Merge branch 'main' into vector-database

.github/CODEOWNERS

@@ -1 +1 @@
-*  @hdhalter @kolchfa-aws @Naarcha-AWS @vagimeli @AMoo-Miki @natebower @dlvenable
+*  @hdhalter @kolchfa-aws @Naarcha-AWS @vagimeli @AMoo-Miki @natebower @dlvenable @scrawfor99 @epugh

.github/vale/styles/OpenSearch/LinksDoubleParentheses.yml

@@ -1,8 +1,8 @@
 extends: existence
-message: "Remove double slashes from the link '%s'."
+message: "Remove double parentheses from the link '%s'."
 level: error
 nonword: true
 scope: raw
 tokens:
-  - '\[.*\](\(){2,}.*(\)){1,}'
-  - '\[.*\](\(){1,}.*(\)){2,}'
+  - '\]\({2,}[^)]*?\){1,}'
+

.github/vale/styles/OpenSearch/LinksDoubleSlash.yml

@@ -4,4 +4,4 @@ level: error
 nonword: true
 scope: raw
 tokens:
-  - '\(\{\{site.url\}\}\{\{site.baseurl\}\}.*\/{2,}.*\)'
+  - '\(\{\{site.url\}\}\{\{site.baseurl\}\}[^)]*?\/{2,}[^)]*?\)'

.github/vale/styles/OpenSearch/SpacingWords.yml

@@ -1,5 +1,5 @@
 extends: existence
-message: "There should be once space between words in '%s'."
+message: "There should be one space between words in '%s'."
 level: error
 nonword: true
 tokens:

.github/vale/styles/OpenSearch/SubstitutionsError.yml

@@ -23,7 +23,8 @@ swap:
   'Huggingface': Hugging Face
   'indices': indexes
   'ingestion pipeline': ingest pipeline
-  'keystore': key store
+  'key store': keystore
+  'key/value': key-value
   'kmeans': k-means
   'kNN': k-NN
   'machine-learning': machine learning
@@ -46,7 +47,7 @@ swap:
   'time stamp': timestamp
   'timezone': time zone
   'tradeoff': trade-off
-  'truststore': trust store
+  'trust store': truststore
   'U.S.': US
   'web page': webpage
   'web site': website

.github/vale/styles/Vocab/OpenSearch/Plugins/accept.txt

@@ -4,6 +4,7 @@ Asynchronous Search plugin
 Crypto plugin
 Cross-Cluster Replication plugin
 Custom Codecs plugin
+Flow Framework plugin
 Maps plugin
 Notebooks plugin
 Notifications plugin
@@ -19,6 +20,7 @@ ML Commons plugin
 Neural Search plugin
 Observability plugin
 Performance Analyzer plugin
+Query Insights plugin
 Query Workbench plugin
 Search Relevance plugin
 Security plugin

.github/vale/styles/Vocab/OpenSearch/Products/accept.txt

@@ -59,6 +59,8 @@ Open Distro
 OpenAI
 OpenID Connect
 OpenSearch
+OpenSearch Assistant
+OpenSearch Assistant Toolkit
 OpenSearch Benchmark
 OpenSearch Dashboards
 OpenSearch Playground

