download_prepare.sh 566 Bytes
Newer Older
1 2 3 4
#!/bin/bash

# Download the XML file.
wget -v http://dblp.dagstuhl.de/xml/release/dblp-2017-11-01.xml.gz
Mateusz Pawlik's avatar
Mateusz Pawlik committed
5
 
6 7 8 9 10 11 12 13 14 15 16
# Download the checksum.
wget -v http://dblp.dagstuhl.de/xml/release/dblp-2017-11-01.xml.gz.md5

# Verify the checksum.
md5sum -c dblp-2017-11-01.xml.gz.md5

# Download the DTD file.
wget -v http://dblp.dagstuhl.de/xml/release/dblp-2017-08-29.dtd

# Extract the XML file.
gzip -d dblp-2017-11-01.xml.gz
Mateusz Pawlik's avatar
Mateusz Pawlik committed
17 18 19 20 21 22 23 24 25 26

# Convert XML to bracket notation.
./dblp_to_bracket.py

# Sort the dataset.
./../utilities/sort_dataset.sh dblp.bracket

# Tidy up.
# rm *xml*
# rm *.dtd