mirror of
https://github.com/renovatebot/renovate.git
synced 2026-10-25 23:11:31 +00:00
a1971afa78
* ci(linter): add renovate/require-regex-util rule Adds a custom oxlint rule that flags raw RegExp usage in lib/ production code: any `new RegExp(...)` call and any regex literal that is not the direct first argument of `regEx(...)`. The regEx() helper from lib/util/regex.ts uses the RE2 engine for ReDoS-safe matching and caches compiled patterns. lib/util/regex.ts itself is exempt. The rule is disabled for **/*.spec.ts, test/**, and tools/** via config overrides, because vitest APIs such as expect.stringMatching need bare RegExp instances (a past commit reverted regEx() there). Severity is set to "warn" instead of "error": the repo currently has 197 pre-existing violations (above the agreed mechanical-fix threshold of 80), and a number of them are deliberately RE2-incompatible patterns (lookahead/lookbehind/named backreferences, see TODO #12872/#12875 markers in e.g. lib/modules/versioning/rez/ pattern.ts and lib/modules/manager/dockerfile/extract.ts) that need per-site judgment before they can be wrapped in regEx() or suppressed with a justified disable comment. No violation fixes are included in this commit. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * ci(linter): enforce renovate/require-regex-util at error Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * refactor: use regEx() for regex literals and RegExp construction in lib Burn down all renovate/require-regex-util violations (197): - wrap RE2-compatible regex literals and RegExp constructions in regEx() - rewrite lookaround patterns where behavior is provably preserved: goproxy separator split, sbt-package link extraction, leiningen comment stripping and keyword search, npm GitHub owner validation (unit-count bound replaced by an explicit length check) - keep native RegExp with disable comments where RE2 cannot be used: moo / good-enough-parser lexer patterns (moo rejects RE2 instances), MigrationsService propertyName (matched via isRegExp, which RE2 instances fail), rez named backreferences and lookaheads, GitHub markdown link negative lookbehind, emoji astral-plane matching - drop stale TODO #12875 comments for patterns current re2 handles Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * refactor: reduce require-regex-util disable comments Rewrite the github massage-markdown-links URL regex to capture an optional `api.` prefix in a named group (skipped in code) instead of relying on a negative lookbehind, so both the base and global variants can use regEx()/RE2 and their two disable comments are removed. Add spec cases for api-prefixed URLs that match the URL shape. Consolidate the four related line disables in rez/pattern.ts (bound and range patterns emulating Python conditional patterns via named backreferences and lookaheads, which RE2 cannot express) into a single block disable/enable pair, matching the treatment of the lexer files. Disable comment count drops from 13 to 8. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * refactor(datasource/sbt-package): use named capture group in link regex Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * refactor(manager/cake): restore original multiLineComment regex spelling The [^] -> [\\s\\S] rewrite was only needed for an RE2 wrap that was later reverted; keep the diff minimal. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(datasource/go): skip empty GOPROXY segments The switch from a lookahead split to a capture-group split (needed because RE2 has no lookahead support) changed how empty GOPROXY segments parse: `a|,b` yielded `{ url: ',', fallback: '|' }` before and `{ url: '', fallback: ',' }` after. The comma fallback only continues on 404/410, so a failing proxy ahead of an empty segment silently stopped the lookup instead of falling through to the remaining proxies. Empty segments carry no url to query, so drop them. * refactor(datasource/go): use isTruthy for empty segment filter * fix(datasource/go): filter empty segments before mapping Filtering after the map broke the contextual typing from the GoproxyItem[] annotation, widening fallback to string. * refactor(platform/github): use regEx() for merge queue query stripping --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
132 lines
3.6 KiB
TypeScript
132 lines
3.6 KiB
TypeScript
import type { SimpleGit } from 'simple-git';
|
|
import upath from 'upath';
|
|
import { GlobalConfig } from '../../../config/global.ts';
|
|
import { logger } from '../../../logger/index.ts';
|
|
import { createSimpleGit } from '../../../util/git/index.ts';
|
|
import { getHttpUrl } from '../../../util/git/url.ts';
|
|
import { regEx } from '../../../util/regex.ts';
|
|
import { GitRefsDatasource } from '../../datasource/git-refs/index.ts';
|
|
import * as semVerVersioning from '../../versioning/semver/index.ts';
|
|
import type { ExtractConfig, PackageFileContent } from '../types.ts';
|
|
import type { GitModule } from './types.ts';
|
|
|
|
async function getUrl(
|
|
git: SimpleGit,
|
|
gitModulesPath: string,
|
|
submoduleName: string,
|
|
): Promise<string> {
|
|
const path = (
|
|
await createSimpleGit().raw([
|
|
'config',
|
|
'--file',
|
|
gitModulesPath,
|
|
'--get',
|
|
`submodule.${submoduleName}.url`,
|
|
])
|
|
)?.trim();
|
|
if (!path?.startsWith('../') && !path?.startsWith('./')) {
|
|
return path;
|
|
}
|
|
const remoteUrl = (
|
|
await git.raw(['config', '--get', 'remote.origin.url'])
|
|
).trim();
|
|
return new URL(path, `${remoteUrl}/`).href;
|
|
}
|
|
|
|
async function getBranch(
|
|
git: SimpleGit,
|
|
gitModulesPath: string,
|
|
submoduleName: string,
|
|
): Promise<string | null> {
|
|
const branchFromConfig = (
|
|
await createSimpleGit().raw([
|
|
'config',
|
|
'--file',
|
|
gitModulesPath,
|
|
'--get',
|
|
`submodule.${submoduleName}.branch`,
|
|
])
|
|
).trim();
|
|
|
|
return branchFromConfig === '.'
|
|
? (await git.branch(['--list'])).current.trim()
|
|
: branchFromConfig || null;
|
|
}
|
|
|
|
async function getModules(
|
|
git: SimpleGit,
|
|
gitModulesPath: string,
|
|
): Promise<GitModule[]> {
|
|
const res: GitModule[] = [];
|
|
try {
|
|
const modules = (
|
|
(await git.raw([
|
|
'config',
|
|
'--file',
|
|
gitModulesPath,
|
|
'--get-regexp',
|
|
'\\.path',
|
|
])) ?? /* istanbul ignore next: should never happen */ ''
|
|
)
|
|
.trim()
|
|
.split(regEx(/\n/))
|
|
.filter((s) => !!s);
|
|
|
|
for (const line of modules) {
|
|
const [, name, path] = line.split(regEx(/submodule\.(.+?)\.path\s(.+)/));
|
|
res.push({ name, path });
|
|
}
|
|
} catch (err) /* istanbul ignore next */ {
|
|
logger.warn({ err }, 'Error getting git submodules during extract');
|
|
}
|
|
return res;
|
|
}
|
|
|
|
export default async function extractPackageFile(
|
|
_content: string,
|
|
packageFile: string,
|
|
_config: ExtractConfig,
|
|
): Promise<PackageFileContent | null> {
|
|
const localDir = GlobalConfig.get('localDir');
|
|
const git = createSimpleGit({ config: { baseDir: localDir } });
|
|
const gitModulesPath = upath.join(localDir, packageFile);
|
|
|
|
const depNames = await getModules(git, gitModulesPath);
|
|
|
|
if (!depNames.length) {
|
|
return null;
|
|
}
|
|
|
|
const deps = [];
|
|
for (const { name, path } of depNames) {
|
|
try {
|
|
const [currentDigest] = (
|
|
await git.subModule(['status', '--cached', path])
|
|
)
|
|
.trim()
|
|
.replace(regEx(/^[-+]/), '')
|
|
.split(regEx(/\s/));
|
|
const subModuleUrl = await getUrl(git, gitModulesPath, name);
|
|
const httpSubModuleUrl = getHttpUrl(subModuleUrl);
|
|
const branch = await getBranch(git, gitModulesPath, name);
|
|
deps.push({
|
|
depName: path,
|
|
packageName: httpSubModuleUrl,
|
|
sourceUrl: httpSubModuleUrl.replace(regEx(/\.git$/), ''),
|
|
currentValue: branch ?? undefined,
|
|
currentDigest,
|
|
...(semVerVersioning.api.isVersion(branch)
|
|
? { versioning: semVerVersioning.id }
|
|
: {}),
|
|
});
|
|
} catch (err) /* istanbul ignore next */ {
|
|
logger.warn(
|
|
{ err, packageFile },
|
|
'Error mapping git submodules during extraction',
|
|
);
|
|
}
|
|
}
|
|
|
|
return { deps, datasource: GitRefsDatasource.id };
|
|
}
|