(tika) branch branch_2x updated: TIKA-4239 -- band aid clear the cache for jenkins

[tallison]

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

tallison pushed a commit to branch branch_2x
in repository https://gitbox.apache.org/repos/asf/tika.git


The following commit(s) were added to refs/heads/branch_2x by this push:
     new ae3a088a6 TIKA-4239 -- band aid clear the cache for jenkins
ae3a088a6 is described below

commit ae3a088a6b4b162f26069c84059ecacbd986deaa
Author: tallison <talli...@apache.org>
AuthorDate: Mon Dec 2 10:13:48 2024 -0500

    TIKA-4239 -- band aid clear the cache for jenkins
---
 .../main/java/org/apache/tika/dl/imagerec/DL4JVGG16Net.java | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git 
a/tika-parsers/tika-parsers-ml/tika-dl/src/main/java/org/apache/tika/dl/imagerec/DL4JVGG16Net.java
 
b/tika-parsers/tika-parsers-ml/tika-dl/src/main/java/org/apache/tika/dl/imagerec/DL4JVGG16Net.java
index 327dbb17e..482b3d929 100644
--- 
a/tika-parsers/tika-parsers-ml/tika-dl/src/main/java/org/apache/tika/dl/imagerec/DL4JVGG16Net.java
+++ 
b/tika-parsers/tika-parsers-ml/tika-dl/src/main/java/org/apache/tika/dl/imagerec/DL4JVGG16Net.java
@@ -18,6 +18,7 @@
 package org.apache.tika.dl.imagerec;
 
 import java.io.File;
+import java.io.FileInputStream;
 import java.io.IOException;
 import java.io.InputStream;
 import java.util.ArrayList;
@@ -26,6 +27,7 @@ import java.util.List;
 import java.util.Map;
 import java.util.Set;
 
+import org.apache.commons.codec.digest.DigestUtils;
 import org.apache.commons.io.FileUtils;
 import org.datavec.image.loader.NativeImageLoader;
 import org.deeplearning4j.nn.graph.ComputationGraph;
@@ -98,8 +100,17 @@ public class DL4JVGG16Net implements ObjectRecogniser {
     public void initialize(Map<String, Param> params) throws 
TikaConfigException {
         try {
             if (serialize) {
+                //temporary workaround nullifies caching to attempt to fix 
jenkins builds
                 if (cacheDir.exists()) {
-                    FileUtils.deleteDirectory(cacheDir);
+                    if (cacheDir.isFile()) {
+                        try (InputStream is = new FileInputStream(cacheDir)) {
+                            String sha256 = DigestUtils.sha256Hex(is);
+                            LOG.info("sha256 of existing {} is {}", cacheDir, 
sha256);
+                        } catch (IOException e) {
+                            LOG.warn("io exception digesting " + cacheDir, e);
+                        }
+                    }
+                    FileUtils.deleteDirectory(cacheDir.getParentFile());
                 }
                 if (cacheDir.exists()) {
                     LOG.info("Trying to load preprocessed model from {}", 
cacheDir);