plugins/scintilla/scintilla/KeyWords.cxx

   1 // Scintilla source code edit control
   2 /** @file KeyWords.cxx
   3  ** Colourise for particular languages.
   4  **/
   5 // Copyright 1998-2002 by Neil Hodgson <neilh@scintilla.org>
   6 // The License.txt file describes the conditions under which this software may be distributed.
   7
   8 #include <stdlib.h>
   9 #include <string.h>
  10 #include <ctype.h>
  11 #include <stdio.h>
  12 #include <stdarg.h>
  13
  14 #include "Platform.h"
  15
  16 #include "PropSet.h"
  17 #include "Accessor.h"
  18 #include "KeyWords.h"
  19 #include "Scintilla.h"
  20 #include "SciLexer.h"
  21
  22 #ifdef SCI_NAMESPACE
  23 using namespace Scintilla;
  24 #endif
  25
  26 /**
  27  * Creates an array that points into each word in the string and puts \0 terminators
  28  * after each word.
  29  */
  30 static char **ArrayFromWordList(char *wordlist, int *len, bool onlyLineEnds = false) {
  31         int prev = '\n';
  32         int words = 0;
  33         // For rapid determination of whether a character is a separator, build
  34         // a look up table.
  35         bool wordSeparator[256];
  36         for (int i=0;i<256; i++) {
  37                 wordSeparator[i] = false;
  38         }
  39         wordSeparator['\r'] = true;
  40         wordSeparator['\n'] = true;
  41         if (!onlyLineEnds) {
  42                 wordSeparator[' '] = true;
  43                 wordSeparator['\t'] = true;
  44         }
  45         for (int j = 0; wordlist[j]; j++) {
  46                 int curr = static_cast<unsigned char>(wordlist[j]);
  47                 if (!wordSeparator[curr] && wordSeparator[prev])
  48                         words++;
  49                 prev = curr;
  50         }
  51         char **keywords = new char *[words + 1];
  52         if (keywords) {
  53                 words = 0;
  54                 prev = '\0';
  55                 size_t slen = strlen(wordlist);
  56                 for (size_t k = 0; k < slen; k++) {
  57                         if (!wordSeparator[static_cast<unsigned char>(wordlist[k])]) {
  58                                 if (!prev) {
  59                                         keywords[words] = &wordlist[k];
  60                                         words++;
  61                                 }
  62                         } else {
  63                                 wordlist[k] = '\0';
  64                         }
  65                         prev = wordlist[k];
  66                 }
  67                 keywords[words] = &wordlist[slen];
  68                 *len = words;
  69         } else {
  70                 *len = 0;
  71         }
  72         return keywords;
  73 }
  74
  75 void WordList::Clear() {
  76         if (words) {
  77                 delete []list;
  78                 delete []words;
  79         }
  80         words = 0;
  81         list = 0;
  82         len = 0;
  83         sorted = false;
  84 }
  85
  86 void WordList::Set(const char *s) {
  87         list = new char[strlen(s) + 1];
  88         strcpy(list, s);
  89         sorted = false;
  90         words = ArrayFromWordList(list, &len, onlyLineEnds);
  91 }
  92
  93 extern "C" int cmpString(const void *a1, const void *a2) {
  94         // Can't work out the correct incantation to use modern casts here
  95         return strcmp(*(char**)(a1), *(char**)(a2));
  96 }
  97
  98 static void SortWordList(char **words, unsigned int len) {
  99         qsort(reinterpret_cast<void*>(words), len, sizeof(*words),
 100               cmpString);
 101 }
 102
 103 bool WordList::InList(const char *s) {
 104         if (0 == words)
 105                 return false;
 106         if (!sorted) {
 107                 sorted = true;
 108                 SortWordList(words, len);
 109                 for (unsigned int k = 0; k < (sizeof(starts) / sizeof(starts[0])); k++)
 110                         starts[k] = -1;
 111                 for (int l = len - 1; l >= 0; l--) {
 112                         unsigned char indexChar = words[l][0];
 113                         starts[indexChar] = l;
 114                 }
 115         }
 116         unsigned char firstChar = s[0];
 117         int j = starts[firstChar];
 118         if (j >= 0) {
 119                 while ((unsigned char)words[j][0] == firstChar) {
 120                         if (s[1] == words[j][1]) {
 121                                 const char *a = words[j] + 1;
 122                                 const char *b = s + 1;
 123                                 while (*a && *a == *b) {
 124                                         a++;
 125                                         b++;
 126                                 }
 127                                 if (!*a && !*b)
 128                                         return true;
 129                         }
 130                         j++;
 131                 }
 132         }
 133         j = starts['^'];
 134         if (j >= 0) {
 135                 while (words[j][0] == '^') {
 136                         const char *a = words[j] + 1;
 137                         const char *b = s;
 138                         while (*a && *a == *b) {
 139                                 a++;
 140                                 b++;
 141                         }
 142                         if (!*a)
 143                                 return true;
 144                         j++;
 145                 }
 146         }
 147         return false;
 148 }
 149
 150 /** similar to InList, but word s can be a substring of keyword.
