1 // Scintilla source code edit control
2 /** @file LexAsm.cxx
3 ** Lexer for Assembler, just for the MASM syntax
4 ** Written by The Black Horus
5 ** Enhancements and NASM stuff by Kein-Hong Man, 2003-10
6 ** SCE_ASM_COMMENTBLOCK and SCE_ASM_CHARACTER are for future GNU as colouring
7 **/
8 // Copyright 1998-2003 by Neil Hodgson <neilh@scintilla.org>
9 // The License.txt file describes the conditions under which this software may be distributed.
10
11 #include <stdlib.h>
12 #include <string.h>
13 #include <ctype.h>
14 #include <stdio.h>
15 #include <stdarg.h>
16
17 #include "Platform.h"
18
19 #include "PropSet.h"
20 #include "Accessor.h"
21 #include "StyleContext.h"
22 #include "KeyWords.h"
23 #include "Scintilla.h"
24 #include "SciLexer.h"
25
26
IsAWordChar(const int ch)27 static inline bool IsAWordChar(const int ch) {
28 return (ch < 0x80) && (isalnum(ch) || ch == '.' ||
29 ch == '_' || ch == '?');
30 }
31
IsAWordStart(const int ch)32 static inline bool IsAWordStart(const int ch) {
33 return (ch < 0x80) && (isalnum(ch) || ch == '_' || ch == '.' ||
34 ch == '%' || ch == '@' || ch == '$' || ch == '?');
35 }
36
IsAsmOperator(char ch)37 static inline bool IsAsmOperator(char ch) {
38 if (isalnum(ch))
39 return false;
40 // '.' left out as it is used to make up numbers
41 if (ch == '*' || ch == '/' || ch == '-' || ch == '+' ||
42 ch == '(' || ch == ')' || ch == '=' || ch == '^' ||
43 ch == '[' || ch == ']' || ch == '<' || ch == '&' ||
44 ch == '>' || ch == ',' || ch == '|' || ch == '~' ||
45 ch == '%' || ch == ':')
46 return true;
47 return false;
48 }
49
ColouriseAsmDoc(unsigned int startPos,int length,int initStyle,WordList * keywordlists[],Accessor & styler)50 static void ColouriseAsmDoc(unsigned int startPos, int length, int initStyle, WordList *keywordlists[],
51 Accessor &styler) {
52
53 WordList &cpuInstruction = *keywordlists[0];
54 WordList &mathInstruction = *keywordlists[1];
55 WordList ®isters = *keywordlists[2];
56 WordList &directive = *keywordlists[3];
57 WordList &directiveOperand = *keywordlists[4];
58 WordList &extInstruction = *keywordlists[5];
59
60 // Do not leak onto next line
61 if (initStyle == SCE_ASM_STRINGEOL)
62 initStyle = SCE_ASM_DEFAULT;
63
64 StyleContext sc(startPos, length, initStyle, styler);
65
66 for (; sc.More(); sc.Forward())
67 {
68
69 // Prevent SCE_ASM_STRINGEOL from leaking back to previous line
70 if (sc.atLineStart && (sc.state == SCE_ASM_STRING)) {
71 sc.SetState(SCE_ASM_STRING);
72 } else if (sc.atLineStart && (sc.state == SCE_ASM_CHARACTER)) {
73 sc.SetState(SCE_ASM_CHARACTER);
74 }
75
76 // Handle line continuation generically.
77 if (sc.ch == '\\') {
78 if (sc.chNext == '\n' || sc.chNext == '\r') {
79 sc.Forward();
80 if (sc.ch == '\r' && sc.chNext == '\n') {
81 sc.Forward();
82 }
83 continue;
84 }
85 }
86
87 // Determine if the current state should terminate.
