Lexers added for Objective Caml, PureBasic and BlitzBasic.

9 files changed, 770 insertions, 12 deletions

diff --git a/gtk/makefile b/gtk/makefile
index 774e6730e..dc66a30e2 100644
--- a/gtk/makefile
+++ b/gtk/makefile
@@ -64,12 +64,13 @@ endif
 #**LEXOBJS=\\\n\(\*.o \)
 LEXOBJS=\
 LexAda.o LexAPDL.o LexAsm.o LexAsn1.o LexAU3.o LexAVE.o LexBaan.o LexBash.o \
-LexBullant.o LexCLW.o LexConf.o LexCPP.o LexCrontab.o LexCSS.o LexEiffel.o \
-LexErlang.o LexEScript.o LexForth.o LexFortran.o LexGui4Cli.o LexHTML.o \
-LexKix.o LexLisp.o LexLout.o LexLua.o LexMatlab.o LexMetapost.o LexMMIXAL.o \
-LexMPT.o LexMSSQL.o LexNsis.o LexOthers.o LexPascal.o LexPB.o LexPerl.o \
-LexPOV.o LexPS.o LexPython.o LexRuby.o LexScriptol.o LexSpecman.o LexSQL.o \
-LexTeX.o LexVB.o LexVerilog.o LexVHDL.o LexYAML.o
+LexBasic.o LexBullant.o LexCaml.o LexCLW.o LexConf.o LexCPP.o LexCrontab.o \
+LexCSS.o LexEiffel.o LexErlang.o LexEScript.o LexForth.o LexFortran.o \
+LexGui4Cli.o LexHTML.o LexKix.o LexLisp.o LexLout.o LexLua.o LexMatlab.o \
+LexMetapost.o LexMMIXAL.o LexMPT.o LexMSSQL.o LexNsis.o LexOthers.o \
+LexPascal.o LexPB.o LexPerl.o LexPOV.o LexPS.o LexPython.o LexRuby.o \
+LexScriptol.o LexSpecman.o LexSQL.o LexTeX.o LexVB.o LexVerilog.o LexVHDL.o \
+LexYAML.o
 #--Autogenerated -- end of automatically generated section
 
 all: $(COMPLIB)
diff --git a/gtk/scintilla.mak b/gtk/scintilla.mak
index a1a536827..8274c04bf 100644
--- a/gtk/scintilla.mak
+++ b/gtk/scintilla.mak
@@ -147,7 +147,9 @@ LEXOBJS=\
 	$(DIR_O)\LexAVE.obj \
 	$(DIR_O)\LexBaan.obj \
 	$(DIR_O)\LexBash.obj \
+	$(DIR_O)\LexBasic.obj \
 	$(DIR_O)\LexBullant.obj \
+	$(DIR_O)\LexCaml.obj \
 	$(DIR_O)\LexCLW.obj \
 	$(DIR_O)\LexConf.obj \
 	$(DIR_O)\LexCPP.obj \
@@ -318,8 +320,12 @@ $(DIR_O)\LexBaan.obj: ..\src\LexBaan.cxx $(LEX_HEADERS)
 
 $(DIR_O)\LexBash.obj: ..\src\LexBash.cxx $(LEX_HEADERS)
 
+$(DIR_O)\LexBasic.obj: ..\src\LexBasic.cxx $(LEX_HEADERS)
+
 $(DIR_O)\LexBullant.obj: ..\src\LexBullant.cxx $(LEX_HEADERS)
 
+$(DIR_O)\LexCaml.obj: ..\src\LexCaml.cxx $(LEX_HEADERS)
+
 $(DIR_O)\LexCLW.obj: ..\src\LexCLW.cxx $(LEX_HEADERS)
 
 $(DIR_O)\LexConf.obj: ..\src\LexConf.cxx $(LEX_HEADERS)
diff --git a/include/SciLexer.h b/include/SciLexer.h
index 4db005a84..2911e450f 100644
--- a/include/SciLexer.h
+++ b/include/SciLexer.h
@@ -79,6 +79,9 @@
 #define SCLEX_BASH 62
 #define SCLEX_ASN1 63
 #define SCLEX_VHDL 64
+#define SCLEX_CAML 65
+#define SCLEX_BLITZBASIC 66
+#define SCLEX_PUREBASIC 67
 #define SCLEX_AUTOMATIC 1000
 #define SCE_P_DEFAULT 0
 #define SCE_P_COMMENTLINE 1
@@ -270,6 +273,10 @@
 #define SCE_B_KEYWORD4 12
 #define SCE_B_CONSTANT 13
 #define SCE_B_ASM 14
+#define SCE_B_LABEL 15
+#define SCE_B_ERROR 16
+#define SCE_B_HEXNUMBER 17
+#define SCE_B_BINNUMBER 18
 #define SCE_PROPS_DEFAULT 0
 #define SCE_PROPS_COMMENT 1
 #define SCE_PROPS_SECTION 2
@@ -785,6 +792,20 @@
 #define SCE_VHDL_STDPACKAGE 12
 #define SCE_VHDL_STDTYPE 13
 #define SCE_VHDL_USERWORD 14
+#define SCE_CAML_DEFAULT 0
+#define SCE_CAML_IDENTIFIER 1
+#define SCE_CAML_TAGNAME 2
+#define SCE_CAML_KEYWORD 3
+#define SCE_CAML_KEYWORD2 4
+#define SCE_CAML_LINENUM 5
+#define SCE_CAML_OPERATOR 6
+#define SCE_CAML_NUMBER 7
+#define SCE_CAML_CHAR 8
+#define SCE_CAML_STRING 9
+#define SCE_CAML_COMMENT 10
+#define SCE_CAML_COMMENT1 11
+#define SCE_CAML_COMMENT2 12
+#define SCE_CAML_COMMENT3 13
 //--Autogenerated -- end of section automatically generated from Scintilla.iface
 
 #endif
diff --git a/src/KeyWords.cxx b/src/KeyWords.cxx
index 66e82094c..858eb54a3 100644
--- a/src/KeyWords.cxx
+++ b/src/KeyWords.cxx
@@ -137,7 +137,10 @@ int Scintilla_LinkLexers() {
 	LINK_LEXER(lmAVE);
 	LINK_LEXER(lmBaan);
 	LINK_LEXER(lmBash);
+	LINK_LEXER(lmBlitzBasic);
+	LINK_LEXER(lmPureBasic);
 	LINK_LEXER(lmBullant);
+	LINK_LEXER(lmCaml);
 	LINK_LEXER(lmClw);
 	LINK_LEXER(lmClwNoCase);
 	LINK_LEXER(lmConf);
diff --git a/src/LexBasic.cxx b/src/LexBasic.cxx
new file mode 100644
index 000000000..b8f83f171
--- /dev/null
+++ b/src/LexBasic.cxx
@@ -0,0 +1,325 @@
+// Scintilla source code edit control
+/** @file LexBB.cxx
+ ** Lexer for BlitzBasic.
+ **/
+// Copyright 1998-2003 by Neil Hodgson <neilh@scintilla.org>
+// The License.txt file describes the conditions under which this software may be distributed.
+
+// This tries to be a unified Lexer/Folder for all the BlitzBasic/BlitzMax/PurBasic basics
+// and derivatives. Once they diverge enough, might want to split it into multiple
+// lexers for more code clearity.
+//
+// Mail me (elias <at> users <dot> sf <dot> net) for any bugs.
+
+// Folding only works for simple things like functions or types.
+
+// You may want to have a look at my ctags lexer as well, if you additionally to coloring
+// and folding need to extract things like label tags in your editor.
+
+#include <stdlib.h>
+#include <string.h>
+#include <stdio.h>
+#include <ctype.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"
+
+/* Bits:
+ * 1  - whitespace
+ * 2  - operator
+ * 4  - identifier
+ * 8  - decimal digit
+ * 16 - hex digit
+ * 32 - bin digit
+ */
+static int character_classification[128] =
+{
+    0,  0,  0,  0,  0,  0,  0,  0,  0,  1,  1,  0,  0,  1,  0,  0,
+    0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,
+    1,  2,  0,  2,  2,  2,  2,  2,  2,  2,  2,  2,  2,  2,  10, 2,
+    60, 60, 28, 28, 28, 28, 28, 28, 28, 28, 2,  2,  2,  2,  2,  2,
+    2,  20, 20, 20, 20, 20, 20, 4,  4,  4,  4,  4,  4,  4,  4,  4,
+    4,  4,  4,  4,  4,  4,  4,  4,  4,  4,  4,  2,  2,  2,  2,  4,
+    2,  20, 20, 20, 20, 20, 20, 4,  4,  4,  4,  4,  4,  4,  4,  4,
+    4,  4,  4,  4,  4,  4,  4,  4,  4,  4,  4,  2,  2,  2,  2,  0
+};
+
+static bool IsSpace(int c) {
+	return c < 128 && (character_classification[c] & 1);
+}
+
+static bool IsOperator(int c) {
+	return c < 128 && (character_classification[c] & 2);
+}
+
+static bool IsIdentifier(int c) {
+	return c < 128 && (character_classification[c] & 4);
+}
+
+static bool IsDigit(int c) {
+	return c < 128 && (character_classification[c] & 8);
+}
+
+static bool IsHexDigit(int c) {
+	return c < 128 && (character_classification[c] & 16);
+}
+
+static bool IsBinDigit(int c) {
+	return c < 128 && (character_classification[c] & 32);
+}
+
+static int LowerCase(int c)
+{
+	if (c >= 'A' && c <= 'Z')
+		return 'a' + c - 'A';
+	return c;
+}
+
+static void ColouriseBasicDoc(unsigned int startPos, int length, int initStyle,
+                           WordList *keywordlists[], Accessor &styler) {
+	bool wasfirst = true, isfirst = true; // true if first token in a line
+	styler.StartAt(startPos);
+
+	StyleContext sc(startPos, length, initStyle, styler);
+
+	// Can't use sc.More() here else we miss the last character
+	for (; ; sc.Forward()) {
+		if (sc.state == SCE_B_IDENTIFIER) {
+			if (!IsIdentifier(sc.ch)) {
+				// Labels
+				if (wasfirst && sc.Match(':')) {
+					sc.ChangeState(SCE_B_LABEL);
+					sc.ForwardSetState(SCE_B_DEFAULT);
+				} else {
+					char s[100];
+					int kstates[4] = {
+						SCE_B_KEYWORD,
+						SCE_B_KEYWORD2,
+						SCE_B_KEYWORD3,
+						SCE_B_KEYWORD4,
+					};
+					sc.GetCurrentLowered(s, sizeof(s));
+					for (int i = 0; i < 4; i++) {
+						if (keywordlists[i]->InList(s)) {
+							sc.ChangeState(kstates[i]);
+						}
+					}
+					// Types, must set them as operator else they will be
+					// matched as number/constant
+					if (sc.Match('.') || sc.Match('$') || sc.Match('%') ||
+						sc.Match('#')) {
+						sc.SetState(SCE_B_OPERATOR);
+					} else {
+						sc.SetState(SCE_B_DEFAULT);
+					}
+				}
+			}
+		} else if (sc.state == SCE_B_OPERATOR) {
+			if (!IsOperator(sc.ch) || sc.Match('#'))
+				sc.SetState(SCE_B_DEFAULT);
+		} else if (sc.state == SCE_B_LABEL) {
+			if (!IsIdentifier(sc.ch))
+				sc.SetState(SCE_B_DEFAULT);
+		} else if (sc.state == SCE_B_CONSTANT) {
+			if (!IsIdentifier(sc.ch))
+				sc.SetState(SCE_B_DEFAULT);
+		} else if (sc.state == SCE_B_NUMBER) {
+			if (!IsDigit(sc.ch))
+				sc.SetState(SCE_B_DEFAULT);
+		} else if (sc.state == SCE_B_HEXNUMBER) {
+			if (!IsHexDigit(sc.ch))
+				sc.SetState(SCE_B_DEFAULT);
+		} else if (sc.state == SCE_B_BINNUMBER) {
