Last active
July 11, 2018 17:19
-
-
Save crashangelbr/37cb29288a74638dcd49db956b34bfca to your computer and use it in GitHub Desktop.
Import Wikipedia to ElasticSearch
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/bin/bash | |
# https://www.elastic.co/blog/loading-wikipedia | |
# https://dumps.wikimedia.org/other/cirrussearch/current/ | |
DeleteAll(){ | |
curl -XDELETE $es/$index?pretty | |
} | |
CreateIndex(){ | |
curl -s 'https://'$site'/w/api.php?action=cirrus-settings-dump&format=json&formatversion=2' -H'Content-Type: application/json' | | |
jq '{ | |
analysis: .content.page.index.analysis, | |
number_of_shards: 1, | |
number_of_replicas: 0 | |
}' | | |
curl -XPUT $es/$index?pretty -H'Content-Type: application/json' -d @- | |
curl -s 'https://'$site'/w/api.php?action=cirrus-mapping-dump&format=json&formatversion=2' -H'Content-Type: application/json' | | |
jq .content | | |
sed 's/"index_analyzer"/"analyzer"/' | | |
sed 's/"position_offset_gap"/"position_increment_gap"/' | | |
curl -XPUT $es/$index/_mapping/page?pretty -H'Content-Type: application/json' -d @- | |
} | |
SplitFiles() | |
{ | |
mkdir chunks | |
cd chunks | |
zcat ../$dump | split -a 10 -l 500 - $index | |
} | |
Dump() | |
{ | |
cd chunks | |
for file in *; do | |
echo -n "${file}: " | |
took=$(curl -s -XPOST $es/$index/_bulk?pretty -H'Content-Type: application/json' --data-binary @$file | | |
grep took | cut -d':' -f 2 | cut -d',' -f 1) | |
printf '%7s\n' $took | |
[ "x$took" = "x" ] || rm $file | |
done | |
cd .. | |
} | |
Execute_Wikipedia_Content() | |
{ | |
export site=pt.wikipedia.org | |
export index=ptwikipedia_content | |
export dump=ptwiki-20180702-cirrussearch-content.json.gz | |
DeleteAll | |
CreateIndex | |
SplitFiles | |
Dump | |
} | |
Execute_Wikipedia_General() | |
{ | |
export site=pt.wikipedia.org | |
export index=ptwikipedia_general | |
export dump=ptwiki-20180702-cirrussearch-general.json.gz | |
DeleteAll | |
CreateIndex | |
SplitFiles | |
Dump | |
} | |
Execute_Wikionary_Content() | |
{ | |
export site=pt.wikionary.org | |
export index=ptwikionary_content | |
export dump=ptwiktionary-20180702-cirrussearch-content.json.gz | |
DeleteAll | |
CreateIndex | |
SplitFiles | |
Dump | |
} | |
Execute_Wikionary_General() | |
{ | |
export site=pt.wikionary.org | |
export index=ptwikionary_general | |
export dump=ptwiktionary-20180702-cirrussearch-general.json.gz | |
DeleteAll | |
CreateIndex | |
SplitFiles | |
Dump | |
} | |
export es=localhost:9200 | |
Execute_Wikipedia_Content | |
Execute_Wikipedia_General | |
Execute_Wikionary_Content | |
Execute_Wikionary_General |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment