commit: 6f71c48cc3558348a0d930f39cce77c99a487584 Author: Alfredo Tupone <tupone <AT> gentoo <DOT> org> AuthorDate: Fri May 6 10:25:28 2022 +0000 Commit: Alfredo Tupone <tupone <AT> gentoo <DOT> org> CommitDate: Fri May 6 10:25:28 2022 +0000 URL: https://gitweb.gentoo.org/repo/gentoo.git/commit/?id=6f71c48c
dev-python/pytesseract: add pytesseract Package-Manager: Portage-3.0.30, Repoman-3.0.3 Signed-off-by: Alfredo Tupone <tupone <AT> gentoo.org> dev-python/pytesseract/Manifest | 1 + dev-python/pytesseract/metadata.xml | 23 +++++++++++++++++++ dev-python/pytesseract/pytesseract-0.3.10.ebuild | 29 ++++++++++++++++++++++++ 3 files changed, 53 insertions(+) diff --git a/dev-python/pytesseract/Manifest b/dev-python/pytesseract/Manifest new file mode 100644 index 000000000000..cac470d1e9e7 --- /dev/null +++ b/dev-python/pytesseract/Manifest @@ -0,0 +1 @@ +DIST pytesseract-0.3.10.tar.gz 1098547 BLAKE2B d89f9082d8c7236b97bb96441809a19f494aacd23d4c02d5b7fb1b742616e7b26c249d49fceecc4f652792cdc3d7f2a79cd580a3360157f81205ff04d65afb10 SHA512 de77f0497c2bf60c1febf439ed13f0a8978aa23df76aadb789f8151177b73f45229799bd6b236aa7356a5145064f892e5b528a2d5a396849348f5b22f4343e16 diff --git a/dev-python/pytesseract/metadata.xml b/dev-python/pytesseract/metadata.xml new file mode 100644 index 000000000000..2f762d632807 --- /dev/null +++ b/dev-python/pytesseract/metadata.xml @@ -0,0 +1,23 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!DOCTYPE pkgmetadata SYSTEM "https://www.gentoo.org/dtd/metadata.dtd";> +<pkgmetadata> + <maintainer type="person"> + <email>tup...@gentoo.org</email> + <name>Tupone Alfredo</name> + </maintainer> + <longdescription lang="en"> + Python-tesseract is an optical character recognition (OCR) tool for + python. + That is, it will recognize and "read" the text embedded in images. + + Python-tesseract is a wrapper for Google's Tesseract-OCR Engine. + It is also useful as a stand-alone invocation script to tesseract, as + it can read all image types supported by the Pillow and Leptonica + imaging libraries, including jpeg, png, gif, bmp, tiff, and others. + Additionally, if used as a script, Python-tesseract will print the + recognized text instead of writing it to a file. + </longdescription> + <upstream> + <remote-id type="github">madmaze/pytesseract</remote-id> + </upstream> +</pkgmetadata> diff --git a/dev-python/pytesseract/pytesseract-0.3.10.ebuild b/dev-python/pytesseract/pytesseract-0.3.10.ebuild new file mode 100644 index 000000000000..02c5fb762226 --- /dev/null +++ b/dev-python/pytesseract/pytesseract-0.3.10.ebuild @@ -0,0 +1,29 @@ +# Copyright 2022 Gentoo Authors +# Distributed under the terms of the GNU General Public License v2 + +EAPI=8 + +PYTHON_COMPAT=( python3_{8,9,10} ) +inherit distutils-r1 + +DESCRIPTION="Optical character recognition (OCR) tool" +HOMEPAGE="https://github.com/madmaze/pytesseract"; +SRC_URI="https://github.com/madmaze/${PN}/archive/refs/tags/v${PV}.tar.gz + -> ${P}.tar.gz" + +LICENSE="Apache-2.0" +SLOT="0" +KEYWORDS="~amd64" + +DEPEND="" +RDEPEND="${DEPEND} + app-text/tesseract" +BDEPEND=" + test? ( + app-text/tesseract[jpeg,png,tiff,webp] + media-libs/leptonica[gif,jpeg2k] + app-text/tessdata_fast[l10n_fr] + ) +" + +distutils_enable_tests pytest