+			if (!IsBinDigit(sc.ch))
+				sc.SetState(SCE_B_DEFAULT);
+		} else if (sc.state == SCE_B_STRING) {
+			if (sc.ch == '"') {
+				sc.ForwardSetState(SCE_B_DEFAULT);
+			}
+			if (sc.atLineEnd) {
+				sc.ChangeState(SCE_B_ERROR);
+				sc.SetState(SCE_B_DEFAULT);
+			}
+		} else if (sc.state == SCE_B_COMMENT) {
+			if (sc.atLineEnd) {
+				sc.SetState(SCE_B_DEFAULT);
+			}
+		}
+
+		if (sc.atLineStart)
+			isfirst = true;
+
+		if (sc.state == SCE_B_DEFAULT || sc.state == SCE_B_ERROR) {
+			if (isfirst && sc.Match('.')) {
+				sc.SetState(SCE_B_LABEL);
+			} else if (sc.Match(';')) {
+				sc.SetState(SCE_B_COMMENT);
+			} else if (sc.Match('"')) {
+				sc.SetState(SCE_B_STRING);
+			} else if (IsDigit(sc.ch)) {
+				sc.SetState(SCE_B_NUMBER);
+			} else if (sc.Match('$')) {
+				sc.SetState(SCE_B_HEXNUMBER);
+			} else if (sc.Match('%')) {
+				sc.SetState(SCE_B_BINNUMBER);
+			} else if (sc.Match('#')) {
+				sc.SetState(SCE_B_CONSTANT);
+			} else if (IsOperator(sc.ch)) {
+				sc.SetState(SCE_B_OPERATOR);
+			} else if (IsIdentifier(sc.ch)) {
+				wasfirst = isfirst;
+				sc.SetState(SCE_B_IDENTIFIER);
+			} else if (!IsSpace(sc.ch)) {
+				sc.SetState(SCE_B_ERROR);
+			}
+		}
+
+		if (!IsSpace(sc.ch))
+			isfirst = false;
+
+		if (!sc.More())
+			break;
+	}
+	sc.Complete();
+}
+
+static int CheckBlitzFoldPoint(char const *token, int &level) {
+	if (!strcmp(token, "function") ||
+		!strcmp(token, "type")) {
+		level |= SC_FOLDLEVELHEADERFLAG;
+		return 1;
+	}
+	if (!strcmp(token, "end function") ||
+		!strcmp(token, "end type")) {
+		return -1;
+	}
+	return 0;
+}
+
+static int CheckPureFoldPoint(char const *token, int &level) {
+	if (!strcmp(token, "procedure") ||
+		!strcmp(token, "enumeration") ||
+		!strcmp(token, "interface") ||
+		!strcmp(token, "structure")) {
+		level |= SC_FOLDLEVELHEADERFLAG;
+		return 1;
+	}
+	if (!strcmp(token, "endprocedure") ||
+		!strcmp(token, "endenumeration") ||
+		!strcmp(token, "endinterface") ||
+		!strcmp(token, "endstructure")) {
+		return -1;
+	}
+	return 0;
+}
+
+static void FoldBasicDoc(unsigned int startPos, int length,
+	Accessor &styler, int (*CheckFoldPoint)(char const *, int &)) {
+	int line = styler.GetLine(startPos);
+	int level = styler.LevelAt(line);
+	int go = 0, done = 0;
+	int endPos = startPos + length;
+	char word[256];
+	int wordlen = 0;
+	int i;
+        bool foldCompact = styler.GetPropertyInt("fold.compact", 1) != 0;
+	// Scan for tokens at the start of the line (they may include
+	// whitespace, for tokens like "End Function"
+	for (i = startPos; i < endPos; i++) {
+		int c = styler.SafeGetCharAt(i);
+		if (!done && !go) {
+			if (wordlen) { // are we scanning a token already?
+				word[wordlen] = static_cast<char>(LowerCase(c));
+				if (!IsIdentifier(c)) { // done with token
+					word[wordlen] = '\0';
+					go = CheckFoldPoint(word, level);
+					if (!go) {
+						// Treat any whitespace as single blank, for
+						// things like "End   Function".
+						if (IsSpace(c) && IsIdentifier(word[wordlen - 1])) {
+							word[wordlen] = ' ';
+							if (wordlen < 255)
+								wordlen++;
+						}
+						else // done with this line
+							done = 1;
+					}
+				} else if (wordlen < 255) {
+					wordlen++;
+				}
+			} else { // start scanning at first non-whitespace character
+				if (!IsSpace(c)) {
+					if (IsIdentifier(c)) {
+						word[0] = static_cast<char>(LowerCase(c));
+						wordlen = 1;
+					} else // done with this line
+						done = 1;
+				}
+			}
+		}
+		if (c == '\n') { // line end
+			if (!done && wordlen == 0 && foldCompact) // line was only space
+				level |= SC_FOLDLEVELWHITEFLAG;
+			if (level != styler.LevelAt(line))
+				styler.SetLevel(line, level);
+			level += go;
+			line++;
+			// reset state
+			wordlen = 0;
+			level &= ~SC_FOLDLEVELHEADERFLAG;
+			level &= ~SC_FOLDLEVELWHITEFLAG;
+			go = 0;
+			done = 0;
+		}
+	}
+}
+
+static void ColouriseBlitzBasicDoc(unsigned int startPos, int length, int initStyle,
+                           WordList *keywordlists[], Accessor &styler) {
+	ColouriseBasicDoc(startPos, length, initStyle, keywordlists, styler);
+}
+
+static void ColourisePureBasicDoc(unsigned int startPos, int length, int initStyle,
+                           WordList *keywordlists[], Accessor &styler) {
+	ColouriseBasicDoc(startPos, length, initStyle, keywordlists, styler);
+}
+
+static void FoldBlitzBasicDoc(unsigned int startPos, int length, int,
+	WordList *[], Accessor &styler) {
+	FoldBasicDoc(startPos, length, styler, CheckBlitzFoldPoint);
+}
+
+static void FoldPureBasicDoc(unsigned int startPos, int length, int,
+	WordList *[], Accessor &styler) {
+	FoldBasicDoc(startPos, length, styler, CheckPureFoldPoint);
