File: CxxTokenizer.cpp

package info (click to toggle)
codelite 17.0.0%2Bdfsg-1
  • links: PTS, VCS
  • area: main
  • in suites: bookworm
  • size: 136,204 kB
  • sloc: cpp: 491,547; ansic: 280,393; php: 10,259; sh: 8,930; lisp: 7,664; vhdl: 6,518; python: 6,020; lex: 4,920; yacc: 3,123; perl: 2,385; javascript: 1,715; cs: 1,193; xml: 1,110; makefile: 804; cobol: 741; sql: 709; ruby: 620; f90: 566; ada: 534; asm: 464; fortran: 350; objc: 289; tcl: 258; java: 157; erlang: 61; pascal: 51; ml: 49; awk: 44; haskell: 36
file content (320 lines) | stat: -rw-r--r-- 8,366 bytes parent folder | download | duplicates (2)
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
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
#include "CxxTokenizer.h"

#include "CxxScannerTokens.h"

#include <stack>

#define SCP_STATE_NORMAL 0
#define SCP_STATE_IN_IF 1
#define SCP_STATE_IN_WHILE 2
#define SCP_STATE_IN_FOR 3
#define SCP_STATE_IN_CATCH 4
#define SCP_STATE_IN_FOR_NO_SEMICOLON 5

CxxTokenizer::CxxTokenizer()
    : m_scanner(nullptr)
{
}

CxxTokenizer::~CxxTokenizer()
{
    if(m_scanner) {
        ::LexerDestroy(&m_scanner);
    }
}

bool CxxTokenizer::NextToken(CxxLexerToken& token)
{
    if(!m_scanner)
        return false;
    m_lastToken = token;
    return ::LexerNext(m_scanner, token);
}

bool CxxTokenizer::UngetToken()
{
    if(!m_scanner) {
        return false;
    }
    ::LexerUnget(m_scanner);
    return true;
}

void CxxTokenizer::Reset(const wxString& buffer)
{
    if(m_scanner) {
        ::LexerDestroy(&m_scanner);
    }
    if(!buffer.empty()) {
        m_buffer = buffer;
        m_scanner = ::LexerNew(buffer, 0);
    }
}

bool CxxTokenizer::ReadUntilClosingBracket(int delim, wxString& bufferRead)
{
    CxxLexerToken tok;
    int depth = 0;
    while(NextToken(tok)) {
        if(IsInPreProcessorSection()) {
            // pre-processor tokens
            continue;
        }
        switch(tok.GetType()) {
        case '<':
        case '(':
        case '[':
        case '{':
            depth++;
            bufferRead << tok.GetWXString() << " ";
            break;
        case '>':
        case ')':
        case ']':
        case '}':
            depth--;
            bufferRead << tok.GetWXString() << " ";
            if((tok.GetType() == delim) && (depth == 0)) {
                ::LexerUnget(m_scanner);
                return true;
            }
            break;
        default:
            bufferRead << tok.GetWXString() << " ";
            break;
        }
    }
    return false;
}

int CxxTokenizer::PeekToken(wxString& text)
{
    CxxLexerToken tok;
    if(!NextToken(tok)) {
        return false;
    }
    text = tok.GetWXString();
    int type = tok.GetType();
    ::LexerUnget(m_scanner);
    return type;
}

wxString CxxTokenizer::GetVisibleScope(const wxString& inputString)
{
    std::stack<wxString> scopes;
    Reset(inputString);

