fix: address codex review round 3

glob leaked VCS internals when the model rooted the search AT a VCS
directory (path: '.git' or 'sub/.git'): the prune glob !**/.git is
matched against root-prefixed candidate paths, which never end in the
directory name when the walk starts inside it. Pair each VCS exclude
with a contents glob (!**/<name>/**), verified empirically to exclude
relative, nested, and absolute VCS roots while leaving broad searches
untouched. Pinned by the command-construction test and a real-rg
integration case rooting at .git.
This commit is contained in:
Dudu-0223
2026-07-09 21:47:39 +08:00
parent 590f520949
commit 460a58639a
3 changed files with 24 additions and 6 deletions

View File

@@ -29,9 +29,12 @@ export const GLOB_MAX_RESULTS = 100
/**
* Directory names ripgrep must never descend into for a discovery listing: VCS
* metadata stores. `--no-ignore --hidden` would otherwise surface them in every
* broad search. Each is excluded with a negated any-depth `--glob` (see
* {@link buildGlobCommand}), which matches — and prunes — the directory
* wherever it appears.
* broad search. Each name is excluded with TWO negated `--glob`s (see
* {@link buildGlobCommand}): an any-depth directory glob that matches — and
* prunes — the directory during traversal, and a contents glob that still
* excludes the internals when the search root itself is at or inside the
* directory (an explicit `path` of `.git` or `sub/.git`), where the prune glob
* alone never matches.
*/
export const GLOB_VCS_EXCLUDES: readonly string[] = ['.git', '.svn', '.hg', '.bzr', '.jj', '.sl']
@@ -81,7 +84,14 @@ export function buildGlobCommand(input: GlobInput): string {
'rg --files',
`--glob=${singleQuote(input.pattern)}`,
'--sort=modified --no-ignore --hidden',
...GLOB_VCS_EXCLUDES.map(name => `--glob=${singleQuote(`!**/${name}`)}`),
// Two negated globs per VCS name: the bare form prunes the directory
// during traversal; the /** form still excludes the contents when the
// search root is AT or INSIDE the directory (where the bare form,
// matched against root-prefixed paths, never fires).
...GLOB_VCS_EXCLUDES.flatMap(name => [
`--glob=${singleQuote(`!**/${name}`)}`,
`--glob=${singleQuote(`!**/${name}/**`)}`,
]),
]
if (input.path !== undefined) parts.push('--', singleQuote(input.path))
return parts.join(' ')

View File

@@ -87,6 +87,12 @@ describe.skipIf(!hasRg)('search tools over the real bash executor + real rg', ()
expect(text(await call('glob', { pattern: '*.nomatch' }))).toBe('No files found')
})
it('excludes VCS internals even when the search root IS the VCS directory', async () => {
// The prune glob alone never matches root-prefixed paths when rg is
// rooted at .git; the paired contents glob keeps the exclusion airtight.
expect(text(await call('glob', { pattern: '*', path: '.git' }))).toBe('No files found')
})
it('classifies an invalid glob as SEARCH_INVALID_PATTERN', async () => {
const result = await call('glob', { pattern: '[' })
expect(result.isError).toBe(true)

View File

@@ -204,11 +204,13 @@ describe('config validation', () => {
})
describe('command construction (shell-safe)', () => {
it('glob: fixed rg --files template with quoted pattern and VCS excludes', () => {
it('glob: fixed rg --files template with quoted pattern and paired VCS excludes', () => {
const command = buildGlobCommand({ pattern: '**/*.ts' })
expect(command).toBe(
"rg --files --glob='**/*.ts' --sort=modified --no-ignore --hidden "
+ "--glob='!**/.git' --glob='!**/.svn' --glob='!**/.hg' --glob='!**/.bzr' --glob='!**/.jj' --glob='!**/.sl'",
+ "--glob='!**/.git' --glob='!**/.git/**' --glob='!**/.svn' --glob='!**/.svn/**' "
+ "--glob='!**/.hg' --glob='!**/.hg/**' --glob='!**/.bzr' --glob='!**/.bzr/**' "
+ "--glob='!**/.jj' --glob='!**/.jj/**' --glob='!**/.sl' --glob='!**/.sl/**'",
)
})