Merge branch 'main' into add_examples_comments

.github/workflows/main.yml

@@ -2,7 +2,7 @@ name: CI
 
 on:
   push:
-    branches: [master]
+    branches: [main]
   pull_request:
   merge_group:
     types: [checks_requested]
@@ -13,9 +13,9 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        version: [1.60.0, stable, beta, nightly]
+        version: [stable, beta, nightly]
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
       - name: Set toolchain
         run: |
@@ -26,16 +26,10 @@ jobs:
         run: git submodule update --init
 
       - name: Cargo bench
-        if: matrix.version != '1.41.0'
         run: cargo bench --all
         env:
           RUSTFLAGS: --cfg bench
 
-      - name: Test "rustc-test/capture" feature
-        if: matrix.version == 'nightly'
-        working-directory: rcdom
-        run: cargo test --features "rustc-test/capture"
-
       - name: Cargo test
         if: matrix.version != 'nightly'
         run: cargo test --all
@@ -44,6 +38,19 @@ jobs:
         if: matrix.version == 'nightly'
         run: cargo doc
 
+  msrv:
+    name: MSRV
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install stable toolchain
+        run: |
+          rustup set profile minimal
+          rustup override set 1.60.0
+
+      - run: cargo check --lib --all-features
+
   build_result:
     name: Result
     runs-on: ubuntu-latest
@@ -56,4 +63,26 @@ jobs:
         if: success()
       - name: Mark the job as unsuccessful
         run: exit 1
-        if: "!success()"
+        if: ${{ !success() }}
+
+  lint:
+    name: Lint
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install stable toolchain
+        run: |
+          rustup set profile minimal
+          rustup override set stable
+
+      - name: Install clippy
+        run: |
+          rustup component add clippy
+          rustup component add rustfmt
+
+      - name: Format
+        run: cargo fmt --all -- --check
+
+      - name: Run clippy
+        run: cargo clippy --all-features --all-targets -- -D warnings

Cargo.toml

@@ -5,3 +5,4 @@ members = [
     "rcdom",
     "xml5ever"
 ]
+resolver = "2"

README.md

@@ -7,11 +7,11 @@
 
 html5ever is an HTML parser developed as part of the [Servo][] project.
 
-It can parse and serialize HTML according to the [WHATWG](https://whatwg.org/) specs (aka "HTML5").  However, there are some differences in the actual behavior currently, most of which are documented [in the bug tracker][].  html5ever passes all tokenizer tests from [html5lib-tests][], with most tree builder tests outside of the unimplemented features.  The goal is to pass all html5lib tests, while also providing all hooks needed by a production web browser, e.g. `document.write`.
+It can parse and serialize HTML according to the [WHATWG](https://whatwg.org/) specs (aka "HTML5"). However, there are some differences in the actual behavior currently, most of which are documented [in the bug tracker][]. html5ever passes all tokenizer tests from [html5lib-tests][], with most tree builder tests outside of the unimplemented features. The goal is to pass all html5lib tests, while also providing all hooks needed by a production web browser, e.g. `document.write`.
 
-Note that the HTML syntax is very similar to XML.  For correct parsing of XHTML, use an XML parser (That said, many XHTML documents in the wild are serialized in an HTML-compatible form).
+Note that the HTML syntax is very similar to XML. For correct parsing of XHTML, use an XML parser (that said, many XHTML documents in the wild are serialized in an HTML-compatible form).
 
-html5ever is written in [Rust][], therefore it avoids the notorious security problems that come along with using C.  Being built with Rust also makes the library come with the high-grade performance you would expect from an HTML parser written in C.  html5ever is basically a C HTML parser, but without needing a garbage collector or other heavy runtime processes.
+html5ever is written in [Rust][], therefore it avoids the notorious security problems that come along with using C. Being built with Rust also makes the library come with the high-grade performance you would expect from an HTML parser written in C. html5ever is basically a C HTML parser, but without needing a garbage collector or other heavy runtime processes.
 
 
 ## Getting started in Rust
@@ -20,11 +20,12 @@ Add html5ever as a dependency in your [`Cargo.toml`](https://crates.io/) file:
 
 ```toml
 [dependencies]
-html5ever = "0.26"
+html5ever = "0.27"
 ```
 
 You should also take a look at [`examples/html2html.rs`], [`examples/print-rcdom.rs`], and the [API documentation][].
 
