ktx/packages/cli/src/connectors/bigquery/dialect.ts

206 lines
6.2 KiB
TypeScript
Raw Normal View History

import type { KtxDialect } from '../../context/connections/dialects.js';
import {
columnDisplayPartCount,
formatDialectDisplayRef,
formatDialectTableName,
limitOffsetClause,
parseDialectDisplayRef,
} from '../../context/connections/dialect-helpers.js';
chore(workspace): gate dead-code with knip production mode (#196) * refactor(workspace): relocate @ktx/llm source into packages/cli/src/llm * refactor(workspace): rewrite @ktx/llm imports to relative paths * refactor(workspace): fold internal packages into cli * chore(workspace): gate dead-code with knip production mode Turn on production-mode knip plus an autofix run in pre-commit and the `pnpm dead-code` script, document the `/** @internal */` convention for test-only exports in AGENTS.md, annotate test-only exports across the CLI with that JSDoc, and drop dead exports/wrappers the new gate surfaced (e.g. `cli-project.ts`, `lookerRuntimeSourceToFileAdapterSource`, `createLocalScanEnrichmentProvidersFromConfig`, `PGLITE_OWNER_PROCESS_BACKEND_CAPABILITIES`, stale type re-exports). Replace the loose `ignoreIssues` allowlist in `knip.json` with explicit production entries so cross-package barrel leaks are caught. * refactor(cli): delete internal barrel index.ts files The 34 `index.ts` re-export barrels inside `packages/cli/src/` were holdovers from the pre-fold multi-workspace structure. Post-fold-in they served no production purpose: external consumers go through the single package main entry, and in-repo callers mostly imported through them only because the path was short. Internally, knip flagged most barrel re-exports as production-dead (only reached via tests). This change: - Deletes every internal barrel except `packages/cli/src/index.ts` (the published package entry). - Rewrites ~270 source/test files to import each name directly from the file that defines it. - Moves `tools/warehouse-verification/index.ts` to `create-warehouse-verification-tools.ts` (the function it defined locally) and updates its single consumer. - Renames `search/backend-conformance.ts` → `.test-utils.ts` to match the existing test-helper file convention. - Deletes 13 dead test-only chains (dbt-descriptions/*, live-database/extracted-schema, live-database/structural-sync, relationship-* feedback/review chain) plus their tests and a cascading orphan integration test. - Updates test mocks that pointed at deleted barrel paths (notion-client, connector barrels in scan/local-scan-connectors tests) to mock the source files instead. - Points the maintainer benchmark script (`scripts/relationship-benchmark-report.mjs`) at source files instead of `dist/context/scan/index.js`. - Drops the barrel `!` entries from `knip.json`; adds explicit production entries only for the benchmark code reached via dist by the maintainer script. Net: 413 files changed, ~1.2k insertions, ~9.4k deletions. `pnpm run dead-code` (Biome + knip default + knip production) and `pnpm run type-check` are clean; 2277 tests pass. * refactor(workspace): rename @ktx/cli to @kaelio/ktx and pack it directly Promote the CLI workspace package to the public name `@kaelio/ktx` and drop the separate `scripts/build-public-npm-package.mjs` wrapper. The CLI package is now publishable in place (`publishConfig.access: public`, `provenance: true`), so artifact packing uses `pnpm pack` against `packages/cli/` instead of assembling a parallel package tree. Updates all workspace filter invocations, docs, tests, and release readiness checks to reference the new package name, and folds the tarball-name helper into `scripts/public-npm-release-metadata.mjs`. * docs: align "agent clients" and "data agents" terminology Replace "client agents" with "agent clients" and "database agents" with "data agents" across AGENTS.md, README.md, the docs-site copy, and the matching setup-agents test description, matching the canonical vocabulary in docs/terminology.md. Also moves packages/cli/tsconfig.json's tsBuildInfoFile from node_modules/.cache/ to dist/.tsbuildinfo so incremental builds survive node_modules reinstalls. * refactor(release): single source of truth for package version Make packages/cli/package.json the single source of truth for the @kaelio/ktx