refactor(tvix/castore): use Directory struct separate from proto one r/8484

This uses our own data type to deal with Directories in the castore model.

It makes some undesired states unrepresentable, removing the need for conversions and checking in various places:

 - In the protobuf, blake3 digests could have a wrong length, as proto doesn't know fixed-size fields. We now use `B3Digest`, which makes cloning cheaper, and removes the need to do size-checking everywhere.
 - In the protobuf, we had three different lists for `files`, `symlinks` and `directories`. This was mostly a protobuf size optimization, but made interacting with them a bit awkward. This has now been replaced with a list of enums, and convenience iterators to get various nodes, and add new ones.

Change-Id: I7b92691bb06d77ff3f58a5ccea94a22c16f84f04
Reviewed-on: https://cl.tvl.fyi/c/depot/+/12057
Tested-by: BuildkiteCI
Reviewed-by: flokli <flokli@flokli.de>

3 files changed, 13 insertions, 189 deletions

diff --git a/tvix/castore/src/proto/tests/directory.rs b/tvix/castore/src/proto/tests/directory.rs
index 81b73a048d52..78b2cf7668e3 100644
--- a/tvix/castore/src/proto/tests/directory.rs
+++ b/tvix/castore/src/proto/tests/directory.rs
@@ -1,7 +1,5 @@
-use crate::proto::{
-    node, Directory, DirectoryNode, FileNode, SymlinkNode, ValidateDirectoryError,
-    ValidateNodeError,
-};
+use crate::proto::{Directory, DirectoryNode, FileNode, SymlinkNode, ValidateDirectoryError};
+use crate::ValidateNodeError;
 
 use hex_literal::hex;
 
@@ -149,7 +147,7 @@ fn digest() {
 #[test]
 fn validate_empty() {
     let d = Directory::default();
-    assert_eq!(d.validate(), Ok(()));
+    assert!(crate::directoryservice::Directory::try_from(d).is_ok());
 }
 
 #[test]
@@ -163,7 +161,7 @@ fn validate_invalid_names() {
             }],
             ..Default::default()
         };
-        match d.validate().expect_err("must fail") {
+        match crate::directoryservice::Directory::try_from(d).expect_err("must fail") {
             ValidateDirectoryError::InvalidNode(n, ValidateNodeError::InvalidName(_)) => {
                 assert_eq!(n, b"")
             }
@@ -180,7 +178,7 @@ fn validate_invalid_names() {
             }],
             ..Default::default()
         };
-        match d.validate().expect_err("must fail") {
+        match crate::directoryservice::Directory::try_from(d).expect_err("must fail") {
             ValidateDirectoryError::InvalidNode(n, ValidateNodeError::InvalidName(_)) => {
                 assert_eq!(n, b".")
             }
@@ -198,7 +196,7 @@ fn validate_invalid_names() {
             }],
             ..Default::default()
         };
-        match d.validate().expect_err("must fail") {
+        match crate::directoryservice::Directory::try_from(d).expect_err("must fail") {
             ValidateDirectoryError::InvalidNode(n, ValidateNodeError::InvalidName(_)) => {
                 assert_eq!(n, b"..")
             }
@@ -214,7 +212,7 @@ fn validate_invalid_names() {
             }],
             ..Default::default()
         };
-        match d.validate().expect_err("must fail") {
+        match crate::directoryservice::Directory::try_from(d).expect_err("must fail") {
             ValidateDirectoryError::InvalidNode(n, ValidateNodeError::InvalidName(_)) => {
                 assert_eq!(n, b"\x00")
             }
@@ -230,7 +228,7 @@ fn validate_invalid_names() {
             }],
             ..Default::default()
         };
-        match d.validate().expect_err("must fail") {
+        match crate::directoryservice::Directory::try_from(d).expect_err("must fail") {
             ValidateDirectoryError::InvalidNode(n, ValidateNodeError::InvalidName(_)) => {
                 assert_eq!(n, b"foo/bar")
             }
@@ -249,7 +247,7 @@ fn validate_invalid_digest() {
         }],
         ..Default::default()
     };
-    match d.validate().expect_err("must fail") {
+    match crate::directoryservice::Directory::try_from(d).expect_err("must fail") {
         ValidateDirectoryError::InvalidNode(_, ValidateNodeError::InvalidDigestLen(n)) => {
             assert_eq!(n, 2)
         }
@@ -276,7 +274,7 @@ fn validate_sorting() {
             ],
             ..Default::default()
         };
-        match d.validate().expect_err("must fail") {
+        match crate::directoryservice::Directory::try_from(d).expect_err("must fail") {
             ValidateDirectoryError::WrongSorting(s) => {
                 assert_eq!(s, b"a");
             }
@@ -301,7 +299,7 @@ fn validate_sorting() {
             ],
             ..Default::default()
         };
-        match d.validate().expect_err("must fail") {
+        match crate::directoryservice::Directory::try_from(d).expect_err("must fail") {
             ValidateDirectoryError::DuplicateName(s) => {
                 assert_eq!(s, b"a");
             }
@@ -327,7 +325,7 @@ fn validate_sorting() {
             ..Default::default()
         };
 
-        d.validate().expect("validate shouldn't error");
+        crate::directoryservice::Directory::try_from(d).expect("validate shouldn't error");
     }
 
     // [b, c] and [a] are both properly sorted.
@@ -352,101 +350,6 @@ fn validate_sorting() {
             ..Default::default()
         };
 
-        d.validate().expect("validate shouldn't error");
+        crate::directoryservice::Directory::try_from(d).expect("validate shouldn't error");
     }
 }
-
-#[test]
-fn validate_overflow() {
-    let d = Directory {
-        directories: vec![DirectoryNode {
-            name: "foo".into(),
-            digest: DUMMY_DIGEST.to_vec().into(),
-            size: u64::MAX,
-        }],
-        ..Default::default()
-    };
-
-    match d.validate().expect_err("must fail") {
-        ValidateDirectoryError::SizeOverflow => {}
-        _ => panic!("unexpected error"),
-    }
-}
-
-#[test]
-fn add_nodes_to_directory() {
-    let mut d = Directory {
-        ..Default::default()
-    };
-
-    d.add(node::Node::Directory(DirectoryNode {
-        name: "b".into(),
-        digest: DUMMY_DIGEST.to_vec().into(),
-        size: 1,
-    }));
-    d.add(node::Node::Directory(DirectoryNode {
-        name: "a".into(),
-        digest: DUMMY_DIGEST.to_vec().into(),
-        size: 1,
-    }));
-    d.add(node::Node::Directory(DirectoryNode {
-        name: "z".into(),
-        digest: DUMMY_DIGEST.to_vec().into(),
-        size: 1,
-    }));
-
-    d.add(node::Node::File(FileNode {
-        name: "f".into(),
-        digest: DUMMY_DIGEST.to_vec().into(),
-        size: 1,
-        executable: true,
-    }));
-    d.add(node::Node::File(FileNode {
-        name: "c".into(),
-        digest: DUMMY_DIGEST.to_vec().into(),
-        size: 1,
-        executable: true,
-    }));
-    d.add(node::Node::File(FileNode {
-        name: "g".into(),
-        digest: DUMMY_DIGEST.to_vec().into(),
-        size: 1,
-        executable: true,
-    }));
-
-    d.add(node::Node::Symlink(SymlinkNode {
-        name: "t".into(),
-        target: "a".into(),
-    }));
-    d.add(node::Node::Symlink(SymlinkNode {
-        name: "o".into(),
-        target: "a".into(),
-    }));
-    d.add(node::Node::Symlink(SymlinkNode {
-        name: "e".into(),
-        target: "a".into(),
-    }));
-
-    d.validate().expect("directory should be valid");
-}
-
-#[test]
-#[cfg_attr(not(debug_assertions), ignore)]
-#[should_panic = "name already exists in directories"]
-fn add_duplicate_node_to_directory_panics() {
-    let mut d = Directory {
-        ..Default::default()
-    };
-
-    d.add(node::Node::Directory(DirectoryNode {
-        name: "a".into(),
-        digest: DUMMY_DIGEST.to_vec().into(),
-        size: 1,
-    }));
-    d.add(node::Node::File(FileNode {
-        name: "a".into(),
-        digest: DUMMY_DIGEST.to_vec().into(),
-        size: 1,
-        executable: true,
-    }));
-}
diff --git a/tvix/castore/src/proto/tests/directory_nodes_iterator.rs b/tvix/castore/src/proto/tests/directory_nodes_iterator.rs
deleted file mode 100644
index 68f147a33210..000000000000
--- a/tvix/castore/src/proto/tests/directory_nodes_iterator.rs
+++ /dev/null
@@ -1,78 +0,0 @@
-use crate::proto::Directory;
-use crate::proto::DirectoryNode;
-use crate::proto::FileNode;
-use crate::proto::NamedNode;
-use crate::proto::SymlinkNode;
-
-#[test]
-fn iterator() {
-    let d = Directory {
-        directories: vec![
-            DirectoryNode {
-                name: "c".into(),
-                ..DirectoryNode::default()
-            },
-            DirectoryNode {
-                name: "d".into(),
-                ..DirectoryNode::default()
-            },
-            DirectoryNode {
-                name: "h".into(),
-                ..DirectoryNode::default()
-            },
-            DirectoryNode {
-                name: "l".into(),
-                ..DirectoryNode::default()
-            },
-        ],
-        files: vec![
-            FileNode {
-                name: "b".into(),
-                ..FileNode::default()
-            },
-            FileNode {
-                name: "e".into(),
-                ..FileNode::default()
-            },
-            FileNode {
-                name: "g".into(),
-                ..FileNode::default()
-            },
-            FileNode {
-                name: "j".into(),
-                ..FileNode::default()
-            },
-        ],
-        symlinks: vec![
-            SymlinkNode {
-                name: "a".into(),
-                ..SymlinkNode::default()
-            },
-            SymlinkNode {
-                name: "f".into(),
-                ..SymlinkNode::default()
-            },
-            SymlinkNode {
-                name: "i".into(),
-                ..SymlinkNode::default()
-            },
-            SymlinkNode {
-                name: "k".into(),
-                ..SymlinkNode::default()
-            },
-        ],
-    };
-
-    // We keep this strings here and convert to string to make the comparison
-    // less messy.
-    let mut node_names: Vec<String> = vec![];
-
-    for node in d.nodes() {
-        node_names.push(String::from_utf8(node.get_name().to_vec()).unwrap());
-    }
-
-    assert_eq!(
-        vec!["a", "b", "c", "d", "e", "f", "g", "h", "i", "j", "k", "l"],
-        node_names
-    );
-}
diff --git a/tvix/castore/src/proto/tests/mod.rs b/tvix/castore/src/proto/tests/mod.rs
index 8d903bacb6c5..74334029e84c 100644
--- a/tvix/castore/src/proto/tests/mod.rs
+++ b/tvix/castore/src/proto/tests/mod.rs
@@ -1,2 +1 @@
 mod directory;
-mod directory_nodes_iterator;