From 2c582ebc1d3c72c7ce1a2b00270492df95065975 Mon Sep 17 00:00:00 2001
From: Jeanette Clark <jclark@nceas.ucsb.edu>
Date: Fri, 13 Sep 2024 23:53:55 +0000
Subject: [PATCH 01/14] fix bug where if no results are found an error is
 thrown trying to rbind empty results

---
 R/citation_search.R | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/R/citation_search.R b/R/citation_search.R
index ab17f77..aebcec9 100644
--- a/R/citation_search.R
+++ b/R/citation_search.R
@@ -30,7 +30,13 @@ citation_search <- function(identifiers,
   })
 
   # Combine the resulting data frames and return the result df
-  result <- dplyr::bind_rows(result_df_list)
+  if (all(sapply(result_df_list, function(x) nrow(x) == 0))) {
+      # If all data frames are empty, create an empty data frame with the same structure
+      result <- data.frame()
+  } else {
+      # Otherwise, bind the rows
+      result <- dplyr::bind_rows(result_df_list)
+  }
 
   return(result)
 }

From c0aff73444ac0856e352ce5e602d24815c40b370 Mon Sep 17 00:00:00 2001
From: Jeanette Clark <jclark@nceas.ucsb.edu>
Date: Fri, 13 Sep 2024 17:14:56 -0700
Subject: [PATCH 02/14] initial commit of helm stuff

Dockerfile and script are working correctly in isolation, neext need to connect to helm templates
---
 helm/.helmignore                          | 23 ++++++++
 helm/Chart.yaml                           | 24 ++++++++
 helm/Dockerfile                           | 31 ++++++++++
 helm/scripts/search.R                     | 69 +++++++++++++++++++++++
 helm/templates/NOTES.txt                  | 22 ++++++++
 helm/templates/_helpers.tpl               | 62 ++++++++++++++++++++
 helm/templates/cron-job.yaml              | 34 +++++++++++
 helm/templates/serviceaccount.yaml        | 12 ++++
 helm/templates/tests/test-connection.yaml | 15 +++++
 helm/values.yaml                          | 65 +++++++++++++++++++++
 10 files changed, 357 insertions(+)
 create mode 100644 helm/.helmignore
 create mode 100644 helm/Chart.yaml
 create mode 100644 helm/Dockerfile
 create mode 100644 helm/scripts/search.R
 create mode 100644 helm/templates/NOTES.txt
 create mode 100644 helm/templates/_helpers.tpl
 create mode 100644 helm/templates/cron-job.yaml
 create mode 100644 helm/templates/serviceaccount.yaml
 create mode 100644 helm/templates/tests/test-connection.yaml
 create mode 100644 helm/values.yaml

