emchateau

xquery version "3.0";

(: find the shortest and longest article and get the average word count of a collection of TEI XML articles :)

declare namespace tei="http://www.tei-c.org/ns/1.0";

(: in our case, 'articles' are TEI divs that have @xml:id attributes and no child divs; 
   we filter out the foreward since they're not full articles. :)
let $milestone-articles := collection('/db/cms/apps/tei-content/data/milestones')//tei:div[@xml:id and not(.//tei:div)][@xml:id ne 'foreword']
let $article-infos := 

emchateau

xquery version "3.0";

declare namespace fn="http://www.w3.org/2005/xpath-functions";

(: Fix problems with mis-capitalized names. For example: 
    Before: MACARTHUR, Douglas II
    After:  MacArthur, Douglas II
:)
declare function local:fix-name-capitalization($name as xs:string) {
    (: 

emchateau

xquery version "1.0";

(: A naive approach to sentence tokenization inspired by http://stackoverflow.com/a/2103653/659732 
 : 
 : Works well with edited text like newspapers. Parameters like punctuation can/should be edited; 
 : see the section below called "criteria".
 :
 : For a more sophisticated approach, see Tibor Kiss and Jan Strunk, "Unsupervised Multilingual 
 : Sentence Boundary Detection", Computational Linguistics, Volume 32, Issue 4, December 2006, 
 : pp. 485-525.  Also, see these discussions of sentence tokenization: 

emchateau

javascript:(function({
  var INSTAPAPER=true,w=window,d=document,pageSelectedTxt=w.getSelection?w.getSelection():(d.getSelection)?d.getSelection():(d.selection?d.selection.createRange().text:0),pageTitle=d.title,pageUri=w.location.href,tmplt="";
  tmplt="From ["+pageTitle+"]("+pageUri+"):\n\n";
  if(pageSelectedTxt!="") {
    pageSelectedTxt=">%20"+pageSelectedTxt;
    pageSelectedTxt=pageSelectedTxt.replace(/(\r\n|\n+|\r)/gm,"\n");
    pageSelectedTxt=pageSelectedTxt.replace(/\n/g,"\n>%20\n>%20");
    w.location.href="nvalt://make/?txt="+encodeURIComponent(tmplt+pageSelectedTxt)+"&title="+encodeURIComponent(pageTitle)
  }
  else {

emchateau

<!--
title:          selectAllExceptFirstAndLast
description:    sélectionne tout sauf le premier et le dernier élément dans une liste
version:        xslt 1.0
-->
 
<xsl:for-each select="element[not(position() = (1, last() ))]">
    <xsl:value-of select="." separator=", "/>
</xsl:for-each>

emchateau

(: list all files in the directory of your query file in BaseX :)

 let $dir := file:parent(static-base-uri())
 for $file in file:list($dir)
 return $dir || $file

emchateau

(: find out the current working directory in BaseX :)

 file:parent('.')

emchateau

<?xml version="1.0" encoding="UTF-8"?>
<!--
    @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
    @Name :         .xsl
    @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
    @version :      000
    @creaDate :     2014/
    @modifDate      
    @vXslt:         2.0
    @autor :        Emmanuel Château emchateau@laposte.net

emchateau

<!-- Split content as attribute value -->
<xsl:template match="element[@id]">
  <xsl:variable name="att-values" select="tokenize(@id, ', ')"/>
  <xsl:for-each select="tokenize(., '; ')">
    <xsl:variable name="pos" select="position()"/>
    <xsl:if test="position() gt 1"><xsl:text>; </xsl:text></xsl:if>
    <a href="#{$att-values[$pos]}">
      <xsl:value-of select="."/>
    </a>
  </xsl:for-each>

emchateau

<div>
  <h2>{$heading} - {count($actions/generate)}</h2>
  <p>Actions are processes that generate a new item from an existing item.</p>
   <div>
   {$partial("action1.xml","action",$actions/generate )}
   </div>
</div>