# HG changeset patch # User Henry S. Thompson # Date 1700040983 0 # Node ID 143d2c6d56daa12a93f791dae6c903cd99391fb8 # Parent 4870e14ec23745a97f952ad39ed29351903e09ec cross-language confusion :-) diff -r 4870e14ec237 -r 143d2c6d56da bin/getcc_multi.aws --- a/bin/getcc_multi.aws Mon Nov 06 15:55:57 2023 +0000 +++ b/bin/getcc_multi.aws Wed Nov 15 09:36:23 2023 +0000 @@ -37,7 +37,7 @@ s=$(grep -Eow "[0-9]*\.$SEG" $wf | head -1) mkdir -p $s/orig/warc -fgrep -v -f <(cd $s/orig/warc && ls *.warc.gz || pass) <(fgrep -w $s warc.paths) > /tmp/hst/$s +fgrep -v -f <(cd $s/orig/warc && ls *.warc.gz || :) <(fgrep -w $s warc.paths) > /tmp/hst/$s split -a 1 --numeric-suffixes=1 -n l/$nthreads /tmp/hst/$s /tmp/hst/${s}_