grace/htmlua
1
0
Fork 0
Code Issues Pull requests Projects Releases 2 Packages Wiki Activity Actions

Merge pull request #8 from trypsynth/syntect

Browse source 
Add basic syntax highlighting with the syntect crate. Closes #5
This commit is contained in:
Grace Yoder 2025-07-07 12:46:48 -06:00 • committed by GitHub
commit 23885aba3f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 392 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

307
Cargo.lock generated
View file

@ -2,6 +2,12 @@
# It is not intended for manual editing.
version = 4
[[package]]
name = "adler2"
version = "2.0.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "320119579fcad9c21884f5c4861d16174d0e06250625266f50fe6898340abefa"
[[package]]
name = "anyhow"
version = "1.0.98"
@ -14,6 +20,21 @@ version = "1.5.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c08606f8c3cbf4ce6ec8e28fb0014a2c086708fe954eaa885384a6165172e7e8"
[[package]]
name = "base64"
version = "0.22.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "72b3254f16251a8381aa12e40e3c4d2f0199f8c6508fbecb9d91f575e0fbb8c6"
[[package]]
name = "bincode"
version = "1.3.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b1f45e9417d87227c7a56d22e471c6206462cba514c7590c09aff4cf6d1ddcad"
dependencies = [
"serde",
]
[[package]]
name = "bitflags"
version = "1.3.2"
@ -44,9 +65,9 @@ checksum = "1fd0f2584146f6f2ef48085050886acf353beff7305ebd1ae69500e27c67f64b"
[[package]]
name = "cc"
version = "1.2.27"
version = "1.2.29"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d487aa071b5f64da6f19a3e848e3578944b726ee5a4854b82172f02aa876bfdc"
checksum = "5c1599538de2394445747c8cf7935946e3cc27e9625f889d979bfb2aaf569362"
dependencies = [
"shlex",
]
@ -63,6 +84,15 @@ version = "0.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6245d59a3e82a7fc217c5828a6692dbc6dfb63a0c8c90495621f7b9d79704a0e"
[[package]]
name = "crc32fast"
version = "1.4.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a97769d94ddab943e4510d138150169a2758b5ef3eb191a9ee688de3e23ef7b3"
dependencies = [
"cfg-if",
]
[[package]]
name = "cssparser"
version = "0.27.2"
@ -71,7 +101,7 @@ checksum = "754b69d351cdc2d8ee09ae203db831e005560fc6030da058f86ad60c92a9cb0a"
dependencies = [
"cssparser-macros",
"dtoa-short",
"itoa",
"itoa 0.4.8",
"matches",
"phf 0.8.0",
"proc-macro2",
@ -90,6 +120,15 @@ dependencies = [
"syn 2.0.104",
]
[[package]]
name = "deranged"
version = "0.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9c9e6a11ca8224451684bc0d7d5a7adbf8f2fd6887261a1cfc3c0432f9d4068e"
dependencies = [
"powerfmt",
]
[[package]]
name = "derive_more"
version = "0.99.20"
@ -130,6 +169,12 @@ version = "0.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c7f84e12ccf0a7ddc17a6c41c93326024c42920d7ee630d04950e6926645c0fe"
[[package]]
name = "equivalent"
version = "1.0.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "877a4ace8713b0bcf2a4e7eec82529c029f1d0619886d18145fea96c3ffe5c0f"
[[package]]
name = "erased-serde"
version = "0.4.6"
@ -150,6 +195,22 @@ dependencies = [
"windows-sys 0.60.2",
]
[[package]]
name = "flate2"
version = "1.1.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4a3d7db9596fecd151c5f638c0ee5d5bd487b6e0ea232e5dc96d5250f6f94b1d"
dependencies = [
"crc32fast",
"miniz_oxide",
]
[[package]]
name = "fnv"
version = "1.0.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3f9eec918d3f24069decb9af1554cad7c880e2da24a9afd88aca000531ab82c1"
[[package]]
name = "futf"
version = "0.1.5"
@ -206,6 +267,12 @@ version = "0.12.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8a9ee70c43aaf417c914396645a0fa852624801b24ebb7ae78fe8272889ac888"
[[package]]
name = "hashbrown"
version = "0.15.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5971ac85611da7067dbfcabef3c70ebb5606018acd9e2a3903a0da507521e0d5"
[[package]]
name = "html5ever"
version = "0.26.0"
@ -249,6 +316,7 @@ dependencies = [
"markup5ever 0.11.0",
"mlua",
"pulldown-cmark",
"syntect",
"tendril",
]
@ -263,7 +331,17 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bd070e393353796e801d209ad339e89596eb4c8d430d18ede6a1cced8fafbd99"
dependencies = [
"autocfg",
"hashbrown",
"hashbrown 0.12.3",
]
[[package]]
name = "indexmap"
version = "2.10.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "fe4cd85333e22411419a0bcae1297d25e58c9443848b11dc6a86fefe8c78a661"
dependencies = [
"equivalent",
"hashbrown 0.15.4",
]
[[package]]
@ -272,6 +350,12 @@ version = "0.4.8"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b71991ff56294aa922b450139ee08b3bfc70982c6b2c7562771375cf73542dd4"
[[package]]
name = "itoa"
version = "1.0.15"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4a5f13b858c8d314ee3e8f639011f7ccefe71f97f96e50151fb991f267928e2c"
[[package]]
name = "kuchikiki"
version = "0.8.2"
@ -279,8 +363,8 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f29e4755b7b995046f510a7520c42b2fed58b77bd94d5a87a8eb43d2fd126da8"
dependencies = [
"cssparser",
"html5ever 0.26.0",
"indexmap",
"html5ever",
"indexmap 1.9.3",
"matches",
"selectors",
]
@ -291,6 +375,12 @@ version = "0.2.174"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1171693293099992e19cddea4e8b849964e9846f4acee11b3948bcc337be8776"
[[package]]
name = "linked-hash-map"
version = "0.5.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0717cef1bc8b636c6e1c1bbdefc09e6322da8a9321966e8928ef80d20f7f770f"
[[package]]
name = "linux-raw-sys"
version = "0.9.4"
@ -386,6 +476,15 @@ version = "2.7.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "32a282da65faaf38286cf3be983213fcf1d2e2a58700e808f83f4ea9a4804bc0"
[[package]]
name = "miniz_oxide"
version = "0.8.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1fa76a2c86f704bdb222d66965fb3d63269ce38518b83cb0575fca855ebb6316"
dependencies = [
"adler2",
]
[[package]]
name = "mlua"
version = "0.10.5"
@ -429,6 +528,12 @@ version = "0.1.14"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "72ef4a56884ca558e5ddb05a1d1e7e1bfd9a68d9ed024c21704cc98872dae1bb"
[[package]]
name = "num-conv"
