From d2c95fb7a98e051639ef875c1d9aa4ba4b794509 Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Wed, 13 May 2020 14:09:43 -0700 Subject: improve pipeline commands --- notes/pipeline_commands.md | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'notes') diff --git a/notes/pipeline_commands.md b/notes/pipeline_commands.md index ca3106c..94d7480 100644 --- a/notes/pipeline_commands.md +++ b/notes/pipeline_commands.md @@ -67,8 +67,14 @@ Create and index existing `fatcat_release` schema: # in fatcat python directory, pipenv shell export LC_ALL=C.UTF-8 + export TODAY="`TZ=UTC date --iso-8601=date`" cat /srv/fatcat_covid19/src/metadata/combined.$TODAY.enrich.json | jq .fatcat_release -c | rg -v '^null$' | pv -l | ./fatcat_transform.py elasticsearch-releases - - | esbulk -verbose -size 1000 -id ident -w 8 -index covid19_fatcat_release -type release +Attempt crawl/ingest of missing papers: + + ./fatcat_ingest.py --env prod --enqueue-kafka --elasticsearch-index covid19_fatcat_release --fatcat-api-url https://api.fatcat.wiki/v0 --kafka-hosts wbgrp-svc263.us.archive.org --allow-non-oa query "pmcid:*" + ./fatcat_ingest.py --env prod --enqueue-kafka --elasticsearch-index covid19_fatcat_release --fatcat-api-url https://api.fatcat.wiki/v0 --kafka-hosts wbgrp-svc263.us.archive.org --allow-non-oa query "-_exists_:pmcid doi:*" + ## GROBID Processing zip -r fulltext_web.zip fulltext_web -- cgit v1.2.3