From 502f3d43184a5bfb47418e3d2d4fa3bfcb022258 Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Tue, 19 Jul 2022 12:52:16 -0700 Subject: 2021 ORCID metadata import notes --- extra/bulk_edits/2022-07-12_orcid.md | 64 ++++++++++++++++++++++++++++++++++++ 1 file changed, 64 insertions(+) create mode 100644 extra/bulk_edits/2022-07-12_orcid.md diff --git a/extra/bulk_edits/2022-07-12_orcid.md b/extra/bulk_edits/2022-07-12_orcid.md new file mode 100644 index 00000000..760a16c8 --- /dev/null +++ b/extra/bulk_edits/2022-07-12_orcid.md @@ -0,0 +1,64 @@ + +Annual ORCID import, using 2021 public data file. Didn't do this last year, so +a catch-up, and will need to do another update later in 2022 (presumably in +November/December). + +Not sure how many records this year. Current count on the orcid.org website is +over 14 million ORCIDs, in July 2022. + +Files download from: + +- +- +- + +## Prep + + ia upload orcid-dump-2021 -m collection:ia_biblio_metadata ORCID_2021_10_* orcid-logo.png + + wget https://github.com/ORCID/orcid-conversion-lib/raw/master/target/orcid-conversion-lib-3.0.7-full.jar + + java -jar orcid-conversion-lib-3.0.7-full.jar --tarball -i ORCID_2021_10_summaries.tar.gz -v v3_0 -o ORCID_2021_10_summaries_json.tar.gz + + tar xvf ORCID_2021_10_summaries_json.tar.gz + + fd .json ORCID_2021_10_summaries/ | parallel cat {} | jq . -c | pv -l | gzip > ORCID_2021_10_summaries.json.gz + # 12.6M 27:59:25 [ 125 /s] + + zcat ORCID_2021_10_summaries.json.gz | shuf -n10000 | gzip > ORCID_2021_10_summaries.sample_10k.json.gz + + ia upload orcid-dump-2021 ORCID_2021_10_summaries.json.gz ORCID_2021_10_summaries.sample_10k.json.gz + +## Import + +Fetch to prod machine: + + wget https://archive.org/download/orcid-dump-2021/ORCID_2021_10_summaries.json.gz + wget https://archive.org/download/orcid-dump-2021/ORCID_2021_10_summaries.sample_10k.json.gz + +Sample: + + export FATCAT_AUTH_WORKER_ORCID=[...] + zcat /srv/fatcat/datasets/ORCID_2021_10_summaries.sample_10k.json.gz | ./fatcat_import.py orcid - + # in 2020: Counter({'total': 10000, 'exists': 7356, 'insert': 2465, 'skip': 179, 'update': 0}) + # this time: Counter({'total': 10000, 'exists': 7577, 'insert': 2191, 'skip': 232, 'update': 0}) + +Bulk import: + + export FATCAT_AUTH_WORKER_ORCID=[...] + time zcat /srv/fatcat/datasets/ORCID_2021_10_summaries.json.gz | pv -l | parallel -j8 --round-robin --pipe ./fatcat_import.py orcid - + 12.6M 1:24:04 [2.51k/s] + Counter({'total': 1574111, 'exists': 1185437, 'insert': 347039, 'skip': 41635, 'update': 0}) + Counter({'total': 1583157, 'exists': 1193341, 'insert': 348187, 'skip': 41629, 'update': 0}) + Counter({'total': 1584441, 'exists': 1193385, 'insert': 349424, 'skip': 41632, 'update': 0}) + Counter({'total': 1575971, 'exists': 1187270, 'insert': 347190, 'skip': 41511, 'update': 0}) + Counter({'total': 1577323, 'exists': 1188892, 'insert': 346759, 'skip': 41672, 'update': 0}) + Counter({'total': 1586719, 'exists': 1195610, 'insert': 349115, 'skip': 41994, 'update': 0}) + Counter({'total': 1578484, 'exists': 1189423, 'insert': 347276, 'skip': 41785, 'update': 0}) + Counter({'total': 1578728, 'exists': 1190316, 'insert': 346445, 'skip': 41967, 'update': 0}) + + real 84m5.297s + user 436m26.428s + sys 41m36.959s + +Roughly 2.7 million new ORCIDs, great! -- cgit v1.2.3