initial commit of helm stuff

Dockerfile and script are working correctly in isolation, neext need to connect to helm templates

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/

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"

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/[email protected]', dependencies = TRUE)"
+
+USER scythe:scythe
+
+WORKDIR /var/data/scythe
+
+COPY ./scripts/search.R .
+
+CMD ["Rscript", "--vanilla", "search.R", "urn:node:ARCTIC"]

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)
+    }
+}

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 }}

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 }}

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

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 }}

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

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: {}