You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tika.apache.org by ta...@apache.org on 2024/03/13 13:04:07 UTC

(tika) branch TIKA-4207 updated: TIKA-4207 -- trivial binary file name refinement

This is an automated email from the ASF dual-hosted git repository.

tallison pushed a commit to branch TIKA-4207
in repository https://gitbox.apache.org/repos/asf/tika.git


The following commit(s) were added to refs/heads/TIKA-4207 by this push:
     new e2b952c80 TIKA-4207 -- trivial binary file name refinement
e2b952c80 is described below

commit e2b952c80c699a82ec9d735dc299dd3d392c10f2
Author: tallison <ta...@apache.org>
AuthorDate: Wed Mar 13 09:03:48 2024 -0400

    TIKA-4207 -- trivial binary file name refinement
---
 .../apache/tika/extractor/AbstractEmbeddedDocumentByteStore.java    | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/tika-core/src/main/java/org/apache/tika/extractor/AbstractEmbeddedDocumentByteStore.java b/tika-core/src/main/java/org/apache/tika/extractor/AbstractEmbeddedDocumentByteStore.java
index cbc1f3411..214c2ab4e 100644
--- a/tika-core/src/main/java/org/apache/tika/extractor/AbstractEmbeddedDocumentByteStore.java
+++ b/tika-core/src/main/java/org/apache/tika/extractor/AbstractEmbeddedDocumentByteStore.java
@@ -19,6 +19,7 @@ package org.apache.tika.extractor;
 import java.io.IOException;
 import java.util.ArrayList;
 import java.util.List;
+import java.util.Locale;
 
 import org.apache.tika.io.FilenameUtils;
 import org.apache.tika.metadata.Metadata;
@@ -40,13 +41,16 @@ public abstract class AbstractEmbeddedDocumentByteStore implements EmbeddedDocum
 
 
         StringBuilder emitKey = new StringBuilder(containerEmitKey)
-                .append("/").append(containerEmitKey).append(embeddedDocumentBytesConfig.getEmbeddedIdPrefix())
+                .append("/")
+                .append(FilenameUtils.getName(containerEmitKey))
+                .append(embeddedDocumentBytesConfig.getEmbeddedIdPrefix())
                 .append(embeddedIdString);
 
         if (embeddedDocumentBytesConfig.getSuffixStrategy().equals(
                 EmbeddedDocumentBytesConfig.SUFFIX_STRATEGY.EXISTING)) {
             String fName = metadata.get(TikaCoreProperties.RESOURCE_NAME_KEY);
             String suffix = FilenameUtils.getSuffixFromPath(fName);
+            suffix = suffix.toLowerCase(Locale.US);
             emitKey.append(suffix);
         }
         return emitKey.toString();