nltk_data: Import version 20171223

[Min Sik Kim <minskim%NetBSD.org@localhost>]

Module Name:	pkgsrc-wip
Committed By:	Min Sik Kim <minskim%NetBSD.org@localhost>
Pushed By:	minskim
Date:		Thu Feb 1 11:26:56 2018 -0800
Changeset:	be2bb6ce0a67cea528b16578b77c2186b92cc705

Modified Files:
	Makefile
Added Files:
	nltk_data/DESCR
	nltk_data/Makefile
	nltk_data/PLIST
	nltk_data/distinfo

Log Message:
nltk_data: Import version 20171223

NLTK comes with many corpora, toy grammars, trained models, etc. This
package provides the entire collection of the NLTK data.

To see a diff of this commit:
https://wip.pkgsrc.org/cgi-bin/gitweb.cgi?p=pkgsrc-wip.git;a=commitdiff;h=be2bb6ce0a67cea528b16578b77c2186b92cc705

Please note that diffs are not public domain; they are subject to the
copyright notices on the relevant files.

diffstat:
 Makefile           |   1 +
 nltk_data/DESCR    |   2 +
 nltk_data/Makefile |  21 ++++++
 nltk_data/PLIST    | 217 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 nltk_data/distinfo |   6 ++
 5 files changed, 247 insertions(+)

diffs:
diff --git a/Makefile b/Makefile
index 4277c4d730..72ef005438 100644
--- a/Makefile
+++ b/Makefile
@@ -2197,6 +2197,7 @@ SUBDIR+=	ninka
 SUBDIR+=	nios2-gdb
 SUBDIR+=	nitrogen
 SUBDIR+=	njb-sharp
+SUBDIR+=	nltk_data
 SUBDIR+=	nmh
 SUBDIR+=	nnrpd
 SUBDIR+=	nodau
diff --git a/nltk_data/DESCR b/nltk_data/DESCR
new file mode 100644
index 0000000000..2dfbe22fcc
--- /dev/null
+++ b/nltk_data/DESCR
@@ -0,0 +1,2 @@
+NLTK comes with many corpora, toy grammars, trained models, etc. This
+package provides the entire collection of the NLTK data.
diff --git a/nltk_data/Makefile b/nltk_data/Makefile
new file mode 100644
index 0000000000..b403991ced
--- /dev/null
+++ b/nltk_data/Makefile
@@ -0,0 +1,21 @@
+# $NetBSD$
+
+DISTNAME=	nltk_data
+PKGNAME=	${DISTNAME}-20171223
+CATEGORIES=	textproc
+MASTER_SITES=	${MASTER_SITE_GITHUB:=nltk/}
+GITHUB_TAG= 	f3dc1f388b08aa310933dbddf21e12b9fc6b50f1
+
+MAINTAINER=	minskim%NetBSD.org@localhost
+HOMEPAGE=	http://www.nltk.org/nltk_data/
+COMMENT=	Data distribution for NLTK
+
+NO_BUILD=	yes
+USE_TOOLS+=	pax
+
+INSTALLATION_DIRS+=	share/${PKGBASE}
+
+do-install:
+	cd ${WRKSRC}/packages && pax -rw . ${DESTDIR}${PREFIX}/share/${PKGBASE}
+
+.include "../../mk/bsd.pkg.mk"
diff --git a/nltk_data/PLIST b/nltk_data/PLIST
new file mode 100644
index 0000000000..bb6d0d448f
--- /dev/null
+++ b/nltk_data/PLIST
@@ -0,0 +1,217 @@
+@comment $NetBSD$
+share/nltk_data/chunkers/maxent_ne_chunker.xml
+share/nltk_data/chunkers/maxent_ne_chunker.zip
+share/nltk_data/corpora/abc.xml
+share/nltk_data/corpora/abc.zip
+share/nltk_data/corpora/alpino.xml
+share/nltk_data/corpora/alpino.zip
+share/nltk_data/corpora/biocreative_ppi.xml
+share/nltk_data/corpora/biocreative_ppi.zip
+share/nltk_data/corpora/brown.xml
+share/nltk_data/corpora/brown.zip
+share/nltk_data/corpora/brown_tei.xml
+share/nltk_data/corpora/brown_tei.zip
+share/nltk_data/corpora/cess_cat.xml
+share/nltk_data/corpora/cess_cat.zip
+share/nltk_data/corpora/cess_esp.xml
+share/nltk_data/corpora/cess_esp.zip
+share/nltk_data/corpora/chat80.xml
+share/nltk_data/corpora/chat80.zip
+share/nltk_data/corpora/city_database.xml
+share/nltk_data/corpora/city_database.zip
+share/nltk_data/corpora/cmudict.xml
+share/nltk_data/corpora/cmudict.zip
+share/nltk_data/corpora/comparative_sentences.xml
+share/nltk_data/corpora/comparative_sentences.zip
+share/nltk_data/corpora/comtrans.xml
+share/nltk_data/corpora/comtrans.zip
+share/nltk_data/corpora/conll2000.xml
+share/nltk_data/corpora/conll2000.zip
+share/nltk_data/corpora/conll2002.xml
+share/nltk_data/corpora/conll2002.zip
+share/nltk_data/corpora/conll2007.xml
+share/nltk_data/corpora/conll2007.zip
+share/nltk_data/corpora/crubadan.xml
+share/nltk_data/corpora/crubadan.zip
+share/nltk_data/corpora/dependency_treebank.xml
+share/nltk_data/corpora/dependency_treebank.zip
+share/nltk_data/corpora/dolch.xml
+share/nltk_data/corpora/dolch.zip
+share/nltk_data/corpora/europarl_raw.xml
+share/nltk_data/corpora/europarl_raw.zip
+share/nltk_data/corpora/floresta.xml
+share/nltk_data/corpora/floresta.zip
+share/nltk_data/corpora/framenet_v15.xml
+share/nltk_data/corpora/framenet_v15.zip
+share/nltk_data/corpora/framenet_v17.xml
+share/nltk_data/corpora/framenet_v17.zip
+share/nltk_data/corpora/gazetteers.xml
+share/nltk_data/corpora/gazetteers.zip
+share/nltk_data/corpora/genesis.xml
+share/nltk_data/corpora/genesis.zip
+share/nltk_data/corpora/gutenberg.xml
+share/nltk_data/corpora/gutenberg.zip
+share/nltk_data/corpora/ieer.xml
+share/nltk_data/corpora/ieer.zip
+share/nltk_data/corpora/inaugural.xml
