D7864: rust-utils: add Rust implementation of Python's "os.path.splitdrive"

[Alphare (Raphaël Gomès)]

Alphare created this revision.
Herald added subscribers: mercurial-devel, kevincox, durin42.
Herald added a reviewer: hg-reviewers.

REVISION SUMMARY
  I also wrote the NT version although I didn't mean to at first, so I thought
  I would keep it, so that any further effort to get the Rust code working on
  Windows is a little easier.

REPOSITORY
  rHG Mercurial

BRANCH
  default

REVISION DETAIL
  https://phab.mercurial-scm.org/D7864

AFFECTED FILES
  rust/hg-core/src/utils/files.rs

CHANGE DETAILS

diff --git a/rust/hg-core/src/utils/files.rs b/rust/hg-core/src/utils/files.rs
--- a/rust/hg-core/src/utils/files.rs
+++ b/rust/hg-core/src/utils/files.rs
@@ -85,6 +85,83 @@
     path.to_ascii_lowercase()
 }
 
+#[cfg(windows)]
+/// Copied from the Python stdlib's `os.path.splitdrive` implementation.
+///
+/// Split a pathname into drive/UNC sharepoint and relative path specifiers.
+/// Returns a 2-tuple (drive_or_unc, path); either part may be empty.
+///
+/// If you assign
+///  result = split_drive(p)
+/// It is always true that:
+///  result[0] + result[1] == p
+///
+/// If the path contained a drive letter, drive_or_unc will contain everything
+/// up to and including the colon.
+/// e.g. split_drive("c:/dir") returns ("c:", "/dir")
+///
+/// If the path contained a UNC path, the drive_or_unc will contain the host
+/// name and share up to but not including the fourth directory separator
+/// character.
+/// e.g. split_drive("//host/computer/dir") returns ("//host/computer", "/dir")
+///
+/// Paths cannot contain both a drive letter and a UNC path.
+pub fn split_drive(path: impl AsRef<HgPath>) -> (HgPathBuf, HgPathBuf) {
+    let path = path.as_ref();
+    let sep = std::path::MAIN_SEPARATOR as u8;
+    let bytes = path.as_bytes();
+    let norm_bytes: Vec<_> = path
+        .as_bytes()
+        .iter()
+        .map(|c| if *c == b'\\' { sep } else { *c })
+        .collect();
+    if norm_bytes.len() > 1 {
+        if norm_bytes[0] == sep
+            && norm_bytes[1] == sep
+            && (norm_bytes.len() < 3 || norm_bytes[2] != sep)
+        {
+            // Is a UNC path:
+            // vvvvvvvvvvvvvvvvvvvv drive letter or UNC path
+            // \\machine\mountpoint\directory\etc\...
+            //           directory ^^^^^^^^^^^^^^^
+            let index = norm_bytes[2..].iter().position(|b| *b == sep);
+            if index.is_none() {
+                return (HgPathBuf::new(), path.to_owned());
+            }
+            let index = index.unwrap() + 2;
+
+            let index2 =
+                norm_bytes[index + 1..].iter().position(|b| *b == sep);
+            // A UNC path can't have two slashes in a row
+            // (after the initial two)
+            if index2 == Some(0) {
+                return (HgPathBuf::new(), path.to_owned());
+            }
+            let index2 = match index2 {
+                Some(i) => i + index + 1,
+                None => norm_bytes.len(),
+            };
+            return (
+                HgPathBuf::from_bytes(&bytes[..index2]),
+                HgPathBuf::from_bytes(&bytes[index2..]),
+            );
+        }
+        if norm_bytes[1] == b':' {
+            return (
+                HgPathBuf::from_bytes(&bytes[..2]),
+                HgPathBuf::from_bytes(&bytes[2..]),
+            );
+        }
+    }
+    (HgPathBuf::new(), path.to_owned())
+}
+
+#[cfg(unix)]
+/// Split a pathname into drive and path. On Posix, drive is always empty.
