Improve performance of globpath with some patterns (#4836)

internal/globpath/globpath.go

@@ -15,8 +15,8 @@ type GlobPath struct {
 	path         string
 	hasMeta      bool
 	hasSuperMeta bool
+	rootGlob     string
 	g            glob.Glob
-	root         string
 }
 
 func Compile(path string) (*GlobPath, error) {
@@ -27,23 +27,25 @@ func Compile(path string) (*GlobPath, error) {
 	}
 
 	// if there are no glob meta characters in the path, don't bother compiling
-	// a glob object or finding the root directory. (see short-circuit in Match)
+	// a glob object
 	if !out.hasMeta || !out.hasSuperMeta {
 		return &out, nil
 	}
 
+	// find the root elements of the object path, the entry point for recursion
+	// when you have a super-meta in your path (which are :
+	// glob(/your/expression/until/first/star/of/super-meta))
+	out.rootGlob = path[:strings.Index(path, "**")+1]
 	var err error
 	if out.g, err = glob.Compile(path, os.PathSeparator); err != nil {
 		return nil, err
 	}
-	// Get the root directory for this filepath
-	out.root = findRootDir(path)
 	return &out, nil
 }
 
 func (g *GlobPath) Match() map[string]os.FileInfo {
+	out := make(map[string]os.FileInfo)
 	if !g.hasMeta {
-		out := make(map[string]os.FileInfo)
 		info, err := os.Stat(g.path)
 		if err == nil {
 			out[g.path] = info
@@ -51,7 +53,6 @@ func (g *GlobPath) Match() map[string]os.FileInfo {
 		return out
 	}
 	if !g.hasSuperMeta {
-		out := make(map[string]os.FileInfo)
 		files, _ := filepath.Glob(g.path)
 		for _, file := range files {
 			info, err := os.Stat(file)
@@ -61,46 +62,19 @@ func (g *GlobPath) Match() map[string]os.FileInfo {
 		}
 		return out
 	}
-	return walkFilePath(g.root, g.g)
-}
-
-// walk the filepath from the given root and return a list of files that match
-// the given glob.
-func walkFilePath(root string, g glob.Glob) map[string]os.FileInfo {
-	matchedFiles := make(map[string]os.FileInfo)
+	roots, err := filepath.Glob(g.rootGlob)
+	if err != nil {
+		return out
+	}
 	walkfn := func(path string, info os.FileInfo, _ error) error {
-		if g.Match(path) {
-			matchedFiles[path] = info
+		if g.g.Match(path) {
+			out[path] = info
 		}
 		return nil
-	}
-	filepath.Walk(root, walkfn)
-	return matchedFiles
-}
 
-// find the root dir of the given path (could include globs).
-// ie:
-//   /var/log/telegraf.conf -> /var/log
-//   /home/** ->               /home
-//   /home/*/** ->             /home
-//   /lib/share/*/*/**.txt ->  /lib/share
-func findRootDir(path string) string {
-	pathItems := strings.Split(path, sepStr)
-	out := sepStr
-	for i, item := range pathItems {
-		if i == len(pathItems)-1 {
-			break
-		}
-		if item == "" {
-			continue
-		}
-		if hasMeta(item) {
-			break
-		}
-		out += item + sepStr
 	}
-	if out != "/" {
-		out = strings.TrimSuffix(out, "/")
+	for _, root := range roots {
+		filepath.Walk(root, walkfn)
 	}
 	return out
 }

internal/globpath/globpath_test.go

@@ -6,7 +6,6 @@ import (
 	"strings"
 	"testing"
 
-	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 )
 
@@ -29,31 +28,32 @@ func TestCompileAndMatch(t *testing.T) {
 	require.NoError(t, err)
 
 	matches := g1.Match()
-	assert.Len(t, matches, 6)
+	require.Len(t, matches, 6)
 	matches = g2.Match()
-	assert.Len(t, matches, 2)
+	require.Len(t, matches, 2)
 	matches = g3.Match()
-	assert.Len(t, matches, 1)
+	require.Len(t, matches, 1)
 	matches = g4.Match()
-	assert.Len(t, matches, 0)
+	require.Len(t, matches, 0)
 	matches = g5.Match()
-	assert.Len(t, matches, 0)
+	require.Len(t, matches, 0)
 }
 
-func TestFindRootDir(t *testing.T) {
+func TestRootGlob(t *testing.T) {
+	dir := getTestdataDir()
 	tests := []struct {
 		input  string
 		output string
 	}{
-		{"/var/log/telegraf.conf", "/var/log"},
-		{"/home/**", "/home"},
-		{"/home/*/**", "/home"},
-		{"/lib/share/*/*/**.txt", "/lib/share"},
+		{dir + "/**", dir + "/*"},
+		{dir + "/nested?/**", dir + "/nested?/*"},
+		{dir + "/ne**/nest*", dir + "/ne*"},
+		{dir + "/nested?/*", ""},
 	}
 
 	for _, test := range tests {
-		actual := findRootDir(test.input)
-		assert.Equal(t, test.output, actual)
+		actual, _ := Compile(test.input)
+		require.Equal(t, actual.rootGlob, test.output)
 	}
 }
 
@@ -64,7 +64,7 @@ func TestFindNestedTextFile(t *testing.T) {
 	require.NoError(t, err)
 
 	matches := g1.Match()
-	assert.Len(t, matches, 1)
+	require.Len(t, matches, 1)
 }
 
 func getTestdataDir() string {