Example usage for java.io FileWriter close

List of usage examples for java.io FileWriter close

Introduction

In this page you can find the example usage for java.io FileWriter close.

Prototype

public void close() throws IOException 

Source Link

Usage

From source file:com.npower.dm.util.ConvertMailProfile.java

/**
 * @param args/*from  w w  w  .  j  av a 2  s .  co m*/
 */
public static void main(String[] args) throws Exception {
    File outputFile = new File("c:/temp/mail.xml");
    FileWriter writer = new FileWriter(outputFile);

    File csvFile = new File("c:/temp/mail.csv");
    BufferedReader reader = new BufferedReader(new FileReader(csvFile));
    String line = reader.readLine();
    while (line != null) {
        line = reader.readLine();
        if (StringUtils.isEmpty(line)) {
            continue;
        }

        String[] cols = StringUtils.split(line, ',');
        Map<String, String> values = new HashMap<String, String>();
        values.put("name", cols[0]);
        values.put("smtp.host", cols[1]);
        values.put("pop.host", cols[2]);

        writeXML(writer, values);
    }

    writer.close();
    reader.close();
}

From source file:eu.smartfp7.foursquare.AttendanceCrawler.java

/**
 * The main takes an undefined number of cities as arguments, then initializes
 * the specific crawling of all the trending venues of these cities.
 * The trending venues must have been previously identified using the `DownloadPages`
 * program.//w  ww .  j a  v a 2  s  . c  o  m
 * 
 * Current valid cities are: london, amsterdam, goldcoast, sanfrancisco.
 * 
 */
public static void main(String[] args) throws Exception {
    Settings settings = Settings.getInstance();
    String folder = settings.getFolder();

    // We keep info and error logs, so that we know what happened in case
    // of incoherence in the time series.
    Map<String, FileWriter> info_logs = new HashMap<String, FileWriter>();
    Map<String, FileWriter> error_logs = new HashMap<String, FileWriter>();

    // For each city we monitor, we store the venue IDs that we got from
    // a previous crawl.
    Map<String, Collection<String>> city_venues = new HashMap<String, Collection<String>>();

    // Contains the epoch time when the last API call has been made for each 
    // venue. Ensures that we get data only once each hour. 
    Map<String, Long> venue_last_call = new HashMap<String, Long>();

    // Contains the epoch time when we last checked if time series were broken
    // for each city.
    // We do these checks once every day before the batch forecasting begins.
    Map<String, Long> sanity_checks = new HashMap<String, Long>();

    // We also keep in memory the number of checkins for the last hour for
    // each venue.
    Map<String, Integer> venue_last_checkin = new HashMap<String, Integer>();

    Map<Long, Integer> APICallsCount = new HashMap<Long, Integer>();

    DateFormat df = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss");

    int total_venues = 0;
    long total_calls = 0;
    long time_spent_on_API = 0;

    for (String c : args) {
        settings.checkFileHierarchy(c);

        city_venues.put(c, loadVenues(c));
        total_venues += city_venues.get(c).size();

        info_logs.put(c,
                new FileWriter(folder + c + File.separator + "log" + File.separator + "info.log", true));
        error_logs.put(c,
                new FileWriter(folder + c + File.separator + "log" + File.separator + "error.log", true));

        Calendar cal = Calendar.getInstance();

        info_logs.get(c).write("[" + df.format(cal.getTime()) + "] Crawler initialization for " + c + ". "
                + city_venues.get(c).size() + " venues loaded.\n");
        info_logs.get(c).flush();

        // If we interrupted the program for some reason, we can get back
        // the in-memory data.
        // Important: the program must not be interrupted for more than one
        // hour, or we will lose time series data.
        for (String venue_id : city_venues.get(c)) {
            String ts_file = folder + c + File.separator + "attendances_crawl" + File.separator + venue_id
                    + ".ts";

            if (new File(ts_file).exists()) {
                BufferedReader buffer = new BufferedReader(new FileReader(ts_file));
                String mem = null, line = null;
                for (; (line = buffer.readLine()) != null; mem = line)
                    ;
                buffer.close();

                if (mem == null)
                    continue;

                String[] tmp = mem.split(",");
                venue_last_call.put(venue_id, df.parse(tmp[0]).getTime());
                venue_last_checkin.put(venue_id, Integer.parseInt(tmp[3]));

