| 1 | // Scintilla source code edit control |
| 2 | /** @file LexNim.cxx |
| 3 | ** Lexer for Nim |
| 4 | ** Written by Jad Altahan (github.com/xv) |
| 5 | ** Nim manual: https://nim-lang.org/docs/manual.html |
| 6 | **/ |
| 7 | // Copyright 1998-2001 by Neil Hodgson <neilh@scintilla.org> |
| 8 | // The License.txt file describes the conditions under which this software may be distributed. |
| 9 | |
| 10 | #include <stdlib.h> |
| 11 | #include <string.h> |
| 12 | #include <stdio.h> |
| 13 | #include <stdarg.h> |
| 14 | #include <assert.h> |
| 15 | #include <ctype.h> |
| 16 | |
| 17 | #include <string> |
| 18 | #include <string_view> |
| 19 | #include <map> |
| 20 | #include <algorithm> |
| 21 | #include <functional> |
| 22 | |
| 23 | #include "ILexer.h" |
| 24 | #include "Scintilla.h" |
| 25 | #include "SciLexer.h" |
| 26 | |
| 27 | #include "StringCopy.h" |
| 28 | #include "WordList.h" |
| 29 | #include "LexAccessor.h" |
| 30 | #include "Accessor.h" |
| 31 | #include "StyleContext.h" |
| 32 | #include "CharacterSet.h" |
| 33 | #include "LexerModule.h" |
| 34 | #include "OptionSet.h" |
| 35 | #include "DefaultLexer.h" |
| 36 | |
| 37 | using namespace Scintilla; |
| 38 | using namespace Lexilla; |
| 39 | |
| 40 | namespace { |
| 41 | // Use an unnamed namespace to protect the functions and classes from name conflicts |
| 42 | |
| 43 | enum NumType { |
| 44 | Binary, |
| 45 | Octal, |
| 46 | Exponent, |
| 47 | Hexadecimal, |
| 48 | Decimal, |
| 49 | FormatError |
| 50 | }; |
| 51 | |
| 52 | int GetNumStyle(const int numType) noexcept { |
| 53 | if (numType == NumType::FormatError) { |
| 54 | return SCE_NIM_NUMERROR; |
| 55 | } |
| 56 | |
| 57 | return SCE_NIM_NUMBER; |
| 58 | } |
| 59 | |
| 60 | constexpr bool IsLetter(const int ch) noexcept { |
| 61 | // 97 to 122 || 65 to 90 |
| 62 | return (ch >= 'a' && ch <= 'z') || (ch >= 'A' && ch <= 'Z'); |
| 63 | } |
| 64 | |
| 65 | bool IsAWordChar(const int ch) noexcept { |
| 66 | return ch < 0x80 && (isalnum(ch) || ch == '_' || ch == '.'); |
| 67 | } |
| 68 | |
| 69 | int IsNumHex(const StyleContext &sc) noexcept { |
| 70 | return sc.chNext == 'x' || sc.chNext == 'X'; |
| 71 | } |
| 72 | |
| 73 | int IsNumBinary(const StyleContext &sc) noexcept { |
| 74 | return sc.chNext == 'b' || sc.chNext == 'B'; |
| 75 | } |
| 76 | |
| 77 | int IsNumOctal(const StyleContext &sc) { |
| 78 | return IsADigit(sc.chNext) || sc.chNext == 'o'; |
| 79 | } |
| 80 | |
| 81 | constexpr bool IsNewline(const int ch) noexcept { |
| 82 | return (ch == '\n' || ch == '\r'); |
| 83 | } |
| 84 | |
| 85 | bool IsFuncName(const char *str) noexcept { |
| 86 | const char *identifiers[] = { |
| 87 | "proc" , |
| 88 | "func" , |
| 89 | "macro" , |
| 90 | "method" , |
| 91 | "template" , |
| 92 | "iterator" , |
| 93 | "converter" |
| 94 | }; |
| 95 | |
| 96 | for (const char *id : identifiers) { |
| 97 | if (strcmp(str, id) == 0) { |
| 98 | return true; |
| 99 | } |
| 100 | } |
| 101 | |
| 102 | return false; |
| 103 | } |
| 104 | |
| 105 | constexpr bool IsTripleLiteral(const int style) noexcept { |
| 106 | return style == SCE_NIM_TRIPLE || style == SCE_NIM_TRIPLEDOUBLE; |
| 107 | } |
| 108 | |
| 109 | constexpr bool (const int style) noexcept { |
| 110 | return style == SCE_NIM_COMMENTLINE || style == SCE_NIM_COMMENTLINEDOC; |
| 111 | } |
| 112 | |
| 113 | constexpr bool (const int style) noexcept { |
| 114 | return style == SCE_NIM_COMMENT || style == SCE_NIM_COMMENTDOC; |
| 115 | } |
| 116 | |
| 117 | // Adopted from Accessor.cxx |
| 118 | int GetIndent(const Sci_Position line, Accessor &styler) { |
| 119 | Sci_Position startPos = styler.LineStart(line); |
| 120 | const Sci_Position eolPos = styler.LineStart(line + 1) - 1; |
| 121 | |
| 122 | char ch = styler[startPos]; |
| 123 | int style = styler.StyleAt(startPos); |
| 124 | |
| 125 | int indent = 0; |
| 126 | bool inPrevPrefix = line > 0; |
| 127 | Sci_Position posPrev = inPrevPrefix ? styler.LineStart(line - 1) : 0; |
| 128 | |
| 129 | // No fold points inside triple literals |
| 130 | while ((IsASpaceOrTab(ch) || IsTripleLiteral(style)) && (startPos < eolPos)) { |
| 131 | if (inPrevPrefix) { |
| 132 | const char chPrev = styler[posPrev++]; |
| 133 | if (chPrev != ' ' && chPrev != '\t') { |
| 134 | inPrevPrefix = false; |
| 135 | } |
| 136 | } |
| 137 | |
| 138 | if (ch == '\t') { |
| 139 | indent = (indent / 8 + 1) * 8; |
| 140 | } else { |
| 141 | indent++; |
| 142 | } |
| 143 | |
| 144 | startPos++; |
| 145 | ch = styler[startPos]; |
| 146 | style = styler.StyleAt(startPos); |
| 147 | } |
| 148 | |
| 149 | // Prevent creating fold lines for comments if indented |
| 150 | if (!(IsStreamComment(style) || IsLineComment(style))) |
| 151 | indent += SC_FOLDLEVELBASE; |
| 152 | |
| 153 | if (styler.LineStart(line) == styler.Length() |
| 154 | || IsASpaceOrTab(ch) |
| 155 | || IsNewline(ch) |
| 156 | || IsStreamComment(style) |
| 157 | || IsLineComment(style)) { |
| 158 | return indent | SC_FOLDLEVELWHITEFLAG; |
| 159 | } else { |
| 160 | return indent; |
| 161 | } |
| 162 | } |
| 163 | |
| 164 | int IndentAmount(const Sci_Position line, Accessor &styler) { |
| 165 | const int indent = GetIndent(line, styler); |
| 166 | const int indentLevel = indent & SC_FOLDLEVELNUMBERMASK; |
| 167 | return indentLevel <= SC_FOLDLEVELBASE ? indent : indentLevel | (indent & ~SC_FOLDLEVELNUMBERMASK); |
| 168 | } |
| 169 | |
| 170 | struct OptionsNim { |
| 171 | bool fold; |
| 172 | bool foldCompact; |
| 173 | bool highlightRawStrIdent; |
| 174 | |
| 175 | OptionsNim() { |
| 176 | fold = true; |
| 177 | foldCompact = true; |
| 178 | highlightRawStrIdent = false; |
| 179 | } |
| 180 | }; |
| 181 | |
| 182 | static const char *const nimWordListDesc[] = { |
| 183 | "Keywords" , |
| 184 | nullptr |
| 185 | }; |
| 186 | |
| 187 | struct OptionSetNim : public OptionSet<OptionsNim> { |
| 188 | OptionSetNim() { |
| 189 | DefineProperty("lexer.nim.raw.strings.highlight.ident" , &OptionsNim::highlightRawStrIdent, |
| 190 | "Set to 1 to enable highlighting generalized raw string identifiers. " |
| 191 | "Generalized raw string identifiers are anything other than r (or R)." ); |
| 192 | |
| 193 | DefineProperty("fold" , &OptionsNim::fold); |
| 194 | DefineProperty("fold.compact" , &OptionsNim::foldCompact); |
| 195 | |
| 196 | DefineWordListSets(nimWordListDesc); |
| 197 | } |
| 198 | }; |
| 199 | |
| 200 | LexicalClass lexicalClasses[] = { |
| 201 | // Lexer Nim SCLEX_NIM SCE_NIM_: |
| 202 | 0, "SCE_NIM_DEFAULT" , "default" , "White space" , |
| 203 | 1, "SCE_NIM_COMMENT" , "comment block" , "Block comment" , |
| 204 | 2, "SCE_NIM_COMMENTDOC" , "comment block doc" , "Block doc comment" , |
| 205 | 3, "SCE_NIM_COMMENTLINE" , "comment line" , "Line comment" , |
| 206 | 4, "SCE_NIM_COMMENTLINEDOC" , "comment doc" , "Line doc comment" , |
