File: stringsearcher.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 (304 lines) | stat: -rw-r--r-- 9,878 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
//////////////////////////////////////////////////////////////////////////////
//////////////////////////////////////////////////////////////////////////////
//
// copyright            : (C) 2008 by Eran Ifrah
// file name            : stringsearcher.cpp
//
// -------------------------------------------------------------------------
// A
//              _____           _      _     _ _
//             /  __ \         | |    | |   (_) |
//             | /  \/ ___   __| | ___| |    _| |_ ___
//             | |    / _ \ / _  |/ _ \ |   | | __/ _ )
//             | \__/\ (_) | (_| |  __/ |___| | ||  __/
//              \____/\___/ \__,_|\___\_____/_|\__\___|
//
//                                                  F i l e
//
//    This program is free software; you can redistribute it and/or modify
//    it under the terms of the GNU General Public License as published by
//    the Free Software Foundation; either version 2 of the License, or
//    (at your option) any later version.
//
//////////////////////////////////////////////////////////////////////////////
//////////////////////////////////////////////////////////////////////////////
#include "stringsearcher.h"

#include "globals.h"
#include "search_thread.h"

#include <algorithm>
#include <string>
#include <wx/regex.h>

static std::wstring Reverse(const std::wstring& str)
{
    // reverse the string content
    std::wstring tmp;
    tmp.reserve(str.length());

    std::wstring::const_reverse_iterator riter = str.rbegin();
    for(; riter != str.rend(); riter++) {
        tmp += *riter;
    }
    return tmp;
}

wxString StringFindReplacer::GetString(const wxString& input, int from, bool search_up)
{
    if(from < 0) {
        from = 0;
    }

    if(!search_up) {

        if(from >= (int)input.Len()) {
            return wxEmptyString;
        }
        return input.Mid((size_t)from);

    } else {
        if(from >= (int)input.Len()) {
            from = (int)input.Len();
        }
        return input.Mid(0, (size_t)from);
    }
}

bool StringFindReplacer::DoWildcardSearch(const wxString& input, int startOffset, const wxString& find_what,
                                          size_t flags, int& pos, int& matchLen)
{
    // Conver the wildcard to regex
    wxString regexPattern = find_what;

    // Escape braces
    regexPattern.Replace("(", "\\(");
    regexPattern.Replace(")", "\\)");
    regexPattern.Replace("[", "\\[");
    regexPattern.Replace("]", "\\]");
    regexPattern.Replace("{", "\\{");
    regexPattern.Replace("}", "\\}");

    // Covnert match syntax to regular expression
    regexPattern.Replace("?", "."); // Any character
    regexPattern.Replace("*",
                         "[^\\n]*?"); // Non greedy wildcard '*', but don't allow matches to go beyond a single line

    return DoRESearch(input, startOffset, regexPattern, flags, pos, matchLen);
}

bool StringFindReplacer::DoRESearch(const wxString& input, int startOffset, const wxString& find_what, size_t flags,
                                    int& pos, int& matchLen)
{
    wxString str = GetString(input, startOffset, flags & wxSD_SEARCH_BACKWARD ? true : false);
    if(str.IsEmpty()) {
        return false;
    }

#ifndef __WXMAC__
    int re_flags = wxRE_ADVANCED;
#else
    int re_flags = wxRE_DEFAULT;
#endif
    wxRegEx re;
    bool matchCase = flags & wxSD_MATCHCASE ? true : false;
    if(!matchCase)
        re_flags |= wxRE_ICASE;
    re_flags |= wxRE_NEWLINE; // Handle \n as a special character
    re.Compile(find_what, re_flags);

    // incase we are scanning NOT backwared, set the offset
    if(!(flags & wxSD_SEARCH_BACKWARD)) {
        pos = startOffset;
    }

    if(re.IsValid()) {
        if(flags & wxSD_SEARCH_BACKWARD) {
            size_t start(0), len(0);
            bool matched(false);

            // get the last match
            while(re.Matches(str)) {
                re.GetMatch(&start, &len);
                if(len == 0) {
                    matched = false;
                    break;
                }
                pos += start;
                if(matched) {
                    pos += matchLen;
                }
                matchLen = len;
                matched = true;
                str = str.Mid(start + len);
            }

            if(matched) {
                return true;
            }

        } else if(re.Matches(str)) {
            size_t start, len;
            re.GetMatch(&start, &len);
            pos += start;
            matchLen = len;
            return true;
        }
    }
    return false;
}

bool StringFindReplacer::DoSimpleSearch(const wchar_t* pinput, int startOffset, const wchar_t* pfind_what, size_t flags,
                                        int& pos, int& matchLen)
{
#if wxVERSION_NUMBER >= 2900
    std::wstring input(pinput);
    std::wstring find_what(pfind_what);

    int from = startOffset;
    if(from < 0) {
        from = 0;
    }
    std::wstring str;
    bool search_up = flags & wxSD_SEARCH_BACKWARD;
    if(!search_up) {

        if(from >= (int)input.length()) {
            str.clear();
            return false;
        }
        str = input.substr((size_t)from);

    } else {
        if(from >= (int)input.length()) {
            from = (int)input.length();
        }
        str = input.substr(0, (size_t)from);
    }
#else
    wxString input(pinput);
    wxString find_what(pfind_what);
    std::wstring str = GetString(pinput, startOffset, flags & wxSD_SEARCH_BACKWARD ? true : false).c_str();
#endif

    size_t init_size = str.length();

    if(str.empty()) {
        return false;
    }

    std::wstring find_str(find_what);
    size_t offset(0);

    // incase we are scanning backwared, revert the strings
    if(flags & wxSD_SEARCH_BACKWARD) {
        find_str = Reverse(find_str);
        str = Reverse(str);
    } else {
        offset = startOffset;
    }

    bool matchCase = flags & wxSD_MATCHCASE ? true : false;
    if(!matchCase) {
        std::transform(find_str.begin(), find_str.end(), find_str.begin(), towlower);
        std::transform(str.begin(), str.end(), str.begin(), towlower);
    }

    size_t upos = str.find(find_str);

    while(upos != std::wstring::npos) {
        if(flags & wxSD_MATCHWHOLEWORD) {
            // full word match
            // test that the characeter at upos - 1 & the character at upos + find_str.Len() are not
            // valid word char [a-zA-Z0-9_]
            if(upos > 0) {
                if(isalpha(str[upos - 1]) || isdigit(str[upos - 1]) || (int)str[upos - 1] == (int)'_') {
                    // remove the part that already been scanned
                    // and search again
                    str = str.substr(upos + find_what.length());
                    offset += upos + find_what.length();
                    upos = str.find(find_str);
                    continue;
                }
            }
            int charAfterOff = upos + find_str.length();
            if(charAfterOff < (int)str.length()) {
                if(isalpha(str[charAfterOff]) || isdigit(str[charAfterOff]) || (int)str[charAfterOff] == (int)'_') {
                    // remove the part that already been scanned
                    // and search again
                    str = str.substr(upos + find_what.length());
                    offset += upos + find_what.length();
                    upos = str.find(find_str);
                    continue;
                }
            }

            matchLen = (int)find_str.length();
            // mirror the result as well
            if(flags & wxSD_SEARCH_BACKWARD) {
                upos = (init_size - (upos + offset + matchLen));
            } else {
                upos += offset;
            }
            pos = (int)upos;
            return true;
        } else {
            // we got a match
            matchLen = (int)find_str.length();
            if(flags & wxSD_SEARCH_BACKWARD) {
                upos = (init_size - (upos + offset + matchLen));
            } else {
                upos += offset;
            }
            pos = (int)upos;
            return true;
        }
    }
    return false;
}

bool StringFindReplacer::Search(const wchar_t* input, int startOffset, const wchar_t* find_what, size_t flags, int& pos,
                                int& matchLen, int& posInChars, int& matchLenInChars)
{
    // adjust startOffset due to it is in bytes but should be in chars
    int iSO = startOffset;
    bool isUTF8 = false;
    if(iSO) {
        int utfLen = clUTF8Length(input, iSO);
        isUTF8 = (utfLen != iSO);
    }

    while(isUTF8 && (iSO > 0) && ((int)clUTF8Length(input, iSO) > startOffset))
        iSO--;
    startOffset = iSO;

    bool bResult = false;
    if(flags & wxSD_WILDCARD) {
        bResult = DoWildcardSearch(input, startOffset, find_what, flags, posInChars, matchLenInChars);
        flags |= wxSD_REGULAREXPRESSION;

    } else if(flags & wxSD_REGULAREXPRESSION) {
        bResult = DoRESearch(input, startOffset, find_what, flags, posInChars, matchLenInChars);

    } else {
        bResult = DoSimpleSearch(input, startOffset, find_what, flags, posInChars, matchLenInChars);
    }

    // correct search Pos and Length owing to non plain ASCII multibyte characters
    if(bResult) {
        pos = clUTF8Length(input, posInChars);
        if(flags & wxSD_REGULAREXPRESSION) {
            matchLen = clUTF8Length(input, posInChars + matchLenInChars) - pos;
        } else {
            matchLen = clUTF8Length(find_what, matchLenInChars);
        }
    }
    return bResult;
}

bool StringFindReplacer::Search(const wchar_t* input, int startOffset, const wchar_t* find_what, size_t flags, int& pos,
                                int& matchLen)
{
    int posInChars(0), matchLenInChars(0);
    return StringFindReplacer::Search(input, startOffset, find_what, flags, pos, matchLen, posInChars, matchLenInChars);
}