Skip to content

feat(enrichment): categorize the full binary inventory as assets #3497

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
davion-knight wants to merge 1 commit into from
Closed

feat(enrichment): categorize the full binary inventory as assets #3497

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 6 additions & 5 deletions review-enrichment/src/analysis-context.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,7 @@ import {
} from "./external-fetch.js";
import { isWorkflowPath } from "./workflow-path.js";
import { isSupportedLockfile } from "./lockfile-path.js";
import { BINARY_EXT_RE } from "./analyzers/binary-extensions.js";

type ChangedFile = NonNullable<EnrichRequest["files"]>[number];

Expand Down Expand Up @@ -448,11 +449,11 @@ function categorizeFile(path: string): FileCategory {
) {
return { path, extension, category: "docs" };
}
if (
[".png", ".jpg", ".jpeg", ".gif", ".webp", ".svg", ".pdf", ".zip", ".gz", ".zst"].includes(
extension,
)
) {
// Binary assets — delegate to the shared binary-extension inventory (used by asset-weight/provenance) rather
// than a narrow hand-listed set, so media/fonts/archives/model weights (mp4, woff2, wasm, safetensors, …)
// categorize as assets instead of falling through to `source`. `.svg` is text (not in the binary inventory)
// but is still an asset for categorization, so it is kept explicitly.
if (BINARY_EXT_RE.test(path) || extension === ".svg") {
return { path, extension, category: "asset" };
}
if (extension) return { path, extension, category: "source" };
Expand Down
30 changes: 30 additions & 0 deletions review-enrichment/test/analysis-context.test.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -570,6 +570,36 @@ test("createAnalysisContext classifies long-form doc extensions as docs", () =>
);
});

test("createAnalysisContext categorizes the full binary inventory as assets", () => {
const context = createAnalysisContext({
repoFullName: "JSONbored/gittensory",
prNumber: 3359,
files: [
// Binaries beyond the original narrow image/archive list — now recognized via the shared inventory.
{ path: "media/demo.mp4", patch: null, status: "added" },
{ path: "fonts/Inter.woff2", patch: null, status: "added" },
{ path: "vendor/lib.wasm", patch: null, status: "added" },
{ path: "models/llama.safetensors", patch: null, status: "added" },
// .svg is text but still an asset for categorization (kept explicitly).
{ path: "icons/logo.svg", patch: "@@ -1,0 +1,1 @@\n+<svg/>" },
// A real source file is unaffected.
{ path: "src/index.ts", patch: "@@ -1,0 +1,1 @@\n+export {};" },
],
});

assert.deepEqual(
context.fileCategories.map((file) => [file.path, file.category]),
[
["media/demo.mp4", "asset"],
["fonts/Inter.woff2", "asset"],
["vendor/lib.wasm", "asset"],
["models/llama.safetensors", "asset"],
["icons/logo.svg", "asset"],
["src/index.ts", "source"],
],
);
});

test("createAnalysisContext classifies lockfile paths case-insensitively", () => {
const context = createAnalysisContext({
repoFullName: "JSONbored/gittensory",
Expand Down
Loading