 151  * eg. the keyword define is defined as def~ine. This means the word must start
 152  * with def to be a keyword, but also defi, defin and define are valid.
 153  * The marker is ~ in this case.
 154  */
 155 bool WordList::InListAbbreviated(const char *s, const char marker) {
 156         if (0 == words)
 157                 return false;
 158         if (!sorted) {
 159                 sorted = true;
 160                 SortWordList(words, len);
 161                 for (unsigned int k = 0; k < (sizeof(starts) / sizeof(starts[0])); k++)
 162                         starts[k] = -1;
 163                 for (int l = len - 1; l >= 0; l--) {
 164                         unsigned char indexChar = words[l][0];
 165                         starts[indexChar] = l;
 166                 }
 167         }
 168         unsigned char firstChar = s[0];
 169         int j = starts[firstChar];
 170         if (j >= 0) {
 171                 while (words[j][0] == firstChar) {
 172                         bool isSubword = false;
 173                         int start = 1;
 174                         if (words[j][1] == marker) {
 175                                 isSubword = true;
 176                                 start++;
 177                         }
 178                         if (s[1] == words[j][start]) {
 179                                 const char *a = words[j] + start;
 180                                 const char *b = s + 1;
 181                                 while (*a && *a == *b) {
 182                                         a++;
 183                                         if (*a == marker) {
 184                                                 isSubword = true;
 185                                                 a++;
 186                                         }
 187                                         b++;
 188                                 }
 189                                 if ((!*a || isSubword) && !*b)
 190                                         return true;
 191                         }
 192                         j++;
 193                 }
 194         }
 195         j = starts['^'];
 196         if (j >= 0) {
 197                 while (words[j][0] == '^') {
 198                         const char *a = words[j] + 1;
 199                         const char *b = s;
 200                         while (*a && *a == *b) {
 201                                 a++;
 202                                 b++;
 203                         }
 204                         if (!*a)
 205                                 return true;
 206                         j++;
 207                 }
 208         }
 209         return false;
 210 }
 211
 212 const LexerModule *LexerModule::base = 0;
 213 int LexerModule::nextLanguage = SCLEX_AUTOMATIC+1;
 214
 215 LexerModule::LexerModule(int language_,
 216         LexerFunction fnLexer_,
 217         const char *languageName_,
 218         LexerFunction fnFolder_,
 219         const char * const wordListDescriptions_[],
 220         int styleBits_) :
 221         language(language_),
 222         fnLexer(fnLexer_),
 223         fnFolder(fnFolder_),
 224         wordListDescriptions(wordListDescriptions_),
 225         styleBits(styleBits_),
 226         languageName(languageName_) {
 227         next = base;
 228         base = this;
 229         if (language == SCLEX_AUTOMATIC) {
 230                 language = nextLanguage;
 231                 nextLanguage++;
