Build(#81): Workflow to pull and update data on a schedule

.github/workflows/update_mdeb_data.yaml

@@ -1,121 +1,72 @@
-name: pull data from MDEB data hub
+name: pull-data-from-MDEB-data-hub
 
 on:
-  push:
-    branches:
-      - main2
-  pull_request:
-    branches:
-      - main2
-  #schedule:
+  workflow_dispatch:
+  schedule:
     # uses UTC/GMT time (+ 5 hrs)
     ## put on HOLD temporarily
-    #- cron: "0 17 * * 3" # Every Wednesday at 1200 hrs = 1700 UTC
+    - cron: "0 17 * * 6" # Every Saturday at 1200 hrs = 1700 UTC
 
 
 jobs:
 
   build:
     runs-on: ubuntu-latest
     env:
-      GITHUB_PAT: ${{ secrets.GH_RELEASE }}
-      R_REMOTES_NO_ERRORS_FROM_WARNINGS: false
+      GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+    permissions:
+      contents: write
+      pull-requests: write
 
     steps:
       - name: Checkout repo
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
         with:
           fetch-depth: 0
 
       - name: set up pandoc
         uses: r-lib/actions/setup-pandoc@v2
 
+      - name: Set up R
+        uses: r-lib/actions/setup-r@v2
+        with:
+          r-version: '4.2.0'
+
+
+      - name: Install system dependencies
+        uses: r-lib/actions/setup-r-dependencies@v2
+
       - name: Install command line packages
         run: |
           sudo apt update
-          sudo apt-get install libcurl4-openssl-dev libgit2-dev
+          sudo apt-get install libcurl4-openssl-dev libgit2-dev libudunits2-dev
 #          sudo apt-get install  libgdal-dev libcurl4-gnutls-dev libgit2-dev libudunits2-dev libharfbuzz-dev libfribidi-dev
         shell: bash
 
-      - name: Set up R
-        uses: r-lib/actions/setup-r@v2
-        with:
-          r-version: '4.2.0'
 
       - name: Install packages
         run: |
-          install.packages(c("remotes","jsonlite", "dplyr", "httr2", "here", "sf","rmarkdown"))
+          install.packages(c("remotes","here","httr2","jsonlite","dplyr","glue"))
           remotes::install_github("NEFSC/NEFSC-Spatial")
         shell: Rscript {0}
 
       - name: Pull MDEB data and save to repo
         run: |
           options(timeout = 60 * 60 * 6)
           source(here::here("data-raw/get_mdeb_for_package.R"))
-          get_mdeb_for_package()
+          get_mdeb_for_package(overwrite = TRUE)
         shell: Rscript {0}
 
-   - name: Make Comparisons for commit
-      # check for new data added or data omitted. Not concerned with data fixes
-      # update NEWS.md, DESCRIPTION with version/notes
-      # increments package version in description
-        run: |
-          options(timeout = 60 * 60 * 6)
-          source(here::here("data-raw/compare_data.r"))
-          source(here::here("data-raw/update_description.R"))
-          source(here::here("data-raw/update_news.R"))
-          diffs <- compare_data()
-          version <- update_description(diffs, digit=3)
-          update_news(version, diffs)
-          rmarkdown::render(here::here("data-raw/sendAsEmail.Rmd"),
-                    params = diffs)
-
-          saveRDS(version,here::here("data-raw/version.rds"))
-        shell: Rscript {0}
-
-      - name: render readme.rmd
-        run: |
-          options(timeout = 60 * 60 * 6)
-          rmarkdown::render(here::here("README.Rmd"))
-        shell: Rscript {0}
-
-      # Send email indicating if anything has changed
-      # - name: Send email
-      #   uses: dawidd6/action-send-mail@v3
-      #
-      #   with:
-      #     server_address: smtp.gmail.com
-      #     server_port: 465
-      #
-      #     username: ${{ secrets.MAIL_USERNAME }}
-      #     password: ${{ secrets.MAIL_PASSWORD }}
-      #
-      #     subject: Github Actions job result
-      #     to: andrew.beet@noaa.gov
-      #
-      #     from: NEFSCspatial GitHub
-      #
-      #     #body: file://${{github.workspace}}/data-raw/datapull.txt
-      #
-      #     html_body: file://${{github.workspace}}/data-raw/sendAsEmail.html
-      #
-      #     #attachments: ./data-raw/sendAsEmail.html
-      #
-      # - name: commit data files
-      #   run: |
-      #     git config user.name github-actions
-      #     git config user.email github-actions@github.com
-      #     git add data/*
-      #     git add README.md
-      #     git add NEWS.md
-      #     git add DESCRIPTION
-      #     git commit -m "automated mdeb pull from update_mdeb_data yml"
-      #     git push
-      #
-      # - name: create gh-release
-      #   run: |
-      #       version <- readRDS(here::here("data-raw/version.rds"))
-      #       if(!is.null(version)){
-      #       usethis::use_github_release(publish = TRUE)
-      #       }
-      #   shell: Rscript {0}
+      # Create the Pull Request from dev if changes are detected
+      - name: Create Pull Request
+        uses: peter-evans/create-pull-request@v8.1.1
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+          commit-message: "chore: update external data"
+          title: "Automated Data Update"
+          body: |
+            This is an automated pull request containing the latest fetched data.
+            Please review the changes before merging.
+          branch: automated-data-update
+          base: dev
+          delete-branch: false