summaryrefslogtreecommitdiff
path: root/src/mongo/util/text.cpp
blob: 5c3693901d14b811c551acbb4a7a7097e542c8ed (plain)
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
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
// text.cpp

/*    Copyright 2009 10gen Inc.
 *
 *    This program is free software: you can redistribute it and/or  modify
 *    it under the terms of the GNU Affero General Public License, version 3,
 *    as published by the Free Software Foundation.
 *
 *    This program is distributed in the hope that it will be useful,
 *    but WITHOUT ANY WARRANTY; without even the implied warranty of
 *    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 *    GNU Affero General Public License for more details.
 *
 *    You should have received a copy of the GNU Affero General Public License
 *    along with this program.  If not, see <http://www.gnu.org/licenses/>.
 *
 *    As a special exception, the copyright holders give permission to link the
 *    code of portions of this program with the OpenSSL library under certain
 *    conditions as described in each individual source file and distribute
 *    linked combinations including the program with the OpenSSL library. You
 *    must comply with the GNU Affero General Public License in all respects
 *    for all of the code used other than as permitted herein. If you modify
 *    file(s) with this exception, you may extend this exception to your
 *    version of the file(s), but you are not obligated to do so. If you do not
 *    wish to do so, delete this exception statement from your version. If you
 *    delete this exception statement from all source files in the program,
 *    then also delete it in the license file.
 */

#include "mongo/util/text.h"

#include <boost/integer_traits.hpp>
#include <boost/smart_ptr/scoped_array.hpp>
#include <errno.h>
#include <sstream>

#ifdef _WIN32
#include <io.h>
#endif

#include "mongo/platform/basic.h"
#include "mongo/util/mongoutils/str.h"

using namespace std;

namespace mongo {

    // --- StringSplitter ----

    /** get next split string fragment */
    string StringSplitter::next() {
        const char * foo = strstr( _big , _splitter );
        if ( foo ) {
            string s( _big , foo - _big );
            _big = foo + strlen( _splitter );
            while ( *_big && strstr( _big , _splitter ) == _big )
                _big++;
            return s;
        }
        
        string s = _big;
        _big += strlen( _big );
        return s;
    }


    void StringSplitter::split( vector<string>& l ) {
        while ( more() ) {
            l.push_back( next() );
        }
    }

    vector<string> StringSplitter::split() {
        vector<string> l;
        split( l );
        return l;
    }

    string StringSplitter::join( const vector<string>& l , const string& split ) {
        stringstream ss;
        for ( unsigned i=0; i<l.size(); i++ ) {
            if ( i > 0 )
                ss << split;
            ss << l[i];
        }
        return ss.str();
    }

    vector<string> StringSplitter::split( const string& big , const string& splitter ) {
        StringSplitter ss( big.c_str() , splitter.c_str() );
        return ss.split();
    }
    


    // --- utf8 utils ------

    inline int leadingOnes(unsigned char c) {
        if (c < 0x80) return 0;
        static const char _leadingOnes[128] = {
            1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 0x80 - 0x8F
            1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 0x90 - 0x99
            1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 0xA0 - 0xA9
            1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 0xB0 - 0xB9
            2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, // 0xC0 - 0xC9
            2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, // 0xD0 - 0xD9
            3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, // 0xE0 - 0xE9
            4, 4, 4, 4, 4, 4, 4, 4,                         // 0xF0 - 0xF7
            5, 5, 5, 5,             // 0xF8 - 0xFB
            6, 6,       // 0xFC - 0xFD
            7,    // 0xFE
            8, // 0xFF
        };
        return _leadingOnes[c & 0x7f];

    }

    bool isValidUTF8(const std::string& s) { 
        return isValidUTF8(s.c_str()); 
    }

    bool isValidUTF8(const char *s) {
        int left = 0; // how many bytes are left in the current codepoint
        while (*s) {
            const unsigned char c = (unsigned char) *(s++);
            const int ones = leadingOnes(c);
            if (left) {
                if (ones != 1) return false; // should be a continuation byte
                left--;
            }
            else {
                if (ones == 0) continue; // ASCII byte
                if (ones == 1) return false; // unexpected continuation byte
                if (c > 0xF4) return false; // codepoint too large (< 0x10FFFF)
                if (c == 0xC0 || c == 0xC1) return false; // codepoints <= 0x7F shouldn't be 2 bytes

