Merge branch 'main' into xamgore-merged-main

Author: danielparks

.github/workflows/pr-checks.yaml

@@ -7,37 +7,16 @@ on:
       - main
   pull_request:
 
-jobs:
-  test:
-    name: cargo test
-    runs-on: ubuntu-latest
-
-    steps:
-      - uses: actions/checkout@v4
-      - uses: actions-rust-lang/setup-rust-toolchain@v1
-      - run: cargo build --tests --all-features
-      - run: cargo test --all-features
-      - run: cargo test --features unescape
-      - run: cargo test --features entities
-      - run: cargo test
-
-  fmt:
-    name: cargo fmt
-    runs-on: ubuntu-latest
-
-    steps:
-      - uses: actions/checkout@v4
-      - uses: actions-rust-lang/setup-rust-toolchain@v1
-        with:
-          components: rustfmt
-      - uses: actions-rust-lang/rustfmt@v1
+env:
+  CLICOLOR: 1
 
+jobs:
   clippy:
     name: cargo clippy
     runs-on: ubuntu-latest
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
       - uses: actions-rust-lang/setup-rust-toolchain@v1
         with:
           components: clippy
@@ -52,17 +31,52 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
       - uses: EmbarkStudios/cargo-deny-action@v2
+        with:
+          rust-version: "1.85.0"
+
+  fmt:
+    name: cargo fmt
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v5
+      - uses: actions-rust-lang/setup-rust-toolchain@v1
+        with:
+          components: rustfmt
+      - uses: actions-rust-lang/rustfmt@v1
 
   msrv:
     name: cargo msrv
     runs-on: ubuntu-latest
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
       - uses: Swatinem/rust-cache@v2
       - uses: taiki-e/install-action@v2
         with:
           tool: cargo-msrv
       - run: cargo msrv verify
+
+  test:
+    name: cargo test
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v5
+      - uses: actions-rust-lang/setup-rust-toolchain@v1
+      - run: cargo build --tests --all-features
+      - run: cargo test --all-features
+      - run: cargo test --features unescape
+      - run: cargo test --features unescape_fast
+      - run: cargo test --features entities
+      - run: cargo test
+
+  typos:
+    name: typos
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v5
+      - uses: crate-ci/typos@v1.38.1

.github/workflows/release.yaml

@@ -1,9 +1,8 @@
-# Mostly copied from https://github.com/taiki-e/cargo-hack/blob/72a9fc95377c453a18026329577c59fa60bfa737/.github/workflows/release.yml
+# Mostly copied from https://github.com/taiki-e/cargo-hack/blob/main/.github/workflows/release.yml
 name: Release
 
 permissions:
-  # TODO: once `releases: write` is supported, use it instead.
-  contents: write
+  contents: read
 
 on:
   push:
@@ -12,31 +11,20 @@ on:
 
 env:
   CARGO_INCREMENTAL: 0
+  CARGO_NET_GIT_FETCH_WITH_CLI: true
   CARGO_NET_RETRY: 10
   CARGO_TERM_COLOR: always
   RUST_BACKTRACE: 1
   RUSTFLAGS: -D warnings
   RUSTUP_MAX_RETRIES: 10
 
-defaults:
-  run:
-    # Setting shell: bash explicitly activates pipefail
-    shell: bash
-
 jobs:
   create-release:
     if: github.repository_owner == 'danielparks'
     runs-on: ubuntu-latest
+    permissions:
+      contents: write
     steps:
-      - uses: actions/checkout@v4
-        with:
-          persist-credentials: false
-      - name: Install Rust
-        run: rustup update stable --no-self-update
-      - run: cargo package
-      - uses: taiki-e/create-gh-release-action@v1
+      - uses: danielparks/github-actions/create-release@main
         with:
-          changelog: CHANGELOG.md
-          title: Release $version
-          branch: main
           token: ${{ secrets.GITHUB_TOKEN }}

.pre-commit-config.yaml

@@ -0,0 +1,47 @@
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v6.0.0
+    hooks:
+      - id: check-added-large-files
+        args: ["--maxkb=1024"]
+      - id: check-case-conflict
+      - id: check-executables-have-shebangs
+      - id: check-json
+      - id: check-merge-conflict
+      - id: check-shebang-scripts-are-executable
+      - id: check-symlinks
+      - id: check-toml
+      - id: check-vcs-permalinks
+      - id: check-xml
+      - id: check-yaml
+      - id: detect-private-key
+      - id: mixed-line-ending
+        args: ["--fix=no"]
+        exclude: "^target/"
+      - id: no-commit-to-branch
+  - repo: https://github.com/crate-ci/typos
+    rev: v1.38.1
+    hooks:
+      - id: typos
+        args: []
+        exclude: "^target/"
+  - repo: local
+    hooks:
+      - id: cargo clippy
+        name: cargo clippy
+        language: system
+        entry: cargo clippy --all-targets --all-features -- -D warnings
+        files: (\.rs|Cargo\.toml)$
+        pass_filenames: false
+      - id: cargo doc
+        name: cargo doc
+        language: system
+        entry: sh -c 'RUSTDOCFLAGS=-Dwarnings cargo doc --all-features --workspace --no-deps --document-private-items'
+        files: \.rs$
+        pass_filenames: false
+      - id: cargo fmt
+        name: cargo fmt
+        language: system
+        entry: cargo fmt --check
+        files: (\.rs|rustfmt\.toml)$
+        pass_filenames: false

.typos.toml

@@ -0,0 +1,6 @@
+[files]
+extend-exclude = [
+  "target",
+  "entities.json",
+  "tests/corpus",
+]

CHANGELOG.md

@@ -4,6 +4,23 @@ All notable changes to this project will be documented in this file.
 
 ## main branch
 
+* Major performance improvements when unescaping text in many cases (for both
+  the `unescape` and `unescape_fast` features).
+* Major improvements in build time for the `unescape_fast` features (went from
+  8 seconds to 3 seconds on my laptop).
+* Add `BARE_ENTITY_MAX_LENGTH` constant that contains the length of the longest
+  entity without a semicolon (enabled with feature `entities`).
+* Clarify examples in documentation and README.
+* Fix a few spelling mistakes in documentation.
+
+## Release 1.0.6 (2025-04-26)
+
+* Switch dependency from [paste], which is no longer maintained, to a new fork,
+  [pastey], which is.
+
+[paste]: https://github.com/dtolnay/paste
+[pastey]: https://github.com/as1100k/pastey
+
 ## Release 1.0.5 (2024-03-14)
 
 * Exclude more files from final package to significantly reduce package size.

Cargo.lock

@@ -1,8 +1,8 @@
 [package]
 name = "htmlize"
-version = "1.0.5"
+version = "1.0.6"
 authors = ["Daniel Parks <oss-htmlize@demonhorse.org>"]
-description = "Encode and decode HTML entities in UTF-8 according to the standard"
+description = "Correctly encode and decode HTML entities in UTF-8"
 homepage = "https://github.com/danielparks/htmlize"
 repository = "https://github.com/danielparks/htmlize"
 readme = "README.md"
@@ -30,14 +30,14 @@ bench = []
 _unescape_either = []
 
 [build-dependencies]
-matchgen = { version = "0.3.0", optional = true }
+matchgen = { version = "0.4.0", optional = true }
 phf = { version = "0.11.1", default-features = false, optional = true }
 phf_codegen = { version = "0.11.1", optional = true }
 serde_json = { version = "1.0", optional = true }
 
 [dependencies]
 memchr = "2.5.0"
-paste = "1.0.11"
+pastey = "0.1.0"
 phf = { version = "0.11.1", default-features = false, optional = true }
 hashify = "0.2.6"
 
@@ -81,6 +81,8 @@ pedantic = { level = "warn", priority = -1 }
 missing_docs_in_private_items = "warn"
 
 # Other restriction lints
+allow_attributes = "warn"
+allow_attributes_without_reason = "warn"
 arithmetic_side_effects = "warn"
 as_underscore = "warn"
 assertions_on_result_states = "warn"
@@ -104,7 +106,6 @@ rc_mutex = "warn"
 same_name_method = "warn"
 semicolon_inside_block = "warn"
 str_to_string = "warn"
-string_to_string = "warn"
 undocumented_unsafe_blocks = "warn"
 unnecessary_safety_doc = "warn"
 unnecessary_self_imports = "warn"
@@ -116,6 +117,7 @@ let_underscore_untyped = "allow"
 manual_string_new = "allow"
 map_unwrap_or = "allow"
 module_name_repetitions = "allow"
+unnecessary_debug_formatting = "allow" # display() doesn’t escape invalid chars
 
 # Nursery exceptions
 option_if_let_else = "allow"

Cargo.toml

@@ -7,10 +7,7 @@ RUN apt-get update \
   && apt-get install -y locales curl valgrind build-essential \
   && rm -rf /var/lib/apt/lists/* \
 	&& localedef -i en_US -c -f UTF-8 -A /usr/share/locale/locale.alias en_US.UTF-8
-ENV LANG en_US.utf8
-
-# Remove after Rust 1.70 when this becomes default
-ENV CARGO_REGISTRIES_CRATES_IO_PROTOCOL=sparse
+ENV LANG=en_US.utf8
 
 # Install rustup, rust, and cargo-binstall
 RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs \