Open dloy opened 7 months ago
I started some brainstorming about use cases here. https://github.com/CDLUC3/mrt-doc/blob/main/design/object-reset/README.md
All non ?changeToken file paths in prod using
SELECT f.pathname FROM inv_files f WHERE f.id IN ( SELECT f.id FROM inv_files f WHERE f.billable_size > 0 AND f.pathname LIKE '%?%=%' AND NOT f.pathname LIKE '%changeToken%' )
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?feed=rss2&p=101
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?page_id=333
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/wp-includes/js/comment-reply.js?ver=20090102
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/player.vimeo.com/video/30709765?title=0&byline=0&portrait=0
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?p=685
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?feed=rss2&p=393
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?feed=rss2&p=251
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?p=469
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?p=657
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/users.soe.ucsc.edu/~mccoyjo/files/EditorGUI/history/?C=S;O=D
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?p=251
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/users.soe.ucsc.edu/~mccoyjo/files/EditorGUI/history/?C=S;O=A
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?p=393
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?page_id=347
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?p=19
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?cat=1&paged=2
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?cat=1
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?feed=rss2&p=149
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/users.soe.ucsc.edu/~mccoyjo/files/EditorGUI/?C=M;O=A
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?p=647
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/users.soe.ucsc.edu/~mccoyjo/files/EditorGUI/history/?C=D;O=A
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/users.soe.ucsc.edu/~mccoyjo/files/EditorGUI/?C=D;O=A
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/users.soe.ucsc.edu/~mccoyjo/files/?C=D;O=A
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?p=745
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?page_id=9
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/users.soe.ucsc.edu/~mccoyjo/files/EditorGUI/?C=M;O=D
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?page_id=133
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/users.soe.ucsc.edu/~mccoyjo/files/cmps248/?C=S;O=D
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/users.soe.ucsc.edu/~mccoyjo/files/cmps248/?C=S;O=A
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/users.soe.ucsc.edu/~mccoyjo/files/cmps248/?C=D;O=A
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?feed=rss2&p=823
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/users.soe.ucsc.edu/~mccoyjo/files/cmps248/?C=N;O=D
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?p=543
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/users.soe.ucsc.edu/~mccoyjo/files/EditorGUI/history/?C=N;O=D
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/users.soe.ucsc.edu/~mccoyjo/files/?C=S;O=A
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/users.soe.ucsc.edu/~mccoyjo/files/?C=S;O=D
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?p=431
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?feed=rss2&author=1
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?feed=rss2&author=3
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?feed=rss2&author=5
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?feed=rss2&author=7
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?feed=rss2&author=9
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?p=187
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?feed=rss2
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?feed=comments-rss2
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?page_id=73
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?p=165
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?author=5
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?author=3
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?author=9
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?author=7
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/users.soe.ucsc.edu/~mccoyjo/files/?C=M;O=D
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/users.soe.ucsc.edu/~mccoyjo/files/cmps248/?C=M;O=D
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?author=1
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/users.soe.ucsc.edu/~mccoyjo/files/cmps248/?C=M;O=A
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?feed=rss2&p=685
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?p=149
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?page_id=25
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/users.soe.ucsc.edu/~mccoyjo/files/?C=M;O=A
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?feed=rss2&p=469
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?page_id=41
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?p=187&replytocom=79
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?feed=rss2&p=847
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/users.soe.ucsc.edu/~mccoyjo/files/EditorGUI/?C=S;O=A
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/users.soe.ucsc.edu/~mccoyjo/files/EditorGUI/?C=S;O=D
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/users.soe.ucsc.edu/~mccoyjo/files/EditorGUI/history/?C=M;O=A
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?p=101
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?p=823
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?feed=rss2&p=431
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?page_id=281
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/facebook/PromWeek.swf?=4
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?feed=rss2&cat=1
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?p=847
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?feed=rss2&p=543
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/wp-content/themes/san-kloud/style.css?v=1.0.5
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?feed=rss2&p=745
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?paged=2
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?feed=rss2&p=165
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/users.soe.ucsc.edu/~mccoyjo/files/EditorGUI/?C=N;O=D
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/users.soe.ucsc.edu/~mccoyjo/files/?C=N;O=D
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?feed=rss2&p=295
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?feed=rss2&p=657
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?feed=rss2&p=19
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?p=295
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?feed=rss2&p=187
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/player.vimeo.com/video/40632382?title=0&byline=0&portrait=0
producer/ARCHIVEIT-1023-NONE-3625-20131029011626627-00000-wbgrp-crawl050.us.archive.org-6440/promweek.soe.ucsc.edu/?feed=rss2&p=647
Counts by collection of '%?%=%'
SELECT COUNT(f.id)
FROM inv_files f
WHERE f.billable_size > 0
AND f.pathname LIKE '%?%'
824985
Objects by Collection
SELECT c.mnemonic, COUNT(distinct o.ark)
FROM inv_objects o,
inv_files f,
inv_collections c,
inv_collections_inv_objects co
WHERE f.id IN (
SELECT f.id
FROM inv_files f
WHERE f.billable_size > 0
AND f.pathname LIKE '%?%=%')
and f.inv_object_id=o.id
AND co.inv_object_id=o.id
AND c.id=co.inv_collection_id
GROUP BY c.id
----------------------
"mnemonic" "COUNT(distinct o.ark)"
"ucm_lib_clark" "1"
"ucr_lib_wrca_laaqua" "7"
"ucsc_lib_promweek" "1"
"ucr_lib_nuxeo" "4548"
"ucsf_lib_stantonglantz" "241"
"ucm_lib_acm" "2"
"ucm_lib_mclean" "40"
"ucm_lib_ucce_ventura" "1524"
"ucm_lib_ucce_humboldt" "3294"
"ucm_lib_ucce_merced" "1819"
"uci_lib_sca_ua" "24"
"uci_lib_sca_se_asian" "1"
"uci_lib_sca_sc" "54"
"uci_lib_sca_crit" "2"
"ucm_lib_ucce_sbslo" "1674"
"ucsf_lib_wan" "92"
"ucm_lib_ucce_anr" "236"
"uci_lib_sca_upub" "15"
"ucm_lib_elowe" "2767"
"ucm_lib_ucce_fresno" "2899"
"ucm_lib_ucce_mariposa" "1745"
"ucm_lib_ucce_madera" "3467"
"ucm_lib_ucce_modoc" "1132"
"ucm_lib_ucce_sd" "110"
"ucm_lib_ucce_sjo" "1791"
"ucm_lib_ucce_syu" "68"
"ucm_lib_ucce_tulare" "393"
"uci_lib_sca_orange" "1"
"ucsf_ctp_archive" "67"
"ucr_lib_eatonfz" "1193"
"ucsf_lib_nhprc_gofman" "341"
"ucsf_lib_nhprc_hardgrove" "97"
"ucsf_lib_nhprc_beyer" "9"
"ucsf_lib_nhprc_fraiberg" "508"
"ucsf_lib_nhprc_thelander" "80"
_________________________________________
By file
SELECT c.mnemonic, COUNT(distinct f.id)
FROM inv_objects o,
inv_files f,
inv_collections c,
inv_collections_inv_objects co
WHERE f.id IN (
SELECT f.id
FROM inv_files f
WHERE f.billable_size > 0
AND f.pathname LIKE '%?%=%')
and f.inv_object_id=o.id
AND co.inv_object_id=o.id
AND c.id=co.inv_collection_id
GROUP BY c.id
"mnemonic" "COUNT(distinct f.id)"
"ucm_lib_clark" "19"
"ucr_lib_wrca_laaqua" "271"
"ucsc_lib_promweek" "87"
"ucr_lib_nuxeo" "117140"
"ucsf_lib_stantonglantz" "241"
"ucm_lib_acm" "2"
"ucm_lib_mclean" "60"
"ucm_lib_ucce_ventura" "45175"
"ucm_lib_ucce_humboldt" "43723"
"ucm_lib_ucce_merced" "73807"
"uci_lib_sca_ua" "73"
"uci_lib_sca_se_asian" "3"
"uci_lib_sca_sc" "76"
"uci_lib_sca_crit" "6"
"ucm_lib_ucce_sbslo" "54175"
"ucsf_lib_wan" "2702"
"ucm_lib_ucce_anr" "7643"
"uci_lib_sca_upub" "27"
"ucm_lib_elowe" "8301"
"ucm_lib_ucce_fresno" "83429"
"ucm_lib_ucce_mariposa" "25681"
"ucm_lib_ucce_madera" "60399"
"ucm_lib_ucce_modoc" "39601"
"ucm_lib_ucce_sd" "3885"
"ucm_lib_ucce_sjo" "88005"
"ucm_lib_ucce_syu" "8336"
"ucm_lib_ucce_tulare" "70227"
"uci_lib_sca_orange" "3"
"ucsf_ctp_archive" "134"
"ucr_lib_eatonfz" "19434"
"ucsf_lib_nhprc_gofman" "22129"
"ucsf_lib_nhprc_hardgrove" "11085"
"ucsf_lib_nhprc_beyer" "393"
"ucsf_lib_nhprc_fraiberg" "25387"
"ucsf_lib_nhprc_thelander" "12057"
Object reset would be a mechanism to allow a user to remove 1 or more current versions of an object.
Features:
Questions about this process:
Changes required
Would be first delete feature provided by users.
Manifest
Ingest
Storage
Inventory
Replication
Scan