ci: Add spell checker

Author: Martin Taillefer

.github/license-check/config.json

@@ -44,6 +44,7 @@
 
     {
         "include": [
+            "**/*.dic",
             "**/*.j2",
             "**/*.svg",
             "**/*.png",

.github/workflows/main.yml

@@ -153,6 +153,100 @@ jobs:
         if: success() || failure()
         run: cargo deny --all-features --workspace --color always check all
 
+  spell-check:
+    needs: constants
+    runs-on: ubuntu-latest
+    env:
+      CARGO_WORKSPACES_VERSION: ${{ needs.constants.outputs.CARGO_WORKSPACES_VERSION }}
+      SCCACHE_VERSION: ${{ needs.constants.outputs.SCCACHE_VERSION }}
+      SCCACHE_GHA_ENABLED: "true"
+      RUSTC_WRAPPER: "sccache"
+    steps:
+      # prep
+      - name: Checkout
+        uses: actions/checkout@v6.0.0
+        with:
+          fetch-depth: 1
+      - name: Cache Cargo Dependencies
+        uses: actions/cache@v4.3.0
+        with:
+          path: |
+            ~/.cargo/bin/
+            ~/.cargo/registry/index/
+            ~/.cargo/registry/cache/
+            ~/.cargo/git/db/
+          key: ${{ runner.os }}-cargo-tools-${{ hashFiles('**/Cargo.lock') }}
+      - name: Start sccache
+        uses: mozilla-actions/sccache-action@v0.0.9
+        with:
+          version: ${{ env.SCCACHE_VERSION }}
+      - name: Install Rust
+        uses: actions-rust-lang/setup-rust-toolchain@v1.15.2
+        with:
+          toolchain: ${{ env.RUST_LATEST }}
+      - name: Install Cargo Tools
+        uses: taiki-e/install-action@v2.62.62
+        with:
+          tool: cargo-spellcheck
+
+      # execute
+      - name: Make sure dictionary words are sorted and unique
+        run: |
+          FILE="spellcheck.dic"
+
+          # Verify the first line is an integer.
+          first_line=$(head -n 1 "$FILE")
+          if ! [[ "$first_line" =~ ^[0-9]+$ ]]; then
+            echo "Error: The first line of $FILE must be an integer, but got: '$first_line'"
+            exit 1
+          fi
+          expected_count="$first_line"
+
+          # Check that the number of lines matches the integer.
+          # xargs (with no arguments) will strip leading/trailing whitespacefrom wc's output.
+          actual_count=$(sed '1d' "$FILE" | wc -l | xargs)
+          if [ "$expected_count" -ne "$actual_count" ]; then
+            echo "Error: The number of lines ($actual_count) does not match $expected_count."
+            exit 1
+          fi
+
+          # `sed` removes the first line (number of words).
+          #
+          # `sort` makes sure everything in between is sorted
+          # and contains no duplicates.
+          #
+          # Since `sort` is sensitive to locale, we set it
+          # using LC_ALL to en_US.UTF8 to be consistent in different
+          # environments.
+
+          (
+            sed '1d' $FILE | LC_ALL=en_US.UTF8 sort -uc
+          ) || {
+            echo "Dictionary is not in sorted order. Correct order is:"
+            LC_ALL=en_US.UTF8 sort -u <(sed '1d' $FILE)
+            false
+          }
+      - name: Run cargo-spellcheck
+        run: |
+          if ! cargo spellcheck --cfg spellcheck.toml --code 1
+          then
+              echo ''
+              echo ''
+              echo 'If this is a Rust method/type/variable name, then you should'
+              echo 'enclose it in backticks like this: `MyRustType`.'
+              echo ''
+              echo 'If this is a real word, then you can add it to spellcheck.dic'
+              exit 1
+          fi
+      - name: Detect trailing whitespace
+        run: |
+          if grep --exclude-dir=.git --exclude-dir=target -rne '\s$' .
+          then
+              echo ''
+              echo 'Please remove trailing whitespace from these lines.'
+              exit 1
+          fi
+
   semver:
     needs: constants
     if: github.event_name == 'pull_request'
@@ -440,3 +534,17 @@ jobs:
       # execute
       - name: Check External Type Exposure
         run: cargo +${{ env.RUST_NIGHTLY_EXTERNAL_TYPES }} -Zscript scripts/check-external-types.rs ${{ env.RUST_NIGHTLY_EXTERNAL_TYPES }}
+
+  spell-check2:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6.0.0
+
+      - name: Spell Check
+        uses: streetsidesoftware/cspell-action@v6
+        with:
+          treat_flagged_words_as_errors: true
+          incremental_files_only: false
+          use_cspell_files: true
+          suggestions: true