| 207 | 5, "SCE_NIM_NUMBER" , "literal numeric" , "Number" , |
| 208 | 6, "SCE_NIM_STRING" , "literal string" , "String" , |
| 209 | 7, "SCE_NIM_CHARACTER" , "literal string" , "Single quoted string" , |
| 210 | 8, "SCE_NIM_WORD" , "keyword" , "Keyword" , |
| 211 | 9, "SCE_NIM_TRIPLE" , "literal string" , "Triple quotes" , |
| 212 | 10, "SCE_NIM_TRIPLEDOUBLE" , "literal string" , "Triple double quotes" , |
| 213 | 11, "SCE_NIM_BACKTICKS" , "operator definition" , "Identifiers" , |
| 214 | 12, "SCE_NIM_FUNCNAME" , "identifier" , "Function name definition" , |
| 215 | 13, "SCE_NIM_STRINGEOL" , "error literal string" , "String is not closed" , |
| 216 | 14, "SCE_NIM_NUMERROR" , "numeric error" , "Numeric format error" , |
| 217 | 15, "SCE_NIM_OPERATOR" , "operator" , "Operators" , |
| 218 | 16, "SCE_NIM_IDENTIFIER" , "identifier" , "Identifiers" , |
| 219 | }; |
| 220 | |
| 221 | } |
| 222 | |
| 223 | class LexerNim : public DefaultLexer { |
| 224 | CharacterSet setWord; |
| 225 | WordList keywords; |
| 226 | OptionsNim options; |
| 227 | OptionSetNim osNim; |
| 228 | |
| 229 | public: |
| 230 | LexerNim() : |
| 231 | DefaultLexer("nim" , SCLEX_NIM, lexicalClasses, ELEMENTS(lexicalClasses)), |
| 232 | setWord(CharacterSet::setAlphaNum, "_" , 0x80, true) { } |
| 233 | |
| 234 | virtual ~LexerNim() { } |
| 235 | |
| 236 | void SCI_METHOD Release() noexcept override { |
| 237 | delete this; |
| 238 | } |
| 239 | |
| 240 | int SCI_METHOD Version() const noexcept override { |
| 241 | return lvRelease5; |
| 242 | } |
| 243 | |
| 244 | const char * SCI_METHOD PropertyNames() override { |
| 245 | return osNim.PropertyNames(); |
| 246 | } |
| 247 | |
| 248 | int SCI_METHOD PropertyType(const char *name) override { |
| 249 | return osNim.PropertyType(name); |
| 250 | } |
| 251 | |
| 252 | const char * SCI_METHOD DescribeProperty(const char *name) override { |
| 253 | return osNim.DescribeProperty(name); |
| 254 | } |
| 255 | |
| 256 | Sci_Position SCI_METHOD PropertySet(const char *key, const char *val) override; |
| 257 | |
| 258 | const char * SCI_METHOD PropertyGet(const char* key) override { |
| 259 | return osNim.PropertyGet(key); |
| 260 | } |
| 261 | |
| 262 | const char * SCI_METHOD DescribeWordListSets() override { |
| 263 | return osNim.DescribeWordListSets(); |
| 264 | } |
| 265 | |
| 266 | Sci_Position SCI_METHOD WordListSet(int n, const char *wl) override; |
| 267 | |
| 268 | void SCI_METHOD Lex(Sci_PositionU startPos, Sci_Position length, int initStyle, IDocument *pAccess) override; |
| 269 | void SCI_METHOD Fold(Sci_PositionU startPos, Sci_Position length, int initStyle, IDocument *pAccess) override; |
| 270 | |
| 271 | void * SCI_METHOD PrivateCall(int, void *) noexcept override { |
| 272 | return nullptr; |
| 273 | } |
| 274 | |
| 275 | int SCI_METHOD LineEndTypesSupported() noexcept override { |
| 276 | return SC_LINE_END_TYPE_UNICODE; |
| 277 | } |
| 278 | |
| 279 | int SCI_METHOD PrimaryStyleFromStyle(int style) noexcept override { |
| 280 | return style; |
| 281 | } |
| 282 | |
| 283 | static ILexer5 *LexerFactoryNim() { |
| 284 | return new LexerNim(); |
| 285 | } |
| 286 | }; |
| 287 | |
| 288 | Sci_Position SCI_METHOD LexerNim::PropertySet(const char *key, const char *val) { |
| 289 | if (osNim.PropertySet(&options, key, val)) { |
| 290 | return 0; |
| 291 | } |
| 292 | |
| 293 | return -1; |
| 294 | } |
| 295 | |
