Gentoo Archives: gentoo-commits

From: "Michał Górny" <mgorny@g.o>
To: gentoo-commits@l.g.o
Subject: [gentoo-commits] repo/gentoo:master commit in: dev-python/nltk-data/
Date: Tue, 21 Dec 2021 09:43:10
Message-Id: 1640079769.08f79ab2f283b49343dd5a4f263eeb5719b1d636.mgorny@gentoo
1 commit: 08f79ab2f283b49343dd5a4f263eeb5719b1d636
2 Author: Michał Górny <mgorny <AT> gentoo <DOT> org>
3 AuthorDate: Tue Dec 21 07:27:25 2021 +0000
4 Commit: Michał Górny <mgorny <AT> gentoo <DOT> org>
5 CommitDate: Tue Dec 21 09:42:49 2021 +0000
6 URL: https://gitweb.gentoo.org/repo/gentoo.git/commit/?id=08f79ab2
7
8 dev-python/nltk-data: Remove old
9
10 Signed-off-by: Michał Górny <mgorny <AT> gentoo.org>
11
12 dev-python/nltk-data/Manifest | 3 -
13 dev-python/nltk-data/nltk-data-20211023.ebuild | 203 -------------------------
14 2 files changed, 206 deletions(-)
15
16 diff --git a/dev-python/nltk-data/Manifest b/dev-python/nltk-data/Manifest
17 index 2a75eb265207..3a61ebbf461e 100644
18 --- a/dev-python/nltk-data/Manifest
19 +++ b/dev-python/nltk-data/Manifest
20 @@ -29,7 +29,6 @@ DIST nltk-gazetteers-20200312.zip 8265 BLAKE2B aa4f8db99a7ae8c26911d33abb67713bc
21 DIST nltk-genesis-20200312.zip 473239 BLAKE2B 5234c2bcc31ae738bbd6cdfe1ee231a75ceacc74334e3b03fcefb409427406aee1700e0d8ca8fad1444736005b53fdb0fbdb9068085837f4bf7292cf61351b8b SHA512 e74f6a8f304bca292bf8e138a739a97633075cf9374c95f43ec75473cd7bbeb0921fe24f7864659e640e694d227e61debd67bc41150bd898b7241a274e28196f
22 DIST nltk-gutenberg-20200312.zip 4251829 BLAKE2B 54448e919010f12faa92c0ffd4adb31a7d1d76c262d5ac99c10129d188830107621f90e4ba611ffc1541c25037fc916b451169a8ae1df276747890fea2b5e06f SHA512 7b4442d18b89f9bb8261f23ad2f4d513b470461255633cbebe2b0c310f003effe819f7a86b39a62a6cde1b3fdbf099dabbdaaed520268c99fd1bb933baa97ead
23 DIST nltk-ieer-20200312.zip 166156 BLAKE2B 4c63be6f0f16e59584b7f97c21da0cf60a1efd3678ce662d683d8a6a9d05d333690b26ebb037d3047b26e3b51163ffa666f048ad8a89ee6c851ddd3edd2faf58 SHA512 b55545f0ac03282fb85c4a86bb69fd9988db8cc504114bff7b763007e20f559efa61b8ae5b7955c251c1c2dd9d23246e23515b1cd5d8d28225c20ec236c05cd8
24 -DIST nltk-inaugural-20200312.zip 329806 BLAKE2B 222e22742d93156b852ddd72ffccdd5be5c907f43973b0ceee8d8d383bc5387575d1f974b29fd6d59499ec86483f56270251e6a5e48d7840c577207849baed59 SHA512 096591769373019883b9a2f85d32bc86021aefb74deb26dc9005233ae7f317d587c247edc53f1a956b8e29911656419d9677c271fb59ded4ca4edf2a80ff86b7
25 DIST nltk-inaugural-20211221.zip 346476 BLAKE2B 6f14827fcd8edf9300725c6ffcfa899f5878537aaefc40b165581af60866ca7e7b0ed316a2b8dd87ff858667ce7a5f4035090a1cc3a404afa64b28d34dcf8747 SHA512 5440bff001209e42ee86c2501d2cd628cf639734c194c11097a862f6759f09a6adef1da0702b77211774f84d5d9d4ee55e89085b39d8a911811def1bd07ac8e2