                VenueUtil.fixBrokenTimeSeriesVenue(new File(ts_file));
            } // if
        } // for

        sanity_checks.put(c, cal.getTimeInMillis());
    } // for

    if (total_venues > 5000) {
        System.out.println(
                "Too much venues for a single API account (max 5000).\nPlease create a new Foursquare API account and use these credentials.\nExiting now.");
        return;
    }

    while (true) {

        for (String c : args) {
            // We create a FIFO queue and pop venue IDs one at a time.
            LinkedList<String> city_venues_buffer = new LinkedList<String>(city_venues.get(c));
            String venue_id = null;

            // Artificial wait to avoid processors looping at 100% of their capacity
            // when there is no more venues to crawl for the current hour.
            Thread.sleep(3000);

            while ((venue_id = city_venues_buffer.pollFirst()) != null) {
                // We get the current time according to the city's time zone
                Calendar cal = Calendar.getInstance();
                cal.add(Calendar.MILLISECOND,
                        TimeZone.getTimeZone(settings.getCityTimezone(c)).getOffset(cal.getTime().getTime())
                                - Calendar.getInstance().getTimeZone().getOffset(cal.getTime().getTime()));
                //TimeZone.getTimeZone("Europe/London").getOffset(cal.getTime().getTime()));

                long current_time = DateUtils.truncate(cal.getTime(), Calendar.HOUR).getTime();

                // We query Foursquare only once per hour per venue.
                if (venue_last_call.get(venue_id) != null
                        && current_time < venue_last_call.get(venue_id) + 3600000)
                    continue;

                intelligentWait(total_venues, cal.getTime().getTime(),
                        (total_calls == 0 ? 0 : Math.round(time_spent_on_API / total_calls)));

                Venue venue = null;

                try {
                    long beforeCall = System.currentTimeMillis();
                    venue = new Venue(getFoursquareVenueById(venue_id, c));

                    // If there is no last call, this is the beginning of the time series
                    // for this venue. We get the number of people "here now" to initialize
                    // the series.
                    if (venue_last_call.get(venue_id) == null) {
                        /** TODO: by doing this, we keep a representation of the venue dating from the beginning
                         *       of the specific crawl. we might want to change this and update this file once
                         *      in a while.
                         */
                        FileWriter info = new FileWriter(folder + c + File.separator + "foursquare_venues"
                                + File.separator + venue_id + ".info");
                        info.write(venue.getFoursquareJson());
                        info.close();

                        FileWriter out = new FileWriter(folder + c + File.separator + "attendances_crawl"
                                + File.separator + venue_id + ".ts");
                        out.write("Date,here_now,hour_checkins,total_checkins\n");
                        out.write(df.format(current_time) + "," + venue.getHereNow() + "," + venue.getHereNow()
                                + "," + venue.getCheckincount() + "\n");
                        out.close();
                    } else {
                        FileWriter out = new FileWriter(folder + c + File.separator + "attendances_crawl"
                                + File.separator + venue_id + ".ts", true);
                        int checks = venue.getCheckincount() - venue_last_checkin.get(venue_id);
                        out.write(df.format(current_time) + "," + venue.getHereNow() + ","
                                + Integer.toString(checks) + "," + venue.getCheckincount() + "\n");
                        out.close();
                    }

                    if (APICallsCount.get(current_time) == null)
                        APICallsCount.put(current_time, 1);
                    else
                        APICallsCount.put(current_time, APICallsCount.get(current_time) + 1);

                    total_calls++;

                    venue_last_call.put(venue_id, current_time);
                    venue_last_checkin.put(venue_id, venue.getCheckincount());

                    time_spent_on_API += System.currentTimeMillis() - beforeCall;
                } catch (Exception e) {
                    // If something bad happens (crawler not available, IO error, ...), we put the
                    // venue_id in the FIFO queue so that it gets reevaluated later.
                    //e.printStackTrace();
                    error_logs.get(c)
                            .write("[" + df.format(cal.getTime().getTime()) + "] Error with venue " + venue_id
                                    + " (" + e.getMessage() + "). " + APICallsCount.get(current_time)
                                    + " API calls so far this hour, " + city_venues_buffer.size()
                                    + " venues remaining in the buffer.\n");
                    error_logs.get(c).flush();

                    System.out.println("[" + df.format(cal.getTime().getTime()) + "] " + c + " -- "
                            + APICallsCount.get(current_time) + " API calls // " + city_venues_buffer.size()
                            + " venues remaining " + " (" + e.getMessage() + ")");

                    if (e instanceof FoursquareAPIException)
                        if (((FoursquareAPIException) e).getHttp_code().equals("400")
                                && ((FoursquareAPIException) e).getError_detail()
                                        .equals("Venue " + venue_id + " has been deleted")) {
                            city_venues.get(c).remove(venue_id);
                            removeVenue(venue_id, c);
                        } else
                            city_venues_buffer.add(venue_id);

                    continue;
                }
            } // while

            // Every day between 0am and 2am, we repair all the broken time series (if there
            // is something to repair).
            Calendar cal = Calendar.getInstance();
            if (city_venues_buffer.peekFirst() == null
                    && (cal.getTimeInMillis() - sanity_checks.get(c)) >= 86400000
                    && cal.get(Calendar.HOUR_OF_DAY) < 2) {
                VenueUtil.fixBrokenTimeSeriesCity(c, folder);
                sanity_checks.put(c, cal.getTimeInMillis());
                info_logs.get(c).write("[" + df.format(cal.getTime()) + "] Sanity check OK.\n");
                info_logs.get(c).flush();
            }
        } // for
    } // while
}

From source file:br.edu.ufcg.lsd.oursim.ui.CLI.java

/**
 * Exemplo://  w  ww  .  java2  s  . c o m
 * 
 * <pre>
 *   java -jar oursim.jar -w resources/trace_filtrado_primeiros_1000_jobs.txt -m resources/hostinfo_sdsc.dat -synthetic_av -o oursim_trace.txt
 *   -w resources/trace_filtrado_primeiros_1000_jobs.txt -s persistent -nr 20 -md resources/hostinfo_sdsc.dat -av resources/disponibilidade.txt -o oursim_trace.txt
 *   -w resources/new_iosup_workload.txt -s persistent -pd resources/iosup_site_description.txt -wt iosup -nr 1 -synthetic_av -o oursim_trace.txt
 *   -w resources/new_workload.txt -s persistent -pd resources/marcus_site_description.txt -wt marcus -nr 20 -d -o oursim_trace.txt
 *   1 ms + 1 dia = 2678400 segundos
 * </pre>
 * 
 * @param args
 * @throws FileNotFoundException
 */
public static void main(String[] args) throws IOException {

    StopWatch stopWatch = new StopWatch();
    stopWatch.start();
    List<Closeable> closeables = new ArrayList<Closeable>();

    CommandLine cmd = parseCommandLine(args, prepareOptions(), HELP, USAGE, EXECUTION_LINE);

    File outputFile = (File) cmd.getOptionObject(OUTPUT);
    PrintOutput printOutput = new PrintOutput(outputFile, false);
    JobEventDispatcher.getInstance().addListener(printOutput);
    closeables.add(printOutput);
    if (cmd.hasOption(EXTRACT_REMOTE_WORKLOAD)) {
        File remoteWorkloadFile = (File) cmd.getOptionObject(EXTRACT_REMOTE_WORKLOAD);
        Output remoteWorkloadExtractor = new RemoteTasksExtractorOutput(remoteWorkloadFile);
        closeables.add(remoteWorkloadExtractor);
        JobEventDispatcher.getInstance().addListener(remoteWorkloadExtractor);
    }
    Grid grid = prepareGrid(cmd);

    ComputingElementEventCounter computingElementEventCounter = prepareOutputAccounting(cmd,
            cmd.hasOption(VERBOSE));

    Input<? extends AvailabilityRecord> availability = defineAvailability(cmd, grid.getMapOfPeers());

    prepareOptionalOutputFiles(cmd, grid, (SyntheticAvailabilityCharacterizationAbstract) availability,
            closeables);

    long timeOfFirstSubmission = cmd.getOptionValue(WORKLOAD_TYPE).equals("gwa")
            ? GWAFormat.extractSubmissionTimeFromFirstJob(cmd.getOptionValue(WORKLOAD))
            : 0;
    Workload workload = defineWorkloadType(cmd, cmd.getOptionValue(WORKLOAD), grid.getMapOfPeers(),
            timeOfFirstSubmission);

    JobSchedulerPolicy jobScheduler = defineScheduler(cmd, grid.getListOfPeers());

    OurSim oursim = new OurSim(EventQueue.getInstance(), grid, jobScheduler, workload, availability);

    oursim.setActiveEntity(new ActiveEntityImp());

    if (cmd.hasOption(HALT_SIMULATION)) {
        oursim.addHaltEvent(((Number) cmd.getOptionObject(HALT_SIMULATION)).longValue());
    }

    oursim.start();

    for (Closeable c : closeables) {
        c.close();
    }

    EventQueue.getInstance().clear();

    // adiciona mtricas-resumo ao fim do arquivo
    FileWriter fw = new FileWriter(cmd.getOptionValue(OUTPUT), true);
    closeables.add(fw);
    stopWatch.stop();
    fw.write("# Simulation                  duration:" + stopWatch + ".\n");

    double utilization = grid.getUtilization();
    double realUtilization = grid.getTrueUtilization();

    int numberOfResourcesByPeer = Integer.parseInt(cmd.getOptionValue(NUM_RESOURCES_BY_PEER, "0"));
    fw.write(formatSummaryStatistics(computingElementEventCounter, "NA", "NA", false, grid.getPeers().size(),
            numberOfResourcesByPeer, utilization, realUtilization, stopWatch.getTime()) + "\n");
    fw.close();

    System.out.println(
            getSummaryStatistics(computingElementEventCounter, "NA", "NA", false, grid.getPeers().size(),
                    numberOfResourcesByPeer, utilization, realUtilization, stopWatch.getTime()));

}

From source file:de.tudarmstadt.ukp.experiments.dip.wp1.documents.Step8GoldDataAggregator.java

public static void main(String[] args) throws Exception {
    String inputDir = args[0] + "/";
    // output dir
    File outputDir = new File(args[1]);
    File turkersConfidence = new File(args[2]);
    if (outputDir.exists()) {
        outputDir.delete();//from www .  j  a v  a2  s .c  o m
    }
    outputDir.mkdir();

    List<String> annotatorsIDs = new ArrayList<>();
    //        for (File f : FileUtils.listFiles(new File(inputDir), new String[] { "xml" }, false)) {
    //            QueryResultContainer queryResultContainer = QueryResultContainer
    //                    .fromXML(FileUtils.readFileToString(f, "utf-8"));
    //            for (QueryResultContainer.SingleRankedResult rankedResults : queryResultContainer.rankedResults) {
    //                for (QueryResultContainer.MTurkRelevanceVote relevanceVote : rankedResults.mTurkRelevanceVotes) {
    //                    if (!annotatorsIDs.contains(relevanceVote.turkID))
    //                        annotatorsIDs.add(relevanceVote.turkID);
    //                }
    //            }
    //        }
    HashMap<String, Integer> countVotesForATurker = new HashMap<>();
    // creates temporary file with format for mace
    // Hashmap annotations: key is the id of a document and a sentence
    // Value is an array votes[] of turkers decisions: true or false (relevant or not)
    // the length of this array equals the number of annotators in List<String> annotatorsIDs.
    // If an annotator worked on the task his decision is written in the array otherwise the value is NULL

    // key: queryID + clueWebID + sentenceID
    // value: true and false annotations
    TreeMap<String, Annotations> annotations = new TreeMap<>();

    for (File f : FileUtils.listFiles(new File(inputDir), new String[] { "xml" }, false)) {
        QueryResultContainer queryResultContainer = QueryResultContainer
                .fromXML(FileUtils.readFileToString(f, "utf-8"));
        System.out.println("Reading " + f.getName());
        for (QueryResultContainer.SingleRankedResult rankedResults : queryResultContainer.rankedResults) {
            String documentID = rankedResults.clueWebID;
            for (QueryResultContainer.MTurkRelevanceVote relevanceVote : rankedResults.mTurkRelevanceVotes) {
                Integer turkerID;
                if (!annotatorsIDs.contains(relevanceVote.turkID)) {
                    annotatorsIDs.add(relevanceVote.turkID);
                    turkerID = annotatorsIDs.size() - 1;
                } else {
                    turkerID = annotatorsIDs.indexOf(relevanceVote.turkID);
                }
                Integer count = countVotesForATurker.get(relevanceVote.turkID);
                if (count == null) {
                    count = 0;
                }
                count++;
                countVotesForATurker.put(relevanceVote.turkID, count);

                String id;
                List<Integer> trueVotes;
                List<Integer> falseVotes;
                for (QueryResultContainer.SingleSentenceRelevanceVote singleSentenceRelevanceVote : relevanceVote.singleSentenceRelevanceVotes)
                    if (!"".equals(singleSentenceRelevanceVote.sentenceID)) {

                        id = f.getName() + "_" + documentID + "_" + singleSentenceRelevanceVote.sentenceID;
                        Annotations turkerVotes = annotations.get(id);
                        if (turkerVotes == null) {
                            trueVotes = new ArrayList<>();
                            falseVotes = new ArrayList<>();
                            turkerVotes = new Annotations(trueVotes, falseVotes);
                        }
                        trueVotes = turkerVotes.trueAnnotations;
                        falseVotes = turkerVotes.falseAnnotations;
                        if ("true".equals(singleSentenceRelevanceVote.relevant)) {
                            // votes[turkerID] = true;
                            trueVotes.add(turkerID);
                        } else if ("false".equals(singleSentenceRelevanceVote.relevant)) {
                            //   votes[turkerID] = false;
                            falseVotes.add(turkerID);
                        } else {
                            throw new IllegalStateException("Annotation value of sentence "
                                    + singleSentenceRelevanceVote.sentenceID + " in " + rankedResults.clueWebID
                                    + " equals " + singleSentenceRelevanceVote.relevant);
                        }
                        try {
                            int allVotesCount = trueVotes.size() + falseVotes.size();
                            if (allVotesCount > 5) {
                                System.err.println(id + " doesn't have 5 annotators: true: " + trueVotes.size()
                                        + " false: " + falseVotes.size());

                                // nasty hack, we're gonna strip some data; true votes first
                                /* we can't do that, it breaks something down the line
                                int toRemove = allVotesCount - 5;
                                if (trueVotes.size() >= toRemove) {
                                trueVotes = trueVotes
                                        .subList(0, trueVotes.size() - toRemove);
                                }
                                else if (
                                    falseVotes.size() >= toRemove) {
                                falseVotes = falseVotes
                                        .subList(0, trueVotes.size() - toRemove);
                                }
                                */
                                System.err.println("Adjusted: " + id + " doesn't have 5 annotators: true: "
                                        + trueVotes.size() + " false: " + falseVotes.size());
                            }
                        } catch (IllegalStateException e) {
                            e.printStackTrace();
                        }
                        turkerVotes.trueAnnotations = trueVotes;
                        turkerVotes.falseAnnotations = falseVotes;
                        annotations.put(id, turkerVotes);
                    } else {
                        throw new IllegalStateException(
                                "Empty Sentence ID in " + f.getName() + " for turker " + turkerID);
                    }

            }
        }

    }
    File tmp = printHashMap(annotations, annotatorsIDs.size());

    String file = TEMP_DIR + "/" + tmp.getName();
    MACE.main(new String[] { "--prefix", file });

    //gets the keys of the documents and sentences
    ArrayList<String> lines = (ArrayList<String>) FileUtils.readLines(new File(file + ".prediction"));
    int i = 0;
    TreeMap<String, TreeMap<String, ArrayList<HashMap<String, String>>>> ids = new TreeMap<>();
    ArrayList<HashMap<String, String>> sentences;
    if (lines.size() != annotations.size()) {
        throw new IllegalStateException(
                "The size of prediction file is " + lines.size() + "but expected " + annotations.size());
    }
    for (Map.Entry entry : annotations.entrySet()) { //1001.xml_clueweb12-1905wb-13-07360_8783
        String key = (String) entry.getKey();
        String[] IDs = key.split("_");
        if (IDs.length > 2) {
            String queryID = IDs[0];
            String clueWebID = IDs[1];
            String sentenceID = IDs[2];
            TreeMap<String, ArrayList<HashMap<String, String>>> clueWebIDs = ids.get(queryID);
            if (clueWebIDs == null) {
                clueWebIDs = new TreeMap<>();
            }
            sentences = clueWebIDs.get(clueWebID);
            if (sentences == null) {
                sentences = new ArrayList<>();
            }
            HashMap<String, String> sentence = new HashMap<>();
            sentence.put(sentenceID, lines.get(i));
            sentences.add(sentence);
            clueWebIDs.put(clueWebID, sentences);
            ids.put(queryID, clueWebIDs);
        } else {
            throw new IllegalStateException("Wrong ID " + key);
        }

