mirror of
https://github.com/garrytan/gbrain.git
synced 2026-08-17 10:22:34 +00:00
Compare commits
1
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
97ddee0548 |
@@ -20,14 +20,6 @@ export const CJK_SLUG_CHARS = '一-鿿-ゟ゠-ヿ가-';
|
||||
|
||||
export const CJK_RANGES_REGEX = new RegExp(`[${CJK_SLUG_CHARS}]`);
|
||||
|
||||
/**
|
||||
* Page-slug segment grammar (no anchors): alnum-or-CJK lead char, then
|
||||
* alnum/CJK/hyphen continuation. Single source for validatePageSlug
|
||||
* (operations.ts), SlugRegistry's SLUG_RE, and the dream-cycle
|
||||
* SUMMARY_SLUG_RE so every slug validator shares one grammar (#738).
|
||||
*/
|
||||
export const PAGE_SLUG_SEG = `[a-z0-9${CJK_SLUG_CHARS}][a-z0-9${CJK_SLUG_CHARS}\\-]*`;
|
||||
|
||||
export const CJK_SENTENCE_DELIMITERS = ['。', '!', '?']; // 。!?
|
||||
export const CJK_CLAUSE_DELIMITERS = [';', ':', ',', '、']; // ;:,、
|
||||
|
||||
|
||||
@@ -43,11 +43,10 @@ import { serializeMarkdown, serializePageToMarkdown } from '../markdown.ts';
|
||||
import type { Page, PageType } from '../types.ts';
|
||||
import { validateSourceId } from '../utils.ts';
|
||||
import { safeSplitIndex } from '../text-safe.ts';
|
||||
import { PAGE_SLUG_SEG } from '../cjk.ts';
|
||||
|
||||
// Slug grammar from validatePageSlug — shared via PAGE_SLUG_SEG (#738).
|
||||
// Slug regex from validatePageSlug — kept in sync.
|
||||
// Used for the orchestrator-written summary index slug.
|
||||
const SUMMARY_SLUG_RE = new RegExp(`^${PAGE_SLUG_SEG}(\\/${PAGE_SLUG_SEG})*$`);
|
||||
const SUMMARY_SLUG_RE = /^[a-z0-9][a-z0-9\-]*(\/[a-z0-9][a-z0-9\-]*)*$/;
|
||||
|
||||
// ── Model context budget (D1, D5, D7, D9) ─────────────────────────────
|
||||
|
||||
|
||||
@@ -25,7 +25,7 @@ import { bumpLastRetrievedAt } from './last-retrieved.ts';
|
||||
import { isSearchMode } from './search/mode.ts';
|
||||
import { stampEvidence } from './search/evidence.ts';
|
||||
import type { SearchResult } from './types.ts';
|
||||
import { CJK_SLUG_CHARS, PAGE_SLUG_SEG } from './cjk.ts';
|
||||
import { CJK_SLUG_CHARS } from './cjk.ts';
|
||||
import * as db from './db.ts';
|
||||
import { VERSION } from '../version.ts';
|
||||
import {
|
||||
@@ -162,6 +162,7 @@ export function validatePageSlug(slug: string): void {
|
||||
}
|
||||
// v0.32.7: CJK ranges (Han / Hiragana / Katakana / Hangul Syllables) allowed
|
||||
// in segments. ASCII shape rules (lead char, hyphen continuation) preserved.
|
||||
const PAGE_SLUG_SEG = `[a-z0-9${CJK_SLUG_CHARS}][a-z0-9${CJK_SLUG_CHARS}\\-]*`;
|
||||
if (!new RegExp(`^${PAGE_SLUG_SEG}(\\/${PAGE_SLUG_SEG})*$`, 'i').test(slug)) {
|
||||
throw new OperationError('invalid_params', `Invalid page_slug: ${slug} (allowed: alphanumeric, CJK, hyphens, forward-slash separated segments)`);
|
||||
}
|
||||
|
||||
@@ -17,7 +17,6 @@
|
||||
|
||||
import type { BrainEngine } from '../engine.ts';
|
||||
import type { PageType } from '../types.ts';
|
||||
import { PAGE_SLUG_SEG } from '../cjk.ts';
|
||||
|
||||
export interface CreateSlugInput {
|
||||
/**
|
||||
@@ -72,9 +71,7 @@ export class SlugRegistryError extends Error {
|
||||
// SlugRegistry
|
||||
// ---------------------------------------------------------------------------
|
||||
|
||||
// Shares the page-slug segment grammar (incl. CJK ranges, #738) with
|
||||
// validatePageSlug; keeps this site's dir/name shape (>= 2 segments).
