ci(schedule-run): add tesseract and dataset

.github/workflows/schedule-run.yml

@@ -7,6 +7,9 @@ on:
   workflow_dispatch:
 # user-config end
 
+env:
+  TESSERACT_DATASET_URL: 'https://github.com/tesseract-ocr/tessdata/raw/refs/heads/main/eng.traineddata'
+
 jobs:
   run:
     name: Run
@@ -32,6 +35,23 @@ jobs:
 
       - uses: extractions/setup-just@v2
 
+      - name: Get required apt packages
+        id: get-pkgs
+        shell: bash
+        run: echo "pkgs=$( tr '\n' ' ' <'./apt_pkgs.txt' )" > "$GITHUB_OUTPUT"
+
+      - uses: awalsh128/cache-apt-pkgs-action@v1
+        with:
+          packages: ${{ steps.get-pkgs.outputs.pkgs }}
+          version: ${{ hashFiles('apt_pkgs.txt') }}
+          execute_install_scripts: true
+
+      - name: Download tesseract dataset
+        run: |
+          sudo mkdir -p /usr/share/tessdata
+          cd /usr/share/tessdata
+          curl -O ${{ env.TESSERACT_DATASET_URL }}
+
       - name: Install production deps
         run: uv sync --no-dev
 

apt_pkgs.txt

@@ -0,0 +1 @@
+tesseract-ocr

docs/usage/usage.md

@@ -3,7 +3,7 @@
 ## Yêu cầu
 
 - [Python](https://www.python.org/downloads/)
-- [Tesseact OCR CLI](https://tesseract-ocr.github.io/tessdoc/Installation.html) (Không bắt buộc)(1)
+- [Tesseact OCR CLI](https://tesseract-ocr.github.io/tessdoc/Installation.html) và [Tesseact data set](https://github.com/tesseract-ocr/tessdata) (Không bắt buộc)(1)
   { .annotate }
 
       1. Sử dụng để giải captcha đối với API csgt.vn