bxie

# ICER work count script (from Jean Salac. Original script by Seth Poulsen). March 2023
# Need to ensure that the PDF in question (paper.pdf), pdfbox, and this script are in the same folder
# Make sure you have the most updated pdfbox version: https://pdfbox.apache.org/download.html
# Set executable permissions `chmod +x icer_word_count.sh` and then run with `./icer_word_count.sh`
# More info: https://icer2023.acm.org/track/icer-2023-papers#Submission-Instructions

java -jar pdfbox-app-2.0.27.jar ExtractText paper.pdf paper.txt;
grep -v -E '^[0-9]+$' paper.txt > paper_no_nums.txt;
sed -n '/REFERENCES/q;p' paper_no_nums.txt > paper_no_refs.txt;
wc -w paper_no_refs.txt