meta.yaml

{% set name = "tesseract" %}
{% set version = "5.4.1" %}

package:
  name: {{ name|lower }}
  version: {{ version }}

source:
  - url: https://github.com/tesseract-ocr/{{ name }}/archive/{{ version }}.tar.gz
    sha256: c4bc2a81c12a472f445b7c2fb4705a08bd643ef467f51ec84f0e148bd368051b
    folder: tesseract
  - url: https://github.com/tesseract-ocr/tessdata_fast/archive/4.1.0.tar.gz
    sha256: d0e3bb6f3b4e75748680524a1d116f2bfb145618f8ceed55b279d15098a530f9
    folder: tessdata_fast


build:
  number: 0
  skip: true  # [win and vc<14]
  run_exports:
    - {{ pin_subpackage(name, max_pin='x.x.x') }}

requirements:
  build:
    - {{ compiler('c') }}
    - {{ stdlib("c") }}
    - {{ compiler('cxx') }}
    - autoconf  # [not win]
    - automake  # [not win]
    - libtool  # [not win]
    - pkg-config  # [not win]
    - make  # [not win]
    - cmake  # [win]

  host:
    - giflib  # [not win]
    - libarchive
    - libjpeg-turbo
    - leptonica
    - libpng
    - libtiff
    - libwebp
    - openjpeg
    - xz  # [not win]
    - zlib

test:
  files:
    - eurotext.tif
  commands:
    - tesseract --help
    - tesseract --list-langs
    - tesseract eurotext.tif outputbase

about:
  home: https://github.com/tesseract-ocr/tesseract
  license: Apache-2.0
  license_family: Apache
  license_file: tesseract/LICENSE
  summary: An optical character recognition (OCR) engine

  description: |
    Tesseract is an OCR engine with support for unicode and the ability
    to recognize more than 100 languages out of the box. It can be
    trained to recognize other languages.
  doc_url: https://github.com/tesseract-ocr/tesseract
  dev_url: https://github.com/tesseract-ocr/tesseract

extra:
  recipe-maintainers:
    - mxr-conda
    - CurtLH
    - carlodri
    - oblute
    - izahn