fix: Include untracked files with --gitignore option

The current `--gitignore` option correctly ignores files which are
"ignored" by git, but the `--ignore` option to `git ls-files` does not
include untracked files in it's output.

These can be detected using `git ls-files --others --exclude-standard`.

Combine the two calls into a single deduplicated gitignore list to
ignore all files properly.

README.md

@@ -102,7 +102,7 @@ Another example is to call *mlc* on a certain directory or file:
 mlc ./docs
 ```
 
-Alternatively you may want to ignore all files currently ignored by `git` (requires `git` binary to be found on $PATH) and set a root-dir for relative links:
+Alternatively you may want to ignore all files currently ignored or untracked by `git` (requires `git` binary to be found on $PATH) and set a root-dir for relative links:
 
 ```bash
 mlc --gitignore --root-dir .
@@ -126,7 +126,7 @@ The following arguments are available:
 | `--match-file-extension` | `-e`  | Set the flag, if the file extension shall be checked as well. For example the following markup link `[link](dir/file)` matches if for example a file called `file.md` exists in `dir`, but would fail when the `--match-file-extension` flag is set. |
 | `--version`      | `-V` | Print current version of mlc |
 | `--ignore-path`  | `-p` | Comma separated list of directories or files which shall be ignored. For example  |
-| `--gitignore`    | `-g` | Ignore all files currently ignored by git (requires `git` binary to be available on $PATH). |
+| `--gitignore`    | `-g` | Ignore all files currently ignored or untracked by git (requires `git` binary to be available on $PATH). |
 | `--ignore-links` | `-i` | Comma separated list of links which shall be ignored. Use simple `?` and `*` wildcards. For example `--ignore-links "http*://crates.io*"` will skip all links to the crates.io website. See the [used lib](https://github.com/becheran/wildmatch) for more information.  |
 | `--markup-types` | `-t` | Comma separated list list of markup types which shall be checked [possible values: md, html] |
 | `--root-dir`     | `-r` | All links to the file system starting with a slash on linux or backslash on windows will use another virtual root dir. For example the link in a file `[link](/dir/other/file.md)` checked with the cli arg `--root-dir /env/another/dir` will let *mlc* check the existence of `/env/another/dir/dir/other/file.md`. |

src/lib.rs

@@ -12,6 +12,7 @@ use crate::link_validator::resolve_target_link;
 use crate::markup::MarkupFile;
 use serde::Deserialize;
 use std::collections::HashMap;
+use std::collections::HashSet;
 use std::env;
 use std::fmt;
 use std::fs;
@@ -132,23 +133,20 @@ fn find_all_links(config: &Config) -> Vec<MarkupLink> {
     links
 }
 
-fn find_git_ignored_files() -> Option<Vec<PathBuf>> {
+fn get_git_files(args: &[&str]) -> Option<Vec<PathBuf>> {
     let output = Command::new("git")
-    .arg("ls-files")
-    .arg("--ignored")
-    .arg("--others")
-    .arg("--exclude-standard")
-    .output()
-    .expect("Failed to execute 'git' command");
+        .arg("ls-files")
+        .args(args)
+        .output()
+        .expect("Failed to execute 'git' command");
 
     if output.status.success() {
-        let ignored_files = String::from_utf8(output.stdout)
+        let files = String::from_utf8(output.stdout)
             .expect("Invalid UTF-8 sequence")
             .lines()
-            .filter(|line| line.ends_with(".md") || line.ends_with(".html"))
             .filter_map(|line| fs::canonicalize(Path::new(line.trim())).ok())
-            .collect::<Vec<_>>();
-        Some(ignored_files)
+            .collect();
+        Some(files)
     } else {
         eprintln!(
             "git ls-files command failed: {}",
@@ -158,6 +156,24 @@ fn find_git_ignored_files() -> Option<Vec<PathBuf>> {
     }
 }
 
+fn find_git_ignored_files() -> Option<Vec<PathBuf>> {
+    let ignored_files = get_git_files(&["--ignored", "--others", "--exclude-standard"])?;
+    let untracked_files = get_git_files(&["--others", "--exclude-standard"])?;
+
+    let mut combined_files: HashSet<PathBuf> = HashSet::new();
+    combined_files.extend(ignored_files);
+    combined_files.extend(untracked_files);
+
+    let result = combined_files
+        .into_iter()
+        .filter(|path| {
+            path.extension()
+                .map_or(false, |ext| ext == "md" || ext == "html")
+        })
+        .collect();
+
+    Some(result)
+}
 
 fn print_helper(
     link: &MarkupLink,