gnu/packages/ocr.scm

   1 ;;; GNU Guix --- Functional package management for GNU
   2 ;;; Copyright © 2013 Ludovic Courtès <ludo@gnu.org>
   3 ;;;
   4 ;;; This file is part of GNU Guix.
   5 ;;;
   6 ;;; GNU Guix is free software; you can redistribute it and/or modify it
   7 ;;; under the terms of the GNU General Public License as published by
   8 ;;; the Free Software Foundation; either version 3 of the License, or (at
   9 ;;; your option) any later version.
  10 ;;;
  11 ;;; GNU Guix is distributed in the hope that it will be useful, but
  12 ;;; WITHOUT ANY WARRANTY; without even the implied warranty of
  13 ;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  14 ;;; GNU General Public License for more details.
  15 ;;;
  16 ;;; You should have received a copy of the GNU General Public License
  17 ;;; along with GNU Guix.  If not, see <http://www.gnu.org/licenses/>.
  18
  19 (define-module (gnu packages ocr)
  20   #:use-module ((guix licenses) #:prefix license:)
  21   #:use-module (guix packages)
  22   #:use-module (guix download)
  23   #:use-module (guix build-system gnu)
  24   #:use-module (gnu packages autotools)
  25   #:use-module (gnu packages compression)
  26   #:use-module (gnu packages image)
  27   #:use-module (gnu packages pkg-config))
  28
  29 (define-public ocrad
  30   (package
  31     (name "ocrad")
  32     (version "0.25")
  33     (source (origin
  34              (method url-fetch)
  35              (uri (string-append "mirror://gnu/ocrad/ocrad-"
  36                                  version ".tar.lz"))
  37              (sha256
  38               (base32
  39                "1m2dblgvvjs48rsglfdwq0ib9zk8h9n34xsh67ibrg0g0ffbw477"))))
  40     (build-system gnu-build-system)
  41     (native-inputs `(("lzip" ,lzip)))
  42     (home-page "http://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 "3.02.02")
  54     (source
  55      (origin
  56        (method url-fetch)
  57        (uri (string-append
  58              "https://tesseract-ocr.googlecode.com/files/tesseract-ocr-"
  59              version ".tar.gz"))
  60        (sha256
  61         (base32 "0g81m9y4iydp7kgr56mlkvjdwpp3mb01q385yhdnyvra7z5kkk96"))
  62        (modules '((guix build utils)))
  63        ;; Leptonica added a pkg-config file in the meanwhile.
  64        (snippet
  65         '(substitute* "tesseract.pc.in"
  66            (("^# Requires: lept  ## .*")
  67             "Requires: lept\n")))))
  68     (build-system gnu-build-system)
  69     (native-inputs
  70      `(("autoconf" ,autoconf)
  71        ("automake" ,automake)
  72        ("libtool" ,libtool)))
  73     (propagated-inputs
  74      `(("leptonica" ,leptonica)))
  75     (arguments
  76      '(#:phases
  77        (modify-phases %standard-phases
  78          (add-after
  79           'unpack 'autogen
  80           (lambda _
  81             (zero? (system* "sh" "autogen.sh")))))
  82        #:configure-flags
  83        (let ((leptonica (assoc-ref %build-inputs "leptonica")))
  84          (list (string-append "LIBLEPT_HEADERSDIR=" leptonica "/include")))))
  85     (home-page "https://code.google.com/p/tesseract-ocr/")
  86     (synopsis "Optical character recognition engine")
  87     (description
  88      "Tesseract is an optical character recognition (OCR) engine with very
  89 high accuracy.  It supports many languages, output text formatting, hOCR
  90 positional information and page layout analysis.  Several image formats are
  91 supported through the Leptonica library.  It can also detect whether text is
  92 monospaced or proportional.")
  93     (license license:asl2.0)))