From c06e765a5b1ce410e2d2bf508c4946f403a9983e Mon Sep 17 00:00:00 2001
From: Zhichang Yu <yuzhichang@gmail.com>
Date: Sun, 3 Nov 2024 00:20:26 +0800
Subject: [PATCH] Added tika jar into image to avoid downloading (#3167)

### What problem does this PR solve?

Added tika jar into image to avoid downloading. Close #3017

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
---
 .github/workflows/tests.yml | 2 +-
 Dockerfile                  | 5 +++++
 Dockerfile.slim             | 5 +++++
 download_deps.py            | 2 ++
 4 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/.github/workflows/tests.yml b/.github/workflows/tests.yml
index 71538deff..b155f8fe0 100644
--- a/.github/workflows/tests.yml
+++ b/.github/workflows/tests.yml
@@ -48,7 +48,7 @@ jobs:
       - name: Build ragflow:dev-slim
         run: |
           RUNNER_WORKSPACE_PREFIX=${RUNNER_WORKSPACE_PREFIX:-$HOME}
-          cp -r ${RUNNER_WORKSPACE_PREFIX}/huggingface.co ${RUNNER_WORKSPACE_PREFIX}/nltk_data ${RUNNER_WORKSPACE_PREFIX}/libssl*.deb .
+          cp -r ${RUNNER_WORKSPACE_PREFIX}/huggingface.co ${RUNNER_WORKSPACE_PREFIX}/nltk_data ${RUNNER_WORKSPACE_PREFIX}/libssl*.deb  ${RUNNER_WORKSPACE_PREFIX}/tika-server*.jar* .
           sudo docker pull ubuntu:24.04
           sudo docker build -f Dockerfile.slim -t infiniflow/ragflow:dev-slim .
 
diff --git a/Dockerfile b/Dockerfile
index 682336f58..b700cca34 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -104,6 +104,11 @@ RUN --mount=type=bind,source=huggingface.co,target=/huggingface.co \
 # Copy nltk data downloaded via download_deps.py
 COPY nltk_data /root/nltk_data
 
+# https://github.com/chrismattmann/tika-python
+# This is the only way to run python-tika without internet access. Without this set, the default is to check the tika version and pull latest every time from Apache.
+COPY tika-server-standard-3.0.0.jar tika-server-standard-3.0.0.jar.md5 ./
+ENV TIKA_SERVER_JAR="file:///ragflow/tika-server-standard.jar"
+
 # Copy compiled web pages
 COPY --from=builder /ragflow/web/dist /ragflow/web/dist
 
diff --git a/Dockerfile.slim b/Dockerfile.slim
index e2e35f326..f61c68b5f 100644
--- a/Dockerfile.slim
+++ b/Dockerfile.slim
@@ -97,6 +97,11 @@ RUN --mount=type=bind,source=huggingface.co,target=/huggingface.co \
 # Copy nltk data downloaded via download_deps.py
 COPY nltk_data /root/nltk_data
 
+# https://github.com/chrismattmann/tika-python
+# This is the only way to run python-tika without internet access. Without this set, the default is to check the tika version and pull latest every time from Apache.
+COPY tika-server-standard-3.0.0.jar tika-server-standard-3.0.0.jar.md5 ./
+ENV TIKA_SERVER_JAR="file:///ragflow/tika-server-standard.jar"
+
 # Copy compiled web pages
 COPY --from=builder /ragflow/web/dist /ragflow/web/dist
 
diff --git a/download_deps.py b/download_deps.py
index ab8fafb2f..58399293d 100644
--- a/download_deps.py
+++ b/download_deps.py
@@ -7,6 +7,8 @@ import urllib.request
 
 urls = [
     "http://archive.ubuntu.com/ubuntu/pool/main/o/openssl/libssl1.1_1.1.1f-1ubuntu2_amd64.deb",
+    "https://repo1.maven.org/maven2/org/apache/tika/tika-server-standard/3.0.0/tika-server-standard-3.0.0.jar",
+    "https://repo1.maven.org/maven2/org/apache/tika/tika-server-standard/3.0.0/tika-server-standard-3.0.0.jar.md5",
 ]
 
 repos = [