From 846ebe6dda3b5b907231f214ce96e74d300e6dd2 Mon Sep 17 00:00:00 2001 From: Peter Dave Hello Date: Thu, 4 Jan 2024 20:30:55 +0800 Subject: [PATCH] Refine Tesseract-OCR file backup process in DockerfileBase --- DockerfileBase | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/DockerfileBase b/DockerfileBase index 4e41d3e8..ffc8a89e 100644 --- a/DockerfileBase +++ b/DockerfileBase @@ -33,6 +33,7 @@ apt-get update && \ ocrmypdf \ unpaper && \ rm -rf /var/lib/apt/lists/* && \ + mv /usr/share/tesseract-ocr /usr/share/tesseract-ocr-original && \ pip install --upgrade pip && \ pip install --no-cache-dir --upgrade ocrmypdf && \ pip install --no-cache-dir --upgrade pillow==10.0.1 reportlab==3.6.13 wheel==0.38.1 setuptools==65.5.1 pyjwt==2.4.0 cryptography==39.0.1 @@ -40,13 +41,3 @@ apt-get update && \ #CV and HTML RUN pip install --no-cache-dir opencv-python-headless WeasyPrint - - -# cleanup and etc -RUN mkdir /usr/share/tesseract-ocr-original && \ - cp -r /usr/share/tesseract-ocr/* /usr/share/tesseract-ocr-original && \ - rm -rf /usr/share/tesseract-ocr - - - - \ No newline at end of file