rust-utils: add util for canonical path

Differential Revision: https://phab.mercurial-scm.org/D7871

rust/Cargo.lock

@@ -169,6 +169,7 b' dependencies = ['
  "rand_pcg 0.1.2 (registry+https://github.com/rust-lang/crates.io-index)",
  "rayon 1.3.0 (registry+https://github.com/rust-lang/crates.io-index)",
  "regex 1.3.4 (registry+https://github.com/rust-lang/crates.io-index)",
+ "same-file 1.0.6 (registry+https://github.com/rust-lang/crates.io-index)",
  "tempfile 3.1.0 (registry+https://github.com/rust-lang/crates.io-index)",
  "twox-hash 1.5.0 (registry+https://github.com/rust-lang/crates.io-index)",
 ]
@@ -489,6 +490,14 b' dependencies = ['
 ]
 
 [[package]]
+name = "same-file"
+version = "1.0.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+dependencies = [
+ "winapi-util 0.1.3 (registry+https://github.com/rust-lang/crates.io-index)",
+]
+
+[[package]]
 name = "scopeguard"
 version = "1.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
@@ -570,6 +579,14 b' version = "0.4.0"'
 source = "registry+https://github.com/rust-lang/crates.io-index"
 
 [[package]]
+name = "winapi-util"
+version = "0.1.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+dependencies = [
+ "winapi 0.3.8 (registry+https://github.com/rust-lang/crates.io-index)",
+]
+
+[[package]]
 name = "winapi-x86_64-pc-windows-gnu"
 version = "0.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
@@ -631,6 +648,7 b' source = "registry+https://github.com/ru'
 "checksum regex-syntax 0.6.14 (registry+https://github.com/rust-lang/crates.io-index)" = "b28dfe3fe9badec5dbf0a79a9cccad2cfc2ab5484bdb3e44cbd1ae8b3ba2be06"
 "checksum remove_dir_all 0.5.2 (registry+https://github.com/rust-lang/crates.io-index)" = "4a83fa3702a688b9359eccba92d153ac33fd2e8462f9e0e3fdf155239ea7792e"
 "checksum rustc_version 0.2.3 (registry+https://github.com/rust-lang/crates.io-index)" = "138e3e0acb6c9fb258b19b67cb8abd63c00679d2851805ea151465464fe9030a"
+"checksum same-file 1.0.6 (registry+https://github.com/rust-lang/crates.io-index)" = "93fc1dc3aaa9bfed95e02e6eadabb4baf7e3078b0bd1b4d7b6b0b68378900502"
 "checksum scopeguard 1.0.0 (registry+https://github.com/rust-lang/crates.io-index)" = "b42e15e59b18a828bbf5c58ea01debb36b9b096346de35d941dcb89009f24a0d"
 "checksum semver 0.9.0 (registry+https://github.com/rust-lang/crates.io-index)" = "1d7eb9ef2c18661902cc47e535f9bc51b78acd254da71d375c2f6720d9a40403"
 "checksum semver-parser 0.7.0 (registry+https://github.com/rust-lang/crates.io-index)" = "388a1df253eca08550bef6c72392cfe7c30914bf41df5269b68cbd6ff8f570a3"
@@ -642,4 +660,5 b' source = "registry+https://github.com/ru'
 "checksum wasi 0.9.0+wasi-snapshot-preview1 (registry+https://github.com/rust-lang/crates.io-index)" = "cccddf32554fecc6acb585f82a32a72e28b48f8c4c1883ddfeeeaa96f7d8e519"
 "checksum winapi 0.3.8 (registry+https://github.com/rust-lang/crates.io-index)" = "8093091eeb260906a183e6ae1abdba2ef5ef2257a21801128899c3fc699229c6"
 "checksum winapi-i686-pc-windows-gnu 0.4.0 (registry+https://github.com/rust-lang/crates.io-index)" = "ac3b87c63620426dd9b991e5ce0329eff545bccbbb34f3be09ff6fb6ab51b7b6"
+"checksum winapi-util 0.1.3 (registry+https://github.com/rust-lang/crates.io-index)" = "4ccfbf554c6ad11084fb7517daca16cfdcaccbdadba4fc336f032a8b12c2ad80"
 "checksum winapi-x86_64-pc-windows-gnu 0.4.0 (registry+https://github.com/rust-lang/crates.io-index)" = "712e227841d057c1ee1cd2fb22fa7e5a5461ae8e48fa2ca79ec42cfc1931183f"

rust/hg-core/Cargo.toml

@@ -18,6 +18,7 b' rand_pcg = "0.1.1"'
 rayon = "1.3.0"
 regex = "1.1.0"
 twox-hash = "1.5.0"
+same-file = "1.0.6"
 
 [dev-dependencies]
 tempfile = "3.1.0"

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

@@ -9,13 +9,18 b''
 
 //! Functions for fiddling with files.
 
