commit:     1b704c5d34ba6eda30d9e2811b4bc97a84179071
Author:     Michał Górny <mgorny <AT> gentoo <DOT> org>
AuthorDate: Thu Jul  7 15:44:13 2022 +0000
Commit:     Michał Górny <mgorny <AT> gentoo <DOT> org>
CommitDate: Thu Jul  7 19:06:39 2022 +0000
URL:        https://gitweb.gentoo.org/repo/gentoo.git/commit/?id=1b704c5d

dev-python/nltk-data: Update to 20220704

Signed-off-by: Michał Górny <mgorny <AT> gentoo.org>

 dev-python/nltk-data/Manifest                  |   3 +
 dev-python/nltk-data/nltk-data-20220704.ebuild | 223 +++++++++++++++++++++++++
 2 files changed, 226 insertions(+)

diff --git a/dev-python/nltk-data/Manifest b/dev-python/nltk-data/Manifest
index 3a61ebbf461e..4dc34058effa 100644
--- a/dev-python/nltk-data/Manifest
+++ b/dev-python/nltk-data/Manifest
@@ -22,6 +22,7 @@ DIST nltk-crubadan-20200312.zip 5288655 BLAKE2B 
2f5103c9801b965ce5d893b690dedc5f
 DIST nltk-dependency_treebank-20200312.zip 457429 BLAKE2B 
a60a95f9bcbb72b4ee19a91c380eb620261687f23bd867ae4cf2d7937b60b8dacafb52c09d7bcbcb9fbbbda4e57954ee55a900d70e69e7e290e53c668dd0775f
 SHA512 
b225ace2e2413f0b9ae0e142d81052e64a1bcacb71caf7b07a577c18dec45dc429116abfd12edd3bb1442a111f4fa6e3e33e2b5f113e26dfc4e917268d821736
 DIST nltk-dolch-20200312.zip 2116 BLAKE2B 
a79b5d5de2ab03be43e5fdb1b34c70a458af6efce0e35f42f3c4d748c84cd950c98981f969fea2b0507ee405438f84b50e526aa94a93f99de7567ccb5c462215
 SHA512 
29254c95d11fd2001f486a5c682f7ab7f23fa13472ac4142db3702e2fa994f74ffabc2f571f1feb94a2e65fcb8da97c57a519f24504379b0e369fd27f9f867f0
 DIST nltk-europarl_raw-20200312.zip 12594977 BLAKE2B 
295e274880ae34c9618a70cabc1b1075e35c442158aabe437972caebbf36d09c4f5f5b66d8ae7ac953f4312f9dac8f5e0c6d3346a444afe98ac700fb3e622539
 SHA512 
47dcd5420df6ab294f75204355cf346257a821d491f65b856c41a77237df1d7aeb352ed1353da55bfb68fa9f0d8782b9aac9c33bd49af3b395cc780dc421e26d
+DIST nltk-extended_omw-20220704.zip 11251284 BLAKE2B 
11dafcc49c3608e5178b2cf82a943a95afd900f80308bf40d56b29a4518029832fe52241df728f6c38114e60b9c03617337717d987221918a11810b77b1b33ea
 SHA512 
b1f53bef1cc43a5bf9996cc037364f4668e1055385d43e3276a1c58e4345b6ee09d8b577ccdebe8e65bf3367b8da37c05c6dabd282e469808143805303bfeec5
 DIST nltk-floresta-20200312.zip 1882021 BLAKE2B 
092886cb15c6215b4fe979ce62a1a137de97c4749c372426211d36117d367697d19ebe6a9337f702ee9dfc133318b1e7de51393c5a41afc31a960e10ebe7c498
 SHA512 
1a71453b9629d622c3468b1e00501683e0415996a62a30c498486354b82f0b3be76080dddc60117c8c9f29de3b34a2166a5de87376a0daeaf8b92bfe5dac668a
 DIST nltk-framenet_v15-20200312.zip 69337891 BLAKE2B 
046087cb20013f3a597034458dd09b4cb7378b19f91f5ebf7196a92a02741a67b671f094262ac5d8e0e376743048c56dd1d65e6c37efb3b254bb3f8f6434addf
 SHA512 
4b55a435f17afbb9cf5fb59691a03776784830cfa6f1f7b9c9c64770fa6dbb640bb3256a099328e44a0a6692ed52703b9f253e5229ef71ee300ace34027ba462
 DIST nltk-framenet_v17-20200312.zip 99207152 BLAKE2B 
b1a32c535d37fddba5c77922f3a6097859d8bf59a4bcf37dca4ff394fcf027fc68d781b3b6c0a8d5cd9a423a944687994ec6a2023dd45808dc697b4c90f28286
 SHA512 
3696c5bb0fdd59058a8723ba3ca962a0d6422b36d8dcfad0427caa21dae9579b85f2f9af431aa1fc1cb76e823676a996c5a26aca99782017270d03ef3bd77f0d
@@ -83,6 +84,7 @@ DIST nltk-snowball_data-20200312.zip 6785405 BLAKE2B 
44c10439b142540ac7eece967ef
 DIST nltk-spanish_grammars-20200312.zip 4047 BLAKE2B 
d8a8dbb558850a6a60f1fe5ab0f617f3a0f3c64bc7d49980cf793d374c6679d1bd42afb7e61776737b5eec162f2520abf2ee3acc92ea9ee0f397c3089b3b5b28
 SHA512 
4513347156e9351c259c0e2448198d68354bbc95e0a54561c31a88f13f333ebcba3e294c820cb62036665f2904eb6a7137546cd580e361c0423c30a8aed950b2
 DIST nltk-state_union-20200312.zip 808757 BLAKE2B 
2d352af0ced736d3c11a821eaba0b035b3b5b6b0f20db3bd5d4ac2451f99daf68bffd3ad984bd404ecc4a1e67ca9281c529af2cc9e295a3a7330f36ee9640bc8
 SHA512 
a6fc83e6230e57ba66a7af62f0d2a5d44a14530ed1e0e914590b3f8b5bf939967c126a5e6f6899ba9134843893f65212e836d311109393c1200191a5c3163485
 DIST nltk-stopwords-20211023.zip 26220 BLAKE2B 
50219508c5fb24c1392064ea0546ca9060829f51689c0d626bb99e3fa8f712df98ed475fc0d27d99f934fb156ce65df91a8e7c22e1b4f16833339fb0aea34a9e
 SHA512 
8308623953560281288b64e695638ca3fa28e1b6201b538d01650d6dfd08e821687217c8d012e93adfa2a48afebdda11af1bb86d638358c2931f36754d1e15ef
+DIST nltk-stopwords-20220704.zip 34276 BLAKE2B 
529a26163c01123bb9b800cfc8f7f5a23701246194c0b55012b418384ca48c56eb5c27a5f104e81ba974cec845e7025829e9d396a384d331903982cd29c98623
 SHA512 
8b76207f53d05c251aac078d9b8537f100a202cc2a43892af0c79da8d99ae8335225a1bc8a56f1be4cd1ef45c9c987b6c9c334e0f9fa59746bb33694c58a556b
 DIST nltk-subjectivity-20200312.zip 521628 BLAKE2B 
0a8777a5b91b1b825fbde41cc927d496480129f0a810349bddde2036ed16f37611f2bc3b007e74fe36523612529a92433d32d094be72d247f5faef8220c3c491
 SHA512 
a3cc4d2d20f26c5eabd86fbced2c013e69d46e607013278eb35831a62e57523a17aec1b580ba62c7a867e61a561e1b222d8430f0c1e2d429a9479e12b008c5b7
 DIST nltk-swadesh-20200312.zip 22828 BLAKE2B 
1cd9d5355c6b53694ec545ca001b0807b4912a7878ba075b0f81ce8b9b22a5c7a18cf52cf2449483a1c89cd20d8d86986dc3d827fa93a7ef5824fddbc0922025
 SHA512 
90cb32532a5378d05ce34b84b5f8363dbb32f24afac58b0dcc5cdccba98fd7d37def7f4fbe76b11c8c64059bd19df745562bfbf5f4c721d65ce9f4be1348ab76
 DIST nltk-switchboard-20200312.zip 791161 BLAKE2B 
211116a751ae246fa31b6aca96b396d3642d89ad112588a09f8d91a5b76dc41c7fb4d36c16c6358cd8e0da8056bc83598ed0dc635cf7b1fd8469a0e80b5f1761
 SHA512 
690e5392dc082c4ac550bde2848aa65117e7a25cbc4bce0887581c531d03be64e21f044ac0a3286648255f0edd7766b1161f5575ad5fd680c7303b34c3226b8f
@@ -95,6 +97,7 @@ DIST nltk-udhr-20200312.zip 1170177 BLAKE2B 
cab5f8b4ffa9c0c303620a499f61bbe65454
 DIST nltk-udhr2-20200312.zip 1653975 BLAKE2B 
43ee8c9c490a6a8ee5f0d9273bab83f77ba3d977da7eaeded3239b8c16f3432ef36478d0d290b1df9fe9af4e0c5de1902b8fe699788b7681003e5c8c426574e3
 SHA512 
eda644aedba1d0b9d2605dc6b1c8c77943692b4404c4a9c904c82956432c9ba7e27bb0f496e63d3eef7f29b4b34eb929f8d9228b4fd56613d5d4f743fa1d87e0
 DIST nltk-unicode_samples-20200312.zip 1212 BLAKE2B 
715c6030baf56d766dce7b920500c29dc98ce4edc9b41fb4c858960a4630469fe5a269be6d0b2d33b54ee0208014b1e43f5d9ec49b878442963ea21e4e3acda6
 SHA512 
88cac1ef0f43fc491285c0638807f88f52d1baba8964cb2cf37c4ee3e8cd8c080071f108fb553fdc14ed17cb0e80343097c08ac7c1613b0abbd84f559e38fba8
 DIST nltk-universal_tagset-20200312.zip 19095 BLAKE2B 
179297dac3a6a30a4a55e8affb480cc95a7a1dd1ee0ac6a0d4381c655c5dbf065e16f750ebd28846299f114d3355a9edf6cbed72242ebf5fd257f339fcd8f40d
 SHA512 
