fix(knowledge): tolerate non-archive detection failures

backend/ruoyi-modules/ruoyi-aihr/src/main/java/org/dromara/aihr/knowledge/parse/TikaKnowledgeDocumentParser.java

@@ -1,6 +1,7 @@
 package org.dromara.aihr.knowledge.parse;
 
 import org.apache.tika.exception.WriteLimitReachedException;
+import org.apache.tika.detect.Detector;
 import org.apache.tika.extractor.EmbeddedDocumentExtractor;
 import org.apache.tika.io.BoundedInputStream;
 import org.apache.tika.io.TemporaryResources;
@@ -8,6 +9,7 @@ import org.apache.tika.io.TikaInputStream;
 import org.apache.tika.metadata.Metadata;
 import org.apache.tika.metadata.TikaCoreProperties;
 import org.apache.tika.mime.MediaType;
+import org.apache.tika.mime.MimeTypes;
 import org.apache.tika.parser.AutoDetectParser;
 import org.apache.tika.parser.ParseContext;
 import org.apache.tika.parser.Parser;
@@ -60,6 +62,8 @@ public class TikaKnowledgeDocumentParser implements KnowledgeDocumentParser {
             metadata.set(TikaCoreProperties.RESOURCE_NAME_KEY, fileName.trim());
         }
         AutoDetectParser parser = new AutoDetectParser();
+        Detector detector = parser.getDetector();
+        parser.setDetector((stream, currentMetadata) -> safeDetect(detector, stream, currentMetadata));
         BodyContentHandler handler = new BodyContentHandler(maxExpandedChars + 1);
         BoundedInputStream bounded = new BoundedInputStream(MAX_INPUT_BYTES + 1, input);
         try (TemporaryResources temporaryResources = new TemporaryResources();
@@ -91,6 +95,21 @@ public class TikaKnowledgeDocumentParser implements KnowledgeDocumentParser {
         }
     }
 
+    private static MediaType safeDetect(Detector detector, InputStream input, Metadata metadata) throws IOException {
+        input.mark(Integer.MAX_VALUE);
+        try {
+            return detector.detect(input, metadata);
+        } catch (Exception exception) {
+            if (!(exception instanceof org.apache.commons.compress.archivers.ArchiveException)) {
+                if (exception instanceof IOException ioException) throw ioException;
+                if (exception instanceof RuntimeException runtimeException) throw runtimeException;
+                throw new IOException("document type detection failed", exception);
+            }
+            input.reset();
+            return MimeTypes.getDefaultMimeTypes().detect(input, metadata);
+        }
+    }
+
     private ParsedDocument parsedDocument(BodyContentHandler handler, Metadata metadata, String mimeType) {
         String text = handler.toString().trim();
         if (text.isEmpty()) {