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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660
|
package tview
import (
"fmt"
"math/rand"
"regexp"
"strconv"
"strings"
"unicode/utf8"
"github.com/gdamore/tcell/v2"
"github.com/rivo/uniseg"
)
// escapedTagPattern matches an escaped tag, e.g. "[red[]", at the beginning of
// a string.
var escapedTagPattern = regexp.MustCompile(`^\[[^\[\]]+\[+\]`)
// stepOptions is a bit field of options for [step]. A value of 0 results in
// [step] having the same behavior as uniseg.Step, i.e. no tview-related parsing
// is performed.
type stepOptions int
// Bit fields for [stepOptions].
const (
stepOptionsNone stepOptions = 0
stepOptionsStyle stepOptions = 1 << iota // Parse style tags.
stepOptionsRegion // Parse region tags.
)
// stepState represents the current state of the parser implemented in [step].
type stepState struct {
unisegState int // The state of the uniseg parser.
boundaries int // Information about boundaries, as returned by uniseg.Step.
style tcell.Style // The current style.
region string // The current region.
escapedTagState int // States for parsing escaped tags (defined in [step]).
grossLength int // The length of the cluster, including any tags not returned.
// The styles for the initial call to [step].
initialForeground tcell.Color
initialBackground tcell.Color
initialAttributes tcell.AttrMask
}
// IsWordBoundary returns true if the boundary between the returned grapheme
// cluster and the one following it is a word boundary.
func (s *stepState) IsWordBoundary() bool {
return s.boundaries&uniseg.MaskWord != 0
}
// IsSentenceBoundary returns true if the boundary between the returned grapheme
// cluster and the one following it is a sentence boundary.
func (s *stepState) IsSentenceBoundary() bool {
return s.boundaries&uniseg.MaskSentence != 0
}
// LineBreak returns whether the string can be broken into the next line after
// the returned grapheme cluster. If optional is true, the line break is
// optional. If false, the line break is mandatory, e.g. after a newline
// character.
func (s *stepState) LineBreak() (lineBreak, optional bool) {
switch s.boundaries & uniseg.MaskLine {
case uniseg.LineCanBreak:
return true, true
case uniseg.LineMustBreak:
return true, false
}
return false, false // uniseg.LineDontBreak.
}
// Width returns the grapheme cluster's width in cells.
func (s *stepState) Width() int {
return s.boundaries >> uniseg.ShiftWidth
}
// GrossLength returns the grapheme cluster's length in bytes, including any
// tags that were parsed but not explicitly returned.
func (s *stepState) GrossLength() int {
return s.grossLength
}
// Style returns the style for the grapheme cluster.
func (s *stepState) Style() tcell.Style {
return s.style
}
// step uses uniseg.Step to iterate over the grapheme clusters of a string but
// (optionally) also parses the string for style or region tags.
//
// This function can be called consecutively to extract all grapheme clusters
// from str, without returning any contained (parsed) tags. The return values
// are the first grapheme cluster, the remaining string, and the new state. Pass
// the remaining string and the returned state to the next call. If the rest
// string is empty, parsing is complete. Call the returned state's methods for
// boundary and width information.
//
// The returned cluster may be empty if the given string consists of only
// (parsed) tags. The boundary and width information will be meaningless in
// this case but the style will describe the style at the end of the string.
//
// Pass nil for state on the first call. This will assume an initial style with
// [Styles.PrimitiveBackgroundColor] as the background color and
// [Styles.PrimaryTextColor] as the text color, no current region. If you want
// to start with a different style or region, you can set the state accordingly
// but you must then set [state.unisegState] to -1.
