Function utf16_literal_to_utf8

cJSON.c:698–816

converts a UTF-16 literal to UTF-8 * A literal can be one or two sequences of the form \uXXXX */

/* converts a UTF-16 literal to UTF-8
 * A literal can be one or two sequences of the form \uXXXX */
static unsigned char utf16_literal_to_utf8(const unsigned char * const input_pointer, const unsigned char * const input_end, unsigned char **output_pointer)
{
    long unsigned int codepoint = 0;
    unsigned int first_code = 0;
    const unsigned char *first_sequence = input_pointer;
    unsigned char utf8_length = 0;
    unsigned char utf8_position = 0;
    unsigned char sequence_length = 0;
    unsigned char first_byte_mark = 0;

    if ((input_end - first_sequence) < 6)
    {
        /* input ends unexpectedly */
        goto fail;
    }

    /* get the first utf16 sequence */
    first_code = parse_hex4(first_sequence + 2);

    /* check that the code is valid */
    if (((first_code >= 0xDC00) && (first_code <= 0xDFFF)))
    {
        goto fail;
    }

    /* UTF16 surrogate pair */
    if ((first_code >= 0xD800) && (first_code <= 0xDBFF))
    {
        const unsigned char *second_sequence = first_sequence + 6;
        unsigned int second_code = 0;
        sequence_length = 12; /* \uXXXX\uXXXX */

        if ((input_end - second_sequence) < 6)
        {
            /* input ends unexpectedly */
            goto fail;
        }

        if ((second_sequence[0] != '\\') || (second_sequence[1] != 'u'))
        {
            /* missing second half of the surrogate pair */
            goto fail;
        }

        /* get the second utf16 sequence */
        second_code = parse_hex4(second_sequence + 2);
        /* check that the code is valid */
        if ((second_code < 0xDC00) || (second_code > 0xDFFF))
        {
            /* invalid second half of the surrogate pair */
            goto fail;
        }


        /* calculate the unicode codepoint from the surrogate pair */
        codepoint = 0x10000 + (((first_code & 0x3FF) << 10) | (second_code & 0x3FF));
    }
    else