Skip to content

Commit 896ae47

Browse files
authored
Merge branch 'gh-pages' into gh-pages
2 parents 697e82a + 9c90384 commit 896ae47

File tree

7 files changed

+613
-522
lines changed

7 files changed

+613
-522
lines changed

Makefile

+1
Original file line numberDiff line numberDiff line change
@@ -2,6 +2,7 @@ PYTHON = python3
22
BASEURL = https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/packages
33

44
pkg_index:
5+
$(PYTHON) tools/build_collections.py .
56
$(PYTHON) tools/build_pkg_index.py . $(BASEURL) index.xml
67
git add index.xml
78
git commit -m "updated data index" index.xml

collections/all-corpora.xml

+89-77
Original file line numberDiff line numberDiff line change
@@ -1,78 +1,90 @@
11
<collection id="all-corpora" name="All the corpora">
2-
<item ref="abc"/>
3-
<item ref="alpino"/>
4-
<item ref="biocreative_ppi"/>
5-
<item ref="brown"/>
6-
<item ref="brown_tei"/>
7-
<item ref="cess_cat"/>
8-
<item ref="cess_esp"/>
9-
<item ref="chat80"/>
10-
<item ref="city_database"/>
11-
<item ref="cmudict"/>
12-
<item ref="comtrans"/>
13-
<item ref="conll2000"/>
14-
<item ref="conll2002"/>
15-
<item ref="conll2007"/>
16-
<item ref="crubadan"/>
17-
<item ref="dependency_treebank"/>
18-
<item ref="dolch"/>
19-
<item ref="floresta"/>
20-
<item ref="framenet_v15"/>
21-
<item ref="framenet_v17"/>
22-
<item ref="gazetteers"/>
23-
<item ref="genesis"/>
24-
<item ref="gutenberg"/>
25-
<item ref="ieer"/>
26-
<item ref="inaugural"/>
27-
<item ref="indian"/>
28-
<item ref="jeita"/>
29-
<item ref="kimmo"/>
30-
<item ref="knbc"/>
31-
<item ref="lin_thesaurus"/>
32-
<item ref="mac_morpho"/>
33-
<item ref="machado"/>
34-
<item ref="masc_tagged"/>
35-
<item ref="movie_reviews"/>
36-
<item ref="names"/>
37-
<item ref="nombank.1.0"/>
38-
<item ref="nps_chat"/>
39-
<item ref="omw"/>
40-
<item ref="paradigms"/>
41-
<item ref="pil"/>
42-
<item ref="pl196x"/>
43-
<item ref="ppattach"/>
44-
<item ref="problem_reports"/>
45-
<item ref="propbank"/>
46-
<item ref="ptb"/>
47-
<item ref="qc"/>
48-
<item ref="reuters"/>
49-
<item ref="rte"/>
50-
<item ref="semcor"/>
51-
<item ref="senseval"/>
52-
<item ref="sentiwordnet"/>
53-
<item ref="shakespeare"/>
54-
<item ref="sinica_treebank"/>
55-
<item ref="state_union"/>
56-
<item ref="stopwords"/>
57-
<item ref="swadesh"/>
58-
<item ref="switchboard"/>
59-
<item ref="timit"/>
60-
<item ref="toolbox"/>
61-
<item ref="treebank"/>
62-
<item ref="udhr"/>
63-
<item ref="udhr2"/>
64-
<item ref="unicode_samples"/>
65-
<item ref="universal_treebanks_v20"/>
66-
<item ref="verbnet"/>
67-
<item ref="verbnet3"/>
68-
<item ref="webtext"/>
69-
<item ref="wordnet"/>
70-
<item ref="wordnet31"/>
71-
<item ref="wordnet_ic"/>
72-
<item ref="words"/>
73-
