// Scintilla source code edit control
/** @file LexPython.cxx
 ** Lexer for Python.
 **/
// Copyright 1998-2002 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"

enum kwType { kwOther, kwClass, kwDef, kwImport };

static bool IsPyComment(Accessor &styler, int pos, int len) {
	return len > 0 && styler[pos] == '#';
}

static bool IsPyStringStart(int ch, int chNext, int chNext2) {
	if (ch == '\'' || ch == '"')
		return true;
	if (ch == 'u' || ch == 'U') {
		if (chNext == '"' || chNext == '\'')
			return true;
		if ((chNext == 'r' || chNext == 'R') && (chNext2 == '"' || chNext2 == '\''))
			return true;
	}
	if ((ch == 'r' || ch == 'R') && (chNext == '"' || chNext == '\''))
		return true;

	return false;
}

/* Return the state to use for the string starting at i; *nextIndex will be set to the first index following the quote(s) */
static int GetPyStringState(Accessor &styler, int i, unsigned int *nextIndex) {
	char ch = styler.SafeGetCharAt(i);
	char chNext = styler.SafeGetCharAt(i + 1);

	// Advance beyond r, u, or ur prefix, but bail if there are any unexpected chars
	if (ch == 'r' || ch == 'R') {
		i++;
		ch = styler.SafeGetCharAt(i);
		chNext = styler.SafeGetCharAt(i + 1);
	} else if (ch == 'u' || ch == 'U') {
		if (chNext == 'r' || chNext == 'R')
			i += 2;
		else
			i += 1;
		ch = styler.SafeGetCharAt(i);
		chNext = styler.SafeGetCharAt(i + 1);
	}

	if (ch != '"' && ch != '\'') {
		*nextIndex = i + 1;
		return SCE_P_DEFAULT;
	}

	if (ch == chNext && ch == styler.SafeGetCharAt(i + 2)) {
		*nextIndex = i + 3;

		if (ch == '"')
			return SCE_P_TRIPLEDOUBLE;
		else
			return SCE_P_TRIPLE;
	} else {
		*nextIndex = i + 1;

		if (ch == '"')
			return SCE_P_STRING;
		else
			return SCE_P_CHARACTER;
	}
}

static inline bool IsAWordChar(int ch) {
	return (ch < 0x80) && (isalnum(ch) || ch == '.' || ch == '_');
}

static inline bool IsAWordStart(int ch) {
	return (ch < 0x80) && (isalnum(ch) || ch == '_');
}

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

	int endPos = startPos + length;

	// Backtrack to previous line in case need to fix its tab whinging
	int lineCurrent = styler.GetLine(startPos);
	if (startPos > 0) {
		if (lineCurrent > 0) {
			lineCurrent--;
			startPos = styler.LineStart(lineCurrent);
			if (startPos == 0)
				initStyle = SCE_P_DEFAULT;
			else
				initStyle = styler.StyleAt(startPos - 1);
		}
	}

	WordList &keywords = *keywordlists[0];

	const int whingeLevel = styler.GetPropertyInt("tab.timmy.whinge.level");

	initStyle = initStyle & 31;
	if (initStyle == SCE_P_STRINGEOL) {
		initStyle = SCE_P_DEFAULT;
	}

	kwType kwLast = kwOther;
	int spaceFlags = 0;
	styler.IndentAmount(lineCurrent, &spaceFlags, IsPyComment);
	bool hexadecimal = false;

	// Python uses a different mask because bad indentation is marked by oring with 32
	StyleContext sc(startPos, endPos - startPos, initStyle, styler, 0x7f);

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

		if (sc.atLineStart) {
			const char chBad = static_cast<char>(64);
			const char chGood = static_cast<char>(0);
			char chFlags = chGood;
			if (whingeLevel == 1) {
				chFlags = (spaceFlags & wsInconsistent) ? chBad : chGood;
			} else if (whingeLevel == 2) {
				chFlags = (spaceFlags & wsSpaceTab) ? chBad : chGood;
			} else if (whingeLevel == 3) {
				chFlags = (spaceFlags & wsSpace) ? chBad : chGood;
			} else if (whingeLevel == 4) {
				chFlags = (spaceFlags & wsTab) ? chBad : chGood;
			}
			sc.SetState(sc.state);
			styler.SetFlags(chFlags, static_cast<char>(sc.state));
		}

