Last active
August 29, 2015 14:01
-
-
Save yaraki/8d5356c530c7c2c2796a to your computer and use it in GitHub Desktop.
S-expression lexer in C++11
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#include <iostream> | |
#include <sstream> | |
namespace ya { | |
void each_token(std::istream& input, void (*proc)(const std::string& token)) | |
{ | |
std::stringstream buffer; | |
auto send = [&buffer, &proc]() { | |
if (0 < buffer.tellp()) { | |
proc(buffer.str()); | |
buffer.str(""); | |
return true; | |
} | |
return false; | |
}; | |
while (!input.eof()) { | |
char c = input.get(); | |
switch (c) { | |
case EOF: | |
case ' ': | |
case '\r': | |
case '\n': | |
case '\t': | |
case '\v': | |
send(); | |
break; | |
case '(': | |
case ')': | |
case '[': | |
case ']': | |
case '\'': | |
case '`': | |
if (send()) { | |
input.unget(); | |
} else { | |
buffer << c; | |
send(); | |
} | |
break; | |
case ',': | |
if (send()) { | |
input.unget(); | |
} else { | |
buffer << c; | |
if ('@' == input.peek()) { | |
buffer << (char) input.get(); | |
} | |
send(); | |
} | |
break; | |
case '\"': | |
if (send()) { | |
input.unget(); | |
} else { | |
buffer << c; | |
bool escaped = false; | |
while (!input.eof()) { | |
char c = input.get(); | |
buffer << c; | |
if (!escaped && c == '"') { | |
send(); | |
break; | |
} else if (c == '\\') { | |
escaped = true; | |
} else { | |
escaped = false; | |
} | |
} | |
} | |
break; | |
default: | |
buffer << c; | |
break; | |
} | |
} | |
send(); | |
} | |
} | |
int main() | |
{ | |
std::stringstream input("`(a ,b ,@(c) \"d e\")"); | |
ya::each_token(input, [](const std::string& token) { | |
std::cout << token << std::endl; | |
}); | |
return 0; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment