From 58b38322d190655bbd4df35285daf0aa2ed4036c Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Fri, 21 Jan 2022 16:53:19 -0800 Subject: container counts update process README --- extra/container_count_update/README.md | 41 ++++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) create mode 100644 extra/container_count_update/README.md (limited to 'extra') diff --git a/extra/container_count_update/README.md b/extra/container_count_update/README.md new file mode 100644 index 00000000..3e9a4315 --- /dev/null +++ b/extra/container_count_update/README.md @@ -0,0 +1,41 @@ + +Here are the fields we want to populate: + + "releases_total": { "type": "integer" }, + "preservation_bright": { "type": "integer" }, + "preservation_dark": { "type": "integer" }, + "preservation_shadows_only":{ "type": "integer" }, + "preservation_none": { "type": "integer" }, + +Populate local index for testing: + + fatcat-cli search container --index-json --limit 100 state:active \ + | pv -l \ + > container_es_docs.json + + cat container_es_docs.json \ + | esbulk -verbose -index fatcat_container_v03c -id ident + + cat container_es_docs.json \ + | jq .ident -r \ + > container_idents.tsv + +Quick way to dump all idents in the current index: + + fatcat-cli search container --index-json --limit 0 state:active \ + | jq .ident -r \ + | pv -l \ + > container_idents.tsv + + cat container_idents.tsv \ + | parallel -j10 curl --fail -s 'https://fatcat.wiki/container/{}/stats.json' \ + | jq -c . \ + | pv -l \ + > container_stats.json + + cat container_stats.json \ + | jq '{ ident: .ident, releases_total: .total, preservation_bright: .preservation.bright, preservation_dark: .preservation.dark, preservation_shadows_only: .preservation.shadows_only, preservation_none: .preservation.none }' -c \ + | esbulk -verbose -index fatcat_container_v03c -optype update -id ident + +This requires a recent version of esbulk (v0.7.5+) + -- cgit v1.2.3