- Get the latest copy of the articles from wikipedia download page.
> wget http://download.wikimedia.org/enwiki/latest/enwiki-latest-pages-articles.xml.bz2
| # GIT REMOVE FILE FROM ALL BRANCHES | |
| git filter-branch --force --index-filter \ | |
| 'git rm --cached --ignore-unmatch contents.sql' \ | |
| --prune-empty --tag-name-filter cat -- --all | |
| # GIT REMOTE BRANCH FETCH AND CREATE | |
| git checkout --track origin/daves_branch |
| awk 'BEGIN { system("mkdir -p splitted/sub"++j) } | |
| /<doc/{x="F"++i".xml";}{ | |
| if (i%5==0 ){ | |
| ++i; | |
| close("splitted/sub"j"/"x); | |
| system("mkdir -p splitted/sub"++j"/"); | |
| } | |
| else{ | |
| print > ("splitted/sub"j"/"x); |
| Rails.application.assets.logger = Logger.new('/dev/null') | |
| Rails::Rack::Logger.class_eval do | |
| def call_with_quiet_assets(env) | |
| previous_level = Rails.logger.level | |
| Rails.logger.level = Logger::ERROR if env['PATH_INFO'].index("/assets/") == 0 | |
| call_without_quiet_assets(env).tap do | |
| Rails.logger.level = previous_level | |
| end | |
| end | |
| alias_method_chain :call, :quiet_assets |