		if (sc.atLineEnd) {
			if ((sc.state == SCE_P_DEFAULT) ||
			        (sc.state == SCE_P_TRIPLE) ||
			        (sc.state == SCE_P_TRIPLEDOUBLE)) {
				// Perform colourisation of white space and triple quoted strings at end of each line to allow
				// tab marking to work inside white space and triple quoted strings
				sc.SetState(sc.state);
			}
			lineCurrent++;
			styler.IndentAmount(lineCurrent, &spaceFlags, IsPyComment);
			if ((sc.state == SCE_P_STRING) || (sc.state == SCE_P_CHARACTER)) {
				sc.ChangeState(SCE_P_STRINGEOL);
				sc.ForwardSetState(SCE_P_DEFAULT);
			}
			if (!sc.More())
				break;
		}

		bool needEOLCheck = false;

		// Check for a state end
		if (sc.state == SCE_P_OPERATOR) {
			kwLast = kwOther;
			sc.SetState(SCE_P_DEFAULT);
		} else if (sc.state == SCE_P_NUMBER) {
			if (!IsAWordChar(sc.ch) &&
			        !(!hexadecimal && ((sc.ch == '+' || sc.ch == '-') && (sc.chPrev == 'e' || sc.chPrev == 'E')))) {
				sc.SetState(SCE_P_DEFAULT);
			}
		} else if (sc.state == SCE_P_IDENTIFIER) {
			if ((sc.ch == '.') || (!IsAWordChar(sc.ch))) {
				char s[100];
				sc.GetCurrent(s, sizeof(s));
				int style = SCE_P_IDENTIFIER;
				if ((kwLast == kwImport) && (strcmp(s, "as") == 0)) {
					style = SCE_P_WORD;
				} else if (keywords.InList(s)) {
					style = SCE_P_WORD;
				} else if (kwLast == kwClass) {
					style = SCE_P_CLASSNAME;
				} else if (kwLast == kwDef) {
					style = SCE_P_DEFNAME;
				}
				sc.ChangeState(style);
				sc.SetState(SCE_P_DEFAULT);
				if (style == SCE_P_WORD) {
					if (0 == strcmp(s, "class"))
						kwLast = kwClass;
					else if (0 == strcmp(s, "def"))
						kwLast = kwDef;
					else if (0 == strcmp(s, "import"))
						kwLast = kwImport;
					else
						kwLast = kwOther;
				} else if (style == SCE_P_CLASSNAME) {
					kwLast = kwOther;
				} else if (style == SCE_P_DEFNAME) {
					kwLast = kwOther;
				}
			}
		} else if ((sc.state == SCE_P_COMMENTLINE) || (sc.state == SCE_P_COMMENTBLOCK)) {
			if (sc.ch == '\r' || sc.ch == '\n') {
				sc.SetState(SCE_P_DEFAULT);
			}
		} else if ((sc.state == SCE_P_STRING) || (sc.state == SCE_P_CHARACTER)) {
			if (sc.ch == '\\') {
				if ((sc.chNext == '\r') && (sc.GetRelative(2) == '\n')) {
					sc.Forward();
				}
				sc.Forward();
			} else if ((sc.state == SCE_P_STRING) && (sc.ch == '\"')) {
				sc.ForwardSetState(SCE_P_DEFAULT);
				needEOLCheck = true;
			} else if ((sc.state == SCE_P_CHARACTER) && (sc.ch == '\'')) {
				sc.ForwardSetState(SCE_P_DEFAULT);
				needEOLCheck = true;
			}
		} else if (sc.state == SCE_P_TRIPLE) {
			if (sc.ch == '\\') {
				sc.Forward();
			} else if (sc.Match("\'\'\'")) {
				sc.Forward();
				sc.Forward();
				sc.ForwardSetState(SCE_P_DEFAULT);
				needEOLCheck = true;
			}
		} else if (sc.state == SCE_P_TRIPLEDOUBLE) {
			if (sc.ch == '\\') {
				sc.Forward();
			} else if (sc.Match("\"\"\"")) {
				sc.Forward();
				sc.Forward();
				sc.ForwardSetState(SCE_P_DEFAULT);
				needEOLCheck = true;
			}
		}

		// State exit code may have moved on to end of line
		if (needEOLCheck && sc.atLineEnd) {
			lineCurrent++;
			styler.IndentAmount(lineCurrent, &spaceFlags, IsPyComment);
			if (!sc.More())
				break;
		}

