feat(handler): add EROFS filesystem handler

EROFS is a high-performance read-only filesystem originally developed by
Huawei and now used extensively in AOSP. It offers features like
compression (LZ4, LZMA), inline data, and reduced storage overhead,
making it ideal for read-only system images.

Create erofs file : > mkfs.erofs -z[compressor, level (optional)]
foo.erofs.img foo/

Extract erofs file: > fsck.erofs --extract=foo_extracted/ foo.erofs.img

Key notes:
- First 1024 bytes are reserved for the boot loader
- Header starts at 0x400 with E0F5E1E2
- Header can be more than 128 bytes if extra slots provided
- File format in little endian
- There is no standarized file extension. The official documentation
  uses ".erofs.img"
- Checksum is differ form verion to version

Unblob struct the header until the feature_incompact. The rest is labeled
as "reserved". Unblob parser the end offset by multiplying the block
size in bit shift with the block count.

Since the checksum is not consistent troughout versions, unblob matched
on block count (at least 1), printable volume name and if there is a
build time.

[Sources]
https://elixir.bootlin.com/linux/v6.14-rc6/source/fs/erofs/erofs_fs.h
https://web.git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/fs/erofs/erofs_fs.h?h=v6.6
https://erofs.docs.kernel.org/en/latest/core_ondisk.html
https://www.kernel.org/doc/html/latest/filesystems/erofs.html

Author: qkaiser

install-deps.sh

@@ -5,6 +5,7 @@ apt-get update
 apt-get install --no-install-recommends -y \
     android-sdk-libsparse-utils \
     curl \
+    erofs-utils \
     lz4 \
     lziprecover \
     lzop \

package.nix

@@ -4,6 +4,7 @@
   fetchFromGitHub,
   makeWrapper,
   e2fsprogs-nofortify,
+  erofs-utils,
   jefferson,
   lz4,
   lziprecover,
@@ -24,6 +25,7 @@ let
   # These dependencies are only added to PATH
   runtimeDeps = [
     e2fsprogs-nofortify
+    erofs-utils
     jefferson
     lziprecover
     lzop

python/unblob/handlers/__init__.py

@@ -49,7 +49,7 @@
     ubi,
     yaffs,
 )
-from .filesystem.android import sparse
+from .filesystem.android import erofs, sparse
 
 BUILTIN_HANDLERS: Handlers = (
     cramfs.CramFSHandler,
@@ -118,6 +118,7 @@
     engenius.EngeniusHandler,
     ecc.AutelECCHandler,
     uzip.UZIPHandler,
+    erofs.EROFSHandler,
 )
 
 BUILTIN_DIR_HANDLERS: DirectoryHandlers = (

python/unblob/handlers/filesystem/android/erofs.py

@@ -0,0 +1,70 @@
+import io
+from typing import Optional
+
+from unblob.extractors import Command
+from unblob.file_utils import (
+    Endian,
+    InvalidInputFormat,
+)
+from unblob.models import (
+    File,
+    HexString,
+    StructHandler,
+    ValidChunk,
+)
+
+C_DEFINITIONS = r"""
+    typedef struct erofs_handler{
+        uint32_t magic;
+        uint32_t crc32c;
+        uint32_t feature_compact;
+        uint8_t block_size_bs;
+        uint8_t sb_extslots;
+        uint16_t root_nid;
+        uint64_t inos;
+        uint64_t build_time;
+        uint32_t build_time_nsec;
+        uint32_t block_count;
+        uint32_t meta_blkaddr;
+        uint32_t xattr_blkaddr;
+        uint8_t uuid[16];
+        char volume_name[16];
+        uint32_t feature_incompact;
+        char reserved[44];
+    } erofs_handler_t;
+"""
+
+SUPERBLOCK_OFFSET = 0x400
+
+
+class EROFSHandler(StructHandler):
+    NAME = "erofs"
+    PATTERNS = [HexString("e2 e1 f5 e0")]  # Magic in little endian
+    HEADER_STRUCT = "erofs_handler_t"
+    C_DEFINITIONS = C_DEFINITIONS
+    EXTRACTOR = Command(
+        "fsck.erofs",
+        "--no-preserve",
+        "--extract={outdir}",
+        "{inpath}",
+    )
+    PATTERN_MATCH_OFFSET = -SUPERBLOCK_OFFSET
+
+    def is_valid_header(self, header) -> bool:
+        return (
+            header.block_count >= 1
+            and header.build_time > 0
+            and str(header.volume_name).isprintable()
+        )
+
+    def calculate_chunk(self, file: File, start_offset: int) -> Optional[ValidChunk]:
+        file.seek(SUPERBLOCK_OFFSET, io.SEEK_CUR)
+        header = self.parse_header(file, Endian.LITTLE)
+        if not self.is_valid_header(header):
+            raise InvalidInputFormat("Invalid erofs header.")
+
+        end_offset = (1 << header.block_size_bs) * header.block_count
+        return ValidChunk(
+            start_offset=start_offset,
+            end_offset=end_offset,
+        )

tests/integration/filesystem/android/erofs/__input__/foo.erofs.img

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f400d3497501c6e68324868d88207aa9398888902414045f4ea498ff26bcdcd
+size 4096

tests/integration/filesystem/android/erofs/__output__/foo.erofs.img_extract/bar.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bfc3200f0152ab9e91e662afd75add3306131f670a1d71539f680c7acdb0a9f
+size 13