aleph-cid 0.1.0__tar.gz

aleph_cid-0.1.0/PKG-INFO

@@ -0,0 +1,82 @@
+Metadata-Version: 2.4
+Name: aleph-cid
+Version: 0.1.0
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Rust
+Classifier: Topic :: System :: Filesystems
+Summary: kubo-compatible IPFS CID computation for Aleph Cloud, backed by the aleph-cid Rust crate
+Keywords: ipfs,cid,unixfs,car,aleph
+Author: Aleph Cloud
+License-Expression: MIT
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown; charset=UTF-8; variant=GFM
+Project-URL: Issues, https://github.com/aleph-im/aleph-rs/issues
+Project-URL: Repository, https://github.com/aleph-im/aleph-rs
+
+# aleph-cid (Python)
+
+kubo-compatible IPFS CID computation for [Aleph Cloud](https://aleph.cloud), backed by the
+[`aleph-cid`](https://crates.io/crates/aleph-cid) Rust crate. Computes the exact CIDs that
+kubo would assign, without running an IPFS node: streaming file hashing (CIDv0 and CIDv1),
+UnixFS folder DAGs (plain and HAMT-sharded directories), and CARv1 packing.
+
+All hashing releases the GIL, so it can run on worker threads without blocking the
+interpreter.
+
+## Install
+
+```sh
+pip install aleph-cid
+```
+
+Prebuilt abi3 wheels cover CPython 3.10+ on Linux (x86_64, aarch64), macOS, and Windows.
+
+## Usage
+
+```python
+import aleph_cid
+
+# One-shot CIDv0 (kubo `ipfs add` default)
+aleph_cid.compute_cid(b"hello\n")
+
+# Streaming, for large files
+hasher = aleph_cid.CidHasher.for_ipfs_v1_raw_leaves()
+with open("video.mp4", "rb") as f:
+    while chunk := f.read(1 << 20):
+        hasher.update(chunk)
+cid = hasher.finalize()
+
+# Verify data against an existing CID of any supported flavor
+hasher = aleph_cid.CidHasher.for_expected(cid)
+hasher.update(data)
+assert hasher.finalize() == cid
+
+# Folder root CID, matching kubo `/api/v0/add?wrap-with-directory=true`
+root = aleph_cid.hash_folder("./site", cid_version=1)
+
+# Pack a folder into a CARv1 file (for `/api/v0/ipfs/add_car` uploads)
+root = aleph_cid.write_folder_car("./site", "site.car")
+assert aleph_cid.read_carv1_root("site.car") == root
+```
+
+## Compatibility
+
+CIDs match kubo defaults: sha2-256, 256 KiB chunks, balanced DAGs with 174 links per node,
+dag-pb leaves for CIDv0 and raw leaves for CIDv1, directories HAMT-sharded above 256 KiB
+of link data. Golden tests pin the output against real kubo.
+
+## Development
+
+Built with [maturin](https://www.maturin.rs):
+
+```sh
+cd crates/aleph-cid-python
+python -m venv .venv && . .venv/bin/activate
+pip install maturin pytest
+maturin develop
+pytest
+```
+

