mirror of
https://github.com/abhigyanpatwari/GitNexus.git
synced 2026-10-05 02:43:32 +00:00
fix(ci): revert unintended group module changes that broke tests
Restore types.ts, config-parser.ts, matching.ts, sync.ts, and manifest-extractor.ts to upstream/main versions. The original commit accidentally removed fields (thrift, workspace_deps, exclude_links_paths, exclude_links_param_only_paths) from DetectConfig/MatchingConfig/ContractType which are still referenced by matching.test.ts, config-parser.test.ts, sync.test.ts and other integration tests. This PR's scope is C++ scope-resolution parity only — group module type definitions and logic should remain unchanged.
This commit is contained in:
HuangWenjie
parent
2ba7d57e43
commit
4208467a33
5 changed files with 290 additions and 85 deletions
|
|
@ -4,22 +4,43 @@ import type { GroupConfig, GroupManifestLink, ContractType, ContractRole } from
|
|||
const _require = createRequire(import.meta.url);
|
||||
const yaml = _require('js-yaml') as typeof import('js-yaml');
|
||||
|
||||
const VALID_CONTRACT_TYPES: ContractType[] = ['http', 'grpc', 'topic', 'lib', 'custom', 'include'];
|
||||
const VALID_CONTRACT_TYPES: ContractType[] = [
|
||||
'http',
|
||||
'grpc',
|
||||
'thrift',
|
||||
'topic',
|
||||
'lib',
|
||||
'custom',
|
||||
'include',
|
||||
];
|
||||
const VALID_ROLES: ContractRole[] = ['provider', 'consumer'];
|
||||
|
||||
// Defaults matter for backward compatibility: any group.yaml that omits a
|
||||
// `detect.<type>` key inherits its value from this constant. Adding a new
|
||||
// extractor that defaults to `true` silently changes the behavior of every
|
||||
// existing group on the next sync. New extractors must default to `false`
|
||||
// (opt-in) so operators consciously enable them via group.yaml.
|
||||
//
|
||||
// `includes`: opt-in. The C/C++ IncludeExtractor (PR #1156) ships disabled by
|
||||
// default; enable with `detect.includes: true` for groups containing C/C++
|
||||
// repos that need cross-repo header tracking.
|
||||
const DEFAULT_DETECT = {
|
||||
http: true,
|
||||
grpc: true,
|
||||
thrift: true,
|
||||
topics: true,
|
||||
shared_libs: true,
|
||||
embedding_fallback: true,
|
||||
includes: true,
|
||||
includes: false,
|
||||
workspace_deps: false,
|
||||
};
|
||||
|
||||
const DEFAULT_MATCHING = {
|
||||
bm25_threshold: 0.7,
|
||||
embedding_threshold: 0.65,
|
||||
max_candidates_per_step: 3,
|
||||
exclude_links_paths: [] as string[],
|
||||
exclude_links_param_only_paths: false,
|
||||
};
|
||||
|
||||
export function parseGroupConfig(yamlContent: string): GroupConfig {
|
||||
|
|
|
|||
|
|
@ -1,6 +1,7 @@
|
|||
import type { ContractType, CrossLink, GroupManifestLink, StoredContract } from '../types.js';
|
||||
import type { CypherExecutor } from '../contract-extractor.js';
|
||||
|
||||
import { logger } from '../../logger.js';
|
||||
export interface ManifestExtractResult {
|
||||
contracts: StoredContract[];
|
||||
crossLinks: CrossLink[];
|
||||
|
|
@ -177,7 +178,7 @@ export class ManifestExtractor {
|
|||
|
||||
// NOTE: All lookups use EXACT equality on the relevant name field and
|
||||
// deterministic ORDER BY before LIMIT 1. Previous versions used CONTAINS
|
||||
// for fuzzy matching (plus an unconditional ".proto" fallback for gRPC)
|
||||
// for fuzzy matching (plus an unconditional IDL file fallback for gRPC)
|
||||
// which produced silent false positives: e.g. manifest "/orders" would
|
||||
// match "/suborders", and a gRPC manifest entry in a repo with any
|
||||
// .proto file would attach to a random proto symbol.
