Last active
August 29, 2015 14:06
-
-
Save m0r13/89638b6e2421a1929b97 to your computer and use it in GitHub Desktop.
This file contains hidden or 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 <cctype> | |
| #include <iostream> | |
| #include <sstream> | |
| std::string convertUnicodeLiteral(std::string literal) { | |
| // if (!util::startswith(escape, "\\u") ... | |
| literal = literal.substr(2); | |
| std::stringstream ss; | |
| ss << std::hex << literal/*.substr(0, 4)*/; | |
| unsigned int ord; | |
| ss >> ord; | |
| std::cout << "ord " << literal << " = " << ord << std::endl; | |
| std::string str; | |
| if (ord <= 0x7f) | |
| str += (char) ord; | |
| else if (ord <= 0x7ff) { | |
| str += (char) (0b11000000 | (ord >> 6)); | |
| str += (char) (0b10000000 | (ord & 0b00111111)); | |
| } else if (ord <= 0xffff) { | |
| str += (char) (0b11100000 | (ord >> 12)); | |
| str += (char) (0b10000000 | ((ord >> 6) & 0b00111111)); | |
| str += (char) (0b10000000 | (ord & 0b00111111)); | |
| } else if (ord <= 0x1fffff) { | |
| str += (char) (0b11110000 | (ord >> 18)); | |
| str += (char) (0b10000000 | ((ord >> 12) & 0b00111111)); | |
| str += (char) (0b10000000 | ((ord >> 6) & 0b00111111)); | |
| str += (char) (0b10000000 | (ord & 0b00111111)); | |
| } else if (ord <= 0x3ffffff) { | |
| str += (char) (0b11111000 | (ord >> 24)); | |
| str += (char) (0b10000000 | ((ord >> 18) & 0b00111111)); | |
| str += (char) (0b10000000 | ((ord >> 12) & 0b00111111)); | |
| str += (char) (0b10000000 | ((ord >> 6) & 0b00111111)); | |
| str += (char) (0b10000000 | (ord & 0b00111111)); | |
| } else if (ord <= 0x7fffffff) { | |
| str += (char) (0b11111100 | (ord >> 30)); | |
| str += (char) (0b10000000 | ((ord >> 24) & 0b00111111)); | |
| str += (char) (0b10000000 | ((ord >> 18) & 0b00111111)); | |
| str += (char) (0b10000000 | ((ord >> 12) & 0b00111111)); | |
| str += (char) (0b10000000 | ((ord >> 6) & 0b00111111)); | |
| str += (char) (0b10000000 | (ord & 0b00111111)); | |
| } | |
| return str; | |
| } | |
| std::string replaceUnicodeEscapes(std::string str) { | |
| } | |
| void compare(std::string chr, std::string literal) { | |
| std::cout << "---" << std::endl; | |
| std::cout << "testing " << literal << " = " << chr << std::endl; | |
| std::cout << "chr len " << chr.size() << " " << chr << std::endl; | |
| std::string chr_converted = convertUnicodeLiteral(literal); | |
| std::cout << "literal len " << chr_converted.size() << " " << chr_converted << std::endl; | |
| if (chr != chr_converted) { | |
| std::cout << "ERROR!" << std::endl; | |
| } | |
| std::cout << "---" << std::endl; | |
| } | |
| int main() { | |
| compare("\u0024", "\\u0024"); | |
| compare("\u00a2", "\\u00a2"); | |
| compare("\u20ac", "\\u20ac"); | |
| compare("\u07ff", "\\u7ff"); | |
| compare("\uffff", "\\uffff"); | |
| compare(u8"\U001fffff", "\\u1fffff"); | |
| compare(u8"\U03ffffff", "\\u3ffffff"); | |
| compare(u8"\U7fffffff", "\\u7fffffff"); | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment