internal/pkg: content-based dependency substitution

This change introduces a new fast path for FloodArtifact. It is taken when a curing artifact has identical-by-content controlled relevant inputs and are otherwise identical to an already-cured artifact.

Signed-off-by: Ophestra <cat@gensokyo.uk>

1 files changed, 47 insertions, 11 deletions

diff --git a/internal/pkg/ir.go b/internal/pkg/ir.go
index c93abc9e..72a2c90c 100644
--- a/internal/pkg/ir.go
+++ b/internal/pkg/ir.go
@@ -76,6 +76,9 @@ type IContext struct {
 	// Written to by various methods, should be zeroed after [Artifact.Params]
 	// returns and must not be exposed directly.
 	w io.Writer
+	// Optional [Artifact] to cureRes cache, replaces [IRKindIdent] with
+	// checksum values if non-nil.
+	inputs map[Artifact]cureRes
 }
 
 // irZero is a zero IR word.
@@ -163,7 +166,15 @@ func (i *IContext) WriteIdent(a Artifact) {
 	defer i.ic.putIdentBuf(buf)
 
 	IRKindIdent.encodeHeader(0).put(buf[:])
-	*(*ID)(buf[wordSize:]) = i.ic.Ident(a).Value()
+	if i.inputs != nil {
+		res, ok := i.inputs[a]
+		if !ok {
+			panic(InvalidLookupError(i.ic.Ident(a).Value()))
+		}
+		*(*ID)(buf[wordSize:]) = res.checksum.Value()
+	} else {
+		*(*ID)(buf[wordSize:]) = i.ic.Ident(a).Value()
+	}
 	i.mustWrite(buf[:])
 }
 
@@ -207,19 +218,44 @@ func (i *IContext) WriteString(s string) {
 // Encode writes a deterministic, efficient representation of a to w and returns
 // the first non-nil error encountered while writing to w.
 func (ic *irCache) Encode(w io.Writer, a Artifact) (err error) {
+	return ic.encode(w, a, nil)
+}
+
+// encode implements Encode but replaces identifiers with their cured checksums
+// for a non-nil ident. Caller must acquire Cache.identMu.
+func (ic *irCache) encode(
+	w io.Writer,
+	a Artifact,
+	inputs map[Artifact]cureRes,
+) (err error) {
 	deps := a.Dependencies()
 	idents := make([]*extIdent, len(deps))
-	for i, d := range deps {
-		dbuf, did := ic.unsafeIdent(d, true)
-		if dbuf == nil {
-			dbuf = ic.getIdentBuf()
+	if inputs == nil {
+		for i, d := range deps {
+			dbuf, did := ic.unsafeIdent(d, true)
+			if dbuf == nil {
+				dbuf = ic.getIdentBuf()
+				binary.LittleEndian.PutUint64(dbuf[:], uint64(d.Kind()))
+				*(*ID)(dbuf[wordSize:]) = did.Value()
+			} else {
+				ic.storeIdent(d, dbuf)
+			}
+			defer ic.putIdentBuf(dbuf)
+			idents[i] = dbuf
+		}
+	} else {
+		for i, d := range deps {
+			res, ok := inputs[d]
+			if !ok {
+				return InvalidLookupError(ic.Ident(d).Value())
+			}
+
+			dbuf := ic.getIdentBuf()
 			binary.LittleEndian.PutUint64(dbuf[:], uint64(d.Kind()))
-			*(*ID)(dbuf[wordSize:]) = did.Value()
-		} else {
-			ic.storeIdent(d, dbuf)
+			*(*ID)(dbuf[wordSize:]) = res.checksum.Value()
+			defer ic.putIdentBuf(dbuf)
+			idents[i] = dbuf
 		}
-		defer ic.putIdentBuf(dbuf)
-		idents[i] = dbuf
 	}
 	slices.SortFunc(idents, func(a, b *extIdent) int {
 		return bytes.Compare(a[:], b[:])
@@ -244,7 +280,7 @@ func (ic *irCache) Encode(w io.Writer, a Artifact) (err error) {
 	}
 
 	func() {
-		i := IContext{ic, w}
+		i := IContext{ic, w, inputs}
 
 		defer panicToError(&err)
 		defer func() { i.ic, i.w = nil, nil }()