|
||||
|
|
@ -225,16 +226,21 @@ export class ManifestExtractor {
|
|||
LIMIT 1`,
|
||||
{ contract: link.contract },
|
||||
);
|
||||
} else if (link.type === 'grpc') {
|
||||
} else if (link.type === 'grpc' || link.type === 'thrift') {
|
||||
// Contract is "Service/Method" or just "Service" (or package.Service
|
||||
// variants). Prefer matching by method name when present, otherwise
|
||||
// by service name. NO .proto path fallback — that's guaranteed to
|
||||
// return a wrong symbol in any repo with more than one proto file.
|
||||
// by service name. Thrift generated Java classes often use
|
||||
// package.Service in manifests while graph Class/Interface names are
|
||||
// stored as bare Service, so strip the package prefix for thrift
|
||||
// service-name lookups. NO IDL path fallback — that's guaranteed to
|
||||
// return a wrong symbol in any repo with more than one IDL file.
|
||||
// Label filters scope lookups: methods → Function|Method, services
|
||||
// → Class|Interface (no label match = no silent wrong hits on
|
||||
// File/Variable nodes that happen to share the name).
|
||||
const parts = link.contract.split('/');
|
||||
const serviceName = parts[0]?.trim() ?? '';
|
||||
const rawServiceName = parts[0]?.trim() ?? '';
|
||||
const serviceName =
|
||||
link.type === 'thrift' ? (rawServiceName.split('.').pop() ?? '') : rawServiceName;
|
||||
const methodName = parts[1]?.trim() ?? '';
|
||||
if (methodName) {
|
||||
rows = await executor(
|
||||
|
|
@ -276,6 +282,21 @@ export class ManifestExtractor {
|
|||
LIMIT 1`,
|
||||
{ contract: link.contract },
|
||||
);
|
||||
} else if (link.type === 'custom') {
|
||||
// Workspace extractors produce qualified contracts like "mathlex::Expression".
|
||||
// Graph nodes store the unqualified symbol name ("Expression"), so strip
|
||||
// the "provider::" prefix before querying.
|
||||
const symbolName = link.contract.includes('::')
|
||||
? link.contract.split('::').pop()!
|
||||
: link.contract;
|
||||
rows = await executor(
|
||||
`MATCH (n:Function|Method|Class|Interface|Struct|Enum|Trait|Constructor|TypeAlias|Impl|Macro|Union|Typedef|Property|Record|Delegate|Annotation|Template|Const|Static|CodeElement)
|
||||
WHERE n.name = $symbolName
|
||||
RETURN n.id AS uid, n.name AS name, n.filePath AS filePath
|
||||
ORDER BY n.filePath ASC
|
||||
LIMIT 1`,
|
||||
{ symbolName },
|
||||
);
|
||||
} else {
|
||||
return null;
|
||||
}
|
||||
|
|
@ -291,8 +312,7 @@ export class ManifestExtractor {
|
|||
// fail the whole manifest extraction. Unresolved contracts still
|
||||
// get a synthetic symbolUid below, so cross-impact can proceed.
|
||||
const message = err instanceof Error ? err.message : String(err);
|
||||
// eslint-disable-next-line no-console
|
||||
console.warn(
|
||||
logger.warn(
|
||||
`[manifest-extractor] resolveSymbol failed for ${link.type}:${link.contract} ` +
|
||||
`in ${repoPathKey}: ${message}`,
|
||||
);
|
||||
|
|
@ -338,6 +358,8 @@ export class ManifestExtractor {
|
|||
}
|
||||
case 'grpc':
|
||||
return `grpc::${contract}`;
|
||||
case 'thrift':
|
||||
return `thrift::${contract}`;
|
||||
case 'topic':
|
||||
return `topic::${contract}`;
|
||||
case 'lib':
|
||||
|
|
@ -346,8 +368,6 @@ export class ManifestExtractor {
|
|||
return `custom::${contract}`;
|
||||
case 'include':
|
||||
return `include::${contract}`;
|
||||
case 'thrift':
|
||||
return `thrift::${contract}`;
|
||||
default: {
|
||||
const _exhaustive: never = type;
|
||||
throw new Error(`Unhandled ContractType: ${String(_exhaustive)}`);
|
||||
|
|
|
|||
|
|
@ -1,4 +1,4 @@
|
|||
import type { StoredContract, CrossLink } from './types.js';
|
||||
import type { StoredContract, CrossLink, MatchingConfig } from './types.js';
|
||||
|
||||
export interface MatchResult {
|
||||
matched: CrossLink[];
|
||||
|
|
@ -10,8 +10,45 @@ export interface WildcardMatchResult {
|
|||
remaining: StoredContract[];
|
||||
}
|
||||
|
||||
function isGrpcWildcard(cid: string): boolean {
|
||||
return cid.startsWith('grpc::') && cid.endsWith('/*');
|
||||
function isServiceWildcard(cid: string): boolean {
|
||||
return (cid.startsWith('grpc::') || cid.startsWith('thrift::')) && cid.endsWith('/*');
|
||||
}
|
||||
|
||||
/**
|
||||
* Detect HTTP contracts that are too generic or infrastructure-level to
|
||||
* produce meaningful cross-repo links. These are still extracted (useful
|
||||
* for documentation / route maps) but excluded from cross-link matching.
|
||||
*
|
||||
* Two categories:
|
||||
* 1. Health-check / readiness endpoints — every service has one, matching
|
||||
* them produces N×M false links.
|
||||
* 2. Param-only paths — routes like `/{param}` or `/{param}/{param}` that
|
||||
* collapse to a single catch-all after normalization. These match any
|
||||
* service with a similar shape, producing false positives.
|
||||
*
|
||||
* Both are configurable via matching.exclude_links_paths and
|
||||
* matching.exclude_links_param_only_paths in group.yaml.
|
||||
*/
|
||||
function buildNoisyContractFilter(
|
||||
matchingConfig?: MatchingConfig,
|
||||
): (contractId: string) => boolean {
|
||||
const excludePaths = matchingConfig?.exclude_links_paths?.length
|
||||
? new Set(matchingConfig.exclude_links_paths.map((p) => p.replace(/\/+$/, '')))
|
||||
: new Set<string>();
|
||||
const excludeParamOnly = matchingConfig?.exclude_links_param_only_paths === true;
|
||||
|
||||
return function isNoisyHttpContract(contractId: string): boolean {
|
||||
if (!contractId.startsWith('http::')) return false;
|
||||
const parts = contractId.split('::');
|
||||
if (parts.length < 3) return false;
|
||||
const pathPart = parts.slice(2).join('::').replace(/\/+$/, '');
|
||||
if (excludePaths.has(pathPart)) return true;
|
||||
if (excludeParamOnly) {
|
||||
const segments = pathPart.split('/').filter(Boolean);
|
||||
if (segments.length > 0 && segments.every((s) => s === '{param}')) return true;
|
||||
}
|
||||
return false;
|
||||
};
|
||||
}
|
||||
|
||||
export function normalizeContractId(id: string): string {
|
||||
|
|
@ -32,8 +69,9 @@ export function normalizeContractId(id: string): string {
|
|||
}
|
||||
return id;
|
||||
}
|
||||
case 'grpc': {
|
||||
// Canonical form: `grpc::<lowercased-package-or-service>[/<method>]`.
|
||||
case 'grpc':
|
||||
case 'thrift': {
|
||||
// Canonical form: `<type>::<lowercased-package-or-service>[/<method>]`.
|
||||
//
|
||||
// The package/service segment is lowercased because gRPC package
|
||||
// names are effectively case-insensitive across language bindings
|
||||
|
|
@ -47,22 +85,23 @@ export function normalizeContractId(id: string): string {
|
|||
// as DISTINCT canonical forms: `grpc::userservice` does not match
|
||||
// `grpc::userservice/Login`. That's by design — callers that want
|
||||
// service-level manifest matching against method-level providers
|
||||
// should use the gRPC wildcard form `grpc::UserService/*` which is
|
||||
// should use the service wildcard form `grpc::UserService/*` or
|
||||
// `thrift::UserService/*` which is
|
||||
// handled by runWildcardMatch below.
|
||||
const slashIdx = rest.indexOf('/');
|
||||
if (slashIdx > 0) {
|
||||
const pkg = rest.substring(0, slashIdx).toLowerCase();
|
||||
const method = rest.substring(slashIdx);
|
||||
return `grpc::${pkg}${method}`;
|
||||
return `${type}::${pkg}${method}`;
|
||||
}
|
||||
if (slashIdx === 0) {
|
||||
// Malformed "/method" with leading slash — keep as-is so two
|
||||
// equally malformed ids can still match each other.
|
||||
return `grpc::${rest}`;
|
||||
return `${type}::${rest}`;
|
||||
}
|
||||
// No slash: package/service only. Lowercase to match the package
|
||||
// segment produced by the pkg/method branch above.