| 296 | Sci_Position SCI_METHOD LexerNim::WordListSet(int n, const char *wl) { |
| 297 | WordList *wordListN = nullptr; |
| 298 | |
| 299 | switch (n) { |
| 300 | case 0: |
| 301 | wordListN = &keywords; |
| 302 | break; |
| 303 | } |
| 304 | |
| 305 | Sci_Position firstModification = -1; |
| 306 | |
| 307 | if (wordListN) { |
| 308 | WordList wlNew; |
| 309 | wlNew.Set(wl); |
| 310 | |
| 311 | if (*wordListN != wlNew) { |
| 312 | wordListN->Set(wl); |
| 313 | firstModification = 0; |
| 314 | } |
| 315 | } |
| 316 | |
| 317 | return firstModification; |
| 318 | } |
| 319 | |
| 320 | void SCI_METHOD LexerNim::Lex(Sci_PositionU startPos, Sci_Position length, |
| 321 | int initStyle, IDocument *pAccess) { |
| 322 | // No one likes a leaky string |
| 323 | if (initStyle == SCE_NIM_STRINGEOL) { |
| 324 | initStyle = SCE_NIM_DEFAULT; |
| 325 | } |
| 326 | |
| 327 | Accessor styler(pAccess, nullptr); |
| 328 | StyleContext sc(startPos, length, initStyle, styler); |
| 329 | |
| 330 | // Nim supports nested block comments! |
| 331 | Sci_Position lineCurrent = styler.GetLine(startPos); |
| 332 | int = lineCurrent > 0 ? styler.GetLineState(lineCurrent - 1) : 0; |
| 333 | |
| 334 | int numType = NumType::Decimal; |
| 335 | int decimalCount = 0; |
| 336 | |
| 337 | bool funcNameExists = false; |
| 338 | bool isStylingRawString = false; |
| 339 | bool isStylingRawStringIdent = false; |
| 340 | |
| 341 | for (; sc.More(); sc.Forward()) { |
| 342 | if (sc.atLineStart) { |
| 343 | if (sc.state == SCE_NIM_STRING) { |
| 344 | sc.SetState(SCE_NIM_STRING); |
| 345 | } |
| 346 | |
| 347 | lineCurrent = styler.GetLine(sc.currentPos); |
| 348 | styler.SetLineState(lineCurrent, commentNestLevel); |
| 349 | } |
| 350 | |
| 351 | // Handle string line continuation |
| 352 | if (sc.ch == '\\' && (sc.chNext == '\n' || sc.chNext == '\r') && |
| 353 | (sc.state == SCE_NIM_STRING || sc.state == SCE_NIM_CHARACTER) && !isStylingRawString) { |
| 354 | sc.Forward(); |
| 355 | |
| 356 | if (sc.ch == '\r' && sc.chNext == '\n') { |
| 357 | sc.Forward(); |
| 358 | } |
| 359 | |
| 360 | continue; |
| 361 | } |
| 362 | |
| 363 | switch (sc.state) { |
| 364 | case SCE_NIM_OPERATOR: |
| 365 | funcNameExists = false; |
| 366 | sc.SetState(SCE_NIM_DEFAULT); |
| 367 | break; |
| 368 | case SCE_NIM_NUMBER: |
| 369 | // For a type suffix, such as 0x80'u8 |
| 370 | if (sc.ch == '\'') { |
| 371 | if (sc.chNext == 'i' || sc.chNext == 'I' || |
| 372 | sc.chNext == 'u' || sc.chNext == 'U' || |
| 373 | sc.chNext == 'f' || sc.chNext == 'F' || |
| 374 | sc.chNext == 'd' || sc.chNext == 'D') { |
| 375 | sc.Forward(2); |
| 376 | } |
| 377 | } else if (sc.ch == '.') { |
| 378 | if (IsADigit(sc.chNext)) { |
| 379 | sc.Forward(); |
| 380 | } else if (numType <= NumType::Exponent) { |
| 381 | sc.SetState(SCE_NIM_OPERATOR); |
| 382 | break; |
| 383 | } else { |
| 384 | decimalCount++; |
| 385 | |
| 386 | if (numType == NumType::Decimal) { |
| 387 | if (decimalCount <= 1 && !IsAWordChar(sc.chNext)) { |
| 388 | break; |
| 389 | } |
| 390 | } else if (numType == NumType::Hexadecimal) { |
| 391 | if (decimalCount <= 1 && IsADigit(sc.chNext, 16)) { |
| 392 | break; |
| 393 | } |
| 394 | |
| 395 | sc.SetState(SCE_NIM_OPERATOR); |
| 396 | break; |
| 397 | } |
| 398 | } |
| 399 | } else if (sc.ch == '_') { |
| 400 | // Accept only one underscore between digits |
| 401 | if (IsADigit(sc.chNext)) { |
