From fbab56c0d440d8c294d83505cd47037ad1bc6a67 Mon Sep 17 00:00:00 2001 From: Quanyi Ma Date: Sun, 12 Oct 2025 22:02:20 +0800 Subject: [PATCH 1/3] Add dependabot config and update issue templates Signed-off-by: Quanyi Ma --- .github/ISSUE_TEMPLATE/pre-task.md | 12 -------- .github/ISSUE_TEMPLATE/r2cn.md | 2 +- .github/dependabot.yml | 11 +++++++ Cargo.toml | 31 ++++++++++---------- src/errors.rs | 47 ++++++++++++++++++++++++++++++ src/lib.rs | 33 ++++++++++++++++++++- 6 files changed, 107 insertions(+), 29 deletions(-) delete mode 100644 .github/ISSUE_TEMPLATE/pre-task.md create mode 100644 .github/dependabot.yml diff --git a/.github/ISSUE_TEMPLATE/pre-task.md b/.github/ISSUE_TEMPLATE/pre-task.md deleted file mode 100644 index e3506130..00000000 --- a/.github/ISSUE_TEMPLATE/pre-task.md +++ /dev/null @@ -1,12 +0,0 @@ ---- -name: pre-task -about: r2cn 测试任务模板 -title: "[r2cn-测试任务] " -labels: git, internal, pre-task -assignees: '' - ---- - -[具体描述] XXX 具体功能描述 - -[实现方案] XXX 实现方案描述 \ No newline at end of file diff --git a/.github/ISSUE_TEMPLATE/r2cn.md b/.github/ISSUE_TEMPLATE/r2cn.md index 008d9b25..a614d68b 100644 --- a/.github/ISSUE_TEMPLATE/r2cn.md +++ b/.github/ISSUE_TEMPLATE/r2cn.md @@ -20,7 +20,7 @@ assignees: '' 2. 所有 __PR__ 提交必须通过 `GitHub Actions` 自动化测试，提交 __PR__ 后请关注 `GitHub Actions` 结果； 3. 代码注释均需要使用英文; -[__PR 提交地址__] 提交到 [git-internal](https://github.com/web3infra-foundation/git-internal) 仓库的 `main` 分支 `` 目录； +[__PR 提交地址__] 提交到 [git-internal](https://github.com/web3infra-foundation/git-internal) 仓库的 `main` 分支 `src` 目录； [__开发指导__] 1. 认领任务参考 [r2cn 开源实习计划 - 任务认领与确认](https://r2cn.dev/docs/student/assign); diff --git a/.github/dependabot.yml b/.github/dependabot.yml new file mode 100644 index 00000000..1c7a5ca5 --- /dev/null +++ b/.github/dependabot.yml @@ -0,0 +1,11 @@ +# To get started with Dependabot version updates, you'll need to specify which +# package ecosystems to update and where the package manifests are located. +# Please see the documentation for all configuration options: +# https://docs.github.com/code-security/dependabot/dependabot-version-updates/configuration-options-for-the-dependabot.yml-file + +version: 2 +updates: + - package-ecosystem: "cargo" # See documentation for possible values + directory: "/" # Location of package manifests + schedule: + interval: "daily" \ No newline at end of file diff --git a/Cargo.toml b/Cargo.toml index ad626cce..fe1a867a 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -7,38 +7,39 @@ license = "MIT" # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html [dependencies] -sea-orm = { version = "1.1.12", features = ["sqlx-sqlite"] } -flate2 = { version = "1.1.1", features = ["zlib"] } -serde = { version = "1.0.219", features = ["derive"] } bstr = "1.12.0" hex = "0.4.3" -thiserror = "2.0.12" +thiserror = "2.0.17" tracing = "0.1.41" +tracing-subscriber = "0.3.20" sha1 = "0.10.6" colored = "3.0.0" -chrono = { version = "0.4.41", features = ["serde"] } -tracing-subscriber = "0.3.19" -uuid = { version = "1.17.0", features = ["v4"] } threadpool = "1.8.1" num_cpus = "1.17.0" dashmap = "6.1.0" -tokio = { version = "1.45.1", features = ["fs"] } lru-mem = "0.3.0" -bincode = { version = "2.0.1", features = ["serde"] } byteorder = "1.5.0" futures-util = "0.3.31" bytes = "1.10.1" -axum = { version = "0.8.4", features = ["macros", "json"] } memchr = "2.7.4" encoding_rs = "0.8.35" -rayon = "1.10.0" -reqwest = "0.12.18" +rayon = "1.11.0" +reqwest = "0.12.23" ring = "0.17.14" -serde_json = "1.0.140" +serde_json = "1.0.145" ahash = "0.8.12" diffs = "0.5.1" -libc = "0.2.172" -zstd-sys = { version = "2.0.15+zstd.1.5.7", features = ["experimental"] } +libc = "0.2.177" +zstd-sys = { version = "2.0.16+zstd.1.5.7", features = ["experimental"] } +sea-orm = { version = "1.1.17", features = ["sqlx-sqlite"] } +flate2 = { version = "1.1.4", features = ["zlib"] } +serde = { version = "1.0.228", features = ["derive"] } +chrono = { version = "0.4.42", features = ["serde"] } +uuid = { version = "1.18.1", features = ["v4"] } +tokio = { version = "1.47.1", features = ["fs"] } +bincode = { version = "2.0.1", features = ["serde"] } +axum = { version = "0.8.6", features = ["macros", "json"] } + [dev-dependencies] tokio = { version = "1.45.1", features = ["full"] } diff --git a/src/errors.rs b/src/errors.rs index 2d0f7bc8..24c4ed91 100644 --- a/src/errors.rs +++ b/src/errors.rs @@ -1,97 +1,144 @@ +//! Error types for the Git-Internal crate. +//! +//! This module defines a unified error enumeration used across object parsing, +//! pack encoding/decoding, index handling, caching, and streaming. It integrates +//! with `thiserror` to provide rich `Display` implementations and error source +//! chaining where applicable. +//! +//! Notes: +//! - Each variant carries contextual details via its message payload. +//! - Variants cover parse/validation, I/O, encoding/decoding, network/auth, +//! and custom errors. + use thiserror::Error; #[derive(Error, Debug)] +/// Unified error enumeration for the Git-Internal library. +/// +/// - Used across object parsing, pack encode/decode, index, caching and streams. +/// - Implements `std::error::Error` via `thiserror`. pub enum GitError { + /// Invalid or unsupported git object type name. #[error("The `{0}` is not a valid git object type.")] InvalidObjectType(String), + /// Malformed or unsupported blob object encoding. #[error("The `{0}` is not a valid git blob object.")] InvalidBlobObject(String), + /// Malformed tree object. #[error("Not a valid git tree object.")] InvalidTreeObject, + /// Invalid tree entry (mode/name/hash). #[error("The `{0}` is not a valid git tree item.")] InvalidTreeItem(String), + /// Tree contains no entries. #[error("`{0}`.")] EmptyTreeItems(String), + /// Invalid commit signature type. #[error("The `{0}` is not a valid git commit signature.")] InvalidSignatureType(String), + /// Malformed commit object. #[error("Not a valid git commit object.")] InvalidCommitObject, + /// Commit parse or validation failed. #[error("Invalid Commit: {0}")] InvalidCommit(String), + /// Malformed tag object. #[error("Not a valid git tag object: {0}")] InvalidTagObject(String), + /// Malformed note object. #[error("Not a valid git note object: {0}")] InvalidNoteObject(String), + /// Malformed or unsupported index (.idx) file. #[error("The `{0}` is not a valid idx file.")] InvalidIdxFile(String), + /// Malformed or unsupported pack file. #[error("The `{0}` is not a valid pack file.")] InvalidPackFile(String), + /// Invalid pack header magic or version. #[error("The `{0}` is not a valid pack header.")] InvalidPackHeader(String), + /// Malformed or unsupported git index file. #[error("The `{0}` is not a valid index file.")] InvalidIndexFile(String), + /// Invalid git index header. #[error("The `{0}` is not a valid index header.")] InvalidIndexHeader(String), + /// Invalid CLI or function argument. #[error("Argument parse failed: {0}")] InvalidArgument(String), + /// I/O error from underlying reader or writer. #[error("IO Error: {0}")] IOError(#[from] std::io::Error), + /// Invalid SHA1 hash formatting or value. #[error("The {0} is not a valid Hash value ")] InvalidHashValue(String), + /// Delta object reconstruction error. #[error("Delta Object Error Info:{0}")] DeltaObjectError(String), + /// Object not fully populated for packing. #[error("The object to be packed is incomplete ,{0}")] UnCompletedPackObject(String), + /// Invalid decoded object info. #[error("Error decode in the Object ,info:{0}")] InvalidObjectInfo(String), + /// Hash not found in current file context. #[error("Can't found Hash value :{0} from current file")] NotFountHashValue(String), + /// Failed to encode object to bytes. #[error("Can't encode the object which id [{0}] to bytes")] EncodeObjectError(String), + /// Text encoding or UTF-8 conversion error. #[error("UTF-8 conversion error: {0}")] ConversionError(String), + /// Invalid path when locating parent tree. #[error("Can't find parent tree by path: {0}")] InvalidPathError(String), + /// Failed to encode pack entries. #[error("Can't