string parse_string()

in GomokuServer/GomokuServer/json11.cpp [480:567]
76 lines of code
23 McCabe index (conditional complexity)

    string parse_string() {
        string out;
        long last_escaped_codepoint = -1;
        while (true) {
            if (i == str.size())
                return fail("unexpected end of input in string", "");

            char ch = str[i++];

            if (ch == '"') {
                encode_utf8(last_escaped_codepoint, out);
                return out;
            }

            if (in_range(ch, 0, 0x1f))
                return fail("unescaped " + esc(ch) + " in string", "");

            // The usual case: non-escaped characters
            if (ch != '\\') {
                encode_utf8(last_escaped_codepoint, out);
                last_escaped_codepoint = -1;
                out += ch;
                continue;
            }

            // Handle escapes
            if (i == str.size())
                return fail("unexpected end of input in string", "");

            ch = str[i++];

            if (ch == 'u') {
                // Extract 4-byte escape sequence
                string esc = str.substr(i, 4);
                // Explicitly check length of the substring. The following loop
                // relies on std::string returning the terminating NUL when
                // accessing str[length]. Checking here reduces brittleness.
                if (esc.length() < 4) {
                    return fail("bad \\u escape: " + esc, "");
                }
                for (size_t j = 0; j < 4; j++) {
                    if (!in_range(esc[j], 'a', 'f') && !in_range(esc[j], 'A', 'F')
                            && !in_range(esc[j], '0', '9'))
                        return fail("bad \\u escape: " + esc, "");
                }

                long codepoint = strtol(esc.data(), nullptr, 16);

                // JSON specifies that characters outside the BMP shall be encoded as a pair
                // of 4-hex-digit \u escapes encoding their surrogate pair components. Check
                // whether we're in the middle of such a beast: the previous codepoint was an
                // escaped lead (high) surrogate, and this is a trail (low) surrogate.
                if (in_range(last_escaped_codepoint, 0xD800, 0xDBFF)
                        && in_range(codepoint, 0xDC00, 0xDFFF)) {
                    // Reassemble the two surrogate pairs into one astral-plane character, per
                    // the UTF-16 algorithm.
                    encode_utf8((((last_escaped_codepoint - 0xD800) << 10)
                                 | (codepoint - 0xDC00)) + 0x10000, out);
                    last_escaped_codepoint = -1;
                } else {
                    encode_utf8(last_escaped_codepoint, out);
                    last_escaped_codepoint = codepoint;
                }

                i += 4;
                continue;
            }

            encode_utf8(last_escaped_codepoint, out);
            last_escaped_codepoint = -1;

            if (ch == 'b') {
                out += '\b';
            } else if (ch == 'f') {
                out += '\f';
            } else if (ch == 'n') {
                out += '\n';
            } else if (ch == 'r') {
                out += '\r';
            } else if (ch == 't') {
                out += '\t';
            } else if (ch == '"' || ch == '\\' || ch == '/') {
                out += ch;
            } else {
                return fail("invalid escape character " + esc(ch), "");
            }
        }
    }