Function ConvertUTF8toUTF32Impl

ext/src/llvm/ConvertUTF.cpp:614–699

/* --------------------------------------------------------------------- */

static ConversionResult ConvertUTF8toUTF32Impl(
        const UTF8** sourceStart, const UTF8* sourceEnd,
        UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags,
        Boolean InputIsPartial) {
    ConversionResult result = conversionOK;
    const UTF8* source = *sourceStart;
    UTF32* target = *targetStart;
    while (source < sourceEnd) {
        UTF32 ch = 0;
        unsigned short extraBytesToRead = trailingBytesForUTF8[*source];
        if (extraBytesToRead >= sourceEnd - source) {
            if (flags == strictConversion || InputIsPartial) {
                result = sourceExhausted;
                break;
            } else {
                result = sourceIllegal;

                /*
                 * Replace the maximal subpart of ill-formed sequence with
                 * replacement character.
                 */
                source += findMaximalSubpartOfIllFormedUTF8Sequence(source,
                                                                    sourceEnd);
                *target++ = UNI_REPLACEMENT_CHAR;
                continue;
            }
        }
        if (target >= targetEnd) {
            result = targetExhausted; break;
        }

        /* Do this check whether lenient or strict */
        if (!isLegalUTF8(source, extraBytesToRead+1)) {
            result = sourceIllegal;
            if (flags == strictConversion) {
                /* Abort conversion. */
                break;
            } else {
                /*
                 * Replace the maximal subpart of ill-formed sequence with
                 * replacement character.
                 */
                source += findMaximalSubpartOfIllFormedUTF8Sequence(source,
                                                                    sourceEnd);
                *target++ = UNI_REPLACEMENT_CHAR;
                continue;
            }
        }
        /*
         * The cases all fall through. See "Note A" below.
         */
        switch (extraBytesToRead) {
            case 5: ch += *source++; ch <<= 6;
            case 4: ch += *source++; ch <<= 6;
            case 3: ch += *source++; ch <<= 6;
            case 2: ch += *source++; ch <<= 6;
            case 1: ch += *source++; ch <<= 6;
            case 0: ch += *source++;