scan_string()

template<typename BasicJsonType , typename InputAdapterType >

token_type nlohmann::detail::lexer< BasicJsonType, InputAdapterType >::scan_string ( )

inlineprivate

scan a string literal

This function scans a string according to Sect. 7 of RFC 8259. While scanning, bytes are escaped and copied into buffer token_buffer. Then the function returns successfully, token_buffer is not null-terminated (as it may contain \0 bytes), and token_buffer.size() is the number of bytes in the string.

Returns

token_type::value_string if string could be successfully scanned, token_type::parse_error otherwise

Note

In case of errors, variable error_message contains a textual description.

Definition at line 6839 of file json.hpp.

    {
        // reset token_buffer (ignore opening quote)
        reset();
        // we entered the function by reading an open quote
        JSON_ASSERT(current == '\"');
 
        while (true)
        {
            // get next character
            switch (get())
            {
                // end of file while parsing string
                case std::char_traits<char_type>::eof():
                {
                    error_message = "invalid string: missing closing quote";
                    return token_type::parse_error;
                }
 
                // closing quote
                case '\"':
                {
                    return token_type::value_string;
                }
 
                // escapes
                case '\\':
                {
                    switch (get())
                    {
                        // quotation mark
                        case '\"':
                            add('\"');
                            break;
 
                        // reverse solidus
                        case '\\':
                            add('\\');
                            break;
 
                        // solidus
                        case '/':
                            add('/');
                            break;
 
                        // backspace
                        case 'b':
                            add('\b');
                            break;
 
                        // form feed
                        case 'f':
                            add('\f');
                            break;
 
                        // line feed
                        case 'n':
                            add('\n');
                            break;
 
                        // carriage return
                        case 'r':
                            add('\r');
                            break;
 
                        // tab
                        case 't':
                            add('\t');
                            break;
 
                        // unicode escapes
                        case 'u':
                        {
                            const int codepoint1 = get_codepoint();
                            int codepoint = codepoint1; // start with codepoint1
 
                            if (JSON_HEDLEY_UNLIKELY(codepoint1 == -1))
                            {
                                error_message = "invalid string: '\\u' must be followed by 4 hex digits";
                                return token_type::parse_error;
                            }
 
                            // check if code point is a high surrogate
                            if (0xD800 <= codepoint1 && codepoint1 <= 0xDBFF)
                            {
                                // expect next \uxxxx entry
                                if (JSON_HEDLEY_LIKELY(get() == '\\' && get() == 'u'))
                                {
                                    const int codepoint2 = get_codepoint();
 
                                    if (JSON_HEDLEY_UNLIKELY(codepoint2 == -1))
                                    {
                                        error_message = "invalid string: '\\u' must be followed by 4 hex digits";
                                        return token_type::parse_error;
                                    }
 
                                    // check if codepoint2 is a low surrogate
                                    if (JSON_HEDLEY_LIKELY(0xDC00 <= codepoint2 && codepoint2 <= 0xDFFF))
                                    {
                                        // overwrite codepoint
                                        codepoint = static_cast<int>(
                                                        // high surrogate occupies the most significant 22 bits
                                                        (static_cast<unsigned int>(codepoint1) << 10u)
                                                        // low surrogate occupies the least significant 15 bits
                                                        + static_cast<unsigned int>(codepoint2)
                                                        // there is still the 0xD800, 0xDC00 and 0x10000 noise
                                                        // in the result so we have to subtract with:
                                                        // (0xD800 << 10) + DC00 - 0x10000 = 0x35FDC00
                                                        - 0x35FDC00u);
                                    }
 
                                    else
                                    {
                                        error_message = "invalid string: surrogate U+D800..U+DBFF must be followed by U+DC00..U+DFFF";
                                        return token_type::parse_error;
                                    }
                                }
 
                                else
                                {
                                    error_message = "invalid string: surrogate U+D800..U+DBFF must be followed by U+DC00..U+DFFF";
                                    return token_type::parse_error;
                                }
                            }
 
                            else
                            {
                                if (JSON_HEDLEY_UNLIKELY(0xDC00 <= codepoint1 && codepoint1 <= 0xDFFF))
                                {
                                    error_message = "invalid string: surrogate U+DC00..U+DFFF must follow U+D800..U+DBFF";
                                    return token_type::parse_error;
                                }
                            }
 