+}
+
+static const char * const blitzbasicWordListDesc[] = {
+	"BlitzBasic Keywords",
+	"user1",
+	"user2",
+	"user3",
+	0
+};
+
+static const char * const purebasicWordListDesc[] = {
+	"PureBasic Keywords",
+	"PureBasic PreProcessor Keywords",
+	"user defined 1",
+	"user defined 2",
+	0
+};
+
+LexerModule lmBlitzBasic(SCLEX_BLITZBASIC, ColouriseBlitzBasicDoc, "blitzbasic",
+	FoldBlitzBasicDoc, blitzbasicWordListDesc);
+
+LexerModule lmPureBasic(SCLEX_PUREBASIC, ColourisePureBasicDoc, "purebasic",
+	FoldPureBasicDoc, purebasicWordListDesc);
+
diff --git a/src/LexCaml.cxx b/src/LexCaml.cxx
new file mode 100644
index 000000000..ac1bfba5d
--- /dev/null
+++ b/src/LexCaml.cxx
@@ -0,0 +1,389 @@
+// Scintilla source code edit control
+/** @file LexCaml.cxx
+ ** Lexer for Objective Caml.
+ **/
+// Copyright 2005 by Robert Roessler <robertr@rftp.com>
+// The License.txt file describes the conditions under which this software may be distributed.
+/*	Release History
+	20050204 Initial release.
+	20050205 Quick compiler standards/"cleanliness" adjustment.
+	20050206 Added cast for IsLeadByte().
+	20050209 Changes to "external" build support.
+*/
+
+#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"
+
+//	Since the Microsoft __iscsym[f] funcs are not ANSI...
+inline int  iscaml(int c) {return isalnum(c) || c == '_';}
+inline int iscamlf(int c) {return isalpha(c) || c == '_';}
+
+#ifdef BUILD_AS_EXTERNAL_LEXER
+/*
+	(actually seems to work!)
+*/
+#include "WindowAccessor.h"
+#include "ExternalLexer.h"
+
+#if PLAT_WIN
+#include <windows.h>
+#endif
+
+static void ColouriseCamlDoc(
+	unsigned int startPos, int length,
+	int initStyle,
+	WordList *keywordlists[],
+	Accessor &styler);
+
+static void FoldCamlDoc(
+	unsigned int startPos, int length,
+	int initStyle,
+	WordList *keywordlists[],
+	Accessor &styler);
+
+static void InternalLexOrFold(int lexOrFold, unsigned int startPos, int length,
+	int initStyle, char *words[], WindowID window, char *props);
+
+static const char* LexerName = "caml";
+
+#ifdef TRACE
+void Platform::DebugPrintf(const char *format, ...) {
+	char buffer[2000];
+	va_list pArguments;
+	va_start(pArguments, format);
+	vsprintf(buffer,format,pArguments);
+	va_end(pArguments);
+	Platform::DebugDisplay(buffer);
+}
+#else
+void Platform::DebugPrintf(const char *, ...) {
+}
+#endif
+
+bool Platform::IsDBCSLeadByte(int codePage, char ch) {
+	return ::IsDBCSLeadByteEx(codePage, ch) != 0;
+}
+
+long Platform::SendScintilla(WindowID w, unsigned int msg, unsigned long wParam, long lParam) {
+	return ::SendMessage(reinterpret_cast<HWND>(w), msg, wParam, lParam);
+}
+
+long Platform::SendScintillaPointer(WindowID w, unsigned int msg, unsigned long wParam, void *lParam) {
+	return ::SendMessage(reinterpret_cast<HWND>(w), msg, wParam,
+		reinterpret_cast<LPARAM>(lParam));
+}
+
+void EXT_LEXER_DECL Fold(unsigned int lexer, unsigned int startPos, int length,
+	int initStyle, char *words[], WindowID window, char *props)
+{
+	// below useless evaluation(s) to supress "not used" warnings
+	lexer;
+	// build expected data structures and do the Fold
+	InternalLexOrFold(1, startPos, length, initStyle, words, window, props);
+
+}
+
+int EXT_LEXER_DECL GetLexerCount()
+{
+	return 1;	// just us [Objective] Caml lexers here!
+}
+
+void EXT_LEXER_DECL GetLexerName(unsigned int Index, char *name, int buflength)
+{
+	// below useless evaluation(s) to supress "not used" warnings
+	Index;
+	// return as much of our lexer name as will fit (what's up with Index?)
+	if (buflength > 0) {
+		buflength--;
+		int n = strlen(LexerName);
+		if (n > buflength)
+			n = buflength;
+		memcpy(name, LexerName, n), name[n] = '\0';
+	}
+}
+
+void EXT_LEXER_DECL Lex(unsigned int lexer, unsigned int startPos, int length,
+	int initStyle, char *words[], WindowID window, char *props)
+{
+	// below useless evaluation(s) to supress "not used" warnings
+	lexer;
+	// build expected data structures and do the Lex
+	InternalLexOrFold(0, startPos, length, initStyle, words, window, props);
+}
+
+static void InternalLexOrFold(int foldOrLex, unsigned int startPos, int length,
+	int initStyle, char *words[], WindowID window, char *props)
+{
+	// create and initialize a WindowAccessor (including contained PropSet)
+	PropSet ps;
+	ps.SetMultiple(props);
+	WindowAccessor wa(window, ps);
+	// create and initialize WordList(s)
+	int nWL = 0;
+	for (; words[nWL]; nWL++) ;	// count # of WordList PTRs needed
+	WordList** wl = new WordList* [nWL + 1];// alloc WordList PTRs
+	int i = 0;
+	for (; i < nWL; i++) {
+		wl[i] = new WordList();	// (works or THROWS bad_alloc EXCEPTION)
+		wl[i]->Set(words[i]);
+	}
+	wl[i] = 0;
+	// call our "internal" folder/lexer (... then do Flush!)
