feat(casi): implement core IO and logging functionality

Cargo.toml

@@ -7,6 +7,7 @@ members = [
     "tools/bottlerocket-variant",
     "tools/buildsys",
     "tools/buildsys-config",
+    "tools/casi",
     "tools/include-env-compressed",
     "tools/include-env-compressed/include-env-compressed-macro",
     "tools/oci-cli-wrapper",
@@ -89,6 +90,8 @@ unplug = { version = "0.1", path = "tools/unplug", artifact = [ "bin:unplug" ] }
 update-metadata = { version = "0.1", path = "tools/update-metadata" }
 
 anyhow = "1"
+astral-tokio-tar = "0.5"
+async-compression = "0.4"
 async-recursion = "1"
 async-stream = "0.3"
 async-trait = "0.1"
@@ -100,6 +103,7 @@ aws-sdk-ec2 = { version = "1", default-features = false, features = ["default-ht
 aws-sdk-kms = { version = "1", default-features = false, features = ["default-https-client", "rt-tokio"] }
 aws-sdk-ssm = { version = "1", default-features = false, features = ["default-https-client", "rt-tokio"] }
 aws-sdk-sts = { version = "1", default-features = false, features = ["default-https-client", "rt-tokio"] }
+aws-sdk-s3  = { version = "1", default-features = false, features = ["default-https-client", "rt-tokio"] }
 aws-smithy-types = "1"
 aws-types = "1"
 base64 = "0.22"
@@ -131,10 +135,13 @@ lzma-rs = "0.3"
 maplit = "1"
 nix = "0.29"
 nonzero_ext = "0.3"
-num_cpus = "1"
+num_cpus = "1.17"
 num-traits = "0.2"
+oci-spec = "0.8"
 once_cell = "1.21"
 olpc-cjson = "0.1"
+owo-colors = "4.2"
+parking_lot = "0.12"
 proc-macro2 = "1"
 quote = "1"
 rand = { version = "0.8", default-features = false }
@@ -166,6 +173,8 @@ tough = "0.21"
 tough-kms = "0.13"
 tough-ssm = "0.16"
 tracing = "0.1"
+tracing-indicatif = "=0.3.9"
+tracing-subscriber = "0.3"
 tuftool = { version = "0.14", artifact = [ "bin:tuftool" ] }
 uds = "0.4.1"
 unescape = "0.1"

deny.toml

@@ -62,6 +62,8 @@ wildcards = "deny"
 skip = [
     # several dependencies are using multiple versions of base64
     { name = "base64" },
+    # owo-colors uses two versions of supports-color by itself
+    { name = "supports-color" }
 ]
 
 skip-tree = [

tools/casi/Cargo.toml

@@ -0,0 +1,45 @@
+[package]
+name = "casi"
+version = "0.1.0"
+authors = ["Jarrett Tierney <[email protected]>"]
+license = "Apache-2.0 OR MIT"
+edition = "2021"
+publish = false
+
+[dependencies]
+astral-tokio-tar.workspace = true
+async-compression = { workspace = true, features = ["tokio", "zstd"] }
+async-trait.workspace = true
+aws-config.workspace = true
+aws-sdk-s3.workspace = true
+aws-smithy-types.workspace = true
+aws-types.workspace = true
+bon.workspace = true
+chrono = { workspace = true, features = ["serde", "now"] }
+clap = { workspace = true, features = ["derive"] }
+futures.workspace = true
+hex.workspace = true
+indicatif.workspace = true
+oci-spec.workspace = true
+olpc-cjson.workspace = true
+owo-colors = { workspace = true, features = ["supports-colors"] }
+parking_lot = { workspace = true, features = ["send_guard", "arc_lock"] }
+rand.workspace = true
+semver = { workspace = true, features = ["serde"] }
+serde = { workspace = true, features = ["derive"] }
+serde_json.workspace = true
+sha2.workspace = true
+snafu.workspace = true
+tempfile.workspace = true
+tokio = { workspace = true, features = ["full"] }
+tracing.workspace = true
+tracing-indicatif.workspace = true
+tracing-subscriber = { workspace = true, features = [
+    "env-filter",
+    "fmt",
+    "registry",
+] }
+url = { workspace = true, features = ["serde"] }
+uuid = { workspace = true, features = ["v4"] }
+walkdir.workspace = true
+zstd.workspace = true

tools/casi/src/constants.rs

@@ -0,0 +1,48 @@
+//! Constants used throughout the casi crate.
+//!
+//! This module centralizes magic numbers and commonly used values to improve
+//! code maintainability and reduce the likelihood of errors.
+
+/// Default buffer size for I/O operations (64KB)
+pub const DEFAULT_BUFFER_SIZE: usize = 64 * 1024;
+
+/// Buffer size for hashing operations (128MB)
+/// Uses 8KB chunks which align with standard memory page sizes for optimal
+/// performance when reading from files and network streams.
+pub const HASH_BUFFER_SIZE: usize = 128 * 1024 * 1024;
+
+/// Maximum number of multipart upload parts for S3
+pub const MAX_MULTIPART_PARTS: usize = 10_000;
+
+/// Minimum size for S3 multipart upload parts (5MB)
+pub const MIN_MULTIPART_PART_SIZE: usize = 5 * 1024 * 1024;
+
+/// Default compression level for Zstd
+pub const DEFAULT_COMPRESSION_LEVEL: i32 = 3;
+
+/// Maximum file name length for cross-platform compatibility
+pub const MAX_FILENAME_LENGTH: usize = 255;
+
+/// Default timeout for network operations (30 seconds)
+pub const DEFAULT_NETWORK_TIMEOUT_SECS: u64 = 30;
+
+/// Maximum retry attempts for transient failures
+pub const MAX_RETRY_ATTEMPTS: usize = 3;
+
+/// Default page size for listing operations
+pub const DEFAULT_PAGE_SIZE: usize = 100;
+
+/// Maximum artifacts to display in table format
+pub const MAX_TABLE_DISPLAY_ARTIFACTS: usize = 1000;
+
+/// Hash truncation length for display purposes
+pub const HASH_DISPLAY_LENGTH: usize = 16;
+
+/// Schema version for OCI manifests
+pub const OCI_MANIFEST_SCHEMA_VERSION: u32 = 2;
+
+/// Default file permissions for created files (0o644)
+pub const DEFAULT_FILE_PERMISSIONS: u32 = 0o644;
+
+/// Default directory permissions for created directories (0o755)
+pub const DEFAULT_DIR_PERMISSIONS: u32 = 0o755;

tools/casi/src/error.rs

@@ -0,0 +1,20 @@
+use snafu::Snafu;
+
+pub type Result<T> = std::result::Result<T, Error>;
+
+#[derive(Debug, Snafu)]
+#[snafu(visibility(pub))]
+pub enum Error {
+    #[snafu(display(
+        "Failed to read data for hashing: {source} - check if the file exists and is readable"
+    ))]
+    HashingReadError { source: std::io::Error },
+
+    #[snafu(display("Failed to initialize logging system: {source}"))]
+    LogInit {
+        source: Box<dyn std::error::Error + Send + Sync>,
+    },
+
+    #[snafu(display("Failed to parse log directive: {directive}"))]
+    LogDirectiveParse { directive: String },
+}