version = "0.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "51d515d32fb182ee37cda2ccdcb92950d6a3c2893aa280e540671c2cd0f3b1d9"
[[package]]
name = "num-traits"
version = "0.2.19"
@ -438,6 +543,34 @@ dependencies = [
"autocfg",
]
[[package]]
name = "once_cell"
version = "1.21.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "42f5e15c9953c5e4ccceeb2e7382a716482c34515315f7b03532b8b4e8393d2d"
[[package]]
name = "onig"
version = "6.5.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "336b9c63443aceef14bea841b899035ae3abe89b7c486aaf4c5bd8aafedac3f0"
dependencies = [
"bitflags 2.9.1",
"libc",
"once_cell",
"onig_sys",
]
[[package]]
name = "onig_sys"
version = "69.9.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c7f86c6eef3d6df15f23bcfb6af487cbd2fed4e5581d58d5bf1f5f8b7f6727dc"
dependencies = [
"cc",
"pkg-config",
]
[[package]]
name = "ordered-float"
version = "2.10.1"
@ -606,6 +739,25 @@ version = "0.3.32"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7edddbd0b52d732b21ad9a5fab5c704c14cd949e5e9a1ec5929a24fded1b904c"
[[package]]
name = "plist"
version = "1.7.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "546b279bf0638ee811d9e47de2ca5b66575a543035d79fdf83959dd2f5c3b4c3"
dependencies = [
"base64",
"indexmap 2.10.0",
"quick-xml",
"serde",
"time",
]
[[package]]
name = "powerfmt"
version = "0.2.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "439ee305def115ba05938db6eb1644ff94165c5ab5e9420d1c1bcedbba909391"
[[package]]
name = "ppv-lite86"
version = "0.2.21"
@ -655,6 +807,15 @@ version = "0.11.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "007d8adb5ddab6f8e3f491ac63566a7d5002cc7ed73901f72057943fa71ae1ae"
[[package]]
name = "quick-xml"
version = "0.37.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "331e97a1af0bf59823e6eadffe373d7b27f485be8748f71471c662c1f269b7fb"
dependencies = [
"memchr",
]
[[package]]
name = "quote"
version = "1.0.40"
@ -754,6 +915,12 @@ dependencies = [
"bitflags 2.9.1",
]
[[package]]
name = "regex-syntax"
version = "0.8.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2b15c43186be67a4fd63bee50d0303afffcef381492ebe2c5d87f324e1b8815c"
[[package]]
name = "rustc-hash"
version = "2.1.1"
@ -788,6 +955,21 @@ version = "1.0.21"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8a0d197bd2c9dc6e53b84da9556a69ba4cdfab8619eb41a8bd1cc2027a0f6b1d"
[[package]]
name = "ryu"
version = "1.0.20"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "28d3b2b1366ec20994f1fd18c3c594f05c5dd4bc44d8bb0c1c632c8d6829481f"
[[package]]
name = "same-file"
version = "1.0.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "93fc1dc3aaa9bfed95e02e6eadabb4baf7e3078b0bd1b4d7b6b0b68378900502"
dependencies = [
"winapi-util",
]
[[package]]
name = "scopeguard"
version = "1.2.0"
@ -850,6 +1032,18 @@ dependencies = [
"syn 2.0.104",
]
[[package]]
name = "serde_json"
version = "1.0.140"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "20068b6e96dc6c9bd23e01df8827e6c7e1f2fddd43c21810382803c136b99373"
dependencies = [
"itoa 1.0.15",
