lint: max_line_length supports utf-8

Signed-off-by: Yoan Blanc <[email protected]>

doc.go

@@ -0,0 +1,2 @@
+// Package eclint is a set of linters to for the EditorConfig rules
+package eclint

files.go

@@ -19,7 +19,7 @@ import (
 // When args are given, it recursively walks into them.
 func ListFiles(log logr.Logger, args ...string) ([]string, error) {
 	if len(args) == 0 {
-		fs, err := gitLsFiles(log, ".")
+		fs, err := GitLsFiles(log, ".")
 		if err == nil {
 			return fs, nil
 		}
@@ -28,11 +28,11 @@ func ListFiles(log logr.Logger, args ...string) ([]string, error) {
 		args = append(args, ".")
 	}
 
-	return walk(log, args...)
+	return Walk(log, args...)
 }
 
-// walk iterates on each path item recursively.
-func walk(log logr.Logger, paths ...string) ([]string, error) {
+// Walk iterates on each path item recursively.
+func Walk(log logr.Logger, paths ...string) ([]string, error) {
 	files := make([]string, 0)
 	for _, path := range paths {
 		err := filepath.Walk(path, func(p string, i os.FileInfo, e error) error {
@@ -53,11 +53,11 @@ func walk(log logr.Logger, paths ...string) ([]string, error) {
 	return files, nil
 }
 
-// gitLsFiles returns the list of file based on what is in the git index.
+// GitLsFiles returns the list of file based on what is in the git index.
 //
 // -z is mandatory as some repositories non-ASCII file names which creates
 // quoted and escaped file names.
-func gitLsFiles(log logr.Logger, path string) ([]string, error) {
+func GitLsFiles(log logr.Logger, path string) ([]string, error) {
 	output, err := exec.Command("git", "ls-files", "-z", path).Output()
 	if err != nil {
 		return nil, err

files_test.go

@@ -1,11 +1,12 @@
-package eclint
+package eclint_test
 
 import (
 	"fmt"
 	"os"
 	"testing"
 
 	tlogr "github.com/go-logr/logr/testing"
+	"gitlab.com/greut/eclint"
 )
 
 const (
@@ -17,7 +18,7 @@ const (
 func TestListFiles(t *testing.T) {
 	l := tlogr.TestLogger{}
 	d := testdataSimple
-	fs, err := ListFiles(l, d)
+	fs, err := eclint.ListFiles(l, d)
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -45,7 +46,7 @@ func TestListFilesNoArgs(t *testing.T) {
 		t.Fatal(err)
 	}
 
-	fs, err := ListFiles(l)
+	fs, err := eclint.ListFiles(l)
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -78,7 +79,7 @@ func TestListFilesNoGit(t *testing.T) {
 		t.Fatal(err)
 	}
 
-	fs, err := ListFiles(l)
+	fs, err := eclint.ListFiles(l)
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -90,7 +91,7 @@ func TestListFilesNoGit(t *testing.T) {
 func TestWalk(t *testing.T) {
 	l := tlogr.TestLogger{}
 	d := testdataSimple
-	fs, err := walk(l, d)
+	fs, err := eclint.Walk(l, d)
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -103,7 +104,7 @@ func TestGitLsFiles(t *testing.T) {
 	l := tlogr.TestLogger{}
 	d := testdataSimple
 
-	fs, err := gitLsFiles(l, d)
+	fs, err := eclint.GitLsFiles(l, d)
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -121,7 +122,7 @@ func TestGitLsFilesFailure(t *testing.T) {
 		t.Fatal(err)
 	}
 
-	_, err = gitLsFiles(l, d)
+	_, err = eclint.GitLsFiles(l, d)
 	if err == nil {
 		t.Error("an error was expected")
 	}

lint.go

@@ -64,18 +64,18 @@ func validate(r io.Reader, log logr.Logger, def *editorconfig.Definition) []erro
 		}
 	}
 
-	errs := readLines(r, func(index int, data []byte) error {
+	errs := ReadLines(r, func(index int, data []byte) error {
 		var err error
 
 		// The first line may contain the BOM for detecting some encodings
-		if index == 1 {
+		if index == 0 {
 			if def.Charset != "utf-8" && def.Charset != "latin1" {
 				charset = detectCharsetUsingBOM(data)
 
 				if def.Charset != "" && charset != def.Charset {
 					return validationError{
 						error:    fmt.Sprintf("no %s prefix were found (got %q)", def.Charset, charset),
-						position: 1,
+						position: 0,
 						index:    index,
 						line:     data,
 					}
@@ -136,7 +136,7 @@ func validate(r io.Reader, log logr.Logger, def *editorconfig.Definition) []erro
 		if err == nil && maxLength > 0 && tabWidth > 0 {
 			// Remove any BOM from the first line.
 			d := data
-			if index == 1 && charset != "" {
+			if index == 0 && charset != "" {
 				for _, bom := range [][]byte{utf8Bom} {
 					if bytes.HasPrefix(data, bom) {
 						d = data[len(utf8Bom):]

print.go

@@ -26,10 +26,10 @@ func PrintErrors(opt Option, filename string, errors []error) error {
 			if ve, ok := err.(validationError); ok {
 				log.V(4).Info("lint error", "error", ve)
 				if !opt.Summary {
-					vi := au.Green(strconv.Itoa(ve.index))
-					vp := au.Green(strconv.Itoa(ve.position))
+					vi := au.Green(strconv.Itoa(ve.index + 1))
+					vp := au.Green(strconv.Itoa(ve.position + 1))
 					fmt.Fprintf(stdout, "%s:%s: %s\n", vi, vp, ve.error)
-					l, err := errorAt(au, ve.line, ve.position-1)
+					l, err := errorAt(au, ve.line, ve.position)
 					if err != nil {
 						log.Error(err, "line formating failure", "error", ve)
 						return err

scanner.go

@@ -5,13 +5,13 @@ import (
 	"io"
 )
 
