Skip to content

parallelize HTML checking tool #99933

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Aug 3, 2022
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions Cargo.lock
Original file line number Diff line number Diff line change
Expand Up @@ -1788,6 +1788,7 @@ dependencies = [
name = "html-checker"
version = "0.1.0"
dependencies = [
"rayon",
"walkdir",
]

Expand Down
1 change: 1 addition & 0 deletions src/tools/html-checker/Cargo.toml
Original file line number Diff line number Diff line change
Expand Up @@ -9,3 +9,4 @@ path = "main.rs"

[dependencies]
walkdir = "2"
rayon = "1.5"
46 changes: 25 additions & 21 deletions src/tools/html-checker/main.rs
Original file line number Diff line number Diff line change
@@ -1,3 +1,4 @@
use rayon::iter::{ParallelBridge, ParallelIterator};
use std::env;
use std::path::Path;
use std::process::{Command, Output};
Expand Down Expand Up @@ -56,27 +57,30 @@ const DOCS_TO_CHECK: &[&str] =

// Returns the number of files read and the number of errors.
fn find_all_html_files(dir: &Path) -> (usize, usize) {
let mut files_read = 0;
let mut errors = 0;

for entry in walkdir::WalkDir::new(dir).into_iter().filter_entry(|e| {
e.depth() != 1
|| e.file_name()
.to_str()
.map(|s| DOCS_TO_CHECK.into_iter().any(|d| *d == s))
.unwrap_or(false)
}) {
let entry = entry.expect("failed to read file");
if !entry.file_type().is_file() {
continue;
}
let entry = entry.path();
if entry.extension().and_then(|s| s.to_str()) == Some("html") {
errors += check_html_file(&entry);
files_read += 1;
}
}
(files_read, errors)
walkdir::WalkDir::new(dir)
.into_iter()
.filter_entry(|e| {
e.depth() != 1
|| e.file_name()
.to_str()
.map(|s| DOCS_TO_CHECK.into_iter().any(|d| *d == s))
.unwrap_or(false)
})
.par_bridge()
.map(|entry| {
let entry = entry.expect("failed to read file");
if !entry.file_type().is_file() {
return (0, 0);
}
let entry = entry.path();
// (Number of files processed, number of errors)
if entry.extension().and_then(|s| s.to_str()) == Some("html") {
(1, check_html_file(&entry))
} else {
(0, 0)
}
})
.reduce(|| (0, 0), |a, b| (a.0 + b.0, a.1 + b.1))
}

/// Default `tidy` command for macOS is too old that it does not have `mute-id` and `mute` options.
Expand Down