+pub fn split_drive(path: impl AsRef<HgPath>) -> (HgPathBuf, HgPathBuf) {
+    (HgPathBuf::new(), path.as_ref().into())
+}
+
 #[derive(Eq, PartialEq, Ord, PartialOrd, Copy, Clone)]
 pub struct HgMetadata {
     pub st_dev: u64,
@@ -133,4 +210,101 @@
         assert_eq!(dirs.next(), None);
         assert_eq!(dirs.next(), None);
     }
+
+    #[test]
+    #[cfg(unix)]
+    fn test_split_drive() {
+        // Taken from the Python stdlib's tests
+        assert_eq!(
+            split_drive(HgPath::new(br"/foo/bar")),
+            (HgPathBuf::new(), HgPathBuf::from_bytes(br"/foo/bar"))
+        );
+        assert_eq!(
+            split_drive(HgPath::new(br"foo:bar")),
+            (HgPathBuf::new(), HgPathBuf::from_bytes(br"foo:bar"))
+        );
+        assert_eq!(
+            split_drive(HgPath::new(br":foo:bar")),
+            (HgPathBuf::new(), HgPathBuf::from_bytes(br":foo:bar"))
+        );
+    }
+
+    #[test]
+    #[cfg(windows)]
+    fn test_split_drive() {
+        assert_eq!(
+            split_drive(HgPathBuf::from_bytes(br"c:\foo\bar")),
+            (
+                HgPathBuf::from_bytes(br"c:"),
+                HgPathBuf::from_bytes(br"\foo\bar")
+            )
+        );
+        assert_eq!(
+            split_drive(HgPathBuf::from_bytes(b"c:/foo/bar")),
+            (
+                HgPathBuf::from_bytes(br"c:"),
+                HgPathBuf::from_bytes(br"/foo/bar")
+            )
+        );
+        assert_eq!(
+            split_drive(HgPathBuf::from_bytes(br"\\conky\mountpoint\foo\bar")),
+            (
+                HgPathBuf::from_bytes(br"\\conky\mountpoint"),
+                HgPathBuf::from_bytes(br"\foo\bar")
+            )
+        );
+        assert_eq!(
+            split_drive(HgPathBuf::from_bytes(br"//conky/mountpoint/foo/bar")),
+            (
+                HgPathBuf::from_bytes(br"//conky/mountpoint"),
+                HgPathBuf::from_bytes(br"/foo/bar")
+            )
+        );
+        assert_eq!(
+            split_drive(HgPathBuf::from_bytes(
+                br"\\\conky\mountpoint\foo\bar"
+            )),
+            (
+                HgPathBuf::from_bytes(br""),
+                HgPathBuf::from_bytes(br"\\\conky\mountpoint\foo\bar")
+            )
+        );
+        assert_eq!(
+            split_drive(HgPathBuf::from_bytes(
+                br"///conky/mountpoint/foo/bar"
+            )),
+            (
+                HgPathBuf::from_bytes(br""),
+                HgPathBuf::from_bytes(br"///conky/mountpoint/foo/bar")
+            )
+        );
+        assert_eq!(
+            split_drive(HgPathBuf::from_bytes(
+                br"\\conky\\mountpoint\foo\bar"
+            )),
+            (
+                HgPathBuf::from_bytes(br""),
+                HgPathBuf::from_bytes(br"\\conky\\mountpoint\foo\bar")
+            )
+        );
+        assert_eq!(
+            split_drive(HgPathBuf::from_bytes(
+                br"//conky//mountpoint/foo/bar"
+            )),
+            (
+                HgPathBuf::from_bytes(br""),
+                HgPathBuf::from_bytes(br"//conky//mountpoint/foo/bar")
+            )
+        );
+        // UNC part containing U+0130
+        assert_eq!(
+            split_drive(HgPathBuf::from_bytes(
+                b"//conky/MOUNTPO\xc4\xb0NT/foo/bar"
+            )),
+            (
+                HgPathBuf::from_bytes(b"//conky/MOUNTPO\xc4\xb0NT"),
+                HgPathBuf::from_bytes(br"/foo/bar")
+            )
+        );
+    }
 }



To: Alphare, #hg-reviewers
Cc: durin42, kevincox, mercurial-devel