26 DIST nltk-indian-20200312.zip 199187 BLAKE2B 9f70f1f28bcb96d828ca2ed96d6f89cd8eca8391b64842c742e940aaf59f31e142a4919ab5a21bce954bbe2ed85add162ac67c9549758f9aa44b3e90d45d44a7 SHA512 08e9342567bcc607e9007aea8415af2cad1f8a289104b47a61bf569f1391629ebbe25f19aacf53e2b14725edfdf18076331f044e1c2e42d07c96d5c875ff8f9e
27 DIST nltk-jeita-20200312.zip 16531215 BLAKE2B 7cf98b389d5c4b41d9d613c14c5116b83c520cfe7418ef982a6acc1294d8ecdb8a5d6d396409c9f13ca83df999793619d5eb5483612e87874766afe565c68362 SHA512 491e6dc27d70ebfd139be4dcd179b02c383f38edbe4290aed85638ecd7c987259b025e4f6f3f1d5bfe2b7aa3eff7188109205417d0acb64759988150f2753129
28 @@ -78,7 +77,6 @@ DIST nltk-senseval-20200312.zip 2151350 BLAKE2B ec21463f7ffe27e3dda47e38e3563464
29 DIST nltk-sentence_polarity-20200312.zip 490256 BLAKE2B 56a1b4668875d5c73b220710e8af84410a273f394d68d7e9decb47c5370f0f7c1982d37710ab903d78dac0108ec2e1a26e8f1cdd3fee172487397c8b2ae01ee7 SHA512 d3772edc13d46fb835f40a9c6714b95885d3ba2eded37a24c8aad6d3e63ca49a9c79387218e2f67bda2e52d52449daf1dd1e603a4819ae46da78f4e0a38ba599
30 DIST nltk-sentiwordnet-20200312.zip 4686546 BLAKE2B 98a45d9a5be971bd9e76ad5c154359c1800aa96ab1e8e301215e435cae6d659cc0fb38604435da4e9a391741a72ef7fcb842a1cf119348a7039f717843035f12 SHA512 cd0ff31abec3b85e3114546918c9152360e3da45fbbaf7b4c76a13a6d288f1d9ea7a4633638080cd0205cc293b4123445106e9b5daddb2ae379d6a08d1c992a5
31 DIST nltk-shakespeare-20200312.zip 475458 BLAKE2B c60acbf2d90f5fffdae43bdf85191dbd694ec5ae19e37b145ad04af6d8481988f0c2ce644baff2e31707e86d95a9b3b03c1da4faaa46be92da2291cce565955e SHA512 72cbbdb237b78df1f6bf27b5504606f805433746b9862dd1ce544ab712783a41fb165f3a4f282a7f1bd58c7dfe6036c14ecb07a82c109f6d326eb95e470002fb
32 -DIST nltk-sinica_treebank-20200312.zip 899237 BLAKE2B e074dbdc7f1fe5958109f8ea019bead946bd2e3cd1c0849cf3ad49eaa34a1989baee7935a70e9103c121e5d375954d1dc53e4a1599e394ce6c2fda4e98769645 SHA512 724fb0905cbd0f903c3a75d70aee8a3e6f29e62971c1501efd8bfb3f4c6619e5fd8a285648e7792ea8e86bbda0a2afc6eecae45ad9f361983bf83b756ab52960
33 DIST nltk-sinica_treebank-20211221.zip 906706 BLAKE2B 0c00bc7d39765b86eb99f55e82522d390cf0270fd2e2688d5825481b6f11e54aaa71b3f9ac95af170be543353746777da130bb6b294b0529330c712f9edaaab8 SHA512 22d44e23e89691f775a0e54971fada692aecd7cfa5181d49e9a53d0a96dc3be1beaa1e1ec6840f9b2756c5c16c93f96b571f6b08c175701485afc0c32261cac8
34 DIST nltk-smultron-20200312.zip 166207 BLAKE2B d0c3e75dd108965e260d913e0c02137da8707a751a4f53a1f59ff6a26af9997e2f0193980b5087277b87b74d9aab3e3c8d066d7264311cec2a94f0f9d21caf44 SHA512 8872717994269caff4ccf3f52cef273b2ef007efeb8ab89392cb4db3b8e3ba4b8859ab2fd70762b8941bee4558aebba3021869772be17a64e1056968aa605e19
