diff options
Diffstat (limited to 'app-text/pdfsandwich')
-rw-r--r-- | app-text/pdfsandwich/Manifest | 1 | ||||
-rw-r--r-- | app-text/pdfsandwich/metadata.xml | 25 | ||||
-rw-r--r-- | app-text/pdfsandwich/pdfsandwich-0.1.4.ebuild | 41 |
3 files changed, 67 insertions, 0 deletions
diff --git a/app-text/pdfsandwich/Manifest b/app-text/pdfsandwich/Manifest new file mode 100644 index 000000000000..67b94d72e7c0 --- /dev/null +++ b/app-text/pdfsandwich/Manifest @@ -0,0 +1 @@ +DIST pdfsandwich-0.1.4.tar.bz2 16401 SHA256 8b82f3ae08000c5cae1ff5a0f6537b0b563befef928e5198255b743a46714af3 SHA512 ee03aea13c72cc5a02136b5d16d2425f685f0b7a9d6fa6cff6c792bd24e6316720dff321b5e8237b949c98c713f39cb8b08b855b76e2a77350927b1ee7943171 WHIRLPOOL d8eb5fd281b1eb3f9e371ee71c486b8e839048f3ab569f8b62644e21ad921692283b2d35dfeb07111f86cf52eeb926da4152fcf58124cca2f96aa05116e8e115 diff --git a/app-text/pdfsandwich/metadata.xml b/app-text/pdfsandwich/metadata.xml new file mode 100644 index 000000000000..6bfdb50e39db --- /dev/null +++ b/app-text/pdfsandwich/metadata.xml @@ -0,0 +1,25 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!DOCTYPE pkgmetadata SYSTEM "http://www.gentoo.org/dtd/metadata.dtd"> +<pkgmetadata> + <maintainer> + <email>tomka@gentoo.org</email> + </maintainer> + <longdescription> +pdfsandwich generates "sandwich" OCR pdf files, i.e. pdf files which +contain only images (no text) will be processed by optical character +recognition (OCR) and the text will be added to each page invisibly +"behind" the images. + +pdfsandwich is a command line tool which is supposed to be useful to +OCR scanned books or journals. It is able to recognize the page layout +even for multicolumn text. + +Essentially, pdfsandwich is a wrapper script which calls the following +binaries: convert, cuneiform, gs, and hocr2pdf. It is known to run on +Unix systems and has been tested on Linux and MacOS X. It supports +parallel processing on multiprocessor systems. +</longdescription> + <upstream> + <remote-id type="sourceforge">pdfsandwich</remote-id> + </upstream> +</pkgmetadata> diff --git a/app-text/pdfsandwich/pdfsandwich-0.1.4.ebuild b/app-text/pdfsandwich/pdfsandwich-0.1.4.ebuild new file mode 100644 index 000000000000..23bf7abd4bea --- /dev/null +++ b/app-text/pdfsandwich/pdfsandwich-0.1.4.ebuild @@ -0,0 +1,41 @@ +# Copyright 1999-2015 Gentoo Foundation +# Distributed under the terms of the GNU General Public License v2 +# $Id$ + +EAPI=5 + +DESCRIPTION="generator of sandwich OCR pdf files" +HOMEPAGE="http://www.tobias-elze.de/pdfsandwich" +SRC_URI="mirror://sourceforge/pdfsandwich/${P}.tar.bz2" + +LICENSE="GPL-2" +KEYWORDS="~amd64 ~x86" +SLOT="0" +IUSE="png" + +RDEPEND=">=app-text/tesseract-3.00 + media-gfx/exact-image + app-text/unpaper + app-text/ghostscript-gpl + || ( + media-gfx/imagemagick[png?] + media-gfx/graphicsmagick[png?] + )" +DEPEND="sys-apps/gawk + >=dev-lang/ocaml-3.10[ocamlopt]" + +src_prepare() { + sed -i "/^OCAMLOPTFLAGS/s/$/ -ccopt \"\$(CFLAGS) \$(LDFLAGS)\"/" Makefile || die + sed -i "s/install -s/install/" Makefile || die +} + +src_install() { + emake DESTDIR="${D}" install +} + +pkg_postinst() { + elog "pdfsandwich relies on the tesseract library for OCR." + elog "Consequently language support is determined by tesseract's" + elog "language support which in turn is controlled via the LINGUAS" + elog "variable in make.conf." +} |