add CRLF handling

Author: bsponge

txtar/archive.go

@@ -1,4 +1,3 @@
-// Copyright 2018 The Go Authors. All rights reserved.
 // Use of this source code is governed by a BSD-style
 // license that can be found in the LICENSE file.
 
@@ -34,14 +33,15 @@ package txtar
 import (
 	"bytes"
 	"fmt"
-	"io/ioutil"
+	"os"
 	"strings"
 )
 
 // An Archive is a collection of files.
 type Archive struct {
 	Comment []byte
 	Files   []File
+	UseCRLF bool
 }
 
 // A File is a single file in an archive.
@@ -55,18 +55,22 @@ type File struct {
 // a.Comment and all a.File[i].Data contain no file marker lines,
 // and all a.File[i].Name is non-empty.
 func Format(a *Archive) []byte {
+	lineSeparator := lf
+	if a.UseCRLF {
+		lineSeparator = crlf
+	}
 	var buf bytes.Buffer
-	buf.Write(fixNL(a.Comment))
+	buf.Write(fixNL(a.Comment, a.UseCRLF))
 	for _, f := range a.Files {
-		fmt.Fprintf(&buf, "-- %s --\n", f.Name)
-		buf.Write(fixNL(f.Data))
+		fmt.Fprintf(&buf, "-- %s --%s", f.Name, lineSeparator)
+		buf.Write(fixNL(f.Data, a.UseCRLF))
 	}
 	return buf.Bytes()
 }
 
 // ParseFile parses the named file as an archive.
 func ParseFile(file string) (*Archive, error) {
-	data, err := ioutil.ReadFile(file)
+	data, err := os.ReadFile(file)
 	if err != nil {
 		return nil, err
 	}
@@ -77,17 +81,23 @@ func ParseFile(file string) (*Archive, error) {
 // The returned Archive holds slices of data.
 func Parse(data []byte) *Archive {
 	a := new(Archive)
+	i := bytes.IndexByte(data, '\n')
+	if i > 0 && data[i-1] == '\r' {
+		a.UseCRLF = true
+	}
 	var name string
-	a.Comment, name, data = findFileMarker(data)
+	a.Comment, name, data = findFileMarker(data, a.UseCRLF)
 	for name != "" {
 		f := File{name, nil}
-		f.Data, name, data = findFileMarker(data)
+		f.Data, name, data = findFileMarker(data, a.UseCRLF)
 		a.Files = append(a.Files, f)
 	}
 	return a
 }
 
 var (
+	crlf          = []byte("\r\n")
+	lf            = []byte("\n")
 	newlineMarker = []byte("\n-- ")
 	marker        = []byte("-- ")
 	markerEnd     = []byte(" --")
@@ -97,15 +107,15 @@ var (
 // extracts the file name, and returns the data before the marker,
 // the file name, and the data after the marker.
 // If there is no next marker, findFileMarker returns before = fixNL(data), name = "", after = nil.
-func findFileMarker(data []byte) (before []byte, name string, after []byte) {
+func findFileMarker(data []byte, useCRLF bool) (before []byte, name string, after []byte) {
 	var i int
 	for {
-		if name, after = isMarker(data[i:]); name != "" {
+		if name, after = isMarker(data[i:], useCRLF); name != "" {
 			return data[:i], name, after
 		}
 		j := bytes.Index(data[i:], newlineMarker)
 		if j < 0 {
-			return fixNL(data), "", nil
+			return fixNL(data, useCRLF), "", nil
 		}
 		i += j + 1 // positioned at start of new possible marker
 	}
@@ -114,27 +124,35 @@ func findFileMarker(data []byte) (before []byte, name string, after []byte) {
 // isMarker checks whether data begins with a file marker line.
 // If so, it returns the name from the line and the data after the line.
 // Otherwise it returns name == "" with an unspecified after.
-func isMarker(data []byte) (name string, after []byte) {
+func isMarker(data []byte, useCRLF bool) (name string, after []byte) {
 	if !bytes.HasPrefix(data, marker) {
 		return "", nil
 	}
 	if i := bytes.IndexByte(data, '\n'); i >= 0 {
-		data, after = data[:i], data[i+1:]
+		if useCRLF && len(data) > 0 && data[i-1] == '\r' {
+			data, after = data[:i-1], data[i+1:]
+		} else {
+			data, after = data[:i], data[i+1:]
+		}
 	}
 	if !(bytes.HasSuffix(data, markerEnd) && len(data) >= len(marker)+len(markerEnd)) {
 		return "", nil
 	}
 	return strings.TrimSpace(string(data[len(marker) : len(data)-len(markerEnd)])), after
 }
 
