encoding-check.cpp File Reference

#include <vector>
#include <iostream>
#include <fstream>
#include <cstdlib>

Include dependency graph for encoding-check.cpp:

Go to the source code of this file.

Functions
unsigned char *	utf8_check (unsigned char *s)
int	main (int argc, char const *argv[])

Function Documentation

main()

int main	(	int	argc,
		char const *	argv[]
	)

{
    if (argc != 3) {
        std::cerr << "Usage: " << argv[0] << " <program/library> <file>" << std::endl;
        return -1;
    }
 
    const char* target = argv[1];
    const char* filename = argv[2];
 
    const auto error_exit = [=](const char* error) {
        std::cerr << "\n\tError: " << error << ": " << filename << "\n"
            << "\tTarget: " << target << "\n"
            << std::endl;
        std::exit(-2);
    };
 
    std::ifstream file(filename, std::ios::binary | std::ios::ate);
    const auto size = file.tellg();
 
    if (size == 0) {
        return 0;
    }
 
    file.seekg(0, std::ios::beg);
    std::vector<char> buffer(size);
 
    if (file.read(buffer.data(), size)) {
        buffer.push_back('\0');
 
        // Check UTF-8 validity
        if (utf8_check(reinterpret_cast<unsigned char*>(buffer.data())) != nullptr) {
            error_exit("Source file does not contain (valid) UTF-8");
        }
 
        // Check against a BOM mark
        if (buffer.size() >= 3
            && buffer[0] == '\xef'
            && buffer[1] == '\xbb'
            && buffer[2] == '\xbf') {
            error_exit("Source file is valid UTF-8 but contains a BOM mark");
        }
    } else {
        error_exit("Could not read source file");
    }
 
    return 0;
}

References error, and utf8_check().

Here is the call graph for this function:

utf8_check()

unsigned char * utf8_check

(

unsigned char *

s

)

{
    while (*s) {
        if (*s < 0x80) {
            // 0xxxxxxx
            s++;
        } else if ((s[0] & 0xe0) == 0xc0) {
            // 110xxxxx 10xxxxxx
            if ((s[1] & 0xc0) != 0x80 ||
                (s[0] & 0xfe) == 0xc0) {         // overlong?
                return s;
            } else {
                s += 2;
            }
        } else if ((s[0] & 0xf0) == 0xe0) {
            // 1110xxxx 10xxxxxx 10xxxxxx
            if ((s[1] & 0xc0) != 0x80 ||
                (s[2] & 0xc0) != 0x80 ||
                (s[0] == 0xe0 && (s[1] & 0xe0) == 0x80) || // overlong?
                (s[0] == 0xed && (s[1] & 0xe0) == 0xa0) || // surrogate?
                (s[0] == 0xef && s[1] == 0xbf &&
                (s[2] & 0xfe) == 0xbe)) {                  // U+FFFE or U+FFFF?
                return s;
            } else {
                s += 3;
            }
        } else if ((s[0] & 0xf8) == 0xf0) {
            // 11110xxX 10xxxxxx 10xxxxxx 10xxxxxx
            if ((s[1] & 0xc0) != 0x80 ||
                (s[2] & 0xc0) != 0x80 ||
                (s[3] & 0xc0) != 0x80 ||
                (s[0] == 0xf0 && (s[1] & 0xf0) == 0x80) ||      // overlong?
                (s[0] == 0xf4 && s[1] > 0x8f) || s[0] > 0xf4) { // > U+10FFFF?
                return s;
            } else {
                s += 4;
            }
        } else {
            return s;
        }
    }
 
    return NULL;
}

Referenced by main().

Here is the caller graph for this function: