Lexer for Motorola 68000 assembler.

7 files changed, 369 insertions, 0 deletions

diff --git a/doc/ScintillaHistory.html b/doc/ScintillaHistory.html
index 5775acd75..2aac5c34d 100644
--- a/doc/ScintillaHistory.html
+++ b/doc/ScintillaHistory.html
@@ -359,6 +359,7 @@
 	<td>Michael Mullin</td>
 	<td>Carlos SS</td>
 	<td>vim</td>
+	<td>Martial Demolins</td>
     </tr>
     </table>
     <p>
diff --git a/include/SciLexer.h b/include/SciLexer.h
index 3aa2c3853..ea49be2c9 100644
--- a/include/SciLexer.h
+++ b/include/SciLexer.h
@@ -112,6 +112,7 @@
 #define SCLEX_SML 97
 #define SCLEX_MARKDOWN 98
 #define SCLEX_TXT2TAGS 99
+#define SCLEX_A68K 100
 #define SCLEX_AUTOMATIC 1000
 #define SCE_P_DEFAULT 0
 #define SCE_P_COMMENTLINE 1
@@ -1415,6 +1416,25 @@
 #define SCE_TXT2TAGS_OPTION 23
 #define SCE_TXT2TAGS_PREPROC 24
 #define SCE_TXT2TAGS_POSTPROC 25
+#define SCE_A68K_DEFAULT 0
+#define SCE_A68K_COMMENT 1
+#define SCE_A68K_NUMBER_DEC 2
+#define SCE_A68K_NUMBER_BIN 3
+#define SCE_A68K_NUMBER_HEX 4
+#define SCE_A68K_STRING1 5
+#define SCE_A68K_OPERATOR 6
+#define SCE_A68K_CPUINSTRUCTION 7
+#define SCE_A68K_EXTINSTRUCTION 8
+#define SCE_A68K_REGISTER 9
+#define SCE_A68K_DIRECTIVE 10
+#define SCE_A68K_MACRO_ARG 11
+#define SCE_A68K_LABEL 12
+#define SCE_A68K_STRING2 13
+#define SCE_A68K_IDENTIFIER 14
+#define SCE_A68K_MACRO_DECLARATION 15
+#define SCE_A68K_COMMENT_WORD 16
+#define SCE_A68K_COMMENT_SPECIAL 17
+#define SCE_A68K_COMMENT_DOXYGEN 18
 /* --Autogenerated -- end of section automatically generated from Scintilla.iface */
 
 #endif
diff --git a/include/Scintilla.iface b/include/Scintilla.iface
index 61031398c..405fc0552 100644
--- a/include/Scintilla.iface
+++ b/include/Scintilla.iface
@@ -2335,6 +2335,7 @@ val SCLEX_NIMROD=96
 val SCLEX_SML=97
 val SCLEX_MARKDOWN=98
 val SCLEX_TXT2TAGS=99
+val SCLEX_A68K=100
 
 # When a lexer specifies its language as SCLEX_AUTOMATIC it receives a
 # value assigned in sequence from SCLEX_AUTOMATIC+1.
@@ -3819,6 +3820,27 @@ val SCE_TXT2TAGS_COMMENT=22
 val SCE_TXT2TAGS_OPTION=23
 val SCE_TXT2TAGS_PREPROC=24
 val SCE_TXT2TAGS_POSTPROC=25
+# Lexical states for SCLEX_A68K
+lex A68k=SCLEX_A68K SCE_A68K_
+val SCE_A68K_DEFAULT=0
+val SCE_A68K_COMMENT=1
+val SCE_A68K_NUMBER_DEC=2
+val SCE_A68K_NUMBER_BIN=3
+val SCE_A68K_NUMBER_HEX=4
+val SCE_A68K_STRING1=5
+val SCE_A68K_OPERATOR=6
+val SCE_A68K_CPUINSTRUCTION=7
+val SCE_A68K_EXTINSTRUCTION=8
+val SCE_A68K_REGISTER=9
+val SCE_A68K_DIRECTIVE=10
+val SCE_A68K_MACRO_ARG=11
+val SCE_A68K_LABEL=12
+val SCE_A68K_STRING2=13
+val SCE_A68K_IDENTIFIER=14
+val SCE_A68K_MACRO_DECLARATION=15
+val SCE_A68K_COMMENT_WORD=16
+val SCE_A68K_COMMENT_SPECIAL=17
+val SCE_A68K_COMMENT_DOXYGEN=18
 
