globpath refactor into pkg separate from filestat

plugins/inputs/filestat/filestat.go

@@ -5,17 +5,12 @@ import (
 	"fmt"
 	"io"
 	"os"
-	"path/filepath"
-	"strings"
-
-	"github.com/gobwas/glob"
 
 	"github.com/influxdata/telegraf"
+	"github.com/influxdata/telegraf/internal/globpath"
 	"github.com/influxdata/telegraf/plugins/inputs"
 )
 
-var sepStr = fmt.Sprintf("%v", string(os.PathSeparator))
-
 const sampleConfig = `
   ## Files to gather stats about.
   ## These accept standard unix glob matching rules, but with the addition of
@@ -29,16 +24,13 @@ type FileStat struct {
 	Md5   bool
 	Files []string
 
-	// maps full file paths to glob obj
-	globs map[string]glob.Glob
-	// maps full file paths to their root dir
-	roots map[string]string
+	// maps full file paths to globmatch obj
+	globs map[string]*globpath.GlobPath
 }
 
 func NewFileStat() *FileStat {
 	return &FileStat{
-		globs: make(map[string]glob.Glob),
-		roots: make(map[string]string),
+		globs: make(map[string]*globpath.GlobPath),
 	}
 }
 
@@ -56,27 +48,14 @@ func (f *FileStat) Gather(acc telegraf.Accumulator) error {
 		// Get the compiled glob object for this filepath
 		g, ok := f.globs[filepath]
 		if !ok {
-			if g, err = glob.Compile(filepath, os.PathSeparator); err != nil {
+			if g, err = globpath.Compile(filepath); err != nil {
 				errS += err.Error() + " "
 				continue
 			}
 			f.globs[filepath] = g
 		}
-		// Get the root directory for this filepath
-		root, ok := f.roots[filepath]
-		if !ok {
-			root = findRootDir(filepath)
-			f.roots[filepath] = root
-		}
 
-		var matches []string
-		// Do not walk file tree if we don't have to.
-		if !hasMeta(filepath) {
-			matches = []string{filepath}
-		} else {
-			matches = walkFilePath(f.roots[filepath], f.globs[filepath])
-		}
-		for _, file := range matches {
+		for _, file := range g.Match() {
 			tags := map[string]string{
 				"file": file,
 			}
@@ -118,20 +97,6 @@ func (f *FileStat) Gather(acc telegraf.Accumulator) error {
 	return nil
 }
 
-// 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) []string {
-	matchedFiles := []string{}
-	walkfn := func(path string, _ os.FileInfo, _ error) error {
-		if g.Match(path) {
-			matchedFiles = append(matchedFiles, path)
-		}
-		return nil
-	}
-	filepath.Walk(root, walkfn)
-	return matchedFiles
-}
-
 // Read given file and calculate an md5 hash.
 func getMd5(file string) (string, error) {
 	of, err := os.Open(file)
@@ -149,35 +114,6 @@ func getMd5(file string) (string, error) {
 	return fmt.Sprintf("%x", hash.Sum(nil)), nil
 }
 
-// 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)
-	outpath := sepStr
-	for i, item := range pathItems {
-		if i == len(pathItems)-1 {
-			break
-		}
-		if item == "" {
-			continue
-		}
-		if hasMeta(item) {
-			break
-		}
-		outpath += item + sepStr
-	}
-	return outpath
-}
-
-// hasMeta reports whether path contains any magic glob characters.
-func hasMeta(path string) bool {
-	return strings.IndexAny(path, "*?[") >= 0
-}
-
 func init() {
 	inputs.Add("filestat", func() telegraf.Input {
 		return NewFileStat()

plugins/inputs/filestat/filestat_test.go

@@ -164,23 +164,6 @@ func TestGatherSuperAsterisk(t *testing.T) {
 	acc.AssertContainsTaggedFields(t, "filestat", fields3, tags3)
 }
 
-func TestFindRootDir(t *testing.T) {
-	tests := []struct {
-		input  string
-		output string
-	}{
-		{"/var/log/telegraf.conf", "/var/log/"},
-		{"/home/**", "/home/"},
-		{"/home/*/**", "/home/"},
-		{"/lib/share/*/*/**.txt", "/lib/share/"},
-	}
-
-	for _, test := range tests {
-		actual := findRootDir(test.input)
-		assert.Equal(t, test.output, actual)
-	}
-}
-
 func TestGetMd5(t *testing.T) {
 	dir := getTestdataDir()
 	md5, err := getMd5(dir + "test.conf")