diff --git a/indexCorpus.sh b/indexCorpus.sh index e306f03..9889474 100644 --- a/indexCorpus.sh +++ b/indexCorpus.sh @@ -66,7 +66,7 @@ mkdir -p $outCurlFolder"/"$corpusName"/split" split -a 4 -l $chunksMaxLines $fullPath $outCurlFolder"/"$corpusName"/split/split" for chunk in `ls $outCurlFolder"/"$corpusName"/split/"` - do echo "indexing "$chunk + do #echo "indexing "$chunk #convert json file to json ready for bulk sed 's/{"corpusname":/{ "index" : {} }\n{"corpusname":/gi' $outCurlFolder"/"$corpusName"/split/"$chunk > $outCurlFolder"/"$corpusName"/"$chunk"-curlReady" curl -k --noproxy '*' -XPOST $ELASTIC_URL":"$ELASTIC_PORT"/analyse-"$corpusName"/_bulk?pretty" -H "Content-Type: application/json" --data-binary "@"$outCurlFolder"/"$corpusName"/"$chunk"-curlReady" > /dev/null 2>&1