		// Check for a new state starting character
		if (sc.state == SCE_P_DEFAULT) {
			if (IsADigit(sc.ch) || (sc.ch == '.' && IsADigit(sc.chNext))) {
				if (sc.ch == '0' && (sc.chNext == 'x' || sc.chNext == 'X')) {
					hexadecimal = true;
				} else {
					hexadecimal = false;
				}
				sc.SetState(SCE_P_NUMBER);
			} else if (isascii(sc.ch) && isoperator(static_cast<char>(sc.ch)) || sc.ch == '`') {
				sc.SetState(SCE_P_OPERATOR);
			} else if (sc.ch == '#') {
				sc.SetState(sc.chNext == '#' ? SCE_P_COMMENTBLOCK : SCE_P_COMMENTLINE);
			} else if (IsPyStringStart(sc.ch, sc.chNext, sc.GetRelative(2))) {
				unsigned int nextIndex = 0;
				sc.SetState(GetPyStringState(styler, sc.currentPos, &nextIndex));
				while (nextIndex > (sc.currentPos + 1) && sc.More()) {
					sc.Forward();
				}
			} else if (IsAWordStart(sc.ch)) {
				sc.SetState(SCE_P_IDENTIFIER);
			}
		}
	}
	sc.Complete();
}

static bool IsCommentLine(int line, Accessor &styler) {
	int pos = styler.LineStart(line);
	int eol_pos = styler.LineStart(line + 1) - 1;
	for (int i = pos; i < eol_pos; i++) {
		chHTTP/1.1 200 OK
Connection: keep-alive
Connection: keep-alive
Content-Disposition: inline; filename="LexPython.cxx"
Content-Disposition: inline; filename="LexPython.cxx"
Content-Length: 14264
Content-Length: 14264
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
Date: Sat, 18 Oct 2025 22:06:44 UTC
ETag: "e13c6220d9c40be7efed0ef868639367a557ea5d"
ETag: "e13c6220d9c40be7efed0ef868639367a557ea5d"
Expires: Tue, 16 Oct 2035 22:06:44 GMT
Expires: Tue, 16 Oct 2035 22:06:44 GMT
Last-Modified: Sat, 18 Oct 2025 22:06:44 GMT
Last-Modified: Sat, 18 Oct 2025 22:06:44 GMT
Server: OpenBSD httpd
Server: OpenBSD httpd
X-Content-Type-Options: nosniff
X-Content-Type-Options: nosniff

// Scintilla source code edit control
/** @file LexPython.cxx
 ** Lexer for Python.
 **/
// Copyright 1998-2002 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"

enum kwType { kwOther, kwClass, kwDef, kwImport };

static bool IsPyComment(Accessor &styler, int pos, int len) {
	return len > 0 && styler[pos] == '#';
}

static bool IsPyStringStart(int ch, int chNext, int chNext2) {
	if (ch == '\'' || ch == '"')
		return true;
	if (ch == 'u' || ch == 'U') {
		if (chNext == '"' || chNext == '\'')
			return true;
		if ((chNext == 'r' || chNext == 'R') && (chNext2 == '"' || chNext2 == '\''))
			return true;
	}
	if ((ch == 'r' || ch == 'R') && (chNext == '"' || chNext == '\''))
		return true;

	return false;
}

/* Return the state to use for the string starting at i; *nextIndex will be set to the first index following the quote(s) */
static int GetPyStringState(Accessor &styler, int i, unsigned int *nextIndex) {
	char ch = styler.SafeGetCharAt(i);
	char chNext = styler.SafeGetCharAt(i + 1);

	// Advance beyond r, u, or ur prefix, but bail if there are any unexpected chars
	if (ch == 'r' || ch == 'R') {
		i++;
		ch = styler.SafeGetCharAt(i);
		chNext = styler.SafeGetCharAt(i + 1);
	} else if (ch == 'u' || ch == 'U') {
		if (chNext == 'r' || chNext == 'R')
			i += 2;
		else
			i += 1;
		ch = styler.SafeGetCharAt(i);
		chNext = styler.SafeGetCharAt(i + 1);
	}

	if (ch != '"' && ch != '\'') {
		*nextIndex = i + 1;
		return SCE_P_DEFAULT;
	}

	if (ch == chNext && ch == styler.SafeGetCharAt(i + 2)) {
		*nextIndex = i + 3;

		if (ch == '"')
			return SCE_P_TRIPLEDOUBLE;
		else
			return SCE_P_TRIPLE;
	} else {
		*nextIndex = i + 1;

		if (ch == '"')
			return SCE_P_STRING;
		else
			return SCE_P_CHARACTER;
	}
}

static inline bool IsAWordChar(int ch) {
	return (ch < 0x80) && (isalnum(ch) || ch == '.' || ch == '_');
}

static inline bool IsAWordStart(int ch) {
	return (ch < 0x80) && (isalnum(ch) || ch == '_');
}

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

	int endPos = startPos + length;

	// Backtrack to previous line in case need to fix its tab whinging
	int lineCurrent = styler.GetLine(startPos);
	if (startPos > 0) {
		if (lineCurrent > 0) {
			lineCurrent--;
			startPos = styler.LineStart(lineCurrent);
			if (startPos == 0)
				initStyle = SCE_P_DEFAULT;
			else
				initStyle = styler.StyleAt(startPos - 1);
		}
	}

	WordList &keywords = *keywordlists[0];

	const int whingeLevel = styler.GetPropertyInt("tab.timmy.whinge.level");

	initStyle = initStyle & 31;
	if (initStyle == SCE_P_STRINGEOL) {
		initStyle = SCE_P_DEFAULT;
	}

	kwType kwLast = kwOther;
	int spaceFlags = 0;
	styler.IndentAmount(lineCurrent, &spaceFlags, IsPyComment);
	bool hexadecimal = false;

	// Python uses a different mask because bad indentation is marked by oring with 32
	StyleContext sc(startPos, endPos - startPos, initStyle, styler, 0x7f);

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

		if (sc.atLineStart) {
			const char chBad = static_cast<char>(64);
			const char chGood = static_cast<char>(0);
			char chFlags = chGood;
			if (whingeLevel == 1) {
				chFlags = (spaceFlags & wsInconsistent) ? chBad : chGood;
			} else if (whingeLevel == 2) {
				chFlags = (spaceFlags & wsSpaceTab) ? chBad : chGood;
			} else if (whingeLevel == 3) {
				chFlags = (spaceFlags & wsSpace) ? chBad : chGood;
			} else if (whingeLevel == 4) {
				chFlags = (spaceFlags & wsTab) ? chBad : chGood;
			}
			sc.SetState(sc.state);
			styler.SetFlags(chFlags, static_cast<char>(sc.state));
		}

		if (sc.atLineEnd) {
			if ((sc.state == SCE_P_DEFAULT) ||
			        (sc.state == SCE_P_TRIPLE) ||
			        (sc.state == SCE_P_TRIPLEDOUBLE)) {
				// Perform colourisation of white space and triple quoted strings at end of each line to allow
				// tab marking to work inside white space and triple quoted strings
				sc.SetState(sc.state);
			}
			lineCurrent++;
			styler.IndentAmount(lineCurrent, &spaceFlags, IsPyComment);
			if ((sc.state == SCE_P_STRING) || (sc.state == SCE_P_CHARACTER)) {
				sc.ChangeState(SCE_P_STRINGEOL);
				sc.ForwardSetState(SCE_P_DEFAULT);
			}
			if (!sc.More())
				break;
		}

		bool needEOLCheck = false;

		// Check for a state end
		if (sc.state == SCE_P_OPERATOR) {
			kwLast = kwOther;
			sc.SetState(SCE_P_DEFAULT);
		} else if (sc.state == SCE_P_NUMBER) {
			if (!IsAWordChar(sc.ch) &&
			        !(!hexadecimal && ((sc.ch == '+' || sc.ch == '-') && (sc.chPrev == 'e' || sc.chPrev == 'E')))) {
				sc.SetState(SCE_P_DEFAULT);
			}
		} else if (sc.state == SCE_P_IDENTIFIER) {
			if ((sc.ch == '.') || (!IsAWordChar(sc.ch))) {
				char s[100];
				sc.GetCurrent(s, sizeof(s));
				int style = SCE_P_IDENTIFIER;
				if ((kwLast == kwImport) && (strcmp(s, "as") == 0)) {
					style = SCE_P_WORD;
				} else if (keywords.InList(s)) {
					style = SCE_P_WORD;
				} else if (kwLast =