distributor/internal/state/distributor.go

package state

import (
	"bytes"
	"encoding/json"
	"fmt"
	"io"
	"time"

	"gitea.maximumdirect.net/eric/distributor/internal/bundle"
)

const SchemaVersion = 1

type DistributorState struct {
	SchemaVersion      int
	DistributorVersion string
	PipelineID         string
	DestinationID      string
	PublishedAt        time.Time
	Source             SourceState
	Links              *LinkState
	Outputs            []OutputFile
}

type SourceState struct {
	Manifest bundle.Manifest
}

type LinkState struct {
	PrimaryURL string
}

type OutputFile struct {
	Path       string
	Kind       string
	SourcePath string
	Transform  string
	URL        string
	SHA256     string
	Size       int64
}

type rawDistributorState struct {
	SchemaVersion      *int            `json:"schema_version"`
	DistributorVersion string          `json:"distributor_version"`
	PipelineID         *string         `json:"pipeline_id"`
	DestinationID      *string         `json:"destination_id"`
	PublishedAt        *string         `json:"published_at"`
	Source             *rawSourceState `json:"source"`
	Links              *rawLinkState   `json:"links"`
	Outputs            []rawOutputFile `json:"outputs"`
}

type rawSourceState struct {
	Manifest json.RawMessage `json:"manifest"`
}

type rawLinkState struct {
	PrimaryURL string `json:"primary_url"`
}

type rawOutputFile struct {
	Path       *string `json:"path"`
	Kind       *string `json:"kind"`
	SourcePath *string `json:"source_path"`
	Transform  string  `json:"transform"`
	URL        string  `json:"url"`
	SHA256     *string `json:"sha256"`
	Size       *int64  `json:"size"`
}

func Parse(data []byte) (DistributorState, error) {
	decoder := json.NewDecoder(bytes.NewReader(data))
	var raw rawDistributorState
	if err := decoder.Decode(&raw); err != nil {
		return DistributorState{}, fmt.Errorf("parse distributor state: %w", err)
	}
	var extra any
	if err := decoder.Decode(&extra); err != io.EOF {
		return DistributorState{}, fmt.Errorf("parse distributor state: trailing data")
	}
	state, err := parseRaw(raw)
	if err != nil {
		return DistributorState{}, err
	}
	if err := Validate(state); err != nil {
		return DistributorState{}, err
	}
	return state, nil
}

func parseRaw(raw rawDistributorState) (DistributorState, error) {
	var state DistributorState
	if raw.SchemaVersion == nil {
		return DistributorState{}, fmt.Errorf("state schema_version is required")
	}
	state.SchemaVersion = *raw.SchemaVersion
	if state.SchemaVersion != SchemaVersion {
		return DistributorState{}, fmt.Errorf("state schema_version must be %d", SchemaVersion)
	}
	state.DistributorVersion = raw.DistributorVersion
	if raw.PipelineID == nil || *raw.PipelineID == "" {
		return DistributorState{}, fmt.Errorf("state pipeline_id is required")
	}
	state.PipelineID = *raw.PipelineID
	if raw.DestinationID == nil || *raw.DestinationID == "" {
		return DistributorState{}, fmt.Errorf("state destination_id is required")
	}
	state.DestinationID = *raw.DestinationID
	if raw.PublishedAt == nil || *raw.PublishedAt == "" {
		return DistributorState{}, fmt.Errorf("state published_at is required")
	}
	publishedAt, err := time.Parse(time.RFC3339, *raw.PublishedAt)
	if err != nil {
		return DistributorState{}, fmt.Errorf("state published_at must be RFC3339: %w", err)
	}
	state.PublishedAt = publishedAt.UTC()
	if raw.Source == nil || len(raw.Source.Manifest) == 0 {
		return DistributorState{}, fmt.Errorf("state source.manifest is required")
	}
	manifest, err := bundle.ParseManifest(raw.Source.Manifest)
	if err != nil {
		return DistributorState{}, fmt.Errorf("state source.manifest: %w", err)
	}
	state.Source.Manifest = manifest
	if raw.Links != nil {
		state.Links = &LinkState{PrimaryURL: raw.Links.PrimaryURL}
	}
	if raw.Outputs == nil {
		return DistributorState{}, fmt.Errorf("state outputs is required")
	}
	outputs, err := parseOutputs(raw.Outputs)
	if err != nil {
		return DistributorState{}, err
	}
	state.Outputs = outputs
	return state, nil
}