                // still valid
                left = ones-1;
            }
        }
        if (left!=0) return false; // string ended mid-codepoint
        return true;
    }

    long long parseLL( const char *n ) {
        long long ret;
        uassert( 13307, "cannot convert empty string to long long", *n != 0 );
#if !defined(_WIN32)
        char *endPtr = 0;
        errno = 0;
        ret = strtoll( n, &endPtr, 10 );
        uassert( 13305, "could not convert string to long long", *endPtr == 0 && errno == 0 );
#elif _MSC_VER>=1600    // 1600 is VS2k10 1500 is VS2k8
        size_t endLen = 0;
        try {
            ret = stoll( n, &endLen, 10 );
        }
        catch ( ... ) {
            endLen = 0;
        }
        uassert( 13306, "could not convert string to long long", endLen != 0 && n[ endLen ] == 0 );
#else // stoll() wasn't introduced until VS 2010.
        char* endPtr = 0;
        ret = _strtoi64( n, &endPtr, 10 );
        uassert( 13310, "could not convert string to long long", (*endPtr == 0) && (ret != _I64_MAX) && (ret != _I64_MIN) );
#endif // !defined(_WIN32)
        return ret;
    }


#if defined(_WIN32)

    std::string toUtf8String(const std::wstring& wide) {
        if (wide.size() > boost::integer_traits<int>::const_max)
            throw std::length_error(
                "Wide string cannot be more than INT_MAX characters long.");
        if (wide.size() == 0)
            return "";

        // Calculate necessary buffer size
        int len = ::WideCharToMultiByte(
                      CP_UTF8, 0, wide.c_str(), static_cast<int>(wide.size()),
                      NULL, 0, NULL, NULL);

        // Perform actual conversion
        if (len > 0) {
            std::vector<char> buffer(len);
            len = ::WideCharToMultiByte(
                      CP_UTF8, 0, wide.c_str(), static_cast<int>(wide.size()),
                      &buffer[0], static_cast<int>(buffer.size()), NULL, NULL);
            if (len > 0) {
                verify(len == static_cast<int>(buffer.size()));
                return std::string(&buffer[0], buffer.size());
            }
        }

        msgasserted( 16091 ,
                     mongoutils::str::stream() << "can't wstring to utf8: " << ::GetLastError() );
        return "";
    }

    std::wstring toWideString(const char *utf8String) {
        int bufferSize = MultiByteToWideChar(
                CP_UTF8,            // Code page
                0,                  // Flags
                utf8String,         // Input string
                -1,                 // Count, -1 for NUL-terminated
                NULL,               // No output buffer
                0                   // Zero means "compute required size"
        );
        if ( bufferSize == 0 ) {
            return std::wstring();
        }
        boost::scoped_array< wchar_t > tempBuffer( new wchar_t[ bufferSize ] );
        tempBuffer[0] = 0;
        MultiByteToWideChar(
                CP_UTF8,            // Code page
                0,                  // Flags
                utf8String,         // Input string
                -1,                 // Count, -1 for NUL-terminated
                tempBuffer.get(),   // UTF-16 output buffer
                bufferSize          // Buffer size in wide characters
        );
        return std::wstring( tempBuffer.get() );
    }

    /**
     * Write a UTF-8 string to the Windows console in Unicode (UTF-16)
     *
     * @param utf8String        UTF-8 input string
     * @param utf8StringSize    Number of bytes in UTF-8 string, no NUL terminator assumed
     * @return                  true if all characters were displayed (including zero characters)
     */
    bool writeUtf8ToWindowsConsole( const char* utf8String, unsigned int utf8StringSize ) {
        int bufferSize = MultiByteToWideChar(
                CP_UTF8,            // Code page
                0,                  // Flags
                utf8String,         // Input string
                utf8StringSize,     // Input string length
                NULL,               // No output buffer
                0                   // Zero means "compute required size"
        );
        if ( bufferSize == 0 ) {
            return true;
        }
        boost::scoped_array<wchar_t> utf16String( new wchar_t[ bufferSize ] );
        MultiByteToWideChar(
                CP_UTF8,            // Code page
                0,                  // Flags
                utf8String,         // Input string
                utf8StringSize,     // Input string length
                utf16String.get(),  // UTF-16 output buffer
                bufferSize          // Buffer size in wide characters
        );
        const wchar_t* utf16Pointer = utf16String.get();
        size_t numberOfCharactersToWrite = bufferSize;
        HANDLE consoleHandle = GetStdHandle( STD_OUTPUT_HANDLE );
        while ( numberOfCharactersToWrite > 0 ) {
            static const DWORD MAXIMUM_CHARACTERS_PER_PASS = 8 * 1024;
            DWORD numberOfCharactersThisPass = static_cast<DWORD>( numberOfCharactersToWrite );
            if ( numberOfCharactersThisPass > MAXIMUM_CHARACTERS_PER_PASS ) {
                numberOfCharactersThisPass = MAXIMUM_CHARACTERS_PER_PASS;
            }
            DWORD numberOfCharactersWritten;
            BOOL success = WriteConsoleW( consoleHandle,
                                          utf16Pointer,
                                          numberOfCharactersThisPass,
                                          &numberOfCharactersWritten,
                                          NULL );
            if ( 0 == success ) {
                DWORD dosError = GetLastError();
                static bool errorMessageShown = false;
                if ( ERROR_GEN_FAILURE == dosError ) {
                    if ( ! errorMessageShown ) {
                        std::cout << "\n---\nUnicode text could not be correctly displayed.\n"
                                "Please change your console font to a Unicode font "
                                "(e.g. Lucida Console).\n---\n" << std::endl;
                        errorMessageShown = true;
                    }
                    // we can't display the text properly using a raster font,
                    // but we can display the bits that will display ...
                    _write( 1, utf8String, utf8StringSize );
                }
                return false;
            }
            numberOfCharactersToWrite -= numberOfCharactersWritten;
            utf16Pointer += numberOfCharactersWritten;
        }
        return true;
    }

