[WTH Core] Adding a spell checker to all pull requests (microsoft#611)

* Create create-new-hack.yml

* Update create-new-hack.yml

* spell check init

* Spell check (#2)

* Create create-new-hack.yml

* Update create-new-hack.yml

* spell check init

* path to cspell.json

* spell check

* rename

* Spell check (#3)

* Create create-new-hack.yml

* Update create-new-hack.yml

* spell check init

* path to cspell.json

* spell check

* rename

* version

* spellcheck

* spelling

* ignore case

* more words

* more words

* more words

* more words

* version

* naming

* spell

* extend

* 3.7

* 8

* yq

* 11

* 12

* 13

* print

* print

* 15

* 47

* 4307

* download

* quotes

* move spellcheck action to repo

* changed files

* 20

* paths

* test

* 21

* extra files

* extra files

* debug

* 23

* 24

* 25

* 26

* 27

* 28

* 29

* 30

* spelling

* action

* fix

* spell

* spelling

* spelling

* spelling

* sync

* label

* asdf

* sha

* spelling

.github/actions/spell-check/Dockerfile

@@ -0,0 +1,22 @@
+FROM python:3.9-slim-buster
+
+LABEL "com.github.actions.name"="WTH Spell Check Action"
+LABEL "com.github.actions.description"="Check spelling of Markdown files in the WhatTheHack repo"
+LABEL "com.github.actions.icon"="clipboard"
+LABEL "com.github.actions.color"="green"
+LABEL "repository"="http://github.com/whatthehack"
+LABEL "homepage"="http://github.com/actions"
+
+RUN apt-get update \
+  && apt-get install -y aspell hunspell wget
+
+RUN wget https://github.com/mikefarah/yq/releases/download/v4.30.7/yq_linux_amd64 -O /usr/bin/yq && \
+  chmod +x /usr/bin/yq
+
+RUN pip3 install pyspelling pyyaml
+
+COPY generate-spellcheck.py /generate-spellcheck.py
+COPY entrypoint.sh /entrypoint.sh
+RUN chmod +x /entrypoint.sh
+
+ENTRYPOINT ["/entrypoint.sh"]

.github/actions/spell-check/README.md

@@ -0,0 +1 @@
+# wth-spell-check-action

.github/actions/spell-check/action.yml

@@ -0,0 +1,26 @@
+name: "WTH Spell Check"
+description: "A Github Action that spell checks the Markdown files in the WTH repository"
+author: Jordan Bean
+inputs:
+  spell_check_yaml_path:
+    description: "Path to the spell check yaml file"
+    required: true
+    default: ".github/workflows/spellcheck.yml"
+  markdown_base_path:
+    description: "Path to the markdown files"
+    required: true
+    default: "."
+  changed_files:
+    description: "Files changed in the PR (space separated)"
+    required: true
+    default: ""
+branding:
+  color: green
+  icon: type
+runs:
+  using: docker
+  image: "Dockerfile"
+  args:
+    - ${{ inputs.spell_check_yaml_path }}
+    - ${{ inputs.markdown_base_path }}
+    - ${{ inputs.changed_files }}

.github/actions/spell-check/entrypoint.sh

@@ -0,0 +1,31 @@
+#!/bin/bash -l
+
+echo "Starting..."
+configFile="$1"; shift
+pathToMarkdownFiles="$1"; shift
+changedFiles=("$@")
+
+echo "Config file: $configFile"
+echo "Path to markdown files: $pathToMarkdownFiles"
+echo "Changed files: ${changedFiles[@]}"
+
+echo "Setup languages and spelling tool..."
+
+python /generate-spellcheck.py "$configFile" "$pathToMarkdownFiles" "${changedFiles[@]}"
+
+# convert from JSON to YAML
+yq -P "$configFile".tmp > "$configFile"
+
+rm -rf /var/lib/apt/lists/*
+
+echo "Using PySpelling according to configuration from $configFile"
+
+pyspelling --config "$configFile"
+
+EXITCODE=$?
+
+test $EXITCODE -gt 1 && echo "Spelling check action failed, please check logs.";
+
+test $EXITCODE -eq 1 && echo "Files in repository contain spelling errors. Please fix these errors. Alternatively, follow the instructions at the following link to add your own words to the dictionary: https://microsoft.github.io/WhatTheHack/CONTRIBUTING.html#spell-check";
+
+exit $EXITCODE

.github/actions/spell-check/generate-spellcheck.py

@@ -0,0 +1,40 @@
+import sys
+import os
+import yaml
+import json
+
+CUSTOM_WORD_LIST_FILENAME = '.wordlist.txt'
+
+def find_wordlist_files(path):
+    wordlist_paths = []
+    for root, dirs, files in os.walk(path):
+        for file in files:
+            if file.endswith(CUSTOM_WORD_LIST_FILENAME):
+                wordlist_paths.append(os.path.join(root, file))
+    return wordlist_paths
+
+if __name__ == '__main__':
+    spell_check_yaml_path = sys.argv[1]
+    markdown_base_path = sys.argv[2]
+    changed_files_tmp = sys.argv[3:]
+    # the changed files come in as a list with a single element, each of which is space-separated in the first element
+    # therefore, we need to split them
+    changed_files = changed_files_tmp[0].split(' ')
+
+    spell_check_yaml = None
+
+    with open(spell_check_yaml_path, 'r') as read_file:
+        spell_check_yaml = yaml.load(read_file, Loader=yaml.FullLoader)
+
+    wordlist_paths = find_wordlist_files(markdown_base_path)
+
+    # Add any custom wordlists defined to the spellcheck config
+    spell_check_yaml['matrix'][0]['dictionary']['wordlists'].extend(wordlist_paths)
+
+    # Set the list of files to check
+    spell_check_yaml['matrix'][0]['sources'] = changed_files
+
+    with open(spell_check_yaml_path + ".tmp", 'w') as write_file:
+        #yaml.dump doesn't work in Python >3, so we dump to JSON instead & convert using yq in the outer script
+        #yaml.dump(write_file, spell_check_yaml, Dumper=yaml.Dumper)
+        json.dump(spell_check_yaml, write_file, indent=4)

.github/workflows/spell-check-markdown.yml

@@ -0,0 +1,28 @@
+name: Spell Check
+
+on:
+  pull_request:
+    types:
+      - opened
+      - synchronize
+    branches: [master]
+    paths:
+      - "**.md"
+
+jobs:
+  spell-check:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - name: Get changed files
+        id: changed-files
+        uses: tj-actions/changed-files@ce810b29b28abf274afebdcd8fe47b8fba0f28bd
+        with:
+          files: |
+            **/*.md
+      - uses: ./.github/actions/spell-check
+        name: WTH Spell Check
+        with:
+          spell_check_yaml_path: .github/workflows/spell-check/spellcheck.yml
+          markdown_base_path: .
+          changed_files: ${{ steps.changed-files.outputs.all_changed_files }}