phette23

SELECT u.first_name, u.last_name, u.email, pub.title, pub.published_in, pub.url,  pub.date, pub.description
FROM people_ppublication pub
JOIN people_portalprofile prof ON (pub.object_id = prof.id)
JOIN people_userprofile u ON (prof.user_id = u.id)

phette23

<?xml version="1.0"?>
<oai_dc:dc xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:dc="http://purl.org/dc/elements/1.1/">
  <dc:title>Do Re Mi</dc:title>
</oai_dc:dc>

phette23

#!/usr/bin/env node
//jshint node:true
// useful for finding location of files on server, for non-advanced storage config location is
// {{data dir}}/Institutions/{{institution name}}/Attachments/${hashCode(uuid)}/${uuid}/${version}
// for advanced storage config it's
// {{data dir}}/Institutions/{{institution name}}/Attachments/${collection UUID}/${hashCode(uuid)}/${uuid}/${version}
const readline = require('readline')

let hashCode = function(str){
	let hash = 0

phette23

SELECT b.title, b.author, b.biblionumber
FROM biblio b
GROUP BY b.datecreated DESC
LIMIT 20

phette23

#!/usr/bin/env fish
# usage: vlog [date string] e.g. `vlog yesterday` or just `vlog` (for today's logs)
# requires SSH aliases for both app nodes (v1 & v2)
set today (gdate "+%Y-%m-%d")
if test -n "$argv[1]"
    # need to use gnu date to get the human readable --date parameter
    set d (gdate --date="$argv[1]" "+%Y-%m-%d")
    # there can be multiple logs per day, rsync does this in only 1 ssh connection (requires rsync 3+)
    rsync -ruzvhP v1:/opt/equella/logs/resource-centre/$d/ :/opt/equella/logs/tomcat/$d/ v1-$d
    rsync -ruzvhP v2:/opt/equella/logs/resource-centre/$d/ :/opt/equella/logs/tomcat/$d/ v2-$d

phette23

// custom function for Google Sheets
// usage: TRANSPOSE(VAULTSEARCH("Student, Name")) returns data from Supplemental Portfolio Review collection
function VAULTSEARCH(query) {
  var token = '...', // oauth access token
        opts = {
            contentType: 'application/json',
            headers: { 'X-Authorization': 'access_token=' + token }
        },
        data = UrlFetchApp.fetch('https://vault.cca.edu/api/search/?collections=3eaf9745-e7d4-4cf6-be07-44691daa4714&order=modified&info=metadata,detail&q=' + encodeURIComponent(query), opts),
        results = JSON.parse(data).results,

phette23

import requests

# request URL looks like
# https://moodle.cca.edu/webservice/rest/server.php?wstoken=...&wsfunction=core_course_get_categories&moodlewsrestformat=json&criteria[0][key]=name&criteria[0][value]=2019SP

def get_mdl_categories(filter):
    """ obtain a list of JSON representations of Moodle course categories

    returns an array of category dicts (see their fields below)

phette23

"""
I tested a few options for testing for inclusion in a very large (millions of items) set. Results if you're curious:
¿ python3 heapq-test.py
> List took 71.93408012390137s time
> Heap took 160.27557826042175s time
> Sorted Containers took 0.004794120788574219s time

sortedcontainers is _real_ fast.
"""
from heapq import *

phette23

#!/usr/bin/env python2
# ################################# #
# UploadTaxonomy.py                 #
#                                   #
# added CLI by Eric Phetteplace     #
# California College of the Arts    #
# vault.cca.edu | libraries.cca.edu #
# 2014-07-32                        #
#                                   #
# Pearson's notes below             #

phette23

-- attachment.value1 is the file size for "file" type attachments
-- does not capture a) zip files, b) generated thumbnails
-- but the item.total_file_size column which should include this is inaccurate
SELECT be.uuid, be_name.text AS collection, SUM(CAST(a.value1 AS bigint)) AS "disk space"
FROM item i 
INNER JOIN base_entity be ON be.id = i.item_definition_id
LEFT JOIN language_string i_name ON i.name_id = i_name.bundle_id
LEFT JOIN language_string be_name ON be.name_id = be_name.bundle_id
JOIN (SELECT * FROM attachment WHERE attachment.type = 'file') a ON i.id = a.item_id
WHERE i.institution_id = 1165188