// Scintilla source code edit control
/** @file LexCPP.cxx
 ** Lexer for C++, C, Java, and JavaScript.
 **/
// Copyright 1998-2005 by Neil Hodgson <neilh@scintilla.org>
// The License.txt file describes the conditions under which this software may be distributed.

#include <stdlib.h>
#include <string.h>
#include <ctype.h>
#include <stdio.h>
#include <stdarg.h>

#include "Platform.h"

#include "PropSet.h"
#include "Accessor.h"
#include "StyleContext.h"
#include "KeyWords.h"
#include "Scintilla.h"
#include "SciLexer.h"
#include "CharacterSet.h"

#ifdef SCI_NAMESPACE
using namespace Scintilla;
#endif

static bool IsSpaceEquiv(int state) {
	return (state <= SCE_C_COMMENTDOC) ||
		// including SCE_C_DEFAULT, SCE_C_COMMENT, SCE_C_COMMENTLINE
		(state == SCE_C_COMMENTLINEDOC) || (state == SCE_C_COMMENTDOCKEYWORD) ||
		(state == SCE_C_COMMENTDOCKEYWORDERROR);
}

// Preconditions: sc.currentPos points to a character after '+' or '-'.
// The test for pos reaching 0 should be redundant,
// and is in only for safety measures.
// Limitation: this code will give the incorrect answer for code like
// a = b+++/ptn/...
// Putting a space between the '++' post-inc operator and the '+' binary op
// fixes this, and is highly recommended for readability anyway.
static bool FollowsPostfixOperator(StyleContext &sc, Accessor &styler) {
	int pos = (int) sc.currentPos;
	while (--pos > 0) {
		char ch = styler[pos];
		if (ch == '+' || ch == '-') {
			return styler[pos - 1] == ch;
		}
	}
	return false;
}

static void ColouriseCppDoc(unsigned int startPos, int length, int initStyle, WordList *keywordlists[],
                            Accessor &styler, bool caseSensitive) {

	WordList &keywords = *keywordlists[0];
	WordList &keywords2 = *keywordlists[1];
	WordList &keywords3 = *keywordlists[2];
	WordList &keywords4 = *keywordlists[3];

	// property styling.within.preprocessor
	//	For C++ code, determines whether all preprocessor code is styled in the preprocessor style (0, the default)
	//	or only from the initial # to the end of the command word(1).
	bool stylingWithinPreprocessor = styler.GetPropertyInt("styling.within.preprocessor") != 0;

	CharacterSet setOKBeforeRE(CharacterSet::setNone, "([{=,:;!%^&*|?~+-");
	CharacterSet setCouldBePostOp(CharacterSet::setNone, "+-");

	CharacterSet setDoxygen(CharacterSet::setAlpha, "$@\\&<>#{}[]");

	CharacterSet setWordStart(CharacterSet::setAlpha, "_", 0x80, true);
	CharacterSet setWord(CharacterSet::setAlphaNum, "._", 0x80, true);

	// property lexer.cpp.allow.dollars
	//	Set to 0 to disallow the '$' character in identifiers with the cpp lexer.
	if (styler.GetPropertyInt("lexer.cpp.allow.dollars", 1) != 0) {
		setWordStart.Add('$');
		setWord.Add('$');
	}

	int chPrevNonWhite = ' ';
	int visibleChars = 0;
	bool lastWordWasUUID = false;
	int styleBeforeDCKeyword = SCE_C_DEFAULT;
	bool continuationLine = false;
	bool isIncludePreprocessor = false;

	if (initStyle == SCE_C_PREPROCESSOR) {
		// Set continuationLine if last character of previous line is '\'
		int lineCurrent = styler.GetLine(startPos);
		if (lineCurrent > 0) {
			int chBack = styler.SafeGetCharAt(startPos-1, 0);
			int chBack2 = styler.SafeGetCharAt(startPos-2, 0);
			int lineEndChar = '!';
			if (chBack2 == '\r' && chBack == '\n') {
				lineEndChar = styler.SafeGetCharAt(startPos-3, 0);
			} else if (chBack == '\n' || chBack == '\r') {
				lineEndChar = chBack2;
			}
			continuationLine = lineEndChar == '\\';
		}
	}

	// look back to set chPrevNonWhite properly for better regex colouring
	if (startPos > 0) {
		int back = startPos;
		while (--back && IsSpaceEquiv(styler.StyleAt(back)))
			;
		if (styler.StyleAt(back) == SCE_C_OPERATOR) {
			chPrevNonWhite = styler.SafeGetCharAt(back);
		}
	}

	StyleContext sc(startPos, length, initStyle, styler);

	for (; sc.More(); sc.Forward()) {

		if (sc.atLineStart) {
			if (sc.state == SCE_C_STRING) {
				// Prevent SCE_C_STRINGEOL from leaking back to previous line which
				// ends with a line continuation by locking in the state upto this position.
				sc.SetState(SCE_C_STRING);
			}
			// Reset states to begining of colourise so no surprises
			// if different sets of lines lexed.
			visibleChars = 0;
			lastWordWasUUID = false;
			isIncludePreprocessor = false;
		}

		// Handle line continuation generically.
		if (sc.ch == '\\') {
			if (sc.chNext == '\n' || sc.chNext == '\r') {
				sc.Forward();
				if (sc.ch == '\r' && sc.chNext == '\n') {
					sc.Forward();
				}
				continuationLine = true;
				continue;
			}
		}

		// Determine if the current state should terminate.
		switch (sc.state) {
			case SCE_C_OPERATOR:
				sc.SetState(SCE_C_DEFAULT);
				break;
			case SCE_C_NUMBER:
				// We accept almost anything because of hex. and number suffixes
				if (!setWord.Contains(sc.ch)) {
					sc.SetState(SCE_C_DEFAULT);
				}
				break;
			case SCE_C_IDENTIFIER:
				if (!setWord.Contains(sc.ch) || (sc.ch == '.')) {
					char s[1000];
					if (caseSensitive) {
						sc.GetCurrent(s, sizeof(s));
					} else {
						sc.GetCurrentLowered(s, sizeof(s));
					}
					if (keywords.InList(s)) {
						lastWordWasUUID = strcmp(s, "uuid") == 0;
						sc.ChangeState(SCE_C_WORD);
					} else if (keywords2.InList(s)) {
						sc.ChangeState(SCE_C_WORD2);
					} else if (keywords4.InList(s)) {
						sc.ChangeState(SCE_C_GLOBALCLASS);
					}
					sc.SetState(SCE_C_DEFAULT);
				}
				break;
			case SCE_C_PREPROCESSOR:
				if (sc.atLineStart && !continuationLine) {
					sc.SetState(SCE_C_DEFAULT);
				} else if (stylingWithinPreprocessor) {
					if (IsASpace(sc.ch)) {
						sc.SetState(SCE_C_DEFAULT);
					}
				} else {
					if (sc.Match('/', '*') || sc.Match('/', '/')) {
						sc.SetState(SCE_C_DEFAULT);
					}
				}
				break;
			case SCE_C_COMMENT:
				if (sc.Match('*', '/')) {
					sc.Forward();
					sc.ForwardSetState(SCE_C_DEFAULT);
				}
				break;
			case SCE_C_COMMENTDOC:
				if (sc.Match('*', '/')) {
					sc.Forward();
					sc.ForwardSetState(SCE_C_DEFAULT);
				} else if (sc.ch == '@' || sc.ch == '\\') { // JavaDoc and Doxygen support
					// Verify that we have the conditions to mark a comment-doc-keyword
					if ((IsASpace(sc.chPrev) || sc.chPrev == '*') && (!IsASpace(sc.chNext))) {
						styleBeforeDCKeyword = SCE_C_COMMENTDOC;
						sc.SetState(SCE_C_COMMENTDOCKEYWORD);
					}
				}
				break;
			case SCE_C_COMMENTLINE:
				if (sc.atLineStart) {
					sc.SetState(SCE_C_DEFAULT);
				}
				break;
			case SCE_C_COMMENTLINEDOC:
				if (sc.atLineStart) {
					sc.SetState(SCE_C_DEFAULT);
				} else if (sc.ch == '@' || sc.ch == '\\') { // JavaDoc and Doxygen support
					// Verify that we have the conditions to mark a comment-doc-keyword
					if ((IsASpace(sc.chPrev) || sc.chPrev == '/' || sc.chPrev == '!') && (!IsASpace(sc.chNext))) {
						styleBeforeDCKeyword = SCE_C_COMMENTLINEDOC;
						sc.SetState(SCE_C_COMMENTDOCKEYWORD);
					}
				}
				break;
			case SCE_C_COMMENTDOCKEYWORD:
				if ((styleBeforeDCKeyword == SCE_C_COMMENTDOC) && sc.Match('*', '/')) {
					sc.ChangeState(SCE_C_COMMENTDOCKEYWORDERROR);
					sc.Forward();
					sc.ForwardSetState(SCE_C_DEFAULT);
				} else if (!setDoxygen.Contains(sc.ch)) {
					char s[100];
					if (caseSensitive) {
						sc.GetCurrent(s, sizeof(s));
					} else {
						sc.GetCurrentLowered(s, sizeof(s));
					}
					if (!IsASpace(sc.ch) || !keywords3.InList(s + 1)) {
						sc.ChangeState(SCE_C_COMMENTDOCKEYWORDERROR);
					}
					sc.SetState(styleBeforeDCKeyword);
				}
				break;
			case SCE_C_STRING:
				if (sc.atLineEnd) {
					sc.ChangeState(SCE_C_STRINGEOL);
				} else if (isIncludePreprocessor) {
					if (sc.ch == '>') {
						sc.ForwardSetState(SCE_C_DEFAULT);
						isIncludePreprocessor = false;
					}
				} else if (sc.ch == '\\') {
					if (sc.chNext == '\"' || sc.chNext == '\'' || sc.chNext == '\\') {
						sc.Forward();
					}
				} else if (sc.ch == '\"') {
					sc.ForwardSetState(SCE_C_DEFAULT);
				}
				break;
			case SCE_C_CHARACTER:
				if (sc.atLineEnd) {
					sc.ChangeState(SCE_C_STRINGEOL);
				} else if (sc.ch == '\\') {
					if (sc.chNext == '\"' || sc.chNext == '\'' || sc.chNext == '\\') {
						sc.Forward();
					}
				} else if (sc.ch == '\'') {
					sc.ForwardSetHTTP/1.1 200 OK
Connection: keep-alive
Connection: keep-alive
Connection: keep-alive
Content-Disposition: inline; filename="LexCPP.cxx"
Content-Disposition: inline; filename="LexCPP.cxx"
Content-Disposition: inline; filename="LexCPP.cxx"
Content-Length: 16317
Content-Length: 16317
Content-Length: 16317
Content-Security-Policy: default-src 'none'
Content-Security-Policy: default-src 'none'
Content-Security-Policy: default-src 'none'
Content-Type: text/plain; charset=UTF-8
Content-Type: text/plain; charset=UTF-8
Content-Type: text/plain; charset=UTF-8
Date: Sat, 18 Oct 2025 08:03:02 UTC
ETag: "8a9395e179e941e88d1a90316f5e24751e673fa2"
ETag: "8a9395e179e941e88d1a90316f5e24751e673fa2"
ETag: "8a9395e179e941e88d1a90316f5e24751e673fa2"
Expires: Tue, 16 Oct 2035 08:03:02 GMT
Expires: Tue, 16 Oct 2035 08:03:03 GMT
Expires: Tue, 16 Oct 2035 08:03:03 GMT
Last-Modified: Sat, 18 Oct 2025 08:03:02 GMT
Last-Modified: Sat, 18 Oct 2025 08:03:03 GMT
Last-Modified: Sat, 18 Oct 2025 08:03:03 GMT
Server: OpenBSD httpd
Server: OpenBSD httpd
Server: OpenBSD httpd
X-Content-Type-Options: nosniff
X-Content-Type-Options: nosniff
X-Content-Type-Options: nosniff

// Scintilla source code edit control
/** @file LexCPP.cxx
 ** Lexer for C++, C, Java, and JavaScript.
 **/
// Copyright 1998-2005 by Neil Hodgson <neilh@scintilla.org>
// The License.txt file describes the conditions under which this software may be distributed.

#include <stdlib.h>
#include <string.h>
#include <ctype.h>
#include <stdio.h>
#include <stdarg.h>

#include "Platform.h"

#include "PropSet.h"
#include "Accessor.h"
#include "StyleContext.h"
#include "KeyWords.h"
#include "Scintilla.h"
#include "SciLexer.h"
#include "CharacterSet.h"

#ifdef SCI_NAMESPACE
using namespace Scintilla;
#endif

static bool IsSpaceEquiv(int state) {
	return (state <= SCE_C_COMMENTDOC) ||
		// including SCE_C_DEFAULT, SCE_C_COMMENT, SCE_C_COMMENTLINE
		(state == SCE_C_COMMENTLINEDOC) || (state == SCE_C_COMMENTDOCKEYWORD) ||
		(state == SCE_C_COMMENTDOCKEYWORDERROR);
}

// Preconditions: sc.currentPos points to a character after '+' or '-'.
// The test for pos reaching 0 should be redundant,
// and is in only for safety measures.
// Limitation: this code will give the incorrect answer for code like
// a = b+++/ptn/...
// Putting a space between the '++' post-inc operator and the '+' binary op
// fixes this, and is highly recommended for readability anyway.
static bool FollowsPostfixOperator(StyleContext &sc, Accessor &styler) {
	int pos = (int) sc.currentPos;
	while (--pos > 0) {
		char ch = styler[pos];
		if (ch == '+' || ch == '-') {
			return styler[pos - 1] == ch;
		}
	}
	return false;
}

static void ColouriseCppDoc(unsigned int startPos, int length, int initStyle, WordList *keywordlists[],
                            Accessor &styler, bool caseSensitive) {

	WordList &keywords = *keywordlists[0];
	WordList &keywords2 = *keywordlists[1];
	WordList &keywords3 = *keywordlists[2];
	WordList &keywords4 = *keywordlists[3];

	// property styling.within.preprocessor
	//	For C++ code, determines whether all preprocessor code is styled in the preprocessor style (0, the default)
	//	or only from the initial # to the end of the command word(1).
	bool stylingWithinPreprocessor = styler.GetPropertyInt("styling.within.preprocessor") != 0;

	CharacterSet setOKBeforeRE(CharacterSet::setNone, "([{=,:;!%^&*|?~+-");
	CharacterSet setCouldBePostOp(CharacterSet::setNone, "+-");

	CharacterSet setDoxygen(CharacterSet::setAlpha, "$@\\&<>#{}[]");

	CharacterSet setWordStart(CharacterSet::setAlpha, "_", 0x80, true);
	CharacterSet setWord(CharacterSet::setAlphaNum, "._", 0x80, true);

	// property lexer.cpp.allow.dollars
	//	Set to 0 to disallow the '$' character in identifiers with the cpp lexer.
	if (styler.GetPropertyInt("lexer.cpp.allow.dollars", 1) != 0) {
		setWordStart.Add('$');
		setWord.Add('$');
	}

	int chPrevNonWhite = ' ';
	int visibleChars = 0;
	bool lastWordWasUUID = false;
	int styleBeforeDCKeyword = SCE_C_DEFAULT;
	bool continuationLine = false;
	bool isIncludePreprocessor = false;

	if (initStyle == SCE_C_PREPROCESSOR) {
		// Set continuationLine if last character of previous line is '\'
		int lineCurrent = styler.GetLine(startPos);
		if (lineCurrent > 0) {
			int chBack = styler.SafeGetCharAt(startPos-1, 0);
			int chBack2 = styler.SafeGetCharAt(startPos-2, 0);
			int lineEndChar = '!';
			if (chBack2 == '\r' && chBack == '\n') {
				lineEndChar = styler.SafeGetCharAt(startPos-3, 0);
			} else if (chBack == '\n' || chBack == '\r') {
				lineEndChar = chBack2;
			}
			continuationLine = lineEndChar == '\\';
		}
	}

	// look back to set chPrevNonWhite properly for better regex colouring
	if (startPos > 0) {
		int back = startPos;
		while (--back && IsSpaceEquiv(styler.StyleAt(back)))
			;
		if (styler.StyleAt(back) == SCE_C_OPERATOR) {
			chPrevNonWhite = styler.SafeGetCharAt(back);
		}
	}

	StyleContext sc(startPos, length, initStyle, styler);

	for (; sc.More(); sc.Forward()) {

		if (sc.atLineStart) {
			if (sc.state == SCE_C_STRING) {
				// Prevent SCE_C_STRINGEOL from leaking back to previous line which
				// ends with a line continuation by locking in the state upto this position.
				sc.SetState(SCE_C_STRING);
			}
			// Reset states to begining of colourise so no surprises
			// if different sets of lines lexed.
			visibleChars = 0;
			lastWordWasUUID = false;
			isIncludePreprocessor = false;
		}

		// Handle line continuation generically.
		if (sc.ch == '\\') {
			if (sc.chNext == '\n' || sc.chNext == '\r') {
				sc.Forward();
				if (sc.ch == '\r' && sc.chNext == '\n') {
					sc.Forward();
				}
				continuationLine = true;
				continue;
			}
		}

		// Determine if the current state should terminate.
		switch (sc.state) {
			case SCE_C_OPERATOR:
				sc.SetState(SCE_C_DEFAULT);
				break;
			case SCE_C_NUMBER:
				// We accept almost anything because of hex. and number suffixes
				if (!setWord.Contains(sc.ch)) {
					sc.SetState(SCE_C_DEFAULT);
				}
				break;
			case SCE_C_IDENTIFIER:
				if (!setWord.Contains(sc.ch) || (sc.ch == '.')) {
					char s[1000];
					if (caseSensitive) {
						sc.GetCurrent(s, sizeof(s));
					} else {
						sc.GetCurrentLowered(s, sizeof(s));
					}
					if (keywords.InList(s)) {
						lastWordWasUUID = strcmp(s, "uuid") == 0;
						sc.ChangeState(SCE_C_WORD);
					} else if (keywords2.InList(s)) {
						sc.ChangeState(SCE_C_WORD2);
					} else if (keywords4.InList(s)) {
						sc.ChangeState(SCE_C_GLOBALCLASS);
					}
					sc.SetState(SCE_C_DEFAULT);
				}
				break;
			case SCE_C_PREPROCESSOR:
				if (sc.atLineStart && !continuationLine) {
					sc.SetState(SCE_C_DEFAULT);
				} else if (stylingWithinPreprocessor) {
					if (IsASpace(sc.ch)) {
						sc.SetState(SCE_C_DEFAULT);
					}
				} else {
					if (sc.Match('/', '*') || sc.Match('/', '/')) {
						sc.SetState(SCE_C_DEFAULT);
					}
				}
				break;
			case SCE_C_COMMENT:
				if (sc.Match('*', '/')) {
					sc.Forward();
					sc.ForwardSetState(SCE_C_DEFAULT);
				}
				break;
			case SCE_C_COMMENTDOC:
				if (sc.Match('*', '/')) {
					sc.Forward();
					sc.ForwardSetState(SCE_C_DEFAULT);
				} else if (sc.ch == '@' || sc.ch == '\\') { // JavaDoc and Doxygen support
					// Verify that we have the conditions to mark a comment-doc-keyword
					if ((IsASpace(sc.chPrev) || sc.chPrev == '*') && (!IsASpace(sc.chNext))) {
						styleBeforeDCKeyword = SCE_C_COMMENTDOC;
						sc.SetState(SCE_C_COMMENTDOCKEYWORD);
					}
				}
				break;
			case SCE_C_COMMENTLINE:
				if (sc.atLineStart) {
					sc.SetState(SCE_C_DEFAULT);
				}
				break;
			case SCE_C_COMMENTLINEDOC:
				if (sc.atLineStart) {
					sc.SetState(SCE_C_DEFAULT);
				} else if (sc.ch == '@' || sc.ch == '\\') { // JavaDoc and Doxygen support
					// Verify that we have the conditions to mark a comment-doc-keyword
					if ((IsASpace(sc.chPrev) || sc.chPrev == '/' || sc.chPrev == '!') && (!IsASpace(sc.chNext))) {
						styleBeforeDCKeyword = SCE_C_COMMENTLINEDOC;
						sc.SetState(SCE_C_COMMENTDOCKEYWORD);
					}
				}
				break;
			case SCE_C_COMMENTDOCKEYWORD:
				if ((styleB