Artifact [c708f13c8d]

Artifact c708f13c8d475de1410b392d9fc568ccc1281b0fc2b16132baf3c4b216288048:

• File internal/merge/resolve.go — part of check-in [0fd2a507b8] at 2026-07-24 15:27:03 on branch trunk — perf: route history-walking expansions through content.Cache (#151) (#153)

  The buffer-reuse fix in #145/#150 cut the cost of expanding one delta chain once. It did nothing for callers that expand many versions of the same artifact in a single operation: each bare content.Expand still replayed the whole O(depth) chain, so a walk over N overlapping revisions cost O(N^2) blob reads even though content.Cache already existed for exactly this pattern.

  Audited every non-test content.Expand caller. Two access patterns genuinely repeat over overlapping delta chains and are now routed through a per-operation content.Cache:

  - annotate walks every revision of one file along the parent chain. content_deltify stores each older file blob as a delta against its successor, so the per-revision expansions are all walks of the same few chains. One cache threaded through the walk (file blob + manifest listing via new manifest.ListFilesCached/GetManifestCached, both nil-passthrough so existing callers are unchanged) turns it linear. Measured on a deltified 150-revision file: 1.60s -> 0.65s (2.5x), 764k -> 308k allocs; the win grows with history depth.

  - verify.Verify and verify.Rebuild sweep every blob more than once (Rebuild: checkBlobs + rebuildManifests + rebuildTags x2). A single cache shared across the pass walks each chain once instead of once per sweep and amortizes overlap within each sweep. Measured on a 150-revision two-file repo: Rebuild 3.34s -> 0.068s (48x), 4.59M -> 98k allocs.

  Callers that only ever touch the tip or make a single pass over distinct blobs (branch create, merge-config load, R-card / delta manifest build, MergeParentFiles, crosslinkSingle, shun undelta, pairwise Diff) are left on bare Expand, each with a comment stating why a cache cannot amortize their access.

  No behavior change: expansion output is byte-identical, verified across the modernc and ncruces drivers with REQUIRE_FOSSIL_BIN=1 cross-checks and the DST suite. (user: [email protected], size: 2271) [annotate] [blame] [check-ins using]

package merge

import (
	"bufio"
	"path/filepath"
	"strings"

	"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"
)

// PatternRule maps a glob pattern to a strategy name.
type PatternRule struct {
	Glob     string
	Strategy string
}

// Resolver picks the merge strategy for a given filename.
type Resolver struct {
	patterns []PatternRule
	fallback string
}

// LoadResolver reads the .libfossil-merge file from the repo at the given
// version, plus the merge-strategy config key as fallback.
func LoadResolver(r *repo.Repo, tipRid libfossil.FslID) *Resolver {
	if r == nil {
		panic("merge.LoadResolver: r must not be nil")
	}
	res := &Resolver{fallback: "three-way"}

	var cfgDefault string
	if r.DB().QueryRow("SELECT value FROM config WHERE name='merge-strategy'").Scan(&cfgDefault) == nil && cfgDefault != "" {
		res.fallback = cfgDefault
	}

	if tipRid > 0 {
		files, err := manifest.ListFiles(r, tipRid)
		if err == nil {
			for _, f := range files {
				if f.Name == ".libfossil-merge" {
					rid, ok := content.AvailableByUUID(r.DB(), f.UUID)
					if ok {
						// Bare Expand: one config file (.libfossil-merge) at one
						// version, read once. No revision walk to cache.
						data, err := content.Expand(r.DB(), rid)
						if err == nil {
							res.patterns = parseMergeFile(data)
						}
					}
					break
				}
			}
		}
	}

	return res
}

// Resolve returns the strategy name for a filename.
func (res *Resolver) Resolve(filename string) string {
	for _, p := range res.patterns {
		matched, matchErr := filepath.Match(p.Glob, filepath.Base(filename))
		if matchErr != nil {
			continue
		}
		if matched {
			return p.Strategy
		}
	}
	return res.fallback
}

func parseMergeFile(data []byte) []PatternRule {
	var rules []PatternRule
	scanner := bufio.NewScanner(strings.NewReader(string(data)))
	for scanner.Scan() {
		line := strings.TrimSpace(scanner.Text())
		if line == "" || strings.HasPrefix(line, "#") {
			continue
		}
		parts := strings.Fields(line)
		if len(parts) >= 2 {
			rules = append(rules, PatternRule{Glob: parts[0], Strategy: parts[1]})
		}
	}
	return rules
}