diff --git a/scripts/extract-parallel-EDdA.sh b/scripts/extract-parallel-EDdA.sh new file mode 100755 index 0000000000000000000000000000000000000000..b18305ec14615ad98fad5f5169263fb896a90ea4 --- /dev/null +++ b/scripts/extract-parallel-EDdA.sh @@ -0,0 +1,35 @@ +#!/bin/bash + +INPUT_METADATA="${1}" +SOURCE_TEXT_ARTICLES="${2}" +OUTPUT="${3}" +if [ -d "${OUTPUT}" ] +then + N=1 + while [ -d "${OUTPUT}.${N}" ] + do + N=$((N+1)) + done + mv "${OUTPUT}" "${OUTPUT}.${N}" +fi + +WORKDIR=$(mktemp -d /tmp/parallel-EDdA.XXX) + +for T in {1..17} +do + mkdir -p "${WORKDIR}/T${T}" +done + +while read LINE +do + LINE="${LINE#*,}" + LINE="${LINE#*,}" + LINE="${LINE#*,}" + LINE="${LINE#*,}" + T="${LINE%%,*}" + LINE="${LINE#*,}" + RANK="${LINE%%,*}" + cp "${SOURCE_TEXT_ARTICLES}/T${T}/article${RANK}."* "${WORKDIR}/T${T}" +done < <(tail -n +2 ${INPUT_METADATA}) + +mv ${WORKDIR} ${OUTPUT} diff --git a/scripts/extract-parallel-LGE.sh b/scripts/extract-parallel-LGE.sh index 1411ce25b8adf497a0aa94a5400634563cc2d33b..b1c0c3abce17becfc7f89a9a121aab11f224527c 100755 --- a/scripts/extract-parallel-LGE.sh +++ b/scripts/extract-parallel-LGE.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash INPUT_METADATA="${1}" SOURCE_TEXT_ARTICLES="${2}"