| 402 | sc.Forward(); |
| 403 | } |
| 404 | } else if (numType == NumType::Decimal) { |
| 405 | if (sc.chPrev != '\'' && (sc.ch == 'e' || sc.ch == 'E')) { |
| 406 | numType = NumType::Exponent; |
| 407 | |
| 408 | if (sc.chNext == '-' || sc.chNext == '+') { |
| 409 | sc.Forward(); |
| 410 | } |
| 411 | |
| 412 | break; |
| 413 | } |
| 414 | |
| 415 | if (IsADigit(sc.ch)) { |
| 416 | break; |
| 417 | } |
| 418 | } else if (numType == NumType::Hexadecimal) { |
| 419 | if (IsADigit(sc.ch, 16)) { |
| 420 | break; |
| 421 | } |
| 422 | } else if (IsADigit(sc.ch)) { |
| 423 | if (numType == NumType::Exponent) { |
| 424 | break; |
| 425 | } |
| 426 | |
| 427 | if (numType == NumType::Octal) { |
| 428 | // Accept only 0-7 |
| 429 | if (sc.ch <= '7') { |
| 430 | break; |
| 431 | } |
| 432 | } else if (numType == NumType::Binary) { |
| 433 | // Accept only 0 and 1 |
| 434 | if (sc.ch <= '1') { |
| 435 | break; |
| 436 | } |
| 437 | } |
| 438 | |
| 439 | numType = NumType::FormatError; |
| 440 | break; |
| 441 | } |
| 442 | |
| 443 | sc.ChangeState(GetNumStyle(numType)); |
| 444 | sc.SetState(SCE_NIM_DEFAULT); |
| 445 | break; |
| 446 | case SCE_NIM_IDENTIFIER: |
| 447 | if (sc.ch == '.' || !IsAWordChar(sc.ch)) { |
| 448 | char s[100]; |
| 449 | sc.GetCurrent(s, sizeof(s)); |
| 450 | int style = SCE_NIM_IDENTIFIER; |
| 451 | |
| 452 | if (keywords.InList(s) && !funcNameExists) { |
| 453 | // Prevent styling keywords if they are sub-identifiers |
| 454 | const Sci_Position segStart = styler.GetStartSegment() - 1; |
| 455 | if (segStart < 0 || styler.SafeGetCharAt(segStart, '\0') != '.') { |
| 456 | style = SCE_NIM_WORD; |
| 457 | } |
| 458 | } else if (funcNameExists) { |
| 459 | style = SCE_NIM_FUNCNAME; |
| 460 | } |
| 461 | |
| 462 | sc.ChangeState(style); |
| 463 | sc.SetState(SCE_NIM_DEFAULT); |
| 464 | |
| 465 | if (style == SCE_NIM_WORD) { |
| 466 | funcNameExists = IsFuncName(s); |
| 467 | } else { |
| 468 | funcNameExists = false; |
| 469 | } |
| 470 | } |
| 471 | |
| 472 | if (IsAlphaNumeric(sc.ch) && sc.chNext == '\"') { |
| 473 | isStylingRawStringIdent = true; |
| 474 | |
| 475 | if (options.highlightRawStrIdent) { |
| 476 | if (styler.SafeGetCharAt(sc.currentPos + 2) == '\"' && |
| 477 | styler.SafeGetCharAt(sc.currentPos + 3) == '\"') { |
| 478 | sc.ChangeState(SCE_NIM_TRIPLEDOUBLE); |
| 479 | } else { |
| 480 | sc.ChangeState(SCE_NIM_STRING); |
| 481 | } |
| 482 | } |
| 483 | |
| 484 | sc.ForwardSetState(SCE_NIM_DEFAULT); |
| 485 | } |
| 486 | break; |
| 487 | case SCE_NIM_FUNCNAME: |
| 488 | if (sc.ch == '`') { |
| 489 | funcNameExists = false; |
| 490 | sc.ForwardSetState(SCE_NIM_DEFAULT); |
| 491 | } else if (sc.atLineEnd) { |
| 492 | // Prevent leaking the style to the next line if not closed |
| 493 | funcNameExists = false; |
| 494 | |
| 495 | sc.ChangeState(SCE_NIM_STRINGEOL); |
| 496 | sc.ForwardSetState(SCE_NIM_DEFAULT); |
| 497 | } |
| 498 | break; |
| 499 | case SCE_NIM_COMMENT: |
| 500 | if (sc.Match(']', '#')) { |
| 501 | if (commentNestLevel > 0) { |
| 502 | commentNestLevel--; |
| 503 | } |
| 504 | |
| 505 | lineCurrent = styler.GetLine(sc.currentPos); |
| 506 | styler.SetLineState(lineCurrent, commentNestLevel); |
| 507 | sc.Forward(); |
| 508 | |
| 509 | if (commentNestLevel == 0) { |
| 510 | sc.ForwardSetState(SCE_NIM_DEFAULT); |
| 511 | } |
| 512 | } else if (sc.Match('#', '[')) { |
| 513 | commentNestLevel++; |
