Skip to content

Commit

Permalink
feat: add wcwidth package
Browse files Browse the repository at this point in the history
This package implements an interface on top of golang.org/x/text/width
to calculate the width of runes and strings similar to `wcwidth` and
`wcswidth` methods. It's a drop-in replacement to go-runewidth without
multi-rune emojis support i.e. ZWJ (zero-width joiner) is ignored.
  • Loading branch information
aymanbagabas committed Aug 29, 2024
1 parent ec9fda2 commit 0336e39
Show file tree
Hide file tree
Showing 6 changed files with 163 additions and 42 deletions.
1 change: 1 addition & 0 deletions go.work
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,7 @@ use (
./sshkey
./term
./termios
./wcwidth
./windows
./xpty
)
47 changes: 5 additions & 42 deletions go.work.sum
Original file line number Diff line number Diff line change
@@ -1,53 +1,16 @@
github.com/acarl005/stripansi v0.0.0-20180116102854-5a71ef0e047d/go.mod h1:asat636LX7Bqt5lYEZ27JNDcqxfjdBQuJ/MM4CN/Lzo=
github.com/anmitsu/go-shlex v0.0.0-20200514113438-38f4b401e2be/go.mod h1:ySMOLuWl6zY27l47sB3qLNK6tF2fkHG55UZxx8oIVo4=
github.com/charmbracelet/bubbletea v0.26.1 h1:xujcQeF73rh4jwu3+zhfQsvV18x+7zIjlw7/CYbzGJ0=
github.com/charmbracelet/bubbletea v0.26.1/go.mod h1:FzKr7sKoO8iFVcdIBM9J0sJOcQv5nDQaYwsee3kpbgo=
github.com/charmbracelet/bubbletea v0.26.5/go.mod h1:dz8CWPlfCCGLFbBlTY4N7bjLiyOGDJEnd2Muu7pOWhk=
github.com/MakeNowJust/heredoc v1.0.0/go.mod h1:mG5amYoWBHf8vpLOuehzbGGw0EHxpZZ6lCpQ4fNJ8LE=
github.com/charmbracelet/harmonica v0.2.0/go.mod h1:KSri/1RMQOZLbw7AHqgcBycp8pgJnQMYYT8QZRqZ1Ao=
github.com/charmbracelet/lipgloss v0.11.0/go.mod h1:1UdRTH9gYgpcdNN5oBtjbu/IzNKtzVtb7sqN1t9LNn8=
github.com/charmbracelet/lipgloss v0.12.0/go.mod h1:beLlcmkF7MWA+5UrKKIRo/VJ21xGXr7YJ9miWfdMRIU=
github.com/charmbracelet/ssh v0.0.0-20240515141028-546b2ee33a4d/go.mod h1:8/Ve8iGRRIGFM1kepYfRF2pEOF5Y3TEZYoJaA54228U=
github.com/charmbracelet/x/errors v0.0.0-20240117030013-d31dba354651/go.mod h1:2P0UgXMEa6TsToMSuFqKFQR+fZTO9CNGUNokkPatT/0=
github.com/charmbracelet/x/exp/term v0.0.0-20240524151031-ff83003bf67a/go.mod h1:YBotIGhfoWhHDlnUpJMkjebGV2pdGRCn1Y4/Nk/vVcU=
github.com/containerd/console v1.0.4-0.20230313162750-1ae8d489ac81/go.mod h1:YynlIjWYF8myEu6sdkwKIvGQq+cOckRm6So2avqoYAk=
github.com/google/go-cmp v0.5.8/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
github.com/kylelemons/godebug v1.1.0/go.mod h1:9/0rRGxNHcop5bhtWyNeEfOS8JIWk580+fNqagV/RAw=
github.com/mattn/go-isatty v0.0.19/go.mod h1:W+V8PltTTMOvKvAeJH7IuucS94S2C6jfK/D7dTCTo3Y=
github.com/mattn/go-runewidth v0.0.15/go.mod h1:Jdepj2loyihRzMpdS35Xk/zdY8IAYHsh153qUoGf23w=
github.com/muesli/reflow v0.3.0/go.mod h1:pbwTDkVPibjO2kyvBQRBxTWEEGDGq0FlB1BIKtnHY/8=
github.com/sahilm/fuzzy v0.1.1-0.20230530133925-c48e322e2a8f/go.mod h1:VFvziUEIMCrT6A6tw2RFIXPXXmzXbOsSHF0DOI8ZK9Y=
github.com/stretchr/objx v0.5.2/go.mod h1:FRsXN1f5AsAjCGJKqEizvkpNtU+EGNCLh3NxZ/8L+MA=
github.com/rivo/uniseg v0.4.4/go.mod h1:FN3SvrM+Zdj16jyLfmOkMNblXMcoc8DfTHruCPUcx88=