+	if (foldOrLex)
+		FoldCamlDoc(startPos, length, initStyle, wl, wa);
+	else
+		ColouriseCamlDoc(startPos, length, initStyle, wl, wa);
+	wa.Flush();
+	// clean up before leaving
+	for (i = nWL - 1; i >= 0; i--)
+		delete wl[i];
+	delete [] wl;
+}
+
+static
+#endif	/* BUILD_AS_EXTERNAL_LEXER */
+
+void ColouriseCamlDoc(
+	unsigned int startPos, int length,
+	int initStyle,
+	WordList *keywordlists[],
+	Accessor &styler)
+{
+	// initialize styler
+	styler.StartAt(startPos);
+	styler.StartSegment(startPos);
+	// set up [initial] state info (terminating states that shouldn't "bleed")
+	int state = initStyle, nesting = 0;
+	if (state < SCE_CAML_STRING)
+		state = SCE_CAML_DEFAULT;
+	if (state >= SCE_CAML_COMMENT)
+		nesting = state - SCE_CAML_COMMENT;
+	int chLast = startPos? static_cast<unsigned char>(styler[startPos - 1]): ' ';
+	int chNext = static_cast<unsigned char>(styler[startPos]);
+
+	int chBase = 'd', chToken = 0, chLit = 0, chSkip;
+	WordList& keywords = *keywordlists[0];
+	WordList& keywords2 = *keywordlists[1];
+
+	// foreach char in range...
+	unsigned int i = startPos;
+	for (unsigned int endPos = startPos + length; i < endPos; i += chSkip) {
+		// set up [per-char] state info
+		int ch = chNext;
+		chNext = static_cast<unsigned char>(styler.SafeGetCharAt(i + 1));
+		int state2 = -1;	// (ASSUME no state change)
+		int chColor = i - 1;// (ASSUME standard coloring range)
+		chSkip = 1;			// (ASSUME scanner "eats" 1 char)
+
+		// this may be the correct thing to do... or not
+		if (styler.IsLeadByte(static_cast<char>(ch))) {
+			chNext = static_cast<unsigned char>(styler.SafeGetCharAt(i + 2)),
+				chSkip++;
+			continue;
+		}
+
+		// step state machine
+		switch (state) {
+		case SCE_CAML_DEFAULT:
+			// it's wide open; what do we have?
+			if (iscamlf(ch))
+				state2 = SCE_CAML_IDENTIFIER, chToken = i;
+			else if (ch == '`')
+				state2 = SCE_CAML_TAGNAME, chToken = i;
+			else if (ch == '#' && isdigit(chNext))
+				state2 = SCE_CAML_LINENUM, chToken = i;
+			else if (isdigit(ch)) {
+				state2 = SCE_CAML_NUMBER,
+					chBase = strchr("xXoObB", chNext)? chNext: 'd';
+				if (chBase != 'd')
+					ch = chNext,
+						chNext = static_cast<unsigned char>(styler.SafeGetCharAt(i + 2)),
+						chSkip++;
+			} else if (ch == '\'')	/* (char literal?) */
+				state2 = SCE_CAML_CHAR, chToken = i, chLit = 0;
+			else if (ch == '\"')
+				state2 = SCE_CAML_STRING;
+			else if (ch == '(' && chNext == '*')
+				state2 = SCE_CAML_COMMENT,
+					ch = ' ',	// (make SURE "(*)" isn't seen as a closed comment)
+					chNext = static_cast<unsigned char>(styler.SafeGetCharAt(i + 2)),
+					chSkip++, nesting = 0;
+			else if (strchr("!?~"		/* Caml "prefix-symbol" */
+					"=<>@^|&+-*/$%"		/* Caml "infix-symbol" */
+					"()[]{};,:.#", ch))	/* Caml "bracket" or ;,:.# */
+				state2 = SCE_CAML_OPERATOR, chToken = i;
+			break;
+
+		case SCE_CAML_IDENTIFIER:
+			// [try to] interpret as [additional] identifier char
+			if (!(iscaml(ch) || ch == '\'')) {
+				const int n = i - chToken;
+				if (n < 24) {
+					// length is believable as keyword, [re-]construct token
+					char t[24];
+					int p = 0;
+					for (int q = chToken; p < n; p++, q++)
+						t[p] = styler[q];
+					t[p] = '\0';
+					// special-case "_" token as KEYWORD
+					if ((n == 1 && chLast == '_') || keywords.InList(t))
+						state = SCE_CAML_KEYWORD;
+					else if (keywords2.InList(t))
+						state = SCE_CAML_KEYWORD2;
+				}
+				state2 = SCE_CAML_DEFAULT, chNext = ch, chSkip--;
+			}
+			break;
+
+		case SCE_CAML_TAGNAME:
+			// [try to] interpret as [additional] tagname char
+			if (!(iscaml(ch) || ch == '\''))
+				state2 = SCE_CAML_DEFAULT, chNext = ch, chSkip--;
+			break;
+
+		/*case SCE_CAML_KEYWORD:
+		case SCE_CAML_KEYWORD2:
+			// [try to] interpret as [additional] keyword char
+			if (!iscaml(ch))
+				state2 = SCE_CAML_DEFAULT, chNext = ch, chSkip--;
+			break;*/
+
+		case SCE_CAML_LINENUM:
+			// [try to] interpret as [additional] linenum directive char
+			if (!isdigit(ch))
+				state2 = SCE_CAML_DEFAULT, chNext = ch, chSkip--;
+			break;
+
+		case SCE_CAML_OPERATOR: {
+			// [try to] interpret as [additional] operator char
+			char* o = 0;
+			if (iscaml(ch) || isspace(ch)			/* ident or whitespace */
+				|| ((o = strchr(")]};,\'\"`#", ch)) != 0)/* "termination" chars */
+				|| !strchr("!$%&*+-./:<=>?@^|~", ch)/* "operator" chars */) {
+				// check for INCLUSIVE termination
+				if (o && strchr(")]};,", ch)) {
+					if ((ch == ')' && chLast == '(') || (ch == ']' && chLast == '['))
+						// special-case "()" and "[]" tokens as KEYWORDS
+						state = SCE_CAML_KEYWORD;
+					chColor++;
+				} else