 # Events
 
diff --git a/lexers/LexA68k.cxx b/lexers/LexA68k.cxx
new file mode 100644
index 000000000..8704fb4db
--- /dev/null
+++ b/lexers/LexA68k.cxx
@@ -0,0 +1,319 @@
+// Scintilla source code edit control
+/** @file LexA68k.cxx
+ ** Lexer for Assembler, just for the MASM syntax
+ ** Written by Martial Demolins AKA Folco
+ **/
+// Copyright 2010 Martial Demolins <mdemolins(a)gmail.com>
+// The License.txt file describes the conditions under which this software
+// may be distributed.
+
+
+#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 "PropSetSimple.h"
+#include "WordList.h"
+#include "LexAccessor.h"
+#include "Accessor.h"
+#include "StyleContext.h"
+#include "CharacterSet.h"
+#include "LexerModule.h"
+
+#ifdef SCI_NAMESPACE
+using namespace Scintilla;
+#endif
+
+
+// Return values for GetOperatorType
+#define NO_OPERATOR     0
+#define OPERATOR_1CHAR  1
+#define OPERATOR_2CHAR  2
+
+
+/**
+ *  IsIdentifierStart
+ *
+ *  Return true if the given char is a valid identifier first char
+ */
+
+static inline bool IsIdentifierStart (const int ch)
+{
+    return (isalpha(ch) || (ch == '_') || (ch == '\\'));
+}
+
+
+/**
+ *  IsIdentifierChar
+ *
+ *  Return true if the given char is a valid identifier char
+ */
+
+static inline bool IsIdentifierChar (const int ch)
+{
+    return (isalnum(ch) || (ch == '_') || (ch == '@') || (ch == ':') || (ch == '.'));
+}
+
+
+/**
+ *  GetOperatorType
+ *
+ *  Return:
+ *  NO_OPERATOR     if char is not an operator
+ *  OPERATOR_1CHAR  if the operator is one char long
+ *  OPERATOR_2CHAR  if the operator is two chars long
+ */
+
+static inline int GetOperatorType (const int ch1, const int ch2)
+{
+    int OpType = NO_OPERATOR;
+
+    if ((ch1 == '+') || (ch1 == '-') || (ch1 == '*') || (ch1 == '/') || (ch1 == '#') ||
+        (ch1 == '(') || (ch1 == ')') || (ch1 == '~') || (ch1 == '&') || (ch1 == '|') || (ch1 == ','))
+        OpType = OPERATOR_1CHAR;
+
+    else if ((ch1 == ch2) && (ch1 == '<' || ch1 == '>'))
+        OpType = OPERATOR_2CHAR;
+
+    return OpType;
+}
+
+
+/**
+ *  IsBin
+ *
+ *  Return true if the given char is 0 or 1
+ */
+
+static inline bool IsBin (const int ch)
+{
+    return (ch == '0') || (ch == '1');
+}
+
+
+/**
+ *  IsDoxygenChar
+ *
+ *  Return true if the char may be part of a Doxygen keyword
+ */
+
+static inline bool IsDoxygenChar (const int ch)
+{
+    return isalpha(ch) || (ch == '$') || (ch == '[') || (ch == ']') || (ch == '{') || (ch == '}');
+}
+
+
+/**
+ *  ColouriseA68kDoc
+ *
+ *  Main function, which colourises a 68k source
+ */
+
+static void ColouriseA68kDoc (unsigned int startPos, int length, int initStyle, WordList *keywordlists[], Accessor &styler)
+{
+
+    // Get references to keywords lists
+    WordList &cpuInstruction = *keywordlists[0];
+    WordList &registers = *keywordlists[1];
+    WordList &directive = *keywordlists[2];
+    WordList &extInstruction = *keywordlists[3];
+    WordList &commentSpecial = *keywordlists[4];
+    WordList &doxygenKeyword = *keywordlists[5];
+
+
+    // Instanciate a context for our source
+    StyleContext sc(startPos, length, initStyle, styler);
+
+
+    /************************************************************
+    *
+    *   Parse the text
+    *
+    ************************************************************/
+
+    for ( ; sc.More(); sc.Forward())
+    {
+        char Buffer[100];
+        int OpType;
+
+        // Reset style at beginning of line
+        if (sc.atLineStart)
+            sc.SetState(SCE_A68K_DEFAULT);
+
+
+        /************************************************************
+        *
+        *   Handle current state if we are not in the "default style"
+        *
+        ************************************************************/
+
+        if (sc.state != SCE_A68K_DEFAULT)
+        {
+            // Check if current style continue.
+            // If this case, we loop because there is nothing else to do
+            if (((sc.state == SCE_A68K_NUMBER_DEC) && isdigit(sc.ch))                                       // Decimal number
+                || ((sc.state == SCE_A68K_NUMBER_BIN) && IsBin(sc.ch))                                      // Binary number
+                || ((sc.state == SCE_A68K_NUMBER_HEX) && isxdigit(sc.ch))                                   // Hexa number
+                || ((sc.state == SCE_A68K_MACRO_ARG)  && isdigit(sc.ch))                                    // Arg of macro
+                || ((sc.state == SCE_A68K_STRING1)    && (sc.ch != '\''))                                   // String single-quoted
+                || ((sc.state == SCE_A68K_STRING2)    && (sc.ch != '\"'))                                   // String double-quoted
+                || ((sc.state == SCE_A68K_MACRO_ARG)  && isdigit(sc.ch))                                    // Macro argument
+                // Label. ' ' and '\t' are needed to handle macro declarations
+                || ((sc.state == SCE_A68K_LABEL)      && (sc.ch != ':') && (sc.ch != ' ') && (sc.ch != '\t'))
+                || ((sc.state == SCE_A68K_IDENTIFIER) && (sc.ch < 0x80) && IsIdentifierChar(sc.ch))         // Identifier
+                || ((sc.state == SCE_A68K_COMMENT_DOXYGEN) && (sc.ch < 0x80) && IsDoxygenChar(sc.ch))       // Doxygen keyword
+                || ((sc.state == SCE_A68K_COMMENT_WORD) && (sc.ch < 0x80) && isalpha(sc.ch)))               // Comment current word
+            {
+                continue;
+            }
+
+            // Check if some states terminate at the current char:
+            // we must include this char in the current style context
+            else if (((sc.state == SCE_A68K_STRING1)    && (sc.ch < 0x80) && (sc.ch == '\''))       // String single-quoted
+                     || ((sc.state == SCE_A68K_STRING2) && (sc.ch < 0x80) && (sc.ch == '\"'))       // String double-quoted
+                     || ((sc.state == SCE_A68K_LABEL)   && (sc.ch < 0x80) && (sc.ch == ':')))       // Label
+            {
+                sc.ForwardSetState(SCE_A68K_DEFAULT);
+            }
+
