(tika) branch main updated: TIKA-4510: Fix nondeterministic failures in LanguageResourceTest (#2360)

[tilman]

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

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


The following commit(s) were added to refs/heads/main by this push:
     new b385819af TIKA-4510: Fix nondeterministic failures in 
LanguageResourceTest (#2360)
b385819af is described below

commit b385819af53e5bc6c580b56876d9d62a098bdb4f
Author: Luca Dai <fff1996...@gmail.com>
AuthorDate: Thu Oct 9 02:47:53 2025 -0500

    TIKA-4510: Fix nondeterministic failures in LanguageResourceTest (#2360)
    
    Co-authored-by: LucaD <lucadai....@gmail.com>
---
 .../server/core/resource/LanguageResource.java     | 37 ++++++++++++++++------
 1 file changed, 27 insertions(+), 10 deletions(-)

diff --git 
a/tika-server/tika-server-core/src/main/java/org/apache/tika/server/core/resource/LanguageResource.java
 
b/tika-server/tika-server-core/src/main/java/org/apache/tika/server/core/resource/LanguageResource.java
index 8e2a2b1df..495b91335 100644
--- 
a/tika-server/tika-server-core/src/main/java/org/apache/tika/server/core/resource/LanguageResource.java
+++ 
b/tika-server/tika-server-core/src/main/java/org/apache/tika/server/core/resource/LanguageResource.java
@@ -38,27 +38,45 @@ import org.apache.tika.language.detect.LanguageResult;
 public class LanguageResource {
     private static final Logger LOG = 
LoggerFactory.getLogger(LanguageResource.class);
 
+    // TIKA-4510: handle @PUT and @POST separately to avoid nondeterministic 
failures
     @PUT
+    @Path("/stream")
+    @Consumes("*/*")
+    @Produces("text/plain")
+    public String detectPutStream(final InputStream is) throws IOException {
+        return detectStream(is);
+    }
+
     @POST
     @Path("/stream")
     @Consumes("*/*")
     @Produces("text/plain")
-    public String detect(final InputStream is) throws IOException {
-        String fileTxt = IOUtils.toString(is, UTF_8);
-        LanguageResult language = new OptimaizeLangDetector()
-                .loadModels()
-                .detect(fileTxt);
-        String detectedLang = language.getLanguage();
-        LOG.info("Detecting language for incoming resource: [{}]", 
detectedLang);
-        return detectedLang;
+    public String detectPostStream(final InputStream is) throws IOException {
+        return detectStream(is);
     }
 
     @PUT
+    @Path("/string")
+    @Consumes("*/*")
+    @Produces("text/plain")
+    public String detectPutString(final String string) throws IOException {
+        return detectString(string);
+    }
+
     @POST
     @Path("/string")
     @Consumes("*/*")
     @Produces("text/plain")
-    public String detect(final String string) throws IOException {
+    public String detectPostString(final String string) throws IOException {
+        return detectString(string);
+    }
+
+    private String detectStream(InputStream is) throws IOException {
+        String fileTxt = IOUtils.toString(is, UTF_8);
+        return detectString(fileTxt);
+    }
+
+    private String detectString(String string) throws IOException {
         LanguageResult language = new OptimaizeLangDetector()
                 .loadModels()
                 .detect(string);
@@ -66,5 +84,4 @@ public class LanguageResource {
         LOG.info("Detecting language for incoming resource: [{}]", 
detectedLang);
         return detectedLang;
     }
-
 }