<item ref="ycoe"/>
74-
<item ref="panlex_swadesh"/>
75-
<item ref="mte_teip5"/>
76-
<item ref="nonbreaking_prefixes"/>
77-
</collection>
78-
2+
<item ref="abc" />
3+
<item ref="alpino" />
4+
<item ref="biocreative_ppi" />
5+
<item ref="brown" />
6+
<item ref="brown_tei" />
7+
<item ref="cess_cat" />
8+
<item ref="cess_esp" />
9+
<item ref="chat80" />
10+
<item ref="city_database" />
11+
<item ref="cmudict" />
12+
<item ref="comparative_sentences" />
13+
<item ref="comtrans" />
14+
<item ref="conll2000" />
15+
<item ref="conll2002" />
16+
<item ref="conll2007" />
17+
<item ref="crubadan" />
18+
<item ref="dependency_treebank" />
19+
<item ref="dolch" />
20+
<item ref="europarl_raw" />
21+
<item ref="floresta" />
22+
<item ref="framenet_v15" />
23+
<item ref="framenet_v17" />
24+
<item ref="gazetteers" />
25+
<item ref="genesis" />
26+
<item ref="gutenberg" />
27+
<item ref="ieer" />
28+
<item ref="inaugural" />
29+
<item ref="indian" />
30+
<item ref="jeita" />
31+
<item ref="kimmo" />
32+
<item ref="knbc" />
33+
<item ref="lin_thesaurus" />
34+
<item ref="mac_morpho" />
35+
<item ref="machado" />
36+
<item ref="masc_tagged" />
37+
<item ref="movie_reviews" />
38+
<item ref="mte_teip5" />
39+
<item ref="names" />
40+
<item ref="nombank.1.0" />
41+
<item ref="nonbreaking_prefixes" />
42+
<item ref="nps_chat" />
43+
<item ref="omw" />
44+
<item ref="omw-1.4" />
45+
<item ref="opinion_lexicon" />
46+
<item ref="panlex_swadesh" />
47+
<item ref="paradigms" />
48+
<item ref="pe08" />
49+
<item ref="pil" />
50+
<item ref="pl196x" />
51+
<item ref="ppattach" />
52+
<item ref="problem_reports" />
53+
<item ref="product_reviews_1" />
54+
<item ref="product_reviews_2" />
55+
<item ref="propbank" />
56+
<item ref="pros_cons" />
57+
<item ref="ptb" />
58+
<item ref="qc" />
59+
<item ref="reuters" />
60+
<item ref="rte" />
61+
<item ref="semcor" />
62+
<item ref="senseval" />
63+
<item ref="sentence_polarity" />
64+
<item ref="sentiwordnet" />
65+
<item ref="shakespeare" />
66+
<item ref="sinica_treebank" />
67+
<item ref="smultron" />
68+
<item ref="state_union" />
69+
<item ref="stopwords" />
70+
<item ref="subjectivity" />
71+
<item ref="swadesh" />
72+
<item ref="switchboard" />
73+
<item ref="timit" />
74+
<item ref="toolbox" />
75+
<item ref="treebank" />
76+
<item ref="twitter_samples" />
77+
<item ref="udhr" />
78+
<item ref="udhr2" />
79+
<item ref="unicode_samples" />
80+
<item ref="universal_treebanks_v20" />
81+
<item ref="verbnet" />
82+
<item ref="verbnet3" />
83+
<item ref="webtext" />
84+
<item ref="wordnet" />
85+
<item ref="wordnet2021" />
86+
<item ref="wordnet31" />
87+
<item ref="wordnet_ic" />
88+
<item ref="words" />
89+
<item ref="ycoe" />
90+
</collection>