                            // result of the above calculation yields a proper codepoint
                            JSON_ASSERT(0x00 <= codepoint && codepoint <= 0x10FFFF);
 
                            // translate codepoint into bytes
                            if (codepoint < 0x80)
                            {
                                // 1-byte characters: 0xxxxxxx (ASCII)
                                add(static_cast<char_int_type>(codepoint));
                            }
 
                            else if (codepoint <= 0x7FF)
                            {
                                // 2-byte characters: 110xxxxx 10xxxxxx
                                add(static_cast<char_int_type>(0xC0u | (static_cast<unsigned int>(codepoint) >> 6u)));
                                add(static_cast<char_int_type>(0x80u | (static_cast<unsigned int>(codepoint) & 0x3Fu)));
                            }
 
                            else if (codepoint <= 0xFFFF)
                            {
                                // 3-byte characters: 1110xxxx 10xxxxxx 10xxxxxx
                                add(static_cast<char_int_type>(0xE0u | (static_cast<unsigned int>(codepoint) >> 12u)));
                                add(static_cast<char_int_type>(0x80u | ((static_cast<unsigned int>(codepoint) >> 6u) & 0x3Fu)));
                                add(static_cast<char_int_type>(0x80u | (static_cast<unsigned int>(codepoint) & 0x3Fu)));
                            }
 
                            else
                            {
                                // 4-byte characters: 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
                                add(static_cast<char_int_type>(0xF0u | (static_cast<unsigned int>(codepoint) >> 18u)));
                                add(static_cast<char_int_type>(0x80u | ((static_cast<unsigned int>(codepoint) >> 12u) & 0x3Fu)));
                                add(static_cast<char_int_type>(0x80u | ((static_cast<unsigned int>(codepoint) >> 6u) & 0x3Fu)));
                                add(static_cast<char_int_type>(0x80u | (static_cast<unsigned int>(codepoint) & 0x3Fu)));
                            }
 
                            break;
                        }
 
                        // other characters after escape
                        default:
                            error_message = "invalid string: forbidden character after backslash";
                            return token_type::parse_error;
                    }
 
                    break;
                }
 
                // invalid control characters
                case 0x00:
                {
                    error_message = "invalid string: control character U+0000 (NUL) must be escaped to \\u0000";
                    return token_type::parse_error;
                }
 
                case 0x01:
                {
                    error_message = "invalid string: control character U+0001 (SOH) must be escaped to \\u0001";
                    return token_type::parse_error;
                }
 
                case 0x02:
                {
                    error_message = "invalid string: control character U+0002 (STX) must be escaped to \\u0002";
                    return token_type::parse_error;
                }
 
                case 0x03:
                {
                    error_message = "invalid string: control character U+0003 (ETX) must be escaped to \\u0003";
                    return token_type::parse_error;
                }
 
                case 0x04:
                {
                    error_message = "invalid string: control character U+0004 (EOT) must be escaped to \\u0004";
                    return token_type::parse_error;
                }
 
                case 0x05:
                {
                    error_message = "invalid string: control character U+0005 (ENQ) must be escaped to \\u0005";
                    return token_type::parse_error;
                }
 
                case 0x06:
                {
                    error_message = "invalid string: control character U+0006 (ACK) must be escaped to \\u0006";
                    return token_type::parse_error;
                }
 
                case 0x07:
                {
                    error_message = "invalid string: control character U+0007 (BEL) must be escaped to \\u0007";
                    return token_type::parse_error;
                }
 
                case 0x08:
                {
                    error_message = "invalid string: control character U+0008 (BS) must be escaped to \\u0008 or \\b";
                    return token_type::parse_error;
                }
 
                case 0x09:
                {
                    error_message = "invalid string: control character U+0009 (HT) must be escaped to \\u0009 or \\t";
                    return token_type::parse_error;
                }
 
                case 0x0A:
                {
                    error_message = "invalid string: control character U+000A (LF) must be escaped to \\u000A or \\n";
                    return token_type::parse_error;
                }
 
                case 0x0B:
                {
                    error_message = "invalid string: control character U+000B (VT) must be escaped to \\u000B";
                    return token_type::parse_error;
                }
 
                case 0x0C:
                {
                    error_message = "invalid string: control character U+000C (FF) must be escaped to \\u000C or \\f";
                    return token_type::parse_error;
                }
 
                case 0x0D:
                {
                    error_message = "invalid string: control character U+000D (CR) must be escaped to \\u000D or \\r";
                    return token_type::parse_error;
                }
 
