Artifact [6fd14f172b]

Artifact 6fd14f172bba509869365cbd69947e374b0f7e023f28ec3adbce88f12ec4b0d3:

• File internal/search/index.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: 2934) [annotate] [blame] [check-ins using]

package search

import (
	"bytes"
	"fmt"
	"strconv"

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

// maxBinaryProbe is the number of bytes checked for null bytes to detect binary files.
const maxBinaryProbe = 8192

// isBinary returns true if data contains a null byte in the first maxBinaryProbe bytes.
func isBinary(data []byte) bool {
	if data == nil {
		panic("isBinary: nil data")
	}
	probe := data
	if len(probe) > maxBinaryProbe {
		probe = probe[:maxBinaryProbe]
	}
	return bytes.ContainsRune(probe, 0)
}

// RebuildIndex walks the trunk tip manifest, expands blob content,
// skips binaries and phantoms, and populates fts_content.
// No-ops if already current.
//
// Panics if idx is nil (TigerStyle precondition).
func (idx *Index) RebuildIndex() error {
	if idx == nil {
		panic("search.RebuildIndex: nil *Index")
	}

	d := idx.repo.DB()

	tip, err := trunkTip(d)
	if err != nil {
		return fmt.Errorf("search.RebuildIndex: %w", err)
	}
	if tip == 0 {
		return nil // empty repo, nothing to index
	}

	current, err := indexedRID(d)
	if err != nil {
		return fmt.Errorf("search.RebuildIndex: %w", err)
	}
	if tip == current {
		return nil // already up to date
	}

	if err := rebuildPopulate(idx.repo, d, tip); err != nil {
		return err
	}

	// Postcondition: verify the meta update took hold.
	stored, err := indexedRID(d)
	if err != nil {
		return fmt.Errorf("search.RebuildIndex: verify meta: %w", err)
	}
	if stored != tip {
		panic("search.RebuildIndex: postcondition: indexed_rid != tip after update")
	}

	return nil
}

// rebuildPopulate clears fts_content, walks the manifest at tip,
// expands each text blob, and inserts into the FTS index.
func rebuildPopulate(r *repo.Repo, d db.Querier, tip libfossil.FslID) error {
	if _, err := d.Exec("DELETE FROM fts_content"); err != nil {
		return fmt.Errorf("search.RebuildIndex: clear: %w", err)
	}

	files, err := manifest.ListFiles(r, tip)
	if err != nil {
		return fmt.Errorf("search.RebuildIndex: list files: %w", err)
	}

	for _, f := range files {
		rid, ok := content.AvailableByUUID(d, f.UUID)
		if !ok {
			continue // phantom — blob not yet received
		}

		data, err := content.Expand(d, rid)
		if err != nil {
			continue // phantom or corrupt — skip
		}

		if isBinary(data) {
			continue
		}

		if _, err := d.Exec(
			"INSERT INTO fts_content(path, content) VALUES(?, ?)",
			f.Name, string(data),
		); err != nil {
			return fmt.Errorf("search.RebuildIndex: insert %s: %w", f.Name, err)
		}
	}

	if _, err := d.Exec(
		"INSERT OR REPLACE INTO fts_meta(key, value) VALUES('indexed_rid', ?)",
		strconv.FormatInt(int64(tip), 10),
	); err != nil {
		return fmt.Errorf("search.RebuildIndex: update meta: %w", err)
	}

	return nil
}