+share/nltk_data/corpora/inaugural.zip
+share/nltk_data/corpora/indian.xml
+share/nltk_data/corpora/indian.zip
+share/nltk_data/corpora/jeita.xml
+share/nltk_data/corpora/jeita.zip
+share/nltk_data/corpora/kimmo.xml
+share/nltk_data/corpora/kimmo.zip
+share/nltk_data/corpora/knbc.xml
+share/nltk_data/corpora/knbc.zip
+share/nltk_data/corpora/lin_thesaurus.xml
+share/nltk_data/corpora/lin_thesaurus.zip
+share/nltk_data/corpora/listing.csv
+share/nltk_data/corpora/listing.csv.zip
+share/nltk_data/corpora/mac_morpho.xml
+share/nltk_data/corpora/mac_morpho.zip
+share/nltk_data/corpora/machado.xml
+share/nltk_data/corpora/machado.zip
+share/nltk_data/corpora/masc_tagged.xml
+share/nltk_data/corpora/masc_tagged.zip
+share/nltk_data/corpora/movie_reviews.xml
+share/nltk_data/corpora/movie_reviews.zip
+share/nltk_data/corpora/mte_teip5.xml
+share/nltk_data/corpora/mte_teip5.zip
+share/nltk_data/corpora/names.xml
+share/nltk_data/corpora/names.zip
+share/nltk_data/corpora/nombank.1.0.xml
+share/nltk_data/corpora/nombank.1.0.zip
+share/nltk_data/corpora/nonbreaking_prefixes.xml
+share/nltk_data/corpora/nonbreaking_prefixes.zip
+share/nltk_data/corpora/nps_chat.xml
+share/nltk_data/corpora/nps_chat.zip
+share/nltk_data/corpora/omw.xml
+share/nltk_data/corpora/omw.zip
+share/nltk_data/corpora/opinion_lexicon.xml
+share/nltk_data/corpora/opinion_lexicon.zip
+share/nltk_data/corpora/panlex_swadesh.xml
+share/nltk_data/corpora/panlex_swadesh.zip
+share/nltk_data/corpora/paradigms.xml
+share/nltk_data/corpora/paradigms.zip
+share/nltk_data/corpora/pe08.xml
+share/nltk_data/corpora/pe08.zip
+share/nltk_data/corpora/pil.xml
+share/nltk_data/corpora/pil.zip
+share/nltk_data/corpora/pl196x.xml
+share/nltk_data/corpora/pl196x.zip
+share/nltk_data/corpora/ppattach.xml
+share/nltk_data/corpora/ppattach.zip
+share/nltk_data/corpora/problem_reports.xml
+share/nltk_data/corpora/problem_reports.zip
+share/nltk_data/corpora/product_reviews_1.xml
+share/nltk_data/corpora/product_reviews_1.zip
+share/nltk_data/corpora/product_reviews_2.xml
+share/nltk_data/corpora/product_reviews_2.zip
+share/nltk_data/corpora/propbank.xml
+share/nltk_data/corpora/propbank.zip
+share/nltk_data/corpora/pros_cons.xml
+share/nltk_data/corpora/pros_cons.zip
+share/nltk_data/corpora/ptb.xml
+share/nltk_data/corpora/ptb.zip
+share/nltk_data/corpora/ptb3.zip
+share/nltk_data/corpora/qc.xml
+share/nltk_data/corpora/qc.zip
+share/nltk_data/corpora/reuters.xml
+share/nltk_data/corpora/reuters.zip
+share/nltk_data/corpora/rte.xml
+share/nltk_data/corpora/rte.zip
+share/nltk_data/corpora/semcor.xml
+share/nltk_data/corpora/semcor.zip
+share/nltk_data/corpora/senseval.xml
+share/nltk_data/corpora/senseval.zip
+share/nltk_data/corpora/sentence_polarity.xml
+share/nltk_data/corpora/sentence_polarity.zip
+share/nltk_data/corpora/sentiwordnet.xml
+share/nltk_data/corpora/sentiwordnet.zip
+share/nltk_data/corpora/shakespeare.xml
+share/nltk_data/corpora/shakespeare.zip
+share/nltk_data/corpora/sinica_treebank.xml
+share/nltk_data/corpora/sinica_treebank.zip
+share/nltk_data/corpora/smultron.xml
+share/nltk_data/corpora/smultron.zip
+share/nltk_data/corpora/state_union.xml
+share/nltk_data/corpora/state_union.zip
+share/nltk_data/corpora/stopwords.xml
+share/nltk_data/corpora/stopwords.zip
+share/nltk_data/corpora/subjectivity.xml
+share/nltk_data/corpora/subjectivity.zip
+share/nltk_data/corpora/swadesh.xml
+share/nltk_data/corpora/swadesh.zip
+share/nltk_data/corpora/switchboard.xml
+share/nltk_data/corpora/switchboard.zip
+share/nltk_data/corpora/timit.xml
+share/nltk_data/corpora/timit.zip
