Add spell-checking that is run by CI

.github/workflows/spellcheck.yml

@@ -0,0 +1,45 @@
+# SPDX-License-Identifier: Apache-2.0
+
+name: Spellcheck
+
+on:
+  push:
+    branches:
+      - "main"
+    paths:
+      - '**.md'
+      - '.github/workflows/spellcheck.yml' # This workflow
+  pull_request:
+    branches:
+      - "main"
+    paths:
+      - '**.md'
+      - '.github/workflows/spellcheck.yml' # This workflow
+
+env:
+  LC_ALL: en_US.UTF-8
+
+defaults:
+  run:
+    shell: bash
+
+permissions:
+  contents: read
+
+jobs:
+  spellcheck:
+    name: Spellcheck (en_US)
+    runs-on: ubuntu-latest
+    steps:
+      - name: "Harden Runner"
+        uses: step-security/harden-runner@a4aa98b93cab29d9b1101a6143fb8bce00e2eac4 # v2.7.1
+        with:
+         egress-policy: audit # TODO: change to 'egress-policy: block' after couple of runs
+
+      - name: "Checkout"
+        uses: actions/checkout@0ad4b8fadaa221de15dcec353f45205ec38ea70b # v4.1.4
+        with:
+          fetch-depth: 0
+
+      - name: Spellcheck
+        uses: rojopolis/spellcheck-github-actions@dbd2f1da869c05ad874fffeb6fe1ed50cd1a6e98 # v0.36.0

.spellcheck-en-custom.txt

@@ -0,0 +1,259 @@
+
+# make spellcheck-sort
+# Please keep this file sorted:
+# SPDX-License-Identifier: Apache-2.0
+Aakanksha
+aakankshaduggal
+abhi
+Abramson
+Acknowledgements
+Adminstrators
+akashgit
+al
+aldopareja
+alimaredia
+Alina
+alinaryan
+Anh
+anik
+Anza
+Approver
+Approvers
+AQuA
+Arapahoe
+ARB
+arge
+Asghar
+Ashgar
+backend
+Bernardino
+bjhargrave
+Boelkins
+bootable
+bootc
+Byars
+Bzostek
+caradelia
+CDLA
+cdoern
+CHANGELOG
+Chatbot
+Choi
+ckadner
+CLI
+CNCF
+coc
+CoCC's
+codebase
+codebases
+compositional
+Conala
+Corbett
+curation
+cybette
+danmcp
+darrellreimer
+datacenter
+Dataset
+dataset
+datasets
+dave
+DCO
+De
+deployable
+DeSaix
+dev
+DM
+Doern
+Duggal
+Eder
+Eggebrecht
+EPEL
+et
+Fraknoi
+Freeform
+freeform
+Frontend
+frontend
+Gair
+gcc
+Greenlaw
+GSM
+Haver
+Helpsteer
+HH
+hickeyma
+Hidaka
+Hinrichs
+Huben
+ibm
+ics
+ilab
+Illowsky
+inglis
+InstructLab
+integrations
+Jaideep
+jaideepr
+JamesKunstle
+Janssen
+jeremyeder
+JJ
+jjasghar
+joesepi
+Jolla
+Jonick
+judgement
+juliadenham
+Keene
+kelbrown
+khaledsulayman
+Kickstart
+kickstart
+Kordas
+Korol
+Kruse
+Kubernetes
+Kunstle
+Lenovo
+LGTM
+LGTMs
+lhawthorn
+lignment
+LLM
+LLM's
+Lovett
+luke
+Lund
+Lyryx
+Mahbobi
+Maintainership
+maintainership
+mairin
+Máirín
+Makefiles
+Maredia
+markstur
+Marymount
+Masaki
+McElaney
+md
+Merlinite
+mingxzhao
+Miniforge
+Mixtral
+mmcelaney
+MMLU
+Moebs
+mrutkows
+mscherer
+Multivariable
+Musique
+nathan
+nerdalert
+Neth
+NOIRLab
+noone
+Norwood
+NumGLUE
+nvidia
+OASST
+obuzek
+OCI
+ODC
+oindrillac
+Oksana
+Oleg
+openbookQA
+Oswego
+ots
+overfitting
+Pfannestiel
+PII
+Podman
+Prahl
+pre
+Precalculus
+PRM
+pyenv
+PyPI
+pypi
+qa
+quantized
+Quinnipiac
+Rao
+README
+Rebecca
+Redbooks
+redbooks
+Repo
+repo
+resynthesizes
+RHEL
+RHLF
+RHUI
+Roadmap
+Roush
+runtime
+russellb
+Saftey
+Sandhills
+Sanny
+Schlicker
+Schneegurt
+Seminario
+Sepi
+SETI
+sexualized
+shivchander
+signoff
+signoffs
+Silkin
+socio
+soltysh
+SPDX
+Spelman
+Spielman
+spzala
+Stanberry
+Standup
+subdirectory
+Sudalairaj
+supermajority
+Tatlock
+TBD
+templated
+Theopold
+Thi
+Tiemann
+TODO
+Toolbx
+transactional
+Triager
+triagers
+Triaging
+UI
+Urone
+USC
+userspace
+Usings
+Ventura
+venv
+Vickery
+vishnoianil
+VLLM
+Volker
+Vretta
+Wakefield
+Waskiewicz
+weinberg
+Wikimedia
+wikimultihop
+wordmarks
+workstreams
+xukai
+YAML
+yhwang
+Zach
+Zedalis
+Zimmitti

.spellcheck.yml

@@ -0,0 +1,28 @@
+# SPDX-License-Identifier: Apache-2.0
+
+matrix:
+- name: markdown
+  aspell:
+    lang: en
+    d: en_US
+    camel-case: true
+    mode: markdown
+  sources:
+  - "**/*.md|!.tox/**|!training/**"
+  dictionary:
+    wordlists:
+    - .spellcheck-en-custom.txt
+  pipeline:
+  - pyspelling.filters.context:
+      context_visible_first: true
+      escapes: '\\[\\`~]'
+      delimiters:
+      # Ignore multiline content between fences (fences can have 3 or more back ticks)
+      # ```language
+      # content
+      # ```
+      - open: '(?s)^(?P<open> *`{3,}).*?$'
+        close: '^(?P=open)$'
+      # Ignore text between inline back ticks
+      - open: '(?P<open>`+)'
+        close: '(?P=open)'

Makefile

@@ -34,6 +34,14 @@ update-training-dir: ## Update the contents of the training directory
 	$(CMD_PREFIX) rm -rf ai-lab-recipes
 	$(CMD_PREFIX) git add training
 
+.PHONY: spellcheck
+spellcheck:
+	$(CMD_PREFIX) python -m pyspelling --config .spellcheck.yml --spellchecker aspell
+
+.PHONY: spellcheck-sort
+spellcheck-sort: .spellcheck-en-custom.txt
+	$(CMD_PREFIX) sort -d -f -o $< $<
+
 # Catch-all target to pass through any other target to the training directory
 %:
 	$(CMD_PREFIX) make -C training $@