Tika v1

setup/flavors/compose/docker-compose.yml

@@ -98,8 +98,16 @@ services:
     volumes:
       - "{{ root }}/mail:/mail"
       - "{{ root }}/overrides/dovecot:/overrides:ro"
+    networks:
+      - default
+    {% if tika_enabled %}
+      - fts_attachments
+    {% endif %}
     depends_on:
       - front
+    {% if tika_enabled %}
+      - fts_attachments
+    {% endif %}
     {% if resolver_enabled %}
       - resolver
     dns:
@@ -140,6 +148,21 @@ services:
     {% endif %}
 {% endif %}
 
+{% if tika_enabled %}
+  fts_attachments:
+    image: apache/tika:2.9.0.0-full
+    hostname: tika
+    restart: always
+    networks:
+      - fts_attachments
+    depends_on:
+    {% if resolver_enabled %}
+      - resolver
+    dns:
+      - {{ dns }}
+    {% endif %}
+{% endif %}
+
   antispam:
     image: ${DOCKER_ORG:-ghcr.io/mailu}/${DOCKER_PREFIX:-}rspamd:${MAILU_VERSION:-{{ version }}}
     hostname: antispam
@@ -257,3 +280,8 @@ networks:
     driver: bridge
     internal: true
 {% endif %}
+{% if tika_enabled %}
+  fts_attachments:
+    driver: bridge
+    internal: true
+{% endif %}

setup/flavors/compose/mailu.env

@@ -113,7 +113,7 @@ COMPRESSION_LEVEL={{ compression_level }}
 # IMAP full-text search is enabled by default.
 # Set the following variable to off in order to disable the feature
 # or a comma separated list of language codes to support
-# FULL_TEXT_SEARCH=off
+FULL_TEXT_SEARCH=en
 
 ###################################
 # Web settings
@@ -188,3 +188,5 @@ DEFAULT_SPAM_THRESHOLD=80
 # This is a mandatory setting for using the RESTful API.
 API_TOKEN={{ api_token }}
 
+# Whether tika should be enabled (scan/OCR email attachements)
+FULL_TEXT_SEARCH_ATTACHMENTS={{ tika_enabled }}

setup/templates/steps/compose/02_services.html

@@ -64,6 +64,15 @@ the security implications caused by such an increase of attack surface.<p>
   <i>Oletools scans documents in email attachements for malicious macros. It has a much lower memory footprint than a full-fledged anti-virus.</i>
 </div>
 
+<div class="form-check form-check-inline">
+  <label class="form-check-label">
+    <input class="form-check-input" type="checkbox" name="tika_enabled" value="true">
+    Enable Tika
+  </label>
+
+  <i>Tika scans documents in email attachments, process (OCR, keyword extraction) and then index them in a way they can be efficiently searched. This requires significant ressources (RAM, CPU and storage).</i>
+</div>
+
 <script src="https://ajax.googleapis.com/ajax/libs/jquery/3.6.0/jquery.min.js"></script>
 
 <script type="text/javascript" src="{{ url_for('static', filename='render.js') }}"></script>