-// lineFunc is the callback for a line.
+// LineFunc is the callback for a line.
 //
 // It returns the line number starting from zero.
-type lineFunc func(int, []byte) error
+type LineFunc func(int, []byte) error
 
-// splitLines works like bufio.ScanLines while keeping the line endings.
-func splitLines(data []byte, atEOF bool) (int, []byte, error) {
+// SplitLines works like bufio.ScanLines while keeping the line endings.
+func SplitLines(data []byte, atEOF bool) (int, []byte, error) {
 	i := 0
 	for i < len(data) {
 		if data[i] == cr {
@@ -38,17 +38,17 @@ func splitLines(data []byte, atEOF bool) (int, []byte, error) {
 	return 0, nil, io.EOF
 }
 
-// readLines consumes the reader and emit each line via the lineFunc
+// ReadLines consumes the reader and emit each line via the LineFunc
 //
-// Line numbering starts at 1. Scanner is pretty smart an will reuse
+// Line numbering starts at 0. Scanner is pretty smart an will reuse
 // its memory structure. This is somehing we explicitly avoid by copying
 // the content to a new slice.
-func readLines(r io.Reader, fn lineFunc) []error {
+func ReadLines(r io.Reader, fn LineFunc) []error {
 	errs := make([]error, 0)
 	sc := bufio.NewScanner(r)
-	sc.Split(splitLines)
+	sc.Split(SplitLines)
 
-	i := 1
+	i := 0
 	for sc.Scan() {
 		l := sc.Bytes()
 		line := make([]byte, len(l))

scanner_test.go

@@ -0,0 +1,70 @@
+package eclint_test
+
+import (
+	"bytes"
+	"fmt"
+	"testing"
+
+	"gitlab.com/greut/eclint"
+)
+
+func TestReadLines(t *testing.T) {
+	tests := []struct {
+		Name     string
+		File     []byte
+		LineFunc eclint.LineFunc
+	}{
+		{
+			Name: "Empty file",
+			File: []byte(""),
+			LineFunc: func(i int, line []byte) error {
+				if i != 0 || len(line) > 0 {
+					return fmt.Errorf("more than one line found (%d), or non epmty line %q", i, line)
+				}
+				return nil
+			},
+		}, {
+			Name: "crlf",
+			File: []byte("\r\n\r\n"),
+			LineFunc: func(i int, line []byte) error {
+				if i > 1 || len(line) > 2 {
+					return fmt.Errorf("more than two lines found (%d), or non empty line %q", i, line)
+				}
+				return nil
+			},
+		}, {
+			Name: "cr",
+			File: []byte("\r\r"),
+			LineFunc: func(i int, line []byte) error {
+				if i > 1 || len(line) > 2 {
+					return fmt.Errorf("more than two lines found (%d), or non empty line %q", i, line)
+				}
+				return nil
+			},
+		}, {
+			Name: "lf",
+			File: []byte("\n\n"),
+			LineFunc: func(i int, line []byte) error {
+				if i > 1 || len(line) > 2 {
+					return fmt.Errorf("more than two lines found (%d), or non empty line %q", i, line)
+				}
+				return nil
+			},
+		},
+	}
+
+	for _, tc := range tests {
+		tc := tc
+
+		t.Run(tc.Name, func(t *testing.T) {
+			t.Parallel()
+
+			r := bytes.NewReader(tc.File)
+			errs := eclint.ReadLines(r, tc.LineFunc)
+			if len(errs) > 0 {
+				t.Errorf("no errors were expected, got some. %s", errs[0])
+				return
+			}
+		})
+	}
+}

validators.go

@@ -113,8 +113,7 @@ func detectCharset(charset string, data []byte) error {
 
 	if len(results) > 0 {
 		return validationError{
-			error:    fmt.Sprintf("detected charset %q does not match expected %q", results[0].Charset, charset),
-			position: 1,
+			error: fmt.Sprintf("detected charset %q does not match expected %q", results[0].Charset, charset),
 		}
 	}
 
@@ -146,15 +145,15 @@ func indentStyle(style string, size int, data []byte) error {
 		if data[i] == x {
 			return validationError{
 				error:    fmt.Sprintf("indentation style mismatch expected %q (%s) got %q", c, style, x),
-				position: i + 1,
+				position: i,
 			}
 		}
 		if data[i] == cr || data[i] == lf || (size > 0 && i%size == 0) {
 			break
 		}
 		return validationError{
 			error:    fmt.Sprintf("indentation size doesn't match expected %d, got %d", size, i),
-			position: i + 1,
+			position: i,
 		}
 	}
 
@@ -170,7 +169,7 @@ func trimTrailingWhitespace(data []byte) error {
 		if data[i] == space || data[i] == tab {
 			return validationError{
 				error:    "line has some trailing whitespaces",
-				position: i + 1,
+				position: i,
 			}
 		}
 		break
@@ -198,7 +197,7 @@ func checkBlockComment(i int, prefix []byte, data []byte) error {
 		if !bytes.HasPrefix(data[i:], prefix) {
 			return validationError{
 				error:    fmt.Sprintf("block_comment prefix %q was expected inside a block comment", string(prefix)),
-				position: i + 1,
+				position: i,
 			}
 		}
 		break
@@ -245,7 +244,7 @@ func MaxLineLength(maxLength int, tabWidth int, data []byte) error {
 	if length > maxLength {
 		return validationError{
 			error:    fmt.Sprintf("line is too long (%d > %d)", length, maxLength),
-			position: breakingPosition + 1,
+			position: breakingPosition,
 		}
 	}