From cca7a1b2ff20e8a5b3fd38a1d276c9f29bdeccf8 Mon Sep 17 00:00:00 2001
From: Matthias Kay <matthias.kay@hlag.com>
Date: Mon, 6 Jan 2025 13:09:18 +0100
Subject: [PATCH] VALIDATE-DICTIONARIES

---
 .../workflows/default_spelling_callable.yml   | 21 ++++++++++
 .../workflows/scripts/check_dictionaries.sh   | 42 +++++++++++++++++++
 2 files changed, 63 insertions(+)
 create mode 100755 .github/workflows/scripts/check_dictionaries.sh

diff --git a/.github/workflows/default_spelling_callable.yml b/.github/workflows/default_spelling_callable.yml
index a4464ea..5f5bf15 100644
--- a/.github/workflows/default_spelling_callable.yml
+++ b/.github/workflows/default_spelling_callable.yml
@@ -19,3 +19,24 @@ jobs:
       - uses: streetsidesoftware/cspell-action@ef95dc49d631fc2a9e9ea089ae2b2127b7c4588e # v6.10.0
         with:
           config: .config/cspell.json
+
+  find-changes-for-shell-output:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: dorny/paths-filter@de90cc6fb38fc0963ad72b210f1f284cd68cea36 # v3.0.2
+        id: changes-for-shell
+        with:
+          list-files: "shell"
+          filters: |
+            markdown:
+            - added|modified: '.config/dictionaries/*.txt'
+    outputs:
+      dictionaries: ${{ steps.changes-for-shell.outputs.dictionaries }}
+
+  validate-dictionaries:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+
+      - run: .github/workflows/scripts/validate-dictionaries.sh
+        if: needs.find-changes-for-shell-output.outputs.dictionaries == 'true'
diff --git a/.github/workflows/scripts/check_dictionaries.sh b/.github/workflows/scripts/check_dictionaries.sh
new file mode 100755
index 0000000..27f63c7
--- /dev/null
+++ b/.github/workflows/scripts/check_dictionaries.sh
@@ -0,0 +1,42 @@
+#!/bin/bash
+
+set -euo pipefail
+
+MISSPELLED_WORDS_PATH="misspelled-words.txt"
+
+CSPELL_CONFIGURATION_FILE=$(find . -name "cspell.json" | head -n 1)
+DICTIONARIES_PATH=".config/dictionaries"
+mapfile -t DICTIONARY_FILES_TO_CHECK < <(ls .config/dictionaries/*.txt)
+
+# Make a list of every misspelled word without any custom dictionaries and configuration file
+mv "$CSPELL_CONFIGURATION_FILE" "${CSPELL_CONFIGURATION_FILE}.temp"
+npx cspell . --dot --no-progress --no-summary --unique --words-only --no-exit-code --exclude ".git/**" --exclude "$DICTIONARIES_PATH/**" | sort --ignore-case --unique > "$MISSPELLED_WORDS_PATH"
+
+# Check the custom dictionaries
+ONE_OR_MORE_FAILURES=0
+for DICTIONARY_NAME in "${DICTIONARY_FILES_TO_CHECK[@]}"; do
+  # Check alphabetically sorted and unique
+  echo "Checking for orphaned words in dictionary: $DICTIONARY_NAME"
+
+  # ensure the dictionary is sorted and unique
+  sort --ignore-case --unique --check "$DICTIONARY_NAME"
+
+  # Check that each word in the dictionary is actually being used
+  while IFS= read -r line; do
+    line=$(echo "$line" | tr -d '\r\n')
+
+    if ! grep "$line" "$MISSPELLED_WORDS_PATH" --ignore-case --silent ; then
+      echo "The following word in the $DICTIONARY_NAME dictionary is not being used: ($line)"
+      ONE_OR_MORE_FAILURES=1
+    fi
+  done < "$DICTIONARY_NAME"
+done
+
+rm -f "$MISSPELLED_WORDS_PATH"
+
+if [ $ONE_OR_MORE_FAILURES -ne "0" ]; then
+  echo "Dictionary check failed."
+  exit 1
+fi
+
+echo "All dictionaries are valid."