|
||||
const SLUG_RE = new RegExp(`^${PAGE_SLUG_SEG}(\\/${PAGE_SLUG_SEG})+$`);
|
||||
const SLUG_RE = /^[a-z0-9][a-z0-9\-]*(\/[a-z0-9][a-z0-9\-]*)+$/;
|
||||
|
||||
export class SlugRegistry {
|
||||
constructor(private engine: BrainEngine) {}
|
||||
|
||||
@@ -18,6 +18,7 @@
|
||||
import type { BrainEngine } from '../engine.ts';
|
||||
import { loadActivePackBestEffort } from './best-effort.ts';
|
||||
import type { OperationContext } from '../operations.ts';
|
||||
import { isUndefinedTableError } from '../utils.ts';
|
||||
|
||||
export interface StatsOpts {
|
||||
/** Single source scope. Omit + omit sourceIds for whole-brain aggregate. */
|
||||
@@ -164,9 +165,17 @@ async function fetchCountRows(engine: BrainEngine, opts: StatsOpts): Promise<Raw
|
||||
`;
|
||||
try {
|
||||
return await engine.executeRaw<RawCountRow>(sql, params);
|
||||
} catch {
|
||||
// Empty / pre-init brain: pages table may not exist yet.
|
||||
return [];
|
||||
} catch (err) {
|
||||
// ONLY swallow the genuine "pages table doesn't exist yet" case
|
||||
// (empty / pre-init brain). #2466: the old bare `catch {}` masked
|
||||
// EVERY error — so any engine-level failure (connection, version
|
||||
// skew, a query incompatibility) was silently converted to 0 rows,
|
||||
// printing "Total pages: 0" on a populated brain and cascading into
|
||||
// false "100% coverage" + a starved `schema suggest`. Surface
|
||||
// everything that is not a missing-table error so the real failure
|
||||
// is visible instead of hidden behind a fake zero.
|
||||
if (isUndefinedTableError(err)) return [];
|
||||
throw err;
|
||||
}
|
||||
}
|
||||
|
||||
@@ -204,9 +213,11 @@ async function detectDeadPrefixes(
|
||||
if (cnt === 0) {
|
||||
hints.push({ type: t.name, prefix });
|
||||
}
|
||||
} catch {
|
||||
// Skip on engine error (no pages table yet, etc.).
|
||||
continue;
|
||||
} catch (err) {
|
||||
// #2466: only skip on the genuine "no pages table yet" case;
|
||||
// rethrow any other engine error so it isn't silently masked.
|
||||
if (isUndefinedTableError(err)) continue;
|
||||
throw err;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -86,12 +86,6 @@ describe('#2415: loadOutputRoot validation + patterns gather scope', () => {
|
||||
expect(await loadOutputRoot(engine)).toBe('wiki');
|
||||
});
|
||||
|
||||
test('CJK root passes the slug grammar (#738)', async () => {
|
||||
await engine.setConfig('dream.synthesize.output_root', '知识/笔记');
|
||||
expect(await loadOutputRoot(engine)).toBe('知识/笔记');
|
||||
await engine.setConfig('dream.synthesize.output_root', '');
|
||||
});
|
||||
|
||||
test('patterns phase gathers reflections under the configured root', async () => {
|
||||
await engine.setConfig('dream.synthesize.output_root', 'notes');
|
||||
for (let i = 0; i < 3; i++) {
|
||||
|
||||
@@ -222,6 +222,89 @@ describe('runStatsCore — JSON envelope shape', () => {
|
||||
});
|
||||
});
|
||||
|
||||
describe('runStatsCore — #2466 catch-narrowing (real count + error surfacing)', () => {
|
||||
// #2466: `gbrain schema stats` reported "Total pages: 0" on a populated
|
||||
// PGLite brain. The bug was a bare `catch {}` in fetchCountRows (and a
|
||||
// sibling in detectDeadPrefixes) that converted ANY engine error into 0
|
||||
// rows. The COUNT query itself is valid on PGLite (proven below), so the
|
||||
// regression pins two things: (a) a populated brain reports the real,
|
||||
// non-zero count through the full runStatsCore path; (b) a non-missing-
|
||||
// table engine error is rethrown, not masked into a fake zero.
|
||||
|
||||
it('reports the real non-zero count on a populated PGLite brain (no false 0)', async () => {
|
||||
await withEnv({ GBRAIN_SCHEMA_PACK: undefined }, async () => {
|
||||
// Seed a realistic mix: typed, untyped, multiple types — like the
|
||||
// 169-page brain in the bug report (scaled down).
|
||||
for (let i = 0; i < 12; i++) {
|
||||
const type = i % 3 === 0 ? '' : (i % 3 === 1 ? 'person' : 'company');
|
||||
await seedPage(`notes/p${i}`, { type, sourcePath: `notes/p${i}.md` });
|
||||
}
|
||||
const result = await runStatsCore(ctxOf());
|
||||
// The core regression: NOT zero.
|
||||
expect(result.aggregate.total_pages).toBe(12);
|
||||
expect(result.aggregate.typed_pages).toBe(8);
|
||||
expect(result.aggregate.untyped_pages).toBe(4);
|
||||
// And coverage is the honest ratio, not the vacuous 1.0 a 0/0 prints.