+share/nltk_data/corpora/toolbox.xml
+share/nltk_data/corpora/toolbox.zip
+share/nltk_data/corpora/treebank.xml
+share/nltk_data/corpora/treebank.zip
+share/nltk_data/corpora/twitter_samples.xml
+share/nltk_data/corpora/twitter_samples.zip
+share/nltk_data/corpora/udhr.xml
+share/nltk_data/corpora/udhr.zip
+share/nltk_data/corpora/udhr2.xml
+share/nltk_data/corpora/udhr2.zip
+share/nltk_data/corpora/unicode.notes
+share/nltk_data/corpora/unicode_samples.xml
+share/nltk_data/corpora/unicode_samples.zip
+share/nltk_data/corpora/universal_treebanks_v20.xml
+share/nltk_data/corpora/universal_treebanks_v20.zip
+share/nltk_data/corpora/verbnet.xml
+share/nltk_data/corpora/verbnet.zip
+share/nltk_data/corpora/webtext.xml
+share/nltk_data/corpora/webtext.zip
+share/nltk_data/corpora/wordnet.xml
+share/nltk_data/corpora/wordnet.zip
+share/nltk_data/corpora/wordnet_ic.xml
+share/nltk_data/corpora/wordnet_ic.zip
+share/nltk_data/corpora/words.xml
+share/nltk_data/corpora/words.zip
+share/nltk_data/corpora/ycoe.xml
+share/nltk_data/corpora/ycoe.zip
+share/nltk_data/grammars/basque_grammars.xml
+share/nltk_data/grammars/basque_grammars.zip
+share/nltk_data/grammars/book_grammars.xml
+share/nltk_data/grammars/book_grammars.zip
+share/nltk_data/grammars/large_grammars.xml
+share/nltk_data/grammars/large_grammars.zip
+share/nltk_data/grammars/sample_grammars.xml
+share/nltk_data/grammars/sample_grammars.zip
+share/nltk_data/grammars/spanish_grammars.xml
+share/nltk_data/grammars/spanish_grammars.zip
+share/nltk_data/help/tagsets.xml
+share/nltk_data/help/tagsets.zip
+share/nltk_data/misc/mwa_ppdb.xml
+share/nltk_data/misc/mwa_ppdb.zip
+share/nltk_data/misc/perluniprops.xml
+share/nltk_data/misc/perluniprops.zip
+share/nltk_data/models/bllip_wsj_no_aux.xml
+share/nltk_data/models/bllip_wsj_no_aux.zip
+share/nltk_data/models/moses_sample.xml
+share/nltk_data/models/moses_sample.zip
+share/nltk_data/models/wmt15_eval.xml
+share/nltk_data/models/wmt15_eval.zip
+share/nltk_data/models/word2vec_sample.xml
+share/nltk_data/models/word2vec_sample.zip
+share/nltk_data/sentiment/vader_lexicon.xml
+share/nltk_data/sentiment/vader_lexicon.zip
+share/nltk_data/stemmers/porter_test.xml
+share/nltk_data/stemmers/porter_test.zip
+share/nltk_data/stemmers/rslp.xml
+share/nltk_data/stemmers/rslp.zip
+share/nltk_data/stemmers/snowball_data.xml
+share/nltk_data/stemmers/snowball_data.zip
+share/nltk_data/taggers/averaged_perceptron_tagger.xml
+share/nltk_data/taggers/averaged_perceptron_tagger.zip
+share/nltk_data/taggers/averaged_perceptron_tagger_ru.xml
+share/nltk_data/taggers/averaged_perceptron_tagger_ru.zip
+share/nltk_data/taggers/maxent_treebank_pos_tagger.xml
+share/nltk_data/taggers/maxent_treebank_pos_tagger.zip
+share/nltk_data/taggers/universal_tagset.xml
+share/nltk_data/taggers/universal_tagset.zip
+share/nltk_data/tokenizers/punkt.xml
+share/nltk_data/tokenizers/punkt.zip
diff --git a/nltk_data/distinfo b/nltk_data/distinfo
new file mode 100644
index 0000000000..78348314f6
--- /dev/null
+++ b/nltk_data/distinfo
@@ -0,0 +1,6 @@
+$NetBSD$
+
+SHA1 (nltk_data-f3dc1f388b08aa310933dbddf21e12b9fc6b50f1.tar.gz) = 02398d79c34a18a00ca62607493dbb1725b52aca
+RMD160 (nltk_data-f3dc1f388b08aa310933dbddf21e12b9fc6b50f1.tar.gz) = edfa75969cb4212ea93658f4e1e3057312a2016a
+SHA512 (nltk_data-f3dc1f388b08aa310933dbddf21e12b9fc6b50f1.tar.gz) = 30f04a38af90ea109fdf0606ab8de24f426a1426f7ac795a63e1def1e6e04d528429743175e0909b4d21ccce2c9539a6729f89f3e1a7449fc597ecf9822d60dd
+Size (nltk_data-f3dc1f388b08aa310933dbddf21e12b9fc6b50f1.tar.gz) = 668333218 bytes