version. publicNpmPackageVersion() now reads it directly, so artifact filenames, release-readiness checks, and the Python wheel version all derive from one field. The duplicate release-policy.json.publicNpmPackageVersion is removed. Previously the two fields could drift: tarballs were named kaelio-ktx-0.4.1.tgz while internally containing @kaelio/ktx@0.0.0-private. - update-public-release-version.mjs rewrites both Python pyproject.toml files (ktx-daemon, ktx-sl) alongside the npm package.jsons, normalizing the version for PEP 440 (e.g. 0.1.0-rc.2 -> 0.1.0rc2). - semantic-release-config.cjs adds the two pyproject.toml files to @semantic-release/git assets so the release commit back to main carries every version source in lockstep. - The six "?? '0.0.0-private'" fallback literals across the CLI are replaced with "?? getKtxCliPackageInfo().version", and createDefaultKtxMcpServer makes its version arg required. - docs/release.md describes the actual commit-back model: the dev tree always reflects the most recent release; no sentinel pin to maintain. Verified: pnpm run artifacts:build now produces kaelio-ktx-0.4.1.tgz and kaelio_ktx-0.4.1-py3-none-any.whl with @kaelio/ktx@0.4.1 inside. Full type-check, dead-code, and 2287 vitests + 173 script tests pass. * refactor(cli): inject embedding provider resolution and detect sentence-transformers runtime Make resolveProjectEmbeddingProvider and runtimeIo injectable in ingest and scan command entrypoints so tests can stub them, and teach resolvePublicIngestRuntimeRequirements to flag the local-embeddings runtime feature when ktx.yaml selects sentence-transformers. * chore(cli): mark buildLocalStatsStatus and LocalStatsStatus as @internal Both symbols are consumed only by status-project.test.ts. Annotating with /** @internal */ keeps knip's production-mode check clean without changing runtime behavior. * fix(cli): use real package metadata in print-command-tree The stubbed package name embedded a forbidden product identifier that tripped the boundary check in CI. Read the metadata from package.json instead — keeps the rendered tree unchanged and removes a duplicate source of truth. * feat(cli): show embedding coverage in `ktx status`, drop duplicate disk counts Inline `(N embedded)` next to the Wiki scope counts and Semantic-layer source counts, computed with `SUM(embedding_json IS NOT NULL)` over `knowledge_pages` and `local_sl_sources`. Rename the "Knowledge" label to "Wiki" (canonical per `docs/terminology.md`) and rename the matching `localStats.knowledgePages` field to `localStats.wikiPages`. Drop `wiki=N md` and `semantic-layer=N yaml` from the Disk row — those duplicated the per-surface rows above. Disk now reports only actual byte usage (db, cache, raw-sources). The unused `wikiGlobalMarkdownCount` / `semanticLayerYamlCount` fields, the `isMarkdownEntry` / `isYamlEntry` helpers, and the `filter` arg on `summarizeDir` are removed.
2026-05-21 15:28:58 +02:00
import type { KtxSchemaDimensionType, KtxTableRef } from '../../context/scan/types.js';
2026-05-10 23:12:26 +02:00
2026-05-10 23:51:24 +02:00
type BigQueryTableNameRef = Pick<KtxTableRef, 'name'> & Partial<Pick<KtxTableRef, 'catalog' | 'db'>>;
2026-05-10 23:12:26 +02:00
export class KtxBigQueryDialect implements KtxDialect {
readonly type = 'bigquery' as const;
2026-05-10 23:12:26 +02:00
2026-05-10 23:51:24 +02:00
private readonly typeMappings: Record<string, KtxSchemaDimensionType> = {
2026-05-10 23:12:26 +02:00
TIMESTAMP: 'time',
DATETIME: 'time',
DATE: 'time',
TIME: 'time',
INT64: 'number',
INTEGER: 'number',
FLOAT64: 'number',
FLOAT: 'number',
NUMERIC: 'number',
BIGNUMERIC: 'number',
STRING: 'string',
BYTES: 'string',
BOOL: 'boolean',
BOOLEAN: 'boolean',
};
quoteIdentifier(identifier: string): string {
return `\`${identifier.replace(/`/g, '\\`')}\``;
}
formatTableName(table: BigQueryTableNameRef): string {
return formatDialectTableName(table, this.quoteIdentifier.bind(this), 'three-part');
}
formatDisplayRef(table: BigQueryTableNameRef): string {
return formatDialectDisplayRef(table, 'three-part');
}
parseDisplayRef(display: string): KtxTableRef | null {
return parseDialectDisplayRef(display, 'three-part');
}
columnDisplayTablePartCount(): 1 | 2 | 3 {
return columnDisplayPartCount('three-part');
2026-05-10 23:12:26 +02:00