|
||||
expect(result.aggregate.coverage).not.toBe(1.0);
|
||||
});
|
||||
});
|
||||
|
||||
it('fetchCountRows rethrows a non-missing-table engine error instead of masking it as 0 pages', async () => {
|
||||
await withEnv({ GBRAIN_SCHEMA_PACK: undefined }, async () => {
|
||||
// No pack → detectDeadPrefixes is skipped, isolating the throw to the
|
||||
// fetchCountRows catch we narrowed. The count query (the GROUP BY one)
|
||||
// throws a column-level error (SQLSTATE 42703) — the exact class the
|
||||
// old bare `catch {}` swallowed into 0 rows; everything else succeeds.
|
||||
__setPackLocatorForTests(() => null);
|
||||
const boom = Object.assign(new Error('column "type" does not exist'), { code: '42703' });
|
||||
const stubEngine = {
|
||||
executeRaw: async (sql: string) => {
|
||||
if (/GROUP BY source_id/.test(sql)) throw boom; // the fetchCountRows query
|
||||
return [];
|
||||
},
|
||||
} as unknown as PGLiteEngine;
|
||||
const ctx = { ...ctxOf(), engine: stubEngine } as unknown as OperationContext;
|
||||
await expect(runStatsCore(ctx)).rejects.toThrow('column "type" does not exist');
|
||||
});
|
||||
});
|
||||
|
||||
it('fetchCountRows still degrades to empty (no throw) on a genuine missing pages table', async () => {
|
||||
await withEnv({ GBRAIN_SCHEMA_PACK: undefined }, async () => {
|
||||
// Pre-init brain shape: the count query hits a missing pages table
|
||||
// (SQLSTATE 42P01). This is the ONLY case the narrowed catch swallows.
|
||||
__setPackLocatorForTests(() => null);
|
||||
const missing = Object.assign(new Error('relation "pages" does not exist'), { code: '42P01' });
|
||||
const stubEngine = {
|
||||
executeRaw: async (sql: string) => {
|
||||
if (/GROUP BY source_id/.test(sql)) throw missing;
|
||||
return [];
|
||||
},
|
||||
} as unknown as PGLiteEngine;
|
||||
const ctx = { ...ctxOf(), engine: stubEngine } as unknown as OperationContext;
|
||||
const result = await runStatsCore(ctx);
|
||||
expect(result.aggregate.total_pages).toBe(0);
|
||||
expect(result.per_source).toEqual([]);
|
||||
});
|
||||
});
|
||||
|
||||
it('detectDeadPrefixes rethrows a non-missing-table error (sibling catch)', async () => {
|
||||
await withEnv({ GBRAIN_HOME: tmpDir, GBRAIN_SCHEMA_PACK: 'tiny' }, async () => {
|
||||
seedTinyPack('tiny', [{ name: 'person', prefix: 'people/' }]);
|
||||
// fetchCountRows (the GROUP BY query) succeeds → []; the per-prefix
|
||||
// dead-prefix LIKE query then throws a non-missing-table error, which
|
||||
// must surface through the narrowed sibling catch.
|
||||
const stubEngine = {
|
||||
executeRaw: async (sql: string) => {
|
||||
if (/GROUP BY source_id/.test(sql)) return []; // count query: empty brain, fine
|
||||
throw Object.assign(new Error('division by zero'), { code: '22012' }); // the LIKE query
|
||||
},
|
||||
} as unknown as PGLiteEngine;
|
||||
const ctx = { ...ctxOf(), engine: stubEngine } as unknown as OperationContext;
|
||||
await expect(runStatsCore(ctx)).rejects.toThrow('division by zero');
|
||||
});
|
||||
});
|
||||
});
|
||||
|
||||
describe('runStatsCore — type/untyped split', () => {
|
||||
it('treats empty-string type as untyped (not its own bucket)', async () => {
|
||||
await withEnv({ GBRAIN_SCHEMA_PACK: undefined }, async () => {
|
||||
|
||||
@@ -203,17 +203,6 @@ describe('SlugRegistry', () => {
|
||||
})).rejects.toThrow(SlugRegistryError);
|
||||
});
|
||||
|
||||
test('create accepts CJK slugs (#738)', async () => {
|
||||
const reg = new SlugRegistry(engine);
|
||||
const r = await reg.create({
|
||||
desiredSlug: '知识/品牌圣经',
|
||||
displayName: '品牌圣经',
|
||||
type: 'note',
|
||||
});
|
||||
expect(r.slug).toBe('知识/品牌圣经');
|
||||
expect(r.exact).toBe(true);
|
||||
});
|
||||
|
||||
test('create throws on invalid slug', async () => {
|
||||
const reg = new SlugRegistry(engine);
|
||||
await expect(reg.create({
|
||||
|
||||
Reference in New Issue
Block a user