check-vocabularyterms.pl

#!/bin/perl
#
# A given textfile is checked for occurrences of misspelled
# vocabulary terms from the following namespaces:
#   rdf, rdfs, owl, xsd
# USAGE: apply script to STDIN!
#   It will print all lines that contains a misspelled term.

# === CONFIG ===

# Separators between prefix and localname (write as character sequence)
$URISHORTFORMSEPARATORS=':';

# === PROGRAM ===

# --- Build map from localnames of vocabularyterms to /all/ its suffixes ---

%localname2prefixes = ();
@vocabularyterms = getVocabularyTerms();
foreach $vocabularyterm (@vocabularyterms) {
    ($prefix, $localname) = split(/:/, $vocabularyterm);
    if (not defined($localname2prefixes{$localname})) {
        $localname2prefixes{$localname} = $prefix;
    } else {
        $localname2prefixes{$localname} = $localname2prefixes{$localname} . " " . $prefix;
    }
}

# --- check file ---
# Each line of the file is searched for occurrences of the localnames
# for all registered vocabulary terms. If an occurrence is found,
# the actual prefix in the file is compared to all allowed prefixes
# for the localname (sometimes there are more than one, as for "Class").

$linenumber = 0;
while ($line = <STDIN>) {
    ++$linenumber;
    chomp($line);
    LOCALNAME: foreach $localname (keys(%localname2prefixes)) {
        $pattern = "([A-Za-z0-9]+)([$URISHORTFORMSEPARATORS])$localname\\W";
        if ($line =~ /$pattern/) {
            $actualPrefix = $1;
            $separator = $2;
            @expectedPrefixes = split(" ", $localname2prefixes{$localname});
            for $expectedPrefix (@expectedPrefixes) {
                if ($actualPrefix eq $expectedPrefix) {
                    next LOCALNAME;
                }
            }
            print "bad vocabulary term in line $linenumber: <$actualPrefix$separator$localname>\n";
        }
    }
}

# === VOCABULARY TERMS ===

sub getVocabularyTerms() {

@vocabularyterms_rdf = (
"rdf:type",
"rdf:Property",
"rdf:Statement",
"rdf:subject",
"rdf:predicate",
"rdf:object",
"rdf:List",
"rdf:first",
"rdf:rest",
"rdf:nil",
"rdf:Seq",
"rdf:Bag",
"rdf:Alt",
"rdf:_1",
"rdf:_2",
"rdf:_3",
"rdf:_4",
"rdf:_5",
"rdf:_6",
"rdf:_7",
"rdf:_8",
"rdf:_9",
"rdf:value",
"rdf:XMLLiteral"
);

@vocabularyterms_rdfs = (
"rdfs:domain",
"rdfs:range",
"rdfs:Resource",
"rdfs:Literal",
"rdfs:Datatype",
"rdfs:Class",
"rdfs:subClassOf",
"rdfs:subPropertyOf",
"rdfs:member",
"rdfs:Container",
"rdfs:ContainerMembershipProperty",
"rdfs:comment",
"rdfs:seeAlso",
"rdfs:isDefinedBy",
"rdfs:label"
);

@vocabularyterms_owl = (
"owl:AllDifferent",
"owl:AllDisjointClasses",
"owl:AllDisjointProperties",
"owl:allValuesFrom",
"owl:annotatedProperty",
"owl:annotatedSource",
"owl:annotatedTarget",
"owl:Annotation",
"owl:AnnotationProperty",
"owl:assertionProperty",
"owl:AsymmetricProperty",
"owl:Axiom",
"owl:backwardCompatibleWith",
"owl:bottomDataProperty",
"owl:bottomObjectProperty",
"owl:cardinality",
"owl:Class",
"owl:complementOf",
"owl:DataRange",
"owl:datatypeComplementOf",
"owl:DatatypeProperty",
"owl:deprecated",
"owl:DeprecatedClass",
"owl:DeprecatedProperty",
"owl:differentFrom",
"owl:disjointUnionOf",
"owl:disjointWith",
"owl:distinctMembers",
"owl:equivalentClass",
"owl:equivalentProperty",
"owl:FunctionalProperty",
"owl:hasKey",
"owl:hasSelf",
"owl:hasValue",
"owl:imports",
"owl:incompatibleWith",
"owl:intersectionOf",
"owl:InverseFunctionalProperty",
"owl:inverseOf",
"owl:IrreflexiveProperty",
"owl:maxCardinality",
"owl:maxQualifiedCardinality",
"owl:members",
"owl:minCardinality",
"owl:minQualifiedCardinality",
"owl:NamedIndividual",
"owl:NegativePropertyAssertion",
"owl:Nothing",
"owl:ObjectProperty",
"owl:onClass",
"owl:onDataRange",
"owl:onDatatype",
"owl:oneOf",
"owl:onProperty",
"owl:onProperties",
"owl:Ontology",
"owl:OntologyProperty",
"owl:priorVersion",
"owl:propertyChainAxiom",
"owl:propertyDisjointWith",
"owl:qualifiedCardinality",
"owl:ReflexiveProperty",
"owl:Restriction",
"owl:sameAs",
"owl:someValuesFrom",
"owl:sourceIndividual",
"owl:SymmetricProperty",
"owl:targetIndividual",
"owl:targetValue",
"owl:Thing",
"owl:topDataProperty",
"owl:topObjectProperty",
"owl:TransitiveProperty",
"owl:unionOf",
"owl:versionInfo",
"owl:versionIRI",
"owl:withRestrictions"
);

@vocabularyterms_dtype = (
"xsd:anyURI",
"xsd:base64Binary",
"xsd:boolean",
"xsd:byte",
"xsd:dateTime",
"xsd:dateTimeStamp",
"xsd:decimal",
"xsd:double",
"xsd:float",
"xsd:hexBinary",
"xsd:int",
"xsd:integer",
"xsd:language",
"xsd:long",
"xsd:Name",
"xsd:NCName",
"xsd:negativeInteger",
"xsd:NMTOKEN",
"xsd:nonNegativeInteger",
"xsd:nonPositiveInteger",
"xsd:normalizedString",
"rdf:PlainLiteral",
"xsd:positiveInteger",
"owl:rational",
"owl:real",
"xsd:short",
"xsd:string",
"xsd:token",
"xsd:unsignedByte",
"xsd:unsignedInt",
"xsd:unsignedLong",
"xsd:unsignedShort",
"rdf:XMLLiteral"
);

@vocabularyterms_facet = (
"rdf:langRange",
"xsd:length",
"xsd:maxExclusive",
"xsd:maxInclusive",
"xsd:maxLength",
"xsd:minExclusive",
"xsd:minInclusive",
"xsd:minLength",
"xsd:pattern"
);

return (
    @vocabularyterms_rdf,
    @vocabularyterms_rdfs,
    @vocabularyterms_owl,
    @vocabularyterms_dtype,
    @vocabularyterms_facet
    );
}