Artifact [4ea0dd9c15]

Artifact 4ea0dd9c156ebefc93b44648522c0a0d076a2bf47b75d7f5fb16458ae3697311:

• File internal/shun/purge.go — part of check-in [6273a0750d] at 2026-07-22 23:03:24 on branch trunk — fix: correct go.mod module path to go-libfossil (#76) (#117)

  * fix: correct go.mod module path to go-libfossil (#76)

  The module directive still declared github.com/danmestas/libfossil after the repository was renamed to go-libfossil. pkg.go.dev/godoc scraping matches the declared module path against its hosting path, so the stale path broke SDK doc generation.

  Rename the module path across all four in-repo modules (root, the two db/driver submodules, observer/otel, and docs/site) and every internal import, plus the release workflow, the doc-generation script, and the docs.

  No tag has been published under the go-libfossil path yet, so the cross-module requires cannot resolve from the proxy. Add replace directives pointing the in-repo requires at their local directories so GOWORK=off builds and the CI matrix resolve without a published version. These replaces are ignored by downstream consumers and can be dropped once new-path tags are cut.

  * Guard releases against replace directives; regenerate SDK docs

  The go-libfossil rename bridges the in-repo modules with `replace` directives. Go refuses a main module that carries them, so a tag cut while they are present breaks `go install .../cmd/libfossil@<tag>` and every `@version` fetch of the driver submodules. Add a Release workflow step that fails the job before anything is published if any tracked go.mod still contains a replace directive, so the bridge is a CI-enforced TODO rather than a silent landmine. The step comment records what unblocks a release: re-tag the submodules with the corrected module paths, bump the root requires, then drop the replace blocks.

  Regenerate the SDK reference docs. The previous pass only substituted URLs over the pre-existing generated files, leaving stale signatures (Repo.Timeline was still documented as taking LogOpts rather than TimelineOpts). Note that gomarkdoc must be run outside a git worktree — inside one it silently strips every source link.

  Also reword the README rename note, which read as though the import path had not changed, and re-sort the ncruces require block. (user: [email protected], size: 3050) [annotate] [blame] [check-ins using]

package shun

import (
	"fmt"

	"github.com/danmestas/go-libfossil/db"
	"github.com/danmestas/go-libfossil/internal/blob"
	"github.com/danmestas/go-libfossil/internal/content"
	libfossil "github.com/danmestas/go-libfossil/internal/fsltype"
)

// PurgeResult summarizes what Purge deleted.
type PurgeResult struct {
	BlobsDeleted   int
	DeltasExpanded int
	PrivateCleaned int
}

// Purge physically removes all shunned blobs from the repo.
// Follows Fossil's shun_artifacts() algorithm from shun.c.
// Requires *db.DB (not Querier) because it runs in a transaction.
func Purge(d *db.DB) (PurgeResult, error) {
	if d == nil {
		panic("shun.Purge: d must not be nil")
	}
	var result PurgeResult

	err := d.WithTx(func(tx *db.Tx) error {
		// Step 1: Find rids to delete.
		_, err := tx.Exec(`CREATE TEMP TABLE toshun(rid INTEGER PRIMARY KEY)`)
		if err != nil {
			return fmt.Errorf("create toshun: %w", err)
		}

		_, err = tx.Exec(`INSERT INTO toshun SELECT rid FROM blob WHERE uuid IN (SELECT uuid FROM shun)`)
		if err != nil {
			return fmt.Errorf("populate toshun: %w", err)
		}

		// Step 2: Undelta dependents — expand blobs whose delta source is being shunned.
		rows, err := tx.Query(`SELECT rid FROM delta WHERE srcid IN (SELECT rid FROM toshun)`)
		if err != nil {
			return fmt.Errorf("query dependents: %w", err)
		}
		var dependents []libfossil.FslID
		for rows.Next() {
			var rid libfossil.FslID
			if err := rows.Scan(&rid); err != nil {
				rows.Close()
				return fmt.Errorf("scan dependent: %w", err)
			}
			dependents = append(dependents, rid)
		}
		rows.Close()

		for _, rid := range dependents {
			expanded, err := content.Expand(tx, rid)
			if err != nil {
				return fmt.Errorf("expand rid %d: %w", rid, err)
			}
			compressed, err := blob.Compress(expanded)
			if err != nil {
				return fmt.Errorf("compress rid %d: %w", rid, err)
			}
			_, err = tx.Exec("UPDATE blob SET content=?, size=? WHERE rid=?",
				compressed, len(expanded), rid)
			if err != nil {
				return fmt.Errorf("update blob rid %d: %w", rid, err)
			}
			_, err = tx.Exec("DELETE FROM delta WHERE rid=?", rid)
			if err != nil {
				return fmt.Errorf("delete delta rid %d: %w", rid, err)
			}
			result.DeltasExpanded++
		}

		// Step 3: Delete shunned blobs.
		_, err = tx.Exec("DELETE FROM delta WHERE rid IN (SELECT rid FROM toshun)")
		if err != nil {
			return fmt.Errorf("delete shunned deltas: %w", err)
		}

		res, err := tx.Exec("DELETE FROM blob WHERE rid IN (SELECT rid FROM toshun)")
		if err != nil {
			return fmt.Errorf("delete shunned blobs: %w", err)
		}
		n, _ := res.RowsAffected()
		result.BlobsDeleted = int(n)

		_, err = tx.Exec("DROP TABLE toshun")
		if err != nil {
			return fmt.Errorf("drop toshun: %w", err)
		}

		// Step 4: Orphan cleanup.
		res, err = tx.Exec("DELETE FROM private WHERE NOT EXISTS (SELECT 1 FROM blob WHERE rid=private.rid)")
		if err != nil {
			return fmt.Errorf("cleanup private: %w", err)
		}
		n, _ = res.RowsAffected()
		result.PrivateCleaned = int(n)

		return nil
	})

	return result, err
}