.spelling

@@ -67,6 +67,7 @@ Clippy
 codebase
 composability
 config
+contoso
 const
 CONTRIBUTING.md
 coverage.json
@@ -99,6 +100,7 @@ filesystem
 fn
 foldhash
 footguns
+formatter
 fundle
 Fundle
 getsockopt
@@ -133,6 +135,7 @@ macros
 Macros
 Makefile
 metadata
+metadata
 Metas
 Microservices
 microsoft.com
@@ -245,4 +248,5 @@ wildcard
 wildcards
 Win32
 winsock
+workspace
 Xamarin

Cargo.toml

@@ -2,7 +2,7 @@
 # Licensed under the MIT License.
 
 [workspace]
-resolver = "3"
+resolver = "2"
 members = ["crates/*"]
 
 [workspace.package]

crates/bytesbuf/README.md

@@ -422,7 +422,7 @@ use bytesbuf::BytesView;
 
 pub fn write(&mut self, message: BytesView) {
     // We now need to identify whether the message actually uses memory that allows us to
-    // ues the optimal I/O path. There is no requirement that the data passed to us contains
+    // use the optimal I/O path. There is no requirement that the data passed to us contains
     // only memory with our preferred configuration.
 
     let use_optimal_path = message.iter_slice_metas().all(|meta| {

crates/bytesbuf/examples/bb_optimal_path.rs

@@ -61,7 +61,7 @@ impl Connection {
 
     pub fn write(&mut self, message: BytesView) {
         // We now need to identify whether the message actually uses memory that allows us to
-        // ues the optimal I/O path. There is no requirement that the data passed to us contains
+        // use the optimal I/O path. There is no requirement that the data passed to us contains
         // only memory with our preferred configuration.
 
         let use_optimal_path = message.iter_slice_metas().all(|meta| {

crates/bytesbuf/src/lib.rs

@@ -456,7 +456,7 @@
 //! # impl Foo {
 //! pub fn write(&mut self, message: BytesView) {
 //!     // We now need to identify whether the message actually uses memory that allows us to
-//!     // ues the optimal I/O path. There is no requirement that the data passed to us contains
+//!     // use the optimal I/O path. There is no requirement that the data passed to us contains
 //!     // only memory with our preferred configuration.
 //!
 //!     let use_optimal_path = message.iter_slice_metas().all(|meta| {

crates/bytesbuf/src/span_builder.rs

@@ -167,7 +167,7 @@ impl SpanBuilder {
         // This cannot overflow - guarded by assertion above.
         self.filled_bytes = self.filled_bytes.wrapping_sub(len.get());
 
-        // SAFETY: We only seeked over filled bytes, so we must still be in-bounds.
+        // SAFETY: We only skipped over filled bytes, so we must still be in-bounds.
         self.start = unsafe { self.start.add(len.get() as usize) };
 
         span

crates/data_privacy/CHANGELOG.md

@@ -73,7 +73,7 @@
 
 - ✨ Features
 
-  - Make RedactionEngine clonable. ([#13](https://github.com/microsoft/oxidizer/pull/13))
+  - Make RedactionEngine cloneable. ([#13](https://github.com/microsoft/oxidizer/pull/13))
 
 - 📚 Documentation
 

crates/data_privacy/src/data_class.rs

@@ -25,7 +25,7 @@ impl DataClass {
     ///
     /// # Panics
     ///
-    /// Panics if `taxonomy` or `name` are not valid ASCII identifiers. Valid identifiers must
+    /// Panics if `taxonomy` or `name` are not valid identifiers. Valid identifiers must
     /// start with `_` or an ASCII letter, followed by zero or more `_`, ASCII letters, or ASCII
     /// digits (e.g., `foo`, `_bar`, `Baz123`)
     #[must_use]