use of zemberek.morphology.external.OflazerAnalyzerRunner in project zemberek-nlp by ahmetaa.
the class ZemberekNlpScripts method parseLargeVocabularyOflazer.
@Test
@Ignore("Not a Test.")
public void parseLargeVocabularyOflazer() throws IOException {
OflazerAnalyzerRunner runner = new OflazerAnalyzerRunner(OFLAZER_ANALYZER_PATH.toFile(), OFLAZER_ANALYZER_PATH.resolve("tfeaturesulx.fst").toFile());
Path wordFile = DATA_PATH.resolve("all-words-sorted-freq.txt");
// Path wordFile = DATA_PATH.resolve("vocab-corpus-and-zemberek");
Path outDir = DATA_PATH.resolve("out");
Files.createDirectories(outDir);
Path outPath = outDir.resolve("oflazer-parses.txt");
runner.parseSentences(wordFile.toFile(), outPath.toFile());
}
Aggregations