diff --git a/helm/.helmignore b/helm/.helmignore
new file mode 100644
index 0000000..0e8a0eb
--- /dev/null
+++ b/helm/.helmignore
@@ -0,0 +1,23 @@
+# Patterns to ignore when building packages.
+# This supports shell glob matching, relative path matching, and
+# negation (prefixed with !). Only one pattern per line.
+.DS_Store
+# Common VCS dirs
+.git/
+.gitignore
+.bzr/
+.bzrignore
+.hg/
+.hgignore
+.svn/
+# Common backup files
+*.swp
+*.bak
+*.tmp
+*.orig
+*~
+# Various IDEs
+.project
+.idea/
+*.tmproj
+.vscode/
diff --git a/helm/Chart.yaml b/helm/Chart.yaml
new file mode 100644
index 0000000..9318f95
--- /dev/null
+++ b/helm/Chart.yaml
@@ -0,0 +1,24 @@
+apiVersion: v2
+name: scythe
+description: A Helm chart for Kubernetes
+
+# A chart can be either an 'application' or a 'library' chart.
+#
+# Application charts are a collection of templates that can be packaged into versioned archives
+# to be deployed.
+#
+# Library charts provide useful utilities or functions for the chart developer. They're included as
+# a dependency of application charts to inject those utilities and functions into the rendering
+# pipeline. Library charts do not define any templates and therefore cannot be deployed.
+type: application
+
+# This is the chart version. This version number should be incremented each time you make changes
+# to the chart and its templates, including the app version.
+# Versions are expected to follow Semantic Versioning (https://semver.org/)
+version: 0.1.0
+
+# This is the version number of the application being deployed. This version number should be
+# incremented each time you make changes to the application. Versions are not expected to
+# follow Semantic Versioning. They should reflect the version the application is using.
+# It is recommended to use it with quotes.
+appVersion: "1.0.0"
diff --git a/helm/Dockerfile b/helm/Dockerfile
new file mode 100644
index 0000000..50042aa
--- /dev/null
+++ b/helm/Dockerfile
@@ -0,0 +1,31 @@
+FROM rocker/r-ver:4
+
+RUN groupadd -r scythe && useradd -r -g scythe scythe
+RUN mkdir -p /var/data/scythe && chown scythe.scythe /var/data/scythe
+
+RUN apt-get update && apt-get install -y \
+    librdf-dev \
+    libxml2-dev \
+    libfontconfig1-dev \
+    libssl-dev \
+    libcurl4-gnutls-dev \
+    libsodium-dev \
+    libfribidi-dev \
+    libgit2-dev \
+    libharfbuzz-dev \
+    libfreetype6-dev \
+    libpng-dev \
+    libtiff5-dev \
+    libjpeg-dev \
+    && rm -rf /var/lib/apt/lists/*
+
+RUN Rscript -e "install.packages(c('devtools', 'dataone', 'tidyr', 'redland', 'jsonlite', 'lubridate'))"
+RUN Rscript -e "devtools::install_github('dataoneorg/scythe@v1.0.0', dependencies = TRUE)"
+
+USER scythe:scythe
+
+WORKDIR /var/data/scythe
+
+COPY ./scripts/search.R .
+
+CMD ["Rscript", "--vanilla", "search.R", "urn:node:ARCTIC"]
\ No newline at end of file
diff --git a/helm/scripts/search.R b/helm/scripts/search.R
new file mode 100644
index 0000000..b42b2f1
--- /dev/null
+++ b/helm/scripts/search.R
@@ -0,0 +1,69 @@
+# search.R
+suppressPackageStartupMessages(library(dplyr))
+library(tidyr)
+library(scythe)
+library(dataone)
+library(jsonlite)
+suppressPackageStartupMessages(library(lubridate))
+
+sources <- c("plos", "xdd", "scopus", "springer")
+nodes <- commandArgs(trailingOnly = TRUE)
+
+get_node_dois <- function(node_id) {
+    mn <- getMNode(CNode("PROD"), node_id)
+    queryParamList <- list(q="id:doi*", 
+                           fl="id",
+                           start ="0",
+                           rows = "10")
+    result <- query(mn, solrQuery=queryParamList, as="data.frame", parse=FALSE)
+    return(result$id)
+}
+
+get_metrics_citations <- function(from = as.POSIXct("2000-01-01"), to = as.POSIXct(Sys.Date())){
+    
+    from <- as.Date(from); to <- as.Date(to)
+    from_q <- paste(stringr::str_pad(month(from), 2, side = "left", pad = "0"),
+                    stringr::str_pad(day(from), 2, side = "left", pad = "0"),
+                    stringr::str_pad(year(from), 2, side = "left", pad = "0"),
+                    sep = "/")
+    
+    to_q <- paste(stringr::str_pad(month(to), 2, side = "left", pad = "0"),
+                  stringr::str_pad(day(to), 2, side = "left", pad = "0"),
+                  stringr::str_pad(year(to), 2, side = "left", pad = "0"),
+                  sep = "/")
+    
+    d <- fromJSON(paste0('https://logproc-stage-ucsb-1.test.dataone.org/metrics?q={%22metricsPage%22:{%22total%22:0,%22start%22:0,%22count%22:0},%22metrics%22:[%22citations%22],%22filterBy%22:[{%22filterType%22:%22repository%22,%22values%22:[%22urn:node:ARCTIC%22],%22interpretAs%22:%22list%22},{%22filterType%22:%22month%22,%22values%22:[%22', from_q,'%22,%22', to_q, '%22],%22interpretAs%22:%22range%22}],%22groupBy%22:[%22month%22]}'))
+    
+    output_json <- d$resultDetails$citations # pulls citation info
+    output_df <- as.data.frame(do.call(rbind, output_json), row.names = FALSE) # binds nested cit info into dataframe
+    
+    output_df <- output_df %>% 
+        unnest_longer(target_id) %>% 
+        unnest_longer(source_id)
+    
+    return(output_df)
+}
+
+dois <- c()
+for (node in nodes){
+    node_dois <- get_node_dois(node)
+    dois <- c(dois, node_dois)
+}
+
+# set up file to write to
+today <- format(Sys.Date(), "%Y%m%d")
+fp <- paste0("scythe-citations-", today, ".json")
+
+found_citations <- citation_search(dois, sources)
+
+if (is.null(found_citations) || nrow(found_citations) == 0){
+    writeLines("No citations found.", fp)
+} else {
+    existing_citations <- get_metrics_citations()
+    new_citations <- anti_join(found_citations, existing_citations, by = c("dataset_id" = "target_id", "article_id" = "source_id"))
+    if (nrow(new_citations) > 0) {
+        write_citation_pairs(new_citations, fp)
+    } else {
+        writeLines("No citations found.", fp)
+    }
+}
\ No newline at end of file
diff --git a/helm/templates/NOTES.txt b/helm/templates/NOTES.txt
new file mode 100644
index 0000000..a5c5c5e
--- /dev/null
+++ b/helm/templates/NOTES.txt
@@ -0,0 +1,22 @@
+1. Get the application URL by running these commands:
+{{- if .Values.ingress.enabled }}
+{{- range $host := .Values.ingress.hosts }}
+  {{- range .paths }}
+  http{{ if $.Values.ingress.tls }}s{{ end }}://{{ $host.host }}{{ .path }}
+  {{- end }}
+{{- end }}
+{{- else if contains "NodePort" .Values.service.type }}
+  export NODE_PORT=$(kubectl get --namespace {{ .Release.Namespace }} -o jsonpath="{.spec.ports[0].nodePort}" services {{ include "scythe.fullname" . }})
+  export NODE_IP=$(kubectl get nodes --namespace {{ .Release.Namespace }} -o jsonpath="{.items[0].status.addresses[0].address}")
+  echo http://$NODE_IP:$NODE_PORT
+{{- else if contains "LoadBalancer" .Values.service.type }}
+     NOTE: It may take a few minutes for the LoadBalancer IP to be available.
+           You can watch the status of by running 'kubectl get --namespace {{ .Release.Namespace }} svc -w {{ include "scythe.fullname" . }}'
+  export SERVICE_IP=$(kubectl get svc --namespace {{ .Release.Namespace }} {{ include "scythe.fullname" . }} --template "{{"{{ range (index .status.loadBalancer.ingress 0) }}{{.}}{{ end }}"}}")
+  echo http://$SERVICE_IP:{{ .Values.service.port }}
+{{- else if contains "ClusterIP" .Values.service.type }}
+  export POD_NAME=$(kubectl get pods --namespace {{ .Release.Namespace }} -l "app.kubernetes.io/name={{ include "scythe.name" . }},app.kubernetes.io/instance={{ .Release.Name }}" -o jsonpath="{.items[0].metadata.name}")
+  export CONTAINER_PORT=$(kubectl get pod --namespace {{ .Release.Namespace }} $POD_NAME -o jsonpath="{.spec.containers[0].ports[0].containerPort}")
+  echo "Visit http://127.0.0.1:8080 to use your application"
+  kubectl --namespace {{ .Release.Namespace }} port-forward $POD_NAME 8080:$CONTAINER_PORT
+{{- end }}
diff --git a/helm/templates/_helpers.tpl b/helm/templates/_helpers.tpl
new file mode 100644
index 0000000..161c0d7
--- /dev/null
+++ b/helm/templates/_helpers.tpl
@@ -0,0 +1,62 @@
+{{/*
+Expand the name of the chart.
+*/}}
+{{- define "scythe.name" -}}
+{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" }}
+{{- end }}
+
+{{/*
+Create a default fully qualified app name.
+We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec).
+If release name contains chart name it will be used as a full name.
+*/}}
+{{- define "scythe.fullname" -}}
+{{- if .Values.fullnameOverride }}
+{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" }}
+{{- else }}
+{{- $name := default .Chart.Name .Values.nameOverride }}
+{{- if contains $name .Release.Name }}
+{{- .Release.Name | trunc 63 | trimSuffix "-" }}
+{{- else }}
+{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" }}
+{{- end }}
+{{- end }}
+{{- end }}
+
+{{/*
+Create chart name and version as used by the chart label.
+*/}}
+{{- define "scythe.chart" -}}
+{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }}
+{{- end }}
+
+{{/*
+Common labels
+*/}}
+{{- define "scythe.labels" -}}
+helm.sh/chart: {{ include "scythe.chart" . }}
+{{ include "scythe.selectorLabels" . }}
+{{- if .Chart.AppVersion }}
+app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
+{{- end }}
+app.kubernetes.io/managed-by: {{ .Release.Service }}
+{{- end }}
+
+{{/*
+Selector labels
+*/}}
+{{- define "scythe.selectorLabels" -}}
+app.kubernetes.io/name: {{ include "scythe.name" . }}
+app.kubernetes.io/instance: {{ .Release.Name }}
+{{- end }}
+
+{{/*
+Create the name of the service account to use
+*/}}
+{{- define "scythe.serviceAccountName" -}}
+{{- if .Values.serviceAccount.create }}
+{{- default (include "scythe.fullname" .) .Values.serviceAccount.name }}
+{{- else }}
+{{- default "default" .Values.serviceAccount.name }}
+{{- end }}
+{{- end }}
diff --git a/helm/templates/cron-job.yaml b/helm/templates/cron-job.yaml
new file mode 100644
index 0000000..2c7ab24
--- /dev/null
+++ b/helm/templates/cron-job.yaml
@@ -0,0 +1,34 @@
+apiVersion: batch/v1beta1
+kind: CronJob
+metadata:
+  name: {{ .Values.cronjob.name }}
+spec:
+  schedule: {{ .Values.cronjob.schedule | quote }}
+  successfulJobsHistoryLimit: 5
+  failedJobsHistoryLimit: 5
+  jobTemplate:
+    spec:
+      template:
+        spec:
+          containers:
+            - name: {{ .Chart.Name }}
+              image: {{ .Values.image.repository }}:{{ .Values.image.tag }}
+              imagePullPolicy: {{ .Values.image.pullPolicy }}
+              env:
+                - name: ENV
+                  value: {{ .Values.env }}
+              command:
+                - /bin/sh
+                - -c
+                - |
+                  {{ .Values.cronjob.command }}
+              volumeMounts:
+              - name: {{ .Values.persistence.claimName }}
+                mountPath: {{ .Values.persistence.mountPath }}
+                readOnly: true
+          volumes:
+          - name: {{ .Values.persistence.claimName }}
+            persistentVolumeClaim:
+              claimName: {{ .Values.persistence.claimName }}
+              readOnly: false
+          restartPolicy: OnFailure
\ No newline at end of file
diff --git a/helm/templates/serviceaccount.yaml b/helm/templates/serviceaccount.yaml
new file mode 100644
index 0000000..6d1c954
--- /dev/null
+++ b/helm/templates/serviceaccount.yaml
@@ -0,0 +1,12 @@
+{{- if .Values.serviceAccount.create -}}
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: {{ include "scythe.serviceAccountName" . }}
+  labels:
+    {{- include "scythe.labels" . | nindent 4 }}
+  {{- with .Values.serviceAccount.annotations }}
+  annotations:
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
+{{- end }}
diff --git a/helm/templates/tests/test-connection.yaml b/helm/templates/tests/test-connection.yaml
new file mode 100644
index 0000000..39e17ac
--- /dev/null
+++ b/helm/templates/tests/test-connection.yaml
@@ -0,0 +1,15 @@
+apiVersion: v1
+kind: Pod
+metadata:
+  name: "{{ include "scythe.fullname" . }}-test-connection"
+  labels:
+    {{- include "scythe.labels" . | nindent 4 }}
+  annotations:
+    "helm.sh/hook": test
+spec:
+  containers:
+    - name: wget
+      image: busybox
+      command: ['wget']
+      args: ['{{ include "scythe.fullname" . }}:{{ .Values.service.port }}']
+  restartPolicy: Never
diff --git a/helm/values.yaml b/helm/values.yaml
new file mode 100644
index 0000000..86de802
--- /dev/null
+++ b/helm/values.yaml
@@ -0,0 +1,65 @@
+# Default values for scythe.
+# This is a YAML-formatted file.
+# Declare variables to be passed into your templates.
+
+replicaCount: 1
+
+image:
+  repository: nginx
+  pullPolicy: IfNotPresent
+  # Overrides the image tag whose default is the chart appVersion.
+  tag: ""
+
+imagePullSecrets: []
+nameOverride: ""
+fullnameOverride: ""
+
+persistence:
+  enabled: true
+  claimName: scythe-results
+  mountPath: /var/data/scythe
+
+cronjob:
+  name: scythe
+  schedule: "*/30 * * * *"
+  command: Rscript -e get_citations.R
+
+serviceAccount:
+  # Specifies whether a service account should be created
+  create: false
+  # Annotations to add to the service account
+  annotations: {}
+  # The name of the service account to use.
+  # If not set and create is true, a name is generated using the fullname template
+  name: ""
+
+podAnnotations: {}
+
+podSecurityContext: {}
+  # fsGroup: 2000
+
+securityContext: {}
+  # capabilities:
+  #   drop:
+  #   - ALL
+  # readOnlyRootFilesystem: true
+  # runAsNonRoot: true
+  # runAsUser: 1000
+
+resources: {}
+  # We usually recommend not to specify default resources and to leave this as a conscious
+  # choice for the user. This also increases chances charts run on environments with little
+  # resources, such as Minikube. If you do want to specify resources, uncomment the following
+  # lines, adjust them as necessary, and remove the curly braces after 'resources:'.
+  # limits:
+  #   cpu: 100m
+  #   memory: 128Mi
+  # requests:
+  #   cpu: 100m
+  #   memory: 128Mi
+
+nodeSelector: {}
+
+tolerations: []
+
+affinity: {}