"memchr",
"ryu",
"serde",
]
[[package]]
name = "servo_arc"
version = "0.1.1"
@ -937,6 +1131,28 @@ dependencies = [
"unicode-ident",
]
[[package]]
name = "syntect"
version = "5.2.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "874dcfa363995604333cf947ae9f751ca3af4522c60886774c4963943b4746b1"
dependencies = [
"bincode",
"bitflags 1.3.2",
"flate2",
"fnv",
"once_cell",
"onig",
"plist",
"regex-syntax",
"serde",
"serde_derive",
"serde_json",
"thiserror",
"walkdir",
"yaml-rust",
]
[[package]]
name = "tendril"
version = "0.4.3"
@ -954,6 +1170,57 @@ version = "0.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8eaa81235c7058867fa8c0e7314f33dcce9c215f535d1913822a2b3f5e289f3c"
[[package]]
name = "thiserror"
version = "1.0.69"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b6aaf5339b578ea85b50e080feb250a3e8ae8cfcdff9a461c9ec2904bc923f52"
dependencies = [
"thiserror-impl",
]
[[package]]
name = "thiserror-impl"
version = "1.0.69"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4fee6c4efc90059e10f81e6d42c60a18f76588c3d74cb83a0b242a2b6c7504c1"
dependencies = [
"proc-macro2",
"quote",
"syn 2.0.104",
]
[[package]]
name = "time"
version = "0.3.41"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8a7619e19bc266e0f9c5e6686659d394bc57973859340060a69221e57dbc0c40"
dependencies = [
"deranged",
"itoa 1.0.15",
"num-conv",
"powerfmt",
"serde",
"time-core",
"time-macros",
]
[[package]]
name = "time-core"
version = "0.1.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c9e9a38711f559d9e3ce1cdb06dd7c5b8ea546bc90052da6d06bb76da74bb07c"
[[package]]
name = "time-macros"
version = "0.2.22"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3526739392ec93fd8b359c8e98514cb3e8e021beb4e5f597b00a0221f8ed8a49"
dependencies = [
"num-conv",
"time-core",
]
[[package]]
name = "typeid"
version = "1.0.3"
@ -984,6 +1251,16 @@ version = "0.7.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "09cc8ee72d2a9becf2f2febe0205bbed8fc6615b7cb429ad062dc7b7ddd036a9"
[[package]]
name = "walkdir"
version = "2.5.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "29790946404f91d9c5d06f9874efddea1dc06c5efe94541a7d6863108e3a5e4b"
dependencies = [
"same-file",
"winapi-util",
]
[[package]]
name = "wasi"
version = "0.9.0+wasi-snapshot-preview1"
@ -1020,6 +1297,15 @@ dependencies = [
"winsafe",
]
[[package]]
name = "winapi-util"
version = "0.1.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "cf221c93e13a30d793f7645a0e7762c55d169dbb0a49671918a2319d289b10bb"
dependencies = [
"windows-sys 0.59.0",
]
[[package]]
name = "windows-sys"
version = "0.59.0"
@ -1172,6 +1458,15 @@ version = "0.0.19"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d135d17ab770252ad95e9a872d365cf3090e3be864a34ab46f48555993efc904"
[[package]]
name = "yaml-rust"
version = "0.4.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "56c1936c4cc7a1c9ab21a1ebb602eb942ba868cbd44a99cb7cdc5892335e1c85"
dependencies = [
"linked-hash-map",
]
[[package]]
name = "zerocopy"
version = "0.8.26"