+            // Check for special words or Doxygen keywords in comments
+            else if (sc.state == SCE_A68K_COMMENT)
+            {
+                if (sc.ch == '\\') {
+                    sc.SetState(SCE_A68K_COMMENT_DOXYGEN);
+                }
+                else if ((sc.ch < 0x80) && isalpha(sc.ch)) {
+                    sc.SetState(SCE_A68K_COMMENT_WORD);
+                }
+                continue;
+            }
+
+            // Check for special words in comment
+            else if ((sc.state == SCE_A68K_COMMENT_WORD) && (sc.ch < 0x80) && !isalpha(sc.ch))
+            {
+                sc.GetCurrent(Buffer, sizeof(Buffer));
+                if (commentSpecial.InList(Buffer)) {
+                    sc.ChangeState(SCE_A68K_COMMENT_SPECIAL);
+                }
+                else {
+                    sc.ChangeState(SCE_A68K_COMMENT);
+                }
+                sc.SetState(SCE_A68K_COMMENT);
+                continue;
+            }
+
+            // Check for Doxygen keywords
+            else if ((sc.state == SCE_A68K_COMMENT_DOXYGEN) && (sc.ch < 0x80) && !IsDoxygenChar(sc.ch))
+            {
+                sc.GetCurrentLowered(Buffer, sizeof(Buffer));                           // Buffer the string of the current context
+                if (!doxygenKeyword.InList(Buffer)) {
+                    sc.ChangeState(SCE_A68K_COMMENT);
+                }
+                sc.SetState(SCE_A68K_COMMENT);
+                continue;
+            }
+
+            // Check if we are in the case of a label which terminates without ':'
+            // It should be a macro declaration, not a label
+            else if ((sc.state == SCE_A68K_LABEL) && (sc.ch < 0x80) && ((sc.ch == ' ') || (sc.ch == '\t')))
+            {
+                sc.ChangeState(SCE_A68K_MACRO_DECLARATION);
+            }
+
+            // Check if we are at the end of an identifier
+            // In this case, colourise it if was a keyword.
+            else if ((sc.state == SCE_A68K_IDENTIFIER) && !IsIdentifierChar(sc.ch))
+            {
+                sc.GetCurrentLowered(Buffer, sizeof(Buffer));                           // Buffer the string of the current context
+                if (cpuInstruction.InList(Buffer)) {                                    // And check if it belongs to a keyword list
+                    sc.ChangeState(SCE_A68K_CPUINSTRUCTION);
+                }
+                else if (extInstruction.InList(Buffer)) {
+                    sc.ChangeState(SCE_A68K_EXTINSTRUCTION);
+                }
+                else if (registers.InList(Buffer)) {
+                    sc.ChangeState(SCE_A68K_REGISTER);
+                }
+                else if (directive.InList(Buffer)) {
+                    sc.ChangeState(SCE_A68K_DIRECTIVE);
+                }
+            }
+
+            // All special contexts are now handled.Come back to default style
+            sc.SetState(SCE_A68K_DEFAULT);
+        }
+
+
+        /************************************************************
+        *
+        *   Check if we must enter a new state
+        *
+        ************************************************************/
+
+        // Label and macro identifiers start at the beginning of a line
+        // We set both as a label, but if it wasn't one (no ':' at the end),
+        // it will be changed as a macro identifier.
+        if (sc.atLineStart && (sc.ch < 0x80) && IsIdentifierStart(sc.ch)) {
+            sc.SetState(SCE_A68K_LABEL);
+        }
+        else if ((sc.ch < 0x80) && (sc.ch == ';')) {                            // Comment
+            sc.SetState(SCE_A68K_COMMENT);
+        }
+        else if ((sc.ch < 0x80) && isdigit(sc.ch)) {                            // Decimal numbers haven't prefix
+            sc.SetState(SCE_A68K_NUMBER_DEC);
+        }
+        else if ((sc.ch < 0x80) && (sc.ch == '%')) {                            // Binary numbers are prefixed with '%'
+            sc.SetState(SCE_A68K_NUMBER_BIN);
+        }
+        else if ((sc.ch < 0x80) && (sc.ch == '$')) {                            // Hexadecimal numbers are prefixed with '$'
+            sc.SetState(SCE_A68K_NUMBER_HEX);
+        }
+        else if ((sc.ch < 0x80) && (sc.ch == '\'')) {                           // String (single-quoted)
+            sc.SetState(SCE_A68K_STRING1);
+        }
+        else if ((sc.ch < 0x80) && (sc.ch == '\"')) {                           // String (double-quoted)
+            sc.SetState(SCE_A68K_STRING2);
+        }
+        else if ((sc.ch < 0x80) && (sc.ch == '\\') && (isdigit(sc.chNext))) {   // Replacement symbols in macro
+            sc.SetState(SCE_A68K_MACRO_ARG);
+        }
+        else if ((sc.ch < 0x80) && IsIdentifierStart(sc.ch)) {                  // An identifier: constant, label, etc...
+            sc.SetState(SCE_A68K_IDENTIFIER);
+        }
+        else {
+            if (sc.ch < 0x80) {
+                OpType = GetOperatorType(sc.ch, sc.chNext);                     // Check if current char is an operator
+                if (OpType != NO_OPERATOR) {
+                    sc.SetState(SCE_A68K_OPERATOR);
+                    if (OpType == OPERATOR_2CHAR) {                             // Check if the operator is 2 bytes long
+                        sc.ForwardSetState(SCE_A68K_OPERATOR);                  // (>> or <<)
+                    }
+                }
+            }
+        }
+    }                                                                           // End of for()
+    sc.Complete();
+}
+
+
+// Names of the keyword lists
+
+static const char * const a68kWordListDesc[] =
+{
+    "CPU instructions",
+    "Registers",
+    "Directives",
+    "Extended instructions",
+    "Comment special words",
+    "Doxygen keywords",
+    0
+};
+
+LexerModule lmA68k(SCLEX_A68K, ColouriseA68kDoc, "a68k", 0, a68kWordListDesc);
diff --git a/src/Catalogue.cxx b/src/Catalogue.cxx
index a7ec50018..8b2e9b342 100644
--- a/src/Catalogue.cxx
+++ b/src/Catalogue.cxx
@@ -81,6 +81,7 @@ int Scintilla_LinkLexers() {
 