func parseOutputs(rawOutputs []rawOutputFile) ([]OutputFile, error) {
	outputs := make([]OutputFile, 0, len(rawOutputs))
	seen := make(map[string]struct{}, len(rawOutputs))
	for index, raw := range rawOutputs {
		output, err := parseOutput(index, raw)
		if err != nil {
			return nil, err
		}
		if _, exists := seen[output.Path]; exists {
			return nil, fmt.Errorf("state outputs[%d].path duplicates %q", index, output.Path)
		}
		seen[output.Path] = struct{}{}
		outputs = append(outputs, output)
	}
	return outputs, nil
}

func parseOutput(index int, raw rawOutputFile) (OutputFile, error) {
	if raw.Path == nil || *raw.Path == "" {
		return OutputFile{}, fmt.Errorf("state outputs[%d].path is required", index)
	}
	if raw.Kind == nil || *raw.Kind == "" {
		return OutputFile{}, fmt.Errorf("state outputs[%d].kind is required", index)
	}
	if raw.SourcePath == nil || *raw.SourcePath == "" {
		return OutputFile{}, fmt.Errorf("state outputs[%d].source_path is required", index)
	}
	if raw.SHA256 == nil || *raw.SHA256 == "" {
		return OutputFile{}, fmt.Errorf("state outputs[%d].sha256 is required", index)
	}
	if raw.Size == nil {
		return OutputFile{}, fmt.Errorf("state outputs[%d].size is required", index)
	}
	return OutputFile{
		Path:       *raw.Path,
		Kind:       *raw.Kind,
		SourcePath: *raw.SourcePath,
		Transform:  raw.Transform,
		URL:        raw.URL,
		SHA256:     *raw.SHA256,
		Size:       *raw.Size,
	}, nil
}

func (s DistributorState) PublishedAtString() string {
	return s.PublishedAt.UTC().Format(time.RFC3339)
}

func (s DistributorState) MarshalJSON() ([]byte, error) {
	type sourceJSON struct {
		Manifest bundle.Manifest `json:"manifest"`
	}
	type stateJSON struct {
		SchemaVersion      int          `json:"schema_version"`
		DistributorVersion string       `json:"distributor_version,omitempty"`
		PipelineID         string       `json:"pipeline_id"`
		DestinationID      string       `json:"destination_id"`
		PublishedAt        string       `json:"published_at"`
		Source             sourceJSON   `json:"source"`
		Links              *LinkState   `json:"links,omitempty"`
		Outputs            []OutputFile `json:"outputs"`
	}
	return json.Marshal(stateJSON{
		SchemaVersion:      s.SchemaVersion,
		DistributorVersion: s.DistributorVersion,
		PipelineID:         s.PipelineID,
		DestinationID:      s.DestinationID,
		PublishedAt:        s.PublishedAtString(),
		Source:             sourceJSON{Manifest: s.Source.Manifest},
		Links:              s.Links,
		Outputs:            s.Outputs,
	})
}

func (l LinkState) MarshalJSON() ([]byte, error) {
	type linkJSON struct {
		PrimaryURL string `json:"primary_url,omitempty"`
	}
	return json.Marshal(linkJSON{PrimaryURL: l.PrimaryURL})
}

func (o OutputFile) MarshalJSON() ([]byte, error) {
	type outputJSON struct {
		Path       string `json:"path"`
		Kind       string `json:"kind"`
		SourcePath string `json:"source_path"`
		Transform  string `json:"transform,omitempty"`
		URL        string `json:"url,omitempty"`
		SHA256     string `json:"sha256"`
		Size       int64  `json:"size"`
	}
	return json.Marshal(outputJSON{
		Path:       o.Path,
		Kind:       o.Kind,
		SourcePath: o.SourcePath,
		Transform:  o.Transform,
		URL:        o.URL,
		SHA256:     o.SHA256,
		Size:       o.Size,
	})
}