Compare commits

..
Author SHA1 Message Date
sneak 82a5df4688 Make **/ in an exclude pattern match zero directories (closes #338)
check / check (push) Waiting to run
The glob library needs a slash on both sides of **, so the anchored
pattern /**/x missed an x directly under the snapshot path, and
a/**/*.log missed a/x.log. As in gitignore, a leading **/ now makes any
pattern, anchored or not, match at every depth, and a pattern holding
/**/ is also compiled with each /**/ made a single slash. The library's
{a,b} alternatives cannot express this: with ** inside them in
mid-pattern they miss paths they should match.

Judgement call: the test for a/**/b uses a/**/*.log, because with a
plain name after the ** the glob library already matched a/b.

Model: opus-5-5
2026-10-13 17:01:21 +00:00
2 changed files with 96 additions and 18 deletions
+51
View File
@@ -578,3 +578,54 @@ func TestExcludePatterns_DoubleStarFileAtEveryDepth(t *testing.T) {
require.Equal(t, 1, result.FilesScanned,
"**/ file pattern should match at the top level and nested")
}
func TestExcludePatterns_AnchoredDoubleStarAtEveryDepth(t *testing.T) {
t.Parallel()
// As in gitignore, /**/ also matches directly under the source dir
fs := setupAnchoredTestFS(t)
scanner, repos, cleanup := createTestScanner(t, fs, []string{"/**/projectname"})
defer cleanup()
ctx := context.Background()
createSnapshotRecord(ctx, t, repos, "test-snapshot")
result, err := scanner.Scan(ctx, "/backup", "test-snapshot")
require.NoError(t, err)
// /**/projectname should exclude BOTH:
// - /backup/projectname/file.txt
// - /backup/otherproject/projectname/file.txt
// Total files: 4, excluded: 2
require.Equal(t, 2, result.FilesScanned,
"/**/ pattern should match at the top level and nested")
}
func TestExcludePatterns_DoubleStarInMiddleMatchesZeroDirectories(t *testing.T) {
t.Parallel()
// As in gitignore, a/**/b matches a/b as well as a/c/b. The last part
// is a glob: with a plain name the glob library already matched a/b.
fs := &afero.MemMapFs{}
files := []string{"/backup/a/x.log", "/backup/a/c/y.log", "/backup/a/c/kept.txt"}
for _, path := range files {
require.NoError(t, fs.MkdirAll(filepath.Dir(path), 0755))
require.NoError(t, afero.WriteFile(fs, path, []byte(path), 0644))
}
scanner, repos, cleanup := createTestScanner(t, fs, []string{"a/**/*.log"})
defer cleanup()
ctx := context.Background()
createSnapshotRecord(ctx, t, repos, "test-snapshot")
result, err := scanner.Scan(ctx, "/backup", "test-snapshot")
require.NoError(t, err)
// a/**/*.log should exclude /backup/a/x.log and /backup/a/c/y.log
// Total files: 3, excluded: 2
require.Equal(t, 1, result.FilesScanned,
"a/**/*.log should match a/x.log as well as a/c/y.log")
}
+45 -18
View File
@@ -2023,33 +2023,60 @@ func compileExcludePatterns(patterns []string) []compiledPattern {
pattern = strings.TrimSuffix(pattern, "/")
// A leading "**/" demands a "/" before the name and so misses an
// entry directly under the source path. An unanchored pattern
// already matches at every depth, so drop the prefix: as in
// gitignore, "**/x" then also matches a top-level "x".
if !anchored {
pattern = strings.TrimPrefix(pattern, "**/")
// entry directly under the source path. It means "at every depth",
// which is what an unanchored pattern already does, so drop the
// prefix and match unanchored: as in gitignore, "**/x" and
// "/**/x" then also match a top-level "x".
if rest, found := strings.CutPrefix(pattern, "**/"); found {
pattern = rest
anchored = false
}
// Compile the glob pattern
// For patterns without path separators, we need to match them as components
// e.g., ".git" should match ".git" anywhere in the path
g, err := glob.Compile(pattern, '/')
if err != nil {
log.Warn("Invalid exclude pattern, skipping", "pattern", p, "error", err)
// Likewise "/**/" inside a pattern demands two slashes, so
// "a/**/b" misses "a/b". As in gitignore it stands for zero or
// more directories, so also compile the pattern with it made a
// single "/". The glob library's {a,b} is no help: with a "**"
// inside it in mid-pattern, it misses paths it should match.
for _, variant := range doubleStarVariants(pattern) {
// For patterns without path separators, we need to match them as components
// e.g., ".git" should match ".git" anywhere in the path
g, err := glob.Compile(variant, '/')
if err != nil {
log.Warn("Invalid exclude pattern, skipping", "pattern", p, "error", err)
continue
break
}
compiled = append(compiled, compiledPattern{
pattern: g,
anchored: anchored,
original: p,
})
}
compiled = append(compiled, compiledPattern{
pattern: g,
anchored: anchored,
original: p,
})
}
return compiled
}
// doubleStarVariants returns pattern once for every way of keeping each
// "/**/" in it or making it a single "/".
func doubleStarVariants(pattern string) []string {
const doubleStar = "/**/"
before, after, found := strings.Cut(pattern, doubleStar)
if !found {
return []string{pattern}
}
var variants []string
for _, rest := range doubleStarVariants(after) {
variants = append(variants, before+doubleStar+rest, before+"/"+rest)
}
return variants
}
// shouldExclude checks if a path should be excluded based on exclude patterns
// filePath is the full path to the file
// rootPath is the root of the backup source directory