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
|
// Scintilla source code edit control
/** @file LexCOBOL.cxx
** Lexer for COBOL
** Based on LexPascal.cxx
** Written by Laurent le Tynevez
** Updated by Simon Steele <s.steele@pnotepad.org> September 2002
** Updated by Mathias Rauen <scite@madshi.net> May 2003 (Delphi adjustments)
** Updated by Rod Falck, Aug 2006 Converted to COBOL
**/
#include <stdlib.h>
#include <string.h>
#include <stdio.h>
#include <stdarg.h>
#include <assert.h>
#include <ctype.h>
#include "ILexer.h"
#include "Scintilla.h"
#include "SciLexer.h"
#include "WordList.h"
#include "LexAccessor.h"
#include "Accessor.h"
#include "StyleContext.h"
#include "CharacterSet.h"
#include "LexerModule.h"
using namespace Scintilla;
#define IN_DIVISION 0x01
#define IN_DECLARATIVES 0x02
#define IN_SECTION 0x04
#define IN_PARAGRAPH 0x08
#define IN_FLAGS 0xF
#define NOT_HEADER 0x10
inline bool isCOBOLoperator(char ch)
{
return isoperator(ch);
}
inline bool isCOBOLwordchar(char ch)
{
return IsASCII(ch) && (isalnum(ch) || ch == '-');
}
inline bool isCOBOLwordstart(char ch)
{
return IsASCII(ch) && isalnum(ch);
}
static int CountBits(int nBits)
{
int count = 0;
for (int i = 0; i < 32; ++i)
{
count += nBits & 1;
nBits >>= 1;
}
return count;
}
static void getRange(Sci_PositionU start,
Sci_PositionU end,
Accessor &styler,
char *s,
Sci_PositionU len) {
Sci_PositionU i = 0;
while ((i < end - start + 1) && (i < len-1)) {
s[i] = static_cast<char>(tolower(styler[start + i]));
i++;
}
s[i] = '\0';
}
static void ColourTo(Accessor &styler, Sci_PositionU end, unsigned int attr) {
styler.ColourTo(end, attr);
}
static int classifyWordCOBOL(Sci_PositionU start, Sci_PositionU end, /*WordList &keywords*/WordList *keywordlists[], Accessor &styler, int nContainment, bool *bAarea) {
int ret = 0;
WordList& a_keywords = *keywordlists[0];
WordList& b_keywords = *keywordlists[1];
WordList& c_keywords = *keywordlists[2];
char s[100];
s[0] = '\0';
s[1] = '\0';
getRange(start, end, styler, s, sizeof(s));
char chAttr = SCE_C_IDENTIFIER;
if (isdigit(s[0]) || (s[0] == '.') || (s[0] == 'v')) {
chAttr = SCE_C_NUMBER;
char *p = s + 1;
while (*p) {
if ((!isdigit(*p) && (*p) != 'v') && isCOBOLwordchar(*p)) {
chAttr = SCE_C_IDENTIFIER;
break;
}
++p;
}
}
else {
if (a_keywords.InList(s)) {
chAttr = SCE_C_WORD;
}
else if (b_keywords.InList(s)) {
chAttr = SCE_C_WORD2;
}
else if (c_keywords.InList(s)) {
chAttr = SCE_C_UUID;
}
}
if (*bAarea) {
if (strcmp(s, "division") == 0) {
ret = IN_DIVISION;
// we've determined the containment, anything else is just ignored for those purposes
*bAarea = false;
} else if (strcmp(s, "declaratives") == 0) {
ret = IN_DIVISION | IN_DECLARATIVES;
if (nContainment & IN_DECLARATIVES)
ret |= NOT_HEADER | IN_SECTION;
// we've determined the containment, anything else is just ignored for those purposes
*bAarea = false;
} else if (strcmp(s, "section") == 0) {
ret = (nContainment &~ IN_PARAGRAPH) | IN_SECTION;
// we've determined the containment, anything else is just ignored for those purposes
*bAarea = false;
} else if (strcmp(s, "end") == 0 && (nContainment & IN_DECLARATIVES)) {
ret = IN_DIVISION | IN_DECLARATIVES | IN_SECTION | NOT_HEADER;
} else {
ret = nContainment | IN_PARAGRAPH;
}
}
ColourTo(styler, end, chAttr);
return ret;
}
static void ColouriseCOBOLDoc(Sci_PositionU startPos, Sci_Position length, int initStyle, WordList *keywordlists[],
Accessor &styler) {
styler.StartAt(startPos);
int state = initStyle;
if (state == SCE_C_CHARACTER) // Does not leak onto next line
state = SCE_C_DEFAULT;
char chPrev = ' ';
char chNext = styler[startPos];
Sci_PositionU lengthDoc = startPos + length;
int nContainment;
Sci_Position currentLine = styler.GetLine(startPos);
if (currentLine > 0) {
styler.SetLineState(currentLine, styler.GetLineState(currentLine-1));
nContainment = styler.GetLineState(currentLine);
nContainment &= ~NOT_HEADER;
} else {
styler.SetLineState(currentLine, 0);
nContainment = 0;
}
styler.StartSegment(startPos);
bool bNewLine = true;
bool bAarea = !isspacechar(chNext);
int column = 0;
for (Sci_PositionU i = startPos; i < lengthDoc; i++) {
char ch = chNext;
chNext = styler.SafeGetCharAt(i + 1);
++column;
if (bNewLine) {
column = 0;
}
if (column <= 1 && !bAarea) {
bAarea = !isspacechar(ch);
}
bool bSetNewLine = false;
if ((ch == '\r' && chNext != '\n') || (ch == '\n')) {
// Trigger on CR only (Mac style) or either on LF from CR+LF (Dos/Win) or on LF alone (Unix)
// Avoid triggering two times on Dos/Win
// End of line
if (state == SCE_C_CHARACTER) {
ColourTo(styler, i, state);
state = SCE_C_DEFAULT;
}
styler.SetLineState(currentLine, nContainment);
currentLine++;
bSetNewLine = true;
if (nContainment & NOT_HEADER)
nContainment &= ~(NOT_HEADER | IN_DECLARATIVES | IN_SECTION);
}
if (styler.IsLeadByte(ch)) {
chNext = styler.SafeGetCharAt(i + 2);
chPrev = ' ';
i += 1;
continue;
}
if (state == SCE_C_DEFAULT) {
if (isCOBOLwordstart(ch) || (ch == '$' && IsASCII(chNext) && isalpha(chNext))) {
ColourTo(styler, i-1, state);
state = SCE_C_IDENTIFIER;
} else if (column == 6 && ch == '*') {
// Cobol comment line: asterisk in column 7.
ColourTo(styler, i-1, state);
state = SCE_C_COMMENTLINE;
} else if (ch == '*' && chNext == '>') {
// Cobol inline comment: asterisk, followed by greater than.
ColourTo(styler, i-1, state);
state = SCE_C_COMMENTLINE;
} else if (column == 0 && ch == '*' && chNext != '*') {
ColourTo(styler, i-1, state);
state = SCE_C_COMMENTLINE;
} else if (column == 0 && ch == '/' && chNext != '*') {
ColourTo(styler, i-1, state);
state = SCE_C_COMMENTLINE;
} else if (column == 0 && ch == '*' && chNext == '*') {
ColourTo(styler, i-1, state);
state = SCE_C_COMMENTDOC;
} else if (column == 0 && ch == '/' && chNext == '*') {
ColourTo(styler, i-1, state);
state = SCE_C_COMMENTDOC;
} else if (ch == '"') {
ColourTo(styler, i-1, state);
state = SCE_C_STRING;
} else if (ch == '\'') {
ColourTo(styler, i-1, state);
state = SCE_C_CHARACTER;
} else if (ch == '?' && column == 0) {
ColourTo(styler, i-1, state);
state = SCE_C_PREPROCESSOR;
} else if (isCOBOLoperator(ch)) {
ColourTo(styler, i-1, state);
ColourTo(styler, i, SCE_C_OPERATOR);
}
} else if (state == SCE_C_IDENTIFIER) {
if (!isCOBOLwordchar(ch)) {
int lStateChange = classifyWordCOBOL(styler.GetStartSegment(), i - 1, keywordlists, styler, nContainment, &bAarea);
if(lStateChange != 0) {
styler.SetLineState(currentLine, lStateChange);
nContainment = lStateChange;
}
state = SCE_C_DEFAULT;
chNext = styler.SafeGetCharAt(i + 1);
if (ch == '"') {
state = SCE_C_STRING;
} else if (ch == '\'') {