github.com/sahilm/fuzzy v0.1.1/go.mod h1:VFvziUEIMCrT6A6tw2RFIXPXXmzXbOsSHF0DOI8ZK9Y=
github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY=
golang.org/x/crypto v0.18.0/go.mod h1:R0j02AL6hcrfOiy9T4ZYp/rcWeMxM3L6QYxlOuEG1mg=
golang.org/x/exp v0.0.0-20220909182711-5c715a9e8561/go.mod h1:cyybsKvd6eL0RnXn6p/Grxp8F5bW7iYuBgsNCOHpMYE=
golang.org/x/exp v0.0.0-20240613232115-7f521ea00fb8 h1:yixxcjnhBmY0nkL253HFVIm0JsFHwrHdT3Yh6szTnfY=
golang.org/x/exp v0.0.0-20240613232115-7f521ea00fb8/go.mod h1:jj3sYF3dwk5D+ghuXyeI3r5MFf+NT2An6/9dOA95KSI=
golang.org/x/mod v0.6.0-dev.0.20220419223038-86c51ed26bb4/go.mod h1:jJ57K6gSWd91VN4djpZkiMVwK6gcyfeH4XE8wZrZaV4=
golang.org/x/mod v0.8.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs=
golang.org/x/mod v0.13.0/go.mod h1:hTbmBsO62+eylJbnUtE2MGJUyE7QWk4xUqPFrRgJ+7c=
golang.org/x/mod v0.14.0/go.mod h1:hTbmBsO62+eylJbnUtE2MGJUyE7QWk4xUqPFrRgJ+7c=
golang.org/x/mod v0.17.0/go.mod h1:hTbmBsO62+eylJbnUtE2MGJUyE7QWk4xUqPFrRgJ+7c=
golang.org/x/mod v0.18.0/go.mod h1:hTbmBsO62+eylJbnUtE2MGJUyE7QWk4xUqPFrRgJ+7c=
golang.org/x/net v0.21.0/go.mod h1:bIjVDfnllIU7BJ2DNgfnXvpSvtn8VRwhlsaeUTyUS44=
golang.org/x/net v0.25.0/go.mod h1:JkAGAh7GEvH74S6FOH42FLoXpXbE/aqXSrIQjXgsiwM=
golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.16.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
golang.org/x/sys v0.18.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
golang.org/x/sys v0.19.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
golang.org/x/sys v0.20.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
golang.org/x/sys v0.21.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
golang.org/x/sys v0.10.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/telemetry v0.0.0-20240228155512-f48c80bd79b2/go.mod h1:TeRTkGYfJXctD9OcfyVLyj2J3IxLnKwHJR8f4D8a3YE=
golang.org/x/term v0.16.0 h1:m+B6fahuftsE9qjo0VWp2FW0mB3MTJvR0BaMQrq0pmE=
golang.org/x/term v0.16.0/go.mod h1:yn7UURbUtPyrVJPGPq404EukNFxcm/foM+bV/bfcDsY=
golang.org/x/term v0.19.0/go.mod h1:2CuTdWZ7KHSQwUzKva0cbMg6q2DMI3Mmxp+gKJbskEk=
golang.org/x/term v0.21.0/go.mod h1:ooXLefLobQVslOqselCNF4SxFAaoS6KujMbsGzSDmX0=
golang.org/x/term v0.22.0/go.mod h1:F3qCibpT5AMpCRfhfT53vVJwhLtIVHhB9XDjfFvnMI4=
golang.org/x/term v0.23.0/go.mod h1:DgV24QBUrK6jhZXl+20l6UWznPlwAHm1Q1mGHtydmSk=
golang.org/x/text v0.3.8/go.mod h1:E6s5w1FMmriuDzIBO73fBruAKo1PCIq6d2Q6DHfQ8WQ=
golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
golang.org/x/tools v0.1.12 h1:VveCTK38A2rkS8ZqFY25HIDFscX5X9OoEhJd3quQmXU=
golang.org/x/tools v0.1.12/go.mod h1:hNGJHUnrk76NpqgfD5Aqm5Crs+Hm0VOH/i9J2+nxYbc=
golang.org/x/tools v0.6.0/go.mod h1:Xwgl3UAJ/d3gWutnCtw505GrjyAbvKui8lOU390QaIU=
golang.org/x/tools v0.14.0/go.mod h1:uYBEerGOWcJyEORxN+Ek8+TT266gXkNlHdJBwexUsBg=
golang.org/x/tools v0.21.1-0.20240508182429-e35e4ccd0d2d/go.mod h1:aiJjzUbINMkxbQROHiO6hDPo2LHcIPhhQsa9DLh0yGk=
golang.org/x/tools v0.22.0/go.mod h1:aCwcsjqvq7Yqt6TNyX7QMU2enbQ/Gt0bo6krSeEri+c=
5 changes: 5 additions & 0 deletions wcwidth/go.mod
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
module github.com/charmbracelet/x/wcwidth

