From 5feb7f429b8ba9d90d40ae40d5b0b3e4910c2b1d Mon Sep 17 00:00:00 2001
From: Shana Moore <shana@scientist.com>
Date: Tue, 3 Oct 2023 10:54:27 -0700
Subject: [PATCH] :gift: install tesseract eng_best

---
 Dockerfile | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/Dockerfile b/Dockerfile
index d13b8e942..c9d3ecdd9 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -47,6 +47,11 @@ RUN wget https://github.com/ImageMagick/ImageMagick/archive/refs/tags/7.1.0-57.t
     && rm -rf ImageMagick* \
     && rm -rf /var/cache/apk/*
 
+# Install "best" training data for Tesseract
+RUN echo "📚 Installing Tesseract Best (training data)!" && \
+    cd /usr/share/tessdata/ && \
+    wget https://github.com/tesseract-ocr/tessdata_best/blob/main/eng.traineddata?raw=true -O eng_best.traineddata
+
 ARG VIPS_VERSION=8.11.3
 
 RUN set -x -o pipefail \