mesh-controller/internal/inventory/catalogue.go

package inventory

import (
	"context"
	"encoding/json"
	"errors"
	"fmt"
	"strings"

	"github.com/jackc/pgx/v5"
	"github.com/novox/mesh-control/internal/catalogue"
)

// ErrNoSuchModule is what the mesh says about a module it has never been told about.
var ErrNoSuchModule = errors.New("no module of that name")

// ErrStillAssigned is why a module cannot be forgotten.
//
// Its own error because it is not a fault: it means a machine is running that module now, and
// removing the record would leave the mesh unable to describe what is on it.
var ErrStillAssigned = errors.New("that module is still assigned to nodes")

// RegisterModule records a module, replacing what was there.
//
// Replacing rather than refusing, because a manifest changing is the ordinary case -- a module
// gains a requirement, a claim, a resource. What matters is that the change is visible the next
// time a node is resolved, which it is.
func (i *Inventory) RegisterModule(ctx context.Context, m catalogue.Manifest) error {
	raw, err := json.Marshal(m)
	if err != nil {
		return err
	}
	_, err = i.store.Pool().Exec(ctx,
		`insert into module (name, manifest, version) values ($1, $2, nullif($3,''))
		 on conflict (name) do update set manifest = excluded.manifest,
		                                  version = excluded.version,
		                                  registered = now()`,
		m.Module, raw, m.Version)
	return err
}

// Catalogue is every module the mesh knows about, which is what resolution needs: the question
// "how many modules provide this" cannot be asked of a subset.
func (i *Inventory) Catalogue(ctx context.Context) (map[string]catalogue.Manifest, error) {
	rows, err := i.store.Pool().Query(ctx, `select manifest from module order by name`)
	if err != nil {
		return nil, err
	}
	defer rows.Close()

	out := map[string]catalogue.Manifest{}
	for rows.Next() {
		var raw []byte
		if err := rows.Scan(&raw); err != nil {
			return nil, err
		}
		var m catalogue.Manifest
		if err := json.Unmarshal(raw, &m); err != nil {
			return nil, err
		}
		out[m.Module] = m
	}
	return out, rows.Err()
}

// ForgetModule removes a module, unless a machine is running it.
func (i *Inventory) ForgetModule(ctx context.Context, name string) error {
	var on []string
	rows, err := i.store.Pool().Query(ctx,
		`select n.name from assignment a join node n on n.id = a.node where a.module = $1
		 order by n.name`, name)
	if err != nil {
		return err
	}
	for rows.Next() {
		var node string
		if err := rows.Scan(&node); err != nil {
			rows.Close()
			return err
		}
		on = append(on, node)
	}
	rows.Close()
	if len(on) > 0 {
		return fmt.Errorf("%w: %s. Unassign it first", ErrStillAssigned, strings.Join(on, ", "))
	}

	tag, err := i.store.Pool().Exec(ctx, `delete from module where name = $1`, name)
	if err != nil {
		return err
	}
	if tag.RowsAffected() == 0 {
		return fmt.Errorf("%w: %s", ErrNoSuchModule, name)
	}
	return nil
}

// Assign puts a module on a node.
//
// Records the intention and checks nothing. Whether the set of assignments can actually become a
// declaration is resolution's question, asked over the whole set at once — and asking it here,
// one module at a time, would let an assignment look accepted and then refuse when a second
// arrives.
func (i *Inventory) Assign(ctx context.Context, nodeName, module string) error {
	node, err := i.NodeByName(ctx, nodeName)
	if err != nil {
		return err
	}
	_, err = i.store.Pool().Exec(ctx,
		`insert into assignment (node, module) values ($1, $2) on conflict do nothing`,
		node.ID, module)
	if err != nil && strings.Contains(err.Error(), "assignment_module_fkey") {
		return fmt.Errorf("%w: %s", ErrNoSuchModule, module)
	}
	return err
}

// Unassign takes a module off a node.
func (i *Inventory) Unassign(ctx context.Context, nodeName, module string) error {
	node, err := i.NodeByName(ctx, nodeName)
	if err != nil {
		return err
	}
	tag, err := i.store.Pool().Exec(ctx,
		`delete from assignment where node = $1 and module = $2`, node.ID, module)
	if err != nil {
		return err
	}
	if tag.RowsAffected() == 0 {
		return fmt.Errorf("%s is not assigned to %s", module, nodeName)
	}
	return nil
}

// Assigned is what a person put on this node, which is not the same as what it runs: resolution
// adds whatever those modules require.
func (i *Inventory) Assigned(ctx context.Context, nodeName string) ([]string, error) {
	node, err := i.NodeByName(ctx, nodeName)
	if err != nil {
		return nil, err
	}
	rows, err := i.store.Pool().Query(ctx,
		`select module from assignment where node = $1 order by module`, node.ID)
	if err != nil {
		return nil, err
	}
	defer rows.Close()

	var out []string
	for rows.Next() {
		var m string
		if err := rows.Scan(&m); err != nil {
			return nil, err
		}
		out = append(out, m)
	}
	return out, rows.Err()
}

// ProfileOf is what a node last said it can do, as resolution needs it: the capabilities that are
// present, and nothing else.
func (i *Inventory) ProfileOf(ctx context.Context, nodeName string) (map[string]bool, error) {
	var raw []byte
	err := i.store.Pool().QueryRow(ctx,
		`select profile from node where name = $1`, nodeName).Scan(&raw)
	if errors.Is(err, pgx.ErrNoRows) {
		return nil, fmt.Errorf("%w: %s", ErrNoSuchNode, nodeName)
	}
	if err != nil {
		return nil, err
	}

	out := map[string]bool{}
	if len(raw) == 0 {
		// A node that has never reported. Not an error, and not an empty machine either — every
		// capability will read as absent, so anything requiring one is refused with "the wrong
		// machine", which is wrong but visible. Better than assuming it can do everything.
		return out, nil
	}
	var reported struct {
		Capabilities []struct {
			Name    string `json:"name"`
			Present bool   `json:"present"`
		} `json:"capabilities"`
	}
	if err := json.Unmarshal(raw, &reported); err != nil {
		return nil, err
	}
	for _, c := range reported.Capabilities {
		if c.Present {
			out[c.Name] = true
		}
	}
	return out, nil
}