+
 ## Getting started in other languages
 
 Bindings for Python and other languages are much desired.
@@ -45,7 +46,7 @@ Run `cargo doc` in the repository root to build local documentation under `targe
 
 html5ever uses callbacks to manipulate the DOM, therefore it does not provide any DOM tree representation. 
 
-html5ever exclusively uses UTF-8 to represent strings.  In the future it will support other document encodings (and UCS-2 `document.write`) by converting input.
+html5ever exclusively uses UTF-8 to represent strings. In the future it will support other document encodings (and UCS-2 `document.write`) by converting input.
 
 The code is cross-referenced with the WHATWG syntax spec, and eventually we will have a way to present code and spec side-by-side.
 
@@ -56,5 +57,5 @@ html5ever builds against the official stable releases of Rust, though some optim
 [Rust]: https://www.rust-lang.org/
 [in the bug tracker]: https://github.com/servo/html5ever/issues?q=is%3Aopen+is%3Aissue+label%3Aweb-compat
 [html5lib-tests]: https://github.com/html5lib/html5lib-tests
-[`examples/html2html.rs`]: https://github.com/servo/html5ever/blob/master/rcdom/examples/html2html.rs
-[`examples/print-rcdom.rs`]: https://github.com/servo/html5ever/blob/master/rcdom/examples/print-rcdom.rs
+[`examples/html2html.rs`]: https://github.com/servo/html5ever/blob/main/rcdom/examples/html2html.rs
+[`examples/print-rcdom.rs`]: https://github.com/servo/html5ever/blob/main/rcdom/examples/print-rcdom.rs

html5ever/Cargo.toml

@@ -1,30 +1,28 @@
 [package]
 
 name = "html5ever"
-version = "0.26.0"
+version = "0.27.0"
 authors = [ "The html5ever Project Developers" ]
 license = "MIT OR Apache-2.0"
 repository = "https://github.com/servo/html5ever"
 description = "High-performance browser-grade HTML5 parser"
 documentation = "https://docs.rs/html5ever"
 build = "build.rs"
 categories = [ "parser-implementations", "web-programming" ]
-edition = "2018"
+edition = "2021"
 
 [dependencies]
 log = "0.4"
 mac = "0.1"
-markup5ever = { version = "0.11", path = "../markup5ever" }
+markup5ever = { version = "0.12", path = "../markup5ever" }
 
 [dev-dependencies]
-typed-arena = "2.0.2"
-
-[target.'cfg(bench)'.dev-dependencies]
 criterion = "0.3"
+typed-arena = "2.0.2"
 
 [build-dependencies]
 quote = "1"
-syn = { version = "1", features = ["extra-traits", "full", "fold"] }
+syn = { version = "2", features = ["extra-traits", "full", "fold"] }
 proc-macro2 = "1"
 
 [[bench]]

html5ever/benches/html5ever.rs

@@ -27,12 +27,11 @@ fn run_bench(c: &mut Criterion, name: &str) {
     let mut path = PathBuf::from(env!("CARGO_MANIFEST_DIR"));
     path.push("data/bench/");
     path.push(name);
-    let mut file = fs::File::open(&path).ok().expect("can't open file");
+    let mut file = fs::File::open(&path).expect("can't open file");
 
     // Read the file and treat it as an infinitely repeating sequence of characters.
     let mut file_input = ByteTendril::new();
     file.read_to_tendril(&mut file_input)
-        .ok()
         .expect("can't read file");
     let file_input: StrTendril = file_input.try_reinterpret().unwrap();
     let size = file_input.len();
@@ -55,7 +54,7 @@ fn run_bench(c: &mut Criterion, name: &str) {
     c.bench_function(&test_name, move |b| {
         b.iter(|| {
             let mut tok = Tokenizer::new(Sink, Default::default());
-            let mut buffer = BufferQueue::new();
+            let mut buffer = BufferQueue::default();
             // We are doing clone inside the bench function, this is not ideal, but possibly
             // necessary since our iterator consumes the underlying buffer.
             for buf in input.clone().into_iter() {

