Loading bolzano-address-trees/download_prepare.sh 0 → 100755 +33 −0 Original line number Diff line number Diff line #!/bin/bash # file: prepare_data.sh # # Program: Downloads and prepares data containing the address trees of Bolzano. # # Author: Thomas Huetter # create target folder and change into it mkdir bolzano-address-trees cd bolzano-address-trees # download the data files wget https://dbresearch.uni-salzburg.at/projects/pq-gram-ordered-labeled-trees/bolzano-address-trees.zip # unzip the data into folder bolzano-address-trees unzip bolzano-address-trees.zip -d original_data # remove zip file rm -rf unzip bolzano-address-trees.zip # change to unzipped folder 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 # 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 "{") iconv -f ISO-8859-1 -t "UTF-8" R.trees | tail -n +14 | sed 's/.*://' | awk '{print gsub("{","{"), $0}' | sort -n | cut -d' ' -f2- > ../R_preprocessed.txt # go back to the folder cd .. No newline at end of file Loading
bolzano-address-trees/download_prepare.sh 0 → 100755 +33 −0 Original line number Diff line number Diff line #!/bin/bash # file: prepare_data.sh # # Program: Downloads and prepares data containing the address trees of Bolzano. # # Author: Thomas Huetter # create target folder and change into it mkdir bolzano-address-trees cd bolzano-address-trees # download the data files wget https://dbresearch.uni-salzburg.at/projects/pq-gram-ordered-labeled-trees/bolzano-address-trees.zip # unzip the data into folder bolzano-address-trees unzip bolzano-address-trees.zip -d original_data # remove zip file rm -rf unzip bolzano-address-trees.zip # change to unzipped folder 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 # 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 "{") iconv -f ISO-8859-1 -t "UTF-8" R.trees | tail -n +14 | sed 's/.*://' | awk '{print gsub("{","{"), $0}' | sort -n | cut -d' ' -f2- > ../R_preprocessed.txt # go back to the folder cd .. No newline at end of file