kschlottmann

import pandas as pd

#load csv file - NB first remove extra rows at top, need to replace these before import
#df = pd.read_csv('clean_input.csv', encoding = 'ISO-8859-1', low_memory=False)

#load Excel directly, - NB first remove extra rows at top, need to replace these before import
df = pd.read_excel(open('clean_input.xlsx','rb'))


#print column headings

kschlottmann

<data>
{
for $Record in /ead

where $Record/archdesc/did/langmaterial/language/@langcode[not(contains(., 'eng'))]

let $id := $Record/archdesc/did/unitid[1]/text()
let $title := $Record/archdesc/did/unittitle
let $repo := $Record/eadheader/eadid/@mainagencycode
let $lang := $Record/archdesc/did/langmaterial/language/text()

kschlottmann

<data>
{
for $Record in /ead

where $Record/archdesc/dsc//title[not(@render)]

let $id := $Record/archdesc/did/unitid[1]/text()
let $title := $Record/archdesc/did/unittitle
let $repo := $Record/eadheader/eadid/@mainagencycode

kschlottmann

(Get-ChildItem -Recurse -File) | 
Where-Object { $_.Name -match '[^a-zA-Z0-9.-]' } | 
Rename-Item -NewName { $_.Name -replace '[^a-zA-Z0-9.-]+', '_' } -WhatIf

# As written, this will preview a list of changes where non-ASCII characters as described by the regex are replaced by an underscore
# Delete line 4 (-WhatIf) and re-run to actually make the changes 
# To act on directories: in line 1, replace -File with -Directory, and replace regex with [^a-zA-Z0-9] so as to capture periods
# In lines 2 and 3, replace regex with any other character or regex that is desired, e.g. ' ' for replacing only spaces

#Be sure to use the correct regex for files and directories, because we do not want to rename hidden files starting with a period (e.g. .DS_store), because they are otherwise hard to find programatically

kschlottmann

xquery version "3.0";
declare namespace marc="http://www.loc.gov/MARC21/slim";

(: This xquery will match all records containing an arbitrary term, from the raw ArchivesSpace MARC output from the OAI feed :)

<results>
{
for $MarcRecord in /repository/record/metadata/collection/record

for $word in ("alien", "Alien", "Aliens", "aliens")

kschlottmann

<?xml version="1.0" encoding="UTF-8"?>
<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
    xmlns:xs="http://www.w3.org/2001/XMLSchema" xmlns:ead="urn:isbn:1-931666-22-9"
    exclude-result-prefixes="xs " version="2.0">


    <xsl:template match="c">

        <xsl:text>Title|Date|Box|Folder|Publish Status &#10;</xsl:text>
        <xsl:apply-templates select="//c[@level = 'file']"/>

kschlottmann

import xmltodict, json
from timeit import default_timer as timer
import os 
import sys
import datetime

#this script will interate over the entire CLIO corpus and return all RBML records as individual marcxml records with bib id as filename

#this function wraps the json in a dict with a record key, and casts it to an individual marcxml record
def write_marcxml_record(record):

kschlottmann

import requests, csv, json, urllib, time

startTime = time.time()

baseURLexact = 'http://id.loc.gov/authorities/names/'
#http://id.loc.gov/authorities/names/nr2002027244.json
with open('input_numbers.csv', 'r') as csvfile:
        reader = csv.reader(csvfile, delimiter=',', quotechar='"')
        for row in reader:
            number = str(row[0])

kschlottmann

<data>
{
for $Record in /ead

where $Record/archdesc/scopecontent/p[contains(., 'Mrs')]

let $id := $Record/archdesc/did/unitid[1]/text()
let $title := $Record/archdesc/did/unittitle
let $repo := $Record/eadheader/eadid/@mainagencycode
let $scopeMrs := $Record/archdesc/scopecontent/p[contains(., 'Mrs')]

kschlottmann

import xmltodict, json
from timeit import default_timer as timer
import os 
import sys
import datetime

#this script will interate over the entire CLIO corpus and return the leaders, 245$a s, and 035s for all RBML records

#this function returns a record
def handle_record(_, record):