%global __brp_check_rpaths %{nil} %global __requires_exclude ^libmpi %global packname textpress %global packver 1.1.1 %global rlibdir /usr/local/lib/R/library Name: R-CRAN-%{packname} Version: 1.1.1 Release: 1%{?dist}%{?buildtag} Summary: A Lightweight and Versatile NLP Toolkit License: MIT + file LICENSE URL: https://cran.r-project.org/package=%{packname} Source0: %{url}&version=%{packver}#/%{packname}_%{packver}.tar.gz BuildRequires: R-devel >= 3.5 Requires: R-core >= 3.5 BuildArch: noarch BuildRequires: R-CRAN-data.table BuildRequires: R-CRAN-httr BuildRequires: R-CRAN-Matrix BuildRequires: R-CRAN-rvest BuildRequires: R-CRAN-stringi BuildRequires: R-CRAN-stringr BuildRequires: R-CRAN-xml2 BuildRequires: R-CRAN-pbapply BuildRequires: R-CRAN-jsonlite BuildRequires: R-CRAN-lubridate Requires: R-CRAN-data.table Requires: R-CRAN-httr Requires: R-CRAN-Matrix Requires: R-CRAN-rvest Requires: R-CRAN-stringi Requires: R-CRAN-stringr Requires: R-CRAN-xml2 Requires: R-CRAN-pbapply Requires: R-CRAN-jsonlite Requires: R-CRAN-lubridate %description A toolkit for web scraping, modular NLP pipelines, and text preparation for large language models. Organized around four core actions: fetching, reading, processing, and searching. Covers the full pipeline from raw web data acquisition to structural text processing and BM25 indexing. Supports multiple retrieval strategies including regex, dictionary matching, and ranked keyword search. Pipe-friendly with no heavy dependencies; all outputs are plain data frames or data.tables. %prep %setup -q -c -n %{packname} # fix end of executable files find -type f -executable -exec grep -Iq . {} \; -exec sed -i -e '$a\' {} \; # prevent binary stripping [ -d %{packname}/src ] && find %{packname}/src -type f -exec \ sed -i 's@/usr/bin/strip@/usr/bin/true@g' {} \; || true [ -d %{packname}/src ] && find %{packname}/src/Make* -type f -exec \ sed -i 's@-g0@@g' {} \; || true # don't allow local prefix in executable scripts find -type f -executable -exec sed -Ei 's@#!( )*/usr/local/bin@#!/usr/bin@g' {} \; %build %install mkdir -p %{buildroot}%{rlibdir} %{_bindir}/R CMD INSTALL -l %{buildroot}%{rlibdir} %{packname} test -d %{packname}/src && (cd %{packname}/src; rm -f *.o *.so) rm -f %{buildroot}%{rlibdir}/R.css # remove buildroot from installed files find %{buildroot}%{rlibdir} -type f -exec sed -i "s@%{buildroot}@@g" {} \; %files %{rlibdir}/%{packname}