35 DIST nltk-snowball_data-20200312.zip 6785405 BLAKE2B 44c10439b142540ac7eece967efa1431fd8f45342f0a90875dacf29ad374fe4c7d30af11d42ba45e0f1ec1836d56b2ff684ee352c5e8536cfb5db5eb7632285b SHA512 6c8a9259d88f6f7f499867d83b731de99d7fa4e8827ecedf836f653fc1a810efa9f6c5c6e2720a9e6610bc00978956b6a119bd08b70e3e241c4e9faccddd81d8
36 @@ -106,7 +104,6 @@ DIST nltk-wmt15_eval-20200312.zip 383096 BLAKE2B 119943db4240171077569b3302c6786
37 DIST nltk-word2vec_sample-20200312.zip 49396025 BLAKE2B 0512b9bb7121a528190079f578e82b4e8f8021bfc0062cfa5613d260f3eee17460aecfeaacb65d950e79d27a653c78633a88c3638ec16377e2dbc3006387ebaa SHA512 09c30a4ab8f9fb6a5b36974b5953260d01cb4f285827fb90a374d054ad775ac978602ab56c452f46f4f8601312e232fd739d2f54dafa44ab8b7b01831cf0d9d1
38 DIST nltk-wordnet-20200312.zip 10775600 BLAKE2B dac56a8fb1fa6882b1871c394ad2acb2d3be739c424570e27c89fb6983df5f896a8f359092ba82752ddfc0531d83563a219e85f80124202f29bda93181efe4dc SHA512 1923a8bcd56fa0b9a9de91f53070dce28c3a7efbab11d2ef55c87134b1bf30de0f40abab59c39eb15dce54aec9491d8a5a259de212ff4cb25cde0ad09317009a
39 DIST nltk-wordnet2021-20211221.zip 11332750 BLAKE2B f4296728b803ef5a48cf312e2dd1471e8a240a0486e0c45b13c4c9998b8577ac30f87d151ffb2957e319e2b7b82706eba82b7b21530bfb3600d7cff2f4aefa0b SHA512 f27e847e0fd3fda83848af8bf94793d0e89c5f89b7868e222ba60be59122587f524e124e9d84f0b904b3a48808aae1c7d849f5851e2f3119ec99b3c30baac400
40 -DIST nltk-wordnet31-20211023.zip 11055271 BLAKE2B e41a1951af5a71c9506d1e948b860574c94ab0ef31c1789a7e7bfb29c6dccea5b1d8895007631f7b595e9f90306365b5042e7a80dc6e1364fdbf4a5f0cba3b28 SHA512 a86091bd55e3a706892550b232be8f5199092623f1f8305d8c9be967a8527fe7d4ecb6250c369b229fdf52b6f3008106b758adc355fa2ad08b5b0cf2a458c173
41 DIST nltk-wordnet31-20211221.zip 11058667 BLAKE2B fb2dca62f602e05226dd62802f42e5f74d11cc535e71b1dc634a202a8c52a7912b1eb0b71edb3c564520c7c05251d9a9928abe88398b816a43035a6db4bda1b3 SHA512 dffea47ded52a042594dced94bc877686d78e6dc9d5a9db5f2a1718190f411cc991b04028d0a4407a8354afd695258e2a5ae881d5f6d9eaf0c3d30de1a8cbf96
42 DIST nltk-wordnet_ic-20200312.zip 12056682 BLAKE2B c2dc2a646015b23699a72f636b588ec5718c70e6941d9d56863257e1e0396c8cf59ac1dc6ed74e5d7f0c2ee9129d63221a03967bf66a3d335e99160f295ed44d SHA512 1c94451a13af6c76bff60a0cab2e70402a3d9abd2e8fc62a5473f24ab4229feb0afe4faa8d389734697a6cf86d2c8b1dc700bb3afa3cbc279b75d7e0ec19fc6d
43 DIST nltk-words-20200312.zip 757777 BLAKE2B eaaaaab6c26e206e9b6ce45daf779e3cc6706a06132afeabf013026d0009caee2d678f3c4ea9125b9654f7143bef29ec7a5706b79e5650ea556c6821b7754e6f SHA512 2810f05d3fc7ee6b6f8636fa1ff7b4e8c8cdac12b415cc54d15c69102290122ea138ec4fa36cb483f790c1ac10b0f83ae4c2c3e0e8df7e67e90e962ee5dbb0be
44
