marklogic.com/appservices/search";>
> <term>
> <term-option>case-insensitive</term-option>
> <term-option>diacritic-insensitive</term-option>
> <term-option>punctuation-insensitive</term-option>
> <term-option>whitespace-insensitive</term-option>
> <term-option>stemmed</term-option>
> <term-option>wildcarded</term-option>
> </term>
> </options>
>
> return search:parse("fiber", $options)
>
> the query text could be more complex, like this: "fiber OR silicon", and then
> it won't be a word-query and that's why I can't use the
> element-word-query you suggested me. The user inputs a text to find, he can
> use the default grammar (AND, OR, parentisis, double quotes), and can limit
> the elements to search (one or more than one), then dynamically the
> element-queries are created and each one will use the parsed query text.
>
>
>
> On Thu, May 16, 2013 at 4:03 PM, Michael Blakeley <[email protected]> wrote:
> I don't see it, unless maybe it's a release-specific bug. With 6.0-3:
>
> import module namespace search = "http://marklogic.com/appservices/search";
> at "/MarkLogic/appservices/search/search.xqy";
>
> search:parse(
> 'author:foo',
> <options xmlns="http://marklogic.com/appservices/search";>
> <return-results>true</return-results>
> <constraint name="author">
> <range type="xs:string">
> <element ns="http://thecompany/facet"; name="author"/>
> <fragment-scope>properties</fragment-scope>
> <facet-option>concurrent</facet-option>
> <facet-option>item-order</facet-option>
> <facet-option>ascending</facet-option>
> <facet-option>limit=6</facet-option>
> </range>
> </constraint>
> <term>
> <term-option>case-insensitive</term-option>
> <term-option>diacritic-insensitive</term-option>
> <term-option>punctuation-insensitive</term-option>
> <term-option>whitespace-insensitive</term-option>
> <term-option>stemmed</term-option>
> <term-option>wildcarded</term-option>
> </term>
> </options>)
> =>
> <cts:properties-query qtextref="schema-element(cts:query)"
> xmlns:cts="http://marklogic.com/cts";
> xmlns:xs="http://www.w3.org/2001/XMLSchema";>
> <cts:element-range-query qtextpre="author:" qtextref="cts:annotation"
> operator="=">
> <cts:element xmlns:_1="http://thecompany/facet";>_1:author</cts:element>
> <cts:annotation qtextref="following-sibling::cts:value"/>
> <cts:value xsi:type="xs:string"
> xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance";>foo</cts:value>
> </cts:element-range-query>
> </cts:properties-query>
>
> I copied those options verbatim from your email. But the query output is
> different. I see an element-range query, not an element-query.
>
> Are you sure those options match up with your test case?
>
> -- Mike
>
> On 16 May 2013, at 11:57 , Mauricio Valderrama Fonseca <[email protected]>
> wrote:
>
> > Hi Michael,
> >
> > The <cts:word-query..> in the script is the result of a search:parse
> > execution, then I cannot use the element-word-query. I need to get the
> > matches limiting the search to a specific element (in the document or in
> > the properties), and using the element-query retrieves the right results. I
> > tried using a constraint and it worked fine when the element was in the
> > document, but when the element is in the properties I could not make it
> > worked. Is there any other way to make it accurate instead of using the
> > "element word positions" index?
> >
> > Thanks
> >
> >
> > On Thu, May 16, 2013 at 12:14 PM, Michael Blakeley <[email protected]>
> > wrote:
> > It looks to me like you could use an element-word-query instead of a nested
> > element-query/word-query combination. That will be more efficient.
> >
> > http://docs.marklogic.com/cts:element-word-query
> >
> > Accurate results with element-query alone will often require element
> > positions, for example the "element word positions" index. However
> > positions require extra disk space and CPU time, so unless they are
> > necessary I prefer to avoid them.