    WindowsCommandLine::WindowsCommandLine(int argc, wchar_t* argvW[], wchar_t* envpW[]) :
            _argv(NULL), _envp(NULL) {

        // Construct UTF-8 copy of arguments
        vector<string> utf8args;
        vector<size_t> utf8argLength;
        size_t blockSize = argc * sizeof(char*);
        size_t blockPtr = blockSize;
        for (int i = 0; i < argc; ++i) {
            utf8args.push_back( toUtf8String(argvW[i]) );
            size_t argLength = utf8args[i].length() + 1;
            utf8argLength.push_back(argLength);
            blockSize += argLength;
        }
        _argv = static_cast<char**>(malloc(blockSize));
        for (int i = 0; i < argc; ++i) {
            _argv[i] = reinterpret_cast<char*>(_argv) + blockPtr;
            strcpy_s(_argv[i], utf8argLength[i], utf8args[i].c_str());
            blockPtr += utf8argLength[i];
        }

        // Construct UTF-8 copy of environment strings
        size_t envCount = 0;
        wchar_t** envpWptr = &envpW[0];
        while (*envpWptr++) {
            ++envCount;
        }
        vector<string> utf8envs;
        vector<size_t> utf8envLength;
        blockSize = (envCount + 1) * sizeof(char*);
        blockPtr = blockSize;
        for (size_t i = 0; i < envCount; ++i) {
            utf8envs.push_back( toUtf8String(envpW[i]) );
            size_t envLength = utf8envs[i].length() + 1;
            utf8envLength.push_back(envLength);
            blockSize += envLength;
        }
        _envp = static_cast<char**>(malloc(blockSize));
        size_t i;
        for (i = 0; i < envCount; ++i) {
            _envp[i] = reinterpret_cast<char*>(_envp) + blockPtr;
            strcpy_s(_envp[i], utf8envLength[i], utf8envs[i].c_str());
            blockPtr += utf8envLength[i];
        }
        _envp[i] = NULL;
    }

    WindowsCommandLine::~WindowsCommandLine() {
        free(_argv);
        free(_envp);
    }

#endif // #if defined(_WIN32)

    // See "Parsing C++ Command-Line Arguments (C++)"
    // http://msdn.microsoft.com/en-us/library/windows/desktop/17w5ykft(v=vs.85).aspx
    static void quoteForWindowsCommandLine(const std::string& arg, std::ostream& os) {
        if (arg.empty()) {
            os << "\"\"";
        }
        else if (arg.find_first_of(" \t\"") == std::string::npos) {
            os << arg;
        }
        else {
            os << '"';
            std::string backslashes = "";
            for (std::string::const_iterator iter = arg.begin(), end = arg.end();
                 iter != end; ++iter) {

                switch (*iter) {
                case '\\':
                    backslashes.push_back(*iter);
                    if (iter + 1 == end)
                        os << backslashes << backslashes;
                    break;
                case '"':
                    os << backslashes << backslashes << "\\\"";
                    break;
                default:
                    os << backslashes << *iter;
                    backslashes.clear();
                    break;
                }
            }
            os << '"';
        }
    }

    std::string constructUtf8WindowsCommandLine(const std::vector<std::string>& argv) {
        if (argv.empty())
            return "";

        std::ostringstream commandLine;
        std::vector<std::string>::const_iterator iter = argv.begin();
        std::vector<std::string>::const_iterator end = argv.end();
        quoteForWindowsCommandLine(*iter, commandLine);
        ++iter;
        for (; iter != end; ++iter) {
            commandLine << ' ';
            quoteForWindowsCommandLine(*iter, commandLine);
        }
        return commandLine.str();
    }
}