//
// There is no need to call uniseg.HasTrailingLineBreakInString on the last
// non-empty cluster as this function will do this for you and adjust the
// returned boundaries accordingly.
func step(str string, state *stepState, opts stepOptions) (cluster, rest string, newState *stepState) {
// Set up initial state.
if state == nil {
state = &stepState{
unisegState: -1,
style: tcell.StyleDefault.Background(Styles.PrimitiveBackgroundColor).Foreground(Styles.PrimaryTextColor),
}
}
if state.unisegState < 0 {
state.initialForeground, state.initialBackground, state.initialAttributes = state.style.Decompose()
}
if len(str) == 0 {
newState = state
return
}
// Get a grapheme cluster.
preState := state.unisegState
cluster, rest, state.boundaries, state.unisegState = uniseg.StepString(str, preState)
state.grossLength = len(cluster)
if rest == "" {
if !uniseg.HasTrailingLineBreakInString(cluster) {
state.boundaries &^= uniseg.MaskLine
}
}
// Parse tags.
if opts != 0 {
const (
etNone int = iota
etStart
etChar
etClosing
)
// Finite state machine for escaped tags.
switch state.escapedTagState {
case etStart:
if cluster[0] == '[' || cluster[0] == ']' { // Invalid escaped tag.
state.escapedTagState = etNone
} else { // Other characters are allowed.
state.escapedTagState = etChar
}
case etChar:
if cluster[0] == ']' { // In theory, this should not happen.
state.escapedTagState = etNone
} else if cluster[0] == '[' { // Starting closing sequence.
// Swallow the first one.
cluster, rest, state.boundaries, state.unisegState = uniseg.StepString(rest, preState)
state.grossLength += len(cluster)
if cluster[0] == ']' {
state.escapedTagState = etNone
} else {
state.escapedTagState = etClosing
}
} // More characters. Remain in etChar.
case etClosing:
if cluster[0] != '[' {
state.escapedTagState = etNone
}
}
// Regular tags.
if state.escapedTagState == etNone {
if cluster[0] == '[' {
// We've already opened a tag. Parse it.
length, style, region := parseTag(str, state)
if length > 0 {
state.style = style
state.region = region
cluster, rest, state.boundaries, state.unisegState = uniseg.StepString(str[length:], preState)
state.grossLength = len(cluster) + length
if rest == "" {
if !uniseg.HasTrailingLineBreakInString(cluster) {
state.boundaries &^= uniseg.MaskLine
}
}
}
// Is this an escaped tag?
if escapedTagPattern.MatchString(str[length:]) {
state.escapedTagState = etStart
}
}
if len(rest) > 0 && rest[0] == '[' {
// A tag might follow the cluster. If so, we need to fix the state
// for the boundaries to be correct.
if length, _, _ := parseTag(rest, state); length > 0 {
if len(rest) > length {
_, l := utf8.DecodeRuneInString(rest[length:])
cluster += rest[length : length+l]
}
var taglessRest string
cluster, taglessRest, state.boundaries, state.unisegState = uniseg.StepString(cluster, preState)
if taglessRest == "" {
if !uniseg.HasTrailingLineBreakInString(cluster) {
state.boundaries &^= uniseg.MaskLine
}
}
}
}
}
}
newState = state
return
}
// parseTag parses str for consecutive style and/or region tags, assuming that
// str starts with the opening bracket for the first tag. It returns the string
// length of all valid tags (0 if the first tag is not valid) and the updated
// style and region for valid tags (based on the provided state).
func parseTag(str string, state *stepState) (length int, style tcell.Style, region string) {
// Automata states for parsing tags.
const (
tagStateNone = iota
tagStateDoneTag
tagStateStart
tagStateRegionStart
tagStateEndForeground
tagStateStartBackground
tagStateNumericForeground
tagStateNameForeground
tagStateEndBackground
tagStateStartAttributes
tagStateNumericBackground
tagStateNameBackground
tagStateAttributes
tagStateRegionEnd
tagStateRegionName
tagStateEndAttributes
tagStateStartURL
tagStateEndURL
tagStateURL
)
// Helper function which checks if the given byte is one of a list of
// characters, including letters and digits.
isOneOf := func(b byte, chars string) bool {
if b >= 'a' && b <= 'z' || b >= 'A' && b <= 'Z' || b >= '0' && b <= '9' {
return true
}
return strings.IndexByte(chars, b) >= 0
}
// Attribute map.
