Protogenie Config

gistfile1.txt

<?xml version="1.0" encoding="UTF-8"?>
<?xml-model href="https://hipster-philology.github.io/protogenie/protogenie/schema.rng"
     schematypens="http://relaxng.org/ns/structure/1.0"?>
<config>
    <output column_marker="TAB">
        <header name="order">
            <key>token</key>
            <key>lemma</key>
            <key>pos</key>
            <key>Dis</key>
            <key>Entity</key>
            
            <key>Gend</key>
            <key>Numb</key>
            <key>Case</key>
            <key>Deg</key>
            
            <key>Mood</key>
            <key>Tense</key>
            <key>Voice</key>
            
            <key>Person</key>
        </header>
    </output>
    <postprocessing>
        <disambiguation matchPattern="_(\d+)$" new-column="Dis" source-column="lemma" default="_" /> <!-- Extract disambiguation -->
 
        <disambiguation matchPattern="_(\w)$" new-column="Entity" source-column="lemma" default="_" /> <!-- Extract disambiguation -->
        
        <disambiguation matchPattern="Gend\=([\w-]+)\|?" new-column="Gend" source-column="morph" default="_" />
        <disambiguation matchPattern="Numb\=([\w-]+)\|?" new-column="Numb" source-column="morph" default="_" />
        <disambiguation matchPattern="Case\=([\w-]+)\|?" new-column="Case" source-column="morph" default="_" />
        <disambiguation matchPattern="Deg\=([\w-]+)\|?" new-column="Deg" source-column="morph" default="_" />
        
        <disambiguation matchPattern="Mood\=([\w-]+)\|?" new-column="Mood" source-column="morph" default="_" />
        <disambiguation matchPattern="Tense\=([\w-]+)\|?" new-column="Tense" source-column="morph" default="_" />        
        <disambiguation matchPattern="Voice\=([\w-]+)\|?" new-column="Voice" source-column="morph" default="_" />
        
        <disambiguation matchPattern="Person\=([\w-]+)\|?" new-column="Person" source-column="morph" default="_" />
        
        <replacement matchPattern="$^" replacementPattern="_">
            <applyTo source="morph">
                <target>morph</target>
            </applyTo>
        </replacement>
        
        <toolbox name="RomanNumeral" matchPattern="^(M{1,4}(CM|CD|D?C{0,3})(XC|XL|L?X{0,3})(IX|IV|V?I{0,3})|M{0,4}(CM|C?D|D?C{1,3})(XC|XL|L?X{0,3})(IX|IV|V?I{0,3})|M{0,4}(CM|CD|D?C{0,3})(XC|X?L|L?X{1,3})(IX|IV|V?I{0,3})|M{0,4}(CM|CD|D?C{0,3})(XC|XL|L?X{0,3})(IX|I?V|V?I{1,3}))$">
            <applyTo source="token">
                <target>token</target>
                <target>form</target>
            </applyTo>
        </toolbox>
        <skip matchPattern="^\W+$" source="token" /> <!-- Remove ponctuation lines -->
    </postprocessing>
    <default-header>
        <header type="explicit">
            <key map-to="token">form</key>
            <key>lemma</key>
            <key>morph</key>
            <key>pos</key>
            <key>index</key>
        </header>
    </default-header>
    <memory path="memory_$file$.csv"/>
    <corpora>
        <corpus path="./output/*.tsv" column_marker="TAB">
            <splitter name="empty_line" />
            <header type="default"/>
        </corpus>
    </corpora>
</config>