summaryrefslogtreecommitdiffstats
path: root/extra/elasticsearch/README.md
diff options
context:
space:
mode:
Diffstat (limited to 'extra/elasticsearch/README.md')
-rw-r--r--extra/elasticsearch/README.md7
1 files changed, 5 insertions, 2 deletions
diff --git a/extra/elasticsearch/README.md b/extra/elasticsearch/README.md
index 3a48a178..17865bc0 100644
--- a/extra/elasticsearch/README.md
+++ b/extra/elasticsearch/README.md
@@ -40,9 +40,11 @@ Drop and rebuild the schema:
http delete :9200/fatcat_release
http delete :9200/fatcat_container
+ http delete :9200/fatcat_file
http delete :9200/fatcat_changelog
http put :9200/fatcat_release < release_schema.json
http put :9200/fatcat_container < container_schema.json
+ http put :9200/fatcat_file < file_schema.json
http put :9200/fatcat_changelog < changelog_schema.json
Put a single object (good for debugging):
@@ -57,8 +59,9 @@ Bulk insert from a file on disk:
Or, in a bulk production live-stream conversion:
export LC_ALL=C.UTF-8
- time zcat /srv/fatcat/snapshots/release_export_expanded.json.gz | pv -l | parallel -j20 --linebuffer --round-robin --pipe ./fatcat_transform.py elasticsearch-releases - - | esbulk -verbose -size 20000 -id ident -w 8 -index fatcat_release -type release
- time zcat /srv/fatcat/snapshots/container_export.json.gz | pv -l | ./fatcat_transform.py elasticsearch-containers - - | esbulk -verbose -size 20000 -id ident -w 8 -index fatcat_container -type container
+ time zcat /srv/fatcat/snapshots/release_export_expanded.json.gz | pv -l | parallel -j20 --linebuffer --round-robin --pipe ./fatcat_transform.py elasticsearch-releases - - | esbulk -verbose -size 1000 -id ident -w 8 -index fatcat_release -type release
+ time zcat /srv/fatcat/snapshots/container_export.json.gz | pv -l | ./fatcat_transform.py elasticsearch-containers - - | esbulk -verbose -size 1000 -id ident -w 8 -index fatcat_container -type container
+ time zcat /srv/fatcat/snapshots/file_export.json.gz | pv -l | parallel -j20 --linebuffer --round-robin --pipe ./fatcat_transform.py elasticsearch-files - - | esbulk -verbose -size 1000 -id ident -w 8 -index fatcat_file -type file
## Index Aliases