+					chNext = ch, chSkip--;
+				state2 = SCE_CAML_DEFAULT;
+			}
+			break;
+		}
+
+		case SCE_CAML_NUMBER:
+			// [try to] interpret as [additional] numeric literal char
+			// N.B. - improperly accepts "extra" digits in base 2 or 8 literals
+			if (isdigit(ch) || ch == '_'
+				|| ((chBase == 'x' || chBase == 'X') && isxdigit(ch)))
+				break;
+			// how about an integer suffix?
+			if ((ch == 'l' || ch == 'L' || ch == 'n')
+				&& (isdigit(chLast) || chLast == '_'))
+				break;
+			// or a floating-point literal?
+			if (ch == '.' && (isdigit(chLast) || chLast == '_'))
+				break;
+			// with an exponent? (I)
+			if ((ch == 'e' || ch == 'E')
+				&& (isdigit(chLast) || chLast == '_' || chLast == '.'))
+				break;
+			// with an exponent? (II)
+			if ((ch == '+' || ch == '-') && (chLast == 'e' || chLast == 'E'))
+				break;
+			// it looks like we have run out of number
+			state2 = SCE_CAML_DEFAULT, chNext = ch, chSkip--;
+			break;
+
+		case SCE_CAML_CHAR:
+			// [try to] interpret as [additional] char literal char
+			if (ch == '\\') {
+				chLit = 1;	// (definitely IS a char literal)
+				if (chLast == '\\')
+					ch = ' ';	// (so termination test isn't fooled)
+			// should we be terminating - one way or another?
+			} else if ((ch == '\'' && chLast != '\\') || ch == '\r' || ch == '\n') {
+				state2 = SCE_CAML_DEFAULT;
+				if (ch == '\'')
+					chColor++;
+				else
+					state = SCE_CAML_IDENTIFIER;
+			// ... maybe a char literal, maybe not
+			} else if (chLit < 1 && i - chToken >= 2)
+				state = SCE_CAML_IDENTIFIER, chNext = ch, chSkip--;
+			break;
+
+		case SCE_CAML_STRING:
+			// [try to] interpret as [additional] string literal char
+			if (ch == '\\' && chLast == '\\')
+				ch = ' ';	// (so '\\' doesn't cause us trouble)
+			else if (ch == '\"' && chLast != '\\')
+				state2 = SCE_CAML_DEFAULT, chColor++;
+			break;
+
+		case SCE_CAML_COMMENT:
+		case SCE_CAML_COMMENT+1:
+		case SCE_CAML_COMMENT+2:
+		case SCE_CAML_COMMENT+3:
+			// we're IN a comment - does this start a NESTED comment?
+			if (ch == '(' && chNext == '*')
+				state2 = state + 1,
+					ch = ' ',	// (make SURE "(*)" isn't seen as a closed comment)
+					chNext = static_cast<unsigned char>(styler.SafeGetCharAt(i + 2)),
+					chSkip++, nesting++;
+			// [try to] interpret as [additional] comment char
+			else if (ch == ')' && chLast == '*')
+				state2 = nesting? (state - 1): SCE_CAML_DEFAULT, chColor++, nesting--;
+			break;
+		}
+
+		// handle state change and char coloring as required
+		if (state2 >= 0) {
+			if (chColor > 0)
+				styler.ColourTo(chColor, state);
+			state = state2;
+		}
+		chLast = ch;
+	}
+
+	// do terminal char coloring (JIC)
+	styler.ColourTo(i, state);
+//	styler.Flush();	// (is this always called by calling code?)
+}
+
+#ifdef BUILD_AS_EXTERNAL_LEXER
+static
+#endif	/* BUILD_AS_EXTERNAL_LEXER */
+void FoldCamlDoc(
+	unsigned int startPos, int length,
+	int initStyle,
+	WordList *keywordlists[],
+	Accessor &styler)
+{
+	// below useless evaluation(s) to supress "not used" warnings
+	startPos || length || initStyle || keywordlists[0] || styler.Length();
+}
+
+static const char * const camlWordListDesc[] = {
+	"Keywords",		// primary Objective Caml keywords
+	"Keywords2",	// "optional" keywords (typically from Pervasives)
+	0
+};
+
+#ifndef BUILD_AS_EXTERNAL_LEXER
+LexerModule lmCaml(SCLEX_CAML, ColouriseCamlDoc, "caml", FoldCamlDoc, camlWordListDesc);
+#endif	/* BUILD_AS_EXTERNAL_LEXER */
diff --git a/win32/makefile b/win32/makefile
index 473ffe0f2..98460fc54 100644
--- a/win32/makefile
+++ b/win32/makefile
@@ -52,12 +52,13 @@ deps:
 #**LEXOBJS=\\\n\(\*.o \)
 LEXOBJS=\
 LexAda.o LexAPDL.o LexAsm.o LexAsn1.o LexAU3.o LexAVE.o LexBaan.o LexBash.o \
-LexBullant.o LexCLW.o LexConf.o LexCPP.o LexCrontab.o LexCSS.o LexEiffel.o \
-LexErlang.o LexEScript.o LexForth.o LexFortran.o LexGui4Cli.o LexHTML.o \
-LexKix.o LexLisp.o LexLout.o LexLua.o LexMatlab.o LexMetapost.o LexMMIXAL.o \
-LexMPT.o LexMSSQL.o LexNsis.o LexOthers.o LexPascal.o LexPB.o LexPerl.o \
-LexPOV.o LexPS.o LexPython.o LexRuby.o LexScriptol.o LexSpecman.o LexSQL.o \
-LexTeX.o LexVB.o LexVerilog.o LexVHDL.o LexYAML.o
+LexBasic.o LexBullant.o LexCaml.o LexCLW.o LexConf.o LexCPP.o LexCrontab.o \
+LexCSS.o LexEiffel.o LexErlang.o LexEScript.o LexForth.o LexFortran.o \
+LexGui4Cli.o LexHTML.o LexKix.o LexLisp.o LexLout.o LexLua.o LexMatlab.o \
+LexMetapost.o LexMMIXAL.o LexMPT.o LexMSSQL.o LexNsis.o LexOthers.o \
+LexPascal.o LexPB.o LexPerl.o LexPOV.o LexPS.o LexPython.o LexRuby.o \
+LexScriptol.o LexSpecman.o LexSQL.o LexTeX.o LexVB.o LexVerilog.o LexVHDL.o \
+LexYAML.o
 #--Autogenerated -- end of automatically generated section
 