 //++Autogenerated -- run src/LexGen.py to regenerate
 //**\(\tLINK_LEXER(\*);\n\)
+	LINK_LEXER(lmA68k);
 	LINK_LEXER(lmAbaqus);
 	LINK_LEXER(lmAda);
 	LINK_LEXER(lmAns1);
diff --git a/win32/scintilla.mak b/win32/scintilla.mak
index c7d0f7441..e4a53a381 100644
--- a/win32/scintilla.mak
+++ b/win32/scintilla.mak
@@ -116,6 +116,7 @@ SOBJS=\
 #++Autogenerated -- run src/LexGen.py to regenerate
 #**LEXOBJS=\\\n\(\t$(DIR_O)\\\*.obj \\\n\)
 LEXOBJS=\
+	$(DIR_O)\LexA68k.obj \
 	$(DIR_O)\LexAbaqus.obj \
 	$(DIR_O)\LexAda.obj \
 	$(DIR_O)\LexAPDL.obj \
@@ -320,6 +321,8 @@ $(DIR_O)\KeyMap.obj: ../src/KeyMap.cxx ../include/Platform.h ../include/Scintill
 #++Autogenerated -- run src/LexGen.py to regenerate
 #**\n\($(DIR_O)\\\*.obj: ..\\lexers\\\*.cxx $(LEX_HEADERS)\n\n\)
 
