Replace go-runewidth with uniseg

Replace the use of `RuneWidth` and `StringWidth` from `mattn/go-
runewidth` with equivalent functions from `rivo/uniseg`.

It is important to be aware that using `RuneWidth` will not be accurate
as the width of a rune cannot be determined in isolation. This requires
a shift to thinking about grapheme clusters instead.

Unfortunately due to the complexity of identifying grapheme clusters,
there has been some signifcant performance regressions in two
functions:

- PrintableRuneWidth: 10x slower
- TruncateString: 4x slower

Two other functions have had performance improvements:

- MarginString: 2x faster
- PaddingString: 2x faster

The documentation for `rivo/uniseg` mentions the use of `Step` and
`StepString` performing "orders of magnitude faster" than using the
`NewGraphemes` method. However, implementing these changes only
resulted in a 10% performance increase.

Signed-off-by: Michael Lorant <[email protected]>

ansi/buffer.go

@@ -3,7 +3,7 @@ package ansi
 import (
 	"bytes"
 
-	"github.com/mattn/go-runewidth"
+	"github.com/rivo/uniseg"
 )
 
 // Buffer is a buffer aware of ANSI escape sequences.
@@ -19,22 +19,22 @@ func (w Buffer) PrintableRuneWidth() int {
 
 // PrintableRuneWidth returns the cell width of the given string.
 func PrintableRuneWidth(s string) int {
-	var n int
+	var n []rune
 	var ansi bool
 
 	for _, c := range s {
-		if c == Marker {
+		switch {
+		case c == Marker:
 			// ANSI escape sequence
 			ansi = true
-		} else if ansi {
-			if IsTerminator(c) {
-				// ANSI sequence terminated
-				ansi = false
-			}
-		} else {
-			n += runewidth.RuneWidth(c)
+		case ansi && IsTerminator(c):
+			// ANSI sequence terminated
+			ansi = false
+		case ansi:
+		default:
+			n = append(n, c)
 		}
 	}
 
-	return n
+	return uniseg.StringWidth(string(n))
 }

go.mod

@@ -2,4 +2,4 @@ module github.com/muesli/reflow
 
 go 1.13
 
-require github.com/mattn/go-runewidth v0.0.14
+require github.com/rivo/uniseg v0.4.4

go.sum

@@ -1,4 +1,2 @@
-github.com/mattn/go-runewidth v0.0.14 h1:+xnbZSEeDbOIg5/mE6JF0w6n9duR1l3/WmbinWVwUuU=
-github.com/mattn/go-runewidth v0.0.14/go.mod h1:Jdepj2loyihRzMpdS35Xk/zdY8IAYHsh153qUoGf23w=
-github.com/rivo/uniseg v0.2.0 h1:S1pD9weZBuJdFmowNwbpi7BJ8TNftyUImj/0WQi72jY=
-github.com/rivo/uniseg v0.2.0/go.mod h1:J6wj4VEh+S6ZtnVlnTBMWIodfgj8LQOQFoIToxlJtxc=
+github.com/rivo/uniseg v0.4.4 h1:8TfxU8dW6PdqD27gjM8MVNuicgxIjxpm4K7x4jp8sis=
+github.com/rivo/uniseg v0.4.4/go.mod h1:FN3SvrM+Zdj16jyLfmOkMNblXMcoc8DfTHruCPUcx88=

padding/padding.go

@@ -5,8 +5,8 @@ import (
 	"io"
 	"strings"
 
-	"github.com/mattn/go-runewidth"
 	"github.com/muesli/reflow/ansi"
+	"github.com/rivo/uniseg"
 )
 
 type PaddingFunc func(w io.Writer)
@@ -71,7 +71,7 @@ func (w *Writer) Write(b []byte) (int, error) {
 				w.ansi = false
 			}
 		} else {
-			w.lineLen += runewidth.StringWidth(string(c))
+			w.lineLen += uniseg.StringWidth(string(c))
 
 			if c == '\n' {
 				// end of current line

truncate/truncate.go

@@ -4,7 +4,7 @@ import (
 	"bytes"
 	"io"
 