 232         }
 233 }
 234
 235 int LexerModule::GetNumWordLists() const {
 236         if (wordListDescriptions == NULL) {
 237                 return -1;
 238         } else {
 239                 int numWordLists = 0;
 240
 241                 while (wordListDescriptions[numWordLists]) {
 242                         ++numWordLists;
 243                 }
 244
 245                 return numWordLists;
 246         }
 247 }
 248
 249 const char *LexerModule::GetWordListDescription(int index) const {
 250         static const char *emptyStr = "";
 251
 252         PLATFORM_ASSERT(index < GetNumWordLists());
 253         if (index >= GetNumWordLists()) {
 254                 return emptyStr;
 255         } else {
 256                 return wordListDescriptions[index];
 257         }
 258 }
 259
 260 int LexerModule::GetStyleBitsNeeded() const {
 261         return styleBits;
 262 }
 263
 264 const LexerModule *LexerModule::Find(int language) {
 265         const LexerModule *lm = base;
 266         while (lm) {
 267                 if (lm->language == language) {
 268                         return lm;
 269                 }
 270                 lm = lm->next;
 271         }
 272         return 0;
 273 }
 274
 275 const LexerModule *LexerModule::Find(const char *languageName) {
 276         if (languageName) {
 277                 const LexerModule *lm = base;
 278                 while (lm) {
 279                         if (lm->languageName && 0 == strcmp(lm->languageName, languageName)) {
 280                                 return lm;
 281                         }
 282                         lm = lm->next;
 283                 }
 284         }
 285         return 0;
 286 }
 287
 288 void LexerModule::Lex(unsigned int startPos, int lengthDoc, int initStyle,
 289           WordList *keywordlists[], Accessor &styler) const {
 290         if (fnLexer)
 291                 fnLexer(startPos, lengthDoc, initStyle, keywordlists, styler);
 292 }
 293
 294 void LexerModule::Fold(unsigned int startPos, int lengthDoc, int initStyle,
 295           WordList *keywordlists[], Accessor &styler) const {
 296         if (fnFolder) {
 297                 int lineCurrent = styler.GetLine(startPos);
 298                 // Move back one line in case deletion wrecked current line fold state
 299                 if (lineCurrent > 0) {
 300                         lineCurrent--;
 301                         int newStartPos = styler.LineStart(lineCurrent);
 302                         lengthDoc += startPos - newStartPos;
 303                         startPos = newStartPos;
 304                         initStyle = 0;
 305                         if (startPos > 0) {
 306                                 initStyle = styler.StyleAt(startPos - 1);
 307                         }
 308                 }
 309                 fnFolder(startPos, lengthDoc, initStyle, keywordlists, styler);
 310         }
 311 }
 312
 313 // Alternative historical name for Scintilla_LinkLexers
 314 int wxForceScintillaLexers(void) {
 315         return Scintilla_LinkLexers();
 316 }
 317
 318 // To add or remove a lexer, add or remove its file and run LexGen.py.
 319
 320 // Force a reference to all of the Scintilla lexers so that the linker will
 321 // not remove the code of the lexers.
 322 int Scintilla_LinkLexers() {
 323         static int forcer = 0;
 324
 325 // Shorten the code that declares a lexer and ensures it is linked in by calling a method.
