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 ;;;
   5 ;;; This file is part of GNU Guix.
   6 ;;;
   7 ;;; GNU Guix is free software; you can redistribute it and/or modify it
   8 ;;; under the terms of the GNU General Public License as published by
   9 ;;; the Free Software Foundation; either version 3 of the License, or (at
  10 ;;; your option) any later version.
  11 ;;;
  12 ;;; GNU Guix is distributed in the hope that it will be useful, but
  13 ;;; WITHOUT ANY WARRANTY; without even the implied warranty of
  14 ;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  15 ;;; GNU General Public License for more details.
  16 ;;;
  17 ;;; You should have received a copy of the GNU General Public License
  18 ;;; along with GNU Guix.  If not, see <http://www.gnu.org/licenses/>.
  19
  20 (define-module (gnu packages ocr)
  21   #:use-module ((guix licenses) #:prefix license:)
  22   #:use-module (guix packages)
  23   #:use-module (guix download)
  24   #:use-module (guix build-system gnu)
  25   #:use-module (gnu packages compression)
  26   #:use-module (gnu packages image))
  27
  28 (define-public ocrad
  29   (package
  30     (name "ocrad")
  31     (version "0.26")
  32     (source (origin
  33              (method url-fetch)
  34              (uri (string-append "mirror://gnu/ocrad/ocrad-"
  35                                  version ".tar.lz"))
  36              (sha256
  37               (base32
  38                "0g4fq7maybdnd1471kd05a3f5sb7spa3d26k706rk85sd5wd70y3"))))
  39     (build-system gnu-build-system)
  40     (native-inputs `(("lzip" ,lzip)))
  41     (home-page "https://www.gnu.org/software/ocrad/")
  42     (synopsis "Optical character recognition based on feature extraction")
  43     (description
  44      "GNU Ocrad is an optical character recognition program based on a
  45 feature extraction method.  It can read images in PBM, PGM or PPM formats and
  46 it produces text in 8-bit or UTF-8 formats.")
  47     (license license:gpl3+)))
  48
  49 (define-public tesseract-ocr
  50   (package
  51     (name "tesseract-ocr")
  52     (version "3.04.01")
  53     (source
  54      (origin
  55        (method url-fetch)
  56        (uri (string-append
  57              "https://github.com/tesseract-ocr/tesseract/archive/"
  58              version ".tar.gz"))
  59        (file-name (string-append name "-" version ".tar.gz"))
  60        (sha256
  61         (base32 "0snwd8as5i8vx7zkimpd2yg898jl96zf90r65a9w615f2hdkxxjp"))))
  62     (build-system gnu-build-system)
  63     (inputs
  64      `(("leptonica" ,leptonica)))
  65     (arguments
  66      '(#:configure-flags
  67        (let ((leptonica (assoc-ref %build-inputs "leptonica")))
  68          (list (string-append "LIBLEPT_HEADERSDIR=" leptonica "/include")))))
  69     (home-page "https://github.com/tesseract-ocr")
  70     (synopsis "Optical character recognition engine")
  71     (description
  72      "Tesseract is an optical character recognition (OCR) engine with very
  73 high accuracy.  It supports many languages, output text formatting, hOCR
  74 positional information and page layout analysis.  Several image formats are
  75 supported through the Leptonica library.  It can also detect whether text is
  76 monospaced or proportional.")
  77     (license license:asl2.0)))