From 40ef4b8a661b2b6f772e8093f4a54ad0db1d4efc Mon Sep 17 00:00:00 2001
From: Marcin Deranek <marcin.deranek@slonko.net>
Date: Sun, 16 Jul 2023 21:02:48 +0200
Subject: dev-python/nltk-data version bump

---
 dev-python/nltk-data/nltk-data-20230602.ebuild | 193 +++++++++++++++++++++++++
 1 file changed, 193 insertions(+)
 create mode 100644 dev-python/nltk-data/nltk-data-20230602.ebuild

(limited to 'dev-python/nltk-data/nltk-data-20230602.ebuild')

diff --git a/dev-python/nltk-data/nltk-data-20230602.ebuild b/dev-python/nltk-data/nltk-data-20230602.ebuild
new file mode 100644
index 0000000..8af2e67
--- /dev/null
+++ b/dev-python/nltk-data/nltk-data-20230602.ebuild
@@ -0,0 +1,193 @@
+# Copyright 2020-2022 Gentoo Authors
+# Distributed under the terms of the GNU General Public License v2
+
+EAPI=8
+
+inherit check-reqs
+
+DESCRIPTION="Data files for NLTK"
+HOMEPAGE="https://www.nltk.org/nltk_data/"
+
+# at least some of the files have poorly documented licenses
+# https://github.com/nltk/nltk_data/issues/102
+# TODO: create a USE flag for free-ish subset
+LICENSE="all-rights-reserved"
+SLOT="0"
+KEYWORDS="amd64 ~ppc64 ~riscv x86"
+RESTRICT="bindist mirror"
+
+BDEPEND="app-arch/unzip"
+
+# https://github.com/nltk/nltk_data/commits/gh-pages
+
+PACKAGES_ZIP=(
+	# wget -O - https://www.nltk.org/nltk_data/ | xml sel -t -m '//package[@unzip=0]' -v @subdir -o "/" -v @id -n - | sort
+	corpora/bcp47
+	corpora/comtrans
+	corpora/conll2007
+	corpora/extended_omw
+	corpora/jeita
+	corpora/knbc
+	corpora/machado
+	corpora/masc_tagged
+	corpora/nombank.1.0
+	corpora/omw
+	corpora/omw-1.4
+	corpora/panlex_swadesh
+	corpora/propbank
+	corpora/reuters
+	corpora/semcor
+	corpora/universal_treebanks_v20
+	corpora/wordnet
+	corpora/wordnet2021
+	corpora/wordnet31
+	sentiment/vader_lexicon
+	stemmers/snowball_data
+)
+
+PACKAGES_UNPACK=(
+	# wget -O - https://www.nltk.org/nltk_data/ | xml sel -t -m '//package[@unzip=1]' -v @subdir -o "/" -v @id -n - | sort
+	chunkers/maxent_ne_chunker
+	corpora/abc
+	corpora/alpino
+	corpora/biocreative_ppi
+	corpora/brown
+	corpora/brown_tei
+	corpora/cess_cat
+	corpora/cess_esp
+	corpora/chat80
+	corpora/city_database
+	corpora/cmudict
+	corpora/comparative_sentences
+	corpora/conll2000
+	corpora/conll2002
+	corpora/crubadan
+	corpora/dependency_treebank
+	corpora/dolch
+	corpora/europarl_raw
+	corpora/floresta
+	corpora/framenet_v15
+	corpora/framenet_v17
+	corpora/gazetteers
+	corpora/genesis
+	corpora/gutenberg
+	corpora/ieer
+	corpora/inaugural
+	corpora/indian
+	corpora/kimmo
+	corpora/lin_thesaurus
+	corpora/mac_morpho
+	corpora/movie_reviews
+	corpora/mte_teip5
+	corpora/names
+	corpora/nonbreaking_prefixes
+	corpora/nps_chat
+	corpora/opinion_lexicon
+	corpora/paradigms
+	corpora/pe08
+	corpora/pil
+	corpora/pl196x
+	corpora/ppattach
+	corpora/problem_reports
+	corpora/product_reviews_1
+	corpora/product_reviews_2
+	corpora/pros_cons
+	corpora/ptb
+	corpora/qc
+	corpora/rte
+	corpora/senseval
+	corpora/sentence_polarity
+	corpora/sentiwordnet
+	corpora/shakespeare
+	corpora/sinica_treebank
+	corpora/smultron
+	corpora/state_union
+	corpora/stopwords
+	corpora/subjectivity
+	corpora/swadesh
+	corpora/switchboard
+	corpora/timit
+	corpora/toolbox
+	corpora/treebank
+	corpora/twitter_samples
+	corpora/udhr
+	corpora/udhr2
+	corpora/unicode_samples
+	corpora/verbnet
+	corpora/verbnet3
+	corpora/webtext
+	corpora/wordnet2022
+	corpora/wordnet_ic
+	corpora/words
+	corpora/ycoe
+	grammars/basque_grammars
+	grammars/book_grammars
+	grammars/large_grammars
+	grammars/sample_grammars
+	grammars/spanish_grammars
+	help/tagsets
+	misc/mwa_ppdb
+	misc/perluniprops
+	models/bllip_wsj_no_aux
+	models/moses_sample
+	models/wmt15_eval
+	models/word2vec_sample
+	stemmers/porter_test
+	stemmers/rslp
+	taggers/averaged_perceptron_tagger
+	taggers/averaged_perceptron_tagger_ru
+	taggers/maxent_treebank_pos_tagger
+	taggers/universal_tagset
+	tokenizers/punkt
+)
+
+add_data() {
+	local data=${1}
+
+	for data; do
+		SRC_URI+="
+			https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/${data}.zip
+				-> nltk-${data#*/}-${PV}.zip"
+	done
+}
+
+add_data "${PACKAGES_ZIP[@]}" "${PACKAGES_UNPACK[@]}"
+
+CHECKREQS_DISK_USR=3G
+CHECKREQS_DISK_BUILD=${CHECKREQS_DISK_USR}
+
+unpack_data() {
+	local data=${1}
+
+	for data; do
+		local cat=${data%/*}
+		local pkg=${data#*/}
+
+		mkdir -p "${S}/${cat}" || die
+		cd "${S}/${cat}" || die
+		unpack "nltk-${pkg}-${PV}.zip"
+	done
+}
+
+src_unpack() {
+	unpack_data "${PACKAGES_UNPACK[@]}"
+}
+
+install_zips() {
+	local data=${1}
+
+	for data; do
+		local cat=${data%/*}
+		local pkg=${data#*/}
+
+		insinto "/usr/share/nltk_data/${cat}"
+		newins "${DISTDIR}/nltk-${pkg}-${PV}.zip" "${pkg}.zip"
+	done
+}
+
+src_install() {
+	dodir /usr/share/nltk_data
+	mv * "${ED}/usr/share/nltk_data/" || die
+
+	install_zips "${PACKAGES_ZIP[@]}"
+}
-- 
cgit v1.2.3