dev-libs/snowball-stemmer: add 2.1.0

This version bump reworks the original ebuild, with following list of
changes:
- use EAPI 8
- append github to HOMEPAGE
- change DESCRIPTION to one used in github
- change license to BSD, this one is used in upstream
- use new shared library patch based on alpinelinux patch
- enable testing

Closes: https://bugs.gentoo.org/719402
Signed-off-by: Petr Vaněk <arkamar@atlas.cz>
Signed-off-by: Hans de Graaff <graaff@gentoo.org>

3 files changed, 114 insertions, 0 deletions

diff --git a/dev-libs/snowball-stemmer/Manifest b/dev-libs/snowball-stemmer/Manifest
index fbb928ad4990..c119bfe7fd7d 100644
--- a/dev-libs/snowball-stemmer/Manifest
+++ b/dev-libs/snowball-stemmer/Manifest
@@ -1 +1,3 @@
+DIST snowball-data-887fb7a3e006f32b4979e0d55f2543abe78a42f1.tar.gz 33063750 BLAKE2B bffc7e9f8fadbaecf9a7d1a2b8ee7a9db0b1dc1d5a6304a9c8d60b6c24a0947307b8780a99d2349b19e5fbcdfe819cc400ffb0b8b1df9748bb401ae1dec7b9aa SHA512 b68567d3e59aaa870251f682988b52a89d82767e954adea6b7f6247a6d432c29c8373c95a5e49df07110d4cb396aafa64ee6c71af2c0680d383ffe22491e50dd
 DIST libstemmer_c-20140325.tgz 129506 BLAKE2B 46040a864b8111bcca1c858a16081542a9900e435e6154582e422e1687b8230b0a5f63c7e349e1ef47128eaa898891df7b87fd2a4d97d0c1304fb8af7ebb627b SHA512 938eb12d4fe9e229f21536a6cb8a4322e0b664a7fbc15685e7ad46b4a6ccdfbefc55cc484f86bc738791d6f3e6d1b61ba777a4332a62cf76a8b0a5efd2c2762b
+DIST snowball-stemmer-2.1.0.tar.gz 220324 BLAKE2B 3d92a2f5b4bd633932d681f2555cf1cc1a2c1a1c71fd0272f09bee17628d034a20649450dd90242c155ab7b262e685913d5ad4034bce6e7a41d76f0dfc724137 SHA512 1efd7d8ab58852987e83247048244882c517e32237c8cb3c0558b66ecfb075733ce8805ebb76041e6e7d6664c236054effe66838e7c524ee529ce869aa8134f0
diff --git a/dev-libs/snowball-stemmer/files/snowball-stemmer-2.1.0-shared-library.patch b/dev-libs/snowball-stemmer/files/snowball-stemmer-2.1.0-shared-library.patch
new file mode 100644
index 000000000000..20c7a386b430
--- /dev/null
+++ b/dev-libs/snowball-stemmer/files/snowball-stemmer-2.1.0-shared-library.patch
@@ -0,0 +1,58 @@
+This is based on a patch taken from alpinelinux, however, duplicated
+libstemmer.o and stemwords targets were removed.
+
+Created shared library contains a lot of relocations, which slow down loading.
+It is known issue and probably the main reason why upstream does not support
+shared library yet [1].
+
+[1] https://github.com/snowballstem/snowball/issues/34#issuecomment-203200078
+
+Alpinelinux-patch: https://git.alpinelinux.org/aports/tree/community/snowball/libstemmer-library.patch?id=28f9d9e192876c43fd96bc5856cd9d8a50dd49c0
+Upstream-issue: https://github.com/snowballstem/snowball/issues/34
+
+diff --git a/GNUmakefile b/GNUmakefile
+index 5cb2179..d1ef193 100644
+--- a/GNUmakefile
++++ b/GNUmakefile
+@@ -3,6 +3,7 @@
+ # After changing this, run `make update_version` to update various sources
+ # which hard-code it.
+ SNOWBALL_VERSION = 2.1.0
++MAJOR_VERSION := $(shell echo $(SNOWBALL_VERSION) | cut -d. -f1)
