static unsigned char utf16_literal_to_utf8()

in BalancingRobot/Software/HighLevelApp/MutableStorageKVP/cJSON.c [578:696]

• 84 lines of code
• 16 McCabe index (conditional complexity)

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
    {
        sequence_length = 6; /* \uXXXX */
        codepoint = first_code;
    }

    /* encode as UTF-8
     * takes at maximum 4 bytes to encode:
     * 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx */
    if (codepoint < 0x80)
    {
        /* normal ascii, encoding 0xxxxxxx */
        utf8_length = 1;
    }
    else if (codepoint < 0x800)
    {
        /* two bytes, encoding 110xxxxx 10xxxxxx */
        utf8_length = 2;
        first_byte_mark = 0xC0; /* 11000000 */
    }
    else if (codepoint < 0x10000)
    {
        /* three bytes, encoding 1110xxxx 10xxxxxx 10xxxxxx */
        utf8_length = 3;
        first_byte_mark = 0xE0; /* 11100000 */
    }
    else if (codepoint <= 0x10FFFF)
    {
        /* four bytes, encoding 1110xxxx 10xxxxxx 10xxxxxx 10xxxxxx */
        utf8_length = 4;
        first_byte_mark = 0xF0; /* 11110000 */
    }
    else
    {
        /* invalid unicode codepoint */
        goto fail;
    }

    /* encode as utf8 */
    for (utf8_position = (unsigned char)(utf8_length - 1); utf8_position > 0; utf8_position--)
    {
        /* 10xxxxxx */
        (*output_pointer)[utf8_position] = (unsigned char)((codepoint | 0x80) & 0xBF);
        codepoint >>= 6;
    }
    /* encode first byte */
    if (utf8_length > 1)
    {
        (*output_pointer)[0] = (unsigned char)((codepoint | first_byte_mark) & 0xFF);
    }
    else
    {
        (*output_pointer)[0] = (unsigned char)(codepoint & 0x7F);
    }

    *output_pointer += utf8_length;

    return sequence_length;

fail:
    return 0;
}