Sign inSign up

everpeace/word2vec-jawiki:0.1.0

Manifest digest

sha256:a946cb37f34b3c3c32dd2057c98595a479285d0f563b4f65109f511758fcb5b0

OS/ARCH

linux/amd64

Compressed size

620.98 MB

Last pushed

about 10 years by everpeace

Type

Image

Manifest digest

sha256:a946cb37f34b3c3c32dd2057c98595a479285d0f563b4f65109f511758fcb5b0

Image Layers

1ADD file ... in /2.2 MB
2MAINTAINER Shingo Omura <[email protected]>0 B
3ENV dep_pkgs=curl git bash0 B
4ENV MECAB_VERSION=0.9960 B
5ENV IPADIC_VERSION=2.7.0-200708010 B
6ENV WORD2VEC_GIT_BRANCH=master0 B
7ENV CONVERTVEC_GIT_BRANCH=master0 B
8ENV WP2TEXT_VERSION=0.8.00 B
9ENV mecab_url=https://drive.google.com/uc?export=download&id=0B4y35FiV1wh7cENtOXlicTFaRUE0 B
10ENV ipadic_url=https://drive.google.com/uc?export=download&id=0B4y35FiV1wh7MWVlSDBCSXZMTXM0 B
11ENV word2vec_git_url=https://github.com/svn2github/word2vec.git0 B
12ENV convertvec_git_url=https://github.com/marekrei/convertvec0 B
13ENV WP2TXT_OPTIONS=-f 990 B
14ENV MECAB_REPROCESS=00 B
15ENV MECAB_OPTIONS=-d /usr/local/lib/mecab/dic/mecab-ipadic-neologd/ -b0 B
16ENV WORD2VEC_OPTIONS=-cbow 0 -size0 B
17ENV JAWIKI_URL=https://dumps.wikimedia.org/jawiki/latest/jawiki-latest-pages-articles.xml.bz20 B
18ENV JAWIKI_FILENAME=jawiki-pages-articles.xml.bz20 B
19ENV OUTPUT_DIR=/var/jawiki0 B
20/bin/sh -c apk add --update44.02 MB
21/bin/sh -c apk add --update19.47 MB
22/bin/sh -c curl -SL -o4.91 MB
23/bin/sh -c curl -SL -o48.02 MB
24/bin/sh -c git clone --depth489.06 MB
25/bin/sh -c git clone ${word2vec_git_url}350.23 KB
26/bin/sh -c git clone ${convertvec_git_url}14.6 KB
27/bin/sh -c gem install wp2txt12.94 MB
28ADD file ... in ./ 1.11 KB
29/bin/sh -c chmod +x build-embedding-jawiki.sh0 B
30/bin/sh -c rm -rf 224 B
31/bin/sh -c which mecab &&0 B
32/bin/sh -c which word2vec &&0 B
33/bin/sh -c which wp2txt &&0 B
34/bin/sh -c which convertvec &&0 B
35VOLUME [/var/jawiki]0 B
36CMD ["/bin/sh" "-c" "/build-embedding-jawiki.sh"]0 B

Command

ADD file:852e9d0cb9d906535af512a89339fc70b2873a0f94defbcbe41cd44942dd6ac8 in /