diff options
Diffstat (limited to 'utility/NaiveTokenizer.cpp')
-rw-r--r-- | utility/NaiveTokenizer.cpp | 62 |
1 files changed, 62 insertions, 0 deletions
diff --git a/utility/NaiveTokenizer.cpp b/utility/NaiveTokenizer.cpp new file mode 100644 index 0000000..320fec0 --- /dev/null +++ b/utility/NaiveTokenizer.cpp @@ -0,0 +1,62 @@ +/* + * Copyright (c) 2011-2014, Intel Corporation + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without modification, + * are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright notice, this + * list of conditions and the following disclaimer. + * + * 2. 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. + * + * 3. Neither the name of the copyright holder nor the names of its contributors + * may be used to endorse or promote products derived from this software without + * specific prior written permission. + * + * 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 HOLDER 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. + */ +#include "NaiveTokenizer.h" +#include <cstring> + +char* NaiveTokenizer::getNextToken(char** line) +{ + const char *quotes = "'\""; // single or double quotes + char separator[2] = " "; + char first[2]; + + if (*line == NULL || (*line)[0] == '\0') { + return NULL; + } + + // Copy the first character into its own new string + first[0] = (*line)[0]; + first[1] = '\0'; + + // Check if the first character is a quote + if (strstr(quotes, first) != NULL) { + // If so, move forward and set the separator to that quote + (*line)++; + strncpy(separator, first, sizeof(separator)); + } + // If it is not, get the next space-delimited token + // First, move the cursor forward if the first character is a space + // This effectively ignores multiple spaces in a row + else if (strstr(separator, first) != NULL) { + (*line)++; + return NaiveTokenizer::getNextToken(line); + } + + return strsep(line, separator); +} |