 326 #define LINK_LEXER(lexer) extern LexerModule lexer; forcer += lexer.GetLanguage();
 327
 328 //++Autogenerated -- run src/LexGen.py to regenerate
 329 //**\(\tLINK_LEXER(\*);\n\)
 330         LINK_LEXER(lmAbaqus);
 331         LINK_LEXER(lmAda);
 332         LINK_LEXER(lmAns1);
 333         LINK_LEXER(lmAPDL);
 334         LINK_LEXER(lmAsm);
 335         LINK_LEXER(lmASY);
 336         LINK_LEXER(lmAU3);
 337         LINK_LEXER(lmAVE);
 338         LINK_LEXER(lmBaan);
 339         LINK_LEXER(lmBash);
 340         LINK_LEXER(lmBatch);
 341         LINK_LEXER(lmBlitzBasic);
 342         LINK_LEXER(lmBullant);
 343         LINK_LEXER(lmCaml);
 344         LINK_LEXER(lmClw);
 345         LINK_LEXER(lmClwNoCase);
 346         LINK_LEXER(lmCmake);
 347         LINK_LEXER(lmCOBOL);
 348         LINK_LEXER(lmConf);
 349         LINK_LEXER(lmCPP);
 350         LINK_LEXER(lmCPPNoCase);
 351         LINK_LEXER(lmCsound);
 352         LINK_LEXER(lmCss);
 353         LINK_LEXER(lmD);
 354         LINK_LEXER(lmDiff);
 355         LINK_LEXER(lmEiffel);
 356         LINK_LEXER(lmEiffelkw);
 357         LINK_LEXER(lmErlang);
 358         LINK_LEXER(lmErrorList);
 359         LINK_LEXER(lmESCRIPT);
 360         LINK_LEXER(lmF77);
 361         LINK_LEXER(lmFlagShip);
 362         LINK_LEXER(lmForth);
 363         LINK_LEXER(lmFortran);
 364         LINK_LEXER(lmFreeBasic);
 365         LINK_LEXER(lmGAP);
 366         LINK_LEXER(lmGui4Cli);
 367         LINK_LEXER(lmHaskell);
 368         LINK_LEXER(lmHTML);
 369         LINK_LEXER(lmInno);
 370         LINK_LEXER(lmKix);
 371         LINK_LEXER(lmLatex);
 372         LINK_LEXER(lmLISP);
 373         LINK_LEXER(lmLot);
 374         LINK_LEXER(lmLout);
 375         LINK_LEXER(lmLua);
 376         LINK_LEXER(lmMagikSF);
 377         LINK_LEXER(lmMake);
 378         LINK_LEXER(lmMarkdown);
 379         LINK_LEXER(lmMatlab);
 380         LINK_LEXER(lmMETAPOST);
 381         LINK_LEXER(lmMMIXAL);
 382         LINK_LEXER(lmMSSQL);
 383         LINK_LEXER(lmMySQL);
 384         LINK_LEXER(lmNimrod);
 385         LINK_LEXER(lmNncrontab);
 386         LINK_LEXER(lmNsis);
 387         LINK_LEXER(lmNull);
 388         LINK_LEXER(lmOctave);
 389         LINK_LEXER(lmOpal);
 390         LINK_LEXER(lmPascal);
 391         LINK_LEXER(lmPB);
 392         LINK_LEXER(lmPerl);
 393         LINK_LEXER(lmPHPSCRIPT);
 394         LINK_LEXER(lmPLM);
 395         LINK_LEXER(lmPo);
 396         LINK_LEXER(lmPOV);
 397         LINK_LEXER(lmPowerPro);
 398         LINK_LEXER(lmPowerShell);
 399         LINK_LEXER(lmProgress);
 400         LINK_LEXER(lmProps);
 401         LINK_LEXER(lmPS);
 402         LINK_LEXER(lmPureBasic);
 403         LINK_LEXER(lmPython);
 404         LINK_LEXER(lmR);
 405         LINK_LEXER(lmREBOL);
 406         LINK_LEXER(lmRuby);
 407         LINK_LEXER(lmScriptol);
 408         LINK_LEXER(lmSmalltalk);
 409         LINK_LEXER(lmSML);
 410         LINK_LEXER(lmSorc);
 411         LINK_LEXER(lmSpecman);
 412         LINK_LEXER(lmSpice);
 413         LINK_LEXER(lmSQL);
 414         LINK_LEXER(lmTACL);
 415         LINK_LEXER(lmTADS3);
 416         LINK_LEXER(lmTAL);
 417         LINK_LEXER(lmTCL);
 418         LINK_LEXER(lmTeX);
 419         LINK_LEXER(lmVB);
 420         LINK_LEXER(lmVBScript);
 421         LINK_LEXER(lmVerilog);
 422         LINK_LEXER(lmVHDL);
 423         LINK_LEXER(lmXML);
 424         LINK_LEXER(lmYAML);
 425
 426 //--Autogenerated -- end of automatically generated section
 427
 428         return 1;
 429 }