| 514 | lineCurrent = styler.GetLine(sc.currentPos); |
| 515 | styler.SetLineState(lineCurrent, commentNestLevel); |
| 516 | } |
| 517 | break; |
| 518 | case SCE_NIM_COMMENTDOC: |
| 519 | if (sc.Match("]##" )) { |
| 520 | if (commentNestLevel > 0) { |
| 521 | commentNestLevel--; |
| 522 | } |
| 523 | |
| 524 | lineCurrent = styler.GetLine(sc.currentPos); |
| 525 | styler.SetLineState(lineCurrent, commentNestLevel); |
| 526 | sc.Forward(2); |
| 527 | |
| 528 | if (commentNestLevel == 0) { |
| 529 | sc.ForwardSetState(SCE_NIM_DEFAULT); |
| 530 | } |
| 531 | } else if (sc.Match("##[" )) { |
| 532 | commentNestLevel++; |
| 533 | lineCurrent = styler.GetLine(sc.currentPos); |
| 534 | styler.SetLineState(lineCurrent, commentNestLevel); |
| 535 | } |
| 536 | break; |
| 537 | case SCE_NIM_COMMENTLINE: |
| 538 | case SCE_NIM_COMMENTLINEDOC: |
| 539 | if (sc.atLineStart) { |
| 540 | sc.SetState(SCE_NIM_DEFAULT); |
| 541 | } |
| 542 | break; |
| 543 | case SCE_NIM_STRING: |
| 544 | if (!isStylingRawStringIdent && !isStylingRawString && sc.ch == '\\') { |
| 545 | if (sc.chNext == '\"' || sc.chNext == '\'' || sc.chNext == '\\') { |
| 546 | sc.Forward(); |
| 547 | } |
| 548 | } else if (isStylingRawString && sc.ch == '\"' && sc.chNext == '\"') { |
| 549 | // Forward in situations such as r"a""bc\" so that "bc\" wouldn't be |
| 550 | // considered a string of its own |
| 551 | sc.Forward(); |
| 552 | } else if (sc.ch == '\"') { |
| 553 | sc.ForwardSetState(SCE_NIM_DEFAULT); |
| 554 | } else if (sc.atLineEnd) { |
| 555 | sc.ChangeState(SCE_NIM_STRINGEOL); |
| 556 | sc.ForwardSetState(SCE_NIM_DEFAULT); |
| 557 | } |
| 558 | break; |
| 559 | case SCE_NIM_CHARACTER: |
| 560 | if (sc.ch == '\\') { |
| 561 | if (sc.chNext == '\"' || sc.chNext == '\'' || sc.chNext == '\\') { |
| 562 | sc.Forward(); |
| 563 | } |
| 564 | } else if (sc.ch == '\'') { |
| 565 | sc.ForwardSetState(SCE_NIM_DEFAULT); |
| 566 | } else if (sc.atLineEnd) { |
| 567 | sc.ChangeState(SCE_NIM_STRINGEOL); |
| 568 | sc.ForwardSetState(SCE_NIM_DEFAULT); |
| 569 | } |
| 570 | break; |
| 571 | case SCE_NIM_BACKTICKS: |
| 572 | if (sc.ch == '`' ) { |
| 573 | sc.ForwardSetState(SCE_NIM_DEFAULT); |
| 574 | } else if (sc.atLineEnd) { |
| 575 | sc.ChangeState(SCE_NIM_STRINGEOL); |
| 576 | sc.ForwardSetState(SCE_NIM_DEFAULT); |
| 577 | } |
| 578 | break; |
| 579 | case SCE_NIM_TRIPLEDOUBLE: |
| 580 | if (sc.Match(R"(""")" )) { |
| 581 | |
| 582 | // Outright forward all " after the closing """ as a triple double |
| 583 | // |
| 584 | // A valid example where this is needed is: """8 double quotes->"""""""" |
| 585 | // You can have as many """ at the end as you wish, as long as the actual |
| 586 | // closing literal is there |
| 587 | while (sc.ch == '"') { |
| 588 | sc.Forward(); |
| 589 | } |
| 590 | |
| 591 | sc.SetState(SCE_NIM_DEFAULT); |
| 592 | } |
| 593 | break; |
| 594 | case SCE_NIM_TRIPLE: |
| 595 | if (sc.Match("'''" )) { |
| 596 | sc.Forward(2); |
| 597 | sc.ForwardSetState(SCE_NIM_DEFAULT); |
| 598 | } |
| 599 | break; |
| 600 | } |
| 601 | |
| 602 | if (sc.state == SCE_NIM_DEFAULT) { |
| 603 | // Number |
| 604 | if (IsADigit(sc.ch)) { |
| 605 | sc.SetState(SCE_NIM_NUMBER); |
| 606 | |
| 607 | numType = NumType::Decimal; |
| 608 | decimalCount = 0; |
| 609 | |
| 610 | if (sc.ch == '0') { |
| 611 | if (IsNumHex(sc)) { |
| 612 | numType = NumType::Hexadecimal; |
| 613 | } else if (IsNumBinary(sc)) { |
