Created
September 3, 2018 16:16
-
-
Save mathias-goebel/828c504c564acd98c76894c4ac4d3adc to your computer and use it in GitHub Desktop.
wikidata to dracor
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
xquery version "3.1"; | |
import module namespace functx="http://www.functx.com"; | |
declare namespace tei="http://www.tei-c.org/ns/1.0"; | |
let $path := "......../dlina/GerDraCor and Wikidata.csv" | |
let $rows := | |
(file:read-binary($path) | |
=> util:binary-to-string() | |
=> tokenize("\n"))[position() gt 1] | |
let $collection-uri := "/db/gerdracorQ" | |
let $read-in := | |
let $directory := "......../dlina/dracor-ger/tei/" | |
return | |
( | |
xmldb:remove($collection-uri), | |
xmldb:create-collection("/db", "gerdracorQ"), | |
xmldb:store-files-from-pattern($collection-uri, $directory, "*.xml") | |
) | |
for $row in $rows | |
(: parse CSV :) | |
let $tokenzzzzz := tokenize($row, ",") | |
let $filename := $tokenzzzzz[1] || ".xml" | |
let $wikidataUrl := $tokenzzzzz[2] | |
let $Q := substring-after($wikidataUrl, "/wiki/") | |
let $idno := <tei:idno type="wikidata" xml:base="https://www.wikidata.org/wiki/">{$Q}</tei:idno> | |
=> functx:change-element-ns-deep("http://www.tei-c.org/ns/1.0", "") | |
let $tei := doc($collection-uri || "/" || $filename)/* | |
let $do := update insert $idno into $tei//tei:publicationStmt | |
return | |
$tei |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment