/**
     * Enumeration of supported API format types.
     */
    protected enum FormatType {
        /** Search API format. */
        SEARCH,
        /** Label API format. */
        LABEL,
        /** Popular word API format. */
        POPULARWORD,
        /** Favorite API format. */
        FAVORITE,
        /** Favorites API format. */
        FAVORITES,
        /** Ping API format. */
        PING,

    int writeString(final String str, final byte[] dst, int dstIndex, final boolean useUnicode) {
        final int start = dstIndex;

        try {
            if (useUnicode) {
                // Unicode requires word alignment
                if ((dstIndex - headerStart) % 2 != 0) {
                    dst[dstIndex++] = (byte) '\0';
                }

labels.facet_contentLength_5m=5MB -  
labels.facet_filetype_title=檔案類型
labels.facet_filetype_html=HTML
labels.facet_filetype_word=MS Word
labels.facet_filetype_excel=MS Excel
labels.facet_filetype_powerpoint=MS PowerPoint
labels.facet_filetype_odt=ODF Word
labels.facet_filetype_ods=ODF Spreadsheet
labels.facet_filetype_odp=ODF Presentation
labels.facet_filetype_pdf=PDF
labels.facet_filetype_fb2=FictionBook

        assertNotNull(ex.toString(), "toString should be safe to call");
    }

    @ParameterizedTest
    @NullAndEmptySource
    @ValueSource(strings = { "oops", "multi word", "中文" })
    @DisplayName("Message+Cause constructor: preserves both values; no interactions with cause")
    void messageAndCauseConstructor_preservesBoth(String message) {
        // Arrange & Act

        Number n,
        Iterable<?> it,
        boolean b,
        Equivalence<String> eq,
        Exception e,
        InputStream in,
        Comparable<?> c,
        Ordering<Integer> ord,
        Charset charset,
        TimeUnit unit,
        Class<?> cls,
        Joiner joiner,
        Pattern pattern,
        UnsignedInteger ui,
        UnsignedLong ul,
        StringBuilder sb,

labels.facet_contentLength_5m=5MB -  
labels.facet_filetype_title=Tipo de arquivo
labels.facet_filetype_html=HTML
labels.facet_filetype_word=MS Word
labels.facet_filetype_excel=MS Excel
labels.facet_filetype_powerpoint=MS PowerPoint
labels.facet_filetype_odt=ODF Word
labels.facet_filetype_ods=ODF Planilha
labels.facet_filetype_odp=ODF Apresentação
labels.facet_filetype_pdf=PDF
labels.facet_filetype_fb2=FictionBook

file: org.apache.spark.rdd.RDD[String] = s3a://testbucket/testdata MapPartitionsRDD[1] at textFile at <console>:24

scala> val counts = file.flatMap(line => line.split(" ")).map(word => (word, 1)).reduceByKey(_ + _)
counts: org.apache.spark.rdd.RDD[(String, Int)] = ShuffledRDD[4] at reduceByKey at <console>:25

scala> counts.saveAsTextFile("s3a://testbucket/wordcount")
```

</p>

<p>
Reads of memory locations larger than a single machine word
are encouraged but not required to meet the same semantics
as word-sized memory locations,
observing a single allowed write <i>w</i>.
For performance reasons,
implementations may instead treat larger operations
as a set of individual machine-word-sized operations
in an unspecified order.
This means that races on multiword data structures

application/mac-binhex40       hqx              # Macintosh binhexed archives
application/mspowerpoint       ppt              # Microsoft Powerpoint
application/msword             doc              # Microsoft Word
application/octet-stream       bin exe ani      # Binary File
application/oda                oda
application/pagemaker          pm5 pt5 pm       # PageMaker
application/pdf                pdf              # Adobe Acrobat

        pdfExtractor = container.getComponent("pdfExtractor");
        pdfExtractorForPdfPassword = container.getComponent("pdfExtractorForPdfPassword");
        pdfExtractorForPdfPassword.addPassword(".*test_.*.pdf", "word");
    }

    public void test_getText() {
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/test.pdf");
        final ExtractData extractData = pdfExtractor.getText(in, null);