admin/gbrain
1
0
Fork 0
mirror of https://github.com/garrytan/gbrain.git synced 2026-07-27 22:15:33 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(extract): link-aware Source — Summary delimiter in timeline bullets

Browse Source 
Takeover of #3060: a bare hyphen inside a markdown link target (e.g.
../people/alice-example.md) matched the old delimiter regex and shattered
one timeline entry into two fragments that re-inserted on every sync. The
delimiter search is now link-aware (whitespace-flanked dash outside
bracket/paren spans); delimiterless bullets are kept whole under the
'markdown' source label. Repaired from the original PR: real-person
fixtures in test/extract.test.ts renamed to privacy-rule placeholders.

Co-authored-by: wright-io <wright-io@users.noreply.github.com>
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Garry Tan
2026-07-23 10:56:28 -07:00
co-authored by wright-io Claude Fable 5
parent e79b8d5780
commit 2d9f4ec243
2 changed files with 89 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/commands/extract.ts
+40 -2
View File
@@ -469,15 +469,53 @@ export async function extractLinksFromFile(
// --- Timeline extraction ---
/**
* Index of the first dash (—, –, -) that can serve as the Source — Summary
* delimiter: it must have whitespace on both sides and sit outside every
* markdown-link span. Hyphens inside link targets
* (`../people/alice-example.md`) and dashes inside link labels
* (`[Deals — Q1 Review](...)`) are content, not delimiters — splitting on
* them shatters one entry into two fragments whose halves re-insert on
* every sync (the (page_id, date, summary, source) uniqueness sees each
* fragment shape as a new row). Returns -1 when the line has no delimiter.
*/
function findDelimiterOutsideLinks(text: string): number {
let depth = 0;
for (let i = 0; i < text.length; i++) {
const c = text[i];
if (c === '[' || c === '(') depth++;
else if (c === ']' || c === ')') { if (depth > 0) depth--; }
else if (
depth === 0 &&
(c === '—' || c === '–' || c === '-') &&
i > 0 && /\s/.test(text[i - 1]) &&
i + 1 < text.length && /\s/.test(text[i + 1])
) {
return i;
}
}
return -1;
}
/** Extract timeline entries from markdown content */
export function extractTimelineFromContent(content: string, slug: string): ExtractedTimelineEntry[] {
const entries: ExtractedTimelineEntry[] = [];
// Format 1: Bullet — - **YYYY-MM-DD** | Source — Summary
const bulletPattern = /^-\s+\*\*(\d{4}-\d{2}-\d{2})\*\*\s*\|\s*(.+?)\s*[—–-]\s*(.+)$/gm;
// The delimiter search is link-aware (see findDelimiterOutsideLinks); a
// bullet with no delimiter (e.g. an auto-generated backlink line
// `- **date** | Referenced in [X](y.md)`) is kept whole as the summary
// rather than dropped or fragmented.
const bulletPattern = /^-\s+\*\*(\d{4}-\d{2}-\d{2})\*\*\s*\|\s*(.+)$/gm;
let match;
while ((match = bulletPattern.exec(content)) !== null) {
entries.push({ slug, date: match[1], source: match[2].trim(), summary: match[3].trim() });
const rest = match[2].trim();
const at = findDelimiterOutsideLinks(rest);
if (at >= 0) {
entries.push({ slug, date: match[1], source: rest.slice(0, at).trim(), summary: rest.slice(at + 1).trim() });
} else {
entries.push({ slug, date: match[1], source: 'markdown', summary: rest });
}
}
// Format 2: Header — ### YYYY-MM-DD — Title
test/extract.test.ts
+49 -17
View File
@@ -8,11 +8,11 @@ import {
describe('extractMarkdownLinks', () => {
it('extracts relative markdown links', () => {
const content = 'Check [Pedro](../people/pedro-franceschi.md) and [Brex](../../companies/brex.md).';
const content = 'Check [Alice](../people/alice-example.md) and [Acme](../../companies/acme-example.md).';
const links = extractMarkdownLinks(content);
expect(links).toHaveLength(2);
expect(links[0].name).toBe('Pedro');
expect(links[0].relTarget).toBe('../people/pedro-franceschi.md');
expect(links[0].name).toBe('Alice');
expect(links[0].relTarget).toBe('../people/alice-example.md');
});
it('skips external URLs ending in .md', () => {
@@ -34,12 +34,12 @@ describe('extractMarkdownLinks', () => {
describe('extractLinksFromFile', () => {
it('resolves relative paths to slugs', async () => {
const content = '---\ntitle: Test\n---\nSee [Pedro](../people/pedro.md).';
const allSlugs = new Set(['people/pedro', 'deals/test-deal']);
const content = '---\ntitle: Test\n---\nSee [Alice](../people/alice.md).';
const allSlugs = new Set(['people/alice', 'deals/test-deal']);
const links = await extractLinksFromFile(content, 'deals/test-deal.md', allSlugs);
expect(links.length).toBeGreaterThanOrEqual(1);
expect(links[0].from_slug).toBe('deals/test-deal');
expect(links[0].to_slug).toBe('people/pedro');
expect(links[0].to_slug).toBe('people/alice');
});
it('skips links to non-existent pages', async () => {
@@ -50,15 +50,15 @@ describe('extractLinksFromFile', () => {
});
it('extracts frontmatter company links (v0.13, includeFrontmatter opt-in)', async () => {
const content = '---\ncompany: brex\ntype: person\n---\nContent.';
const content = '---\ncompany: acme-example\ntype: person\n---\nContent.';
// v0.13 canonical: person page with company: X → person → company works_at (outgoing).
// Resolver needs companies/brex to exist in allSlugs to emit the edge.
const allSlugs = new Set(['people/test', 'companies/brex']);
// Resolver needs companies/acme-example to exist in allSlugs to emit the edge.
const allSlugs = new Set(['people/test', 'companies/acme-example']);
const links = await extractLinksFromFile(content, 'people/test.md', allSlugs, { includeFrontmatter: true });
const companyLinks = links.filter(l => l.link_type === 'works_at');
expect(companyLinks.length).toBeGreaterThanOrEqual(1);
expect(companyLinks[0].from_slug).toBe('people/test');
expect(companyLinks[0].to_slug).toBe('companies/brex');
expect(companyLinks[0].to_slug).toBe('companies/acme-example');
});
it('extracts frontmatter investors array (v0.13: incoming direction)', async () => {
@@ -79,22 +79,22 @@ describe('extractLinksFromFile', () => {
it('frontmatter extraction is default OFF (back-compat)', async () => {
// Without includeFrontmatter, fs-source no longer auto-extracts frontmatter.
// Matches db-source behavior. User opts in with --include-frontmatter flag.
const content = '---\ncompany: brex\ntype: person\n---\nContent.';
const allSlugs = new Set(['people/test', 'companies/brex']);
const content = '---\ncompany: acme-example\ntype: person\n---\nContent.';
const allSlugs = new Set(['people/test', 'companies/acme-example']);
const links = await extractLinksFromFile(content, 'people/test.md', allSlugs);
expect(links).toEqual([]);
});
it('infers link type from directory structure', async () => {
const content = 'See [Brex](../companies/brex.md).';
const allSlugs = new Set(['people/pedro', 'companies/brex']);
const links = await extractLinksFromFile(content, 'people/pedro.md', allSlugs);
const content = 'See [Acme](../companies/acme-example.md).';
const allSlugs = new Set(['people/alice', 'companies/acme-example']);
const links = await extractLinksFromFile(content, 'people/alice.md', allSlugs);
expect(links[0].link_type).toBe('works_at');
});
it('infers deal_for type for deals -> companies', async () => {
const content = 'See [Brex](../companies/brex.md).';
const allSlugs = new Set(['deals/seed', 'companies/brex']);
const content = 'See [Acme](../companies/acme-example.md).';
const allSlugs = new Set(['deals/seed', 'companies/acme-example']);
const links = await extractLinksFromFile(content, 'deals/seed.md', allSlugs);
expect(links[0].link_type).toBe('deal_for');
});
@@ -136,6 +136,38 @@ describe('extractTimelineFromContent', () => {
expect(entries).toHaveLength(1);
});
it('does not split on hyphens inside markdown link targets', () => {
const content = `- **2025-03-18** | Referenced in [Alice](../people/alice-example.md)`;
const entries = extractTimelineFromContent(content, 'companies/acme-example');
expect(entries).toHaveLength(1);
expect(entries[0].source).toBe('markdown');
expect(entries[0].summary).toBe('Referenced in [Alice](../people/alice-example.md)');
});
it('does not split on spaced dashes inside link labels', () => {
const content = `- **2025-03-18** | Referenced in [Deals — Q1 Review](../deals/q1-review.md)`;
const entries = extractTimelineFromContent(content, 'companies/acme-example');
expect(entries).toHaveLength(1);
expect(entries[0].source).toBe('markdown');
expect(entries[0].summary).toBe('Referenced in [Deals — Q1 Review](../deals/q1-review.md)');
});
it('splits on the first spaced dash outside links', () => {
const content = `- **2025-03-18** | [Board notes](../meetings/2025-03-18-board.md) — Approved the hire`;
const entries = extractTimelineFromContent(content, 'test');
expect(entries).toHaveLength(1);
expect(entries[0].source).toBe('[Board notes](../meetings/2025-03-18-board.md)');
expect(entries[0].summary).toBe('Approved the hire');
});
it('keeps delimiterless bullet lines whole instead of dropping them', () => {
const content = `- **2025-03-18** | Imported from legacy tracker`;
const entries = extractTimelineFromContent(content, 'test');
expect(entries).toHaveLength(1);
expect(entries[0].source).toBe('markdown');
expect(entries[0].summary).toBe('Imported from legacy tracker');
});
it('extracts inline citation format entries', () => {
const content = `Closed the seed round with fund-a leading. [Source: board meeting notes, 2025-04-02]`;
const entries = extractTimelineFromContent(content, 'deals/acme-seed');