aleph_cid-0.1.0/README.md

@@ -0,0 +1,63 @@
+# aleph-cid (Python)
+
+kubo-compatible IPFS CID computation for [Aleph Cloud](https://aleph.cloud), backed by the
+[`aleph-cid`](https://crates.io/crates/aleph-cid) Rust crate. Computes the exact CIDs that
+kubo would assign, without running an IPFS node: streaming file hashing (CIDv0 and CIDv1),
+UnixFS folder DAGs (plain and HAMT-sharded directories), and CARv1 packing.
+
+All hashing releases the GIL, so it can run on worker threads without blocking the
+interpreter.
+
+## Install
+
+```sh
+pip install aleph-cid
+```
+
+Prebuilt abi3 wheels cover CPython 3.10+ on Linux (x86_64, aarch64), macOS, and Windows.
+
+## Usage
+
+```python
+import aleph_cid
+
+# One-shot CIDv0 (kubo `ipfs add` default)
+aleph_cid.compute_cid(b"hello\n")
+
+# Streaming, for large files
+hasher = aleph_cid.CidHasher.for_ipfs_v1_raw_leaves()
+with open("video.mp4", "rb") as f:
+    while chunk := f.read(1 << 20):
+        hasher.update(chunk)
+cid = hasher.finalize()
+
+# Verify data against an existing CID of any supported flavor
+hasher = aleph_cid.CidHasher.for_expected(cid)
+hasher.update(data)
+assert hasher.finalize() == cid
+
+# Folder root CID, matching kubo `/api/v0/add?wrap-with-directory=true`
+root = aleph_cid.hash_folder("./site", cid_version=1)
+
+# Pack a folder into a CARv1 file (for `/api/v0/ipfs/add_car` uploads)
+root = aleph_cid.write_folder_car("./site", "site.car")
+assert aleph_cid.read_carv1_root("site.car") == root
+```
+
+## Compatibility
+
+CIDs match kubo defaults: sha2-256, 256 KiB chunks, balanced DAGs with 174 links per node,
+dag-pb leaves for CIDv0 and raw leaves for CIDv1, directories HAMT-sharded above 256 KiB
+of link data. Golden tests pin the output against real kubo.
+
+## Development
+
+Built with [maturin](https://www.maturin.rs):
+
+```sh
+cd crates/aleph-cid-python
+python -m venv .venv && . .venv/bin/activate
+pip install maturin pytest
+maturin develop
+pytest
+```

aleph_cid-0.1.0/aleph-cid/Cargo.toml

@@ -0,0 +1,31 @@
+[package]
+name = "aleph-cid"
+version = "0.1.0"
+edition = "2024"
+description = "kubo-compatible IPFS CID computation for Aleph Cloud: UnixFS dag-pb hashing, HAMT-sharded directories and CARv1 framing."
+license = "MIT"
+repository = "https://github.com/aleph-im/aleph-rs"
+homepage = "https://github.com/aleph-im/aleph-rs"
+
+[dependencies]
+bs58 = "^0.5"
+cid = "^0.11"
+multihash = "^0.19"
+murmur3 = "^0.5"
+prost = "^0.13"
+serde = { version = "^1.0.228", optional = true, features = ["derive"] }
+sha2 = "^0.10.9"
+thiserror = "^2.0.17"
+walkdir = "^2"
+
+[features]
+default = []
+# serde impls for `cid::Cid` (string round-trip). Enabled by aleph-types.
+serde = ["dep:serde"]
+
+[dev-dependencies]
+multihash-codetable = { version = "^0.1", features = ["sha2"] }
+reqwest = { version = "^0.13.2", features = ["json", "stream", "multipart"] }
+serde_json = "^1.0.145"
+tempfile = "^3"
+tokio = { version = "^1.48.0", features = ["rt", "rt-multi-thread", "macros", "fs", "sync", "time"] }

aleph_cid-0.1.0/aleph-cid/proto/merkledag.proto

@@ -0,0 +1,13 @@
+syntax = "proto2";
+package merkledag;
+
+message PBLink {
+  optional bytes Hash = 1;
+  optional string Name = 2;
+  optional uint64 Tsize = 3;
+}
+
+message PBNode {
+  repeated PBLink Links = 2;
+  optional bytes Data = 1;
+}

aleph_cid-0.1.0/aleph-cid/proto/unixfs.proto

@@ -0,0 +1,20 @@
+syntax = "proto2";
+package unixfs;
+
+enum DataType {
+  Raw = 0;
+  Directory = 1;
+  File = 2;
+  Metadata = 3;
+  Symlink = 4;
+  HAMTShard = 5;
+}
+
+message Data {
+  required DataType Type = 1;
+  optional bytes Data = 2;
+  optional uint64 filesize = 3;
+  repeated uint64 blocksizes = 4;
+  optional uint64 hashType = 5;
+  optional uint64 fanout = 6;
+}