From 08af574cb14ec889ea49a89926a57ef7926f749b Mon Sep 17 00:00:00 2001
From: Paul Millar <paul.millar@desy.de>
Date: Thu, 2 Jan 2025 15:01:42 +0100
Subject: [PATCH] update_oai-pmh Improve HTTP request headers
Motivation:
The `User-Agent` request header was not being sent due to a bug.
The havester lacks support for the `From` request header.
Both HTTP request headers are recommented by the Harvester's guidelines:
https://www.openarchives.org/OAI/2.0/guidelines-harvester.htm
Modification:
Fix bug with `User-Agent` header. Add support for `From` header.
The `From` header takes an email address as an argument. Rather than
requiring a configuration file, the code looks for likely places where
the user may have already configured their email address.
Result:
The OAI-PMH harvester more closely followes the corresponding
guidelines.
---
scripts/update_oai-pmh.rb | 35 +++++++++++++++++++++++++++++++----
1 file changed, 31 insertions(+), 4 deletions(-)
diff --git a/scripts/update_oai-pmh.rb b/scripts/update_oai-pmh.rb
index d94a368..e98ab25 100644
--- a/scripts/update_oai-pmh.rb
+++ b/scripts/update_oai-pmh.rb
@@ -17,12 +17,11 @@ class OaiPmhClient
persistent_connection_adapter
- headers {"User-Agent" => "LEAPS-WG3-client/0.1"}
+ headers 'User-Agent' => 'LEAPS-WG3-client/0.1'
def initialize(oai_pmh_endpoint, from_id=nil)
self.class.base_uri oai_pmh_endpoint
-
- # TODO add from_id support as 'From' request header
+ self.class.headers "From" => from_id if from_id
# WORK_AROUND: The connection adapter is persistent across multiple
# URLs (which is good), but the adapter+connection-caching somehow
@@ -233,6 +232,27 @@ class SeriesStatistics
end
end
+# Try to discover someone's email address by looking in various likely
+# configuration files. Returns the email address if it's unambiguous.
+def find_email_address
+ candidate_emails = []
+
+ # Look in Zoom
+ zoomConfig = File.expand_path("~/.config/zoomus.conf")
+ if File.file?(zoomConfig)
+ File.open( zoomConfig ).each do |line|
+ if line =~ /^userEmailAddress=(.*?)$/
+ candidate_emails.append($1)
+ end
+ end
+ end
+
+ # TODO Look in Thunderbird
+ #find ~.thunderbird -name prefs.js | xargs sed -n 's/user_pref."mail.identity.id1.useremail", "\([^"]*\)".*/\1/p'
+
+ # Return email address if there is no ambiguity.
+ return candidate_emails.uniq.count == 1 ? candidate_emails[0] : nil
+end
def check_oai_pmh_endpoint(endpoint_url)
queryIdentify_url = endpoint_url + "?verb=Identify"
@@ -423,6 +443,13 @@ up_to_date = true
file_path = '_data/facilities.yml'
facilities = YAML.safe_load(File.read(file_path), permitted_classes: [Date])
+email_address = find_email_address
+if email_address
+ puts "INFO: identifying OAI-PMH activity as from <#{email_address}>"
+else
+ puts "WARNING: unable to discover your email address. Carrying on under a cloak of anonymity."
+end
+
facilities.each do |facility|
odr = facility['odr']
next unless odr && odr.key?('oai-pmh-endpoint')
@@ -433,7 +460,7 @@ facilities.each do |facility|
oai_pmh_endpoint = oai_pmh['link']
next unless oai_pmh_endpoint
- $client = OaiPmhClient.new(oai_pmh_endpoint)
+ $client = OaiPmhClient.new(oai_pmh_endpoint, email_address)
expected_status = oai_pmh['status']
--
GitLab