Rollup merge of #143957 - samueltardieu:tidy-filenames, r=Kobzol

tidy: check for invalid file names

Check for file names added to git with:
- non-UTF8 filenames (this would fail "fmt check" with a decoding error for the moment, but maybe we should not count on it as it is an accidental failure)
- control characters (such as "\n" or "\r" in file names)
- ":" (which is a special character on Windows, made rust-lang/rust#142936 fail in bors while it could have be caught earlier)

It only checks files known by git as a developer might want to have "strange" file names alongside their local repository as long as they don't check them in.

r? jieyouxu
as he stumbled upon such a file in rust-lang/rust#142936

3 files changed, 43 insertions, 0 deletions

diff --git a/src/tools/tidy/src/filenames.rs b/src/tools/tidy/src/filenames.rs
new file mode 100644
index 00000000000..53115f4eaa4
--- /dev/null
+++ b/src/tools/tidy/src/filenames.rs
@@ -0,0 +1,40 @@
+//! Tidy check to ensure that there are no filenames containing forbidden characters
+//! checked into the source tree by accident:
+//! - Non-UTF8 filenames
+//! - Control characters such as CR or TAB
+//! - Filenames containing ":" as they are not supported on Windows
+//!
+//! Only files added to git are checked, as it may be acceptable to have temporary
+//! invalid filenames in the local directory during development.
+
+use std::path::Path;
+use std::process::Command;
+
+pub fn check(root_path: &Path, bad: &mut bool) {
+    let stat_output = Command::new("git")
+        .arg("-C")
+        .arg(root_path)
+        .args(["ls-files", "-z"])
+        .output()
+        .unwrap()
+        .stdout;
+    for filename in stat_output.split(|&b| b == 0) {
+        match str::from_utf8(filename) {
+            Err(_) => tidy_error!(
+                bad,
+                r#"non-UTF8 file names are not supported: "{}""#,
+                String::from_utf8_lossy(filename),
+            ),
+            Ok(name) if name.chars().any(|c| c.is_control()) => tidy_error!(
+                bad,
+                r#"control characters are not supported in file names: "{}""#,
+                String::from_utf8_lossy(filename),
+            ),
+            Ok(name) if name.contains(':') => tidy_error!(
+                bad,
+                r#"":" is not supported in file names because of Windows compatibility: "{name}""#,
+            ),
+            _ => (),
+        }
+    }
+}
diff --git a/src/tools/tidy/src/lib.rs b/src/tools/tidy/src/lib.rs
index 77855392b4d..ade4055b5bd 100644
--- a/src/tools/tidy/src/lib.rs
+++ b/src/tools/tidy/src/lib.rs
@@ -167,6 +167,7 @@ pub mod error_codes;
 pub mod ext_tool_checks;
 pub mod extdeps;
 pub mod features;
+pub mod filenames;
 pub mod fluent_alphabetical;
 pub mod fluent_period;
 mod fluent_used;
diff --git a/src/tools/tidy/src/main.rs b/src/tools/tidy/src/main.rs
index a67f7a511b5..0f1116a632e 100644
--- a/src/tools/tidy/src/main.rs
+++ b/src/tools/tidy/src/main.rs
@@ -155,6 +155,8 @@ fn main() {
 
         check!(triagebot, &root_path);
 
+        check!(filenames, &root_path);
+
         let collected = {
             drain_handles(&mut handles);