        i++;
    }

    for (Map.Entry entry : ids.entrySet()) {
        TreeMap<Integer, String> value = (TreeMap<Integer, String>) entry.getValue();
        String queryID = (String) entry.getKey();
        QueryResultContainer queryResultContainer = QueryResultContainer
                .fromXML(FileUtils.readFileToString(new File(inputDir, queryID), "utf-8"));
        for (QueryResultContainer.SingleRankedResult rankedResults : queryResultContainer.rankedResults) {
            for (Map.Entry val : value.entrySet()) {
                String clueWebID = (String) val.getKey();
                if (clueWebID.equals(rankedResults.clueWebID)) {
                    List<QueryResultContainer.SingleSentenceRelevanceVote> goldEstimatedLabels = new ArrayList<>();
                    List<QueryResultContainer.SingleSentenceRelevanceVote> turkersVotes = new ArrayList<>();
                    int size = 0;
                    int hitSize = 0;
                    String hitID = "";
                    for (QueryResultContainer.MTurkRelevanceVote vote : rankedResults.mTurkRelevanceVotes) {
                        if (!hitID.equals(vote.hitID)) {
                            hitID = vote.hitID;
                            hitSize = vote.singleSentenceRelevanceVotes.size();
                            size = size + hitSize;
                            turkersVotes.addAll(vote.singleSentenceRelevanceVotes);
                        } else {
                            if (vote.singleSentenceRelevanceVotes.size() != hitSize) {
                                hitSize = vote.singleSentenceRelevanceVotes.size();
                                size = size + hitSize;
                                turkersVotes.addAll(vote.singleSentenceRelevanceVotes);
                            }
                        }
                    }
                    ArrayList<HashMap<String, String>> sentenceList = (ArrayList<HashMap<String, String>>) val
                            .getValue();
                    if (sentenceList.size() != turkersVotes.size()) {
                        try {
                            throw new IllegalStateException("Expected size of annotations is "
                                    + turkersVotes.size() + "but found " + sentenceList.size()
                                    + " for document " + rankedResults.clueWebID + " in " + queryID);
                        } catch (IllegalStateException ex) {
                            ex.printStackTrace();
                        }
                    }
                    for (QueryResultContainer.SingleSentenceRelevanceVote s : turkersVotes) {
                        String valSentence = null;
                        for (HashMap<String, String> anno : sentenceList) {
                            if (anno.keySet().contains(s.sentenceID)) {
                                valSentence = anno.get(s.sentenceID);
                            }
                        }
                        QueryResultContainer.SingleSentenceRelevanceVote singleSentenceVote = new QueryResultContainer.SingleSentenceRelevanceVote();
                        singleSentenceVote.sentenceID = s.sentenceID;
                        if (("false").equals(valSentence)) {
                            singleSentenceVote.relevant = "false";
                        } else if (("true").equals(valSentence)) {
                            singleSentenceVote.relevant = "true";
                        } else {
                            throw new IllegalStateException("Annotation value of sentence "
                                    + singleSentenceVote.sentenceID + " equals " + val.getValue());
                        }
                        goldEstimatedLabels.add(singleSentenceVote);
                    }
                    rankedResults.goldEstimatedLabels = goldEstimatedLabels;
                }
            }
        }
        File outputFile = new File(outputDir, queryID);
        FileUtils.writeStringToFile(outputFile, queryResultContainer.toXML(), "utf-8");
        System.out.println("Finished " + outputFile);
    }

    ArrayList<String> annotators = (ArrayList<String>) FileUtils.readLines(new File(file + ".competence"));
    FileWriter fileWriter;
    StringBuilder sb = new StringBuilder();
    for (int j = 0; j < annotatorsIDs.size(); j++) {
        String[] s = annotators.get(0).split("\t");
        Float score = Float.parseFloat(s[j]);
        String turkerID = annotatorsIDs.get(j);
        System.out.println(turkerID + " " + score + " " + countVotesForATurker.get(turkerID));
        sb.append(turkerID).append(" ").append(score).append(" ").append(countVotesForATurker.get(turkerID))
                .append("\n");
    }
    fileWriter = new FileWriter(turkersConfidence);
    fileWriter.append(sb.toString());
    fileWriter.close();

}

From source file:com.waku.mmdataextract.ComprehensiveSearch.java

@SuppressWarnings("unchecked")
public static void main(String[] args) {
    FileWriter fw = null;
    try {/*from ww w.  ja  v a 2 s.  c o m*/
        fw = new FileWriter(new File("output/ComprehensiveSearch.csv"));
        fw.write(
                ",??,?,?,,?,??,,?,1,2,3,\n");
    } catch (IOException e) {
        e.printStackTrace();
    }
    Document firstPage = MyHttpClient.getAsDom4jDoc(START_ACTION);
    // System.out.println(doc.asXML());
    List<Element> brandOptions = firstPage.selectNodes("//select[@name='brandId']/option");
    for (Element brandOption : brandOptions) {
        String brandId = brandOption.attributeValue("value");
        if (!brandId.equalsIgnoreCase("0")) {
            for (int i = 1; true; i++) {
                logger.info("Get brandId/page -> " + brandId + "/" + i);
                if (searchDone(fw, brandId, i)) {
                    break;
                }
            }
        }
    }
    try {
        fw.close();
    } catch (IOException e) {
        e.printStackTrace();
    }
    logger.info("----> Done!");

    logger.info("----> Start to compare production search ... ");
    CompareProductions.start(prodIdList, 0);
}

From source file:com.joliciel.frenchTreebank.FrenchTreebank.java

/**
 * @param args/*from  w  ww.  jav a 2  s. co m*/
 */
public static void main(String[] args) throws Exception {
    String command = args[0];

    String outFilePath = "";
    String outDirPath = "";
    String treebankPath = "";
    String ftbFileName = "";
    String rawTextDir = "";
    String queryPath = "";
    String sentenceNumber = null;
    boolean firstArg = true;
    for (String arg : args) {
        if (firstArg) {
            firstArg = false;
            continue;
        }
        int equalsPos = arg.indexOf('=');
        String argName = arg.substring(0, equalsPos);
        String argValue = arg.substring(equalsPos + 1);
        if (argName.equals("outfile"))
            outFilePath = argValue;
        else if (argName.equals("outdir"))
            outDirPath = argValue;
        else if (argName.equals("ftbFileName"))
            ftbFileName = argValue;
        else if (argName.equals("treebank"))
            treebankPath = argValue;
        else if (argName.equals("sentence"))
            sentenceNumber = argValue;
        else if (argName.equals("query"))
            queryPath = argValue;
        else if (argName.equals("rawTextDir"))
            rawTextDir = argValue;
        else
            throw new RuntimeException("Unknown argument: " + argName);
    }

    TalismaneServiceLocator talismaneServiceLocator = TalismaneServiceLocator.getInstance();

    TreebankServiceLocator locator = TreebankServiceLocator.getInstance(talismaneServiceLocator);

    if (treebankPath.length() == 0)
        locator.setDataSourcePropertiesFile("jdbc-live.properties");

    if (command.equals("search")) {
        final SearchService searchService = locator.getSearchService();
        final XmlPatternSearch search = searchService.newXmlPatternSearch();
        search.setXmlPatternFile(queryPath);
        List<SearchResult> searchResults = search.perform();

