marketplace/cli/internal/cmd/labels.go

package cmd

import (
	"flag"
	"fmt"
	"os"
	"regexp"
	"strings"

	sdk "code.gitea.io/sdk/gitea"

	"git.noodles.cam/claude-skills/marketplace/cli/internal/mapping"
	"git.noodles.cam/claude-skills/marketplace/cli/internal/wire"
)

func init() {
	register(&Command{
		Name:  "labels",
		Group: GroupSync,
		Short: "put the canonical type/* and severity/* labels into a repository",
		Long: `Every ` + "`type/*`" + ` and every ` + "`severity/*`" + ` the domain taxonomy defines, created up
front instead of trickling in as a side effect of whichever push first happens
to use one. Until a name exists in the repository nobody can filter by it in the
web UI, so somebody makes their own — foreign colour, no ` + "`exclusive`" + ` — and the
set arrives in pieces over months.

NO LABEL NAME IS SPELLED OUT HERE. The names come from the domain taxonomy and
are painted by the mapping layer, because a hex code is how a tracker paints a
chip and not what an issue is. Add a type over in the domain and the next run
creates it.

THE REPOSITORY'S OWN LABELS ARE READ BEFORE ANYTHING IS WRITTEN, and read from
the repository, never from a cache — a cache answers "what did we create last
time" and the question here is "what does this repository have right now". A
name that matches exactly is left alone; a colour or ` + "`exclusive`" + ` that disagrees
with the spec is reported, and corrected only under --fix. A name that merely
RESEMBLES a canonical one (the same tail, up to case, separator and whatever
namespace is in front: ` + "`x`" + `, ` + "`X`" + `, ` + "`kind/x`" + `, ` + "`type: x`" + ` against ` + "`type/x`" + `) is
reported with its id and never touched — renaming somebody else's label is a
decision, not a step.

Out of scope by design: ` + "`tech/*`" + ` and ` + "`comp/*`" + `, which are open-ended and are
created by push as they come up, and deleting or renaming anything at all. Only
repository labels are read; an organization's own labels sit behind a different
endpoint and are neither read nor written.

The issue store is out of scope too, and not incidentally: a label belongs to
the repository and not to any issue, so this neither reads the store nor creates
it. Request bodies go to the transport's own scratchpad, which is a sibling of
the store and never a child.`,
		Examples: []Example{
			{"kettle labels --dry-run", "print the plan; not one writing request"},
			{"kettle labels", "create whatever is missing"},
			{"kettle labels --fix", "also patch colour / exclusive drift"},
			{"kettle labels --repo owner/name", "bootstrap another repository"},
		},
		Setup: func(fs *flag.FlagSet) func([]string) error {
			dryRun := fs.Bool("dry-run", false, "print the plan; not one writing request")
			fix := fs.Bool("fix", false, "also patch colour/exclusive on labels that already exist")
			repo := fs.String("repo", "", "repository to bootstrap, as owner/name (default: this project's)")

			return func(args []string) error {
				if len(args) > 0 {
					return Fail("labels takes no arguments — the set comes from the taxonomy, not the command line")
				}
				// The store root is resolved and then deliberately dropped: this
				// command must fail the same way as every other sync command when
				// there is no project, and must touch no issue once there is one.
				_, client, err := syncStart("")
				if err != nil {
					return err
				}
				if *repo != "" {
					r, err := wire.ParseRepo(*repo)
					if err != nil {
						return Fail("--repo %v", err)
					}
					client = client.For(r)
				}

				specs := mapping.CanonicalLabelSpecs()
				existing, err := client.ListLabels()
				if err != nil {
					return err
				}
				rows, similar := labelPlan(specs, existing)

				created, fixed, drifted := 0, 0, 0
				for _, row := range rows {
					mark := ""
					if row.spec.Exclusive {
						mark = "  exclusive"
					}

					if row.got == nil {
						created++
						if *dryRun {
							fmt.Printf("create   %-20s %s%s\n", row.spec.Name, row.spec.Color, mark)
							continue
						}
						made, err := client.CreateLabel(row.spec)
						if err != nil {
							return err
						}
						fmt.Printf("created  %-20s id %-5d %s%s\n", row.spec.Name, made.ID, row.spec.Color, mark)
						continue
					}
					if len(row.drift) == 0 {
						fmt.Printf("present  %-20s id %d\n", row.spec.Name, row.got.ID)
						continue
					}

					drifted++
					shown := labelShowDrift(row.drift)
					if !*fix {
						fmt.Printf("present  %-20s id %-5d drift: %s\n", row.spec.Name, row.got.ID, shown)
						continue
					}
					if *dryRun {
						fmt.Printf("fix      %-20s id %-5d %s\n", row.spec.Name, row.got.ID, shown)
						continue
					}
					// The unchanged name rides along because a server that reads an
					// absent field as empty would blank it, and the description is
					// the repository's own: a description somebody rewrote is
					// theirs, and this run is about colour and exclusivity.
					patch := row.spec
					patch.Description = row.got.Description
					if _, err := client.EditLabel(row.got.ID, patch); err != nil {
						return err
					}
					fixed++
					fmt.Printf("fixed    %-20s id %-5d %s\n", row.spec.Name, row.got.ID, shown)
				}

