From b12d4f0bde96bfe39df1cc94a993da4b25e53304 Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Tue, 19 Jul 2022 12:48:15 -0700 Subject: dblp import/update notes --- extra/bulk_edits/2022-07-13_dblp.md | 114 ++++++++++++++++++++++++++++++++++++ 1 file changed, 114 insertions(+) create mode 100644 extra/bulk_edits/2022-07-13_dblp.md (limited to 'extra') diff --git a/extra/bulk_edits/2022-07-13_dblp.md b/extra/bulk_edits/2022-07-13_dblp.md new file mode 100644 index 00000000..25405132 --- /dev/null +++ b/extra/bulk_edits/2022-07-13_dblp.md @@ -0,0 +1,114 @@ + +## Prep + + 2022-07-13 05:24:33 (177 KB/s) - ‘dblp.xml.gz’ saved [715701831/715701831] + + Counter({'total': 9186263, 'skip': 9186263, 'has-doi': 4960506, 'skip-key-type': 3037457, 'skip-arxiv-corr': 439104, 'skip-title': 1, 'insert': 0, 'update': 0, 'exists': 0}) + 5.71M 3:37:38 [ 437 /s] + + 7.48k 0:38:18 [3.25 /s] + + +## Container Import + +Run 2022-07-15, after a database backup/snapshot. + + export FATCAT_AUTH_WORKER_DBLP=[...] + ./fatcat_import.py dblp-container --issn-map-file /srv/fatcat/datasets/ISSN-to-ISSN-L.txt --dblp-container-map-file ../extra/dblp/existing_dblp_containers.tsv --dblp-container-map-output ../extra/dblp/all_dblp_containers.tsv ../extra/dblp/dblp_container_meta.json + # Got 5310 existing dblp container mappings. + # Counter({'total': 7471, 'exists': 7130, 'insert': 341, 'skip': 0, 'update': 0}) + + wc -l existing_dblp_containers.tsv all_dblp_containers.tsv dblp_container_meta.json prefix_list.txt + 5310 existing_dblp_containers.tsv + 12782 all_dblp_containers.tsv + 7471 dblp_container_meta.json + 7476 prefix_list.txt + + +## Release Import + + export FATCAT_AUTH_WORKER_DBLP=[...] + ./fatcat_import.py dblp-release --dblp-container-map-file ../extra/dblp/all_dblp_containers.tsv ../extra/dblp/dblp.xml + # Got 7480 dblp container mappings. + + /1/srv/fatcat/src/python/fatcat_tools/importers/dblp_release.py:358: UserWarning: unexpected dblp ext_id match after lookup failed dblp=conf/gg/X90 ident=gfvkxubvsfdede7ps4af3oa34q + warnings.warn(warn_str) + /1/srv/fatcat/src/python/fatcat_tools/importers/dblp_release.py:358: UserWarning: unexpected dblp ext_id match after lookup failed dblp=conf/visalg/X88 ident=lvfyrd3lvva3hjuaaokzyoscmm + warnings.warn(warn_str) + /1/srv/fatcat/src/python/fatcat_tools/importers/dblp_release.py:358: UserWarning: unexpected dblp ext_id match after lookup failed dblp=conf/msr/PerumaANMO22 ident=2grlescl2bcpvd5yoc4npad3bm + warnings.warn(warn_str) + /1/srv/fatcat/src/python/fatcat_tools/importers/dblp_release.py:358: UserWarning: unexpected dblp ext_id match after lookup failed dblp=conf/dagstuhl/Brodlie97 ident=l6nh222fpjdzfotchu7vfjh6qu + warnings.warn(warn_str) + /1/srv/fatcat/src/python/fatcat_tools/importers/dblp_release.py:358: UserWarning: unexpected dblp ext_id match after lookup failed dblp=series/gidiss/2018 ident=x6t7ze4z55enrlq2dnac4qqbve + + Counter({'total': 9186263, 'exists': 5356574, 'has-doi': 4960506, 'skip': 3633039, 'skip-key-type': 3037457, 'skip-arxiv-corr': 439104, 'exists-fuzzy': 192376, 'skip-dblp-container-missing': 156477, 'insert': 4216, 'skip-arxiv': 53, 'skip-dblp-id-mismatch': 5, 'skip-title': 1, 'update': 0}) + +NOTE: had to re-try in the middle, so these counts not accurate overall. + +Seems like a large number of `skip-dblp-container-missing`. Maybe should have +re-generated that file differently? + +After this import there are 2,217,670 releases with a dblp ID, and 478,983 with +a dblp ID and no DOI. + + +## Sandcrawler Seedlist Generation + +Almost none of the ~487k dblp releases with no DOI have an associated file. +This implies that no ingest has happened yet, even though the fatcat importer +does parse and filter the "fulltext" URLs out of dblp records. + + cat dblp_releases_partial.json | pipenv run ./dblp2ingestrequest.py - | pv -l | gzip > dblp_sandcrawler_ingest_requests.json.gz + # 631k 0:02:39 [3.96k/s] + + zcat dblp_sandcrawler_ingest_requests.json.gz | jq -r .base_url | cut -f3 -d/ | sort | uniq -c | sort -nr | head -n25 + 43851 ceur-ws.org + 33638 aclanthology.org + 32077 aisel.aisnet.org + 31017 ieeexplore.ieee.org + 26426 dl.acm.org + 23817 hdl.handle.net + 22400 www.isca-speech.org + 20072 tel.archives-ouvertes.fr + 18609 www.aaai.org + 18244 eprint.iacr.org + 15720 ethos.bl.uk + 14727 nbn-resolving.org + 14470 proceedings.mlr.press + 14095 dl.gi.de + 12159 proceedings.neurips.cc + 10890 knowledge.amia.org + 10049 www.usenix.org + 9675 papers.nips.cc + 7541 subs.emis.de + 7396 openaccess.thecvf.com + 7345 mindmodeling.org + 6574 ojs.aaai.org + 5814 www.lrec-conf.org + 5773 search.ndltd.org + 5311 ijcai.org + +This is the first ingest, so let's do some sampling in the 'daily' queue: + + zcat dblp_sandcrawler_ingest_requests.json.gz + + zcat dblp_sandcrawler_ingest_requests.json.gz | shuf -n100 | rg -v "\\\\" | jq . -c | kafkacat -P -b wbgrp-svc350.us.archive.org -t sandcrawler-prod.ingest-file-requests-daily -p -1 + +Looks like we can probably get away with doing these in the daily ingest queue, +instead of bulk? Try a larger batch: + + zcat dblp_sandcrawler_ingest_requests.json.gz | shuf -n10000 | rg -v "\\\\" | jq . -c | kafkacat -P -b wbgrp-svc350.us.archive.org -t sandcrawler-prod.ingest-file-requests-daily -p -1 + +Nope, these are going to need bulk ingest then follow-up crawling. Will +heritrix crawl along with JALC and DOAJ stuff. + + zcat dblp_sandcrawler_ingest_requests.json.gz | rg -v "\\\\" | jq . -c | pv -l | kafkacat -P -b wbgrp-svc350.us.archive.org -t sandcrawler-prod.ingest-file-requests-bulk -p -1 + # 631k 0:00:11 [54.0k/s] + + +TODO: +x python or jq transform of JSON objects +x filter out german book/library URLs +x ensure fatcat importer will actually import dblp matches +x test with a small batch in daily or priority queue +- enqueue all in bulk mode, even if processed before? many probably MAG or OAI-PMH previously -- cgit v1.2.3