use of org.languagetool.Language in project languagetool by languagetool-org.
the class SentenceSourceChecker method run.
private void run(File propFile, Set<String> disabledRules, String langCode, List<String> fileNames, String[] ruleIds, String[] additionalCategoryIds, int maxSentences, int maxErrors, File languageModelDir, Pattern filter) throws IOException {
Language lang = Languages.getLanguageForShortCode(langCode);
MultiThreadedJLanguageTool languageTool = new MultiThreadedJLanguageTool(lang);
languageTool.setCleanOverlappingMatches(false);
if (languageModelDir != null) {
languageTool.activateLanguageModelRules(languageModelDir);
}
if (ruleIds != null) {
enableOnlySpecifiedRules(ruleIds, languageTool);
} else {
applyRuleDeactivation(languageTool, disabledRules);
}
if (filter != null) {
System.out.println("*** NOTE: only sentences that match regular expression '" + filter + "' will be checked");
}
activateAdditionalCategories(additionalCategoryIds, languageTool);
disableSpellingRules(languageTool);
System.out.println("Working on: " + StringUtils.join(fileNames, ", "));
System.out.println("Sentence limit: " + (maxSentences > 0 ? maxSentences : "no limit"));
System.out.println("Error limit: " + (maxErrors > 0 ? maxErrors : "no limit"));
ResultHandler resultHandler = null;
int ruleMatchCount = 0;
int sentenceCount = 0;
try {
if (propFile != null) {
resultHandler = new DatabaseHandler(propFile, maxSentences, maxErrors);
} else {
//resultHandler = new CompactStdoutHandler(maxSentences, maxErrors);
resultHandler = new StdoutHandler(maxSentences, maxErrors);
}
MixingSentenceSource mixingSource = MixingSentenceSource.create(fileNames, lang, filter);
while (mixingSource.hasNext()) {
Sentence sentence = mixingSource.next();
try {
List<RuleMatch> matches = languageTool.check(sentence.getText());
resultHandler.handleResult(sentence, matches, lang);
sentenceCount++;
if (sentenceCount % 5000 == 0) {
System.err.printf("%s sentences checked...\n", NumberFormat.getNumberInstance(Locale.US).format(sentenceCount));
}
ruleMatchCount += matches.size();
} catch (DocumentLimitReachedException | ErrorLimitReachedException e) {
throw e;
} catch (Exception e) {
throw new RuntimeException("Check failed on sentence: " + StringUtils.abbreviate(sentence.getText(), 250), e);
}
}
} catch (DocumentLimitReachedException | ErrorLimitReachedException e) {
System.out.println(getClass().getSimpleName() + ": " + e);
} finally {
languageTool.shutdown();
if (resultHandler != null) {
float matchesPerSentence = (float) ruleMatchCount / sentenceCount;
System.out.printf(lang + ": %d total matches\n", ruleMatchCount);
System.out.printf(lang + ": ø%.2f rule matches per sentence\n", matchesPerSentence);
try {
resultHandler.close();
} catch (Exception e) {
e.printStackTrace();
}
}
}
}
use of org.languagetool.Language in project languagetool by languagetool-org.
the class Searcher method main.
public static void main(String[] args) throws Exception {
ensureCorrectUsageOrExit(args);
long startTime = System.currentTimeMillis();
String[] ruleIds = args[0].split(",");
String languageCode = args[1];
Language language = Languages.getLanguageForShortCode(languageCode);
File indexDir = new File(args[2]);
boolean limitSearch = !(args.length > 3 && "--no_limit".equals(args[3]));
Searcher searcher = new Searcher(new SimpleFSDirectory(indexDir.toPath()));
if (!limitSearch) {
searcher.setMaxHits(100_000);
}
searcher.limitSearch = limitSearch;
ContextTools contextTools = getContextTools(140);
int totalMatches = 0;
for (String ruleId : ruleIds) {
long ruleStartTime = System.currentTimeMillis();
for (PatternRule rule : searcher.getRuleById(ruleId, language)) {
System.out.println("===== " + rule.getFullId() + " =========================================================");
SearcherResult searcherResult = searcher.findRuleMatchesOnIndex(rule, language);
int i = 1;
if (searcherResult.getMatchingSentences().size() == 0) {
System.out.println("[no matches]");
}
for (MatchingSentence ruleMatch : searcherResult.getMatchingSentences()) {
for (RuleMatch match : ruleMatch.getRuleMatches()) {
String context = contextTools.getContext(match.getFromPos(), match.getToPos(), ruleMatch.getSentence());
if (WIKITEXT_OUTPUT) {
ContextTools contextTools2 = getContextTools(0);
String coveredText = contextTools2.getContext(match.getFromPos(), match.getToPos(), ruleMatch.getSentence());
coveredText = coveredText.replaceFirst("^\\.\\.\\.", "").replaceFirst("\\.\\.\\.$", "");
coveredText = coveredText.replaceFirst("^\\*\\*", "").replaceFirst("\\*\\*$", "");
String encodedTextWithQuotes = URLEncoder.encode("\"" + coveredText + "\"", "UTF-8");
String searchLink = "https://de.wikipedia.org/w/index.php?search=" + encodedTextWithQuotes + "&title=Spezial%3ASuche&go=Artikel";
context = context.replaceAll("\\*\\*.*?\\*\\*", "[" + searchLink + " " + coveredText + "]");
String encTitle = URLEncoder.encode(ruleMatch.getTitle(), "UTF-8");
String encodedText = URLEncoder.encode(coveredText, "UTF-8");
System.out.println("# [[" + ruleMatch.getTitle() + "]]: " + context + " ([http://wikipedia.ramselehof.de/wikiblame.php?user_lang=de&lang=de&project=wikipedia&article=" + encTitle + "&needle=" + encodedText + "&skipversions=0&ignorefirst=0&limit=500&searchmethod=int&order=desc&start=Start WikiBlame])");
} else {
System.out.println(i + ": " + context + " [" + ruleMatch.getSource() + "]");
}
}
totalMatches += ruleMatch.getRuleMatches().size();
i++;
}
System.out.println("Time: " + (System.currentTimeMillis() - ruleStartTime) + "ms");
}
}
System.out.println("Total time: " + (System.currentTimeMillis() - startTime) + "ms, " + totalMatches + " matches");
}
use of org.languagetool.Language in project languagetool by languagetool-org.
the class ToolsTest method testBitextCheck.
private void testBitextCheck(ResultCache cache) throws IOException, ParserConfigurationException, SAXException {
Language english = Languages.getLanguageForShortCode("en");
JLanguageTool srcTool = new JLanguageTool(english, null, cache);
Language polish = Languages.getLanguageForShortCode("pl");
JLanguageTool trgTool = new JLanguageTool(polish, null, cache);
List<BitextRule> rules = Tools.getBitextRules(english, polish);
int matchCount = Tools.checkBitext("This is a perfectly good sentence.", "To jest całkowicie prawidłowe zdanie.", srcTool, trgTool, rules).size();
assertEquals(0, matchCount);
List<RuleMatch> matches1 = Tools.checkBitext("This is not actual.", "To nie jest aktualne.", srcTool, trgTool, rules);
assertEquals(1, matches1.size());
assertThat(matches1.get(0).getRule().getId(), is("ACTUAL"));
assertThat(matches1.get(0).getFromPos(), is(12));
assertThat(matches1.get(0).getToPos(), is(20));
List<RuleMatch> matches2 = Tools.checkBitext("A sentence. This is not actual.", "Zdanie. To nie jest aktualne.", srcTool, trgTool, rules);
assertEquals(1, matches2.size());
assertThat(matches2.get(0).getRule().getId(), is("ACTUAL"));
assertThat(matches2.get(0).getFromPos(), is(20));
assertThat(matches2.get(0).getToPos(), is(28));
List<RuleMatch> matches3 = Tools.checkBitext("A new sentence. This is not actual.", "Nowa zdanie. To nie jest aktualne.", srcTool, trgTool, rules);
assertEquals(1, matches3.size());
assertThat(matches3.get(0).getRule().getId(), is("ACTUAL"));
assertThat(matches3.get(0).getFromPos(), is(25));
assertThat(matches3.get(0).getToPos(), is(33));
}
use of org.languagetool.Language in project languagetool by languagetool-org.
the class WikipediaQuickCheck method getMediaWikiContent.
public String getMediaWikiContent(URL wikipediaUrl) throws IOException {
Language lang = getLanguage(wikipediaUrl);
String pageTitle = getPageTitle(wikipediaUrl);
String apiUrl = "https://" + lang.getShortCode() + ".wikipedia.org/w/api.php?titles=" + URLEncoder.encode(pageTitle, "utf-8") + "&action=query&prop=revisions&rvprop=content|timestamp&format=xml";
return getContent(new URL(apiUrl));
}
use of org.languagetool.Language in project languagetool by languagetool-org.
the class POSDictionaryBuilderTest method testExportAndImport.
@Test
@Ignore("for interactive use only")
public void testExportAndImport() throws Exception {
for (Language language : Languages.get()) {
String langCode = language.getShortCode();
File dir = new File("./languagetool-language-modules/" + langCode + "/src/main/resources/org/languagetool/resource/" + langCode);
File oldBinaryFile = new File(dir, language.getName().toLowerCase() + ".dict");
File infoFile = new File(dir, language.getName().toLowerCase() + ".info");
File exportFile = exportDictionaryContents(oldBinaryFile);
if (exportFile.length() == 0) {
System.out.println("Zero-size output for " + language + ", skipping dictionary generation");
exportFile.delete();
continue;
}
POSDictionaryBuilder builder = new POSDictionaryBuilder(infoFile);
File newBinaryFile = builder.build(exportFile);
exportFile.delete();
System.out.println(language + " old binary file size: " + oldBinaryFile.length() + " bytes (" + oldBinaryFile.getName() + ")");
System.out.println(language + " new binary file size: " + newBinaryFile.length() + " bytes (" + newBinaryFile.getAbsolutePath() + ")");
// comment in to copy the new files over the old ones:
/*boolean b = newBinaryFile.renameTo(oldBinaryFile);
if (!b) {
throw new RuntimeException("Could not rename" + newBinaryFile.getAbsolutePath() + " to " + oldBinaryFile.getCanonicalPath());
}*/
System.out.println("");
}
}
Aggregations