Example TEI Files

Minimal Example

tip

If you want to test this file on LAUDATIO, save the contents to a file called corpusHeader.xml or download our example file (you may need to right-click in order to download the file).

Note that this minimal example includes all fields required by the LAUDATIO data ingestion pipeline, even if they are optional according to the schema. (That is, this example contains all tags/attributes marked with ‼️ in the metadata model description.)

<?xml version='1.0' encoding='utf-8'?>
<?xml-model href="../rng/corpus.rng" type="application/xml" schematypens="http://relaxng.org/ns/structure/1.0"?>
<TEI xmlns="http://www.tei-c.org/ns/1.0">
    <teiHeader type="CorpusHeader">
        <fileDesc>
            <titleStmt>
                <title>Minimal Demo Corpus</title>
                <editor role="CorpusEditor">
                    <persName>
                        <forename>Jane</forename>
                        <surname>Doe</surname>
                    </persName>
                    <affiliation>
                        <orgName type="Department">Department of Linguistics</orgName>
                        <orgName type="Institution">University</orgName>
                    </affiliation>
                </editor>
            </titleStmt>
            <extent type="Tokens">123456789</extent>
            <publicationStmt>
                <authority>Humboldt-Universität zu Berlin</authority>
                <availability status="free">
                    <licence target="http://creativecommons.org/licenses/by/4.0/" />
                    <p>The corpus is published under a CC-BY 4.0 licence.</p>
                </availability>
                <date when="2026-06-16">First complete corpus release.</date>
            </publicationStmt>
            <sourceDesc>
                <list type="CorpusDocument">
                    <item corresp="document1" n="1" />
                </list>
            </sourceDesc>
        </fileDesc>
        <profileDesc>
            <langUsage>
                <language ident="de" style="Language">German</language>
            </langUsage>
        </profileDesc>
        <encodingDesc>
            <appInfo>
                <application ident="EXMARaLDA" version="3.0">
                    <label>EXMARaLDA XML for Partitur editor.</label>
                </application>
            </appInfo>
            <projectDesc>
                <p>
                    This is the project description of the corpus "Minimal Demo Corpus". It is part
                    of the LAUDATIO user documentation.
                </p>
            </projectDesc>
            <editorialDecl>
                <segmentation>
                    <p>Annotation 'dipl' has an independent segmentation. Every other annotation is
                        based on the segmentation of 'dipl.</p>
                </segmentation>
            </editorialDecl>
            <tagsDecl>
                <namespace xml:id="dipl" name="dipl" rend="Transcription">
                    <tagUsage gi="String">Diplomatic, character-based transcription.</tagUsage>
                </namespace>
            </tagsDecl>
        </encodingDesc>
        <revisionDesc>
            <change n="1.0" when="2026">First release of the corpus.</change>
        </revisionDesc>
    </teiHeader>
    <text />
</TEI>