                case 0x0E:
                {
                    error_message = "invalid string: control character U+000E (SO) must be escaped to \\u000E";
                    return token_type::parse_error;
                }
 
                case 0x0F:
                {
                    error_message = "invalid string: control character U+000F (SI) must be escaped to \\u000F";
                    return token_type::parse_error;
                }
 
                case 0x10:
                {
                    error_message = "invalid string: control character U+0010 (DLE) must be escaped to \\u0010";
                    return token_type::parse_error;
                }
 
                case 0x11:
                {
                    error_message = "invalid string: control character U+0011 (DC1) must be escaped to \\u0011";
                    return token_type::parse_error;
                }
 
                case 0x12:
                {
                    error_message = "invalid string: control character U+0012 (DC2) must be escaped to \\u0012";
                    return token_type::parse_error;
                }
 
                case 0x13:
                {
                    error_message = "invalid string: control character U+0013 (DC3) must be escaped to \\u0013";
                    return token_type::parse_error;
                }
 
                case 0x14:
                {
                    error_message = "invalid string: control character U+0014 (DC4) must be escaped to \\u0014";
                    return token_type::parse_error;
                }
 
                case 0x15:
                {
                    error_message = "invalid string: control character U+0015 (NAK) must be escaped to \\u0015";
                    return token_type::parse_error;
                }
 
                case 0x16:
                {
                    error_message = "invalid string: control character U+0016 (SYN) must be escaped to \\u0016";
                    return token_type::parse_error;
                }
 
                case 0x17:
                {
                    error_message = "invalid string: control character U+0017 (ETB) must be escaped to \\u0017";
                    return token_type::parse_error;
                }
 
                case 0x18:
                {
                    error_message = "invalid string: control character U+0018 (CAN) must be escaped to \\u0018";
                    return token_type::parse_error;
                }
 
                case 0x19:
                {
                    error_message = "invalid string: control character U+0019 (EM) must be escaped to \\u0019";
                    return token_type::parse_error;
                }
 
                case 0x1A:
                {
                    error_message = "invalid string: control character U+001A (SUB) must be escaped to \\u001A";
                    return token_type::parse_error;
                }
 
                case 0x1B:
                {
                    error_message = "invalid string: control character U+001B (ESC) must be escaped to \\u001B";
                    return token_type::parse_error;
                }
 
                case 0x1C:
                {
                    error_message = "invalid string: control character U+001C (FS) must be escaped to \\u001C";
                    return token_type::parse_error;
                }
 
                case 0x1D:
                {
                    error_message = "invalid string: control character U+001D (GS) must be escaped to \\u001D";
                    return token_type::parse_error;
                }
 
                case 0x1E:
                {
                    error_message = "invalid string: control character U+001E (RS) must be escaped to \\u001E";
                    return token_type::parse_error;
                }
 
                case 0x1F:
                {
                    error_message = "invalid string: control character U+001F (US) must be escaped to \\u001F";
                    return token_type::parse_error;
                }
 
                // U+0020..U+007F (except U+0022 (quote) and U+005C (backspace))
                case 0x20:
                case 0x21:
                case 0x23:
                case 0x24:
                case 0x25:
                case 0x26:
                case 0x27:
                case 0x28:
                case 0x29:
                case 0x2A:
                case 0x2B:
                case 0x2C:
                case 0x2D:
                case 0x2E:
                case 0x2F:
                case 0x30:
                case 0x31:
                case 0x32:
                case 0x33:
                case 0x34:
                case 0x35:
                case 0x36:
                case 0x37:
                case 0x38:
                case 0x39:
                case 0x3A:
                case 0x3B:
                case 0x3C:
                case 0x3D:
                case 0x3E:
                case 0x3F:
                case 0x40:
                case 0x41:
                case 0x42:
                case 0x43:
                case 0x44:
                case 0x45:
                case 0x46:
                case 0x47:
                case 0x48:
                case 0x49:
                case 0x4A:
                case 0x4B:
                case 0x4C:
                case 0x4D:
                case 0x4E:
                case 0x4F:
                case 0x50:
                case 0x51:
                case 0x52:
                case 0x53:
                case 0x54:
                case 0x55:
                case 0x56:
                case 0x57:
                case 0x58:
                case 0x59:
                case 0x5A:
                case 0x5B:
                case 0x5D:
                case 0x5E:
                case 0x5F:
                case 0x60:
                case 0x61:
                case 0x62:
                case 0x63:
                case 0x64:
                case 0x65:
                case 0x66:
                case 0x67:
                case 0x68:
                case 0x69:
                case 0x6A:
                case 0x6B:
                case 0x6C:
                case 0x6D:
                case 0x6E:
                case 0x6F:
                case 0x70:
                case 0x71:
                case 0x72:
                case 0x73:
                case 0x74:
                case 0x75:
                case 0x76:
                case 0x77:
                case 0x78:
                case 0x79:
                case 0x7A:
                case 0x7B:
                case 0x7C:
                case 0x7D:
                case 0x7E:
                case 0x7F:
                {
                    add(current);
                    break;
                }
 
