Github user lewismc commented on a diff in the pull request: https://github.com/apache/any23/pull/59#discussion_r163680939 --- Diff: core/src/main/java/org/apache/any23/extractor/rdf/BaseRDFExtractor.java --- @@ -105,7 +109,24 @@ public void run( parser.getParserConfig().addNonFatalError(BasicParserSettings.NORMALIZE_DATATYPE_VALUES); //ByteBuffer seems to represent incorrect content. Need to make sure it is the content //of the <script> node and not anything else! - parser.parse(in, extractionContext.getDocumentIRI().stringValue()); + RDFFormat format = parser.getRDFFormat(); + String iri = extractionContext.getDocumentIRI().stringValue(); + + if (format.hasFileExtension("xhtml")) { --- End diff -- ack, please ignore
---