Tidied up bolzano script.

#!/bin/bash

# file: prepare_data.sh

# The MIT License (MIT)

# Copyright (c) 2017 Thomas Hütter, Mateusz Pawlik.

# 

# Program: Downloads and prepares data containing the address trees of Bolzano.

# Permission is hereby granted, free of charge, to any person obtaining a copy

# of this software and associated documentation files (the "Software"), to deal

# in the Software without restriction, including without limitation the rights

# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell

# copies of the Software, and to permit persons to whom the Software is

# furnished to do so, subject to the following conditions:

# 

# Author: Thomas Huetter

# create target folder and change into it

mkdir bolzano-address-trees

cd bolzano-address-trees

# download the data files

# The above copyright notice and this permission notice shall be included in

# all copies or substantial portions of the Software.

# 

# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR

# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,

# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE

# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER

# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,

# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE

# SOFTWARE.

# 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

# Extract data into subdirectory.

unzip bolzano-address-trees.zip -d original_data

# remove zip file

rm -rf bolzano-address-trees.zip

# change to unzipped folder

cd original_data

# prepare data for file L.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" 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 "{")

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

# prepare dataset with a single label

#                         | remove non-bracket chars. | add single dummy label 'o' > save to file

cat ../L_preprocessed.txt | sed 's/[^\{\}]//g'        | sed 's/[\{]/\{o/g'         > ../L_preprocessed_single_label.bracket

# Prepare output from 'L.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" original_data/L.trees | tail -n +14 | sed 's/.*://' | awk '{print gsub("{","{"), $0}' | sort -n | cut -d' ' -f2- > bolzano_sorted.bracket

# go back to the folder

cd ..

# Tidy up.

rm bolzano-address-trees.zip

rm -rf original_data

 No newline at end of file