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).

ci/lint/04_install.sh

@@ -57,3 +57,9 @@ 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-${SHELLCHECK_VERSION}/shellcheck" /usr/bin/
+
+# Markdown Link Checker: https://github.com/becheran/mlc
+MLC_VERSION=v0.16.3
+MLC_BIN=mlc-x86_64-linux
+curl -sL "https://github.com/becheran/mlc/releases/download/${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`](lint/lint-python-dead-code.py) | [vulture](https://github.com/jendrikseipp/vulture)
 | [`lint-shell.py`](lint/lint-shell.py) | [ShellCheck](https://github.com/koalaman/shellcheck)
 | [`lint-spelling.py`](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

@@ -5,8 +5,7 @@
 use std::env;
 use std::fs;
 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>;
@@ -284,6 +283,47 @@ fn lint_doc() -> LintResult {
     }
 }
 
+// Find a program on $PATH
+fn which(program: &str) -> bool {
+    if let Ok(path) = env::var("PATH") {
+        for p in path.split(':') {
+            let p_str = format!("{}/{}", p, program);
+            if fs::metadata(p_str).is_ok() {
+                return true;
+            }
+        }
+    }
+    false
+}
+
+fn lint_markdown() -> LintResult {
+    let bin_name = "mlc";
+    if !which(bin_name) {
+        println!(
+            "{} was not found in $PATH, skipping markdown lint check.",
+            bin_name
+        );
+        return Ok(());
+    }
+    let mut md_ignore_paths = get_subtrees()
+        .into_iter()
+        .map(|path| path.to_string())
+        .collect::<Vec<_>>();
+    md_ignore_paths.push("./doc/README_doxygen.md".to_string());
+    let md_ignore_path_str = md_ignore_paths.join(",");
+
+    let mut cmd = Command::new(bin_name);
+    cmd.arg("--offline")
+        .arg("--ignore-path")
+        .arg(md_ignore_path_str)
+        .arg("--root-dir")
+        .arg(".")
+        .stdout(Stdio::null())
+        .stderr(Stdio::inherit());
+
+    check_output(&mut cmd).map(|_output| ())
+}
+
 fn lint_all() -> LintResult {
     let mut good = true;
     let lint_dir = get_git_root().join("test/lint");
@@ -317,6 +357,7 @@ 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),
     ];