#!/bin/bash
# Usage: unfold.sh links_...
pdfs=/beegfs/common_crawl/CC-MAIN-2019-35/pdfs
links=$pdfs/links
f=$1
IFS='  '
awk '{if (NR==1) { o=$1 ; u=$2 }
else
{ if ($1=="annot" || $1=="scrape") {
print o,"\t",u
o=$1
u=$2
}
else {
u=u $1     
}             
}
}
END { print o,"\t",u }' $f