go 1.18

require golang.org/x/text v0.17.0
2 changes: 2 additions & 0 deletions wcwidth/go.sum
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
golang.org/x/text v0.17.0 h1:XtiM5bkSOt+ewxlOE/aE/AKEHibwj/6gvWMl9Rsh0Qc=
golang.org/x/text v0.17.0/go.mod h1:BuEKDfySbSR4drPmRPG/7iBdf8hvFMuRexcpahXilzY=
45 changes: 45 additions & 0 deletions wcwidth/wcwidth.go
Original file line number Diff line number Diff line change
@@ -0,0 +1,45 @@
// wcwidth is a Go implementation of wcwidth(3) that uses
// golang.org/x/text/width. It is a drop-in replacement for
// github.com/mattn/go-runewidth.
//
// Unlike go-runewidth, wcwidth treats East Asian ambiguous characters as
// single-width characters. This is consistent with the behavior of wcwidth(3).

package wcwidth

import (
"unicode"

"golang.org/x/text/width"
)

// IsComb returns true if r is a Unicode combining character. Alias of:
//
// unicode.Is(unicode.Mn, r)
func IsComb(r rune) bool { return unicode.Is(unicode.Mn, r) }

// RuneWidth returns fixed-width width of rune.
// https://en.wikipedia.org/wiki/Halfwidth_and_fullwidth_forms#In_Unicode
func RuneWidth(r rune) int {
if r == 0 || !unicode.IsPrint(r) || IsComb(r) {
return 0
}
k := width.LookupRune(r)
switch k.Kind() {
case width.EastAsianWide, width.EastAsianFullwidth:
return 2
case width.EastAsianNarrow, width.EastAsianHalfwidth, width.EastAsianAmbiguous, width.Neutral:
return 1
default:
return 0
}
}

// StringWidth returns fixed-width width of string.
// https://en.wikipedia.org/wiki/Halfwidth_and_fullwidth_forms#In_Unicode
func StringWidth(s string) (n int) {
for _, r := range s {
n += RuneWidth(r)
}
return n
}
105 changes: 105 additions & 0 deletions wcwidth/wcwidth_test.go
Original file line number Diff line number Diff line change
@@ -0,0 +1,105 @@
package wcwidth

import (
"testing"
)

// test cases copied from https://github.com/mattn/go-runewidth/raw/master/runewidth_test.go

var stringwidthtests = []struct {
in string
out int
eaout int
}{
{"■㈱の世界①", 10, 12},
{"スター☆", 7, 8},
{"つのだ☆HIRO", 11, 12},
}

func BenchmarkStringWidth(b *testing.B) {
for i := 0; i < b.N; i++ {
StringWidth(stringwidthtests[i%len(stringwidthtests)].in)
}
}

func TestStringWidth(t *testing.T) {
for _, tt := range stringwidthtests {
if out := StringWidth(tt.in); out != tt.out {
t.Errorf("StringWidth(%q) = %d, want %d", tt.in, out, tt.out)
}
}
}

var runewidthtests = []struct {
in rune
out int
eaout int
nseout int
}{
{'世', 2, 2, 2},
{'界', 2, 2, 2},
{'セ', 1, 1, 1},
{'カ', 1, 1, 1},
{'イ', 1, 1, 1},
{'☆', 1, 2, 2}, // double width in ambiguous
{'☺', 1, 1, 2},
{'☻', 1, 1, 2},
{'♥', 1, 2, 2},
{'♦', 1, 1, 2},
{'♣', 1, 2, 2},
{'♠', 1, 2, 2},
{'♂', 1, 2, 2},
{'♀', 1, 2, 2},
{'♪', 1, 2, 2},
{'♫', 1, 1, 2},
{'☼', 1, 1, 2},
{'↕', 1, 2, 2},
{'‼', 1, 1, 2},
{'↔', 1, 2, 2},
{'\x00', 0, 0, 0},
{'\x01', 0, 0, 0},
{'\u0300', 0, 0, 0},
{'\u2028', 0, 0, 0},
{'\u2029', 0, 0, 0},
{'a', 1, 1, 1}, // ASCII classified as "na" (narrow)
{'⟦', 1, 1, 1}, // non-ASCII classified as "na" (narrow)
{'👁', 1, 1, 2},
}

func BenchmarkRuneWidth(b *testing.B) {
for i := 0; i < b.N; i++ {
RuneWidth(runewidthtests[i%len(runewidthtests)].in)
}
}

func TestRuneWidth(t *testing.T) {
for i, tt := range runewidthtests {
if out := RuneWidth(tt.in); out != tt.out {
t.Errorf("case %d: RuneWidth(%q) = %d, want %d", i, tt.in, out, tt.out)
}
}
}

func TestZeroWidthJoiner(t *testing.T) {
tests := []struct {
in string
want int
}{
{"👩", 2},
{"👩\u200d", 2},
{"👩\u200d🍳", 4},
{"\u200d🍳", 2},
{"👨\u200d👨", 4},
{"👨\u200d👨\u200d👧", 6},
{"🏳️\u200d🌈", 3},
{"あ👩\u200d🍳い", 8},
{"あ\u200d🍳い", 6},
{"あ\u200dい", 4},
}

for _, tt := range tests {
if got := StringWidth(tt.in); got != tt.want {
t.Errorf("StringWidth(%q) = %d, want %d", tt.in, got, tt.want)
}
}
}

0 comments on commit 0336e39

Please sign in to comment.