sebegini
begitu
begitukah
begitulah
begitupun
sebegitu
belum
belumlah
sebelum
sebelumnya
sebenarnya
berapa
berapakah
berapalah
berapapun
betulkah
sebetulnya
biasa
biasanya
bila
bilakah
bisa
bisakah
sebisanya
boleh
bolehkah
bolehlah
buat
bukan
bukankah
bukanlah
bukannya
cuma
percuma
dahulu
dalam
dan
dapat
dari
daripada
dekat
demi

aber
alle
allem
allen
aller
alles
als
also
am
an
ander
andere
anderem
anderen
anderer
anderes
anderm
andern
anderr
anders
auch
auf
aus
bei
bin
bis
bist
da
damit
dann
der
den
des
dem
die
das
daß
derselbe
derselben
denselben
desselben
demselben
dieselbe
dieselben
dasselbe
dazu
dein
deine
deinem
deinen

        final BufferedInputStream bis = new BufferedInputStream(in);
        final String encoding = xmlExtractor.getEncoding(bis);
        CloseableUtil.closeQuietly(bis);
        assertEquals("UTF-8", encoding);
    }

    public void test_getEncoding_sjis() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/test_sjis.xml");
        final BufferedInputStream bis = new BufferedInputStream(in);

iekām
iekāms
kolīdz
līdzko
tiklīdz
jebšu
tālab
tāpēc
nekā
itin
jā
jau
jel
nē
nezin
tad
tikai
vis
tak
iekams
vien
# modal verbs
būt  
biju 
biji
bija
bijām
bijāt
esmu
esi
esam
esat 
būšu     
būsi
būs
būsim
būsiet
tikt
tiku
tiki
tika
tikām
tikāt
tieku
tiec
tiek
tiekam
tiekat
tikšu

        final BufferedInputStream bis = new BufferedInputStream(in);
        final String encoding = htmlXpathExtractor.getEncoding(bis);
        CloseableUtil.closeQuietly(bis);
        assertEquals("UTF-8", encoding);
    }

    public void test_getEncoding_sjis() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/test_sjis.html");
        final BufferedInputStream bis = new BufferedInputStream(in);

        }
        try {
            final BufferedInputStream bis = new BufferedInputStream(in);
            final String enc = getEncoding(bis);
            final String content = UNESCAPE_HTML4.translate(new String(InputStreamUtil.getBytes(bis), enc));
            return createExtractData(content);
        } catch (final Exception e) {
            throw new ExtractException(e);

        try (BufferedInputStream bis = new BufferedInputStream(getContentAsStream());
                ByteArrayOutputStream baos = new ByteArrayOutputStream()) {
            int length = bis.read(bytes);
            while (length != -1) {
                if (length != 0) {
                    baos.write(bytes, 0, length);
                }
                length = bis.read(bytes);
            }

        final BufferedInputStream bis = new BufferedInputStream(in);
        final String encoding = htmlExtractor.getEncoding(bis);
        CloseableUtil.closeQuietly(bis);
        assertEquals("UTF-8", encoding);
    }

    public void test_getEncoding_sjis() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/test_sjis.html");
        final BufferedInputStream bis = new BufferedInputStream(in);

        }

        final ResultData resultData = new ResultData();
        resultData.setTransformerName(getName());

        try (BufferedInputStream bis = new BufferedInputStream(responseData.getResponseBody())) {
            resultData.setData(IOUtils.toByteArray(bis));
            resultData.setEncoding(responseData.getCharSet());
            return resultData;
        } catch (final IOException e) {