-// If data is empty or ends in \n, fixNL returns data.
-// Otherwise fixNL returns a new slice consisting of data with a final \n added.
-func fixNL(data []byte) []byte {
-	if len(data) == 0 || data[len(data)-1] == '\n' {
+// If data is empty or ends in lineSeparator, fixNL returns data.
+// Otherwise fixNL returns a new slice consisting of data with a final lineSeparator added.
+func fixNL(data []byte, useCRLF bool) []byte {
+	lineSeparator := lf
+	if useCRLF {
+		lineSeparator = crlf
+	}
+	if len(data) == 0 || (len(data) >= len(lineSeparator) && bytes.Equal(data[len(data)-len(lineSeparator):], lineSeparator)) {
 		return data
 	}
-	d := make([]byte, len(data)+1)
+	d := make([]byte, len(data)+len(lineSeparator))
 	copy(d, data)
-	d[len(data)] = '\n'
+	d = append(d[:len(d)-len(lineSeparator)], lineSeparator...)
 	return d
 }

txtar/archive_test.go

@@ -18,7 +18,7 @@ func TestParse(t *testing.T) {
 		parsed *Archive
 	}{
 		{
-			name: "basic",
+			name: "basic LF",
 			text: `comment1
 comment2
 -- file1 --
@@ -42,6 +42,35 @@ some content
 					{"noNL", []byte("hello world\n")},
 					{"empty filename line", []byte("some content\n-- --\n")},
 				},
+				UseCRLF: false,
+			},
+		},
+		{
+			name: "basic CRLF",
+			text: "comment1\r\n" +
+				"comment2\r\n" +
+				"-- file1 --\r\n" +
+				"File 1 text.\r\n" +
+				"-- foo ---\r\n" +
+				"More file 1 text.\r\n" +
+				"-- file 2 --\r\n" +
+				"File 2 text.\r\n" +
+				"-- empty --\r\n" +
+				"-- noNL --\r\n" +
+				"hello world\r\n" +
+				"-- empty filename line --\r\n" +
+				"some content\r\n" +
+				"-- --\r\n",
+			parsed: &Archive{
+				Comment: []byte("comment1\r\ncomment2\r\n"),
+				Files: []File{
+					{"file1", []byte("File 1 text.\r\n-- foo ---\r\nMore file 1 text.\r\n")},
+					{"file 2", []byte("File 2 text.\r\n")},
+					{"empty", []byte{}},
+					{"noNL", []byte("hello world\r\n")},
+					{"empty filename line", []byte("some content\r\n-- --\r\n")},
+				},
+				UseCRLF: true,
 			},
 		},
 	}
@@ -67,7 +96,7 @@ func TestFormat(t *testing.T) {
 		wanted string
 	}{
 		{
-			name: "basic",
+			name: "basic LF",
 			input: &Archive{
 				Comment: []byte("comment1\ncomment2\n"),
 				Files: []File{
@@ -76,6 +105,7 @@ func TestFormat(t *testing.T) {
 					{"empty", []byte{}},
 					{"noNL", []byte("hello world")},
 				},
+				UseCRLF: false,
 			},
 			wanted: `comment1
 comment2
@@ -90,6 +120,30 @@ File 2 text.
 hello world
 `,
 		},
+		{
+			name: "basic CRLF",
+			input: &Archive{
+				Comment: []byte("comment1\r\ncomment2\r\n"),
+				Files: []File{
+					{"file1", []byte("File 1 text.\r\n-- foo ---\r\nMore file 1 text.\r\n")},
+					{"file 2", []byte("File 2 text.\r\n")},
+					{"empty", []byte{}},
+					{"noNL", []byte("hello world")},
+				},
+				UseCRLF: true,
+			},
+			wanted: "comment1\r\n" +
+				"comment2\r\n" +
+				"-- file1 --\r\n" +
+				"File 1 text.\r\n" +
+				"-- foo ---\r\n" +
+				"More file 1 text.\r\n" +
+				"-- file 2 --\r\n" +
+				"File 2 text.\r\n" +
+				"-- empty --\r\n" +
+				"-- noNL --\r\n" +
+				"hello world\r\n",
+		},
 	}
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {