Examples with Language org.omegat.util.Language used on opensource projects

Example 36 with Language

use of org.omegat.util.Language in project omegat by omegat-org.

the class GlossaryReaderTBX method readMartif.

public static List<GlossaryEntry> readMartif(final Martif tbx, boolean priorityGlossary, String origin) throws Exception {
    if (tbx.getText() == null) {
        return Collections.emptyList();
    }
    String sLang = Core.getProject().getProjectProperties().getSourceLanguage().getLanguageCode();
    String tLang = Core.getProject().getProjectProperties().getTargetLanguage().getLanguageCode();
    StringBuilder note = new StringBuilder();
    StringBuilder descTerm = new StringBuilder();
    StringBuilder descTig = new StringBuilder();
    List<GlossaryEntry> result = new ArrayList<GlossaryEntry>();
    List<String> sTerms = new ArrayList<String>();
    List<String> tTerms = new ArrayList<String>();
    for (TermEntry te : tbx.getText().getBody().getTermEntry()) {
        note.setLength(0);
        descTerm.setLength(0);
        descTig.setLength(0);
        appendDescOrNote(te.getDescripOrDescripGrpOrAdmin(), descTerm);
        for (LangSet ls : te.getLangSet()) {
            Language termLanguage = new Language(ls.getLang());
            // We use only the language code
            String lang = termLanguage.getLanguageCode();
            appendDescOrNote(ls.getDescripOrDescripGrpOrAdmin(), descTig);
            for (Object o : ls.getTigOrNtig()) {
                if (o instanceof Tig) {
                    Tig t = (Tig) o;
                    if (sLang.equalsIgnoreCase(lang)) {
                        sTerms.add(readContent(t.getTerm().getContent()));
                    } else if (tLang.equalsIgnoreCase(lang)) {
                        tTerms.add(readContent(t.getTerm().getContent()));
                        appendDescOrNote(t.getTermNote(), note);
                    }
                    appendDescOrNote(t.getDescripOrDescripGrpOrAdmin(), descTig);
                } else if (o instanceof Ntig) {
                    Ntig n = (Ntig) o;
                    if (sLang.equalsIgnoreCase(lang)) {
                        sTerms.add(readContent(n.getTermGrp().getTerm().getContent()));
                    } else if (tLang.equalsIgnoreCase(lang)) {
                        tTerms.add(readContent(n.getTermGrp().getTerm().getContent()));
                        appendDescOrNote(n.getTermGrp().getTermNoteOrTermNoteGrp(), note);
                    }
                    appendDescOrNote(n.getDescripOrDescripGrpOrAdmin(), descTig);
                }
            }
        }
        StringBuilder comment = new StringBuilder();
        appendLine(comment, descTerm.toString());
        appendLine(comment, descTig.toString());
        appendLine(comment, note.toString());
        for (String s : sTerms) {
            boolean addedForLang = false;
            for (String t : tTerms) {
                result.add(new GlossaryEntry(s, t, comment.toString(), priorityGlossary, origin));
                addedForLang = true;
            }
            if (!addedForLang) {
                // An entry is created just to get the definition
                result.add(new GlossaryEntry(s, "", comment.toString(), priorityGlossary, origin));
            }
        }
        sTerms.clear();
        tTerms.clear();
    }
    return result;
}

Example 37 with Language

use of org.omegat.util.Language in project omegat by omegat-org.

the class AlignFilePickerController method main.

/**
 * Entry point for debugging or standalone use. Optionally accepts four arguments to pre-fill the picker:
 * <ol>
 * <li>Source language
 * <li>Source file path
 * <li>Target language
 * <li>Target file path
 * </ol>
 *
 * @param args
 * @throws Exception
 */
public static void main(String[] args) throws Exception {
    System.setProperty("apple.laf.useScreenMenuBar", "true");
    Preferences.init();
    PluginUtils.loadPlugins(Collections.emptyMap());
    Core.setFilterMaster(new FilterMaster(FilterMaster.createDefaultFiltersConfig()));
    Core.setSegmenter(new Segmenter(SRX.getDefault()));
    AlignFilePickerController picker = new AlignFilePickerController();
    if (args.length == 4) {
        picker.sourceLanguage = new Language(args[0]);
        picker.sourceFile = args[1];
        picker.targetLanguage = new Language(args[2]);
        picker.targetFile = args[3];
    }
    picker.show(null);
}

Example 38 with Language

use of org.omegat.util.Language in project omegat by omegat-org.

the class ParseEntry method addEntryWithProperties.

/**
 * This method is called by filters to add new entry in OmegaT after read it from source file.
 *
 * @param id
 *            ID of entry, if format supports it
 * @param source
 *            Translatable source string
 * @param translation
 *            translation of the source string, if format supports it
 * @param isFuzzy
 *            flag for fuzzy translation. If a translation is fuzzy, it is not added to the projects TMX,
 *            but it is added to the generated 'reference' TMX, a special TMX that is used as extra
 *            reference during translation.
 * @param props
 *            a staggered array of non-uniquely-identifying key=value properties (metadata) for the entry
 * @param path
 *            path of entry in file
 * @param filter
 *            filter which produces entry
 * @param protectedParts
 *            protected parts
 */
@Override
public void addEntryWithProperties(String id, String source, String translation, boolean isFuzzy, String[] props, String path, IFilter filter, List<ProtectedPart> protectedParts) {
    if (StringUtil.isEmpty(source)) {
        // empty string - not need to save
        return;
    }
    if (props != null && props.length % 2 != 0) {
        throw new IllegalArgumentException("Entry properties must be in a key=value array with an even number of items.");
    }
    ParseEntryResult tmp = new ParseEntryResult();
    boolean removeSpaces = Core.getFilterMaster().getConfig().isRemoveSpacesNonseg();
    source = stripSomeChars(source, tmp, config.isRemoveTags(), removeSpaces);
    source = StringUtil.normalizeUnicode(source);
    if (config.isRemoveTags() && protectedParts != null) {
        for (int i = 0; i < protectedParts.size(); i++) {
            ProtectedPart p = protectedParts.get(i);
            String s = p.getTextInSourceSegment();
            s = PatternConsts.OMEGAT_TAG.matcher(s).replaceAll("");
            if (s.isEmpty()) {
                protectedParts.remove(i);
                i--;
            } else {
                p.setTextInSourceSegment(s);
            }
        }
    }
    if (translation != null) {
        translation = stripSomeChars(translation, tmp, config.isRemoveTags(), removeSpaces);
        translation = StringUtil.normalizeUnicode(translation);
    }
    if (config.isSentenceSegmentingEnabled()) {
        List<StringBuilder> spaces = new ArrayList<StringBuilder>();
        List<Rule> brules = new ArrayList<Rule>();
        Language sourceLang = config.getSourceLanguage();
        List<String> segments = Core.getSegmenter().segment(sourceLang, source, spaces, brules);
        if (segments.size() == 1) {
            internalAddSegment(id, (short) 0, segments.get(0), translation, isFuzzy, props, path, protectedParts);
        } else {
            for (short i = 0; i < segments.size(); i++) {
                String onesrc = segments.get(i);
                List<ProtectedPart> segmentProtectedParts = ProtectedPart.extractFor(protectedParts, onesrc);
                internalAddSegment(id, i, onesrc, null, false, props, path, segmentProtectedParts);
            }
        }
    } else {
        internalAddSegment(id, (short) 0, source, translation, isFuzzy, props, path, protectedParts);
    }
}

Example 39 with Language

use of org.omegat.util.Language in project omegat by omegat-org.

the class RealProject method loadOtherLanguages.

/**
 * Locates and loads external TMX files with legacy translations. Uses directory monitor for check file
 * updates.
 */
private void loadOtherLanguages() throws IOException {
    File tmOtherLanguagesRoot = new File(config.getTMOtherLangRoot());
    tmOtherLanguagesMonitor = new DirectoryMonitor(tmOtherLanguagesRoot, file -> {
        String name = file.getName();
        if (!name.matches("[A-Z]{2}([-_][A-Z]{2})?\\.tmx")) {
            // not a TMX file in XX_XX.tmx format
            return;
        }
        Language targetLanguage = new Language(name.substring(0, name.length() - ".tmx".length()));
        // create new translation memories map
        Map<Language, ProjectTMX> newOtherTargetLangTMs = new TreeMap<>(otherTargetLangTMs);
        if (file.exists()) {
            try {
                ProjectTMX newTMX = new ProjectTMX(config.getSourceLanguage(), targetLanguage, config.isSentenceSegmentingEnabled(), file, checkOrphanedCallback);
                newOtherTargetLangTMs.put(targetLanguage, newTMX);
            } catch (Exception e) {
                String filename = file.getPath();
                Log.logErrorRB(e, "TF_TM_LOAD_ERROR", filename);
                Core.getMainWindow().displayErrorRB(e, "TF_TM_LOAD_ERROR", filename);
            }
        } else {
            newOtherTargetLangTMs.remove(targetLanguage);
        }
        otherTargetLangTMs = newOtherTargetLangTMs;
    });
    tmOtherLanguagesMonitor.checkChanges();
    tmOtherLanguagesMonitor.start();
}

Example 40 with Language

use of org.omegat.util.Language in project omegat by omegat-org.

the class TranslateEntry method getTranslation.

/**
 * {@inheritDoc}
 */
@Override
public String getTranslation(final String id, final String origSource, final String path) {
    ParseEntry.ParseEntryResult spr = new ParseEntry.ParseEntryResult();
    // fix for bug 3487497;
    // Fetch removed tags if the options
    // has been enabled.
    String tags = null;
    if (config.isRemoveTags()) {
        tags = TagUtil.buildTagListForRemove(origSource);
    }
    boolean removeSpaces = Core.getFilterMaster().getConfig().isRemoveSpacesNonseg();
    final String source = StringUtil.normalizeUnicode(ParseEntry.stripSomeChars(origSource, spr, config.isRemoveTags(), removeSpaces));
    StringBuilder res = new StringBuilder();
    if (config.isSentenceSegmentingEnabled()) {
        boolean translated = false;
        List<StringBuilder> spaces = new ArrayList<StringBuilder>();
        List<Rule> brules = new ArrayList<Rule>();
        Language sourceLang = config.getSourceLanguage();
        Language targetLang = config.getTargetLanguage();
        List<String> segments = Core.getSegmenter().segment(sourceLang, source, spaces, brules);
        for (int i = 0; i < segments.size(); i++) {
            String onesrc = segments.get(i);
            String tr = internalGetSegmentTranslation(id, i, onesrc, path);
            if (tr == null) {
                tr = onesrc;
            } else {
                translated = true;
            }
            segments.set(i, tr);
        }
        if (!translated) {
            // there is no even one translated segment
            return null;
        }
        res.append(Core.getSegmenter().glue(sourceLang, targetLang, segments, spaces, brules));
    } else {
        String tr = internalGetSegmentTranslation(id, 0, source, path);
        if (tr == null) {
            // non-translated
            return null;
        }
        res.append(tr);
    }
    // replacing all occurrences of LF (\n) by either single CR (\r) or CRLF
    // (\r\n)
    // this is a reversal of the process at the beginning of this method
    // fix for bug 1462566
    String r = res.toString();
    // - Word: anything placed before the leading tag is omitted in translated document
    // https://sourceforge.net/p/omegat/bugs/634/
    // This is a Word document, Remove Tags (from Project Properties) is not checked and Remove leading and
    // trailing tags (from File Filters) is not checked
    String fileName = getCurrentFile().toLowerCase(Locale.ENGLISH);
    if ((fileName.endsWith(".docx") || fileName.endsWith(".docm")) && !config.isRemoveTags() && !Core.getFilterMaster().getConfig().isRemoveTags()) {
        // Locate the location of the first tag
        String firstTag = TagUtil.getFirstTag(r);
        if (firstTag != null) {
            int locFirstTag = r.indexOf(firstTag);
            // Is there text before that first tag?
            if (locFirstTag > 0) {
                // Was the first tag between two words without any spaces around?
                String addSpace = "";
                if (!Character.isWhitespace(r.codePointBefore(locFirstTag)) && !Character.isWhitespace(r.codePointAt(locFirstTag + firstTag.length())) && Core.getProject().getProjectProperties().getTargetLanguage().isSpaceDelimited()) {
                    addSpace = " ";
                }
                // Move that first tag before the text, adding a space if needed.
                r = firstTag + r.substring(0, locFirstTag) + addSpace + r.substring(locFirstTag + firstTag.length());
            }
        }
    }
    // the end of the translated string.
    if (config.isRemoveTags()) {
        r += tags;
    }
    if (spr.crlf) {
        r = r.replace("\n", "\r\n");
    } else if (spr.cr) {
        r = r.replace("\n", "\r");
    }
    if (spr.spacesAtBegin > 0) {
        r = origSource.substring(0, spr.spacesAtBegin) + r;
    }
    if (spr.spacesAtEnd > 0) {
        r = r + origSource.substring(origSource.length() - spr.spacesAtEnd);
    }
    return r;
}