    CxxLexerToken token;
    wxString currentScope;
    int parenthesisDepth = 0;
    int state = SCP_STATE_NORMAL;
    CppLexerUserData* scannerData = GetUserData();
    while(NextToken(token)) {
        // Skip pre-processor block
        if(scannerData && scannerData->IsInPreProcessorSection()) {
            continue;
        }
        switch(state) {
        case SCP_STATE_NORMAL:
            switch(token.GetType()) {
            case T_PP_STATE_EXIT:
                break;
            case '{':
                currentScope << "{";
                scopes.push(currentScope);
                currentScope.clear();
                break;
            case '}':
                if(scopes.empty())
                    return ""; // Invalid braces count
                currentScope = scopes.top();
                scopes.pop();
                currentScope << "} ";
                break;
            case T_IF:
                state = SCP_STATE_IN_IF;
                currentScope << " if ";
                break;
            case T_WHILE:
                state = SCP_STATE_IN_WHILE;
                currentScope << " while ";
                break;
            case T_FOR:
                state = SCP_STATE_IN_FOR_NO_SEMICOLON;
                currentScope << ";";
                break;
            case T_CATCH:
                state = SCP_STATE_IN_CATCH;
                currentScope << ";";
                break;
            case '(':
                parenthesisDepth++;
                currentScope << "(";
                // Handle lambda
                // If we are enterting lamda function defenition, collect the locals
                // this is exactly what we in 'catch' hence the state change to SCP_STATE_IN_CATCH
                if(GetLastToken().GetType() == ']') {
                    state = SCP_STATE_IN_CATCH;
                }
                break;
            case ')':
                parenthesisDepth--;
                currentScope << ")";
                break;
            default:
                if(parenthesisDepth == 0) {
                    currentScope << " " << token.GetWXString();
                }
                break;
            }
            break;
        case SCP_STATE_IN_WHILE:
        case SCP_STATE_IN_IF:
            switch(token.GetType()) {
            case '(':
                parenthesisDepth++;
                currentScope << "(";
                break;
            case ')':
                parenthesisDepth--;
                currentScope << ")";
                if(parenthesisDepth == 0) {
                    state = SCP_STATE_NORMAL;
                }
                break;
            }
            break;
        case SCP_STATE_IN_FOR_NO_SEMICOLON:
            switch(token.GetType()) {
            case '(':
                parenthesisDepth++;
                currentScope << "(";
                break;
            case ')':
                parenthesisDepth--;
                currentScope << ")";
                if(parenthesisDepth == 0) {
                    state = SCP_STATE_NORMAL;
                }
                break;
            case ';':
                currentScope << ";";
                state = SCP_STATE_IN_FOR;
                break;
            default:
                currentScope << " " << token.GetWXString();
                break;
            }
            break;
        case SCP_STATE_IN_FOR:
            switch(token.GetType()) {
            case '(':
                parenthesisDepth++;
                currentScope << "(";
                break;
            case ')':
                parenthesisDepth--;
                currentScope << ")";
                if(parenthesisDepth == 0) {
                    state = SCP_STATE_NORMAL;
                }
                break;
            default:
                break;
            }
            break;
        case SCP_STATE_IN_CATCH:
            switch(token.GetType()) {
            case '(':
                currentScope << "(";
                parenthesisDepth++;
                break;
            case ')':
                parenthesisDepth--;
                currentScope << ")";
                if(parenthesisDepth == 0) {
                    state = SCP_STATE_NORMAL;
                }
                break;
            default:
                currentScope << " " << token.GetWXString();
                break;
            }
            break;
        default:
            break;
        }
    }

    wxString s;
    while(!scopes.empty()) {
        s.Prepend(scopes.top());
        scopes.pop();
    }
    s << currentScope;
    return s;
}

CppLexerUserData* CxxTokenizer::GetUserData() const
{
    if(!m_scanner)
        return NULL;
    return ::LexerGetUserData(m_scanner);
}

bool CxxTokenizer::IsInPreProcessorSection() const
{
    if(!GetUserData())
        return false;
    return GetUserData()->IsInPreProcessorSection();
}

void CxxTokenizer::read_until_find(CxxLexerToken& token, int type_1, int type_2, int* what_was_found,
                                   wxString* consumed)
{
    int depth = 0;
    consumed->clear();
    *what_was_found = 0;
    consumed->reserve(256); // 256 bytes should be enough for most cases

    while(NextToken(token)) {
        if(depth == 0 && token.GetType() == type_1) {
            *what_was_found = type_1;
            consumed->Trim().Trim(false);
            return;
        } else if(depth == 0 && token.GetType() == type_2) {
            *what_was_found = type_2;
            consumed->Trim().Trim(false);
            return;
        }

        if(token.is_keyword() || token.is_builtin_type()) {
            consumed->Append(token.GetWXString() + " ");
            continue;
        } else if(token.is_pp_keyword()) {
            continue;
        }

        // append it
        consumed->Append(token.GetWXString());
        switch(token.GetType()) {
        case '<':
        case '{':
        case '[':
        case '(':
            depth++;
            break;
        case '>':
        case '}':
        case ']':
        case ')':
            depth--;
            break;
        default:
            break;
        }
    }

    // eof
    consumed->Trim().Trim(false);
}