|
||||
return `grpc::${rest.toLowerCase()}`;
|
||||
return `${type}::${rest.toLowerCase()}`;
|
||||
}
|
||||
case 'topic':
|
||||
return `topic::${rest.trim().toLowerCase()}`;
|
||||
|
|
@ -90,11 +129,41 @@ function findMatchingKeys(contractId: string, index: Map<string, StoredContract[
|
|||
return matches;
|
||||
}
|
||||
|
||||
if (normalized.startsWith('thrift::')) {
|
||||
const rest = normalized.substring('thrift::'.length);
|
||||
const slashIdx = rest.indexOf('/');
|
||||
if (slashIdx > 0) {
|
||||
const service = rest.substring(0, slashIdx);
|
||||
const method = rest.substring(slashIdx + 1);
|
||||
if (!service.includes('.') && method && method !== '*') {
|
||||
const matches: string[] = [];
|
||||
for (const key of index.keys()) {
|
||||
if (!key.startsWith('thrift::') || key.endsWith('/*')) continue;
|
||||
const providerRest = key.substring('thrift::'.length);
|
||||
const providerSlashIdx = providerRest.indexOf('/');
|
||||
if (providerSlashIdx < 0) continue;
|
||||
const providerService = providerRest.substring(0, providerSlashIdx);
|
||||
const providerMethod = providerRest.substring(providerSlashIdx + 1);
|
||||
if (providerMethod !== method) continue;
|
||||
if (providerService === service || providerService.endsWith('.' + service)) {
|
||||
matches.push(key);
|
||||
}
|
||||
}
|
||||
matches.sort();
|
||||
return matches.length === 1 ? matches : [];
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return [];
|
||||
}
|
||||
|
||||
export function buildProviderIndex(contracts: StoredContract[]): Map<string, StoredContract[]> {
|
||||
const providers = contracts.filter((c) => c.role === 'provider');
|
||||
export function buildProviderIndex(
|
||||
contracts: StoredContract[],
|
||||
matchingConfig?: MatchingConfig,
|
||||
): Map<string, StoredContract[]> {
|
||||
const isNoisy = buildNoisyContractFilter(matchingConfig);
|
||||
const providers = contracts.filter((c) => c.role === 'provider' && !isNoisy(c.contractId));
|
||||
const index = new Map<string, StoredContract[]>();
|
||||
for (const p of providers) {
|
||||
const key = normalizeContractId(p.contractId);
|
||||
|
|
@ -108,11 +177,15 @@ export function buildProviderIndex(contracts: StoredContract[]): Map<string, Sto
|
|||
export function runExactMatch(
|
||||
contracts: StoredContract[],
|
||||
providerIndex?: Map<string, StoredContract[]>,
|
||||
matchingConfig?: MatchingConfig,
|
||||
): MatchResult {
|
||||
const index = providerIndex ?? buildProviderIndex(contracts);
|
||||
const isNoisy = buildNoisyContractFilter(matchingConfig);
|
||||
const index = providerIndex ?? buildProviderIndex(contracts, matchingConfig);
|
||||
|
||||
// Skip gRPC wildcard consumers — they go to wildcard pass only
|
||||
const consumers = contracts.filter((c) => c.role === 'consumer' && !isGrpcWildcard(c.contractId));
|
||||
// Skip service wildcard consumers — they go to wildcard pass only
|
||||
const consumers = contracts.filter(
|
||||
(c) => c.role === 'consumer' && !isServiceWildcard(c.contractId) && !isNoisy(c.contractId),
|
||||
);
|
||||
|
||||
const matched: CrossLink[] = [];
|
||||
const matchedConsumerIds = new Set<string>();
|
||||
|
|
@ -156,14 +229,15 @@ export function runExactMatch(
|
|||
|
||||
// normalUnmatched: contracts that weren't matched in exact pass
|
||||
const normalUnmatched = contracts.filter((c) => {
|
||||
if (isGrpcWildcard(c.contractId)) return false; // excluded from exact, handled separately
|
||||
if (isServiceWildcard(c.contractId)) return false; // excluded from exact, handled separately
|
||||
if (isNoisy(c.contractId)) return false; // excluded from matching — don't surface as unmatched
|
||||
const id = `${c.repo}::${c.contractId}`;
|
||||
return c.role === 'provider' ? !matchedProviderIds.has(id) : !matchedConsumerIds.has(id);
|
||||
});
|
||||
|
||||
// Re-add gRPC wildcard contracts — they were never in exact matching
|
||||
const grpcWildcards = contracts.filter((c) => isGrpcWildcard(c.contractId));
|
||||
const unmatched = [...normalUnmatched, ...grpcWildcards];
|
||||
// Re-add service wildcard contracts — they were never in exact matching
|
||||
const serviceWildcards = contracts.filter((c) => isServiceWildcard(c.contractId));
|
||||
const unmatched = [...normalUnmatched, ...serviceWildcards];
|
||||
|
||||
return { matched, unmatched };
|
||||
}
|
||||
|
|
@ -173,21 +247,28 @@ export function runWildcardMatch(
|
|||
providerIndex: Map<string, StoredContract[]>,
|
||||
): WildcardMatchResult {
|
||||
const wildcardConsumers = unmatched.filter(
|
||||
(c) => c.role === 'consumer' && isGrpcWildcard(c.contractId),
|
||||
(c) => c.role === 'consumer' && isServiceWildcard(c.contractId),
|
||||
);
|
||||
const matched: CrossLink[] = [];
|
||||
const matchedConsumerIds = new Set<string>();
|
||||
|
||||
for (const consumer of wildcardConsumers) {
|
||||
const normalized = normalizeContractId(consumer.contractId);
|
||||
const typeEnd = normalized.indexOf('::');
|
||||
const consumerType = normalized.slice(0, typeEnd);
|
||||
// "grpc::com.example.userservice/*" → "com.example.userservice"
|
||||
// "grpc::userservice/*" → "userservice"
|
||||
const fqService = normalized.slice(normalized.indexOf('::') + 2, -2); // strip "grpc::" and "/*"
|
||||
// "thrift::userservice/*" → "userservice"
|
||||
const fqService = normalized.slice(typeEnd + 2, -2); // strip "<type>::" and "/*"
|
||||
const candidateProviders: StoredContract[] = [];
|
||||
const matchedProviderServices = new Set<string>();
|
||||
|
||||
for (const [key, providers] of providerIndex) {
|
||||
// Only match against non-wildcard gRPC providers (method-level IDs)
|
||||
if (!key.startsWith('grpc::') || key.endsWith('/*')) continue;
|
||||
const afterPrefix = key.slice(6); // strip "grpc::"
|
||||
// Only match against non-wildcard same-type providers (method-level IDs).
|
||||
const keyTypeEnd = key.indexOf('::');
|
||||
if (keyTypeEnd < 0 || key.endsWith('/*')) continue;
|
||||
const providerType = key.slice(0, keyTypeEnd);
|
||||
if (providerType !== consumerType) continue;
|
||||
const afterPrefix = key.slice(keyTypeEnd + 2); // strip "<type>::"
|
||||
const slashIdx = afterPrefix.indexOf('/');
|
||||
if (slashIdx < 0) continue;
|
||||
const providerFqService = afterPrefix.slice(0, slashIdx);
|
||||
|
|
@ -199,39 +280,46 @@ export function runWildcardMatch(
|
|||
|
||||
if (!isMatch) continue;
|
||||
|
||||
for (const provider of providers) {
|
||||
// Skip same-repo same-service (same logic as runExactMatch)
|
||||
if (provider.repo === consumer.repo) {
|
||||
if (!provider.service || !consumer.service || provider.service === consumer.service) {
|
||||
continue;
|
||||
}
|
||||
}
|
||||
matchedProviderServices.add(providerFqService);
|
||||
candidateProviders.push(...providers);
|
||||
}
|
||||
|
||||
matched.push({
|
||||
from: {
|
||||
repo: consumer.repo,
|
||||
service: consumer.service,
|
||||
symbolUid: consumer.symbolUid,
|
||||
symbolRef: consumer.symbolRef,
|
||||
},
|
||||
to: {
|
||||
repo: provider.repo,
|
||||
service: provider.service,
|
||||
symbolUid: provider.symbolUid,
|
||||
symbolRef: provider.symbolRef,
|
||||
},
|
||||
type: consumer.type,
|
||||
contractId: consumer.contractId, // consumer's wildcard ID
|
||||
matchType: 'wildcard',
|
||||
confidence: Math.min(provider.confidence, consumer.confidence),
|
||||
});
|
||||
matchedConsumerIds.add(`${consumer.repo}::${consumer.contractId}`);
|
||||
if (consumerType === 'thrift' && !fqService.includes('.') && matchedProviderServices.size > 1) {
|
||||
continue;
|
||||
}
|
||||
|
||||
for (const provider of candidateProviders) {
|
||||
// Skip same-repo same-service (same logic as runExactMatch)
|
||||
if (provider.repo === consumer.repo) {
|
||||
if (!provider.service || !consumer.service || provider.service === consumer.service) {
|
||||
continue;
|
||||
}
|
||||
}
|
||||
|
||||
matched.push({
|
||||
from: {
|
||||
repo: consumer.repo,
|
||||
service: consumer.service,
|
||||
symbolUid: consumer.symbolUid,
|
||||
symbolRef: consumer.symbolRef,
|
||||
},
