Remove support for Visio and potm files

* Parse a non supported document using `mapper-attachments`
* If Tika is not able to parse the document because of a missing class (we are not importing all jars needed by Tika), Tika throws a Throwable which is not catch.

This commit removes support for Visio and POTM office files.

The good news is that it does not kill the node anymore and allows to extract the text which is in the Office document even if we have a Visio content (which is not extracted anymore).

Related to #22077 and #22079 for mapper-attachments plugin

Backport of #23214 in 5.2 branch

Author: dadoonet

plugins/mapper-attachments/build.gradle

@@ -74,9 +74,11 @@ dependencyLicenses {
 }
 
 forbiddenPatterns {
+  exclude '**/*.doc'
   exclude '**/*.docx'
   exclude '**/*.pdf'
   exclude '**/*.epub'
+  exclude '**/*.vsdx'
 }
 
 thirdPartyAudit.excludes = [

plugins/mapper-attachments/src/main/java/org/elasticsearch/mapper/attachments/TikaImpl.java

@@ -22,8 +22,10 @@
 import org.apache.tika.Tika;
 import org.apache.tika.exception.TikaException;
 import org.apache.tika.metadata.Metadata;
+import org.apache.tika.mime.MediaType;
 import org.apache.tika.parser.AutoDetectParser;
 import org.apache.tika.parser.Parser;
+import org.apache.tika.parser.ParserDecorator;
 import org.elasticsearch.SpecialPermission;
 import org.elasticsearch.bootstrap.JarHell;
 import org.elasticsearch.common.SuppressForbidden;
@@ -45,7 +47,9 @@
 import java.security.PrivilegedExceptionAction;
 import java.security.ProtectionDomain;
 import java.security.SecurityPermission;
+import java.util.Collections;
 import java.util.PropertyPermission;
+import java.util.Set;
 
 /**
  * Runs tika with limited parsers and limited permissions.
@@ -54,6 +58,9 @@
  */
 final class TikaImpl {
 
+    /** Exclude some formats */
+    private static final Set<MediaType> EXCLUDES = Collections.singleton(MediaType.application("x-tika-ooxml"));
+
     /** subset of parsers for types we support */
     private static final Parser PARSERS[] = new Parser[] {
         // documents
@@ -63,7 +70,7 @@ final class TikaImpl {
         new org.apache.tika.parser.txt.TXTParser(),
         new org.apache.tika.parser.microsoft.OfficeParser(),
         new org.apache.tika.parser.microsoft.OldExcelParser(),
-        new org.apache.tika.parser.microsoft.ooxml.OOXMLParser(),
+        ParserDecorator.withoutTypes(new org.apache.tika.parser.microsoft.ooxml.OOXMLParser(), EXCLUDES),
         new org.apache.tika.parser.odf.OpenDocumentParser(),
         new org.apache.tika.parser.iwork.IWorkPackageParser(),
         new org.apache.tika.parser.xml.DcXMLParser(),

plugins/mapper-attachments/src/test/java/org/elasticsearch/mapper/attachments/VariousDocTests.java

@@ -44,7 +44,9 @@
 import static org.elasticsearch.mapper.attachments.AttachmentMapper.FieldNames.TITLE;
 import static org.elasticsearch.test.StreamsUtils.copyToBytesFromClasspath;
 import static org.elasticsearch.test.StreamsUtils.copyToStringFromClasspath;
+import static org.hamcrest.Matchers.is;
 import static org.hamcrest.Matchers.isEmptyOrNullString;
+import static org.hamcrest.Matchers.isEmptyString;
 import static org.hamcrest.Matchers.not;
 
 /**
@@ -121,6 +123,40 @@ public void testAsciidocDocument() throws Exception {
         testMapper("asciidoc.asciidoc", false);
     }
 
+    public void testWordDocumentWithVisioSchema() throws Exception {
+        assertParseable("issue-22077.docx");
+        testMapper("issue-22077.docx", false);
+    }
+
+    public void testLegacyWordDocumentWithVisioSchema() throws Exception {
+        assertParseable("issue-22077.doc");
+        testMapper("issue-22077.doc", false);
+    }
+
+    public void testVisioIsExcluded() throws Exception {
+        String filename = "issue-22077.vsdx";
+        try (InputStream is = VariousDocTests.class.getResourceAsStream("/org/elasticsearch/index/mapper/attachment/test/sample-files/" +
+            filename)) {
+            byte bytes[] = IOUtils.toByteArray(is);
+            String parsedContent = TikaImpl.parse(bytes, new Metadata(), -1);
+            assertThat(parsedContent, isEmptyString());
+        }
+
+        byte[] html = copyToBytesFromClasspath("/org/elasticsearch/index/mapper/attachment/test/sample-files/" + filename);
+        BytesReference json = jsonBuilder()
+                .startObject()
+                    .startObject("file")
+                        .field("_name", filename)
+                        .field("_content", html)
+                    .endObject()
+                .endObject().bytes();
+
+        ParseContext.Document doc =  docMapper.parse("person", "person", "1", json).rootDoc();
+        assertThat(doc.get(docMapper.mappers().getMapper("file.content").fieldType().name()), isEmptyString());
+        assertThat(doc.get(docMapper.mappers().getMapper("file.content_type").fieldType().name()), is("application/vnd.ms-visio.drawing"));
+        assertThat(doc.get(docMapper.mappers().getMapper("file.content_length").fieldType().name()), is("210451"));
+    }
+
     void assertException(String filename, String expectedMessage) throws Exception {
         try (InputStream is = VariousDocTests.class.getResourceAsStream("/org/elasticsearch/index/mapper/attachment/test/sample-files/" + filename)) {
             byte bytes[] = IOUtils.toByteArray(is);