attrs := map[byte]tcell.AttrMask{
'B': tcell.AttrBold,
'U': tcell.AttrUnderline,
'I': tcell.AttrItalic,
'L': tcell.AttrBlink,
'D': tcell.AttrDim,
'S': tcell.AttrStrikeThrough,
'R': tcell.AttrReverse,
}
var (
tagState, tagLength int
tempStr strings.Builder
)
tStyle := state.style
tRegion := state.region
// Process state transitions.
for len(str) > 0 {
ch := str[0]
str = str[1:]
tagLength++
// Transition.
switch tagState {
case tagStateNone:
if ch == '[' { // Start of a tag.
tagState = tagStateStart
} else { // Not a tag. We're done.
return
}
case tagStateStart:
if ch == '"' { // Start of a region tag.
tempStr.Reset()
tagState = tagStateRegionStart
} else if !isOneOf(ch, "#:-") { // Invalid style tag.
return
} else if ch == '-' { // Reset foreground color.
tStyle = tStyle.Foreground(state.initialForeground)
tagState = tagStateEndForeground
} else if ch == ':' { // No foreground color.
tagState = tagStateStartBackground
} else {
tempStr.Reset()
tempStr.WriteByte(ch)
if ch == '#' { // Numeric foreground color.
tagState = tagStateNumericForeground
} else { // Letters or numbers.
tagState = tagStateNameForeground
}
}
case tagStateEndForeground:
if ch == ']' { // End of tag.
tagState = tagStateDoneTag
} else if ch == ':' {
tagState = tagStateStartBackground
} else { // Invalid tag.
return
}
case tagStateNumericForeground:
if ch == ']' || ch == ':' {
if tempStr.Len() != 7 { // Must be #rrggbb.
return
}
tStyle = tStyle.Foreground(tcell.GetColor(tempStr.String()))
}
if ch == ']' { // End of tag.
tagState = tagStateDoneTag
} else if ch == ':' { // Start of background color.
tagState = tagStateStartBackground
} else if strings.IndexByte("0123456789abcdefABCDEF", ch) >= 0 { // Hex digit.
tempStr.WriteByte(ch)
tagState = tagStateNumericForeground
} else { // Invalid tag.
return
}
case tagStateNameForeground:
if ch == ']' || ch == ':' {
name := tempStr.String()
if name[0] >= '0' && name[0] <= '9' { // Must not start with a digit.
return
}
tStyle = tStyle.Foreground(tcell.ColorNames[name])
}
if !isOneOf(ch, "]:") { // Invalid tag.
return
} else if ch == ']' { // End of tag.
tagState = tagStateDoneTag
} else if ch == ':' { // Start of background color.
tagState = tagStateStartBackground
} else { // Letters or numbers.
tempStr.WriteByte(ch)
}
case tagStateStartBackground:
if !isOneOf(ch, "#:-]") { // Invalid style tag.
return
} else if ch == ']' { // End of tag.
tagState = tagStateDoneTag
} else if ch == '-' { // Reset background color.
tStyle = tStyle.Background(state.initialBackground)
tagState = tagStateEndBackground
} else if ch == ':' { // No background color.
tagState = tagStateStartAttributes
} else {
tempStr.Reset()
tempStr.WriteByte(ch)
if ch == '#' { // Numeric background color.
tagState = tagStateNumericBackground
} else { // Letters or numbers.
tagState = tagStateNameBackground
}
}
case tagStateEndBackground:
if ch == ']' { // End of tag.
tagState = tagStateDoneTag
} else if ch == ':' { // Start of attributes.
tagState = tagStateStartAttributes
} else { // Invalid tag.
return
}
case tagStateNumericBackground:
if ch == ']' || ch == ':' {
if tempStr.Len() != 7 { // Must be #rrggbb.
return
}
tStyle = tStyle.Background(tcell.GetColor(tempStr.String()))
}
if ch == ']' { // End of tag.