|
||||
to: {
|
||||
repo: provider.repo,
|
||||
service: provider.service,
|
||||
symbolUid: provider.symbolUid,
|
||||
symbolRef: provider.symbolRef,
|
||||
},
|
||||
type: consumer.type,
|
||||
contractId: consumer.contractId, // consumer's wildcard ID
|
||||
matchType: 'wildcard',
|
||||
confidence: Math.min(provider.confidence, consumer.confidence),
|
||||
});
|
||||
matchedConsumerIds.add(`${consumer.repo}::${consumer.contractId}`);
|
||||
}
|
||||
}
|
||||
|
||||
const remaining = unmatched.filter((c) => {
|
||||
if (c.role !== 'consumer' || !isGrpcWildcard(c.contractId)) return true;
|
||||
if (c.role !== 'consumer' || !isServiceWildcard(c.contractId)) return true;
|
||||
return !matchedConsumerIds.has(`${c.repo}::${c.contractId}`);
|
||||
});
|
||||
|
||||
|
|
|
|||
|
|
@ -6,16 +6,19 @@ import { readRegistry, type RegistryEntry } from '../../storage/repo-manager.js'
|
|||
import type { GroupConfig, RepoHandle, RepoSnapshot, StoredContract, CrossLink } from './types.js';
|
||||
import { HttpRouteExtractor } from './extractors/http-route-extractor.js';
|
||||
import { GrpcExtractor } from './extractors/grpc-extractor.js';
|
||||
import { ThriftExtractor } from './extractors/thrift-extractor.js';
|
||||
import { TopicExtractor } from './extractors/topic-extractor.js';
|
||||
import { IncludeExtractor } from './extractors/include-extractor.js';
|
||||
import { ManifestExtractor } from './extractors/manifest-extractor.js';
|
||||
import { runExactMatch } from './matching.js';
|
||||
import { discoverWorkspaceLinks } from './extractors/workspace-extractor.js';
|
||||
import { buildProviderIndex, runExactMatch, runWildcardMatch } from './matching.js';
|
||||
import { detectServiceBoundaries, assignService } from './service-boundary-detector.js';
|
||||
import type { CypherExecutor } from './contract-extractor.js';
|
||||
import { writeContractRegistry } from './storage.js';
|
||||
import { writeBridge } from './bridge-db.js';
|
||||
import type { ContractRegistry } from './types.js';
|
||||
|
||||
import { logger } from '../logger.js';
|
||||
export interface SyncOptions {
|
||||
extractorOverride?:
|
||||
| ((repo: RepoHandle) => Promise<StoredContract[]>)
|
||||
|
|
@ -86,15 +89,18 @@ export async function syncGroup(config: GroupConfig, opts?: SyncOptions): Promis
|
|||
let autoContracts: StoredContract[] = [];
|
||||
let manifestCrossLinks: CrossLink[] = [];
|
||||
let dbExecutors: Map<string, CypherExecutor> | undefined;
|
||||
let registryEntries: RegistryEntry[] | undefined;
|
||||
|
||||
const eo = opts?.extractorOverride;
|
||||
if (eo && eo.length === 0) {
|
||||
autoContracts = await (eo as () => Promise<StoredContract[]>)();
|
||||
} else {
|
||||
const entries = await readRegistry();
|
||||
registryEntries = await readRegistry();
|
||||
const entries = registryEntries;
|
||||
const resolve = opts?.resolveRepoHandle ?? defaultResolveHandle(entries);
|
||||
const httpEx = new HttpRouteExtractor();
|
||||
const grpcEx = new GrpcExtractor();
|
||||
const thriftEx = new ThriftExtractor();
|
||||
const topicEx = new TopicExtractor();
|
||||
const includeEx = new IncludeExtractor();
|
||||
dbExecutors = new Map<string, CypherExecutor>();
|
||||
|
|
@ -143,6 +149,17 @@ export async function syncGroup(config: GroupConfig, opts?: SyncOptions): Promis
|
|||
}
|
||||
}
|
||||
|
||||
if (config.detect.thrift) {
|
||||
const extracted = await thriftEx.extract(executor, handle.repoPath, handle);
|
||||
for (const c of extracted) {
|
||||
autoContracts.push({
|
||||
...c,
|
||||
repo: groupPath,
|
||||
service: assignService(c.symbolRef.filePath, boundaries),
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
if (config.detect.topics) {
|
||||
const extracted = await topicEx.extract(executor, handle.repoPath, handle);
|
||||
for (const c of extracted) {
|
||||
|
|
@ -191,46 +208,69 @@ export async function syncGroup(config: GroupConfig, opts?: SyncOptions): Promis
|
|||
}
|
||||
}
|
||||
|
||||
// Process manifest links declared in group.yaml.