encode entries to pack: {0}")] PackEncodeError(String), + /// Object missing from caches or storage. #[error("Can't find specific object: {0}")] ObjectNotFound(String), + /// Repository not found. #[error("Repository not found")] RepoNotFound, + /// Unauthorized access. #[error("UnAuthorized: {0}")] UnAuthorized(String), + /// Network communication error. #[error("Network Error: {0}")] NetworkError(String), + /// Generic custom error for miscellaneous failures. #[error("{0}")] CustomError(String), } diff --git a/src/lib.rs b/src/lib.rs index 8cd21eb4..a76bbaf9 100644 --- a/src/lib.rs +++ b/src/lib.rs @@ -1,4 +1,35 @@ -//! Git-Internal is a library for encoding and decoding Git Pack format files or streams. +//! Git-Internal: a high-performance Rust library for Git objects and pack files—encode/decode, delta (ref/offset/zstd), +//! caching, streaming, and sync/async pipelines. +//! +//! Goals +//! - Provide high-performance parsing and generation of Git pack format and Git objects. +//! - Support both file-based and streaming inputs of Git Pack. +//! - Offer synchronous and asynchronous APIs for multi-threaded and Tokio runtimes. +//! +//! Core Capabilities +//! - Decoding: base objects and delta objects (Ref-Delta, Offset-Delta, ZstdDelta). +//! - Encoding: serial and parallel pipelines; offset deltas and Zstd-based deltas. +//! - Streaming: `decode_stream` for `Stream`; `decode_async` decodes in a new thread and sends entries. +//! - Caching & memory: LRU-based cache; `MemSizeRecorder` tracks heap usage; optional `mem_limit` to bound memory. +//! - Utilities: SHA1, zlib, delta, zstdelta toolkits. +//! +//! Modules +//! - `internal::pack`: decode/encode, caches, waitlists, parallel pipelines, helpers. +//! - `internal::object`: Blob/Tree/Commit/Tag/Note objects, type enum, object trait. +//! - `internal::zlib`: compression/decompression stream utilities. +//! - `delta` and `zstdelta`: delta algorithms and rebuild helpers. +//! - `errors`: unified error types. +//! - `hash`: SHA1 helpers. +//! - `utils`: common utilities (e.g., `CountingReader`). +//! +//! Typical Usage +//! - Offline large-file decode: `Pack::decode_async(reader, sender)` decodes in a thread and sends `Entry`s. +//! - Stream decode: `Pack::decode_stream(stream, sender)` consumes `ReaderStream` under Tokio. +//! - Parallel encode: `encode_async` / `parallel_encode` build packs from many objects. +//! +//! Test Data +//! - Located under `tests/data/`, includes real pack files and object sets. + pub mod errors; pub mod hash; pub mod internal; From e3ebc74e0f9639a2c6bf356041dadec4dd2fe851 Mon Sep 17 00:00:00 2001 From: Quanyi Ma Date: Sun, 12 Oct 2025 22:08:24 +0800 Subject: [PATCH 2/3] Apply suggestion from @Copilot Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> --- Cargo.toml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Cargo.toml b/Cargo.toml index fe1a867a..c23cea5a 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -42,7 +42,7 @@ axum = { version = "0.8.6", features = ["macros", "json"] } [dev-dependencies] -tokio = { version = "1.45.1", features = ["full"] } +tokio = { version = "1.47.1", features = ["full"] } tokio-util = { version = "0.7.15", features = ["io"] } quickcheck = "1.0.3" rand = "0.9.2" From f5224967d0d6a23bd239d4eaf62ff432e8b5ef3f Mon Sep 17 00:00:00 2001 From: Quanyi Ma Date: Sun, 12 Oct 2025 22:10:28 +0800 Subject: [PATCH 3/3] Update src/errors.rs Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> --- src/errors.rs | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/src/errors.rs b/src/errors.rs index 24c4ed91..9c76a1a6 100644 --- a/src/errors.rs +++ b/src/errors.rs @@ -103,8 +103,8 @@ pub enum GitError { InvalidObjectInfo(String), /// Hash not found in current file context. - #[error("Can't found Hash value :{0} from current file")] - NotFountHashValue(String), + #[error("Cannot find Hash value: {0} from current file")] + NotFoundHashValue(String), /// Failed to encode object to bytes. #[error("Can't encode the object which id [{0}] to bytes")]