-	"github.com/mattn/go-runewidth"
+	"github.com/rivo/uniseg"
 
 	"github.com/muesli/reflow/ansi"
 )
@@ -79,17 +79,20 @@ func (w *Writer) Write(b []byte) (int, error) {
 	w.width -= uint(tw)
 	var curWidth uint
 
-	for _, c := range string(b) {
-		if c == ansi.Marker {
+	gr := uniseg.NewGraphemes(string(b))
+	for gr.Next() {
+		rs := gr.Runes()
+
+		switch {
+		case len(rs) == 1 && rs[0] == ansi.Marker:
 			// ANSI escape sequence
 			w.ansi = true
-		} else if w.ansi {
-			if ansi.IsTerminator(c) {
-				// ANSI sequence terminated
-				w.ansi = false
-			}
-		} else {
-			curWidth += uint(runewidth.RuneWidth(c))
+		case len(rs) == 1 && w.ansi && ansi.IsTerminator(rs[0]):
+			// ANSI sequence terminated
+			w.ansi = false
+		case w.ansi:
+		default:
+			curWidth += uint(gr.Width())
 		}
 
 		if curWidth > w.width {
@@ -100,7 +103,7 @@ func (w *Writer) Write(b []byte) (int, error) {
 			return n, err
 		}
 
-		_, err := w.ansiWriter.Write([]byte(string(c)))
+		_, err := w.ansiWriter.Write([]byte(gr.Str()))
 		if err != nil {
 			return 0, err
 		}

wrap/wrap.go

@@ -5,8 +5,8 @@ import (
 	"strings"
 	"unicode"
 
-	"github.com/mattn/go-runewidth"
 	"github.com/muesli/reflow/ansi"
+	"github.com/rivo/uniseg"
 )
 
 var (
@@ -67,6 +67,7 @@ func String(s string, limit int) string {
 
 func (w *Wrap) Write(b []byte) (int, error) {
 	s := strings.Replace(string(b), "\t", strings.Repeat(" ", w.TabWidth), -1)
+
 	if !w.KeepNewlines {
 		s = strings.Replace(s, "\n", "", -1)
 	}
@@ -78,37 +79,39 @@ func (w *Wrap) Write(b []byte) (int, error) {
 		return w.buf.Write(b)
 	}
 
-	for _, c := range s {
-		if c == ansi.Marker {
+	gr := uniseg.NewGraphemes(s)
+	for gr.Next() {
+		rs := gr.Runes()
+
+		switch {
+		case len(rs) == 1 && rs[0] == ansi.Marker:
 			w.ansi = true
-		} else if w.ansi {
-			if ansi.IsTerminator(c) {
-				w.ansi = false
-			}
-		} else if inGroup(w.Newline, c) {
+		case len(rs) == 1 && w.ansi && ansi.IsTerminator(rs[0]):
+			w.ansi = false
+		case w.ansi:
+		case len(rs) == 1 && inGroup(w.Newline, rs[0]):
 			w.addNewLine()
 			w.forcefulNewline = false
 			continue
-		} else {
-			width := runewidth.RuneWidth(c)
-
-			if w.lineLen+width > w.Limit {
+		default:
+			if w.lineLen + gr.Width() > w.Limit {
 				w.addNewLine()
 				w.forcefulNewline = true
 			}
 
-			if w.lineLen == 0 {
-				if w.forcefulNewline && !w.PreserveSpace && unicode.IsSpace(c) {
+			switch {
+			case w.lineLen == 0:
+				if len(rs) == 1 && w.forcefulNewline && !w.PreserveSpace && unicode.IsSpace(rs[0]) {
 					continue
 				}
-			} else {
+			default:
 				w.forcefulNewline = false
 			}
 
-			w.lineLen += width
+			w.lineLen += gr.Width()
 		}
 
-		_, _ = w.buf.WriteRune(c)
+		_, _ = w.buf.WriteString(gr.Str())
 	}
 
 	return len(b), nil