pipeline: reject resref collisions when chunking; document erf post-write hashing (#8)
## What Two correctness fixes surfaced in review of the direct-depot HAK artifact work. ### Reject resref+type collisions in `chunksFromManifest` A manifest can name two distinct source paths that collapse to the same `resref+type` (e.g. `creature/foo.tga` and `placeable/foo.tga` — resref is the lowercase basename minus extension). The ERF writer keys resources on `Name:Type`, so the second silently shadowed the first: an asset would vanish from the packed HAK with no error. `chunksFromManifest` now runs `ensureUniqueChunkResources` per chunk and fails the build on a duplicate. This guards **both** build paths — the legacy `--source-manifest` flow and the direct content-addressed flow (`chunksFromSourceManifest` → `chunksFromManifest`). ### Document erf post-write hash coupling `writeResourceData` streams the source into the output while hashing, so size/SHA mismatches are only detected *after* the bytes are written. A non-nil return therefore means the writer holds partial, unverified output and the caller must discard it. Added a comment making that contract explicit; `writeHAKArchive` already honours it (writes to a temp file, removes on any Write error, never renames a bad archive into place). ## Tests - `TestChunksFromManifestRejectsResrefCollision`: collision → error, distinct resrefs → clean. Asserts only error presence/absence — silent asset loss is the contract, not any specific wording. - `go vet ./internal/erf/ ./internal/pipeline/` clean. - `go test ./internal/erf/ ./internal/pipeline/` green. ## Follow-up A new crucible release must be cut after this merges so the guard ships in the binary `sow-assets-manifest` pins. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Reviewed-on: #8 Co-authored-by: vickydotbat <vickydotbat@tutamail.com> Co-committed-by: vickydotbat <vickydotbat@tutamail.com>
This commit was merged in pull request #8.
This commit is contained in:
@@ -6,6 +6,7 @@ import (
|
||||
"testing"
|
||||
|
||||
"git.westgate.pw/ShadowsOverWestgate/sow-tools/internal/buildinfo"
|
||||
"git.westgate.pw/ShadowsOverWestgate/sow-tools/internal/erf"
|
||||
)
|
||||
|
||||
const validAsset = "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa"
|
||||
@@ -141,6 +142,32 @@ func TestValidateDirectSourceManifestRejectsBuilderMismatch(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
// Two distinct source paths can collapse to the same resref+type; the chunker
|
||||
// must reject that rather than let one silently shadow the other in the ERF.
|
||||
func TestChunksFromManifestRejectsResrefCollision(t *testing.T) {
|
||||
tga, ok := erf.HAKResourceTypeForExtension("tga")
|
||||
if !ok {
|
||||
t.Fatal("tga is not a hak resource type")
|
||||
}
|
||||
mk := func(rel, resref string) assetResource {
|
||||
r := erf.Resource{Name: resref, Type: tga}
|
||||
return assetResource{Rel: rel, Resource: r, Size: erf.ArchiveSize([]erf.Resource{r})}
|
||||
}
|
||||
entry := BuildManifestHAK{Name: "core_01", Group: "core"}
|
||||
|
||||
collide := []assetResource{mk("creature/foo.tga", "foo"), mk("placeable/foo.tga", "foo")}
|
||||
entry.Assets = []string{"creature/foo.tga", "placeable/foo.tga"}
|
||||
if _, err := chunksFromManifest(collide, []BuildManifestHAK{entry}); err == nil {
|
||||
t.Fatal("expected resref+type collision rejection")
|
||||
}
|
||||
|
||||
distinct := []assetResource{mk("creature/foo.tga", "foo"), mk("placeable/bar.tga", "bar")}
|
||||
entry.Assets = []string{"creature/foo.tga", "placeable/bar.tga"}
|
||||
if _, err := chunksFromManifest(distinct, []BuildManifestHAK{entry}); err != nil {
|
||||
t.Fatalf("distinct resrefs should pack cleanly: %v", err)
|
||||
}
|
||||
}
|
||||
|
||||
func TestContentAddressedBlobPath(t *testing.T) {
|
||||
root := "/var/cache/blobs"
|
||||
got, err := contentAddressedBlobPath(root, validAsset)
|
||||
|
||||
Reference in New Issue
Block a user