| 614 | numType = NumType::Binary; |
| 615 | } else if (IsNumOctal(sc)) { |
| 616 | numType = NumType::Octal; |
| 617 | } |
| 618 | |
| 619 | if (numType != NumType::Decimal) { |
| 620 | sc.Forward(); |
| 621 | } |
| 622 | } |
| 623 | } |
| 624 | // Raw string |
| 625 | else if (IsAlphaNumeric(sc.ch) && sc.chNext == '\"') { |
| 626 | isStylingRawString = true; |
| 627 | |
| 628 | // Triple doubles can be raw strings too. How sweet |
| 629 | if (styler.SafeGetCharAt(sc.currentPos + 2) == '\"' && |
| 630 | styler.SafeGetCharAt(sc.currentPos + 3) == '\"') { |
| 631 | sc.SetState(SCE_NIM_TRIPLEDOUBLE); |
| 632 | } else { |
| 633 | sc.SetState(SCE_NIM_STRING); |
| 634 | } |
| 635 | |
| 636 | const int rawStrStyle = options.highlightRawStrIdent ? IsLetter(sc.ch) : |
| 637 | (sc.ch == 'r' || sc.ch == 'R'); |
| 638 | |
| 639 | if (rawStrStyle) { |
| 640 | sc.Forward(); |
| 641 | |
| 642 | if (sc.state == SCE_NIM_TRIPLEDOUBLE) { |
| 643 | sc.Forward(2); |
| 644 | } |
| 645 | } else { |
| 646 | // Anything other than r/R is considered a general raw string identifier |
| 647 | isStylingRawStringIdent = true; |
| 648 | sc.SetState(SCE_NIM_IDENTIFIER); |
| 649 | } |
| 650 | } |
| 651 | // String and triple double literal |
| 652 | else if (sc.ch == '\"') { |
| 653 | isStylingRawString = false; |
| 654 | |
| 655 | if (sc.Match(R"(""")" )) { |
| 656 | sc.SetState(SCE_NIM_TRIPLEDOUBLE); |
| 657 | |
| 658 | // Keep forwarding until the total opening literal count is 5 |
| 659 | // A valid example where this is needed is: """""<-5 double quotes""" |
| 660 | while (sc.ch == '"') { |
| 661 | sc.Forward(); |
| 662 | |
| 663 | if (sc.Match(R"(""")" )) { |
| 664 | sc.Forward(); |
| 665 | break; |
| 666 | } |
| 667 | } |
| 668 | } else { |
| 669 | sc.SetState(SCE_NIM_STRING); |
| 670 | } |
| 671 | } |
| 672 | // Charecter and triple literal |
| 673 | else if (sc.ch == '\'') { |
| 674 | if (sc.Match("'''" )) { |
| 675 | sc.SetState(SCE_NIM_TRIPLE); |
| 676 | } else { |
| 677 | sc.SetState(SCE_NIM_CHARACTER); |
| 678 | } |
| 679 | } |
| 680 | // Operator definition |
| 681 | else if (sc.ch == '`') { |
| 682 | if (funcNameExists) { |
| 683 | sc.SetState(SCE_NIM_FUNCNAME); |
| 684 | } else { |
| 685 | sc.SetState(SCE_NIM_BACKTICKS); |
| 686 | } |
| 687 | } |
| 688 | // Keyword |
| 689 | else if (iswordstart(sc.ch)) { |
| 690 | sc.SetState(SCE_NIM_IDENTIFIER); |
| 691 | } |
| 692 | // Comments |
| 693 | else if (sc.ch == '#') { |
| 694 | if (sc.Match("##[" ) || sc.Match("#[" )) { |
| 695 | commentNestLevel++; |
| 696 | lineCurrent = styler.GetLine(sc.currentPos); |
| 697 | styler.SetLineState(lineCurrent, commentNestLevel); |
| 698 | } |
| 699 | |
| 700 | if (sc.Match("##[" )) { |
| 701 | sc.SetState(SCE_NIM_COMMENTDOC); |
| 702 | sc.Forward(); |
| 703 | } else if (sc.Match("#[" )) { |
| 704 | sc.SetState(SCE_NIM_COMMENT); |
| 705 | sc.Forward(); |
| 706 | } else if (sc.Match("##" )) { |
| 707 | sc.SetState(SCE_NIM_COMMENTLINEDOC); |
| 708 | } else { |
| 709 | sc.SetState(SCE_NIM_COMMENTLINE); |
| 710 | } |
| 711 | } |
| 712 | // Operators |
| 713 | else if (strchr("()[]{}:=;-\\/&%$!+<>|^?,.*~@" , sc.ch)) { |
| 714 | sc.SetState(SCE_NIM_OPERATOR); |
| 715 | } |
| 716 | } |
| 717 | |
| 718 | if (sc.atLineEnd) { |
| 719 | funcNameExists = false; |
| 720 | isStylingRawString = false; |
| 721 | isStylingRawStringIdent = false; |
| 722 | } |
| 723 | } |
