-
Notifications
You must be signed in to change notification settings - Fork 122
/
string.go
324 lines (300 loc) · 8.93 KB
/
string.go
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
package text
import (
"strings"
"unicode/utf8"
"github.com/mattn/go-runewidth"
"golang.org/x/text/width"
)
// RuneWidth stuff
var (
rwCondition = runewidth.NewCondition()
)
// InsertEveryN inserts the rune every N characters in the string. For ex.:
//
// InsertEveryN("Ghost", '-', 1) == "G-h-o-s-t"
// InsertEveryN("Ghost", '-', 2) == "Gh-os-t"
// InsertEveryN("Ghost", '-', 3) == "Gho-st"
// InsertEveryN("Ghost", '-', 4) == "Ghos-t"
// InsertEveryN("Ghost", '-', 5) == "Ghost"
func InsertEveryN(str string, runeToInsert rune, n int) string {
if n <= 0 {
return str
}
sLen := StringWidthWithoutEscSequences(str)
var out strings.Builder
out.Grow(sLen + (sLen / n))
outLen, esp := 0, escSeqParser{}
for idx, c := range str {
if esp.InSequence() {
esp.Consume(c)
out.WriteRune(c)
continue
}
esp.Consume(c)
if !esp.InSequence() && outLen > 0 && (outLen%n) == 0 && idx != sLen {
out.WriteRune(runeToInsert)
}
out.WriteRune(c)
if !esp.InSequence() {
outLen += RuneWidth(c)
}
}
return out.String()
}
// LongestLineLen returns the length of the longest "line" within the
// argument string. For ex.:
//
// LongestLineLen("Ghost!\nCome back here!\nRight now!") == 15
func LongestLineLen(str string) int {
maxLength, currLength, esp := 0, 0, escSeqParser{}
//fmt.Println(str)
for _, c := range str {
//fmt.Printf("%03d | %03d | %c | %5v | %v | %#v\n", idx, c, c, esp.inEscSeq, esp.Codes(), esp.escapeSeq)
if esp.InSequence() {
esp.Consume(c)
continue
}
esp.Consume(c)
if c == '\n' {
if currLength > maxLength {
maxLength = currLength
}
currLength = 0
} else if !esp.InSequence() {
currLength += RuneWidth(c)
}
}
if currLength > maxLength {
maxLength = currLength
}
return maxLength
}
// OverrideRuneWidthEastAsianWidth can *probably* help with alignment, and
// length calculation issues when dealing with Unicode character-set and a
// non-English language set in the LANG variable.
//
// Set this to 'false' to force the "runewidth" library to pretend to deal with
// English character-set. Be warned that if the text/content you are dealing
// with contains East Asian character-set, this may result in unexpected
// behavior.
//
// References:
// * https://github.com/mattn/go-runewidth/issues/64#issuecomment-1221642154
// * https://github.com/jedib0t/go-pretty/issues/220
// * https://github.com/jedib0t/go-pretty/issues/204
func OverrideRuneWidthEastAsianWidth(val bool) {
rwCondition.EastAsianWidth = val
}
// Pad pads the given string with as many characters as needed to make it as
// long as specified (maxLen). This function does not count escape sequences
// while calculating length of the string. Ex.:
//
// Pad("Ghost", 0, ' ') == "Ghost"
// Pad("Ghost", 3, ' ') == "Ghost"
// Pad("Ghost", 5, ' ') == "Ghost"
// Pad("Ghost", 7, ' ') == "Ghost "
// Pad("Ghost", 10, '.') == "Ghost....."
func Pad(str string, maxLen int, paddingChar rune) string {
strLen := StringWidthWithoutEscSequences(str)
if strLen < maxLen {
str += strings.Repeat(string(paddingChar), maxLen-strLen)
}
return str
}
// ProcessCRLF converts "\r\n" to "\n", and processes lone "\r" by moving the
// cursor/carriage to the start of the line and overwrites the contents
// accordingly. Ex.:
//
// ProcessCRLF("abc") == "abc"
// ProcessCRLF("abc\r\ndef") == "abc\ndef"
// ProcessCRLF("abc\r\ndef\rghi") == "abc\nghi"
// ProcessCRLF("abc\r\ndef\rghi\njkl") == "abc\nghi\njkl"
// ProcessCRLF("abc\r\ndef\rghi\njkl\r") == "abc\nghi\njkl"
// ProcessCRLF("abc\r\ndef\rghi\rjkl\rmn") == "abc\nmnl"
func ProcessCRLF(str string) string {
str = strings.ReplaceAll(str, "\r\n", "\n")
if !strings.Contains(str, "\r") {
return str
}
lines := strings.Split(str, "\n")
for lineIdx, line := range lines {
if !strings.Contains(line, "\r") {
continue
}
lineRunes, newLineRunes := []rune(line), make([]rune, 0)
for idx, realIdx := 0, 0; idx < len(lineRunes); idx++ {
// if a CR, move "cursor" back to beginning of line
if lineRunes[idx] == '\r' {
realIdx = 0
continue
}
// if cursor is not at end, overwrite
if realIdx < len(newLineRunes) {
newLineRunes[realIdx] = lineRunes[idx]
} else { // else append
newLineRunes = append(newLineRunes, lineRunes[idx])
}
realIdx++
}
lines[lineIdx] = string(newLineRunes)
}
return strings.Join(lines, "\n")
}
// RepeatAndTrim repeats the given string until it is as long as maxRunes.
