Examples with Dictionary morfologik.stemming.Dictionary used on opensource projects

Example 6 with Dictionary

use of morfologik.stemming.Dictionary in project languagetool by languagetool-org.

the class BaseSynthesizer method getDictionary.

/**
   * Returns the {@link Dictionary} used for this synthesizer.
   * The dictionary file can be defined in the {@link #BaseSynthesizer(String, String) constructor}.
   * @throws IOException In case the dictionary cannot be loaded.
   */
protected Dictionary getDictionary() throws IOException {
    Dictionary dict = this.dictionary;
    if (dict == null) {
        synchronized (this) {
            dict = this.dictionary;
            if (dict == null) {
                URL url = JLanguageTool.getDataBroker().getFromResourceDirAsUrl(resourceFileName);
                this.dictionary = dict = Dictionary.read(url);
            }
        }
    }
    return dict;
}

Example 7 with Dictionary

use of morfologik.stemming.Dictionary in project languagetool by languagetool-org.

the class MorfologikGermanyGermanSpellerRuleTest method testCommonMisspellings.

@Test
@Ignore("help testing for https://github.com/morfologik/morfologik-stemming/issues/34")
public void testCommonMisspellings() throws IOException {
    URL fsaURL = JLanguageTool.getDataBroker().getFromResourceDirAsUrl("de/hunspell/de_DE.dict");
    Dictionary dictionary = Dictionary.read(fsaURL);
    Speller speller = new Speller(dictionary, 2);
    List<String> input = Arrays.asList((// tiny subset from https://de.wikipedia.org/wiki/Wikipedia:Liste_von_Tippfehlern
    "Abenteur Abhängikeit abzuschliessen agerufen Aktivitiäten Aktzeptanz " + "Algorhitmus Algoritmus aliiert allgmein Amtsitz änlich Anstoss atakieren begrüsst Bezeichnug chinesiche " + "dannach Frima Fahrad Gebaüde gesammt Schrifsteller seperat Septmber Staddteil Rhytmen rhytmisch Maschiene " + "Lebensmittelgäschefte enstand großmutter Rytmus " + // from user feedback:
    "Vorstelungsgespräch Heißhunge-Attakcen evntl. langwalig Selbstportät Erdgeshoss " + "kommmischeweise gegensatz Gesichte Suedkaukasus Englisch-sprachigige " + // from gutefrage.net:
    "gerägelt Aufjedenfall ivh hällt daß muß woeder oderso anwalt").split(" "));
    for (String word : input) {
        check(word, speller);
    }
}

Example 8 with Dictionary

use of morfologik.stemming.Dictionary in project languagetool by languagetool-org.

the class GermanSpellerRuleTest method testMorfologikSpeller.

@Test
@Ignore("testing a potential bug in Morfologik")
public void testMorfologikSpeller() throws Exception {
    List<byte[]> lines = new ArrayList<>();
    lines.add("die".getBytes());
    lines.add("ist".getBytes());
    byte[] info = "fsa.dict.separator=+\nfsa.dict.encoding=utf-8\nfsa.dict.frequency-included=true".getBytes();
    Dictionary dict = getDictionary(lines, new ByteArrayInputStream(info));
    Speller speller = new Speller(dict, 2);
    // why do both "die" and "ist" have a distance of 1 in the CandidateData constructor?
    System.out.println(speller.findReplacements("is"));
}

Example 9 with Dictionary

use of morfologik.stemming.Dictionary in project languagetool by languagetool-org.

the class MorfologikGermanyGermanSpellerRuleTest method testFrequency.

@Test
@Ignore("testing for https://github.com/languagetool-org/languagetool/issues/236")
public void testFrequency() throws IOException {
    URL fsaURL = JLanguageTool.getDataBroker().getFromResourceDirAsUrl("de/hunspell/de_DE.dict");
    Dictionary dictionary = Dictionary.read(fsaURL);
    Speller speller = new Speller(dictionary, 2);
    assertThat(speller.getFrequency("der"), is(25));
    assertThat(speller.getFrequency("Haus"), is(11));
    assertThat(speller.getFrequency("schön"), is(9));
    assertThat(speller.getFrequency("gippsnicht"), is(0));
}