tben
d3357cb7df
`text_content` is an extracted-text cache, but nothing stopped it from
holding a dump of bytes:
- `fileToText` ended its switch with `default: return buffer.toString("utf-8")`
and defaulted a missing extension to "txt", so any binary was decoded.
- Both extraction callers gated on `media_type == "document"`, and
`attachmentFileKind` classes everything non-image/audio/video as a
document: an SVG, a zip, a spreadsheet, a .bin.
- Nothing capped the length, so a 20 MB attachment could leave 20 MB of
text in the database.
- `storeChatAttachments` copied the text onto a second `media` row, and
`SELECT m.*` pulled the column into page props and API responses.
On a real install an SVG held 6852 characters of markup and a
`.designcraft` file held 142 KB of raw bytes.
Changes:
- `file-to-text.ts` lists the text extensions explicitly and returns
undefined for anything else; no extension is no text.
- `can-extract-text.ts` is the one allowlist (reusing
`BotTextFileExtensions`), used by both upload routes and by
`uploadAndRecordMedia`; `extension-of.ts` is shared with the storage
catalog instead of duplicated.
- `BotAttachmentTextStoreMaxChars` (200k) caps the column via
`cap-text-content.ts`.
- `store-chat-attachments.ts` no longer copies the text; ingestion
re-reads the bytes once.
- `media-columns.ts` selects every media column but `text_content`, which
now has to be asked for (`grab-messages-media`'s reply path and
ingestion do); the media CRUD routes sanitize rows they write.
- `ingest-bot-file.ts` decides on size alone, since a cached slice made
an oversized file look already read.
- `bun run media:prune-text` cleans rows that were already stored
(rerunnable, with a VACUUM hint).
Verified on the dev database: both bad rows cleared (146 KB), rerun
reports nothing to do.
32 lines
1008 B
TypeScript
32 lines
1008 B
TypeScript
import { AppData } from "@/src/data/app-data";
|
|
|
|
type Params = {
|
|
/**
|
|
* The text extracted from a file.
|
|
*/
|
|
text: string;
|
|
};
|
|
|
|
/**
|
|
* Extracted document text, cut to what the `media` row keeps
|
|
* (`AppData.BotAttachmentTextStoreMaxChars`) with a line saying so.
|
|
*
|
|
* The column is a cache, not a copy of the file: a 20 MB document would
|
|
* otherwise put 20 MB of text into the database, and no reader takes more
|
|
* than a slice of it anyway.
|
|
*/
|
|
export default function capTextContent({ text }: Params) {
|
|
const max = AppData.BotAttachmentTextStoreMaxChars;
|
|
|
|
if (text.length <= max) return text;
|
|
|
|
const note = `\n\n[Truncated: this document is ${text.length} characters long, so only its beginning was kept. Read the file itself for the rest.]`;
|
|
/**
|
|
* The note counts against the ceiling too: the column is capped, not
|
|
* the text plus whatever was appended to it.
|
|
*/
|
|
const kept = Math.max(0, max - note.length);
|
|
|
|
return `${text.slice(0, kept)}${note}`;
|
|
}
|