+$(DIR_O)\LexA68k.obj: ..\lexers\LexA68k.cxx $(LEX_HEADERS)
+
 $(DIR_O)\LexAbaqus.obj: ..\lexers\LexAbaqus.cxx $(LEX_HEADERS)
 
 $(DIR_O)\LexAda.obj: ..\lexers\LexAda.cxx $(LEX_HEADERS)
diff --git a/win32/scintilla_vc6.mak b/win32/scintilla_vc6.mak
index 68175ad0c..fe33f3c50 100644
--- a/win32/scintilla_vc6.mak
+++ b/win32/scintilla_vc6.mak
@@ -118,6 +118,7 @@ SOBJS=\
 #++Autogenerated -- run src/LexGen.py to regenerate
 #**LEXOBJS=\\\n\(\t$(DIR_O)\\\*.obj \\\n\)
 LEXOBJS=\
+	$(DIR_O)\LexA68k.obj \
 	$(DIR_O)\LexAbaqus.obj \
 	$(DIR_O)\LexAda.obj \
 	$(DIR_O)\LexAPDL.obj \
@@ -322,6 +323,8 @@ $(DIR_O)\KeyMap.obj: ../src/KeyMap.cxx ../include/Platform.h ../include/Scintill
 #++Autogenerated -- run src/LexGen.py to regenerate
 #**\n\($(DIR_O)\\\*.obj: ..\\lexers\\\*.cxx $(LEX_HEADERS)\n\n\)
 
+$(DIR_O)\LexA68k.obj: ..\lexers\LexA68k.cxx $(LEX_HEADERS)
+
 $(DIR_O)\LexAbaqus.obj: ..\lexers\LexAbaqus.cxx $(LEX_HEADERS)
 
 $(DIR_O)\LexAda.obj: ..\lexers\LexAda.cxx $(LEX_HEADERS)