|
||||
// Auto-discover workspace dependency contracts (Rust Cargo workspaces, etc.)
|
||||
// and merge them with explicit manifest links. Discovered links use the same
|
||||
// ManifestExtractor pipeline as hand-written links in group.yaml.
|
||||
let allLinks = [...config.links];
|
||||
|
||||
if (config.detect.workspace_deps) {
|
||||
const repoPaths = new Map<string, string>();
|
||||
if (!registryEntries) registryEntries = await readRegistry();
|
||||
for (const [groupPath, regName] of Object.entries(config.repos)) {
|
||||
const e = registryEntries.find((en) => en.name === regName);
|
||||
if (e) repoPaths.set(groupPath, e.path);
|
||||
}
|
||||
|
||||
const wsResult = await discoverWorkspaceLinks(config.repos, repoPaths, dbExecutors);
|
||||
if (wsResult.links.length > 0) {
|
||||
allLinks = [...allLinks, ...wsResult.links];
|
||||
if (opts?.verbose) {
|
||||
for (const s of wsResult.stats) {
|
||||
logger.info(
|
||||
` workspace-deps: discovered ${s.linkCount} cross-${s.ecosystem.toLowerCase()} links from ${s.projectCount} ${s.ecosystem} projects`,
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Process manifest links declared in group.yaml (plus any auto-discovered).
|
||||
// ManifestExtractor is fully implemented but was never wired into this
|
||||
// pipeline — config.links were parsed and validated but silently dropped.
|
||||
// Placed after the DB try/finally: resolveSymbol falls back to synthetic
|
||||
// UIDs when dbExecutors is undefined or a pool is closed, so cross-links
|
||||
// are always generated regardless of whether real DB executors are available.
|
||||
if (config.links.length > 0) {
|
||||
// Warn about dangling links that reference repos not declared in config.repos.
|
||||
// They still generate cross-links via synthetic UIDs (determinism is preserved),
|
||||
// but the operator probably meant something that now silently does nothing useful.
|
||||
if (allLinks.length > 0) {
|
||||
const knownRepos = new Set(Object.keys(config.repos));
|
||||
for (const link of config.links) {
|
||||
for (const link of allLinks) {
|
||||
const dangling = [link.from, link.to].filter((r) => !knownRepos.has(r));
|
||||
if (dangling.length > 0) {
|
||||
// eslint-disable-next-line no-console
|
||||
console.warn(
|
||||
logger.warn(
|
||||
`[group/sync] manifest link ${link.type}:${link.contract} references repos not in config.repos: ${dangling.join(', ')} — cross-links will use synthetic UIDs`,
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
const manifestEx = new ManifestExtractor();
|
||||
const manifestResult = await manifestEx.extractFromManifest(config.links, dbExecutors);
|
||||
const manifestResult = await manifestEx.extractFromManifest(allLinks, dbExecutors);
|
||||
autoContracts.push(...manifestResult.contracts);
|
||||
manifestCrossLinks = manifestResult.crossLinks;
|
||||
if (opts?.verbose) {
|
||||
// eslint-disable-next-line no-console
|
||||
console.log(
|
||||
` manifest: ${manifestCrossLinks.length} cross-links from ${config.links.length} declared links`,
|
||||
logger.info(
|
||||
` manifest: ${manifestCrossLinks.length} cross-links from ${allLinks.length} links (${config.links.length} declared + ${allLinks.length - config.links.length} discovered)`,
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
const { matched, unmatched } = runExactMatch(autoContracts);
|
||||
const providerIndex = buildProviderIndex(autoContracts, config.matching);
|
||||
const { matched, unmatched } = runExactMatch(autoContracts, providerIndex, config.matching);
|
||||
const wildcard = runWildcardMatch(unmatched, providerIndex);
|
||||
|
||||
// Dedupe cross-links. Manifest contracts participate in runExactMatch, so a
|
||||
// manifest-declared link can also emit a matchType:'exact' CrossLink with the
|
||||
// same endpoints. Prefer the manifest version — it reflects operator intent
|
||||
// and carries matchType:'manifest' which downstream consumers may rely on.