| 724 | |
| 725 | sc.Complete(); |
| 726 | } |
| 727 | |
| 728 | void SCI_METHOD LexerNim::Fold(Sci_PositionU startPos, Sci_Position length, int, IDocument *pAccess) { |
| 729 | if (!options.fold) { |
| 730 | return; |
| 731 | } |
| 732 | |
| 733 | Accessor styler(pAccess, nullptr); |
| 734 | |
| 735 | const Sci_Position docLines = styler.GetLine(styler.Length()); |
| 736 | const Sci_Position maxPos = startPos + length; |
| 737 | const Sci_Position maxLines = styler.GetLine(maxPos == styler.Length() ? maxPos : maxPos - 1); |
| 738 | |
| 739 | Sci_Position lineCurrent = styler.GetLine(startPos); |
| 740 | int indentCurrent = IndentAmount(lineCurrent, styler); |
| 741 | |
| 742 | while (lineCurrent > 0) { |
| 743 | lineCurrent--; |
| 744 | indentCurrent = IndentAmount(lineCurrent, styler); |
| 745 | |
| 746 | if (!(indentCurrent & SC_FOLDLEVELWHITEFLAG)) { |
| 747 | break; |
| 748 | } |
| 749 | } |
| 750 | |
| 751 | int indentCurrentLevel = indentCurrent & SC_FOLDLEVELNUMBERMASK; |
| 752 | indentCurrent = indentCurrentLevel | (indentCurrent & ~SC_FOLDLEVELNUMBERMASK); |
| 753 | |
| 754 | while (lineCurrent <= docLines && lineCurrent <= maxLines) { |
| 755 | Sci_Position lineNext = lineCurrent + 1; |
| 756 | int indentNext = indentCurrent; |
| 757 | int lev = indentCurrent; |
| 758 | |
| 759 | if (lineNext <= docLines) { |
| 760 | indentNext = IndentAmount(lineNext, styler); |
| 761 | } |
| 762 | |
| 763 | if (indentNext & SC_FOLDLEVELWHITEFLAG) { |
| 764 | indentNext = SC_FOLDLEVELWHITEFLAG | indentCurrentLevel; |
| 765 | } |
| 766 | |
| 767 | while (lineNext < docLines && (indentNext & SC_FOLDLEVELWHITEFLAG)) { |
| 768 | lineNext++; |
| 769 | indentNext = IndentAmount(lineNext, styler); |
| 770 | } |
| 771 | |
| 772 | const int indentNextLevel = indentNext & SC_FOLDLEVELNUMBERMASK; |
| 773 | indentNext = indentNextLevel | (indentNext & ~SC_FOLDLEVELNUMBERMASK); |
| 774 | |
| 775 | const int = std::max(indentCurrentLevel, indentNextLevel); |
| 776 | |
| 777 | Sci_Position skipLine = lineNext; |
| 778 | int skipLevel = indentNextLevel; |
| 779 | |
| 780 | while (--skipLine > lineCurrent) { |
| 781 | const int skipLineIndent = IndentAmount(skipLine, styler); |
| 782 | |
| 783 | if (options.foldCompact) { |
| 784 | if ((skipLineIndent & SC_FOLDLEVELNUMBERMASK) > indentNextLevel) { |
| 785 | skipLevel = levelBeforeComments; |
| 786 | } |
| 787 | |
| 788 | const int whiteFlag = skipLineIndent & SC_FOLDLEVELWHITEFLAG; |
| 789 | styler.SetLevel(skipLine, skipLevel | whiteFlag); |
| 790 | } else { |
| 791 | if ((skipLineIndent & SC_FOLDLEVELNUMBERMASK) > indentNextLevel && |
| 792 | !(skipLineIndent & SC_FOLDLEVELWHITEFLAG)) { |
| 793 | skipLevel = levelBeforeComments; |
| 794 | } |
| 795 | |
| 796 | styler.SetLevel(skipLine, skipLevel); |
| 797 | } |
| 798 | } |
| 799 | |
| 800 | if (!(indentCurrent & SC_FOLDLEVELWHITEFLAG)) { |
| 801 | if ((indentCurrent & SC_FOLDLEVELNUMBERMASK) < (indentNext & SC_FOLDLEVELNUMBERMASK)) { |
| 802 | lev |= SC_FOLDLEVELHEADERFLAG; |
| 803 | } |
| 804 | } |
| 805 | |
| 806 | styler.SetLevel(lineCurrent, options.foldCompact ? lev : lev & ~SC_FOLDLEVELWHITEFLAG); |
| 807 | |
| 808 | indentCurrent = indentNext; |
| 809 | indentCurrentLevel = indentNextLevel; |
| 810 | lineCurrent = lineNext; |
| 811 | } |
| 812 | } |
| 813 | |
| 814 | LexerModule lmNim(SCLEX_NIM, LexerNim::LexerFactoryNim, "nim" , nimWordListDesc); |