Skip to content

Instantly share code, notes, and snippets.

View dmj's full-sized avatar

David Maus dmj

View GitHub Profile
<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<PcGts xmlns="http://schema.primaresearch.org/PAGE/gts/pagecontent/2013-07-15" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://schema.primaresearch.org/PAGE/gts/pagecontent/2013-07-15 http://schema.primaresearch.org/PAGE/gts/pagecontent/2013-07-15/pagecontent.xsd">
<Metadata>
<Creator>prov=University of Rostock/Institute of Mathematics/CITlab|PLANET AI GmbH/Tobias Gruening/tobias.gruening@planet-ai.de:name=/net_tf/LA73_249_0mod360.pb:de.uros.citlab.segmentation.CITlab_LA_ML:v=2.6.6
Transkribus</Creator>
<Created>2020-05-07T16:39:07.021+02:00</Created>
<LastChange>2021-02-18T16:36:43.024+01:00</LastChange>
<TranskribusMetadata docId="381927" pageId="14891631" pageNr="2" tsid="52825554" status="IN_PROGRESS" userId="17934" imgUrl="https://files.transkribus.eu/Get?id=UIHLEKMMJIAETOIHVHUGJRYJ&amp;fileType=view" xmlUrl="https://files.transkribus.eu/Get?id=BHVNQOCNFBOXXCROAPWCNSYD" imageId="10
@dmj
dmj / tsv2tei.xpr
Last active October 15, 2021 11:10
tsv2tei
<?xml version="1.0" encoding="UTF-8"?>
<project>
<meta>
<filters directoryPatterns="" filePatterns="\Qtsv2tei.xpr\E" positiveFilePatterns="" showHiddenFiles="false"/>
<options>
<serialized xml:space="preserve">
<serializableOrderedMap>
<entry>
<String>scenario.associations</String>
<scenarioAssociation-array>
@dmj
dmj / publish.xpl
Last active September 22, 2021 06:47
Simple XProc 3.0 pipeline for publishing letters
<p:declare-step version="3.0" name="main"
xmlns:c="http://www.w3.org/ns/xproc-step"
xmlns:p="http://www.w3.org/ns/xproc"
xmlns:xs="http://www.w3.org/2001/XMLSchema">
<p:output port="result" sequence="true"/>
<p:variable name="targetDirectory" as="xs:string" select="resolve-uri('../../export/publish/', static-base-uri())"/>
<p:file-delete href="{$targetDirectory}" recursive="true" fail-on-error="false"/>
{
"require": {
"hab/picarecord": "^1.1",
"hab/picareader": "^1.2"
}
}
@dmj
dmj / pagelib.xsl
Created April 29, 2021 12:57
Parse Transkribus PAGE-XML annotations
<xsl:transform version="3.0" exclude-result-prefixes="#all"
xpath-default-namespace="http://schema.primaresearch.org/PAGE/gts/pagecontent/2013-07-15"
xmlns="http://www.tei-c.org/ns/1.0"
xmlns:fn="https://code.dehmel.digital/ns"
xmlns:map="http://www.w3.org/2005/xpath-functions/map"
xmlns:xs="http://www.w3.org/2001/XMLSchema"
xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
<xsl:template name="fn:properties-to-fs" as="element(Q{http://www.tei-c.org/ns/1.0}fs)?">
<xsl:param name="properties" as="map(*)" required="true"/>
@dmj
dmj / records.sch
Created March 20, 2021 19:32
A streaming Schematron
<sch:schema xmlns:sch="http://purl.oclc.org/dsdl/schematron" queryBinding="xslt3"
xmlns:xs="http://www.w3.org/2001/XMLSchema"
xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
<sch:ns prefix="mets" uri="http://www.loc.gov/METS/"/>
<sch:ns prefix="oai" uri="http://www.openarchives.org/OAI/2.0/"/>
<sch:ns prefix="xs" uri="http://www.w3.org/2001/XMLSchema"/>
<xsl:accumulator name="recordId" streamable="yes" initial-value="()" as="xs:string?">
<xsl:accumulator-rule match="oai:identifier/text()" select="."/>
</xsl:accumulator>
<sch:pattern>
@dmj
dmj / 000000002.xml
Last active March 17, 2021 06:19
Example of a TEI encoded letter (HANSb14780, postcard to Richard Dehmel, Vienna 1899)
<PcGts xmlns="http://schema.primaresearch.org/PAGE/gts/pagecontent/2013-07-15" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://schema.primaresearch.org/PAGE/gts/pagecontent/2013-07-15 http://schema.primaresearch.org/PAGE/gts/pagecontent/2013-07-15/pagecontent.xsd">
<Metadata>
<Creator>prov=University of Rostock/Institute of Mathematics/CITlab|PLANET AI GmbH/XXXX/XXXX:name=/net_tf/LA73_249_0mod360.pb:de.uros.citlab.segmentation.CITlab_LA_ML:v=2.6.6
Transkribus</Creator>
<Created>2020-05-07T16:39:07.021+02:00</Created>
<LastChange>2021-02-18T16:36:43.024+01:00</LastChange>
<TranskribusMetadata docId="381927" pageId="14891631" pageNr="2" tsid="52825554" status="IN_PROGRESS" userId="17934" imgUrl="https://files.transkribus.eu/Get?id=XXXX&amp;fileType=view" xmlUrl="https://files.transkribus.eu/Get?id=XXXX" imageId="10820798"/>
</Metadata>
<Page imageFilename="00000002.tif" imageWidth="3849" imageHeight="2478">
<ReadingOrder>
@dmj
dmj / abstract-rule.sch
Last active March 2, 2021 18:48
Recursive sch:include
<sch:rule xmlns:sch="http://purl.oclc.org/dsdl/schematron" abstract="true">
<sch:assert test="false()"/>
</sch:rule>
@dmj
dmj / example.odd
Created October 18, 2020 10:39
TEI Stylesheets Issue 467
<?xml version="1.0"?>
<TEI xmlns="http://www.tei-c.org/ns/1.0" xml:lang="en">
<teiHeader>
<fileDesc>
<titleStmt>
<title>My TEI Extension</title>
<author>generated by Roma 5.0.1</author>
</titleStmt>
<publicationStmt>
<p>for use by whoever wants it</p>
<xsl:transform version="3.0" expand-text="yes"
xmlns:mets="http://www.loc.gov/METS/"
xmlns:mods="http://www.loc.gov/mods/v3"
xmlns:xs="http://www.w3.org/2001/XMLSchema"
xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
<xsl:output method="text" encoding="utf-8"/>
<xsl:template match="ul">