}
mapDataType(nativeType: string): string {
const fieldType = nativeType.toUpperCase().trim();
if (fieldType === 'RECORD' || fieldType === 'STRUCT') {
return 'JSON';
}
const typeMapping: Record<string, string> = {
STRING: 'VARCHAR',
BYTES: 'VARBINARY',
INTEGER: 'BIGINT',
INT64: 'BIGINT',
FLOAT: 'DOUBLE',
FLOAT64: 'DOUBLE',
NUMERIC: 'DECIMAL',
BIGNUMERIC: 'DECIMAL',
BOOLEAN: 'BOOLEAN',
BOOL: 'BOOLEAN',
TIMESTAMP: 'TIMESTAMP',
DATE: 'DATE',
TIME: 'TIME',
DATETIME: 'DATETIME',
GEOGRAPHY: 'GEOGRAPHY',
JSON: 'JSON',
};
return typeMapping[fieldType] || fieldType;
}
2026-05-10 23:51:24 +02:00
mapToDimensionType(nativeType: string): KtxSchemaDimensionType {
2026-05-10 23:12:26 +02:00
if (!nativeType) {
return 'string';
}
const normalizedType = nativeType.toUpperCase().trim();
if (this.typeMappings[normalizedType]) {
return this.typeMappings[normalizedType];
}
if (normalizedType.includes('TIME') || normalizedType.includes('DATE')) {
return 'time';
}
if (normalizedType.includes('INT') || normalizedType.includes('NUM') || normalizedType.includes('FLOAT')) {
return 'number';
}
if (normalizedType.includes('BOOL')) {
return 'boolean';
}
return 'string';
}
generateSampleQuery(tableName: string, limit: number, columns?: string[]): string {
const columnList =
columns && columns.length > 0 ? columns.map((column) => this.quoteIdentifier(column)).join(', ') : '*';
return `SELECT ${columnList} FROM ${tableName} ORDER BY RAND() LIMIT ${limit}`;
}
generateColumnSampleQuery(tableName: string, columnName: string, limit: number): string {
const quotedColumn = this.quoteIdentifier(columnName);
return `SELECT ${quotedColumn} FROM ${tableName} WHERE ${quotedColumn} IS NOT NULL AND TRIM(CAST(${quotedColumn} AS STRING)) != '' ORDER BY RAND() LIMIT ${limit}`;
}
prepareQuery(sql: string, params?: Record<string, unknown>): { sql: string; params?: Record<string, unknown> } {
if (!params) {
return { sql, params: undefined };
}
let processedSql = sql;
const processedParams: Record<string, unknown> = {};
for (const [key, value] of Object.entries(params)) {
processedSql = processedSql.replace(new RegExp(`:${key}\\b`, 'g'), `@${key}`);
processedParams[key] = value;
}
return { sql: processedSql, params: Object.keys(processedParams).length > 0 ? processedParams : undefined };
}
getRandomSampleFilter(samplePct: number): string {
if (samplePct <= 0 || samplePct >= 1) {
return '';
}
return `RAND() < ${samplePct}`;
}
getTableSampleClause(samplePct: number): string {
if (samplePct <= 0 || samplePct >= 1) {
return '';
}
return `TABLESAMPLE SYSTEM (${samplePct * 100} PERCENT)`;
}
getLimitOffsetClause(limit: number, offset?: number): string {
return limitOffsetClause(limit, offset);
}
getTopClause(_limit: number): string {
return '';
2026-05-10 23:12:26 +02:00
}
getNullCountExpression(column: string): string {
return `COUNTIF(${column} IS NULL)`;
}
getDistinctCountExpression(column: string): string {
return `APPROX_COUNT_DISTINCT(${column})`;
}
textLengthExpression(columnSql: string): string {
return `LENGTH(CAST(${columnSql} AS STRING))`;
}
castToText(columnSql: string): string {
return `CAST(${columnSql} AS STRING)`;
}
getSampleValueAggregation(innerSql: string): string {
return `(SELECT STRING_AGG(CAST(value AS STRING), '\\u001F') FROM (${innerSql}) AS relationship_profile_values)`;
}
2026-05-10 23:12:26 +02:00
generateCardinalitySampleQuery(tableName: string, columnName: string, sampleSize: number): string {
return `
WITH sampled AS (
SELECT ${columnName} AS val
FROM ${tableName}
WHERE ${columnName} IS NOT NULL
LIMIT ${sampleSize}
)
SELECT APPROX_COUNT_DISTINCT(val) AS cardinality
FROM sampled
`;
}
generateDistinctValuesQuery(tableName: string, columnName: string, limit: number): string {
return `
SELECT DISTINCT CAST(${columnName} AS STRING) AS val
FROM ${tableName}
WHERE ${columnName} IS NOT NULL
ORDER BY val
LIMIT ${limit}
`;
}
generateColumnStatisticsQuery(_schemaName: string, _tableName: string): string | null {
return null;
}
generateRandomizedCardinalitySampleQuery(tableName: string, columnName: string, sampleSize: number): string {
return `
WITH sampled AS (
SELECT ${columnName} AS val
FROM ${tableName}
WHERE ${columnName} IS NOT NULL
ORDER BY RAND()
LIMIT ${sampleSize}
)
SELECT APPROX_COUNT_DISTINCT(val) AS cardinality
FROM sampled
`;
}
}