On Sat, 2020-04-25 at 13:46 -0400, Graydon Saunders wrote:
>
> I think I have figured out a way to connect the adjacent marked words
> in
> the phrasal term into a single mark element. I cannot convince myself
> that
> this is the right way; is there a better approach than tumbling
> windows?
I just search for the multi-word phrase and surround that. Enclosed is
a sample from a prototype for a keyword in context search index for
fromoldbooks.org (not yet live). Lookognow i see it's not very neat but
maybe it'll give some ideas.
let $results :=
(
let $matches := $doc//p[not(ancestor::longdesc) and (.//text() contains text {
$term })]
for $match at $pos in $matches
let $sock := <singleton>{ft:mark( $match[text() contains text { $term }] ,
'sock')}</singleton>,
(: "sock" is now a singleton element likely containing a p or title element,
: with every phrase matching the query surrounded with a sock element.
:)
$longbefore := concat(
"
",
local:ws( string-join(($sock//sock)[1]/preceding-sibling::node(), '' ))),
$before := replace($longbefore, " $", " "),
$after:= local:ws( string-join(
($sock//sock)[last()]/following-sibling::node(), '')),
$uri := document-uri( $match/ancestor::document-node() ),
$image := $match/ancestor::image
where not( empty(($sock//sock)))
return
<details id="d{$pos}" data-group="{ ($image/@source) }">
<summary class="{if ($image) then 'image' else 'text'}{
if ($image and ($image eq $matches[$pos - 1]/ancestor::image))
then ' same ' else ''}"
>
<before>
{
substring($before, string-length($before) - 100, string-length($before))
}
</before>
<match><b>{ string-join($sock//sock, ' ') }</b><after>{
local:trunc($after, 60) }</after>
</match>
</summary>
)
return
<results>
{
for $r in $results
group by $g := $r/@data-group
return
<div class="group">
<p class="metadata">{
if ($g ne "") then
let $source := $doc//source[@id = $g]
return
(
<a href="/{$g}/">{
$source/title/node()
}</a>,
if ($source/author and ($source/author ne "Anonymous"))
then ", by " || $source/author
else "",
if ($source/date)
then " (" || $source/date || ")"
else ""
)
else
$r[1]//a[contains-token(@class, 'info')]
}</p>
{$r}
</div>
}
</results>
--
Liam Quin, https://www.delightfulcomputing.com/
Available for XML/Document/Information Architecture/XSLT/
XSL/XQuery/Web/Text Processing/A11Y training, work & consulting.
Barefoot Web-slave, antique illustrations: http://www.fromoldbooks.org