 SOBJS	= ScintillaWin.o ScintillaBase.o Editor.o Document.o \
diff --git a/win32/scintilla.mak b/win32/scintilla.mak
index 99d978e8a..0ecfb642c 100644
--- a/win32/scintilla.mak
+++ b/win32/scintilla.mak
@@ -117,7 +117,9 @@ LEXOBJS=\
 	$(DIR_O)\LexAVE.obj \
 	$(DIR_O)\LexBaan.obj \
 	$(DIR_O)\LexBash.obj \
+	$(DIR_O)\LexBasic.obj \
 	$(DIR_O)\LexBullant.obj \
+	$(DIR_O)\LexCaml.obj \
 	$(DIR_O)\LexCLW.obj \
 	$(DIR_O)\LexConf.obj \
 	$(DIR_O)\LexCPP.obj \
@@ -281,8 +283,12 @@ $(DIR_O)\LexBaan.obj: ..\src\LexBaan.cxx $(LEX_HEADERS)
 
 $(DIR_O)\LexBash.obj: ..\src\LexBash.cxx $(LEX_HEADERS)
 
+$(DIR_O)\LexBasic.obj: ..\src\LexBasic.cxx $(LEX_HEADERS)
+
 $(DIR_O)\LexBullant.obj: ..\src\LexBullant.cxx $(LEX_HEADERS)
 