collections/all-nltk.xml

+111-107
Original file line numberDiff line numberDiff line change
@@ -1,108 +1,112 @@
11
<collection id="all-nltk" name="All packages available on nltk_data gh-pages branch">
2-
<item ref="abc"/>
3-
<item ref="alpino"/>
4-
<item ref="biocreative_ppi"/>
5-
<item ref="brown"/>
6-
<item ref="brown_tei"/>
7-
<item ref="cess_cat"/>
8-
<item ref="cess_esp"/>
9-
<item ref="chat80"/>
10-
<item ref="city_database"/>
11-
<item ref="cmudict"/>
12-
<item ref="comparative_sentences"/>
13-
<item ref="comtrans"/>
14-
<item ref="conll2000"/>
15-
<item ref="conll2002"/>
16-
<item ref="conll2007"/>
17-
<item ref="crubadan"/>
18-
<item ref="dependency_treebank"/>
19-
<item ref="europarl_raw"/>
20-
<item ref="floresta"/>
21-
<item ref="framenet_v15"/>
22-
<item ref="framenet_v17"/>
23-
<item ref="gazetteers"/>
24-
<item ref="genesis"/>
25-
<item ref="gutenberg"/>
26-
<item ref="ieer"/>
27-
<item ref="inaugural"/>
28-
<item ref="indian"/>
29-
<item ref="jeita"/>
30-
<item ref="kimmo"/>
31-
<item ref="knbc"/>
32-
<item ref="lin_thesaurus"/>
33-
<item ref="mac_morpho"/>
34-
<item ref="machado"/>
35-
<item ref="masc_tagged"/>
36-
<item ref="moses_sample"/>
37-
<item ref="movie_reviews"/>
38-
<item ref="names"/>
39-
<item ref="nombank.1.0"/>
40-
<item ref="nps_chat"/>
41-
<item ref="omw"/>
42-
<item ref="opinion_lexicon"/>
43-
<item ref="paradigms"/>
44-
<item ref="pil"/>
45-
<item ref="pl196x"/>
46-
<item ref="ppattach"/>
47-
<item ref="problem_reports"/>
48-
<item ref="propbank"/>
49-
<item ref="ptb"/>
50-
<item ref="product_reviews_1"/>
51-
<item ref="product_reviews_2"/>
52-
<item ref="pros_cons"/>
53-
<item ref="qc"/>
54-
<item ref="reuters"/>
55-
<item ref="rte"/>
56-
<item ref="semcor"/>
57-
<item ref="senseval"/>
58-
<item ref="sentiwordnet"/>
59-
<item ref="sentence_polarity"/>
60-
<item ref="shakespeare"/>
61-
<item ref="sinica_treebank"/>
62-
<item ref="smultron"/>
63-
<item ref="state_union"/>
64-
<item ref="stopwords"/>
65-
<item ref="subjectivity"/>
66-
<item ref="swadesh"/>
67-
<item ref="switchboard"/>
68-
<item ref="timit"/>
69-
<item ref="toolbox"/>
70-
<item ref="treebank"/>
71-
<item ref="twitter_samples"/>
72-
<item ref="udhr"/>
73-
<item ref="udhr2"/>
74-
<item ref="unicode_samples"/>
75-
<item ref="universal_treebanks_v20"/>
76-
<item ref="verbnet"/>
77-
<item ref="verbnet3"/>
78-
<item ref="webtext"/>
79-
<item ref="wordnet"/>
80-
<item ref="wordnet31"/>
81-
<item ref="wordnet_ic"/>
82-
<item ref="words"/>
83-
<item ref="ycoe"/>
84-
<item ref="rslp"/>
85-
<item ref="maxent_treebank_pos_tagger"/>
86-
<item ref="universal_tagset"/>
87-
<item ref="maxent_ne_chunker"/>
88-
<item ref="punkt"/>
89-
<item ref="book_grammars"/>
90-
<item ref="sample_grammars"/>
91-
<item ref="spanish_grammars"/>
92-
<item ref="basque_grammars"/>
93-
<item ref="large_grammars"/>
94-
<item ref="tagsets"/>
95-
<item ref="snowball_data"/>
96-
<item ref="bllip_wsj_no_aux"/>
97-
<item ref="word2vec_sample"/>
98-
<item ref="panlex_swadesh"/>
99-
<item ref="mte_teip5"/>
100-
<item ref="averaged_perceptron_tagger"/>
101-
<item ref="averaged_perceptron_tagger_ru"/>
102-
<item ref="perluniprops"/>
103-
<item ref="nonbreaking_prefixes"/>
104-
<item ref="vader_lexicon"/>
105-
<item ref="porter_test"/>
106-
<item ref="wmt15_eval"/>
107-
<item ref="mwa_ppdb"/>
108-
</collection>
2+
<item ref="abc" />
3+
