name: tesseract
version: git
summary: open source optical character recognition engine
description: |
  Tesseract has unicode (UTF-8) support, and can recognize more than 100
  languages "out of the box". It can be trained to recognize other languages.
  Tesseract supports various output formats: plain-text, hocr(html), pdf.

  If you want to access the files under /media/* or /run/media/* you'll have
  to connect the snap to the `core` snap's `removable-media` interface:

      $ sudo snap connect tesseract:removable-media

grade: stable # must be 'stable' to release into candidate/stable channels
confinement: strict
base: core22

apps:
  tesseract:
    command: usr/local/bin/tesseract
    environment:
      TESSDATA_PREFIX: $SNAP_USER_COMMON
    plugs:
      - home
      - removable-media

parts:
  tesseract:
    source: .
    plugin: autotools
    build-packages:
      - pkg-config
      - libpng-dev
      - libjpeg-dev
      - libtiff-dev
      - zlib1g-dev
      - libicu-dev
      - libpango1.0-dev
      - libcairo2-dev
    stage-packages:
      - libgomp1
    after: [leptonica]
  leptonica:
    source: https://github.com/DanBloomberg/leptonica/archive/1.83.1.tar.gz
    plugin: autotools
    stage-packages:
      - libjbig0
      - libjpeg-turbo8
      - libopenjp2-7
      - libtiff5