tagState = tagStateDoneTag
} else if ch == ':' { // Start of attributes.
tagState = tagStateStartAttributes
} else if strings.IndexByte("0123456789abcdefABCDEF", ch) >= 0 { // Hex digit.
tempStr.WriteByte(ch)
tagState = tagStateNumericBackground
} else { // Invalid tag.
return
}
case tagStateNameBackground:
if ch == ']' || ch == ':' {
name := tempStr.String()
if name[0] >= '0' && name[0] <= '9' { // Must not start with a digit.
return
}
tStyle = tStyle.Background(tcell.ColorNames[name])
}
if !isOneOf(ch, "]:") { // Invalid tag.
return
} else if ch == ']' { // End of tag.
tagState = tagStateDoneTag
} else if ch == ':' { // Start of background color.
tagState = tagStateStartAttributes
} else { // Letters or numbers.
tempStr.WriteByte(ch)
}
case tagStateStartAttributes:
if ch == ']' { // End of tag.
tagState = tagStateDoneTag
} else if ch == '-' { // Reset attributes.
tStyle = tStyle.Attributes(state.initialAttributes)
tagState = tagStateEndAttributes
} else if ch == ':' { // Start of URL.
tagState = tagStateStartURL
} else if strings.IndexByte("buildsrBUILDSR", ch) >= 0 { // Attribute tag.
tempStr.Reset()
tempStr.WriteByte(ch)
tagState = tagStateAttributes
} else { // Invalid tag.
return
}
case tagStateAttributes:
if ch == ']' || ch == ':' {
flags := tempStr.String()
_, _, a := tStyle.Decompose()
for index := 0; index < len(flags); index++ {
ch := flags[index]
if ch >= 'a' && ch <= 'z' {
a |= attrs[ch-('a'-'A')]
} else {
a &^= attrs[ch]
}
}
tStyle = tStyle.Attributes(a)
}
if ch == ']' { // End of tag.
tagState = tagStateDoneTag
} else if ch == ':' { // Start of URL.
tagState = tagStateStartURL
} else if strings.IndexByte("buildsrBUILDSR", ch) >= 0 { // Attribute tag.
tempStr.WriteByte(ch)
} else { // Invalid tag.
return
}
case tagStateEndAttributes:
if ch == ']' { // End of tag.
tagState = tagStateDoneTag
} else if ch == ':' { // Start of URL.
tagState = tagStateStartURL
} else { // Invalid tag.
return
}
case tagStateStartURL:
if ch == ']' { // End of tag.
tagState = tagStateDoneTag
} else if ch == '-' { // Reset URL.
tStyle = tStyle.Url("").UrlId("")
tagState = tagStateEndURL
} else { // URL character.
tempStr.Reset()
tempStr.WriteByte(ch)
tStyle = tStyle.UrlId(strconv.Itoa(int(rand.Uint32()))) // Generate a unique ID for this URL.
tagState = tagStateURL
}
case tagStateEndURL:
if ch == ']' { // End of tag.
tagState = tagStateDoneTag
} else { // Invalid tag.
return
}
case tagStateURL:
if ch == ']' { // End of tag.
tStyle = tStyle.Url(tempStr.String())
tagState = tagStateDoneTag
} else { // URL character.
tempStr.WriteByte(ch)
}
case tagStateRegionStart:
if ch == '"' { // End of region tag.
tagState = tagStateRegionEnd
} else if isOneOf(ch, "_,;: -.") { // Region name.
tempStr.WriteByte(ch)
tagState = tagStateRegionName
} else { // Invalid tag.
return
}
case tagStateRegionEnd:
if ch == ']' { // End of tag.
tRegion = tempStr.String()
tagState = tagStateDoneTag
} else { // Invalid tag.
return
}
case tagStateRegionName:
if ch == '"' { // End of region tag.
tagState = tagStateRegionEnd
} else if isOneOf(ch, "_,;: -.") { // Region name.
tempStr.WriteByte(ch)
} else { // Invalid tag.
return
}
}
// The last transition led to a tag end. Make the tag permanent.
if tagState == tagStateDoneTag {
length, style, region = tagLength, tStyle, tRegion
tagState = tagStateNone // Reset state.