45 diff --git a/dev-python/nltk-data/nltk-data-20211023.ebuild b/dev-python/nltk-data/nltk-data-20211023.ebuild
46 deleted file mode 100644
47 index df8437c785be..000000000000
48 --- a/dev-python/nltk-data/nltk-data-20211023.ebuild
49 +++ /dev/null
50 @@ -1,203 +0,0 @@
51 -# Copyright 2020-2021 Gentoo Authors
52 -# Distributed under the terms of the GNU General Public License v2
53 -
54 -EAPI=7
55 -
56 -inherit check-reqs
57 -
58 -DESCRIPTION="Data files for NLTK"
59 -HOMEPAGE="https://www.nltk.org/nltk_data/"
60 -
61 -# at least some of the files have poorly documented licenses
62 -# TODO: create a USE flag for free-ish subset
63 -LICENSE="all-rights-reserved"
64 -SLOT="0"
65 -KEYWORDS="amd64 x86"
66 -IUSE="extra"
67 -RESTRICT="bindist mirror"
68 -
69 -BDEPEND="app-arch/unzip"
70 -
71 -PACKAGES_ZIP_2020=(
72 - # wget -O - https://www.nltk.org/nltk_data/ | xml sel -t -m '//package[@unzip=0]' -v @subdir -o "/" -v @id -n - | sort
73 - corpora/comtrans
74 - corpora/conll2007
75 - corpora/jeita
76 - corpora/knbc
77 - corpora/machado
78 - corpora/masc_tagged
79 - corpora/nombank.1.0
80 - corpora/panlex_swadesh
81 - corpora/propbank
82 - corpora/reuters
83 - corpora/semcor
84 - corpora/universal_treebanks_v20
85 - sentiment/vader_lexicon
86 - stemmers/snowball_data
87 -)
88 -
89 -PACKAGES_UNPACK_2020=(
90 - # wget -O - https://www.nltk.org/nltk_data/ | xml sel -t -m '//package[@unzip=1]' -v @subdir -o "/" -v @id -n - | sort
91 - corpora/abc
92 - corpora/alpino
93 - corpora/brown
94 - corpora/cess_cat
95 - corpora/cess_esp
96 - corpora/chat80
97 - corpora/city_database
98 - corpora/cmudict
99 - corpora/comparative_sentences
100 - corpora/conll2000
101 - corpora/conll2002
102 - corpora/crubadan
103 - corpora/dependency_treebank
104 - corpora/dolch
105 - corpora/europarl_raw
106 - corpora/floresta
107 - corpora/framenet_v15
108 - corpora/framenet_v17
109 - corpora/gazetteers
110 - corpora/genesis
111 - corpora/gutenberg
112 - corpora/ieer
113 - corpora/inaugural
114 - corpora/indian
115 - corpora/lin_thesaurus
116 - corpora/mac_morpho
117 - corpora/movie_reviews
118 - corpora/mte_teip5
119 - corpora/names
120 - corpora/nonbreaking_prefixes
121 - corpora/nps_chat
122 - corpora/omw
123 - corpora/opinion_lexicon
124 - corpora/pl196x
125 - corpora/ppattach
126 - corpora/product_reviews_1
127 - corpora/product_reviews_2
128 - corpora/pros_cons
129 - corpora/ptb
130 - corpora/qc
131 - corpora/rte
132 - corpora/senseval
133 - corpora/sentence_polarity
134 - corpora/sentiwordnet
135 - corpora/shakespeare
136 - corpora/sinica_treebank
137 - corpora/state_union
138 - corpora/subjectivity
139 - corpora/swadesh
140 - corpora/switchboard
141 - corpora/timit
142 - corpora/toolbox
143 - corpora/treebank
144 - corpora/twitter_samples
145 - corpora/udhr
146 - corpora/udhr2
147 - corpora/verbnet
148 - corpora/webtext
149 - corpora/wordnet
150 - corpora/wordnet_ic
151 - corpora/words
152 - grammars/book_grammars
153 - grammars/large_grammars
154 - grammars/sample_grammars
155 - misc/perluniprops
156 - models/bllip_wsj_no_aux
157 - models/moses_sample
158 - models/wmt15_eval
159 - models/word2vec_sample
160 - stemmers/porter_test
161 - stemmers/rslp
162 - taggers/averaged_perceptron_tagger
163 - taggers/averaged_perceptron_tagger_ru
164 - taggers/universal_tagset
165 - tokenizers/punkt
166 -)
167 -
168 -PACKAGES_UNPACK_2021=(
169 - corpora/stopwords
170 - corpora/wordnet31
171 -)
172 -
173 -PACKAGES_UNPACK_EXTRA_2020=(
174 - chunkers/maxent_ne_chunker
175 - corpora/biocreative_ppi
176 - corpora/brown_tei
177 - corpora/kimmo
178 - corpora/paradigms
179 - corpora/pe08
180 - corpora/pil
181 - corpora/problem_reports
182 - corpora/smultron
183 - corpora/unicode_samples
184 - corpora/verbnet3
185 - corpora/ycoe
186 - grammars/basque_grammars
187 - grammars/spanish_grammars
188 - help/tagsets
189 - misc/mwa_ppdb
190 - taggers/maxent_treebank_pos_tagger
191 -)
192 -
193 -add_data() {
194 - local x version=${1}
195 - shift
196 -
197 - for x; do
198 - SRC_URI+="
199 - https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages/${x}.zip
200 - -> nltk-${x#*/}-${version}.zip"
201 - done
202 -}
203 -
204 -add_data 20200312 "${PACKAGES_ZIP_2020[@]}" "${PACKAGES_UNPACK_2020[@]}"
205 -add_data 20211023 "${PACKAGES_UNPACK_2021[@]}"
206 -SRC_URI+="
207 - extra? ("
208 -add_data 20200312 "${PACKAGES_UNPACK_EXTRA_2020[@]}"
209 -SRC_URI+="
210 - )"
211 -
212 -CHECKREQS_DISK_USR=3G
213 -CHECKREQS_DISK_BUILD=${CHECKREQS_DISK_USR}
214 -
215 -unpack_data() {
216 - local x version=${1}
217 - shift
218 -
219 - for x; do
220 - local cat=${x%/*}
221 - local pkg=${x#*/}
222 -
223 - mkdir -p "${S}/${cat}" || die
224 - cd "${S}/${cat}" || die
225 - unpack "nltk-${pkg}-${version}.zip"
226 - done
227 -}
228 -
229 -src_unpack() {
230 - unpack_data 20200312 "${PACKAGES_UNPACK_2020[@]}"
231 - unpack_data 20211023 "${PACKAGES_UNPACK_2021[@]}"
232 - use extra && unpack_data 20200312 "${PACKAGES_UNPACK_EXTRA_2020[@]}"
233 -}
234 -
235 -install_zips() {
236 - local x version=${1}
237 - shift
238 -
239 - for x; do
240 - local cat=${x%/*}
241 - local pkg=${x#*/}
242 -
243 - insinto "/usr/share/nltk_data/${cat}"
244 - newins "${DISTDIR}/nltk-${pkg}-${version}.zip" "${pkg}.zip"
245 - done
246 -}
247 -
248 -src_install() {
249 - dodir /usr/share/nltk_data
250 - mv * "${ED}/usr/share/nltk_data/" || die
251 -
252 - install_zips 20200312 "${PACKAGES_ZIP_2020[@]}"
253 -}