.github/vale/styles/Vocab/OpenSearch/Words/accept.txt

@@ -20,11 +20,13 @@ Boolean
 [Dd]eallocate
 [Dd]eduplicates?
 [Dd]eduplication
+[Dd]eprovision(s|ed|ing)?
 [Dd]eserialize
 [Dd]eserialization
 Dev
 [Dd]iscoverability
 Distro
+[Dd]ownvote(s|d)?
 [Dd]uplicative
 [Ee]gress
 [Ee]num
@@ -75,7 +77,11 @@ Levenshtein
 [Mm]ultivalued
 [Mm]ultiword
 [Nn]amespace
+[Oo]versamples?
+[Oo]nboarding
 pebibyte
+[Pp]erformant
+[Pp]laintext
 [Pp]luggable
 [Pp]reconfigure
 [Pp]refetch
@@ -87,6 +93,7 @@ pebibyte
 [Pp]reprocess
 [Pp]retrain
 [Pp]seudocode
+[Quantiz](e|ation|ing|er)
 [Rr]ebalance
 [Rr]ebalancing
 [Rr]edownload
@@ -103,6 +110,7 @@ pebibyte
 [Ss]erverless
 [Ss]harding
 [Ss]ignificand
+[Ss]napshott(ed|ing)
 stdout
 [Ss]temmers?
 [Ss]ubaggregation
@@ -117,21 +125,25 @@ stdout
 [Ss]ubvector
 [Ss]ubwords?
 [Ss]uperset
+[Ss]yslog
 tebibyte
 [Tt]emplated
 [Tt]okenization
 [Tt]okenizer?
 [Tt]ooltip
 [Tt]ranslog
+[Tt]ruststore
 [Uu]nary
 [Uu]ncheck
 [Uu]ncomment
 [Uu]ndeploy
 [Uu]nigram
 [Uu]nnesting
 [Uu]nrecovered
+[Uu]nregister(s|ed|ing)?
 [Uu]pdatable
 [Uu]psert
+[Uu]pvote(s|d)?
 [Ww]alkthrough
 [Ww]ebpage
 xy

.github/vale/tests/test-style-neg.md

@@ -2,8 +2,6 @@
 
 This sentence tests Advanced Placement (AP). We should define AP before using.
 
-Then this sentence tests adverbs of time.
-
 This sentence tests cybersecurity.
 
 This sentence tests dash---spacing.

.github/vale/tests/test-style-pos.md

@@ -2,8 +2,6 @@
 
 This sentence tests AP. AP should be defined before using.
 
-Then, this sentence tests adverbs of time.
-
 This sentence tests cyber security.
 
 This sentence tests dash --- spacing.

.github/workflows/automerge-backport.yml

@@ -0,0 +1,33 @@
+name: Automerge Backport
+on:
+  pull_request:
+  pull_request_review:
+    types:
+      - submitted
+  check_suite:
+    types:
+      - completed
+  status: {}
+jobs:
+  automerge-backport:
+    if: |
+      github.repository == 'opensearch-project/documentation-website' &&
+      startsWith(github.event.pull_request.head.ref, 'backport/')
+    runs-on: ubuntu-latest
+    steps:
+      - name: Wait some time so that label and approval is up
+        run: sleep 30
+      - id: automerge
+        name: automerge
+        uses: "pascalgn/[email protected]"
+        env:
+          GITHUB_TOKEN: "${{ secrets.GITHUB_TOKEN }}"
+          MERGE_LABELS: "backport-automerge,!On hold"
+          MERGE_FILTER_AUTHOR: "opensearch-trigger-bot[bot]"
+          MERGE_REQUIRED_APPROVALS: "1"
+          MERGE_RETRIES: "20"
+          MERGE_RETRY_SLEEP: "10000"
+          MERGE_ERROR_FAIL: "true"
+          MERGE_FORKS: "false"
+          MERGE_METHOD: "squash"
+          MERGE_DELETE_BRANCH: "true"

.github/workflows/backport.yml

@@ -16,6 +16,7 @@ jobs:
     # See https://docs.github.com/en/actions/using-workflows/events-that-trigger-workflows#pull_request_target.
     if: >
       github.event.pull_request.merged
+      && github.repository == 'opensearch-project/documentation-website'
       && (
         github.event.action == 'closed'
         || (
@@ -38,3 +39,25 @@ jobs:
         with:
           github_token: ${{ steps.github_app_token.outputs.token }}
           head_template: backport/backport-<%= number %>-to-<%= base %>
+
+      - name: Label new backport PR with backport-automerge label
+        run: |
+          PR_LABELS=`echo "${{ toJson(github.event.pull_request.labels.*.name) }}" | sed -e 's/\[//g;s/\]//g;s/^\s*//g;s/\s*$//g' | tr -d '\n'`
+          echo $PR_LABELS
+          OLDIFS=$IFS
+          export IFS=','
+          for label in $PR_LABELS
+          do
+            if [[ "$label" == "backport"* ]]; then
+              echo "Found label \"$label\""
+              PR_REPO="opensearch-project/documentation-website"
+              PR_BRANCH=backport/backport-${{ github.event.pull_request.number }}-to-`echo $label | cut -d ' ' -f2`
+              PR_NUMBER=`gh pr list -R $PR_REPO --json "number,headRefName" --state open | jq -r ".[] | select(.headRefName == \"$PR_BRANCH\") | .number"`
+              echo "Update Backport PR '#$PR_NUMBER' on branch '$PR_BRANCH' with 'backport-automerge' label"
+              gh issue edit -R $PR_REPO $PR_NUMBER --add-label backport-automerge
+              echo "Auto approve $PR_REPO PR #$PR_NUMBER with opensearch-trigger-bot"
+              gh pr review -R $PR_REPO $PR_NUMBER --approve
+            fi
+          done
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/delete_merged_branch.yml