+$(DIR_O)\LexCaml.obj: ..\src\LexCaml.cxx $(LEX_HEADERS)
+
 $(DIR_O)\LexCLW.obj: ..\src\LexCLW.cxx $(LEX_HEADERS)
 
 $(DIR_O)\LexConf.obj: ..\src\LexConf.cxx $(LEX_HEADERS)
diff --git a/win32/scintilla_vc6.mak b/win32/scintilla_vc6.mak
index 29d6a493e..a9bb782f2 100644
--- a/win32/scintilla_vc6.mak
+++ b/win32/scintilla_vc6.mak
@@ -119,7 +119,9 @@ LEXOBJS=\
 	$(DIR_O)\LexAVE.obj \
 	$(DIR_O)\LexBaan.obj \
 	$(DIR_O)\LexBash.obj \
+	$(DIR_O)\LexBasic.obj \
 	$(DIR_O)\LexBullant.obj \
+	$(DIR_O)\LexCaml.obj \
 	$(DIR_O)\LexCLW.obj \
 	$(DIR_O)\LexConf.obj \
 	$(DIR_O)\LexCPP.obj \
@@ -283,8 +285,12 @@ $(DIR_O)\LexBaan.obj: ..\src\LexBaan.cxx $(LEX_HEADERS)
 
 $(DIR_O)\LexBash.obj: ..\src\LexBash.cxx $(LEX_HEADERS)
 
+$(DIR_O)\LexBasic.obj: ..\src\LexBasic.cxx $(LEX_HEADERS)
+
 $(DIR_O)\LexBullant.obj: ..\src\LexBullant.cxx $(LEX_HEADERS)
 
+$(DIR_O)\LexCaml.obj: ..\src\LexCaml.cxx $(LEX_HEADERS)
+
 $(DIR_O)\LexCLW.obj: ..\src\LexCLW.cxx $(LEX_HEADERS)
 
 $(DIR_O)\LexConf.obj: ..\src\LexConf.cxx $(LEX_HEADERS)