fix(package): check dirtiness of symlink source files

This adds a special case for checking source files are symlinks
and have been modified when under a VCS control

This is required because those paths may link to a file outside the
current package root, but still under the git workdir, affecting the
final packaged `.crate` file.

This may have potential performance issue. If a package contains
thousands of symlinks, Cargo will fire `git status` for each of them.

Author: weihanglo

src/cargo/ops/cargo_package/vcs.rs

@@ -1,5 +1,6 @@
 //! Helpers to gather the VCS information for `cargo package`.
 
+use std::collections::HashSet;
 use std::path::Path;
 use std::path::PathBuf;
 
@@ -187,6 +188,7 @@ fn git(
         .filter(|src_file| dirty_files.iter().any(|path| src_file.starts_with(path)))
         .map(|p| p.as_ref())
         .chain(dirty_metadata_paths(pkg, repo)?.iter())
+        .chain(dirty_symlinks(pkg, repo, src_files)?.iter())
         .map(|path| {
             pathdiff::diff_paths(path, cwd)
                 .as_ref()
@@ -249,6 +251,34 @@ fn dirty_metadata_paths(pkg: &Package, repo: &git2::Repository) -> CargoResult<V
     Ok(dirty_files)
 }
 
+/// Checks whether source files are symlinks and have been modified.
+///
+/// This is required because those paths may link to a file outside the
+/// current package root, but still under the git workdir, affecting the
+/// final packaged `.crate` file.
+fn dirty_symlinks(
+    pkg: &Package,
+    repo: &git2::Repository,
+    src_files: &[PathEntry],
+) -> CargoResult<HashSet<PathBuf>> {
+    let workdir = repo.workdir().unwrap();
+    let mut dirty_symlinks = HashSet::new();
+    for rel_path in src_files
+        .iter()
+        .filter(|p| p.is_symlink_or_under_symlink())
+        .map(|p| p.as_ref().as_path())
+        // If inside package root. Don't bother checking git status.
+        .filter(|p| paths::strip_prefix_canonical(p, pkg.root()).is_err())
+        // Handle files outside package root but under git workdir,
+        .filter_map(|p| paths::strip_prefix_canonical(p, workdir).ok())
+    {
+        if repo.status_file(&rel_path)? != git2::Status::CURRENT {
+            dirty_symlinks.insert(workdir.join(rel_path));
+        }
+    }
+    Ok(dirty_symlinks)
+}
+
 /// Helper to collect dirty statuses for a single repo.
 fn collect_statuses(repo: &git2::Repository, dirty_files: &mut Vec<PathBuf>) -> CargoResult<()> {
     let mut status_opts = git2::StatusOptions::new();

tests/testsuite/package.rs

@@ -1378,10 +1378,13 @@ fn dirty_file_outside_pkg_root_considered_dirty() {
     p.cargo("package --workspace --no-verify")
         .with_status(101)
         .with_stderr_data(str![[r#"
-[ERROR] 2 files in the working directory contain changes that were not yet committed into git:
+[ERROR] 5 files in the working directory contain changes that were not yet committed into git:
 
 LICENSE
 README.md
+README.md
+lib.rs
+original-dir/file
 
 to proceed despite this and include the uncommitted changes, pass the `--allow-dirty` flag