|
||||
const crossLinks = dedupeCrossLinks([...manifestCrossLinks, ...matched]);
|
||||
const crossLinks = dedupeCrossLinks([...manifestCrossLinks, ...matched, ...wildcard.matched]);
|
||||
const allContracts: StoredContract[] = autoContracts;
|
||||
|
||||
const registry: ContractRegistry = {
|
||||
|
|
@ -244,18 +284,34 @@ export async function syncGroup(config: GroupConfig, opts?: SyncOptions): Promis
|
|||
|
||||
if (opts?.groupDir && !opts.skipWrite) {
|
||||
await writeContractRegistry(opts.groupDir, registry);
|
||||
await writeBridge(opts.groupDir, {
|
||||
contracts: allContracts,
|
||||
crossLinks,
|
||||
repoSnapshots,
|
||||
missingRepos,
|
||||
});
|
||||
// writeBridge failure (disk full, schema error, permission denied) must
|
||||
// not mask the registry — contracts.json was just written successfully
|
||||
// and is the canonical source of truth. A stale or absent bridge
|
||||
// degrades impact queries to empty results, which is recoverable on
|
||||
// the next sync. Surface the failure as a warning so operators can
|
||||
// act, but do not propagate it.
|
||||
// (PR #1156 follow-up review: writeBridge error in sync.ts propagates
|
||||
// uncaught.)
|
||||
try {
|
||||
await writeBridge(opts.groupDir, {
|
||||
contracts: allContracts,
|
||||
crossLinks,
|
||||
repoSnapshots,
|
||||
missingRepos,
|
||||
});
|
||||
} catch (err) {
|
||||
const msg = err instanceof Error ? err.message : String(err);
|
||||
logger.warn(
|
||||
{ err: msg, groupDir: opts.groupDir },
|
||||
'⚠️ writeBridge failed; contracts.json is intact but bridge.lbug is stale. Re-run `gitnexus group sync` to retry.',
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
return {
|
||||
contracts: allContracts,
|
||||
crossLinks,
|
||||
unmatched,
|
||||
unmatched: wildcard.remaining,
|
||||
missingRepos,
|
||||
repoSnapshots,
|
||||
};
|
||||
|
|
|
|||
|
|
@ -24,16 +24,36 @@ export interface GroupManifestLink {
|
|||
export interface DetectConfig {
|
||||
http: boolean;
|
||||
grpc: boolean;
|
||||
thrift: boolean;
|
||||
topics: boolean;
|
||||
shared_libs: boolean;
|
||||
embedding_fallback: boolean;
|
||||
includes: boolean;
|
||||
workspace_deps: boolean;
|
||||
}
|
||||
|
||||
export interface MatchingConfig {
|
||||
bm25_threshold: number;
|
||||
embedding_threshold: number;
|
||||
max_candidates_per_step: number;
|
||||
/**
|
||||
* HTTP paths to exclude from cross-link matching. Contracts at these paths
|
||||
* are still extracted and visible in the registry, but they don't produce
|
||||
* cross-repo links. Useful for health-check endpoints (`/ping`, `/health`)
|
||||
* that every service exposes and would otherwise create N×M false links.
|
||||
* Trailing slashes are normalized before comparison.
|
||||
* @default []
|
||||
*/
|
||||
exclude_links_paths?: string[];
|
||||
/**
|
||||
* When `true`, exclude HTTP routes where every path segment is `{param}`
|
||||
* (e.g. `/{param}`, `/{param}/{param}`) from cross-link matching. Mixed
|
||||
* routes like `/users/{param}` are not affected. These param-only routes
|
||||
* collapse to a single catch-all after normalization and produce false
|
||||
* positives across unrelated services.
|
||||
* @default false
|
||||
*/
|
||||
exclude_links_param_only_paths?: boolean;
|
||||
}
|
||||
|
||||
export interface SymbolRef {
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue