Claudenw commented on code in PR #240: URL: https://github.com/apache/creadur-rat/pull/240#discussion_r1579860679
########## apache-rat-core/src/main/java/org/apache/rat/api/Document.java: ########## @@ -33,47 +36,416 @@ public interface Document { */ enum Type { /** A generated document. */ - GENERATED, + GENERATED, /** An unknown document type. */ UNKNOWN, /** An archive type document. */ - ARCHIVE, + ARCHIVE, /** A notice document (e.g. LICENSE file) */ NOTICE, /** A binary file */ BINARY, /** A standard document */ - STANDARD} + STANDARD; + + public static Map<String, Type> documentTypeMap; + + public static Type fromContentType(String documentType, Log log) { + Type result = documentTypeMap.get(documentType); + if (result == null) { + log.warn(String.format("Please open a Jira ticket with the subject: 'Unknown media type %s in Document.Type'", documentType)); + return UNKNOWN; + } + return result; + } + + /* + * https://tika.apache.org/3.0.0-BETA/formats.html + */ + static { + documentTypeMap = new HashMap<>(); Review Comment: Shall we just open a JIRA ticket for this. I think that collecting some of the files will be difficult. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: dev-unsubscr...@creadur.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org