From 5f15347354b7b36483e8bebe09375e6640f3be5c Mon Sep 17 00:00:00 2001
From: Jeanette Clark <jclark@nceas.ucsb.edu>
Date: Tue, 17 Sep 2024 16:51:36 +0000
Subject: [PATCH 03/14] return empty data frame if no token is set

this ensures consistent return behavior amongst various scenarious
---
 R/citation_search_scopus.R   | 18 ++++++++++--------
 R/citation_search_springer.R | 10 +++++++++-
 2 files changed, 19 insertions(+), 9 deletions(-)

diff --git a/R/citation_search_scopus.R b/R/citation_search_scopus.R
index ae7036a..af6951a 100644
--- a/R/citation_search_scopus.R
+++ b/R/citation_search_scopus.R
@@ -19,11 +19,20 @@ citation_search_scopus <- function(identifiers) {
   report_est_wait(length(identifiers), wait_seconds)
 
   key <- scythe_get_key("scopus")
+  
+  # initialize df for storing results in orderly fashion
+  scopus_results <- data.frame(
+      article_id = character(),
+      article_title = character(),
+      dataset_id = character(),
+      source = character()
+  )
+  
   if (is.na(key)) {
     warning(
       "Skipping Scopus search due to missing API key. Set an API key using scythe_set_key() to include Scopus results."
     )
-    return()
+    return(scopus_results)
   }
   identifiers_enc <- utils::URLencode(identifiers, reserved = TRUE)
 
@@ -40,13 +49,6 @@ citation_search_scopus <- function(identifiers) {
       ))
   }
 
-  # initialize df for storing results in orderly fashion
-  scopus_results <- data.frame(
-    article_id = character(),
-    article_title = character(),
-    dataset_id = character(),
-    source = character()
-  )
 
   # extract relevant information from raw results
   for (i in 1:length(results)) {
diff --git a/R/citation_search_springer.R b/R/citation_search_springer.R
index 9fefad7..dfaf27c 100644
--- a/R/citation_search_springer.R
+++ b/R/citation_search_springer.R
@@ -22,13 +22,21 @@ citation_search_springer <- function(identifiers) {
   report_est_wait(length(identifiers), wait_seconds)
 
   identifiers <- check_identifiers(identifiers)
+  
+  # initialize df for storing results in orderly fashion
+  springer_results <- data.frame(
+      article_id = character(),
+      article_title = character(),
+      dataset_id = character(),
+      source = character()
+  )
 
   key <- scythe_get_key("springer")
   if (is.na(key)) {
     warning(
       "Skipping Springer search due to missing API key. Set an API key using scythe_set_key() to include Springer results."
     )
-    return()
+    return(springer_results)
   }
 
   identifiers_enc <- utils::URLencode(identifiers, reserved = TRUE)

From 6ea399756c6a3ce5cfda74c604f47535616def24 Mon Sep 17 00:00:00 2001
From: Jeanette Clark <jclark@nceas.ucsb.edu>
Date: Tue, 17 Sep 2024 13:37:38 -0700
Subject: [PATCH 04/14] update scythe dependency, change script location

---
 helm/Dockerfile | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/helm/Dockerfile b/helm/Dockerfile
index 50042aa..a792f3c 100644
--- a/helm/Dockerfile
+++ b/helm/Dockerfile
@@ -2,6 +2,8 @@ FROM rocker/r-ver:4
 
 RUN groupadd -r scythe && useradd -r -g scythe scythe
 RUN mkdir -p /var/data/scythe && chown scythe.scythe /var/data/scythe
+RUN mkdir -p /apps/scythe && chown scythe.scythe /apps/scythe
+
 
 RUN apt-get update && apt-get install -y \
     librdf-dev \
@@ -20,12 +22,10 @@ RUN apt-get update && apt-get install -y \
     && rm -rf /var/lib/apt/lists/*
 
 RUN Rscript -e "install.packages(c('devtools', 'dataone', 'tidyr', 'redland', 'jsonlite', 'lubridate'))"
-RUN Rscript -e "devtools::install_github('dataoneorg/scythe@v1.0.0', dependencies = TRUE)"
+RUN Rscript -e "devtools::install_github('dataoneorg/scythe@89d52978', dependencies = TRUE)"
 
 USER scythe:scythe
 
 WORKDIR /var/data/scythe
 
-COPY ./scripts/search.R .
-
-CMD ["Rscript", "--vanilla", "search.R", "urn:node:ARCTIC"]
\ No newline at end of file
+COPY ./scripts/search.R /apps/scythe/
\ No newline at end of file

From 48fcdda24770d453de760a3c31e2e54476cb5b46 Mon Sep 17 00:00:00 2001
From: Jeanette Clark <jclark@nceas.ucsb.edu>
Date: Tue, 17 Sep 2024 13:38:22 -0700
Subject: [PATCH 05/14] update helm config to pull correct image and run
 cronjob

---
 helm/templates/NOTES.txt                  | 14 --------------
 helm/templates/cron-job.yaml              | 19 +++++++++++++------
 helm/templates/tests/test-connection.yaml |  2 +-
 helm/values.yaml                          | 16 +++++++++++-----
 4 files changed, 25 insertions(+), 26 deletions(-)

diff --git a/helm/templates/NOTES.txt b/helm/templates/NOTES.txt
index a5c5c5e..0dc54d5 100644
--- a/helm/templates/NOTES.txt
+++ b/helm/templates/NOTES.txt
@@ -5,18 +5,4 @@
   http{{ if $.Values.ingress.tls }}s{{ end }}://{{ $host.host }}{{ .path }}
   {{- end }}
 {{- end }}
-{{- else if contains "NodePort" .Values.service.type }}
-  export NODE_PORT=$(kubectl get --namespace {{ .Release.Namespace }} -o jsonpath="{.spec.ports[0].nodePort}" services {{ include "scythe.fullname" . }})
-  export NODE_IP=$(kubectl get nodes --namespace {{ .Release.Namespace }} -o jsonpath="{.items[0].status.addresses[0].address}")
-  echo http://$NODE_IP:$NODE_PORT
-{{- else if contains "LoadBalancer" .Values.service.type }}
-     NOTE: It may take a few minutes for the LoadBalancer IP to be available.
-           You can watch the status of by running 'kubectl get --namespace {{ .Release.Namespace }} svc -w {{ include "scythe.fullname" . }}'
-  export SERVICE_IP=$(kubectl get svc --namespace {{ .Release.Namespace }} {{ include "scythe.fullname" . }} --template "{{"{{ range (index .status.loadBalancer.ingress 0) }}{{.}}{{ end }}"}}")
-  echo http://$SERVICE_IP:{{ .Values.service.port }}
-{{- else if contains "ClusterIP" .Values.service.type }}
-  export POD_NAME=$(kubectl get pods --namespace {{ .Release.Namespace }} -l "app.kubernetes.io/name={{ include "scythe.name" . }},app.kubernetes.io/instance={{ .Release.Name }}" -o jsonpath="{.items[0].metadata.name}")
-  export CONTAINER_PORT=$(kubectl get pod --namespace {{ .Release.Namespace }} $POD_NAME -o jsonpath="{.spec.containers[0].ports[0].containerPort}")
-  echo "Visit http://127.0.0.1:8080 to use your application"
-  kubectl --namespace {{ .Release.Namespace }} port-forward $POD_NAME 8080:$CONTAINER_PORT
 {{- end }}
diff --git a/helm/templates/cron-job.yaml b/helm/templates/cron-job.yaml
index 2c7ab24..54174a0 100644
--- a/helm/templates/cron-job.yaml
+++ b/helm/templates/cron-job.yaml
@@ -1,4 +1,4 @@
-apiVersion: batch/v1beta1
+apiVersion: batch/v1
 kind: CronJob
 metadata:
   name: {{ .Values.cronjob.name }}
@@ -15,17 +15,24 @@ spec:
               image: {{ .Values.image.repository }}:{{ .Values.image.tag }}
               imagePullPolicy: {{ .Values.image.pullPolicy }}
               env:
-                - name: ENV
-                  value: {{ .Values.env }}
+              - name: springer
+                valueFrom:
+                  secretKeyRef:
+                    name: api-keys
+                    key: springer
+              - name: scopus
+                valueFrom:
+                  secretKeyRef:
+                    name: api-keys
+                    key: scopus
               command:
                 - /bin/sh
                 - -c
-                - |
-                  {{ .Values.cronjob.command }}
+                - {{ .Values.cronjob.command }} {{- range .Values.cronjob.nodes }} {{ . }} {{ end }}
               volumeMounts:
               - name: {{ .Values.persistence.claimName }}
                 mountPath: {{ .Values.persistence.mountPath }}
-                readOnly: true
+                readOnly: false
           volumes:
           - name: {{ .Values.persistence.claimName }}
             persistentVolumeClaim:
diff --git a/helm/templates/tests/test-connection.yaml b/helm/templates/tests/test-connection.yaml
index 39e17ac..41e0f83 100644
--- a/helm/templates/tests/test-connection.yaml
+++ b/helm/templates/tests/test-connection.yaml
@@ -11,5 +11,5 @@ spec:
     - name: wget
       image: busybox
       command: ['wget']
-      args: ['{{ include "scythe.fullname" . }}:{{ .Values.service.port }}']
+      args: ['{{ include "scythe.fullname" . }}:8080']
   restartPolicy: Never
diff --git a/helm/values.yaml b/helm/values.yaml
index 86de802..81308f5 100644
--- a/helm/values.yaml
+++ b/helm/values.yaml
@@ -5,10 +5,10 @@
 replicaCount: 1
 
 image:
-  repository: nginx
-  pullPolicy: IfNotPresent
+  repository: ghcr.io/dataoneorg/scythe
+  pullPolicy: Always
   # Overrides the image tag whose default is the chart appVersion.
-  tag: ""
+  tag: dev
 
 imagePullSecrets: []
 nameOverride: ""
@@ -21,8 +21,11 @@ persistence:
 
 cronjob:
   name: scythe
-  schedule: "*/30 * * * *"
-  command: Rscript -e get_citations.R
+  schedule: "* * 1 * *"
+  command: Rscript --vanilla /apps/scythe/search.R
+  nodes:
+    - urn:node:ARCTIC
+    - urn:node:ESS_DIVE
 
 serviceAccount:
   # Specifies whether a service account should be created
@@ -33,6 +36,9 @@ serviceAccount:
   # If not set and create is true, a name is generated using the fullname template
   name: ""
 
+ingress:
+  enabled: false
+
 podAnnotations: {}
 
 podSecurityContext: {}

From 578a76aad2bde980916b401bb66d841559f995a6 Mon Sep 17 00:00:00 2001
From: Jeanette Clark <jclark@nceas.ucsb.edu>
Date: Tue, 17 Sep 2024 13:38:39 -0700
Subject: [PATCH 06/14] add logging output and search sids for DOIs too

---
 helm/scripts/search.R | 21 +++++++++++++--------
 1 file changed, 13 insertions(+), 8 deletions(-)

diff --git a/helm/scripts/search.R b/helm/scripts/search.R
index b42b2f1..2c08ae6 100644
--- a/helm/scripts/search.R
+++ b/helm/scripts/search.R
@@ -11,12 +11,14 @@ nodes <- commandArgs(trailingOnly = TRUE)
 
 get_node_dois <- function(node_id) {
     mn <- getMNode(CNode("PROD"), node_id)
-    queryParamList <- list(q="id:doi*", 
-                           fl="id",
+    queryParamList <- list(q="id:doi* OR seriesId:doi*", 
+                           fl="id, seriesId",
                            start ="0",
                            rows = "10")
     result <- query(mn, solrQuery=queryParamList, as="data.frame", parse=FALSE)
-    return(result$id)
+    pids <- c(result$id, result$seriesId)
+    dois <- grep("doi:", pids, value = TRUE)
+    return(dois)
 }
 
 get_metrics_citations <- function(from = as.POSIXct("2000-01-01"), to = as.POSIXct(Sys.Date())){
@@ -46,15 +48,18 @@ get_metrics_citations <- function(from = as.POSIXct("2000-01-01"), to = as.POSIX
 
 dois <- c()
 for (node in nodes){
+    message(paste("Gathering DOIs for: ", node)) 
     node_dois <- get_node_dois(node)
     dois <- c(dois, node_dois)
-}
+} 
+dois_unique <- unique(dois)
 
 # set up file to write to
 today <- format(Sys.Date(), "%Y%m%d")
-fp <- paste0("scythe-citations-", today, ".json")
+fp <- paste0("scythe-citations-", today, ".csv") 
 
-found_citations <- citation_search(dois, sources)
+message("Beginning citations search.")
+found_citations <- citation_search(dois_unique, sources) 
 
 if (is.null(found_citations) || nrow(found_citations) == 0){
     writeLines("No citations found.", fp)
@@ -62,8 +67,8 @@ if (is.null(found_citations) || nrow(found_citations) == 0){
     existing_citations <- get_metrics_citations()
     new_citations <- anti_join(found_citations, existing_citations, by = c("dataset_id" = "target_id", "article_id" = "source_id"))
     if (nrow(new_citations) > 0) {
-        write_citation_pairs(new_citations, fp)
+        write.csv(new_citations, fp, row_names = FALSE)
     } else {
-        writeLines("No citations found.", fp)
+        writeLines("No new citations found.", fp)
     }
 }
\ No newline at end of file

From bbafe770190a56bc228e486fda893d63ae09e58e Mon Sep 17 00:00:00 2001
From: Jeanette Clark <jclark@nceas.ucsb.edu>
Date: Tue, 17 Sep 2024 13:38:45 -0700
Subject: [PATCH 07/14] add a readme

---
 helm/README.md | 51 ++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 51 insertions(+)
 create mode 100644 helm/README.md

diff --git a/helm/README.md b/helm/README.md
new file mode 100644
index 0000000..eba7392
--- /dev/null
+++ b/helm/README.md
@@ -0,0 +1,51 @@
+# Scythe Helm Chart
+
+This Helm chart deploys a CronJob that does a citation search on a set of DataONE member nodes using `scythe`.
+
+## Search Script and Container
+
+`scripts/search.R` is copied into the Dockerfile and run in the CronJob. It takes the node identifiers
+listed in the `values.yaml` file as input. DOIs (either identifiers or series identifiers) are retrieved from each node,
+then passed through `scythe::citation_search`, which searches for citations in PLOS, Springer, Scopus, and xDD. Citations
+already in the metrics service are removed, and the citations are written to a csv. This table can be passed to `scythe::write_citation_pairs` to create the JSON file needed for ingest into the metrics system.
+
+## CronJob
+
+In `values.yaml`, key fields to configure are:
+
+- **`cronjob.schedule`**: Schedule for the CronJob (in cron format).
+- **`cronjob.nodes`**: A set of node identifiers to be passed to the R script.
+
+## API Keys
+
+For instructions on obtaining an API key, see README.md at the package level.
+
+Keys are made accessible to the deployment using Kubernetes secrets. To set API keys, run:
+
+```
+kubectl create secret generic -n scythe api-keys \
+  --from-literal=springer={key} \
+  --from-literal=scopus={key}
+```
+
+## Persistent Storage
+
+This Helm chart uses a dynamic PVC using CephFS to save results from the `scythe` run. An example configuration file is shown below.
+For more information on CephFS on the cluster see [k8s-cluster docs](https://github.com/DataONEorg/k8s-cluster/blob/main/storage/Ceph/Ceph-CSI-CephFS.md#provisioning-dynamic-cephfs-volumes).
+
+```
+---
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: scythe-results
+spec:
+  accessModes:
+    - ReadWriteMany
+  resources:
+    requests:
+      storage: 10Gi
+  storageClassName: csi-cephfs-sc
+```
+
+To create the PVC, run `kubectl apply -f pvc.yaml -n scythe`. This should only be done once.
\ No newline at end of file

From 066ab39bfcb5efe8991617fbfe049ee4f4a56d89 Mon Sep 17 00:00:00 2001
From: Jeanette Clark <jclark@nceas.ucsb.edu>
Date: Tue, 17 Sep 2024 14:48:51 -0700
Subject: [PATCH 08/14] update grant

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 5ab7f9a..0a985f4 100644
--- a/README.md
+++ b/README.md
@@ -66,7 +66,7 @@ keyring::key_get("springer", keyring = "scythe")
 ## Acknowledgments
 Work on this package was supported by:
 
-- NSF-PLR grant #1546024 to M. B. Jones, S. Baker-Yeboah, J. Dozier, M. Schildhauer, and A. Budden
+- NSF-PLR grant #2042102 to M. B. Jones, A. Budden, M. Schildhauer, and J. Dozier
 
 [![nceas_footer](https://live-ncea-ucsb-edu-v01.pantheonsite.io/sites/default/files/2020-03/NCEAS-full%20logo-4C.png)](https://www.nceas.ucsb.edu)
 

From 2c68825d93249c324f7273a8edfca1af308d080f Mon Sep 17 00:00:00 2001
From: Jeanette Clark <jclark@nceas.ucsb.edu>
Date: Tue, 17 Sep 2024 16:16:42 -0700
Subject: [PATCH 09/14] update chart to accept named arguments in cmd line
 invocation of R script

---
 helm/Chart.yaml              |  2 +-
 helm/Dockerfile              |  4 +-
 helm/README.md               |  3 +-
 helm/scripts/search.R        | 87 ++++++++++++++++++++----------------
 helm/templates/cron-job.yaml |  6 ++-
 helm/values.yaml             |  8 ++--
 6 files changed, 63 insertions(+), 47 deletions(-)

diff --git a/helm/Chart.yaml b/helm/Chart.yaml
index 9318f95..56e9554 100644
--- a/helm/Chart.yaml
+++ b/helm/Chart.yaml
@@ -21,4 +21,4 @@ version: 0.1.0
 # incremented each time you make changes to the application. Versions are not expected to
 # follow Semantic Versioning. They should reflect the version the application is using.
 # It is recommended to use it with quotes.
-appVersion: "1.0.0"
+appVersion: "1.1.0"
diff --git a/helm/Dockerfile b/helm/Dockerfile
index a792f3c..7419b97 100644
--- a/helm/Dockerfile
+++ b/helm/Dockerfile
@@ -21,8 +21,8 @@ RUN apt-get update && apt-get install -y \
     libjpeg-dev \
     && rm -rf /var/lib/apt/lists/*
 
-RUN Rscript -e "install.packages(c('devtools', 'dataone', 'tidyr', 'redland', 'jsonlite', 'lubridate'))"
-RUN Rscript -e "devtools::install_github('dataoneorg/scythe@89d52978', dependencies = TRUE)"
+RUN Rscript -e "install.packages(c('remotes', 'dataone', 'tidyr', 'redland', 'jsonlite', 'lubridate', 'optparse'))"
+RUN Rscript -e "remotes::install_github('dataoneorg/scythe@89d52978')"
 
 USER scythe:scythe
 
diff --git a/helm/README.md b/helm/README.md
index eba7392..88a5433 100644
--- a/helm/README.md
+++ b/helm/README.md
@@ -14,7 +14,8 @@ already in the metrics service are removed, and the citations are written to a c
 In `values.yaml`, key fields to configure are:
 
 - **`cronjob.schedule`**: Schedule for the CronJob (in cron format).
-- **`cronjob.nodes`**: A set of node identifiers to be passed to the R script.
+- **`cronjob.nodes`**: A set of node identifiers to be passed to the R script, as a comma separated list
+- **`cronjob.rows`**: Optional number of rows to return per node when getting DOIs. Leave empty to return all identifiers
 
 ## API Keys
 
diff --git a/helm/scripts/search.R b/helm/scripts/search.R
index 2c08ae6..0daace3 100644
--- a/helm/scripts/search.R
+++ b/helm/scripts/search.R
@@ -1,74 +1,85 @@
-# search.R
+#!/usr/bin/env Rscript
 suppressPackageStartupMessages(library(dplyr))
 library(tidyr)
 library(scythe)
 library(dataone)
 library(jsonlite)
 suppressPackageStartupMessages(library(lubridate))
+library(optparse)
 
