rusteerio 0.0.0-stage → 0.1.0

package/native/vendor/html5gum-0.8.4/Cargo.toml

@@ -0,0 +1,109 @@
+# THIS FILE IS AUTOMATICALLY GENERATED BY CARGO
+#
+# When uploading crates to the registry Cargo will automatically
+# "normalize" Cargo.toml files for maximal compatibility
+# with all versions of Cargo and also rewrite `path` dependencies
+# to registry (e.g., crates.io) dependencies.
+#
+# If you are reading this file be aware that the original Cargo.toml
+# will likely look very different (and much more reasonable).
+# See Cargo.toml.orig for the original contents.
+
+[package]
+edition = "2018"
+name = "html5gum"
+version = "0.8.4"
+authors = ["Markus Unterwaditzer <markus-honeypot@unterwaditzer.net>"]
+build = false
+include = [
+    "src/**/*",
+    "LICENSE",
+    "README.md",
+    "benches",
+]
+autolib = false
+autobins = false
+autoexamples = false
+autotests = false
+autobenches = false
+description = "A WHATWG-compliant HTML5 tokenizer and tag soup parser."
+readme = "README.md"
+keywords = [
+    "html",
+    "html5",
+    "whatwg",
+    "parser",
+    "tokenizer",
+]
+categories = [
+    "parser-implementations",
+    "web-programming",
+]
+license = "MIT"
+repository = "https://github.com/untitaker/html5gum"
+
+[features]
+afl-ijon = ["afl"]
+default = ["jetscii"]
+tree-builder = ["html5ever"]
+
+[lib]
+name = "html5gum"
+path = "src/lib.rs"
+bench = false
+
+[[bench]]
+name = "files"
+path = "benches/files.rs"
+harness = false
+
+[[bench]]
+name = "patterns"
+path = "benches/patterns.rs"
+harness = false
+
+[dependencies.afl]
+version = "0.17.0"
+optional = true
+
+[dependencies.html5ever]
+version = "0.29.0"
+optional = true
+
+[dependencies.jetscii]
+version = "0.5.1"
+optional = true
+
+[dev-dependencies.annotate-snippets]
+version = "0.11.5"
+
+[dev-dependencies.argh]
+version = "0.1.12"
+
+[dev-dependencies.glob]
+version = "0.3.0"
+
+[dev-dependencies.libtest-mimic]
+version = "0.8.1"
+
+[dev-dependencies.markup5ever_rcdom]
+version = "0.5.0-unofficial"
+
+[dev-dependencies.pretty_assertions]
+version = "1.0.0"
+
+[dev-dependencies.scraper]
+version = "0.21.0"
+
+[dev-dependencies.serde]
+version = "1.0.130"
+features = ["derive"]
+
+[dev-dependencies.serde_bytes]
+version = "0.11.5"
+
+[dev-dependencies.serde_json]
+version = "1.0.71"
+
+[dev-dependencies.test-generator]
+version = "0.3.0"

package/native/vendor/html5gum-0.8.4/LICENSE

@@ -0,0 +1,19 @@
+Copyright (c) 2021 Markus Unterwaditzer
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of
+this software and associated documentation files (the "Software"), to deal in
+the Software without restriction, including without limitation the rights to
+use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies
+of the Software, and to permit persons to whom the Software is furnished to do
+so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

