An R script that queries the DataONE Node Registry and extracts a list of dates when each MN became operational

dataone-node-operation-dates.R

# Query the DataONE Node Registry to find dates that Member Nodes began operation

# The DataONE Node registry service returns results as XML
library(httr)
library(xml2)

# The base URL for the DataONE Coordinating Node
cn_base_url <- "https://cn.dataone.org/cn"

# The Solr query service endpoint
cn_node_service <- "/v2/node"

nodes_url <- paste(cn_base_url, cn_node_service, sep = "")

# Execute the query
request <- GET(nodes_url)
node_list <- read_xml(content(request, as = "text", encoding = "UTF-8"))

# Filter the XML node list:
# - for Member Nodes only (type = mn)
# - with identifiers that don't start with 'urn:node:mn' (D1 replica nodes)
# - with a CN_operational_date property
nodes <- xml_find_all(node_list, 
    "//node[@type='mn' and not(starts-with(identifier, 'urn:node:mn'))]/property[@key='CN_date_operational']")

# Construct a node date list of just the text values from the filtered XML
dates <- xml_text(nodes)



# FYI: the node_list XML above looks like this (some elements removed for brevity):
# <?xml version="1.0" encoding="UTF-8"?>
# <ns3:nodeList xmlns:ns2="http://ns.dataone.org/service/types/v1" 
#               xmlns:ns3="http://ns.dataone.org/service/types/v2.0">
#     <node replicate="false" synchronize="true" type="mn" state="up">
#       <identifier>urn:node:RW</identifier>
#       <name>Research Workspace</name>
#       <description>
#         The Research Workspace is a web-based, scientific data management 
#         platform that allows researchers to store and share their data.
#       </description>
#       <baseURL>https://dataone.researchworkspace.com/mn</baseURL>
#       <property key="CN_date_operational">2017-07-25T00:00:0.000Z</property>
#     </node>
#     ...
# </ns3:nodeList>