1
htmlua-parser/Cargo.toml
View file

@ -10,6 +10,7 @@ kuchikiki = "0.8.2"
markup5ever = "0.11.0"
mlua = { version = "0.10.5", features = ["lua54", "vendored", "serialize"] }
pulldown-cmark = "0.13.0"
syntect = "5.2.0"
tendril = "0.4.3"

90
htmlua-parser/src/render.rs
View file

@ -4,6 +4,13 @@ use anyhow::{Result, anyhow};
use kuchikiki::{NodeRef, traits::TendrilSink};
use mlua::{Lua, Table};
use pulldown_cmark::{Options, Parser, html};
use syntect::{
easy::HighlightLines,
highlighting::{Style, ThemeSet},
html::{IncludeBackground, styled_line_to_highlighted_html},
parsing::SyntaxSet,
util::LinesWithEndings,
};
use crate::helpers::read_doc_from_file;
@ -129,6 +136,54 @@ pub fn expand_template(document: NodeRef, component_path: &PathBuf, include_from
Ok(document)
}
pub fn process_syntax_highlighting(document: NodeRef) -> Result<NodeRef> {
let ps = SyntaxSet::load_defaults_newlines();
let mut ts = ThemeSet::load_defaults();
let syntax_elements: Vec<_> = match document.select("syntaxhighlight") {
Ok(e) => e.collect(),
Err(()) => return Err(anyhow!("Unable to find syntaxhighlight elements")),
};
if !syntax_elements.is_empty() {
// TODO: read from config
let themes = PathBuf::from("/var/www/htmlua/themes");
ts.add_from_folder(themes)?;
}
for node in syntax_elements {
let attrs = match node.as_node().as_element() {
Some(e) => e.attributes.borrow(),
None => continue,
};
let language = attrs.get("lang").unwrap_or("text");
let theme_name = attrs.get("theme").unwrap_or("base16-ocean.dark");
if let Some(text_node) = node.as_node().first_child() {
if let Some(code_text) = text_node.as_text() {
let syntax = ps
.find_syntax_by_extension(language)
.or_else(|| ps.find_syntax_by_name(language))
.unwrap_or_else(|| ps.find_syntax_plain_text());
let theme = &ts.themes[theme_name];
let mut h = HighlightLines::new(syntax, theme);
let mut html_output = String::new();
write!(html_output, r#"<pre class="syntax-highlight" data-lang="{language}">"#)?;
html_output.push_str("<code>");
for line in LinesWithEndings::from(&code_text.borrow()) {
let ranges: Vec<(Style, &str)> = h.highlight_line(line, &ps)?;
let escaped = styled_line_to_highlighted_html(&ranges[..], IncludeBackground::No)?;
html_output.push_str(&escaped);
}
html_output.push_str("</code></pre>");
let html_fragment = kuchikiki::parse_html().one(html_output);
for child in html_fragment.children() {
node.as_node().insert_before(child);
}
// Remove the original syntaxhighlight node.
node.as_node().detach();
}
}
}
Ok(document)
}
#[cfg(test)]
mod tests {
use super::*;
@ -238,7 +293,6 @@ mod tests {
let text = d.select_first("#inc1").unwrap().as_node().text_contents();
assert_eq!(text, "included1");
assert!(d.select_first("include").is_err());
}
#[test]
@ -293,7 +347,7 @@ mod tests {
#[test]
fn basic_markdown() {
let page = r#"
let page = r"
<!DOCTYPE html>
<html>
<head>
@ -312,11 +366,41 @@ This is a paragraph with **bold text** and *italic text*.
</markdown>
</div>
</body>
</html>"#;
</html>";
let document = kuchikiki::parse_html().one(page);
let d = process_markdown(document).unwrap();
assert!(d.select_first("markdown").is_err());
assert!(d.select_first("p").is_ok());
assert!(d.select_first("ul").is_ok());
}
#[test]
fn basic_syntax_highlighting() {
let page = r#"
<!DOCTYPE html>
<html>
<head>
<title>Syntax Highlighting Test</title>
</head>
<body>
<h1>Code Example</h1>
<syntaxhighlight lang="rust">
fn main() {
println!("Hello, world!");
let x = 42;
let y = "test";
}
</syntaxhighlight>
</body>
</html>"#;
let document = kuchikiki::parse_html().one(page);
let d = process_syntax_highlighting(document).unwrap();
assert!(d.select_first("syntaxhighlight").is_err());
assert!(d.select_first("pre").is_ok());
assert!(d.select_first("code").is_ok());
let pre = d.select_first("pre").unwrap();
let attrs = pre.attributes.borrow();
assert_eq!(attrs.get("data-lang"), Some("rust"));
assert!(attrs.get("class").unwrap().contains("syntax-highlight"));
}
}

5
htmlua-parser/src/serve.rs
View file

@ -1,6 +1,6 @@
use crate::helpers::read_doc_from_file;
use super::render::{execute_lua, expand_template, process_markdown};
use super::render::{execute_lua, expand_template, process_markdown, process_syntax_highlighting};
use anyhow::Result;
use std::path::{Path, PathBuf}
;
@ -16,6 +16,7 @@ pub fn serve_content(request_uri: &str) -> Result<String> {
let full_doc = expand_template(doc, &components, None)?;
let markdown_doc = process_markdown(full_doc)?;
let executed_doc = execute_lua(markdown_doc)?;
let highlighted_doc = process_syntax_highlighting(markdown_doc)?;
let executed_doc = execute_lua(highlighted_doc)?;
Ok(executed_doc.to_string())
}