fix venv

.github/workflows/predict.yml

@@ -29,8 +29,8 @@ jobs:
       - name: Run inference
         run: |
           docker run \
-            -v ./src:/ocr2pdf \
-            -v ./pdf:/ocr2pdf/pdf \
+            -v ./src:/app \
+            -v ./pdf:/app/pdf \
             ghcr.io/ipitio/ocr-pdf:latest \
             bash predict.sh pdf
 

README.md

@@ -52,7 +52,7 @@ If you want to skip building an image, just use mine:
 
 ```bash
 docker run --rm \
-    -v ./pdf:/ocr2pdf/pdf \
+    -v ./pdf:/app/pdf \
     ghcr.io/ipitio/ocr-pdf:latest \
     bash predict.sh pdf [OCRmyPDF options]
 ```
@@ -77,7 +77,7 @@ git push
 git pull
 ```
 
-To add OCRmyPDF options, edit the command the `predict.yml` file before committing.
+To add OCRmyPDF options, edit the command in the `predict.yml` file before committing.
 
 ### Self-hosted
 

colab.ipynb

@@ -59,7 +59,7 @@
     "# Transform them\n",
     "%pip install udocker\n",
     "!udocker --allow-root install\n",
-    "!udocker --allow-root run -v /content/pdf:/ocr2pdf/pdf ghcr.io/ipitio/ocr-pdf bash predict.sh pdf\n",
+    "!udocker --allow-root run -v /content/pdf:/app/pdf ghcr.io/ipitio/ocr-pdf bash predict.sh pdf\n",
     "converted = os.listdir(\"pdf/done\")\n",
     "\n",
     "# And load\n",

compose.yml

@@ -2,7 +2,7 @@ services:
     predict:
         container_name: ocr2pdf
         build: ./src
-        command: bash predict.sh pdf -l eng+fra
+        command: bash predict.sh pdf
         volumes:
-            - ./src:/ocr2pdf
-            - ./pdf:/ocr2pdf/pdf
+            - ./src:/app
+            - ./pdf:/app/pdf

src/Dockerfile

@@ -1,5 +1,5 @@
 FROM jbarlow83/ocrmypdf-ubuntu:v16.5.0
-WORKDIR /ocr2pdf
+WORKDIR /app
 COPY . .
 RUN bash predict.sh
 ENTRYPOINT []

src/predict.sh

@@ -3,16 +3,11 @@
 
 apt_install() {
     # shellcheck disable=SC2068
-    apt-get install -y python3 python3-pip python3-venv tesseract-ocr poppler-utils git ocrmypdf $@
-}
-
-main() {
-    find . -name requirements.txt -exec pip3 install --user --root-user-action ignore --break-system-packages --no-cache-dir -r {} \;
-    [ -z "$1" ] || find . -name main.py -exec python3 {} "${@:1}" \;
+    apt-get install -yqq python3 python3-pip python3-venv tesseract-ocr poppler-utils git ocrmypdf $@
 }
 
 langs=$(echo "$*" | grep -oP '(?<=-l )[^ ]+' | tr '+' '\n' | sed 's/^/tesseract-ocr-/' | sort -u | tr '\n' ' ')
-if ! apt_install "$langs" 2>/dev/null; then
+if ! apt_install "$langs"; then
     apt-get update
     apt_install "$langs"
 fi
@@ -22,9 +17,11 @@ export OMP_THREAD_LIMIT=1
 
 if [[ -e venv/bin/pip3 ]]; then
     source venv/bin/activate
-    main "${@}"
+    ./venv/bin/pip3 install --no-cache-dir -qr requirements.txt
+    [ -z "$1" ] || ./venv/bin/python3 main.py "${@:1}"
     deactivate
 elif [[ -f /.dockerenv ]]; then
     [[ ":$PATH:" == *":/root/.local/bin:"* ]] || export PATH=$PATH:/root/.local/bin
-    main "${@}"
+    /usr/bin/pip3 install --user --break-system-packages --no-cache-dir -qr requirements.txt
+    [ -z "$1" ] || /usr/bin/python3 main.py "${@:1}"
 fi