From 74622568934c79d4c2407b7f02b3d626685b6ad2 Mon Sep 17 00:00:00 2001
From: Mark Munro <73947246+Munza2020@users.noreply.github.com>
Date: Tue, 25 Aug 2026 10:23:25 +0100
Subject: [PATCH] fix(apache-tika): handle upstream's switch from jar to zip
 distribution (#16726)

* fix(apache-tika): handle upstream's switch from jar to zip distribution

Apache Tika 4.0.0 stopped publishing tika-server-standard as a standalone
executable jar and now ships it as a zip: the jar inside is a thin launcher
whose manifest Class-Path resolves ~150 dependencies from a sibling lib/
(and plugins/) directory, so downloading just the jar 404s and, even if it
didn't, would no longer be runnable on its own.

Both install and update now use fetch_and_deploy_from_url (already used by
several other scripts in this repo, e.g. ct/technitiumdns.sh) to fetch and
extract the whole archive in place, instead of hand-rolling curl+unzip.
update_script() also passes CLEAN_INSTALL=1 so a later update replaces the
lib/ tree wholesale rather than layering a new version's jars on top of an
old one's.

Verified by running the real ct/apache-tika.sh (via build.func/tools.func
pulled live from this repo's main) against a live LXC container previously
on 3.3.2: it downloads and extracts the 4.0.0 zip, starts the service, and
`java -jar tika-server-standard.jar` answers on port 9998 with
"Apache Tika 4.0.0".

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

* Clean up comments in apache-tika.sh

Removed outdated comments regarding tika-server-standard installation method.

* Update Apache Tika installation script

Removed comments regarding the change in Apache Tika packaging and updated the installation process.

---------

Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
Co-authored-by: CanbiZ (MickLesk) <47820557+MickLesk@users.noreply.github.com>
---
 ct/apache-tika.sh              | 7 ++-----
 install/apache-tika-install.sh | 6 ++----
 2 files changed, 4 insertions(+), 9 deletions(-)

diff --git a/ct/apache-tika.sh b/ct/apache-tika.sh
index 4d731da8e..9b6daf3c2 100755
--- a/ct/apache-tika.sh
+++ b/ct/apache-tika.sh
@@ -35,11 +35,8 @@ function update_script() {
     msg_ok "Stopped Service"
 
     msg_info "Updating ${APP} to v${RELEASE}"
-    cd /opt/apache-tika
-    curl -fsSL -o tika-server-standard-${RELEASE}.jar "https://dlcdn.apache.org/tika/${RELEASE}/tika-server-standard-${RELEASE}.jar"
-    mv --force tika-server-standard.jar tika-server-standard-prev-version.jar
-    mv tika-server-standard-${RELEASE}.jar tika-server-standard.jar
-    rm -rf /opt/apache-tika/tika-server-standard-prev-version.jar
+    CLEAN_INSTALL=1 fetch_and_deploy_from_url "https://dlcdn.apache.org/tika/${RELEASE}/tika-server-standard-${RELEASE}.zip" /opt/apache-tika
+    mv "/opt/apache-tika/tika-server-standard-${RELEASE}.jar" /opt/apache-tika/tika-server-standard.jar
     echo "${RELEASE}" >/opt/${APP}_version.txt
     msg_ok "Updated ${APP} to v${RELEASE}"
 
diff --git a/install/apache-tika-install.sh b/install/apache-tika-install.sh
index 5c277e2bf..9577eb6a9 100644
--- a/install/apache-tika-install.sh
+++ b/install/apache-tika-install.sh
@@ -35,11 +35,9 @@ msg_ok "Installed Dependencies"
 JAVA_VERSION="21" setup_java
 
 msg_info "Installing Apache Tika"
-mkdir -p /opt/apache-tika
-cd /opt/apache-tika
 RELEASE="$(curl -fsSL https://dlcdn.apache.org/tika/ | grep -oP '(?<=href=")[0-9]+\.[0-9]+\.[0-9]+(?=/")' | sort -V | tail -n1)"
-curl -fsSL "https://dlcdn.apache.org/tika/${RELEASE}/tika-server-standard-${RELEASE}.jar" -o tika-server-standard-${RELEASE}.jar
-mv tika-server-standard-${RELEASE}.jar tika-server-standard.jar
+fetch_and_deploy_from_url "https://dlcdn.apache.org/tika/${RELEASE}/tika-server-standard-${RELEASE}.zip" /opt/apache-tika
+mv "/opt/apache-tika/tika-server-standard-${RELEASE}.jar" /opt/apache-tika/tika-server-standard.jar
 echo "${RELEASE}" >/opt/${APPLICATION}_version.txt
 msg_ok "Installed Apache Tika"