				for _, s := range similar {
					fmt.Fprintf(os.Stderr, "warning: %q (id %d) resembles %s — left alone; rename it by hand or ignore it\n",
						s.name, s.id, strings.Join(s.hits, ", "))
				}

				verb := "created"
				if *dryRun {
					verb = "to create"
				}
				line := fmt.Sprintf("%d canonical label(s): %d %s, %d present",
					len(rows), created, verb, len(rows)-created)
				if drifted > 0 {
					line += fmt.Sprintf(" (%d drifted, %d fixed)", drifted, fixed)
				}
				if len(similar) > 0 {
					line += fmt.Sprintf(", %d similar", len(similar))
				}
				fmt.Println(line)
				if drifted > 0 && !*fix {
					fmt.Println("drift is shown, not applied — re-run with --fix to patch colour/exclusive")
				}
				if *dryRun {
					fmt.Println("dry-run — nothing was written")
				}
				return nil
			}
		},
	})
}

// labelRow is one canonical label, decided before anything is written: what the
// taxonomy says it should be, what the repository already has under that exact
// name (nil when it has nothing), and where the two disagree.
type labelRow struct {
	spec  sdk.CreateLabelOption
	got   *sdk.Label
	drift []labelDiff
}

// labelDiff is one field that disagrees, with both readings, so a receipt can
// show the change without the caller re-deriving it.
type labelDiff struct{ field, is, want string }

// labelLookalike is a label of the repository's own that resembles a canonical
// name. Reported with its id and never touched.
type labelLookalike struct {
	name string
	id   int64
	hits []string
}

// labelPlan pairs the canonical set with what the repository holds.
//
// In taxonomy order, because a bootstrap prints its plan in that order and a map
// would shuffle it on every run — two identical runs would look like different
// ones.
func labelPlan(specs []sdk.CreateLabelOption, existing []*sdk.Label) ([]labelRow, []labelLookalike) {
	byName := make(map[string]*sdk.Label, len(existing))
	for _, l := range existing {
		byName[l.Name] = l
	}

	canonical := make(map[string]map[string]bool, len(specs))
	rows := make([]labelRow, 0, len(specs))
	for _, spec := range specs {
		canonical[spec.Name] = labelAkin(spec.Name)
		row := labelRow{spec: spec, got: byName[spec.Name]}
		if row.got != nil {
			row.drift = labelDrift(spec, row.got)
		}
		rows = append(rows, row)
	}

	var similar []labelLookalike
	for _, l := range existing {
		if _, exact := canonical[l.Name]; exact {
			continue
		}
		mine := labelAkin(l.Name)
		var hits []string
		for _, spec := range specs {
			if labelIntersects(canonical[spec.Name], mine) {
				hits = append(hits, spec.Name)
			}
		}
		if len(hits) > 0 {
			similar = append(similar, labelLookalike{name: l.Name, id: l.ID, hits: hits})
		}
	}
	return rows, similar
}

// labelDrift is where an existing label disagrees with the spec.
//
// Colour and `exclusive` only. A description somebody rewrote is theirs, and the
// name matched exactly or this row would not exist.
func labelDrift(spec sdk.CreateLabelOption, got *sdk.Label) []labelDiff {
	var out []labelDiff
	if labelHex(got.Color) != labelHex(spec.Color) {
		out = append(out, labelDiff{"color", labelHex(got.Color), labelHex(spec.Color)})
	}
	if got.Exclusive != spec.Exclusive {
		out = append(out, labelDiff{"exclusive",
			fmt.Sprintf("%t", got.Exclusive), fmt.Sprintf("%t", spec.Exclusive)})
	}
	return out
}

// labelHex normalizes a colour for comparison. Gitea reports them bare
// (`ee0701`) and the mapping layer writes them with a `#`; same colour, so a
// comparison has to strip before it compares.
func labelHex(v string) string { return strings.ToLower(strings.TrimPrefix(strings.TrimSpace(v), "#")) }

var labelWords = regexp.MustCompile(`[^a-z0-9]+`)

// labelAkin is the comparison keys for a label name: its tail, and the whole
// name squashed.
//
// Case, separators and the namespace in front are noise — what a person meant is
// the tail. `x`, `X` and `kind/x` all reduce to the same tail as `type/x`, and
// `severity: x y` to the same squashed form as `severity/xy`. Two names resemble
// each other when these sets intersect.
func labelAkin(name string) map[string]bool {
	var parts []string
	for _, p := range labelWords.Split(strings.ToLower(name), -1) {
		if p != "" {
			parts = append(parts, p)
		}
	}
	if len(parts) == 0 {
		return nil
	}
	return map[string]bool{parts[len(parts)-1]: true, strings.Join(parts, ""): true}
}

func labelIntersects(a, b map[string]bool) bool {
	for k := range a {
		if b[k] {
			return true
		}
	}
	return false
}

func labelShowDrift(drift []labelDiff) string {
	var out []string
	for _, d := range drift {
		out = append(out, fmt.Sprintf("%s %s -> %s", d.field, d.is, d.want))
	}
	return strings.Join(out, ", ")
}