// For ex.:
//
// RepeatAndTrim("", 5) == ""
// RepeatAndTrim("Ghost", 0) == ""
// RepeatAndTrim("Ghost", 5) == "Ghost"
// RepeatAndTrim("Ghost", 7) == "GhostGh"
// RepeatAndTrim("Ghost", 10) == "GhostGhost"
func RepeatAndTrim(str string, maxRunes int) string {
if str == "" || maxRunes == 0 {
return ""
} else if maxRunes == utf8.RuneCountInString(str) {
return str
}
repeatedS := strings.Repeat(str, int(maxRunes/utf8.RuneCountInString(str))+1)
return Trim(repeatedS, maxRunes)
}
// RuneCount is similar to utf8.RuneCountInString, except for the fact that it
// ignores escape sequences while counting. For ex.:
//
// RuneCount("") == 0
// RuneCount("Ghost") == 5
// RuneCount("\x1b[33mGhost\x1b[0m") == 5
// RuneCount("\x1b[33mGhost\x1b[0") == 5
//
// Deprecated: in favor of RuneWidthWithoutEscSequences
func RuneCount(str string) int {
return StringWidthWithoutEscSequences(str)
}
// RuneWidth returns the mostly accurate character-width of the rune. This is
// not 100% accurate as the character width is usually dependent on the
// typeface (font) used in the console/terminal. For ex.:
//
// RuneWidth('A') == 1
// RuneWidth('ツ') == 2
// RuneWidth('⊙') == 1
// RuneWidth('︿') == 2
// RuneWidth(0x27) == 0
func RuneWidth(r rune) int {
return rwCondition.RuneWidth(r)
}
// RuneWidthWithoutEscSequences is similar to RuneWidth, except for the fact
// that it ignores escape sequences while counting. For ex.:
//
// RuneWidthWithoutEscSequences("") == 0
// RuneWidthWithoutEscSequences("Ghost") == 5
// RuneWidthWithoutEscSequences("\x1b[33mGhost\x1b[0m") == 5
// RuneWidthWithoutEscSequences("\x1b[33mGhost\x1b[0") == 5
//
// deprecated: use StringWidthWithoutEscSequences instead
func RuneWidthWithoutEscSequences(str string) int {
return StringWidthWithoutEscSequences(str)
}
// Snip returns the given string with a fixed length. For ex.:
//
// Snip("Ghost", 0, "~") == "Ghost"
// Snip("Ghost", 1, "~") == "~"
// Snip("Ghost", 3, "~") == "Gh~"
// Snip("Ghost", 5, "~") == "Ghost"
// Snip("Ghost", 7, "~") == "Ghost "
// Snip("\x1b[33mGhost\x1b[0m", 7, "~") == "\x1b[33mGhost\x1b[0m "
func Snip(str string, length int, snipIndicator string) string {
if length > 0 {
lenStr := StringWidthWithoutEscSequences(str)
if lenStr > length {
lenStrFinal := length - StringWidthWithoutEscSequences(snipIndicator)
return Trim(str, lenStrFinal) + snipIndicator
}
}
return str
}
// StringWidth is similar to RuneWidth, except it works on a string. For
// ex.:
//
// StringWidth("Ghost 生命"): 10
// StringWidth("\x1b[33mGhost 生命\x1b[0m"): 19
func StringWidth(str string) int {
return rwCondition.StringWidth(str)
}
// StringWidthWithoutEscSequences is similar to RuneWidth, except for the fact
// that it ignores escape sequences while counting. For ex.:
//
// StringWidthWithoutEscSequences("") == 0
// StringWidthWithoutEscSequences("Ghost") == 5
// StringWidthWithoutEscSequences("\x1b[33mGhost\x1b[0m") == 5
// StringWidthWithoutEscSequences("\x1b[33mGhost\x1b[0") == 5
// StringWidthWithoutEscSequences("Ghost 生命"): 10
// StringWidthWithoutEscSequences("\x1b[33mGhost 生命\x1b[0m"): 10
func StringWidthWithoutEscSequences(str string) int {
count, esp := 0, escSeqParser{}
for _, c := range str {
if esp.InSequence() {
esp.Consume(c)
continue
}
esp.Consume(c)
if !esp.InSequence() {
count += RuneWidth(c)
}
}
return count
}
// Trim trims a string to the given length while ignoring escape sequences. For
// ex.:
//
// Trim("Ghost", 3) == "Gho"
// Trim("Ghost", 6) == "Ghost"
// Trim("\x1b[33mGhost\x1b[0m", 3) == "\x1b[33mGho\x1b[0m"
// Trim("\x1b[33mGhost\x1b[0m", 6) == "\x1b[33mGhost\x1b[0m"
func Trim(str string, maxLen int) string {
if maxLen <= 0 {
return ""
}
var out strings.Builder
out.Grow(maxLen)
outLen, esp := 0, escSeqParser{}
for _, sChr := range str {
if esp.InSequence() {
esp.Consume(sChr)
out.WriteRune(sChr)
continue
}
esp.Consume(sChr)
if esp.InSequence() {
out.WriteRune(sChr)
continue
}
if outLen < maxLen {
outLen++
out.WriteRune(sChr)
continue
}
}
return out.String()
}
// Widen is like width.Widen.String() but ignores escape sequences. For ex:
//
// Widen("Ghost 生命"): "Ghost\u3000生命"
// Widen("\x1b[33mGhost 生命\x1b[0m"): "\x1b[33mGhost\u3000生命\x1b[0m"
func Widen(str string) string {
sb := strings.Builder{}
sb.Grow(len(str))
esp := escSeqParser{}
for _, c := range str {
if esp.InSequence() {
sb.WriteRune(c)
esp.Consume(c)
continue
}
esp.Consume(c)
if !esp.InSequence() {
sb.WriteString(width.Widen.String(string(c)))
} else {
sb.WriteRune(c)
}
}
return sb.String()
}