new bblfs: dev-libs/snowball-stemmer-2.2.0

This commit is contained in:
2026-01-17 20:17:25 -05:00
parent d7e5d91b8b
commit 5ef9b0dda7
2 changed files with 98 additions and 0 deletions

View File

@@ -0,0 +1,39 @@
pkgname=snowball-stemmer
pkgver=2.2.0
pkgdesc="Snowball compiler and stemming algorithms"
homepage="https://snowballstem.org/ https://github.com/snowballstem/snowball/"
license=("BSD")
slot="0/${pkgver%%.*}"
_patches=("snowball-stemmer-2.2.0-shared-library.patch")
_patch_sums=("611dc546bd3744d0c9d86fea2206707eafbe6c9bd2384bbe6d017a4e8a5ef919eeb32e594157e6767a63398f7cdb2fc9d87969eb544756a7c853d33efdc45693")
sources=("${pkgname}-${pkgver}.tar.gz"
"${_patches[@]}"
)
urls=("https://github.com/snowballstem/snowball/archive/v${pkgver}.tar.gz"
"${_patches[@]}"
)
sha512sums=("02c43313de9de2518ea51cfb11f1c29145fc046c7838329bfdefd70b604009ad44b6db8175c25b0db31f03db30a6aec5857aa35775a9c204ec976df9cae62957"
"${_patch_sums[@]}"
)
src_prepare() {
tar -xf ${distdir}/${sources[0]} --strip-components=1
for _patch in ${_patches[@]}; do
patch -p1 -i ${filedir}/${_patch}
done
}
src_build() {
make
}
src_install() {
install -D snowball stemwords -t "$pkgdir/usr/bin"
install -Dm644 COPYING -t "$pkgdir/usr/share/licenses/$pkgname"
install -Dm644 include/libstemmer.h -t "$pkgdir/usr/include"
install -Dm644 libstemmer.so.${pkgver} -t "$pkgdir/usr/lib"
ln -s libstemmer.so.${pkgver} "$pkgdir/usr/lib/libstemmer.so.${pkgver%%.*}"
ln -s libstemmer.so.${pkgver%%.*} "$pkgdir/usr/lib/libstemmer.so"
}
# vim:ft=sh syn=sh et sw=2:

View File

@@ -0,0 +1,59 @@
This is based on a patch taken from alpinelinux, however, duplicated
libstemmer.o and stemwords targets were removed and the patch was
rebased on top of v2.2.0 tag.
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 98eb1fa..9b539ec 100644
--- a/GNUmakefile
+++ b/GNUmakefile
@@ -4,6 +4,8 @@
# which hard-code it.
SNOWBALL_VERSION = 2.2.0
+MAJOR_VERSION := $(shell echo $(SNOWBALL_VERSION) | cut -d. -f1)
+
ifeq ($(OS),Windows_NT)
EXEEXT = .exe
endif
@@ -170,12 +172,17 @@ 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=
+CFLAGS+=-fPIC -W -Wall -Wmissing-prototypes -Wmissing-declarations
+CPPFLAGS+=
INCLUDES=-Iinclude
-all: snowball$(EXEEXT) libstemmer.a stemwords$(EXEEXT) $(C_OTHER_SOURCES) $(C_OTHER_HEADERS) $(C_OTHER_OBJECTS)
+all: snowball$(EXEEXT) libstemmer.a libstemmer.so stemwords$(EXEEXT) $(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) $@
algorithms.mk: libstemmer/mkalgorithms.pl libstemmer/modules.txt
libstemmer/mkalgorithms.pl algorithms.mk libstemmer/modules.txt
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:
+ *;
+};