-sources <- c("plos", "xdd", "scopus", "springer")
-nodes <- commandArgs(trailingOnly = TRUE)
+main <- function(){
+    
+    option_list <- list(
+        make_option(c("-r", "--rows"), type="integer", default=100000,
+                    help="Number of rows to return from query [default %default]"),
+        make_option(c("-n", "--nodes"), type="character", help="Comma separated list of nodes to query")
+    )
+    
+    # parse command-line arguments
+    parser <- OptionParser(option_list=option_list)
+    opts <- parse_args(parser)
+    
+    num_rows <- opts$rows
+    nodes <- strsplit(opts$nodes, ",", fixed = TRUE)[[1]]
+    
+    sources <- c("plos", "xdd", "scopus", "springer")
+    
+    dois <- c()
+    for (node in nodes){
+        message(paste("Gathering DOIs for: ", node)) 
+        node_dois <- get_node_dois(node, num_rows)
+        dois <- c(dois, node_dois)
+    } 
+    dois_unique <- unique(dois)
+    
+    # set up file to write to
+    today <- format(Sys.Date(), "%Y%m%d")
+    fp <- paste0("scythe-citations-", today, ".csv") 
+    
+    message("Beginning citations search.")
+    found_citations <- citation_search(dois_unique, sources) 
+    
+    if (is.null(found_citations) || nrow(found_citations) == 0){
+        writeLines("No citations found.", fp)
+    } else {
+        existing_citations <- get_metrics_citations()
+        new_citations <- anti_join(found_citations, existing_citations, by = c("dataset_id" = "target_id", "article_id" = "source_id"))
+        if (nrow(new_citations) > 0) {
+            write.csv(new_citations, fp, row_names = FALSE)
+        } else {
+            writeLines("No new citations found.", fp)
+        }
+    }
+}
 
-get_node_dois <- function(node_id) {
+get_node_dois <- function(node_id, num_rows) {
     mn <- getMNode(CNode("PROD"), node_id)
     queryParamList <- list(q="id:doi* OR seriesId:doi*", 
                            fl="id, seriesId",
                            start ="0",
-                           rows = "10")
+                           rows = num_rows)
     result <- query(mn, solrQuery=queryParamList, as="data.frame", parse=FALSE)
     pids <- c(result$id, result$seriesId)
     dois <- grep("doi:", pids, value = TRUE)
     return(dois)
 }
-
 get_metrics_citations <- function(from = as.POSIXct("2000-01-01"), to = as.POSIXct(Sys.Date())){
-    
     from <- as.Date(from); to <- as.Date(to)
     from_q <- paste(stringr::str_pad(month(from), 2, side = "left", pad = "0"),
                     stringr::str_pad(day(from), 2, side = "left", pad = "0"),
                     stringr::str_pad(year(from), 2, side = "left", pad = "0"),
                     sep = "/")
-    
     to_q <- paste(stringr::str_pad(month(to), 2, side = "left", pad = "0"),
                   stringr::str_pad(day(to), 2, side = "left", pad = "0"),
                   stringr::str_pad(year(to), 2, side = "left", pad = "0"),
                   sep = "/")
-    
     d <- fromJSON(paste0('https://logproc-stage-ucsb-1.test.dataone.org/metrics?q={%22metricsPage%22:{%22total%22:0,%22start%22:0,%22count%22:0},%22metrics%22:[%22citations%22],%22filterBy%22:[{%22filterType%22:%22repository%22,%22values%22:[%22urn:node:ARCTIC%22],%22interpretAs%22:%22list%22},{%22filterType%22:%22month%22,%22values%22:[%22', from_q,'%22,%22', to_q, '%22],%22interpretAs%22:%22range%22}],%22groupBy%22:[%22month%22]}'))
-    
     output_json <- d$resultDetails$citations # pulls citation info
     output_df <- as.data.frame(do.call(rbind, output_json), row.names = FALSE) # binds nested cit info into dataframe
-    
     output_df <- output_df %>% 
         unnest_longer(target_id) %>% 
         unnest_longer(source_id)
-    
     return(output_df)
 }
 
-dois <- c()
-for (node in nodes){
-    message(paste("Gathering DOIs for: ", node)) 
-    node_dois <- get_node_dois(node)
-    dois <- c(dois, node_dois)
-} 
-dois_unique <- unique(dois)
-
-# set up file to write to
-today <- format(Sys.Date(), "%Y%m%d")
-fp <- paste0("scythe-citations-", today, ".csv") 
-
-message("Beginning citations search.")
-found_citations <- citation_search(dois_unique, sources) 
-
-if (is.null(found_citations) || nrow(found_citations) == 0){
-    writeLines("No citations found.", fp)
-} else {
-    existing_citations <- get_metrics_citations()
-    new_citations <- anti_join(found_citations, existing_citations, by = c("dataset_id" = "target_id", "article_id" = "source_id"))
-    if (nrow(new_citations) > 0) {
-        write.csv(new_citations, fp, row_names = FALSE)
-    } else {
-        writeLines("No new citations found.", fp)
-    }
-}
\ No newline at end of file
+main()
diff --git a/helm/templates/cron-job.yaml b/helm/templates/cron-job.yaml
index 54174a0..79de389 100644
--- a/helm/templates/cron-job.yaml
+++ b/helm/templates/cron-job.yaml
@@ -28,7 +28,11 @@ spec:
               command:
                 - /bin/sh
                 - -c
-                - {{ .Values.cronjob.command }} {{- range .Values.cronjob.nodes }} {{ . }} {{ end }}
+                - {{- if .Values.cronjob.rows }}
+                    {{ .Values.cronjob.command }} -r {{ .Values.cronjob.rows }} -n {{ .Values.cronjob.nodes }}
+                  {{- else }}
+                    {{ .Values.cronjob.command }} -n {{ .Values.cronjob.nodes }}
+                  {{- end }}
               volumeMounts:
               - name: {{ .Values.persistence.claimName }}
                 mountPath: {{ .Values.persistence.mountPath }}
diff --git a/helm/values.yaml b/helm/values.yaml
index 81308f5..033b68a 100644
--- a/helm/values.yaml
+++ b/helm/values.yaml
@@ -21,11 +21,11 @@ persistence:
 
 cronjob:
   name: scythe
-  schedule: "* * 1 * *"
+  schedule: "0 12 1 * *"
   command: Rscript --vanilla /apps/scythe/search.R
-  nodes:
-    - urn:node:ARCTIC
-    - urn:node:ESS_DIVE
+  nodes: 'urn:node:ARCTIC,urn:node:ESS_DIVE'
+  # leave blank if returning all rows
+  rows:
 
 serviceAccount:
   # Specifies whether a service account should be created

From 704d52ec708827a0a58cbaa0f1dca6b4e2b7d806 Mon Sep 17 00:00:00 2001
From: Jeanette Clark <jclark@nceas.ucsb.edu>
Date: Tue, 17 Sep 2024 16:23:41 -0700
Subject: [PATCH 10/14] update scythe version in dockerfile