88 if (sc.state == SCE_ASM_OPERATOR) {
89 if (!IsAsmOperator(static_cast<char>(sc.ch))) {
90 sc.SetState(SCE_ASM_DEFAULT);
91 }
92 }else if (sc.state == SCE_ASM_NUMBER) {
93 if (!IsAWordChar(sc.ch)) {
94 sc.SetState(SCE_ASM_DEFAULT);
95 }
96 } else if (sc.state == SCE_ASM_IDENTIFIER) {
97 if (!IsAWordChar(sc.ch) ) {
98 char s[100];
99 sc.GetCurrentLowered(s, sizeof(s));
100
101 if (cpuInstruction.InList(s)) {
102 sc.ChangeState(SCE_ASM_CPUINSTRUCTION);
103 } else if (mathInstruction.InList(s)) {
104 sc.ChangeState(SCE_ASM_MATHINSTRUCTION);
105 } else if (registers.InList(s)) {
106 sc.ChangeState(SCE_ASM_REGISTER);
107 } else if (directive.InList(s)) {
108 sc.ChangeState(SCE_ASM_DIRECTIVE);
109 } else if (directiveOperand.InList(s)) {
110 sc.ChangeState(SCE_ASM_DIRECTIVEOPERAND);
111 } else if (extInstruction.InList(s)) {
112 sc.ChangeState(SCE_ASM_EXTINSTRUCTION);
113 }
114 sc.SetState(SCE_ASM_DEFAULT);
115 }
116 }
117 else if (sc.state == SCE_ASM_COMMENT ) {
118 if (sc.atLineEnd) {
119 sc.SetState(SCE_ASM_DEFAULT);
120 }
121 } else if (sc.state == SCE_ASM_STRING) {
122 if (sc.ch == '\\') {
123 if (sc.chNext == '\"' || sc.chNext == '\'' || sc.chNext == '\\') {
124 sc.Forward();
125 }
126 } else if (sc.ch == '\"') {
127 sc.ForwardSetState(SCE_ASM_DEFAULT);
128 } else if (sc.atLineEnd) {
129 sc.ChangeState(SCE_ASM_STRINGEOL);
130 sc.ForwardSetState(SCE_ASM_DEFAULT);
131 }
132 } else if (sc.state == SCE_ASM_CHARACTER) {
133 if (sc.ch == '\\') {
134 if (sc.chNext == '\"' || sc.chNext == '\'' || sc.chNext == '\\') {
135 sc.Forward();
136 }
137 } else if (sc.ch == '\'') {
138 sc.ForwardSetState(SCE_ASM_DEFAULT);
139 } else if (sc.atLineEnd) {
140 sc.ChangeState(SCE_ASM_STRINGEOL);
141 sc.ForwardSetState(SCE_ASM_DEFAULT);
142 }
143 }
144
145 // Determine if a new state should be entered.
146 if (sc.state == SCE_ASM_DEFAULT) {
147 if (sc.ch == ';'){
148 sc.SetState(SCE_ASM_COMMENT);
149 } else if (isdigit(sc.ch) || (sc.ch == '.' && isdigit(sc.chNext))) {
150 sc.SetState(SCE_ASM_NUMBER);
151 } else if (IsAWordStart(sc.ch)) {
152 sc.SetState(SCE_ASM_IDENTIFIER);
153 } else if (sc.ch == '\"') {
154 sc.SetState(SCE_ASM_STRING);
155 } else if (sc.ch == '\'') {
156 sc.SetState(SCE_ASM_CHARACTER);
157 } else if (IsAsmOperator(static_cast<char>(sc.ch))) {
158 sc.SetState(SCE_ASM_OPERATOR);
159 }
160 }
161
162 }
163 sc.Complete();
164 }
165
166 static const char * const asmWordListDesc[] = {
167 "CPU instructions",
168 "FPU instructions",
169 "Registers",
170 "Directives",
171 "Directive operands",
172 "Extended instructions",
173 0
174 };
175
176 LexerModule lmAsm(SCLEX_ASM, ColouriseAsmDoc, "asm", 0, asmWordListDesc);
177
178