lint: add markdown hyperlink checker

This adds a markdown hyperlink check task to the lint test_runner. It
relies on having the [`mlc`](https://crates.io/crates/mlc) binary found
on $PATH, but will fail with `success` if the binary is not found.

`mlc` is also added to the ci/04_install.sh script run by the
containerfile.

Note that broken markdown hyperlinks will be detected in untracked
markdown files found in a dirty working directory (including e.g.
.venv).

Author: willcl-ark

ci/lint/04_install.sh

@@ -57,3 +57,8 @@ SHELLCHECK_VERSION=v0.8.0
 curl -sL "https://github.com/koalaman/shellcheck/releases/download/${SHELLCHECK_VERSION}/shellcheck-${SHELLCHECK_VERSION}.linux.x86_64.tar.xz" | \
     tar --xz -xf - --directory /tmp/
 mv "/tmp/shellcheck-${SHELLCHECK_VERSION}/shellcheck" /usr/bin/
+
+MLC_VERSION=v0.16.3
+MLC_BIN=mlc-x86_64-linux
+curl -sL "https://github.com/becheran/mlc/releases/download/${MLC_VERSION}/${MLC_BIN}" -o "/usr/bin/mlc"
+chmod +x /usr/bin/mlc

test/lint/README.md

@@ -37,6 +37,7 @@ Then you can use:
 | [`lint-python-dead-code.py`](/test/lint/lint-python-dead-code.py) | [vulture](https://github.com/jendrikseipp/vulture)
 | [`lint-shell.py`](/test/lint/lint-shell.py) | [ShellCheck](https://github.com/koalaman/shellcheck)
 | [`lint-spelling.py`](/test/lint/lint-spelling.py) | [codespell](https://github.com/codespell-project/codespell)
+| markdown link check | [mlc](https://github.com/becheran/mlc)
 
 In use versions and install instructions are available in the [CI setup](../../ci/lint/04_install.sh).
 

test/lint/test_runner/src/main.rs

@@ -4,9 +4,9 @@
 
 use std::env;
 use std::fs;
+use std::io::ErrorKind;
 use std::path::{Path, PathBuf};
-use std::process::Command;
-use std::process::ExitCode;
+use std::process::{Command, ExitCode, Stdio};
 
 type LintError = String;
 type LintResult = Result<(), LintError>;
@@ -292,6 +292,51 @@ fn lint_doc() -> LintResult {
     }
 }
 
+fn lint_markdown() -> LintResult {
+    let bin_name = "mlc";
+    let mut md_ignore_paths = get_subtrees();
+    md_ignore_paths.push("./doc/README_doxygen.md");
+    let md_ignore_path_str = md_ignore_paths.join(",");
+
+    let mut cmd = Command::new(bin_name);
+    cmd.args([
+        "--offline",
+        "--ignore-path",
+        md_ignore_path_str.as_str(),
+        "--root-dir",
+        ".",
+    ])
+    .stdout(Stdio::null()); // Suppress overly-verbose output
+
+    match cmd.output() {
+        Ok(output) if output.status.success() => Ok(()),
+        Ok(output) => {
+            let stderr = String::from_utf8_lossy(&output.stderr);
+            let filtered_stderr: String = stderr // Filter out this annoying trailing line
+                .lines()
+                .filter(|&line| line != "The following links could not be resolved:")
+                .collect::<Vec<&str>>()
+                .join("\n");
+            Err(format!(
+                r#"
+One or more markdown links are broken.
+
+Relative links are preferred (but not required) as jumping to file works natively within Emacs.
+
+Markdown link errors found:
+{}
+                "#,
+                filtered_stderr
+            ))
+        }
+        Err(e) if e.kind() == ErrorKind::NotFound => {
+            println!("`mlc` was not found in $PATH, skipping markdown lint check.");
+            Ok(())
+        }
+        Err(e) => Err(format!("Error running mlc: {}", e)), // Misc errors
+    }
+}
+
 fn lint_all() -> LintResult {
     let mut good = true;
     let lint_dir = get_git_root().join("test/lint");
@@ -325,6 +370,7 @@ fn main() -> ExitCode {
         ("no-tabs check", lint_tabs_whitespace),
         ("build config includes check", lint_includes_build_config),
         ("-help=1 documentation check", lint_doc),
+        ("markdown hyperlink check", lint_markdown),
         ("lint-*.py scripts", lint_all),
     ];