@@ -0,0 +1,22 @@
+name: Delete merged branch of the PRs
+on:
+  pull_request:
+    types:
+      - closed
+
+jobs:
+  delete-branch:
+    runs-on: ubuntu-latest
+    if: |
+      github.repository == 'opensearch-project/documentation-website' &&
+      ${{ !startsWith(github.event.pull_request.head.ref, 'main') }} &&
+      ${{ !startsWith(github.event.pull_request.head.ref, '1.') }} &&
+      ${{ !startsWith(github.event.pull_request.head.ref, '2.') }} &&
+      ${{ !startsWith(github.event.pull_request.head.ref, 'version/') }}
+    steps:
+      - name: Echo remove branch
+        run: echo Removing ${{github.event.pull_request.head.ref}}
+      - name: Delete merged branch
+        uses: SvanBoxel/delete-merged-branch@main
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/encoding-check.yml

@@ -0,0 +1,27 @@
+name: Encoding Checker
+
+on: [pull_request]
+
+jobs:
+  encoding-checker:
+    runs-on: ubuntu-latest
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v3
+    - name: Check for possible file that does not follow utf-8 encoding
+      run: |
+          set +e
+          IFS=$(echo -en "\n\b")
+          COUNTER=0
+          for i in `find . -type f \( -name "*.txt" -o -name "*.md" -o -name "*.markdown" -o -name "*.html" \) | grep -vE "^./.git"`;
+          do
+              grep -axv '.*' "$i"
+              if [ "$?" -eq 0 ]; then
+                  echo -e "######################\n$i\n######################"
+                  COUNTER=$(( COUNTER + 1 ))
+              fi
+          done
+          if [ "$COUNTER" != 0 ]; then
+              echo "Found files that is not following utf-8 encoding, exit 1"
+              exit 1
+          fi

.github/workflows/jekyll-build.yml

@@ -3,14 +3,14 @@ name: Jekyll Build Verification
 on: [pull_request]
 
 jobs:
-  check:
+  jekyll-build:
     runs-on: ubuntu-latest
 
     steps:
     - uses: actions/checkout@v3
     - uses: ruby/setup-ruby@v1
       with:
-        ruby-version: '3.0'
+        ruby-version: '3.2'
         bundler-cache: true
     - run: |
         JEKYLL_FATAL_LINK_CHECKER=internal bundle exec jekyll build --future

.github/workflows/link-checker.yml

@@ -4,7 +4,7 @@ on:
   schedule:
     - cron: "30 11 * * 0"
 jobs:
-  check:
+  link-checker:
     if: github.repository == 'opensearch-project/documentation-website'
     runs-on: ubuntu-latest
     steps:

.github/workflows/vale.yml

@@ -1,4 +1,4 @@
-name: Style check
+name: Style Check
 
 on:
   pull_request:
@@ -20,4 +20,5 @@ jobs:
           reporter: github-pr-check
           filter_mode: added
           vale_flags: "--no-exit"
-          version: 2.28.0
+          version: 2.28.0
+        continue-on-error: true

.vale.ini

@@ -19,7 +19,6 @@ Vale.Spelling = NO
 Vale.Repetition = NO
 Vale.Terms = YES
 OpenSearch.AcronymParentheses = YES
-OpenSearch.AdverbsOfTime = YES
 OpenSearch.Ampersand = YES
 OpenSearch.Cyber = YES
 OpenSearch.DashSpacing = YES