apunkt/SurfSense
1
0
Fork 0
mirror of https://github.com/MODSetter/SurfSense.git synced 2026-07-26 23:51:14 +02:00
Code Issues Projects Releases Packages Wiki Activity

feat: parse run citation tokens

Browse source
This commit is contained in:
CREDO23 2026-07-22 19:35:04 +02:00
parent dd5d267056
commit 57d6182ca3
1 changed files with 7 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

10
surfsense_web/lib/citations/citation-parser.ts
View file

@ -11,18 +11,20 @@ import { FENCED_OR_INLINE_CODE } from "@/lib/markdown/code-regions";
/**
* Matches `[citation:...]` with numeric IDs (incl. negative, doc- prefix,
* comma-separated), URL-based IDs from live web search, or `urlciteN`
* placeholders produced by `preprocessCitationMarkdown`.
* comma-separated), URL-based IDs from live web search, `urlciteN`
* placeholders produced by `preprocessCitationMarkdown`, or a scraper-run
* handle (`run_<uuid>`).
*
* Also matches Chinese brackets 【】 and zero-width spaces that LLMs
* sometimes emit.
*/
export const CITATION_REGEX =
/[[【]\u200B?citation:\s*(https?:\/\/[^\]】\u200B]+|urlcite\d+|(?:doc-)?-?\d+(?:\s*,\s*(?:doc-)?-?\d+)*)\s*\u200B?[\]】]/g;
/[[【]\u200B?citation:\s*(https?:\/\/[^\]】\u200B]+|urlcite\d+|run_[0-9a-fA-F-]+|(?:doc-)?-?\d+(?:\s*,\s*(?:doc-)?-?\d+)*)\s*\u200B?[\]】]/g;
/** A single parsed citation reference. */
export type CitationToken =
| { kind: "url"; url: string }
| { kind: "run"; runId: string }
| { kind: "chunk"; chunkId: number; isDocsChunk: boolean };
/** Output of `parseTextWithCitations` — interleaved text + citation tokens. */
@ -102,6 +104,8 @@ export function parseTextWithCitations(text: string, urlMap: CitationUrlMap): Pa
if (url) {
segments.push({ kind: "url", url });
}
} else if (captured.startsWith("run_")) {
segments.push({ kind: "run", runId: captured.trim() });
} else {
const rawIds = captured.split(",").map((s) => s.trim());
for (const rawId of rawIds) {