Examples with SourceTextEntry org.omegat.core.data.SourceTextEntry used on opensource projects

Example 36 with SourceTextEntry

use of org.omegat.core.data.SourceTextEntry in project omegat by omegat-org.

the class CalcMatchStatistics method forFile.

MatchStatCounts forFile(IProject.FileInfo fi) {
    MatchStatCounts result = new MatchStatCounts();
    alreadyProcessedInFile.clear();
    final List<SourceTextEntry> untranslatedEntries = new ArrayList<SourceTextEntry>();
    // We should iterate all segments from file.
    for (SourceTextEntry ste : fi.entries) {
        checkInterrupted();
        StatCount count = new StatCount(ste);
        boolean existInFile = alreadyProcessedInFile.contains(ste.getSrcText());
        boolean existInPreviousFiles = alreadyProcessedInProject.contains(ste.getSrcText());
        if (Core.getProject().getTranslationInfo(ste).isTranslated()) {
            // segment has translation - should be calculated as
            // "Exact matched"
            result.addExact(count);
            treated++;
        } else if (existInPreviousFiles) {
            // exist in other file
            result.addRepetitionFromOtherFiles(count);
            entryProcessed();
        } else if (existInFile) {
            // exist in this file
            result.addRepetitionWithinThisFile(count);
            entryProcessed();
        } else {
            // first time
            untranslatedEntries.add(ste);
            alreadyProcessedInFile.add(ste.getSrcText());
        }
    }
    alreadyProcessedInProject.addAll(alreadyProcessedInFile);
    calcSimilarity(untranslatedEntries).ifPresent(result::addCounts);
    return result;
}

Example 37 with SourceTextEntry

use of org.omegat.core.data.SourceTextEntry in project omegat by omegat-org.

the class CalcStandardStatistics method buildProjectStats.

/**
 * Builds a file with statistic info about the project. The total word &
 * character count of the project, the total number of unique segments, plus
 * the details for each file.
 */
public static String buildProjectStats(final IProject project, final StatisticsInfo hotStat, final StatisticsPanel callback) {
    StatCount total = new StatCount();
    StatCount remaining = new StatCount();
    StatCount unique = new StatCount();
    StatCount remainingUnique = new StatCount();
    // find unique segments
    Map<String, SourceTextEntry> uniqueSegment = new HashMap<String, SourceTextEntry>();
    Set<String> translated = new HashSet<String>();
    for (SourceTextEntry ste : project.getAllEntries()) {
        String src = ste.getSrcText();
        for (ProtectedPart pp : ste.getProtectedParts()) {
            src = src.replace(pp.getTextInSourceSegment(), pp.getReplacementUniquenessCalculation());
        }
        if (!uniqueSegment.containsKey(src)) {
            uniqueSegment.put(src, ste);
        }
        TMXEntry tr = project.getTranslationInfo(ste);
        if (tr.isTranslated()) {
            translated.add(src);
        }
    }
    Set<String> filesUnique = new HashSet<String>();
    Set<String> filesRemainingUnique = new HashSet<String>();
    for (Map.Entry<String, SourceTextEntry> en : uniqueSegment.entrySet()) {
        /* Number of words and chars calculated without all tags and protected parts. */
        StatCount count = new StatCount(en.getValue());
        // add to unique
        unique.add(count);
        filesUnique.add(en.getValue().getKey().file);
        // add to unique remaining
        if (!translated.contains(en.getKey())) {
            remainingUnique.add(count);
            filesRemainingUnique.add(en.getValue().getKey().file);
        }
    }
    unique.addFiles(filesUnique.size());
    remainingUnique.addFiles(filesRemainingUnique.size());
    List<FileData> counts = new ArrayList<FileData>();
    Map<String, Boolean> firstSeenUniqueSegment = new HashMap<String, Boolean>();
    for (FileInfo file : project.getProjectFiles()) {
        FileData numbers = new FileData();
        numbers.filename = file.filePath;
        counts.add(numbers);
        int fileTotal = 0;
        int fileRemaining = 0;
        for (SourceTextEntry ste : file.entries) {
            String src = ste.getSrcText();
            for (ProtectedPart pp : ste.getProtectedParts()) {
                src = src.replace(pp.getTextInSourceSegment(), pp.getReplacementUniquenessCalculation());
            }
            /* Number of words and chars calculated without all tags and protected parts. */
            StatCount count = new StatCount(ste);
            // add to total
            total.add(count);
            fileTotal = 1;
            // add to remaining
            TMXEntry tr = project.getTranslationInfo(ste);
            if (!tr.isTranslated()) {
                remaining.add(count);
                fileRemaining = 1;
            }
            // add to file's info
            numbers.total.add(count);
            Boolean firstSeen = firstSeenUniqueSegment.get(src);
            if (firstSeen == null) {
                firstSeenUniqueSegment.put(src, false);
                numbers.unique.add(count);
                if (!tr.isTranslated()) {
                    numbers.remainingUnique.add(count);
                }
            }
            if (!tr.isTranslated()) {
                numbers.remaining.add(count);
            }
        }
        total.addFiles(fileTotal);
        remaining.addFiles(fileRemaining);
    }
    StringBuilder result = new StringBuilder();
    result.append(OStrings.getString("CT_STATS_Project_Statistics"));
    result.append("\n\n");
    String[][] headerTable = calcHeaderTable(new StatCount[] { total, remaining, unique, remainingUnique });
    if (callback != null) {
        callback.setProjectTableData(HT_HEADERS, headerTable);
    }
    result.append(TextUtil.showTextTable(HT_HEADERS, headerTable, HT_ALIGN));
    result.append("\n\n");
    // STATISTICS BY FILE
    result.append(OStrings.getString("CT_STATS_FILE_Statistics"));
    result.append("\n\n");
    String[][] filesTable = calcFilesTable(project.getProjectProperties(), counts);
    if (callback != null) {
        callback.setFilesTableData(FT_HEADERS, filesTable);
    }
    result.append(TextUtil.showTextTable(FT_HEADERS, filesTable, FT_ALIGN));
    if (hotStat != null) {
        hotStat.numberOfSegmentsTotal = total.segments;
        hotStat.numberofTranslatedSegments = translated.size();
        hotStat.numberOfUniqueSegments = unique.segments;
        hotStat.uniqueCountsByFile.clear();
        for (FileData fd : counts) {
            hotStat.uniqueCountsByFile.put(fd.filename, fd.unique.segments);
        }
    }
    return result.toString();
}