casa-mp-base

# -*- coding: utf-8; mode: tcl; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- vim:fenc=utf-8:ft=tcl:et:sw=4:ts=4:sts=4

​

PortSystem          1.0

PortGroup           cmake 1.1

PortGroup           github 1.0

PortGroup           compiler_blacklist_versions 1.0

​

github.setup        google sentencepiece 0.1.84 v

revision            0

categories          textproc

​

license             Apache-2

maintainers         nomaintainer

platforms           darwin

​

description         Unsupervised text tokenizer for Neural Network-based\

                    text generation.

​

long_description    SentencePiece is an unsupervised text tokenizer\

                    and detokenizer mainly for Neural Network-based\

                    text generation systems where the vocabulary size\

                    is predetermined prior to the neural model\

                    training. SentencePiece implements subword units\

                    (e.g., byte-pair-encoding (BPE) \[Sennrich et al.\])\

                    and unigram language model \[Kudo.\]) with the\

                    extension of direct training from raw\

                    sentences. SentencePiece allows us to make a\

                    purely end-to-end system that does not depend on\

                    language-specific pre/postprocessing.

​

checksums           rmd160  91bc4a0a23d9a4daf98abbb9ec83aed2241fdc42 \

                    sha256  dacab5fe63875b94538e06f4995ffb8cf35400708f3c333263f7b72e2e5b43de \

                    size    11828855

​

compiler.cxx_standard 2011

​

# build fails with "error: thread-local storage is not supported for the current target"

# setting "compiler.thread_local_storage yes" does not work, so for now just use blacklisting

# See: https://lists.macports.org/pipermail/macports-dev/2019-November/041503.html

compiler.blacklist-append {clang < 800}

​

depends_lib-append  port:gperftools