}
}
return
}
// TaggedStringWidth returns the width of the given string needed to print it on
// screen. The text may contain style tags which are not counted.
func TaggedStringWidth(text string) (width int) {
var state *stepState
for len(text) > 0 {
_, text, state = step(text, state, stepOptionsStyle)
width += state.Width()
}
return
}
// WordWrap splits a text such that each resulting line does not exceed the
// given screen width. Split points are determined using the algorithm described
// in [Unicode Standard Annex #14].
//
// This function considers style tags to have no width.
//
// [Unicode Standard Annex #14]: https://www.unicode.org/reports/tr14/
func WordWrap(text string, width int) (lines []string) {
if width <= 0 {
return
}
var (
state *stepState
lineWidth, lineLength, lastOption, lastOptionWidth int
)
str := text
for len(str) > 0 {
// Parse the next character.
_, str, state = step(str, state, stepOptionsStyle)
cWidth := state.Width()
// Would it exceed the line width?
if lineWidth+cWidth > width {
if lastOptionWidth == 0 {
// No split point so far. Just split at the current position.
lines = append(lines, text[:lineLength])
text = text[lineLength:]
lineWidth, lineLength, lastOption, lastOptionWidth = 0, 0, 0, 0
} else {
// Split at the last split point.
lines = append(lines, text[:lastOption])
text = text[lastOption:]
lineWidth -= lastOptionWidth
lineLength -= lastOption
lastOption, lastOptionWidth = 0, 0
}
}
// Move ahead.
lineWidth += cWidth
lineLength += state.GrossLength()
// Check for split points.
if lineBreak, optional := state.LineBreak(); lineBreak {
if optional {
// Remember this split point.
lastOption = lineLength
lastOptionWidth = lineWidth
} else {
// We must split here.
lines = append(lines, strings.TrimRight(text[:lineLength], "\n\r"))
text = text[lineLength:]
lineWidth, lineLength, lastOption, lastOptionWidth = 0, 0, 0, 0
}
}
}
lines = append(lines, text)
return
}
// Escape escapes the given text such that color and/or region tags are not
// recognized and substituted by the print functions of this package. For
// example, to include a tag-like string in a box title or in a TextView:
//
// box.SetTitle(tview.Escape("[squarebrackets]"))
// fmt.Fprint(textView, tview.Escape(`["quoted"]`))
func Escape(text string) string {
return nonEscapePattern.ReplaceAllString(text, "$1[]")
}
// ReplaceRegionStyles replaces style tags within text regions.
func ReplaceRegionStyles(text string, getStyle func(region string) string) string {
var (
str, regionText strings.Builder
state *stepState
region string
escapedState int
)
for len(text) > 0 {
var c string
c, text, state = step(text, state, stepOptionsStyle)
if escapedState > 0 && state.escapedTagState == 0 {
c = "[]"
}
escapedState = state.escapedTagState
if region != "" && region != state.region {
if regionText.Len() > 0 {
fmt.Fprintf(&str, "[\"%s\"]", region)
text := regionText.String()
if tag := getStyle(region); tag != "" {
fmt.Fprintf(&str, "%s%s[-:-:-]", tag, text)
} else {
str.WriteString(text)
}
str.WriteString("[\"\"]")
regionText.Reset()
region = state.region
}
}
if state.region == "" && region == "" {
str.WriteString(c)
continue
}
region = state.region
regionText.WriteString(c)
}
return str.String()
}
// stripTags strips style tags from the given string. (Region tags are not
// stripped.)
func stripTags(text string) string {
var (
str strings.Builder
state *stepState
)
for len(text) > 0 {
var c string
c, text, state = step(text, state, stepOptionsStyle)
str.WriteString(c)
}
return str.String()
}
|