summaryrefslogtreecommitdiff
path: root/src/mesh/assimp-master/code/AssetLib/FBX/FBXTokenizer.cpp
blob: 8698abac624dbc020e2e346ddad391f3f1b5bb4e (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
/*
Open Asset Import Library (assimp)
----------------------------------------------------------------------

Copyright (c) 2006-2022, assimp team


All rights reserved.

Redistribution and use of this software in source and binary forms,
with or without modification, are permitted provided that the
following conditions are met:

* Redistributions of source code must retain the above
  copyright notice, this list of conditions and the
  following disclaimer.

* Redistributions in binary form must reproduce the above
  copyright notice, this list of conditions and the
  following disclaimer in the documentation and/or other
  materials provided with the distribution.

* Neither the name of the assimp team, nor the names of its
  contributors may be used to endorse or promote products
  derived from this software without specific prior
  written permission of the assimp team.

THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

----------------------------------------------------------------------
*/

/** @file  FBXTokenizer.cpp
 *  @brief Implementation of the FBX broadphase lexer
 */

#ifndef ASSIMP_BUILD_NO_FBX_IMPORTER

// tab width for logging columns
#define ASSIMP_FBX_TAB_WIDTH 4

#include <assimp/ParsingUtils.h>

#include "FBXTokenizer.h"
#include "FBXUtil.h"
#include <assimp/Exceptional.h>
#include <assimp/DefaultLogger.hpp>

namespace Assimp {
namespace FBX {

// ------------------------------------------------------------------------------------------------
Token::Token(const char* sbegin, const char* send, TokenType type, unsigned int line, unsigned int column)
    :
#ifdef DEBUG
    contents(sbegin, static_cast<size_t>(send-sbegin)),
#endif
    sbegin(sbegin)
    , send(send)
    , type(type)
    , line(line)
    , column(column)
{
    ai_assert(sbegin);
    ai_assert(send);

    // tokens must be of non-zero length
    ai_assert(static_cast<size_t>(send-sbegin) > 0);
}

// ------------------------------------------------------------------------------------------------
Token::~Token()
{
}

namespace {

// ------------------------------------------------------------------------------------------------
// signal tokenization error, this is always unrecoverable. Throws DeadlyImportError.
AI_WONT_RETURN void TokenizeError(const std::string& message, unsigned int line, unsigned int column) AI_WONT_RETURN_SUFFIX;
AI_WONT_RETURN void TokenizeError(const std::string& message, unsigned int line, unsigned int column)
{
    throw DeadlyImportError("FBX-Tokenize", Util::GetLineAndColumnText(line,column), message);
}


// process a potential data token up to 'cur', adding it to 'output_tokens'.
// ------------------------------------------------------------------------------------------------
void ProcessDataToken( TokenList& output_tokens, const char*& start, const char*& end,
                      unsigned int line,
                      unsigned int column,
                      TokenType type = TokenType_DATA,
                      bool must_have_token = false)
{
    if (start && end) {
        // sanity check:
        // tokens should have no whitespace outside quoted text and [start,end] should
        // properly delimit the valid range.
        bool in_double_quotes = false;
        for (const char* c = start; c != end + 1; ++c) {
            if (*c == '\"') {
                in_double_quotes = !in_double_quotes;
            }

            if (!in_double_quotes && IsSpaceOrNewLine(*c)) {
                TokenizeError("unexpected whitespace in token", line, column);
            }
        }

        if (in_double_quotes) {
            TokenizeError("non-terminated double quotes", line, column);
        }

        output_tokens.push_back(new_Token(start,end + 1,type,line,column));
    }
    else if (must_have_token) {
        TokenizeError("unexpected character, expected data token", line, column);
    }

    start = end = nullptr;
}

}

// ------------------------------------------------------------------------------------------------
void Tokenize(TokenList& output_tokens, const char* input)
{
	ai_assert(input);
	ASSIMP_LOG_DEBUG("Tokenizing ASCII FBX file");

    // line and column numbers numbers are one-based
    unsigned int line = 1;
    unsigned int column = 1;

    bool comment = false;
    bool in_double_quotes = false;
    bool pending_data_token = false;

    const char *token_begin = nullptr, *token_end = nullptr;
    for (const char* cur = input;*cur;column += (*cur == '\t' ? ASSIMP_FBX_TAB_WIDTH : 1), ++cur) {
        const char c = *cur;

        if (IsLineEnd(c)) {
            comment = false;

            column = 0;
            ++line;
        }

        if(comment) {
            continue;
        }

        if(in_double_quotes) {
            if (c == '\"') {
                in_double_quotes = false;
                token_end = cur;

                ProcessDataToken(output_tokens,token_begin,token_end,line,column);
                pending_data_token = false;
            }
            continue;
        }

        switch(c)
        {
        case '\"':
            if (token_begin) {
                TokenizeError("unexpected double-quote", line, column);
            }
            token_begin = cur;
            in_double_quotes = true;
            continue;

        case ';':
            ProcessDataToken(output_tokens,token_begin,token_end,line,column);
            comment = true;
            continue;

        case '{':
            ProcessDataToken(output_tokens,token_begin,token_end, line, column);
            output_tokens.push_back(new_Token(cur,cur+1,TokenType_OPEN_BRACKET,line,column));
            continue;

        case '}':
            ProcessDataToken(output_tokens,token_begin,token_end,line,column);
            output_tokens.push_back(new_Token(cur,cur+1,TokenType_CLOSE_BRACKET,line,column));
            continue;

        case ',':
            if (pending_data_token) {
                ProcessDataToken(output_tokens,token_begin,token_end,line,column,TokenType_DATA,true);
            }
            output_tokens.push_back(new_Token(cur,cur+1,TokenType_COMMA,line,column));
            continue;

        case ':':
            if (pending_data_token) {
                ProcessDataToken(output_tokens,token_begin,token_end,line,column,TokenType_KEY,true);
            }
            else {
                TokenizeError("unexpected colon", line, column);
            }
            continue;
        }

        if (IsSpaceOrNewLine(c)) {

            if (token_begin) {
                // peek ahead and check if the next token is a colon in which
                // case this counts as KEY token.
                TokenType type = TokenType_DATA;
                for (const char* peek = cur;  *peek && IsSpaceOrNewLine(*peek); ++peek) {
                    if (*peek == ':') {
                        type = TokenType_KEY;
                        cur = peek;
                        break;
                    }
                }

                ProcessDataToken(output_tokens,token_begin,token_end,line,column,type);
            }

            pending_data_token = false;
        }
        else {
            token_end = cur;
            if (!token_begin) {
                token_begin = cur;
            }

            pending_data_token = true;
        }
    }
}

} // !FBX
} // !Assimp

#endif