package/native/vendor/html5gum-0.8.4/README.md

@@ -0,0 +1,110 @@
+# html5gum
+
+[![docs.rs](https://img.shields.io/docsrs/html5gum)](https://docs.rs/html5gum)
+[![crates.io](https://img.shields.io/crates/l/html5gum.svg)](https://crates.io/crates/html5gum)
+
+`html5gum` is a WHATWG-compliant HTML tokenizer.
+
+```rust
+use std::fmt::Write;
+use html5gum::{Tokenizer, Token};
+
+let html = "<title   >hello world</title>";
+let mut new_html = String::new();
+
+for Ok(token) in Tokenizer::new(html) {
+    match token {
+        Token::StartTag(tag) => {
+            write!(new_html, "<{}>", String::from_utf8_lossy(&tag.name)).unwrap();
+        }
+        Token::String(hello_world) => {
+            write!(new_html, "{}", String::from_utf8_lossy(&hello_world)).unwrap();
+        }
+        Token::EndTag(tag) => {
+            write!(new_html, "</{}>", String::from_utf8_lossy(&tag.name)).unwrap();
+        }
+        _ => panic!("unexpected input"),
+    }
+}
+
+assert_eq!(new_html, "<title>hello world</title>");
+```
+
+`html5gum` provides multiple kinds of APIs:
+
+* Iterating over tokens as shown above.
+* Implementing your own `Emitter` for maximum performance, see [the `custom_emitter.rs` example][examples/custom_emitter.rs].
+* A callbacks-based API for a middleground between convenience and performance, see [the `callback_emitter.rs` example][examples/callback_emitter.rs].
+* With the `tree-builder` feature, html5gum can be integrated with `html5ever` and `scraper`. See [the `scraper.rs` example][examples/scraper.rs].
+
+## What a tokenizer does and what it does not do
+
+`html5gum` fully implements [13.2.5 of the WHATWG HTML
+spec](https://html.spec.whatwg.org/#tokenization), i.e. is able to tokenize HTML documents and passes [html5lib's tokenizer
+test suite](https://github.com/html5lib/html5lib-tests/tree/master/tokenizer). Since it is just a tokenizer, this means:
+
+* `html5gum` **does not** [implement charset
+  detection.](https://html.spec.whatwg.org/#determining-the-character-encoding)
+  This implementation takes and returns bytes, but assumes UTF-8. It recovers
+  gracefully from invalid UTF-8.
+* `html5gum` **does not** [correct mis-nested
+  tags.](https://html.spec.whatwg.org/#an-introduction-to-error-handling-and-strange-cases-in-the-parser)
+* `html5gum` doesn't implement the DOM, and unfortunately in the HTML spec,
+  constructing the DOM ("tree construction") influences how tokenization is
+  done. For an example of which problems this causes see [this example
+  code][examples/tokenize_with_state_switches.rs].
+* `html5gum` **does not** generally qualify as a browser-grade HTML *parser* as
+  per the WHATWG spec. This can change in the future, see [issue
+  21](https://github.com/untitaker/html5gum/issues/21).
+
+With those caveats in mind, `html5gum` can pretty much ~parse~ _tokenize_
+anything that browsers can. However, using the experimental `tree-builder`
+feature, html5gum can be integrated with `html5ever` and `scraper`. See [the
+`scraper.rs` example][examples/scraper.rs].
+
+## Other features
+
+* No unsafe Rust
+* Only dependency is `jetscii`, and can be disabled via crate features (see `Cargo.toml`)
+
+## Alternative HTML parsers
+
+`html5gum` was created out of a need to parse HTML tag soup efficiently. Previous options were to:
+
+* use [quick-xml](https://github.com/tafia/quick-xml/) or
+  [xmlparser](https://github.com/RazrFalcon/xmlparser) with some hacks to make
+  either one not choke on bad HTML. For some (rather large) set of HTML input
+  this works well (particularly `quick-xml` can be configured to be very
+  lenient about parsing errors) and parsing speed is stellar. But neither can
+  parse all HTML.
+
+  For my own usecase `html5gum` is about 2x slower than `quick-xml`.
+
+* use [html5ever's own
+  tokenizer](https://docs.rs/html5ever/0.25.1/html5ever/tokenizer/index.html)
+  to avoid as much tree-building overhead as possible. This was functional but
+  had poor performance for my own usecase (10-15x slower than `quick-xml`).
+
+* use [lol-html](https://github.com/cloudflare/lol-html), which would probably
+  perform at least as well as `html5gum`, but comes with a closure-based API
+  that I didn't manage to get working for my usecase.
+
+## Etymology
+
+Why is this library called `html5gum`?
+
+* G.U.M: **G**iant **U**nreadable **M**atch-statement
+
+* \<insert "how it feels to <s>chew 5 gum</s> _parse HTML_" meme here\>
+
+## License
+
+Licensed under the MIT license, see [`./LICENSE`][LICENSE].
+
+
+<!-- These link destinations are defined like this so that src/lib.rs can override them. -->
+[LICENSE]: ./LICENSE
+[examples/tokenize_with_state_switches.rs]: ./examples/tokenize_with_state_switches.rs
+[examples/custom_emitter.rs]: ./examples/custom_emitter.rs
+[examples/callback_emitter.rs]: ./examples/callback_emitter.rs
+[examples/scraper.rs]: ./examples/scraper.rs