You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@tika.apache.org by GitBox <gi...@apache.org> on 2021/01/01 16:39:14 UTC

[GitHub] [tika-docker] mhf-ir commented on a change in pull request #2: set tesseract ocr langauges as docker build args

mhf-ir commented on a change in pull request #2:
URL: https://github.com/apache/tika-docker/pull/2#discussion_r550784351



##########
File path: docker-tool.sh
##########
@@ -58,13 +60,18 @@ test_docker_image() {
 shift $((OPTIND -1))
 subcommand=$1; shift
 version=$1; shift
+tesseract_languages=$1; shift
 
 case "$subcommand" in
   build)
+    build_args="--build-arg TIKA_VERSION=${version}"
+    if [[ ! -z "$tesseract_languages" ]]; then
+      build_args="$build_args --build-arg TESSERACT_LANGUAGES='${tesseract_languages}'"
+    fi
     # Build slim version with minimal dependencies
     docker build -t apache/tika:${version} --build-arg TIKA_VERSION=${version} - < minimal/Dockerfile --no-cache
     # Build full version with OCR, Fonts and GDAL
-    docker build -t apache/tika:${version}-full --build-arg TIKA_VERSION=${version} - < full/Dockerfile --no-cache
+    docker build -t apache/tika:${version}-full ${build_args} - < full/Dockerfile --no-cache

Review comment:
       How about to run:
   ```bash
   ./docker-tool.sh build 1.25 'tesseract-ocr-eng tesseract-ocr-ita`
   ```

##########
File path: docker-tool.sh
##########
@@ -58,13 +60,18 @@ test_docker_image() {
 shift $((OPTIND -1))
 subcommand=$1; shift
 version=$1; shift
+tesseract_languages=$1; shift
 
 case "$subcommand" in
   build)
+    build_args="--build-arg TIKA_VERSION=${version}"
+    if [[ ! -z "$tesseract_languages" ]]; then
+      build_args="$build_args --build-arg TESSERACT_LANGUAGES='${tesseract_languages}'"
+    fi
     # Build slim version with minimal dependencies
     docker build -t apache/tika:${version} --build-arg TIKA_VERSION=${version} - < minimal/Dockerfile --no-cache
     # Build full version with OCR, Fonts and GDAL
-    docker build -t apache/tika:${version}-full --build-arg TIKA_VERSION=${version} - < full/Dockerfile --no-cache
+    docker build -t apache/tika:${version}-full ${build_args} - < full/Dockerfile --no-cache

Review comment:
       How about to run:
   ```bash
   ./docker-tool.sh build 1.25 'tesseract-ocr-eng tesseract-ocr-ita'
   ```




----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

For queries about this service, please contact Infrastructure at:
users@infra.apache.org