html5ever/examples/arena.rs

@@ -22,7 +22,7 @@ use std::ptr;
 /// By using our Sink type, the arena is filled with parsed HTML.
 fn html5ever_parse_slice_into_arena<'a>(bytes: &[u8], arena: Arena<'a>) -> Ref<'a> {
     let sink = Sink {
-        arena: arena,
+        arena,
         document: arena.alloc(Node::new(NodeData::Document)),
         quirks_mode: QuirksMode::NoQuirks,
     };
@@ -88,7 +88,7 @@ impl<'arena> Node<'arena> {
             next_sibling: Cell::new(None),
             first_child: Cell::new(None),
             last_child: Cell::new(None),
-            data: data,
+            data,
         }
     }
 
@@ -211,7 +211,7 @@ impl<'arena> TreeSink for Sink<'arena> {
 
     fn get_template_contents(&mut self, target: &Ref<'arena>) -> Ref<'arena> {
         if let NodeData::Element {
-            template_contents: Some(ref contents),
+            template_contents: Some(contents),
             ..
         } = target.data
         {
@@ -257,7 +257,7 @@ impl<'arena> TreeSink for Sink<'arena> {
 
     fn create_pi(&mut self, target: StrTendril, data: StrTendril) -> Ref<'arena> {
         self.new_node(NodeData::ProcessingInstruction {
-            target: target,
+            target,
             contents: data,
         })
     }

html5ever/examples/noop-tokenize.rs

@@ -11,7 +11,6 @@
 
 extern crate html5ever;
 
-use std::default::Default;
 use std::io;
 
 use html5ever::tendril::*;
@@ -37,8 +36,8 @@ fn main() {
     // Read HTML from standard input
     let mut chunk = ByteTendril::new();
     io::stdin().read_to_tendril(&mut chunk).unwrap();
-
-    let mut input = BufferQueue::new();
+  
+    let mut input = BufferQueue::default();
     input.push_back(chunk.try_reinterpret().unwrap());
 
     let mut tok = Tokenizer::new(Sink(Vec::new()), Default::default());

html5ever/examples/noop-tree-builder.rs

@@ -12,7 +12,6 @@ extern crate html5ever;
 
 use std::borrow::Cow;
 use std::collections::HashMap;
-use std::default::Default;
 use std::io;
 
 use html5ever::parse_document;
@@ -49,7 +48,7 @@ impl TreeSink for Sink {
     }
 
     fn get_template_contents(&mut self, target: &usize) -> usize {
-        if let Some(expanded_name!(html "template")) = self.names.get(&target).map(|n| n.expanded())
+        if let Some(expanded_name!(html "template")) = self.names.get(target).map(|n| n.expanded())
         {
             target + 1
         } else {
@@ -96,7 +95,7 @@ impl TreeSink for Sink {
 
     fn append_doctype_to_document(&mut self, _: StrTendril, _: StrTendril, _: StrTendril) {}
     fn add_attrs_if_missing(&mut self, target: &usize, _attrs: Vec<Attribute>) {
-        assert!(self.names.contains_key(&target), "not an element");
+        assert!(self.names.contains_key(target), "not an element");
     }
     fn remove_from_parent(&mut self, _target: &usize) {}
     fn reparent_children(&mut self, _node: &usize, _new_parent: &usize) {}

html5ever/examples/print-tree-actions.rs

@@ -12,7 +12,6 @@ extern crate html5ever;
 
 use std::borrow::Cow;
 use std::collections::HashMap;
-use std::default::Default;
 use std::io;
 
 use html5ever::parse_document;

html5ever/examples/tokenize.rs

@@ -9,7 +9,6 @@
 
 extern crate html5ever;
 
-use std::default::Default;
 use std::io;
 
 use html5ever::tendril::*;
@@ -91,7 +90,7 @@ fn main() {
     let mut chunk = ByteTendril::new();
     io::stdin().read_to_tendril(&mut chunk).unwrap();
 
-    let mut input = BufferQueue::new();
+    let mut input = BufferQueue::default();
     input.push_back(chunk.try_reinterpret().unwrap());
 
     let mut tok = Tokenizer::new(