This is an automated email from the ASF dual-hosted git repository.
chibenwa pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/james-project.git
The following commit(s) were added to refs/heads/master by this push:
new cdf8eae01f [ENHANCEMENT] Tika: as answer can be large parse then on
parallel scheduler (#3171)
cdf8eae01f is described below
commit cdf8eae01f9dfdbdb424d9f088eb7802ebe88e4a
Author: Benoit TELLIER <[email protected]>
AuthorDate: Sat Sep 12 13:17:53 2026 +0200
[ENHANCEMENT] Tika: as answer can be large parse then on parallel scheduler
(#3171)
---
.../src/main/java/org/apache/james/mailbox/tika/TikaTextExtractor.java | 2 ++
1 file changed, 2 insertions(+)
diff --git
a/mailbox/tika/src/main/java/org/apache/james/mailbox/tika/TikaTextExtractor.java
b/mailbox/tika/src/main/java/org/apache/james/mailbox/tika/TikaTextExtractor.java
index 119d7555bb..43cc9d0ae5 100644
---
a/mailbox/tika/src/main/java/org/apache/james/mailbox/tika/TikaTextExtractor.java
+++
b/mailbox/tika/src/main/java/org/apache/james/mailbox/tika/TikaTextExtractor.java
@@ -53,6 +53,7 @@ import com.google.common.collect.ImmutableList;
import com.google.common.collect.ImmutableMap;
import reactor.core.publisher.Mono;
+import reactor.core.scheduler.Schedulers;
public class TikaTextExtractor implements TextExtractor {
private static final ContentType.MediaType TEXT =
ContentType.MediaType.of("text");
@@ -101,6 +102,7 @@ public class TikaTextExtractor implements TextExtractor {
private Mono<ContentAndMetadata> convert(Mono<InputStream>
maybeInputStream) {
return maybeInputStream
+ .publishOn(Schedulers.parallel())
.map(Throwing.function(inputStream ->
objectMapper.readValue(inputStream, ContentAndMetadata.class)))
.switchIfEmpty(Mono.just(ContentAndMetadata.empty()));
}
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]