gnu/packages/ocr.scm

   1 ;;; GNU Guix --- Functional package management for GNU
   2 ;;; Copyright © 2013 Ludovic Courtès <ludo@gnu.org>
   3 ;;; Copyright © 2016 Efraim Flashner <efraim@flashner.co.il>
   4 ;;; Copyright © 2019 Tobias Geerinckx-Rice <me@tobias.gr>
   5 ;;;
   6 ;;; This file is part of GNU Guix.
   7 ;;;
   8 ;;; GNU Guix is free software; you can redistribute it and/or modify it
   9 ;;; under the terms of the GNU General Public License as published by
  10 ;;; the Free Software Foundation; either version 3 of the License, or (at
  11 ;;; your option) any later version.
  12 ;;;
  13 ;;; GNU Guix is distributed in the hope that it will be useful, but
  14 ;;; WITHOUT ANY WARRANTY; without even the implied warranty of
  15 ;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  16 ;;; GNU General Public License for more details.
  17 ;;;
  18 ;;; You should have received a copy of the GNU General Public License
  19 ;;; along with GNU Guix.  If not, see <http://www.gnu.org/licenses/>.
  20
  21 (define-module (gnu packages ocr)
  22   #:use-module ((guix licenses) #:prefix license:)
  23   #:use-module (guix packages)
  24   #:use-module (guix download)
  25   #:use-module (guix build-system gnu)
  26   #:use-module (gnu packages compression)
  27   #:use-module (gnu packages image))
  28
  29 (define-public ocrad
  30   (package
  31     (name "ocrad")
  32     (version "0.27")
  33     (source (origin
  34              (method url-fetch)
  35              (uri (string-append "mirror://gnu/ocrad/ocrad-"
  36                                  version ".tar.lz"))
  37              (sha256
  38               (base32
  39                "0divffvcaim89g4pvqs8kslbcxi475bcl3b4ynphf284k9zfdgx9"))))
  40     (build-system gnu-build-system)
  41     (native-inputs `(("lzip" ,lzip)))
  42     (home-page "https://www.gnu.org/software/ocrad/")
  43     (synopsis "Optical character recognition based on feature extraction")
  44     (description
  45      "GNU Ocrad is an optical character recognition program based on a
  46 feature extraction method.  It can read images in PBM, PGM or PPM formats and
  47 it produces text in 8-bit or UTF-8 formats.")
  48     (license license:gpl3+)))
  49
  50 (define-public tesseract-ocr
  51   (package
  52     (name "tesseract-ocr")
  53     (version "3.04.01")
  54     (source
  55      (origin
  56        (method url-fetch)
  57        (uri (string-append
  58              "https://github.com/tesseract-ocr/tesseract/archive/"
  59              version ".tar.gz"))
  60        (file-name (string-append name "-" version ".tar.gz"))
  61        (sha256
  62         (base32 "0snwd8as5i8vx7zkimpd2yg898jl96zf90r65a9w615f2hdkxxjp"))))
  63     (build-system gnu-build-system)
  64     (inputs
  65      `(("leptonica" ,leptonica)))
  66     (arguments
  67      '(#:configure-flags
  68        (let ((leptonica (assoc-ref %build-inputs "leptonica")))
  69          (list (string-append "LIBLEPT_HEADERSDIR=" leptonica "/include")))))
  70     (home-page "https://github.com/tesseract-ocr")
  71     (synopsis "Optical character recognition engine")
  72     (description
  73      "Tesseract is an optical character recognition (OCR) engine with very
  74 high accuracy.  It supports many languages, output text formatting, hOCR
  75 positional information and page layout analysis.  Several image formats are
  76 supported through the Leptonica library.  It can also detect whether text is
  77 monospaced or proportional.")
  78     (license license:asl2.0)))