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);

  static final ImmutableMap<String, String> TEST_STRINGS =
      ImmutableMap.<String, String>builder()
          .put("empty", "")
          .put("1 char", "0")
          .put("1 word", "hello")
          .put("2 words", "hello world")
          .put("\\n line break", "hello\nworld")
          .put("\\r line break", "hello\rworld")
          .put("\\r\\n line break", "hello\r\nworld")

labels.facet_contentLength_5m=5MB -  
labels.facet_filetype_title=Tipo di file
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 Foglio di calcolo
labels.facet_filetype_odp=ODF Presentazione
labels.facet_filetype_pdf=PDF
labels.facet_filetype_fb2=FictionBook

labels.facet_contentLength_5m=5 MB -  
labels.facet_filetype_title=Dateityp
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-Tabelle
labels.facet_filetype_odp=ODF-Präsentation
labels.facet_filetype_pdf=PDF
labels.facet_filetype_fb2=FictionBook

labels.facet_contentLength_5m=5MB -  
labels.facet_filetype_title=Typ pliku
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 Arkusz kalkulacyjny
labels.facet_filetype_odp=ODF Prezentacja
labels.facet_filetype_pdf=PDF
labels.facet_filetype_fb2=FictionBook

labels.facet_contentLength_5m=5MB -  
labels.facet_filetype_title=Dosya Türü
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 Elektronik Tablo
labels.facet_filetype_odp=ODF Sunum
labels.facet_filetype_pdf=PDF
labels.facet_filetype_fb2=FictionBook

    /**
     * {@return the dependency scope for the given identifier, or {@code null} if none}.
     * The identifiers are usually in lower cases with {@code '-'} instead of {@code '_'}
     * as word separator.
     *
     * @param id the identifier of the scope (case-sensitive)
     */
    public static DependencyScope forId(String id) {
        return IDS.get(id);
    }

    private final String id;