Remove non-free scraped web pages from SRPM

generate-tarball.sh

@@ -0,0 +1,21 @@
+#!/bin/bash
+set -e
+
+name=jsoup
+version="$(sed -n 's/Version:\s*//p' *.spec)"
+
+# RETRIEVE
+wget "https://github.com/jhy/${name}/archive/${name}-${version}.tar.gz" -O "${name}-${version}.orig.tar.gz"
+
+rm -rf tarball-tmp
+mkdir tarball-tmp
+cd tarball-tmp
+tar xf "../${name}-${version}.orig.tar.gz"
+
+# CLEAN TARBALL
+# contains scraped news articles (non-free)
+rm -r */src/test/resources
+
+tar cf "../${name}-${version}.tar.gz" *
+cd ..
+rm -r tarball-tmp "${name}-${version}.orig.tar.gz"

jsoup.spec

@@ -1,12 +1,15 @@
 Name:           jsoup
 Version:        1.11.3
-Release:        2%{?dist}
+Release:        3%{?dist}
 Summary:        Java library for working with real-world HTML
 License:        MIT
 URL:            http://jsoup.org/
 BuildArch:      noarch
 
-Source0:        https://github.com/jhy/%{name}/archive/%{name}-%{version}.tar.gz
+# ./generate-tarball.sh
+Source0:        %{name}-%{version}.tar.gz
+# The sources contain non-free scraped web pages as test data
+Source1:        generate-tarball.sh
 
 BuildRequires:  maven-local
 BuildRequires:  mvn(org.apache.felix:maven-bundle-plugin)
@@ -57,6 +60,9 @@ API documentation for %{name}.
 %license LICENSE
 
 %changelog
+* Wed Jul 18 2018 Michael Simacek <msimacek@redhat.com> - 1.11.3-3
+- Remove non-free scraped web pages from SRPM
+
 * Fri Jul 13 2018 Fedora Release Engineering <releng@fedoraproject.org> - 1.11.3-2
 - Rebuilt for https://fedoraproject.org/wiki/Fedora_29_Mass_Rebuild
 

sources

@@ -1 +1 @@
-SHA512 (jsoup-1.11.3.tar.gz) = aa17dae2fc5c1589c60aa7cdaed717b52b175727d9c9e35c7600de985a02855ba8d7770509bd4a97e0e8a72b7036d3d6609e08f37e7c71649d1ae9f46a1117b8
+SHA512 (jsoup-1.11.3.tar.gz) = d7a980a180a42708c4860f0df085f37831d94ce17e57be0333b6315b25cac3c94b1e965e97eae6e70786aee8263e843d746905b98919eba512c0a9bf67de41b9