Skip to content

Latest commit

 

History

History
82 lines (58 loc) · 3.31 KB

README.md

File metadata and controls

82 lines (58 loc) · 3.31 KB

partial

GoDoc

Partial Implementations

There are roughly two kinds of image representations: compressed and uncompressed.

The implementations for these kinds of images are almost identical, with the only major difference being how blobs (config and layers) are fetched. This common code lives in this package, where you provide a partial implementation of a compressed or uncompressed image, and you get back a full v1.Image implementation.

Examples

In a registry, blobs are compressed, so it's easiest to implement a v1.Image in terms of compressed layers. remote.remoteImage does this by implementing CompressedImageCore:

type CompressedImageCore interface {
	RawConfigFile() ([]byte, error)
	MediaType() (types.MediaType, error)
	RawManifest() ([]byte, error)
	LayerByDigest(v1.Hash) (CompressedLayer, error)
}

In a tarball, blobs are (often) uncompressed, so it's easiest to implement a v1.Image in terms of uncompressed layers. tarball.uncompressedImage does this by implementing UncompressedImageCore:

type UncompressedImageCore interface {
	RawConfigFile() ([]byte, error)
	MediaType() (types.MediaType, error)
	LayerByDiffID(v1.Hash) (UncompressedLayer, error)
}

Optional Methods

Where possible, we access some information via optional methods as an optimization.

There are some properties of a Descriptor that aren't derivable from just image data:

  • MediaType
  • Platform
  • URLs
  • Annotations

For example, in a tarball.Image, there is a LayerSources field that contains an entire layer descriptor with URLs information for foreign layers. This information can be passed through to callers by implementing this optional Descriptor method.

See #654.

Usually, you don't need to know the uncompressed size of a layer, since that information isn't stored in a config file (just he sha256 is needed); however, there are cases where it is very helpful to know the layer size, e.g. when writing the uncompressed layer into a tarball.

See #655.

We generally don't care about the existence of something as granular as a layer, and would rather ensure all the invariants of an image are upheld via the validate package. However, there are situations where we want to do a quick smoke test to ensure that the underlying storage engine hasn't been corrupted by something e.g. deleting files or blobs. Thus, we've exposed an optional Exists method that does an existence check without actually reading any bytes.

The remote package implements this via HEAD requests.

The layout package implements this via os.Stat.

See #838.