%global __brp_check_rpaths %{nil}
%global __requires_exclude ^libmpi
%global packname  tidyEmoji
%global packver   0.4.0
%global rlibdir   /usr/local/lib/R/library

Name:             R-CRAN-%{packname}
Version:          0.4.0
Release:          1%{?dist}%{?buildtag}
Summary:          Discover, Count, Categorise, Score, Translate and Relate Emoji in Text

License:          GPL (>= 3)
URL:              https://cran.r-project.org/package=%{packname}
Source0:          %{url}&version=%{packver}#/%{packname}_%{packver}.tar.gz


BuildRequires:    R-devel >= 4.1.0
Requires:         R-core >= 4.1.0
BuildArch:        noarch
BuildRequires:    R-CRAN-emoji >= 16.0.0
BuildRequires:    R-CRAN-tidyr >= 1.3.0
BuildRequires:    R-CRAN-dplyr >= 1.1.0
BuildRequires:    R-CRAN-lifecycle >= 1.0.3
BuildRequires:    R-CRAN-rlang 
BuildRequires:    R-stats 
BuildRequires:    R-CRAN-tibble 
BuildRequires:    R-utils 
Requires:         R-CRAN-emoji >= 16.0.0
Requires:         R-CRAN-tidyr >= 1.3.0
Requires:         R-CRAN-dplyr >= 1.1.0
Requires:         R-CRAN-lifecycle >= 1.0.3
Requires:         R-CRAN-rlang 
Requires:         R-stats 
Requires:         R-CRAN-tibble 
Requires:         R-utils 

%description
A tidy toolkit for working with the emoji in any text column, such as
social-media posts, product reviews, chat logs or survey responses.
Unicode is awkward to handle and not every code point is an emoji, which
makes emoji statistics fiddly to obtain. 'tidyEmoji' extracts, counts,
categorises, sentiment-scores and emotion-scores emoji, converts them to
and from text (for accessibility and NLP preprocessing), searches the
emoji catalogue, maps emoji co-occurrence and sequences (graph-ready edge
lists and n-grams), measures where and how densely emoji are used, and
builds document-by-emoji feature tables for machine learning, with
grapheme-aware detection (so skin-tone and multi-person sequences stay
intact), returning tidy data frames that slot straight into a 'tidyverse'
workflow. It also quantifies how much annotators disagreed about an emoji
(interpretation risk), extracts the words around each emoji, tracks emoji
use over time, measures text-emoji sentiment mismatch, and applies
explicit emoji-preprocessing policies for language-model pipelines. The
bundled emoji sentiment lexicon is from the Emoji Sentiment Ranking of
Kralj Novak et al. (2015) <doi:10.1371/journal.pone.0144296>, released
under CC BY-SA 4.0; the emotion lexicon is from EmoTag1200 of Shoeb & de
Melo (2020) <https://aclanthology.org/2020.emnlp-main.720/>, released
under the MIT licence.

%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}