-use crate::utils::hg_path::{HgPath, HgPathBuf};
-
-use crate::utils::replace_slice;
+use crate::utils::{
+    hg_path::{path_to_hg_path_buf, HgPath, HgPathBuf, HgPathError},
+    path_auditor::PathAuditor,
+    replace_slice,
+};
 use lazy_static::lazy_static;
+use same_file::is_same_file;
+use std::borrow::ToOwned;
 use std::fs::Metadata;
 use std::iter::FusedIterator;
-use std::path::Path;
+use std::ops::Deref;
+use std::path::{Path, PathBuf};
 
 pub fn get_path_from_bytes(bytes: &[u8]) -> &Path {
     let os_str;
@@ -189,9 +194,66 b' impl HgMetadata {'
     }
 }
 
+/// Returns the canonical path of `name`, given `cwd` and `root`
+pub fn canonical_path(
+    root: impl AsRef<Path>,
+    cwd: impl AsRef<Path>,
+    name: impl AsRef<Path>,
+) -> Result<PathBuf, HgPathError> {
+    // TODO add missing normalization for other platforms
+    let root = root.as_ref();
+    let cwd = cwd.as_ref();
+    let name = name.as_ref();
+
+    let name = if !name.is_absolute() {
+        root.join(&cwd).join(&name)
+    } else {
+        name.to_owned()
+    };
+    let mut auditor = PathAuditor::new(&root);
+    if name != root && name.starts_with(&root) {
+        let name = name.strip_prefix(&root).unwrap();
+        auditor.audit_path(path_to_hg_path_buf(name)?)?;
+        return Ok(name.to_owned());
+    } else if name == root {
+        return Ok("".into());
+    } else {
+        // Determine whether `name' is in the hierarchy at or beneath `root',
+        // by iterating name=name.parent() until it returns `None` (can't
+        // check name == '/', because that doesn't work on windows).
+        let mut name = name.deref();
+        let original_name = name.to_owned();
+        loop {
+            let same = is_same_file(&name, &root).unwrap_or(false);
+            if same {
+                if name == original_name {
+                    // `name` was actually the same as root (maybe a symlink)
+                    return Ok("".into());
+                }
+                // `name` is a symlink to root, so `original_name` is under
+                // root
+                let rel_path = original_name.strip_prefix(&name).unwrap();
+                auditor.audit_path(path_to_hg_path_buf(&rel_path)?)?;
+                return Ok(rel_path.to_owned());
+            }
+            name = match name.parent() {
+                None => break,
+                Some(p) => p,
+            };
+        }
+        // TODO hint to the user about using --cwd
+        // Bubble up the responsibility to Python for now
+        Err(HgPathError::NotUnderRoot {
+            path: original_name.to_owned(),
+            root: root.to_owned(),
+        })
+    }
+}
+
 #[cfg(test)]
 mod tests {
     use super::*;
+    use pretty_assertions::assert_eq;
 
     #[test]
     fn find_dirs_some() {
@@ -235,4 +297,88 b' mod tests {'
         assert_eq!(dirs.next(), None);
         assert_eq!(dirs.next(), None);
     }
+
+    #[test]
+    fn test_canonical_path() {
+        let root = Path::new("/repo");
+        let cwd = Path::new("/dir");
+        let name = Path::new("filename");
+        assert_eq!(
+            canonical_path(root, cwd, name),
+            Err(HgPathError::NotUnderRoot {
+                path: PathBuf::from("/dir/filename"),
+                root: root.to_path_buf()
+            })
+        );
+
+        let root = Path::new("/repo");
+        let cwd = Path::new("/");
+        let name = Path::new("filename");
+        assert_eq!(
+            canonical_path(root, cwd, name),
+            Err(HgPathError::NotUnderRoot {
+                path: PathBuf::from("/filename"),
+                root: root.to_path_buf()
+            })
+        );
+
+        let root = Path::new("/repo");
+        let cwd = Path::new("/");
+        let name = Path::new("repo/filename");
+        assert_eq!(
+            canonical_path(root, cwd, name),
+            Ok(PathBuf::from("filename"))
+        );
+
+        let root = Path::new("/repo");
+        let cwd = Path::new("/repo");
+        let name = Path::new("filename");
+        assert_eq!(
+            canonical_path(root, cwd, name),
+            Ok(PathBuf::from("filename"))
+        );
+
+        let root = Path::new("/repo");
+        let cwd = Path::new("/repo/subdir");
+        let name = Path::new("filename");
+        assert_eq!(
+            canonical_path(root, cwd, name),
+            Ok(PathBuf::from("subdir/filename"))
+        );
+    }
+
+    #[test]
+    fn test_canonical_path_not_rooted() {
+        use std::fs::create_dir;
+        use tempfile::tempdir;
+
+        let base_dir = tempdir().unwrap();
+        let base_dir_path = base_dir.path();
+        let beneath_repo = base_dir_path.join("a");
+        let root = base_dir_path.join("a/b");
+        let out_of_repo = base_dir_path.join("c");
+        let under_repo_symlink = out_of_repo.join("d");
+
+        create_dir(&beneath_repo).unwrap();
+        create_dir(&root).unwrap();
+
+        // TODO make portable
+        std::os::unix::fs::symlink(&root, &out_of_repo).unwrap();
+
+        assert_eq!(
+            canonical_path(&root, Path::new(""), out_of_repo),
+            Ok(PathBuf::from(""))
+        );
+        assert_eq!(
+            canonical_path(&root, Path::new(""), &beneath_repo),
+            Err(HgPathError::NotUnderRoot {
+                path: beneath_repo.to_owned(),
+                root: root.to_owned()
+            })
+        );
+        assert_eq!(
+            canonical_path(&root, Path::new(""), &under_repo_symlink),
+            Ok(PathBuf::from("d"))
+        );
+    }
 }