+ 
+ c_src_dir = src_c
+ 
+@@ -162,10 +163,18 @@ C_OTHER_OBJECTS = $(C_OTHER_SOURCES:.c=.o)
+ JAVA_CLASSES = $(JAVA_SOURCES:.java=.class)
+ JAVA_RUNTIME_CLASSES=$(JAVARUNTIME_SOURCES:.java=.class)
+ 
+-CFLAGS=-O2 -W -Wall -Wmissing-prototypes -Wmissing-declarations
+-CPPFLAGS=-Iinclude
++CFLAGS+=-fPIC -W -Wall -Wmissing-prototypes -Wmissing-declarations
++CPPFLAGS+=-Iinclude
+ 
+-all: snowball libstemmer.o stemwords $(C_OTHER_SOURCES) $(C_OTHER_HEADERS) $(C_OTHER_OBJECTS)
++all: snowball libstemmer.o libstemmer.so libstemmer.a stemwords $(C_OTHER_SOURCES) $(C_OTHER_HEADERS) $(C_OTHER_OBJECTS)
++
++libstemmer.so: libstemmer/libstemmer.o $(RUNTIME_OBJECTS) $(C_LIB_OBJECTS)
++	$(CC) $(CFLAGS) -shared $(LDFLAGS) -Wl,-soname,$@.$(MAJOR_VERSION),-version-script,libstemmer/symbol.map -o $@.$(SNOWBALL_VERSION) $^
++	ln -s $@.$(SNOWBALL_VERSION) $@.$(MAJOR_VERSION)
++	ln -s $@.$(SNOWBALL_VERSION) $@
++
++libstemmer.a: libstemmer.o
++	$(AR) -crs $@ $^
+ 
+ clean:
+ 	rm -f $(COMPILER_OBJECTS) $(RUNTIME_OBJECTS) \
+diff --git a/libstemmer/symbol.map b/libstemmer/symbol.map
+new file mode 100644
+index 0000000..7a3d423
+--- /dev/null
++++ b/libstemmer/symbol.map
+@@ -0,0 +1,6 @@
++SB_STEMMER_0 {
++    global:
++        sb_stemmer_*;
++    local:
++        *;
++};
diff --git a/dev-libs/snowball-stemmer/snowball-stemmer-2.1.0.ebuild b/dev-libs/snowball-stemmer/snowball-stemmer-2.1.0.ebuild
new file mode 100644
index 000000000000..c486383408f3
--- /dev/null
+++ b/dev-libs/snowball-stemmer/snowball-stemmer-2.1.0.ebuild
@@ -0,0 +1,54 @@
+# Copyright 1999-2021 Gentoo Authors
+# Distributed under the terms of the GNU General Public License v2
+
+EAPI=8
+
+inherit toolchain-funcs
+
+MY_TESTDATA_COMMIT="887fb7a3e006f32b4979e0d55f2543abe78a42f1"
+
+DESCRIPTION="Snowball compiler and stemming algorithms"
+HOMEPAGE="https://snowballstem.org/ https://github.com/snowballstem/snowball/"
+SRC_URI="https://github.com/snowballstem/snowball/archive/v${PV}.tar.gz -> ${P}.tar.gz
+	test? ( https://github.com/snowballstem/snowball-data/archive/${MY_TESTDATA_COMMIT}.tar.gz -> snowball-data-${MY_TESTDATA_COMMIT}.tar.gz )"
+
+LICENSE="BSD"
+SLOT="0"
+KEYWORDS="~alpha ~amd64 ~arm ~arm64 ~hppa ~ia64 ~ppc ~ppc64 ~riscv ~s390 ~sparc ~x86 ~amd64-linux ~ppc-macos ~sparc-solaris ~sparc64-solaris"
+IUSE="static-libs test"
+
+DEPEND=""
+RDEPEND="${DEPEND}"
+BDEPEND="dev-lang/perl
+	test? ( virtual/libiconv )"
+RESTRICT="!test? ( test )"
+
+S="${WORKDIR}/snowball-${PV}"
+
+PATCHES=(
+	"${FILESDIR}/${P}-shared-library.patch"
+)
+
+src_compile() {
+	export CC=$(tc-getCC)
+	export AR=$(tc-getAR)
+	default
+}
+
+src_install() {
+	dodoc README.rst NEWS
+
+	dobin stemwords
+
+	doheader include/libstemmer.h
+
+	dolib.so libstemmer.so.${PV}
+	dolib.so libstemmer.so.$(ver_cut 1)
+	dolib.so libstemmer.so
+
+	use static-libs && dolib.a libstemmer.a
+}
+
+src_test() {
+	emake -j1 STEMMING_DATA="${WORKDIR}/snowball-data-${MY_TESTDATA_COMMIT}" check
+}