---
 helm/Dockerfile  | 2 +-
 helm/values.yaml | 2 --
 2 files changed, 1 insertion(+), 3 deletions(-)

diff --git a/helm/Dockerfile b/helm/Dockerfile
index 7419b97..3c9b11a 100644
--- a/helm/Dockerfile
+++ b/helm/Dockerfile
@@ -22,7 +22,7 @@ RUN apt-get update && apt-get install -y \
     && rm -rf /var/lib/apt/lists/*
 
 RUN Rscript -e "install.packages(c('remotes', 'dataone', 'tidyr', 'redland', 'jsonlite', 'lubridate', 'optparse'))"
-RUN Rscript -e "remotes::install_github('dataoneorg/scythe@89d52978')"
+RUN Rscript -e "remotes::install_github('dataoneorg/scythe@v1.1.0')"
 
 USER scythe:scythe
 
diff --git a/helm/values.yaml b/helm/values.yaml
index 033b68a..b0de420 100644
--- a/helm/values.yaml
+++ b/helm/values.yaml
@@ -7,8 +7,6 @@ replicaCount: 1
 image:
   repository: ghcr.io/dataoneorg/scythe
   pullPolicy: Always
-  # Overrides the image tag whose default is the chart appVersion.
-  tag: dev
 
 imagePullSecrets: []
 nameOverride: ""

From 4193dfba0b76d7992eea466860afb114a53a086e Mon Sep 17 00:00:00 2001
From: Jeanette Clark <jclark@nceas.ucsb.edu>
Date: Tue, 17 Sep 2024 17:01:01 -0700
Subject: [PATCH 11/14] keep both grants in readme

---
 README.md | 1 +
 1 file changed, 1 insertion(+)

diff --git a/README.md b/README.md
index 0a985f4..08ce1b9 100644
--- a/README.md
+++ b/README.md
@@ -66,6 +66,7 @@ keyring::key_get("springer", keyring = "scythe")
 ## Acknowledgments
 Work on this package was supported by:
 
+- NSF-PLR grant #1546024 to M. B. Jones, S. Baker-Yeboah, J. Dozier, M. Schildhauer, and A. Budden
 - NSF-PLR grant #2042102 to M. B. Jones, A. Budden, M. Schildhauer, and J. Dozier
 
 [![nceas_footer](https://live-ncea-ucsb-edu-v01.pantheonsite.io/sites/default/files/2020-03/NCEAS-full%20logo-4C.png)](https://www.nceas.ucsb.edu)

From c929974fb9a6dd46c8aec84f8cef82b6db673c17 Mon Sep 17 00:00:00 2001
From: Jeanette Clark <jclark@nceas.ucsb.edu>
Date: Tue, 17 Sep 2024 17:01:22 -0700
Subject: [PATCH 12/14] make chart version same as app version

---
 helm/Chart.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/helm/Chart.yaml b/helm/Chart.yaml
index 56e9554..889c2df 100644
--- a/helm/Chart.yaml
+++ b/helm/Chart.yaml
@@ -15,7 +15,7 @@ type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
 # Versions are expected to follow Semantic Versioning (https://semver.org/)
-version: 0.1.0
+version: 1.1.0
 
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application. Versions are not expected to

From 37c24b276d4ee0c5976bef65a5aae3cafbaf691a Mon Sep 17 00:00:00 2001
From: Jeanette Clark <jclark@nceas.ucsb.edu>
Date: Wed, 18 Sep 2024 09:46:40 -0700
Subject: [PATCH 13/14] increment version

---
 DESCRIPTION | 2 +-
 README.md   | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/DESCRIPTION b/DESCRIPTION
index 4ee6e2b..61e8fc7 100644
--- a/DESCRIPTION
+++ b/DESCRIPTION
@@ -1,6 +1,6 @@
 Package: scythe
 Title: Harvest and register data package citations 
-Version: 1.0.0
+Version: 1.1.0
 Authors@R: c(
     person("Jeanette", "Clark", role = c("aut", "cre"), email = "jclark@nceas.ucsb.edu", comment=c(ORCID = "0000-0003-4703-1974")),
     person("Matthew B.", "Jones", role = "aut", email = "jones@nceas.ucsb.edu", comment=c(ORCID = "0000-0003-0077-4738")),
diff --git a/README.md b/README.md
index 08ce1b9..de0a761 100644
--- a/README.md
+++ b/README.md
@@ -16,7 +16,7 @@ including Scopus, PLOS, Springer, and XDD.
 ### Released version
 
 ```
-remotes::install_github("DataONEorg/scythe@v1.0.0")
+remotes::install_github("DataONEorg/scythe@v1.1.0")
 ```
 
 The *scythe* R package should be available for use at this point.

From b8ba920d8c9f28f2aeb435720430a88f7bd65fd1 Mon Sep 17 00:00:00 2001
From: Jeanette Clark <jclark@nceas.ucsb.edu>
Date: Wed, 18 Sep 2024 11:45:34 -0700
Subject: [PATCH 14/14] update version and add default image tag

---
 helm/Chart.yaml              | 4 ++--
 helm/templates/cron-job.yaml | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/helm/Chart.yaml b/helm/Chart.yaml
index 889c2df..048695d 100644
--- a/helm/Chart.yaml
+++ b/helm/Chart.yaml
@@ -15,10 +15,10 @@ type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
 # Versions are expected to follow Semantic Versioning (https://semver.org/)
-version: 1.1.0
+version: "v1.1.0"
 
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application. Versions are not expected to
 # follow Semantic Versioning. They should reflect the version the application is using.
 # It is recommended to use it with quotes.
-appVersion: "1.1.0"
+appVersion: "v1.1.0"
diff --git a/helm/templates/cron-job.yaml b/helm/templates/cron-job.yaml
index 79de389..2973aae 100644
--- a/helm/templates/cron-job.yaml
+++ b/helm/templates/cron-job.yaml
@@ -12,7 +12,7 @@ spec:
         spec:
           containers:
             - name: {{ .Chart.Name }}
-              image: {{ .Values.image.repository }}:{{ .Values.image.tag }}
+              image: {{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}
               imagePullPolicy: {{ .Values.image.pullPolicy }}
               env:
               - name: springer