Mercurial > hg > cc > cirrus_home
annotate bin/unfold.sh @ 194:1845222b3d73
move DummyContext out
author | Henry S. Thompson <ht@inf.ed.ac.uk> |
---|---|
date | Wed, 25 Sep 2024 17:45:52 +0100 |
parents | a82c325e8b32 |
children |
rev | line source |
---|---|
18 | 1 #!/bin/bash |
2 # Usage: unfold.sh links_... | |
3 pdfs=/beegfs/common_crawl/CC-MAIN-2019-35/pdfs | |
4 links=$pdfs/links | |
5 f=$1 | |
25 | 6 IFS=' ' |
18 | 7 awk '{if (NR==1) { o=$1 ; u=$2 } |
8 else | |
9 { if ($1=="annot" || $1=="scrape") { | |
10 print o,"\t",u | |
11 o=$1 | |
12 u=$2 | |
13 } | |
14 else { | |
15 u=u $1 | |
16 } | |
17 } | |
18 } | |
19 END { print o,"\t",u }' $f |