ca8915e8c3bcb8515ffe0da21fb7066d213683ff702bf247d9fa9f7c966c66d06facafef1d600b7223d7aa1e4dfba1a2a75e1bb05b2c5d78beb312b8551d3fed
+DIST nltk-universal_tagset-20220704.zip 19095 BLAKE2B 
829bb169ec42005fd5c0bc827d0820eab49acce562240b942dcccc4d3bd96b3f17d24fe46f21d528264ebe976df79e2bb00da33a889759cc20cbb06f40a6ac41
 SHA512 
2a0094744c0e697e0cbc2c49002f41d52973a87dc940636b5edb1a162f7ac4f165911555be590c5b66d69cede918ed9cf2d3ccd59f91286eba274ef44c8df28c
 DIST nltk-universal_treebanks_v20-20200312.zip 25908853 BLAKE2B 
20f8a6c0e759ab15560e71f48527e26a0dac554b8996dcebcacd2c5d5e3cea8947481734a03680843176025fde6d5e484e9414dd239043dca380c79053d71d8f
 SHA512 
3dcabe02ff8bb1044f7d9e1c5af294af05291ff33a6c8dc16d3a3c855ccbf3a8261d92ea926e15e0d7f9228ae81e7863a283b156812ad30575c9ea947ecbcc55
 DIST nltk-vader_lexicon-20200312.zip 90486 BLAKE2B 
aaa4a07a600d6ef53373250afd62a1a5e76cbeb28b56c06879d07a6cea593d7041300e6eaf2ce39b87dc0c04a536fae111df80604e7f517878e680fb9db16019
 SHA512 
55d41757736806a2a0dbcaedef28000b4461eb44dce308c9e06315feb55f843914f743c37b6cf220fc9e61c04f8f7f41dd338438059e2e803fc2b4e91f739923
 DIST nltk-verbnet-20200312.zip 323661 BLAKE2B 
af5b26a63853d1bc3fc99c9cba3c50a82bc148cb6d95a26045c9aa29ba83408db76b098354e99f07696d5e2373ed9d8a35ed8504ac9b20e1b4d16252a238bc85
 SHA512 
00368fb2d5cf1bf818f1d72762d2c40a98067937d71a65ece2ca0f4bfab6f8957b32ba66741901af34258cf3309d00dae433b1092d0b7adb145a791dc3bf859b

diff --git a/dev-python/nltk-data/nltk-data-20220704.ebuild 
b/dev-python/nltk-data/nltk-data-20220704.ebuild
new file mode 100644
index 000000000000..fdbb6fd0da4e
--- /dev/null
+++ b/dev-python/nltk-data/nltk-data-20220704.ebuild
@@ -0,0 +1,223 @@
+# 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
+# TODO: create a USE flag for free-ish subset
+LICENSE="all-rights-reserved"
+SLOT="0"
+KEYWORDS="amd64 ~riscv x86"
+IUSE="extra"
+RESTRICT="bindist mirror"
+
+BDEPEND="app-arch/unzip"
+
+# https://github.com/nltk/nltk_data/commits/gh-pages
+
+PACKAGES_ZIP_2020=(
+       # wget -O - https://www.nltk.org/nltk_data/ | xml sel -t -m 
'//package[@unzip=0]' -v @subdir -o "/" -v @id -n - | sort
+       corpora/comtrans
+       corpora/conll2007
+       corpora/jeita
+       corpora/knbc
+       corpora/machado
+       corpora/masc_tagged
+       corpora/nombank.1.0
+       corpora/panlex_swadesh
+       corpora/propbank
+       corpora/reuters
+       corpora/semcor
+       corpora/universal_treebanks_v20
+       sentiment/vader_lexicon
+       stemmers/snowball_data
+)
+
+PACKAGES_UNPACK_2020=(
+       # wget -O - https://www.nltk.org/nltk_data/ | xml sel -t -m 
'//package[@unzip=1]' -v @subdir -o "/" -v @id -n - | sort
+       corpora/abc
+       corpora/alpino
+       corpora/brown
+       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/indian
+       corpora/lin_thesaurus
+       corpora/mac_morpho
+       corpora/movie_reviews
+       corpora/mte_teip5
+       corpora/names
+       corpora/nonbreaking_prefixes
+       corpora/nps_chat
+       corpora/omw
+       corpora/opinion_lexicon
+       corpora/pl196x
+       corpora/ppattach
+       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/state_union
+       corpora/subjectivity
+       corpora/swadesh
+       corpora/switchboard
