Method DetectType

src/include/rapidjson/encodedstream.h:171–217

Detect encoding type with BOM or RFC 4627

    // Detect encoding type with BOM or RFC 4627
    void DetectType() {
        // BOM (Byte Order Mark):
        // 00 00 FE FF  UTF-32BE
        // FF FE 00 00  UTF-32LE
        // FE FF        UTF-16BE
        // FF FE        UTF-16LE
        // EF BB BF     UTF-8

        const unsigned char* c = reinterpret_cast<const unsigned char *>(is_->Peek4());
        if (!c)
            return;

        unsigned bom = static_cast<unsigned>(c[0] | (c[1] << 8) | (c[2] << 16) | (c[3] << 24));
        hasBOM_ = false;
        if (bom == 0xFFFE0000)                  { type_ = kUTF32BE; hasBOM_ = true; is_->Take(); is_->Take(); is_->Take(); is_->Take(); }
        else if (bom == 0x0000FEFF)             { type_ = kUTF32LE; hasBOM_ = true; is_->Take(); is_->Take(); is_->Take(); is_->Take(); }
        else if ((bom & 0xFFFF) == 0xFFFE)      { type_ = kUTF16BE; hasBOM_ = true; is_->Take(); is_->Take();                           }
        else if ((bom & 0xFFFF) == 0xFEFF)      { type_ = kUTF16LE; hasBOM_ = true; is_->Take(); is_->Take();                           }
        else if ((bom & 0xFFFFFF) == 0xBFBBEF)  { type_ = kUTF8;    hasBOM_ = true; is_->Take(); is_->Take(); is_->Take();              }

        // RFC 4627: Section 3
        // "Since the first two characters of a JSON text will always be ASCII
        // characters [RFC0020], it is possible to determine whether an octet
        // stream is UTF-8, UTF-16 (BE or LE), or UTF-32 (BE or LE) by looking
        // at the pattern of nulls in the first four octets."
        // 00 00 00 xx  UTF-32BE
        // 00 xx 00 xx  UTF-16BE
        // xx 00 00 00  UTF-32LE
        // xx 00 xx 00  UTF-16LE
        // xx xx xx xx  UTF-8

        if (!hasBOM_) {
            int pattern = (c[0] ? 1 : 0) | (c[1] ? 2 : 0) | (c[2] ? 4 : 0) | (c[3] ? 8 : 0);
            switch (pattern) {
            case 0x08: type_ = kUTF32BE; break;
            case 0x0A: type_ = kUTF16BE; break;
            case 0x01: type_ = kUTF32LE; break;
            case 0x05: type_ = kUTF16LE; break;
            case 0x0F: type_ = kUTF8;    break;
            default: break; // Use type defined by user.
            }
        }

        // Runtime check whether the size of character type is sufficient. It only perform checks with assertion.
        if (type_ == kUTF16LE || type_ == kUTF16BE) RAPIDJSON_ASSERT(sizeof(Ch) >= 2);
        if (type_ == kUTF32LE || type_ == kUTF32BE) RAPIDJSON_ASSERT(sizeof(Ch) >= 4);
    }

    typedef Ch (*TakeFunc)(InputByteStream& is);
    InputByteStream* is_;