Loading bolzano-address-trees/download_prepare.sh +2 −2 Original line number Diff line number Diff line Loading @@ -22,8 +22,8 @@ rm -rf unzip bolzano-address-trees.zip cd original_data # prepare data for file L.trees # remove header | remove IDs | sort by number of nodes (equivalent to number of "{") tail -n +14 L.trees | sed 's/.*://' | awk '{print gsub("{","{"), $0}' | sort -n | cut -d' ' -f2- > ../L_preprocessed.txt # convert file into UTF-8 format | remove header | remove IDs | sort by number of nodes (equivalent to number of "{") iconv -f ISO-8859-1 -t "UTF-8" L.trees | tail -n +14 | sed 's/.*://' | awk '{print gsub("{","{"), $0}' | sort -n | cut -d' ' -f2- > ../L_preprocessed.txt # prepare data for file R.trees # convert file into UTF-8 format | remove header | remove IDs | sort by number of nodes (equivalent to number of "{") Loading Loading
bolzano-address-trees/download_prepare.sh +2 −2 Original line number Diff line number Diff line Loading @@ -22,8 +22,8 @@ rm -rf unzip bolzano-address-trees.zip cd original_data # prepare data for file L.trees # remove header | remove IDs | sort by number of nodes (equivalent to number of "{") tail -n +14 L.trees | sed 's/.*://' | awk '{print gsub("{","{"), $0}' | sort -n | cut -d' ' -f2- > ../L_preprocessed.txt # convert file into UTF-8 format | remove header | remove IDs | sort by number of nodes (equivalent to number of "{") iconv -f ISO-8859-1 -t "UTF-8" L.trees | tail -n +14 | sed 's/.*://' | awk '{print gsub("{","{"), $0}' | sort -n | cut -d' ' -f2- > ../L_preprocessed.txt # prepare data for file R.trees # convert file into UTF-8 format | remove header | remove IDs | sort by number of nodes (equivalent to number of "{") Loading