> >
> > http://docs.marklogic.com/guide/admin/text_index
> >
> > -- Mike
> >
> > On 16 May 2013, at 07:50 , Mauricio Valderrama Fonseca <[email protected]>
> > wrote:
> >
> > > Hi All,
> > >
> > > I'm facing a problem using the search:resolve function, this is the
> > > xquery:
> > >
> > > xquery version "1.0-ml";
> > > import module namespace dls = "http://marklogic.com/xdmp/dls"; at
> > > "/MarkLogic/dls.xqy";
> > > import module namespace search="http://marklogic.com/appservices/search";
> > > at "/MarkLogic/appservices/search/search.xqy";
> > >
> > > let $query := <cts:and-query xmlns:cts="http://marklogic.com/cts";>
> > > { dls:documents-query() }
> > > <cts:not-query>
> > > <cts:collection-query>
> > > <cts:uri>error</cts:uri>
> > > <cts:uri>collection-A</cts:uri>
> > > <cts:uri>collection-B</cts:uri>
> > > </cts:collection-query>
> > > </cts:not-query>
> > > <cts:collection-query>
> > > <cts:uri>collection-C</cts:uri>
> > > <cts:uri>collection-D</cts:uri>
> > > </cts:collection-query>
> > > <cts:properties-query>
> > > <cts:element-query>
> > > <cts:element
> > > xmlns:ft="http://thecompany/facet";>ft:author</cts:element>
> > > <cts:word-query qtextref="cts:text"
> > > xmlns:xs="http://www.w3.org/2001/XMLSchema";>
> > > <cts:text>fiber</cts:text>
> > > <cts:option>case-insensitive</cts:option>
> > > <cts:option>diacritic-insensitive</cts:option>
> > > <cts:option>punctuation-insensitive</cts:option>
> > > <cts:option>whitespace-insensitive</cts:option>
> > > <cts:option>stemmed</cts:option>
> > > <cts:option>wildcarded</cts:option>
> > > </cts:word-query>
> > > </cts:element-query>
> > > </cts:properties-query>
> > > </cts:and-query>
> > >
> > > let $options := <options xmlns="http://marklogic.com/appservices/search";>
> > > <return-results>true</return-results>
> > > <constraint name="author">
> > > <range type="xs:string">
> > > <element ns="http://thecompany/facet"; name="author"/>
> > > <fragment-scope>properties</fragment-scope>
> > > <facet-option>concurrent</facet-option>
> > > <facet-option>item-order</facet-option>
> > > <facet-option>ascending</facet-option>
> > > <facet-option>limit=6</facet-option>
> > > </range>
> > > </constraint>
> > > <term>
> > > <term-option>case-insensitive</term-option>
> > > <term-option>diacritic-insensitive</term-option>
> > > <term-option>punctuation-insensitive</term-option>
> > > <term-option>whitespace-insensitive</term-option>
> > > <term-option>stemmed</term-option>
> > > <term-option>wildcarded</term-option>
> > > </term>
> > > </options>
> > >
> > > return search:resolve($query, $options)
> > >
> > >
> > > The result is this one:
> > >
> > > <search:response total="32" start="1" page-length="10" xmlns=""
> > > xmlns:search="http://marklogic.com/appservices/search";>
> > > <search:facet name="author">
> > > <search:facet-value name="author 1" count="1">author
> > > 1</search:facet-value>
> > > <search:facet-value name="author 2" count="1">author
> > > 2</search:facet-value>
> > > <search:facet-value name="author 3" count="1">author
> > > 3</search:facet-value>
> > > <search:facet-value name="author 4" count="1">author
> > > 4</search:facet-value>
> > > <search:facet-value name="author 5" count="1">author
> > > 5</search:facet-value>
> > > <search:facet-value name="author 6" count="1">author
> > > 6</search:facet-value>
> > > </search:facet>
> > > <search:metrics>
> > > <search:query-resolution-time>PT0.007S</search:query-resolution-time>
> > > <search:facet-resolution-time>PT0.002S</search:facet-resolution-time>
> > > <search:snippet-resolution-time>PT0S</search:snippet-resolution-time>
> > > <search:total-time>PT0.01S</search:total-time>
> > > </search:metrics>
> > > </search:response>
> > >
> > >
> > >
> > > In that case the facet is done using a element-range-index: <element
> > > ns="http://thecompany/facet"; name="author"/> this element is in the
> > > properties, but the result is inconsistent too if we use an element in
> > > the document. It is important to make notice that the facet and the
> > > results are CONSISTENT until we include a <cts:element-query> in the
> > > query.
> > >
> > > Watching the source, I noticed the functions: cts:element-values and
> > > cts:frequency are used to create the search:facet element. Then, I tried
> > > them directly and had the same result:
> > >
> > >
> > > xquery version "1.0-ml";
> > > import module namespace dls = "http://marklogic.com/xdmp/dls"; at
> > > "/MarkLogic/dls.xqy";
> > >
> > > let $facet-options := ("type=string", "properties", "descending",
> > > "frequency-order", "limit=6")
> > > let $query := cts:document-fragment-query(
> > > cts:and-query((
> > > dls:documents-query(),
> > > cts:not-query(cts:collection-query(("error", "collection-A",
> > > "collection-B")), 1),
> > > cts:collection-query(("collection-C", "collection-D")),
> > > cts:properties-query(
> > > cts:element-query(
> > > fn:QName("http://thecompany/facet";, "author"),
> > > cts:word-query(
> > > "fiber",
> > >
> > > ("case-insensitive","diacritic-insensitive","punctuation-insensitive","whitespace-insensitive","stemmed","wildcarded","lang=en"),
> > > 1
> > > ),
> > > ()
> > > )
> > > )
> > > ), ())
> > > )
> > > return
> > > cts:element-values(fn:QName("http://thecompany/facet","author";),(),($facet-options,"concurrent"),$query,1,
> > > ())
> > >
> > >
> > > The response was:
> > >
> > > author 1
> > > author 2
> > > author 3
> > > author 4
> > > author 5
> > > author 6
> > >
> > > Now, executing a cts:search with the same $query value:
> > >
> > > xquery version "1.0-ml";
> > > import module namespace dls = "http://marklogic.com/xdmp/dls"; at
> > > "/MarkLogic/dls.xqy";
> > >
> > > let $query := cts:document-fragment-query(
> > > cts:and-query((
> > > dls:documents-query(),
> > > cts:not-query(cts:collection-query(("error", "collection-A",
> > > "collection-B")), 1),
> > > cts:collection-query(("collection-C", "collection-D")),
> > > cts:properties-query(
> > > cts:element-query(
> > > fn:QName("http://thecompany/facet";, "author"),
> > > cts:word-query(
> > > "fiber",
> > >
> > > ("case-insensitive","diacritic-insensitive","punctuation-insensitive","whitespace-insensitive","stemmed","wildcarded","lang=en"),
> > > 1
> > > ),
> > > ()
> > > )
> > > )
> > > ), ())
> > > )
> > > return cts:search(fn:collection(),$query)
> > >
> > >
> > > I got an empty sequence. Then the questions are: Why am I getting this
> > > inconsistencies when there is an element-query in the search? how can I
> > > avoid it?
> > >
> > > Thanks!
> > >
> > > _______________________________________________
> > > General mailing list
> > > [email protected]
> > > http://developer.marklogic.com/mailman/listinfo/general
> >
> > _______________________________________________
> > General mailing list
> > [email protected]
> > http://developer.marklogic.com/mailman/listinfo/general
> >
> >
> >
> > --
> > Atentamente
> > Mauricio Valderrama Fonseca
> > _______________________________________________
> > General mailing list
> > [email protected]
> > http://developer.marklogic.com/mailman/listinfo/general
>
> _______________________________________________
> General mailing list
> [email protected]
> http://developer.marklogic.com/mailman/listinfo/general
>
>
>
> --
> Atentamente
> Mauricio Valderrama Fonseca
> _______________________________________________
> General mailing list
> [email protected]
> http://developer.marklogic.com/mailman/listinfo/general
_______________________________________________
General mailing list
[email protected]
http://developer.marklogic.com/mailman/listinfo/general