Full example

<?xml version='1.0' encoding='utf-8'?>
<?xml-model href="./corpus.rng" type="application/xml" schematypens="http://relaxng.org/ns/structure/1.0"?>
<TEI xmlns="http://www.tei-c.org/ns/1.0">
    <teiHeader type="CorpusHeader">
        <fileDesc>
            <titleStmt>
                <title>Demo Corpus</title>
                <editor n="1" role="CorpusEditor">
                    <persName>
                        <forename>Jane</forename>
                        <surname>Doe</surname>
                    </persName>
                    <affiliation>
                        <orgName type="Department">Department of Linguistics</orgName>
                        <orgName type="Institution">University</orgName>
                    </affiliation>
                </editor>
                <author n="1" role="Annotator">
                    <persName>
                        <forename>John</forename>
                        <surname>Doe</surname>
                    </persName>
                    <affiliation>
                        <orgName type="Department">Department of History</orgName>
                        <orgName type="Institution">University</orgName>
                    </affiliation>
                </author>
                <author n="1" role="Infrastructure">
                    <persName>
                        <forename>Someone</forename>
                        <surname>Else</surname>
                    </persName>
                    <affiliation>
                        <orgName type="Department">Institut für deutsche Sprache und Linguistik</orgName>
                        <orgName type="Institution">Humboldt-Universität zu Berlin</orgName>
                    </affiliation>
                </author>
                <respStmt>
                    <resp>Metadata</resp>
                    <persName>
                        <forename>John</forename>
                        <surname>Doe</surname>
                    </persName>
                    <orgName type="Department">Department of History</orgName>
                    <orgName type="Institution">University</orgName>
                </respStmt>
            </titleStmt>
            <extent type="Tokens">123456789</extent>
            <publicationStmt>
                <authority>Humboldt-Universität zu Berlin</authority>
                <idno></idno>
                <availability status="free">
                    <licence target="http://creativecommons.org/licenses/by/4.0/"/>
                    <p>The corpus is published under a CC-BY 4.0 licence.</p>
                </availability>
                <date when="2026-06-16">First complete corpus release.</date>
            </publicationStmt>
            <sourceDesc>
                <list type="CorpusDocument">
                    <item corresp="document1" n="1" />
                    <item corresp="document2" n="2" />
                </list>
            </sourceDesc>
        </fileDesc>
        <profileDesc>
            <langUsage>
                <language ident="de" style="Language">Early New High German</language>
                <language ident="de" style="LanguageArea">Southern dialects</language>
                <language ident="de" style="LanguageType">Bavarian</language>
            </langUsage>
        </profileDesc>
        <encodingDesc n="1">
            <appInfo>
                <application ident="EXMARaLDA" version="3.0">
                    <label>EXMARaLDA XML for Partitur editor.</label>
                </application>
            </appInfo>
            <projectDesc>
                <p>
                    <ref target="https://laudatio-documentation.pages.cms.hu-berlin.de"/>
                    This is the project description of the corpus "Minimal Demo Corpus". It is part of the LAUDATIO user documentation.
                </p>
            </projectDesc>
            <editorialDecl>
                <segmentation>
                    <p>Annotation 'dipl' has an independent segmentation. Every other annotation is
                        based on the segmentation of 'dipl.</p>
                </segmentation>
                <normalization>
                    <p>No normalization is applied.</p>
                </normalization>
            </editorialDecl>
            <tagsDecl>
                <namespace name="dipl" rend="Transcription" xml:id="d">
                    <tagUsage gi="String">Diplomatic,character based transcription.</tagUsage>
                </namespace>
                <namespace name="POS" rend="Lexical" xml:id="pos">
                    <tagUsage gi="DET">Determiner.</tagUsage>
                    <tagUsage gi="N">Noun.</tagUsage>
                    <tagUsage gi="V">Verb.</tagUsage>
                    <tagUsage gi="P">Punctuation.</tagUsage>
                    <tagUsage gi="PRON">Pronoun.</tagUsage>
                </namespace>
            </tagsDecl>
        </encodingDesc>
        <encodingDesc n="2">
            <appInfo>
                <application ident="ANNIS" version="4.15.1">
                    <label>Search and Visualization in Multilevel Linguistic Corpora ANNIS.</label>
                </application>
            </appInfo>
            <projectDesc>
                <p>
                    <ref target="https://laudatio-documentation.pages.cms.hu-berlin.de"/>
                    This is the project description of the corpus "Minimal Demo Corpus". It is part of the LAUDATIO user documentation.
                </p>
            </projectDesc>
            <editorialDecl>
                <segmentation>
                    <p>Annotation 'dipl' has an independent segmentation. Every other annotation is
                        based on the segmentation of 'dipl.</p>
                </segmentation>
                <normalization>
                    <p>No normalization is applied.</p>
                </normalization>
            </editorialDecl>
            <tagsDecl>
                <namespace xml:id="dipl" name="dipl" rend="Transcription">
                    <tagUsage gi="String">Diplomatic, character-based transcription.</tagUsage>
                </namespace>
                <namespace xml:id="pos" name="POS" rend="Lexical">
                    <tagUsage gi="DET">Determiner.</tagUsage>
                    <tagUsage gi="N">Noun.</tagUsage>
                    <tagUsage gi="V">Verb.</tagUsage>
                    <tagUsage gi="P">Punctuation.</tagUsage>
                    <tagUsage gi="PRON">Pronoun.</tagUsage>
                </namespace>
            </tagsDecl>
        </encodingDesc>
        <revisionDesc>
            <change n="1.0" type="CorpusRelease" when="2026" who="LAUDATIO">First release of the corpus.</change>
            <change n="2.0" type="CorpusExtension" when="2026-06-16" who="LAUDATIO">Consistency check of
                annotation keys. Change of corpus architecture, multiple tokenizations/segmentations.
                Additional texts were added to the corpus. Several annotation keys were deleted, replaced
                and checked.
            </change>
        </revisionDesc>
    </teiHeader>
    <text/>
</TEI>