1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
|
// Scintilla source code edit control
/** @file LexStata.cxx
** Lexer for Stata
**/
// Author: Luke Rasmussen (luke.rasmussen@gmail.com)
//
// The License.txt file describes the conditions under which this software may
// be distributed.
//
// Developed as part of the StatTag project at Northwestern University Feinberg
// School of Medicine with funding from Northwestern University Clinical and
// Translational Sciences Institute through CTSA grant UL1TR001422. This work
// has not been reviewed or endorsed by NCATS or the NIH.
#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 "WordList.h"
#include "LexAccessor.h"
#include "Accessor.h"
#include "StyleContext.h"
#include "CharacterSet.h"
#include "LexerModule.h"
using namespace Scintilla;
static void ColouriseStataDoc(Sci_PositionU startPos, Sci_Position length, int initStyle, WordList *keywordlists[],
Accessor &styler) {
WordList &keywords = *keywordlists[0];
WordList &types = *keywordlists[1];
CharacterSet setCouldBePostOp(CharacterSet::setNone, "+-");
CharacterSet setWordStart(CharacterSet::setAlpha, "_", 0x80, true);
CharacterSet setWord(CharacterSet::setAlphaNum, "._", 0x80, true);
StyleContext sc(startPos, length, initStyle, styler);
bool lineHasNonCommentChar = false;
for (; sc.More(); sc.Forward()) {
if (sc.atLineStart) {
lineHasNonCommentChar = false;
}
// Determine if the current state should terminate.
switch (sc.state) {
case SCE_STATA_OPERATOR:
sc.SetState(SCE_STATA_DEFAULT);
break;
case SCE_STATA_NUMBER:
// We accept almost anything because of hex. and number suffixes
if (!setWord.Contains(sc.ch)) {
sc.SetState(SCE_STATA_DEFAULT);
}
break;
case SCE_STATA_IDENTIFIER:
if (!setWord.Contains(sc.ch) || (sc.ch == '.')) {
char s[1000];
sc.GetCurrent(s, sizeof(s));
if (keywords.InList(s)) {
sc.ChangeState(SCE_STATA_WORD);
}
else if (types.InList(s)) {
sc.ChangeState(SCE_STATA_TYPE);
}
sc.SetState(SCE_STATA_DEFAULT);
}
break;
case SCE_STATA_COMMENTBLOCK:
if (sc.Match('*', '/')) {
sc.Forward();
sc.ForwardSetState(SCE_STATA_DEFAULT);
}
break;
case SCE_STATA_COMMENT:
case SCE_STATA_COMMENTLINE:
if (sc.atLineStart) {
sc.SetState(SCE_STATA_DEFAULT);
}
break;
case SCE_STATA_STRING:
if (sc.ch == '\\') {
// Per Stata documentation, the following characters are the only ones that can
// be escaped (not our typical set of quotes, etc.):
// https://www.stata.com/support/faqs/programming/backslashes-and-macros/
if (sc.chNext == '$' || sc.chNext == '`' || sc.chNext == '\\') {
sc.Forward();
}
}
else if (sc.ch == '\"') {
sc.ForwardSetState(SCE_STATA_DEFAULT);
}
break;
}
// Determine if a new state should be entered.
if (sc.state == SCE_STATA_DEFAULT) {
if (IsADigit(sc.ch) || (sc.ch == '.' && IsADigit(sc.chNext))) {
lineHasNonCommentChar = true;
sc.SetState(SCE_STATA_NUMBER);
}
else if (setWordStart.Contains(sc.ch)) {
lineHasNonCommentChar = true;
sc.SetState(SCE_STATA_IDENTIFIER);
}
else if (sc.Match('*') && !lineHasNonCommentChar) {
sc.SetState(SCE_STATA_COMMENT);
}
else if (sc.Match('/', '*')) {
sc.SetState(SCE_STATA_COMMENTBLOCK);
sc.Forward(); // Eat the * so it isn't used for the end of the comment
}
else if (sc.Match('/', '/')) {
sc.SetState(SCE_STATA_COMMENTLINE);
}
else if (sc.ch == '\"') {
lineHasNonCommentChar = true;
sc.SetState(SCE_STATA_STRING);
}
else if (isoperator(sc.ch)) {
lineHasNonCommentChar = true;
sc.SetState(SCE_STATA_OPERATOR);
}
}
}
sc.Complete();
}
// Store both the current line's fold level and the next lines in the
// level store to make it easy to pick up with each increment
// and to make it possible to fiddle the current level for "} else {".
static void FoldStataDoc(Sci_PositionU startPos, Sci_Position length, int, WordList *[],
Accessor &styler) {
bool foldCompact = styler.GetPropertyInt("fold.compact", 1) != 0;
bool foldAtElse = styler.GetPropertyInt("fold.at.else", 0) != 0;
Sci_PositionU endPos = startPos + length;
int visibleChars = 0;
Sci_Position lineCurrent = styler.GetLine(startPos);
int levelCurrent = SC_FOLDLEVELBASE;
if (lineCurrent > 0)
levelCurrent = styler.LevelAt(lineCurrent - 1) >> 16;
int levelMinCurrent = levelCurrent;
int levelNext = levelCurrent;
char chNext = styler[startPos];
int styleNext = styler.StyleAt(startPos);
for (Sci_PositionU i = startPos; i < endPos; i++) {
char ch = chNext;
chNext = styler.SafeGetCharAt(i + 1);
int style = styleNext;
styleNext = styler.StyleAt(i + 1);
bool atEOL = (ch == '\r' && chNext != '\n') || (ch == '\n');
if (style == SCE_R_OPERATOR) {
if (ch == '{') {
// Measure the minimum before a '{' to allow
// folding on "} else {"
if (levelMinCurrent > levelNext) {
levelMinCurrent = levelNext;
}
levelNext++;
}
else if (ch == '}') {
levelNext--;
}
}
if (atEOL) {
int levelUse = levelCurrent;
if (foldAtElse) {
levelUse = levelMinCurrent;
}
int lev = levelUse | levelNext << 16;
if (visibleChars == 0 && foldCompact)
lev |= SC_FOLDLEVELWHITEFLAG;
if (levelUse < levelNext)
lev |= SC_FOLDLEVELHEADERFLAG;
if (lev != styler.LevelAt(lineCurrent)) {
styler.SetLevel(lineCurrent, lev);
}
lineCurrent++;
levelCurrent = levelNext;
levelMinCurrent = levelCurrent;
visibleChars = 0;
}
if (!isspacechar(ch))
visibleChars++;
}
}
static const char * const StataWordLists[] = {
"Language Keywords",
"Types",
0,
};
LexerModule lmStata(SCLEX_STATA, ColouriseStataDoc, "stata", FoldStataDoc, StataWordLists);
|
