External/SnapOtter
1
0
Fork 0
mirror of https://github.com/snapotter-hq/SnapOtter.git synced 2026-08-03 07:46:42 +02:00
Code Issues Packages Projects Releases Wiki Activity

test(qa): decode subtitle output as text in the sweep oracle (#704)

Browse Source 
The canonical lane classified .srt/.vtt/.ass artifacts served as
application/octet-stream as binary and passed them on a 16-byte floor, so
auto-subtitles and extract-subtitles only proved their output was
non-trivial, not that it was a real subtitle. classify() already keys
several formats off the filename extension; extend the text branch the same
way so these decode as text and the oracle asserts real content.

Verified on a live v2.2.0 container: auto-subtitles now reports
'text 180chars 8lines' and extract-subtitles 'text 101chars 9lines' (both
were binary no-signature), still passing, and an empty subtitle would now
fail as whitespace-only instead of sliding through.
This commit is contained in:
SnapOtter
2026-07-31 16:05:29 +08:00
committed by GitHub
parent 447190afda
commit d88031ac0f
1 changed files with 9 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/qa/lib/oracles.ts
+9
View File
@@ -100,6 +100,14 @@ export function detectSignature(data: Buffer): string | null {
const IMAGE_SIGNATURES = new Set(["PNG", "JPEG", "GIF", "BMP", "TIFF-LE", "TIFF-BE", "ICO", "PSD"]); const IMAGE_SIGNATURES = new Set(["PNG", "JPEG", "GIF", "BMP", "TIFF-LE", "TIFF-BE", "ICO", "PSD"]);
const MEDIA_SIGNATURES = new Set(["ISOBMFF", "MATROSKA", "OGG", "FLAC", "ID3", "MP3", "RIFF"]); const MEDIA_SIGNATURES = new Set(["ISOBMFF", "MATROSKA", "OGG", "FLAC", "ID3", "MP3", "RIFF"]);
/**
* Plain-text formats a tool may serve as application/octet-stream, so the
* content-type check below misses them and they fall through to "binary".
* Subtitles are the ones that reach here without a text/* type; decoding them
* as text asserts real content instead of passing on a byte-count floor.
*/
const TEXT_EXTS = new Set([".srt", ".vtt", ".ass", ".txt"]);
function classify(data: Buffer, filename: string, contentType: string): OutputKind { function classify(data: Buffer, filename: string, contentType: string): OutputKind {
if (data.length === 0) return "empty"; if (data.length === 0) return "empty";
const ct = contentType.split(";")[0].trim().toLowerCase(); const ct = contentType.split(";")[0].trim().toLowerCase();
@@ -120,6 +128,7 @@ function classify(data: Buffer, filename: string, contentType: string): OutputKi
if (signature === "ISOBMFF" || signature === "MATROSKA") return "video"; if (signature === "ISOBMFF" || signature === "MATROSKA") return "video";
if (signature && MEDIA_SIGNATURES.has(signature)) return "audio"; if (signature && MEDIA_SIGNATURES.has(signature)) return "audio";
if (ct.startsWith("text/") || ct.includes("xml") || ct.includes("markdown")) return "text"; if (ct.startsWith("text/") || ct.includes("xml") || ct.includes("markdown")) return "text";
if (TEXT_EXTS.has(ext)) return "text";
return "binary"; return "binary";
} }