state = SCE_C_CHARACTER;
} else if (isCOBOLoperator(ch)) {
ColourTo(styler, i, SCE_C_OPERATOR);
}
}
} else {
if (state == SCE_C_PREPROCESSOR) {
if ((ch == '\r' || ch == '\n') && !(chPrev == '\\' || chPrev == '\r')) {
ColourTo(styler, i-1, state);
state = SCE_C_DEFAULT;
}
} else if (state == SCE_C_COMMENT) {
if (ch == '\r' || ch == '\n') {
ColourTo(styler, i, state);
state = SCE_C_DEFAULT;
}
} else if (state == SCE_C_COMMENTDOC) {
if (ch == '\r' || ch == '\n') {
if (((i > styler.GetStartSegment() + 2) || (
(initStyle == SCE_C_COMMENTDOC) &&
(styler.GetStartSegment() == static_cast<Sci_PositionU>(startPos))))) {
ColourTo(styler, i, state);
state = SCE_C_DEFAULT;
}
}
} else if (state == SCE_C_COMMENTLINE) {
if (ch == '\r' || ch == '\n') {
ColourTo(styler, i-1, state);
state = SCE_C_DEFAULT;
}
} else if (state == SCE_C_STRING) {
if (ch == '"') {
ColourTo(styler, i, state);
state = SCE_C_DEFAULT;
}
} else if (state == SCE_C_CHARACTER) {
if (ch == '\'') {
ColourTo(styler, i, state);
state = SCE_C_DEFAULT;
}
}
}
chPrev = ch;
bNewLine = bSetNewLine;
if (bNewLine)
{
bAarea = false;
}
}
ColourTo(styler, lengthDoc - 1, state);
}
static void FoldCOBOLDoc(Sci_PositionU startPos, Sci_Position length, int, WordList *[],
Accessor &styler) {
bool foldCompact = styler.GetPropertyInt("fold.compact", 1) != 0;
Sci_PositionU endPos = startPos + length;
int visibleChars = 0;
Sci_Position lineCurrent = styler.GetLine(startPos);
int levelPrev = lineCurrent > 0 ? styler.LevelAt(lineCurrent - 1) & SC_FOLDLEVELNUMBERMASK : 0xFFF;
char chNext = styler[startPos];
bool bNewLine = true;
bool bAarea = !isspacechar(chNext);
int column = 0;
bool bComment = false;
for (Sci_PositionU i = startPos; i < endPos; i++) {
char ch = chNext;
chNext = styler.SafeGetCharAt(i + 1);
++column;
if (bNewLine) {
column = 0;
bComment = (ch == '*' || ch == '/' || ch == '?');
}
if (column <= 1 && !bAarea) {
bAarea = !isspacechar(ch);
}
bool atEOL = (ch == '\r' && chNext != '\n') || (ch == '\n');
if (atEOL) {
int nContainment = styler.GetLineState(lineCurrent);
int lev = CountBits(nContainment & IN_FLAGS) | SC_FOLDLEVELBASE;
if (bAarea && !bComment)
--lev;
if (visibleChars == 0 && foldCompact)
lev |= SC_FOLDLEVELWHITEFLAG;
if ((bAarea) && (visibleChars > 0) && !(nContainment & NOT_HEADER) && !bComment)
lev |= SC_FOLDLEVELHEADERFLAG;
if (lev != styler.LevelAt(lineCurrent)) {
styler.SetLevel(lineCurrent, lev);
}
if ((lev & SC_FOLDLEVELNUMBERMASK) <= (levelPrev & SC_FOLDLEVELNUMBERMASK)) {
// this level is at the same level or less than the previous line
// therefore these is nothing for the previous header to collapse, so remove the header
styler.SetLevel(lineCurrent - 1, levelPrev & ~SC_FOLDLEVELHEADERFLAG);
}
levelPrev = lev;
visibleChars = 0;
bAarea = false;
bNewLine = true;
lineCurrent++;
} else {
bNewLine = false;
}
if (!isspacechar(ch))
visibleChars++;
}
// Fill in the real level of the next line, keeping the current flags as they will be filled in later
int flagsNext = styler.LevelAt(lineCurrent) & ~SC_FOLDLEVELNUMBERMASK;
styler.SetLevel(lineCurrent, levelPrev | flagsNext);
}
static const char * const COBOLWordListDesc[] = {
"A Keywords",
"B Keywords",
"Extended Keywords",
0
};
LexerModule lmCOBOL(SCLEX_COBOL, ColouriseCOBOLDoc, "COBOL", FoldCOBOLDoc, COBOLWordListDesc);
|