+       corpora/timit
+       corpora/toolbox
+       corpora/treebank
+       corpora/twitter_samples
+       corpora/udhr
+       corpora/udhr2
+       corpora/verbnet
+       corpora/webtext
+       corpora/wordnet
+       corpora/wordnet_ic
+       corpora/words
+       grammars/book_grammars
+       grammars/large_grammars
+       grammars/sample_grammars
+       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
+       tokenizers/punkt
+)
+
+PACKAGES_UNPACK_2021_12=(
+       corpora/inaugural
+       corpora/omw-1.4
+       corpora/wordnet2021
+       corpora/wordnet31
+       corpora/sinica_treebank
+)
+
+PACKAGES_UNPACK_2022=(
+       corpora/stopwords
+       taggers/universal_tagset
+)
+
+PACKAGES_UNPACK_EXTRA_2020=(
+       chunkers/maxent_ne_chunker
+       corpora/biocreative_ppi
+       corpora/brown_tei
+       corpora/kimmo
+       corpora/paradigms
+       corpora/pe08
+       corpora/pil
+       corpora/problem_reports
+       corpora/smultron
+       corpora/unicode_samples
+       corpora/verbnet3
+       corpora/ycoe
+       grammars/basque_grammars
+       grammars/spanish_grammars
+       help/tagsets
+       misc/mwa_ppdb
+       taggers/maxent_treebank_pos_tagger
+)
+
+PACKAGES_ZIP_EXTRA_2022=(
+       corpora/extended_omw
+)
+
+add_data() {
+       local x version=${1}
+       shift
+
+       for x; do
+               SRC_URI+="
+                       
https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/${x}.zip
+                               -> nltk-${x#*/}-${version}.zip"
+       done
+}
+
+add_data 20200312 "${PACKAGES_ZIP_2020[@]}" "${PACKAGES_UNPACK_2020[@]}"
+add_data 20211221 "${PACKAGES_UNPACK_2021_12[@]}"
+add_data 20220704 "${PACKAGES_UNPACK_2022[@]}"
+SRC_URI+="
+       extra? ("
+add_data 20200312 "${PACKAGES_UNPACK_EXTRA_2020[@]}"
+add_data 20220704 "${PACKAGES_ZIP_EXTRA_2022[@]}"
+SRC_URI+="
+       )"
+
+CHECKREQS_DISK_USR=3G
+CHECKREQS_DISK_BUILD=${CHECKREQS_DISK_USR}
+
+unpack_data() {
+       local x version=${1}
+       shift
+
+       for x; do
+               local cat=${x%/*}
+               local pkg=${x#*/}
+
+               mkdir -p "${S}/${cat}" || die
+               cd "${S}/${cat}" || die
+               unpack "nltk-${pkg}-${version}.zip"
+       done
+}
+
+src_unpack() {
+       unpack_data 20200312 "${PACKAGES_UNPACK_2020[@]}"
+       unpack_data 20211023 "${PACKAGES_UNPACK_2021[@]}"
+       unpack_data 20211221 "${PACKAGES_UNPACK_2021_12[@]}"
+       unpack_data 20220704 "${PACKAGES_UNPACK_2022[@]}"
+       if use extra; then
+               unpack_data 20200312 "${PACKAGES_UNPACK_EXTRA_2020[@]}"
+       fi
+}
+
+install_zips() {
+       local x version=${1}
+       shift
+
+       for x; do
+               local cat=${x%/*}
+               local pkg=${x#*/}
+
+               insinto "/usr/share/nltk_data/${cat}"
+               newins "${DISTDIR}/nltk-${pkg}-${version}.zip" "${pkg}.zip"
+       done
+}
+
+src_install() {
+       dodir /usr/share/nltk_data
+       mv * "${ED}/usr/share/nltk_data/" || die
+
+       install_zips 20200312 "${PACKAGES_ZIP_2020[@]}"
+       if use extra; then
+               install_zips 20220704 "${PACKAGES_ZIP_EXTRA_2022[@]}"
+       fi
+}

Reply via email to