<item ref="alpino" />
4+
<item ref="averaged_perceptron_tagger" />
5+
<item ref="averaged_perceptron_tagger_ru" />
6+
<item ref="basque_grammars" />
7+
<item ref="biocreative_ppi" />
8+
<item ref="bllip_wsj_no_aux" />
9+
<item ref="book_grammars" />
10+
<item ref="brown" />
11+
<item ref="brown_tei" />
12+
<item ref="cess_cat" />
13+
<item ref="cess_esp" />
14+
<item ref="chat80" />
15+
<item ref="city_database" />
16+
<item ref="cmudict" />
17+
<item ref="comparative_sentences" />
18+
<item ref="comtrans" />
19+
<item ref="conll2000" />
20+
<item ref="conll2002" />
21+
<item ref="conll2007" />
22+
<item ref="crubadan" />
23+
<item ref="dependency_treebank" />
24+
<item ref="dolch" />
25+
<item ref="europarl_raw" />
26+
<item ref="floresta" />
27+
<item ref="framenet_v15" />
28+
<item ref="framenet_v17" />
29+
<item ref="gazetteers" />
30+
<item ref="genesis" />
31+
<item ref="gutenberg" />
32+
<item ref="ieer" />
33+
<item ref="inaugural" />
34+
<item ref="indian" />
35+
<item ref="jeita" />
36+
<item ref="kimmo" />
37+
<item ref="knbc" />
38+
<item ref="large_grammars" />
39+
<item ref="lin_thesaurus" />
40+
<item ref="mac_morpho" />
41+
<item ref="machado" />
42+
<item ref="masc_tagged" />
43+
<item ref="maxent_ne_chunker" />
44+
<item ref="maxent_treebank_pos_tagger" />
45+
<item ref="moses_sample" />
46+
<item ref="movie_reviews" />
47+
<item ref="mte_teip5" />
48+
<item ref="mwa_ppdb" />
49+
<item ref="names" />
50+
<item ref="nombank.1.0" />
51+
<item ref="nonbreaking_prefixes" />
52+
<item ref="nps_chat" />
53+
<item ref="omw" />
54+
<item ref="omw-1.4" />
55+
<item ref="opinion_lexicon" />
56+
<item ref="panlex_swadesh" />
57+
<item ref="paradigms" />
58+
<item ref="pe08" />
59+
<item ref="perluniprops" />
60+
<item ref="pil" />
61+
<item ref="pl196x" />
62+
<item ref="porter_test" />
63+
<item ref="ppattach" />
64+
<item ref="problem_reports" />
65+
<item ref="product_reviews_1" />
66+
<item ref="product_reviews_2" />
67+
<item ref="propbank" />
68+
<item ref="pros_cons" />
69+
<item ref="ptb" />
70+
<item ref="punkt" />
71+
<item ref="qc" />
72+
<item ref="reuters" />
73+
<item ref="rslp" />
74+
<item ref="rte" />
75+
<item ref="sample_grammars" />
76+
<item ref="semcor" />
77+
<item ref="senseval" />
78+
<item ref="sentence_polarity" />
79+
<item ref="sentiwordnet" />
80+
<item ref="shakespeare" />
81+
<item ref="sinica_treebank" />
82+
<item ref="smultron" />
83+
<item ref="snowball_data" />
84+
<item ref="spanish_grammars" />
85+
<item ref="state_union" />
86+
<item ref="stopwords" />
87+
<item ref="subjectivity" />
88+
<item ref="swadesh" />
89+
<item ref="switchboard" />
90+
<item ref="tagsets" />
91+
<item ref="timit" />
92+
<item ref="toolbox" />
93+
<item ref="treebank" />
94+
<item ref="twitter_samples" />
95+
<item ref="udhr" />
96+
<item ref="udhr2" />
97+
<item ref="unicode_samples" />
98+
<item ref="universal_tagset" />
99+
<item ref="universal_treebanks_v20" />
100+
<item ref="vader_lexicon" />
101+
<item ref="verbnet" />
102+
<item ref="verbnet3" />
103+
<item ref="webtext" />
104+
<item ref="wmt15_eval" />
105+
<item ref="word2vec_sample" />
106+
<item ref="wordnet" />
107+
<item ref="wordnet2021" />
108+
<item ref="wordnet31" />
109+
<item ref="wordnet_ic" />
110+
<item ref="words" />
111+
<item ref="ycoe" />
112+
</collection>

0 commit comments

Comments
 (0)