                // U+0080..U+07FF: bytes C2..DF 80..BF
                case 0xC2:
                case 0xC3:
                case 0xC4:
                case 0xC5:
                case 0xC6:
                case 0xC7:
                case 0xC8:
                case 0xC9:
                case 0xCA:
                case 0xCB:
                case 0xCC:
                case 0xCD:
                case 0xCE:
                case 0xCF:
                case 0xD0:
                case 0xD1:
                case 0xD2:
                case 0xD3:
                case 0xD4:
                case 0xD5:
                case 0xD6:
                case 0xD7:
                case 0xD8:
                case 0xD9:
                case 0xDA:
                case 0xDB:
                case 0xDC:
                case 0xDD:
                case 0xDE:
                case 0xDF:
                {
                    if (JSON_HEDLEY_UNLIKELY(!next_byte_in_range({0x80, 0xBF})))
                    {
                        return token_type::parse_error;
                    }
                    break;
                }
 
                // U+0800..U+0FFF: bytes E0 A0..BF 80..BF
                case 0xE0:
                {
                    if (JSON_HEDLEY_UNLIKELY(!(next_byte_in_range({0xA0, 0xBF, 0x80, 0xBF}))))
                    {
                        return token_type::parse_error;
                    }
                    break;
                }
 
                // U+1000..U+CFFF: bytes E1..EC 80..BF 80..BF
                // U+E000..U+FFFF: bytes EE..EF 80..BF 80..BF
                case 0xE1:
                case 0xE2:
                case 0xE3:
                case 0xE4:
                case 0xE5:
                case 0xE6:
                case 0xE7:
                case 0xE8:
                case 0xE9:
                case 0xEA:
                case 0xEB:
                case 0xEC:
                case 0xEE:
                case 0xEF:
                {
                    if (JSON_HEDLEY_UNLIKELY(!(next_byte_in_range({0x80, 0xBF, 0x80, 0xBF}))))
                    {
                        return token_type::parse_error;
                    }
                    break;
                }
 
                // U+D000..U+D7FF: bytes ED 80..9F 80..BF
                case 0xED:
                {
                    if (JSON_HEDLEY_UNLIKELY(!(next_byte_in_range({0x80, 0x9F, 0x80, 0xBF}))))
                    {
                        return token_type::parse_error;
                    }
                    break;
                }
 
                // U+10000..U+3FFFF F0 90..BF 80..BF 80..BF
                case 0xF0:
                {
                    if (JSON_HEDLEY_UNLIKELY(!(next_byte_in_range({0x90, 0xBF, 0x80, 0xBF, 0x80, 0xBF}))))
                    {
                        return token_type::parse_error;
                    }
                    break;
                }
 
                // U+40000..U+FFFFF F1..F3 80..BF 80..BF 80..BF
                case 0xF1:
                case 0xF2:
                case 0xF3:
                {
                    if (JSON_HEDLEY_UNLIKELY(!(next_byte_in_range({0x80, 0xBF, 0x80, 0xBF, 0x80, 0xBF}))))
                    {
                        return token_type::parse_error;
                    }
                    break;
                }
 
                // U+100000..U+10FFFF F4 80..8F 80..BF 80..BF
                case 0xF4:
                {
                    if (JSON_HEDLEY_UNLIKELY(!(next_byte_in_range({0x80, 0x8F, 0x80, 0xBF, 0x80, 0xBF}))))
                    {
                        return token_type::parse_error;
                    }
                    break;
                }
 
                // remaining bytes (80..C1 and F5..FF) are ill-formed
                default:
                {
                    error_message = "invalid string: ill-formed UTF-8 byte";
                    return token_type::parse_error;
                }
            }
        }
    }