Commit b308386d by John Jarvis

Merge pull request #559 from edx/jarv/nltk-download

switch to s3 download for nltk
parents 3f928dbc 7ef098f6
...@@ -31,6 +31,8 @@ discern_ease_pre_requirements_file: "{{ discern_ease_code_dir }}/pre-requirement ...@@ -31,6 +31,8 @@ discern_ease_pre_requirements_file: "{{ discern_ease_code_dir }}/pre-requirement
discern_ease_post_requirements_file: "{{ discern_ease_code_dir }}/requirements.txt" discern_ease_post_requirements_file: "{{ discern_ease_code_dir }}/requirements.txt"
discern_nltk_data_dir: "{{ discern_data_dir}}/nltk_data" discern_nltk_data_dir: "{{ discern_data_dir}}/nltk_data"
discern_nltk_download_url: http://edx-static.s3.amazonaws.com/nltk/nltk-data-20131113.tar.gz
discern_nltk_tmp_file: "{{ discern_nltk_data_dir }}/nltk.tmp.tar.tz"
discern_source_repo: https://github.com/edx/discern.git discern_source_repo: https://github.com/edx/discern.git
discern_settings: discern.aws discern_settings: discern.aws
......
...@@ -71,17 +71,22 @@ ...@@ -71,17 +71,22 @@
tags: tags:
- deploy - deploy
#Needed for the ease package to work - name: discern | download and install nltk
- name: discern | install nltk data using rendered shell script shell: |
shell: > set -e
{{ discern_venv_dir }}/bin/python -m nltk.downloader -d {{ discern_nltk_data_dir }} all curl -o {{ discern_nltk_tmp_file }} {{ discern_nltk_download_url }}
creates={{ discern_nltk_data_dir }}/taggers/maxent_treebank_pos_tagger/english.pickle tar zxf {{ discern_nltk_tmp_file }}
rm -f {{ discern_nltk_tmp_file }}
touch {{ discern_nltk_download_url|basename }}-installed
creates={{ discern_data_dir }}/{{ discern_nltk_download_url|basename }}-installed
chdir={{ discern_data_dir }}
sudo_user: "{{ discern_user }}" sudo_user: "{{ discern_user }}"
notify: notify:
- discern | restart discern - discern | restart discern
tags: tags:
- deploy - deploy
#Run this instead of using the ansible module because the ansible module only support syncdb of these three, and does not #Run this instead of using the ansible module because the ansible module only support syncdb of these three, and does not
#support virtualenvs as of this comment #support virtualenvs as of this comment
- name: discern | django syncdb migrate and collectstatic for discern - name: discern | django syncdb migrate and collectstatic for discern
......
...@@ -12,6 +12,9 @@ ora_user: "ora" ...@@ -12,6 +12,9 @@ ora_user: "ora"
ora_deploy_path: "{{ ora_venv_bin }}:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin" ora_deploy_path: "{{ ora_venv_bin }}:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin"
ora_nltk_data_dir: "{{ ora_data_dir}}/nltk_data" ora_nltk_data_dir: "{{ ora_data_dir}}/nltk_data"
ora_nltk_download_url: http://edx-static.s3.amazonaws.com/nltk/nltk-data-20131113.tar.gz
ora_nltk_tmp_file: "{{ ora_nltk_data_dir }}/nltk.tmp.tar.tz"
ora_source_repo: https://github.com/edx/edx-ora.git ora_source_repo: https://github.com/edx/edx-ora.git
ora_version: 'master' ora_version: 'master'
ora_pre_requirements_file: "{{ ora_code_dir }}/pre-requirements.txt" ora_pre_requirements_file: "{{ ora_code_dir }}/pre-requirements.txt"
......
...@@ -48,10 +48,15 @@ ...@@ -48,10 +48,15 @@
tags: tags:
- deploy - deploy
- name: ora | install nltk data using rendered shell script - name: ora | download and install nltk
command: > shell: |
"{{ora_ease_venv_dir}}/bin/python -m nltk.downloader -d {{ ora_nltk_data_dir }} all" set -e
creates={{ ora_nltk_data_dir }}/taggers/maxent_treebank_pos_tagger/english.pickle curl -o {{ ora_nltk_tmp_file }} {{ ora_nltk_download_url }}
tar zxf {{ ora_nltk_tmp_file }}
rm -f {{ ora_nltk_tmp_file }}
touch {{ ora_nltk_download_url|basename }}-installed
creates={{ ora_data_dir }}/{{ ora_nltk_download_url|basename }}-installed
chdir={{ ora_data_dir }}
sudo_user: "{{ common_web_user }}" sudo_user: "{{ common_web_user }}"
notify: notify:
- ora | restart ora - ora | restart ora
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment