geth/crates/geth-cas/src/lib.rs

use geth_types::BlobHash;
use serde::{Deserialize, Serialize};
use std::collections::{BTreeMap, BTreeSet};
use std::path::{Path, PathBuf};

pub const CAS_TREE_OBJECT_VERSION: u16 = 1;

#[derive(Debug, thiserror::Error)]
pub enum CasError {
    #[error("io error: {0}")]
    Io(#[from] std::io::Error),
    #[error("canonical codec error: {0}")]
    Codec(#[from] geth_codec::CodecError),
    #[error("invalid blob hash: {0}")]
    InvalidHash(String),
    #[error("blob not found: {0}")]
    NotFound(String),
    #[error("CAS tree root is not a directory: {0}")]
    TreeRootNotDirectory(String),
    #[error("CAS tree paths must be relative: {0}")]
    NonRelativeTreePath(String),
    #[error("invalid file root name: {0}")]
    InvalidFileRootName(String),
}

#[derive(Clone, Debug)]
pub struct LocalCas {
    root: PathBuf,
}

#[derive(Clone, Debug, PartialEq, Eq)]
pub struct BlobInfo {
    pub hash: BlobHash,
    pub size_bytes: u64,
    pub path: PathBuf,
}

#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize)]
pub struct CasTreeObject {
    pub version: u16,
    pub entries: Vec<CasTreeEntry>,
}

#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize)]
pub struct CasTreeEntry {
    pub path: String,
    pub kind: CasTreeEntryKind,
    pub blob: Option<BlobHash>,
    pub size_bytes: u64,
    pub executable: bool,
}

#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize)]
#[serde(rename_all = "kebab-case")]
pub enum CasTreeEntryKind {
    Directory,
    File,
}

#[derive(Clone, Debug, PartialEq, Eq)]
pub struct CasTreeStored {
    pub tree: CasTreeObject,
    pub object: BlobInfo,
}

#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize)]
pub struct FileRoot {
    pub id: String,
    pub resource: String,
    pub name: String,
    pub path: String,
    pub latest_tree: Option<BlobHash>,
    pub updated_at_ms: i64,
}

#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize)]
pub struct FileRootScan {
    pub root: FileRoot,
    pub tree: BlobInfoSummary,
    pub changes: Vec<FileRootChange>,
    pub note: String,
}

#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize)]
pub struct BlobInfoSummary {
    pub hash: BlobHash,
    pub size_bytes: u64,
}

#[derive(Clone, Debug, PartialEq, Eq, Serialize, Deserialize)]
#[serde(tag = "kind", rename_all = "kebab-case")]
pub enum FileRootChange {
    Created { path: String },
    Modified { path: String },
    Deleted { path: String },
    Renamed { from: String, to: String },
}

impl LocalCas {
    #[must_use]
    pub fn new(root: impl Into<PathBuf>) -> Self {
        Self { root: root.into() }
    }

    pub fn add_path(&self, path: &Path) -> Result<BlobInfo, CasError> {
        let bytes = std::fs::read(path)?;
        self.add_bytes(&bytes)
    }

    pub fn add_bytes(&self, bytes: &[u8]) -> Result<BlobInfo, CasError> {
        let hash = hash_bytes(bytes);
        let path = self.blob_path(&hash)?;
        if let Some(parent) = path.parent() {
            std::fs::create_dir_all(parent)?;
        }
        if !path.exists() {
            let tmp = path.with_extension("tmp");
            std::fs::write(&tmp, bytes)?;
            std::fs::rename(tmp, &path)?;
        }
        Ok(BlobInfo {
            hash,
            size_bytes: bytes.len() as u64,
            path,
        })
    }

    pub fn get_to_path(&self, hash: &BlobHash, out: &Path) -> Result<u64, CasError> {
        let path = self.blob_path(hash)?;
        if !path.exists() {
            return Err(CasError::NotFound(hash.to_string()));
        }
        if let Some(parent) = out.parent() {
            std::fs::create_dir_all(parent)?;
        }
        std::fs::copy(path, out).map_err(CasError::from)
    }

    pub fn has(&self, hash: &BlobHash) -> Result<bool, CasError> {
        Ok(self.blob_path(hash)?.exists())
    }

    pub fn remove(&self, hash: &BlobHash) -> Result<bool, CasError> {
        let path = self.blob_path(hash)?;
        if !path.exists() {
            return Ok(false);
        }
        std::fs::remove_file(path)?;
        Ok(true)
    }

    pub fn list(&self) -> Result<Vec<BlobInfo>, CasError> {
        let blobs = self.root.join("blobs");
        if !blobs.exists() {
            return Ok(Vec::new());
        }
        let mut infos = Vec::new();
        for first in std::fs::read_dir(blobs)? {
            let first = first?;
            if !first.file_type()?.is_dir() {
                continue;
            }
            for second in std::fs::read_dir(first.path())? {
                let second = second?;
                if !second.file_type()?.is_dir() {
                    continue;
                }
                for entry in std::fs::read_dir(second.path())? {
                    let entry = entry?;
                    if !entry.file_type()?.is_file() {
                        continue;
                    }
                    let hash = entry.file_name().to_string_lossy().to_string();
                    if is_valid_hash(&hash) {
                        let meta = entry.metadata()?;
                        infos.push(BlobInfo {
                            hash: BlobHash::new(hash),
                            size_bytes: meta.len(),
                            path: entry.path(),
                        });
                    }
                }
            }
        }
        infos.sort_by(|a, b| a.hash.as_str().cmp(b.hash.as_str()));
        Ok(infos)
    }

    pub fn blob_path(&self, hash: &BlobHash) -> Result<PathBuf, CasError> {
        validate_hash(hash)?;
        let hash = hash.as_str();
        Ok(self
            .root
            .join("blobs")
            .join(&hash[0..2])
            .join(&hash[2..4])
            .join(hash))
    }

    pub fn add_tree_path(&self, root: &Path) -> Result<CasTreeStored, CasError> {
        let tree = build_tree_object(self, root)?;
        let bytes = geth_codec::encode_canonical(&tree)?;
        let object = self.add_bytes(&bytes)?;
        Ok(CasTreeStored { tree, object })
    }
}

pub fn build_tree_object(cas: &LocalCas, root: &Path) -> Result<CasTreeObject, CasError> {
    if !root.is_dir() {
        return Err(CasError::TreeRootNotDirectory(root.display().to_string()));
    }

    let mut entries = Vec::new();
    collect_tree_entries(cas, root, root, &mut entries)?;
    entries.sort_by(|left, right| {
        left.path
            .cmp(&right.path)
            .then_with(|| kind_order(&left.kind).cmp(&kind_order(&right.kind)))
    });

    Ok(CasTreeObject {
        version: CAS_TREE_OBJECT_VERSION,
        entries,
    })
}

pub fn diff_tree_objects(
    previous: Option<&CasTreeObject>,
    current: &CasTreeObject,
) -> Vec<FileRootChange> {
    let Some(previous) = previous else {
        return current
            .entries
            .iter()
            .map(|entry| FileRootChange::Created {
                path: entry.path.clone(),
            })
            .collect();
    };

    let previous_entries = tree_entry_map(previous);
    let current_entries = tree_entry_map(current);
    let previous_paths = previous_entries.keys().cloned().collect::<BTreeSet<_>>();
    let current_paths = current_entries.keys().cloned().collect::<BTreeSet<_>>();
    let deleted = previous_paths
        .difference(&current_paths)
        .cloned()
        .collect::<Vec<_>>();
    let created = current_paths
        .difference(&previous_paths)
        .cloned()
        .collect::<Vec<_>>();

    let mut changes = Vec::new();
    let mut consumed_deleted = BTreeSet::new();
    let mut consumed_created = BTreeSet::new();
    for deleted_path in &deleted {
        let Some(deleted_entry) = previous_entries.get(deleted_path) else {
            continue;
        };
        let Some(deleted_blob) = &deleted_entry.blob else {
            continue;
        };
        if let Some(created_path) = created.iter().find(|created_path| {
            !consumed_created.contains(*created_path)
                && current_entries
                    .get(*created_path)
                    .and_then(|entry| entry.blob.as_ref())
                    == Some(deleted_blob)
        }) {
            changes.push(FileRootChange::Renamed {
                from: deleted_path.clone(),
                to: created_path.clone(),
            });
            consumed_deleted.insert(deleted_path.clone());
            consumed_created.insert(created_path.clone());
        }
    }

    for path in deleted {
        if !consumed_deleted.contains(&path) {
            changes.push(FileRootChange::Deleted { path });
        }
    }
    for path in created {
        if !consumed_created.contains(&path) {
            changes.push(FileRootChange::Created { path });
        }
    }

    for path in previous_paths.intersection(&current_paths) {
        let previous = previous_entries.get(path).expect("previous entry");
        let current = current_entries.get(path).expect("current entry");
        if previous.kind != current.kind
            || previous.blob != current.blob
            || previous.executable != current.executable
            || previous.size_bytes != current.size_bytes
        {
            changes.push(FileRootChange::Modified { path: path.clone() });
        }
    }

    changes.sort_by_key(change_sort_key);
    changes
}

#[must_use]
pub fn file_root_scan_note() -> &'static str {
    "local scan only; geth never overwrites file roots without a recorded future sync decision"
}

fn tree_entry_map(tree: &CasTreeObject) -> BTreeMap<String, &CasTreeEntry> {
    tree.entries
        .iter()
        .map(|entry| (entry.path.clone(), entry))
        .collect()
}

fn change_sort_key(change: &FileRootChange) -> (u8, String, String) {
    match change {
        FileRootChange::Created { path } => (0, path.clone(), String::new()),
        FileRootChange::Modified { path } => (1, path.clone(), String::new()),
        FileRootChange::Deleted { path } => (2, path.clone(), String::new()),
        FileRootChange::Renamed { from, to } => (3, from.clone(), to.clone()),
    }
}

fn collect_tree_entries(
    cas: &LocalCas,
    root: &Path,
    current: &Path,
    entries: &mut Vec<CasTreeEntry>,
) -> Result<(), CasError> {
    let mut children = std::fs::read_dir(current)?.collect::<Result<Vec<_>, _>>()?;
    children.sort_by_key(|entry| entry.file_name());

    for child in children {
        let path = child.path();
        let metadata = child.metadata()?;
        let relative = relative_tree_path(root, &path)?;
        if metadata.is_dir() {
            entries.push(CasTreeEntry {
                path: relative,
                kind: CasTreeEntryKind::Directory,
                blob: None,
                size_bytes: 0,
                executable: false,
            });
            collect_tree_entries(cas, root, &path, entries)?;
        } else if metadata.is_file() {
            let blob = cas.add_path(&path)?;
            entries.push(CasTreeEntry {
                path: relative,
                kind: CasTreeEntryKind::File,
                blob: Some(blob.hash),
                size_bytes: metadata.len(),
                executable: is_executable(&metadata),
            });
        }
    }

    Ok(())
}

fn relative_tree_path(root: &Path, path: &Path) -> Result<String, CasError> {
    let relative = path
        .strip_prefix(root)
        .map_err(|_| CasError::NonRelativeTreePath(path.display().to_string()))?;
    Ok(relative
        .components()
        .map(|component| component.as_os_str().to_string_lossy())
        .collect::<Vec<_>>()
        .join("/"))
}

fn kind_order(kind: &CasTreeEntryKind) -> u8 {
    match kind {
        CasTreeEntryKind::Directory => 0,
        CasTreeEntryKind::File => 1,
    }
}

#[cfg(unix)]
fn is_executable(metadata: &std::fs::Metadata) -> bool {
    use std::os::unix::fs::PermissionsExt;
    metadata.permissions().mode() & 0o111 != 0
}

#[cfg(not(unix))]
fn is_executable(_metadata: &std::fs::Metadata) -> bool {
    false
}

#[must_use]
pub fn hash_bytes(bytes: &[u8]) -> BlobHash {
    BlobHash::new(blake3::hash(bytes).to_hex().to_string())
}

pub fn hash_path(path: &Path) -> Result<BlobHash, CasError> {
    let bytes = std::fs::read(path)?;
    Ok(hash_bytes(&bytes))
}

pub fn validate_hash(hash: &BlobHash) -> Result<(), CasError> {
    if is_valid_hash(hash.as_str()) {
        Ok(())
    } else {
        Err(CasError::InvalidHash(hash.to_string()))
    }
}

#[must_use]
pub fn is_valid_hash(hash: &str) -> bool {
    hash.len() == 64 && hash.bytes().all(|byte| byte.is_ascii_hexdigit())
}

pub fn validate_file_root_name(name: &str) -> Result<(), CasError> {
    if name.is_empty()
        || !name
            .bytes()
            .all(|byte| byte.is_ascii_alphanumeric() || matches!(byte, b'.' | b'_' | b'-'))
    {
        return Err(CasError::InvalidFileRootName(name.to_owned()));
    }
    Ok(())
}

#[cfg(test)]
mod tests {
    use super::*;

    #[test]
    fn cas_add_get_has_list() {
        let dir = tempfile::tempdir().expect("tempdir");
        let cas = LocalCas::new(dir.path());
        let info = cas.add_bytes(b"hello geth").expect("add");
        assert!(cas.has(&info.hash).expect("has"));
        assert_eq!(cas.list().expect("list").len(), 1);
        let out = dir.path().join("out.txt");
        cas.get_to_path(&info.hash, &out).expect("get");
        assert_eq!(std::fs::read(out).expect("read"), b"hello geth");
    }

    #[test]
    fn cas_remove_deletes_blob_file() {
        let dir = tempfile::tempdir().expect("tempdir");
        let cas = LocalCas::new(dir.path());
        let info = cas.add_bytes(b"remove me").expect("add");

        assert!(cas.remove(&info.hash).expect("remove"));
        assert!(!cas.has(&info.hash).expect("has after remove"));
        assert!(!cas.remove(&info.hash).expect("remove missing"));
    }

    #[test]
    fn cas_tree_objects_are_deterministic_and_store_file_blobs() {
        let dir = tempfile::tempdir().expect("tempdir");
        let cas = LocalCas::new(dir.path().join("cas"));
        let root = dir.path().join("root");
        std::fs::create_dir_all(root.join("sub")).expect("create subdir");
        std::fs::write(root.join("b.txt"), b"bravo").expect("write b");
        std::fs::write(root.join("sub").join("a.txt"), b"alpha").expect("write a");

        let first = cas.add_tree_path(&root).expect("first tree");
        let second = cas.add_tree_path(&root).expect("second tree");

        assert_eq!(first.object.hash, second.object.hash);
        assert_eq!(first.tree, second.tree);
        assert_eq!(
            first
                .tree
                .entries
                .iter()
                .map(|entry| entry.path.as_str())
                .collect::<Vec<_>>(),
            vec!["b.txt", "sub", "sub/a.txt"]
        );
        assert!(
            first
                .tree
                .entries
                .iter()
                .find(|entry| entry.path == "b.txt")
                .and_then(|entry| entry.blob.clone())
                .is_some_and(|hash| cas.has(&hash).expect("has blob"))
        );
        assert!(cas.has(&first.object.hash).expect("has tree object"));
    }

    #[test]
    fn cas_tree_rejects_file_root() {
        let dir = tempfile::tempdir().expect("tempdir");
        let cas = LocalCas::new(dir.path().join("cas"));
        let file = dir.path().join("file.txt");
        std::fs::write(&file, b"not a directory").expect("write");

        assert!(matches!(
            cas.add_tree_path(&file),
            Err(CasError::TreeRootNotDirectory(_))
        ));
    }

    #[test]
    fn cas_tree_diff_detects_create_modify_delete_and_rename() {
        let previous = CasTreeObject {
            version: CAS_TREE_OBJECT_VERSION,
            entries: vec![
                tree_file("deleted.txt", "01", 1),
                tree_file("modified.txt", "02", 1),
                tree_file("old.txt", "03", 1),
            ],
        };
        let current = CasTreeObject {
            version: CAS_TREE_OBJECT_VERSION,
            entries: vec![
                tree_file("created.txt", "04", 1),
                tree_file("modified.txt", "05", 1),
                tree_file("new.txt", "03", 1),
            ],
        };

        let diff = diff_tree_objects(Some(&previous), &current);

        assert!(diff.contains(&FileRootChange::Created {
            path: "created.txt".to_owned()
        }));
        assert!(diff.contains(&FileRootChange::Modified {
            path: "modified.txt".to_owned()
        }));
        assert!(diff.contains(&FileRootChange::Deleted {
            path: "deleted.txt".to_owned()
        }));
        assert!(diff.contains(&FileRootChange::Renamed {
            from: "old.txt".to_owned(),
            to: "new.txt".to_owned(),
        }));
    }

    #[test]
    fn cas_tree_diff_does_not_reuse_rename_targets() {
        let previous = CasTreeObject {
            version: CAS_TREE_OBJECT_VERSION,
            entries: vec![tree_file("one.txt", "01", 1), tree_file("two.txt", "01", 1)],
        };
        let current = CasTreeObject {
            version: CAS_TREE_OBJECT_VERSION,
            entries: vec![tree_file("renamed.txt", "01", 1)],
        };

        let diff = diff_tree_objects(Some(&previous), &current);
        let rename_count = diff
            .iter()
            .filter(|change| matches!(change, FileRootChange::Renamed { .. }))
            .count();
        let delete_count = diff
            .iter()
            .filter(|change| matches!(change, FileRootChange::Deleted { .. }))
            .count();

        assert_eq!(rename_count, 1);
        assert_eq!(delete_count, 1);
    }

    fn tree_file(path: &str, byte: &str, size_bytes: u64) -> CasTreeEntry {
        CasTreeEntry {
            path: path.to_owned(),
            kind: CasTreeEntryKind::File,
            blob: Some(BlobHash::new(byte.repeat(32))),
            size_bytes,
            executable: false,
        }
    }
}