From 77bb974f9be421a3488e079ae75537b2db91c4cd Mon Sep 17 00:00:00 2001 From: Dominik Schmidt Date: Mon, 31 Aug 2026 17:14:33 +0200 Subject: [PATCH] test(search): run acceptance and CI against the released tika 4.0.0 Both tika pins (local compose and the CI service) point at apache/tika:4.0.0-full; the search README links tika version-less. --- .woodpecker.star | 5 ++++- services/search/README.md | 2 +- tests/acceptance/docker/src/tika.yml | 2 +- 3 files changed, 6 insertions(+), 3 deletions(-) diff --git a/.woodpecker.star b/.woodpecker.star index 978a1dfdfa..e5cd56303f 100644 --- a/.woodpecker.star +++ b/.woodpecker.star @@ -8,7 +8,7 @@ docker_repo_slug = "opencloudeu/opencloud" # images ALPINE_GIT = "alpine/git:latest" -APACHE_TIKA = "apache/tika:3.2.3.0-full" +APACHE_TIKA = "apache/tika:4.0.0-full" CHKO_DOCKER_PUSHRM = "chko/docker-pushrm:1" CODACY_COVERAGE_REPORTER = "codacy/codacy-coverage-reporter:14.1.3" COLLABORA_CODE = "collabora/code:24.04.5.1.1" @@ -3442,6 +3442,9 @@ def tikaService(): return [{ "name": "tika", "image": APACHE_TIKA, + # tika 4 discovers its plugins relative to the image working directory, + # the workspace default would leave the pipes fetchers empty + "directory": "/opt/tika-server", "detach": True, }, { "name": "wait-for-tika-service", diff --git a/services/search/README.md b/services/search/README.md index 026f4fc5ae..96bdc00c21 100644 --- a/services/search/README.md +++ b/services/search/README.md @@ -99,7 +99,7 @@ It does not do any further content analysis. The main difference is that this extractor is able to analyze and extract data from more advanced file types like PDF, DOCX, PPTX, etc. However, [Apache Tika](https://tika.apache.org/) is required for this task. -Read the [Getting Started with Apache Tika](https://tika.apache.org/2.6.0/gettingstarted.html) guide on how to install and run Tika or use a ready to run [Tika container](https://hub.docker.com/r/apache/tika). +Read the [Getting Started with Apache Tika](https://tika.apache.org/) guide on how to install and run Tika or use a ready to run [Tika container](https://hub.docker.com/r/apache/tika). See the [Tika container usage document](https://github.com/apache/tika-docker#usage) for a quickstart. As soon as Tika is installed and configured, the search service needs to be told to use it. diff --git a/tests/acceptance/docker/src/tika.yml b/tests/acceptance/docker/src/tika.yml index 4c9768a090..fe8eff86e8 100644 --- a/tests/acceptance/docker/src/tika.yml +++ b/tests/acceptance/docker/src/tika.yml @@ -5,4 +5,4 @@ services: - tika command: tika:9998 tika: - image: apache/tika:3.2.3.0-full + image: apache/tika:4.0.0-full