        FileWriter fileWriter = new FileWriter(outFilePath);
        for (SearchResult searchResult : searchResults) {
            String lineToWrite = "";
            Sentence sentence = searchResult.getSentence();
            Phrase phrase = searchResult.getPhrase();
            lineToWrite += sentence.getFile().getFileName() + "|";
            lineToWrite += sentence.getSentenceNumber() + "|";
            List<PhraseUnit> phraseUnits = searchResult.getPhraseUnits();
            LOG.debug("Phrase: " + phrase.getId());
            for (PhraseUnit phraseUnit : phraseUnits)
                lineToWrite += phraseUnit.getLemma().getText() + "|";
            lineToWrite += phrase.getText();
            fileWriter.write(lineToWrite + "\n");
        }
        fileWriter.flush();
        fileWriter.close();
    } else if (command.equals("load")) {
        final TreebankService treebankService = locator.getTreebankService();
        final TreebankSAXParser parser = new TreebankSAXParser();
        parser.setTreebankService(treebankService);
        parser.parseDocument(treebankPath);
    } else if (command.equals("loadAll")) {
        final TreebankService treebankService = locator.getTreebankService();

        File dir = new File(treebankPath);

        String firstFile = null;
        if (args.length > 2)
            firstFile = args[2];
        String[] files = dir.list();
        if (files == null) {
            throw new RuntimeException("Not a directory or no children: " + treebankPath);
        } else {
            boolean startProcessing = true;
            if (firstFile != null)
                startProcessing = false;
            for (int i = 0; i < files.length; i++) {
                if (!startProcessing && files[i].equals(firstFile))
                    startProcessing = true;
                if (startProcessing) {
                    String filePath = args[1] + "/" + files[i];
                    LOG.debug(filePath);
                    final TreebankSAXParser parser = new TreebankSAXParser();
                    parser.setTreebankService(treebankService);
                    parser.parseDocument(filePath);
                }
            }
        }
    } else if (command.equals("loadRawText")) {
        final TreebankService treebankService = locator.getTreebankService();
        final TreebankRawTextAssigner assigner = new TreebankRawTextAssigner();
        assigner.setTreebankService(treebankService);
        assigner.setRawTextDirectory(rawTextDir);
        assigner.loadRawText();
    } else if (command.equals("tokenize")) {
        Writer csvFileWriter = null;
        if (outFilePath != null && outFilePath.length() > 0) {
            if (outFilePath.lastIndexOf("/") > 0) {
                String outputDirPath = outFilePath.substring(0, outFilePath.lastIndexOf("/"));
                File outputDir = new File(outputDirPath);
                outputDir.mkdirs();
            }

            File csvFile = new File(outFilePath);
            csvFile.delete();
            csvFile.createNewFile();
            csvFileWriter = new BufferedWriter(
                    new OutputStreamWriter(new FileOutputStream(csvFile, false), "UTF8"));
        }
        try {

            final TreebankService treebankService = locator.getTreebankService();
            TreebankExportService treebankExportService = locator.getTreebankExportServiceLocator()
                    .getTreebankExportService();
            TreebankUploadService treebankUploadService = locator.getTreebankUploadServiceLocator()
                    .getTreebankUploadService();
            TreebankReader treebankReader = null;

            if (treebankPath.length() > 0) {
                File treebankFile = new File(treebankPath);
                if (sentenceNumber != null)
                    treebankReader = treebankUploadService.getXmlReader(treebankFile, sentenceNumber);
                else
                    treebankReader = treebankUploadService.getXmlReader(treebankFile);

            } else {
                treebankReader = treebankService.getDatabaseReader(TreebankSubSet.ALL, 0);
            }

            TokeniserAnnotatedCorpusReader reader = treebankExportService
                    .getTokeniserAnnotatedCorpusReader(treebankReader, csvFileWriter);

            while (reader.hasNextTokenSequence()) {
                TokenSequence tokenSequence = reader.nextTokenSequence();
                List<Integer> tokenSplits = tokenSequence.getTokenSplits();
                String sentence = tokenSequence.getText();
                LOG.debug(sentence);
                int currentPos = 0;
                StringBuilder sb = new StringBuilder();
                for (int split : tokenSplits) {
                    if (split == 0)
                        continue;
                    String token = sentence.substring(currentPos, split);
                    sb.append('|');
                    sb.append(token);
                    currentPos = split;
                }
                LOG.debug(sb.toString());
            }
        } finally {
            csvFileWriter.flush();
            csvFileWriter.close();
        }
    } else if (command.equals("export")) {
        if (outDirPath.length() == 0)
            throw new RuntimeException("Parameter required: outdir");
        File outDir = new File(outDirPath);
        outDir.mkdirs();

        final TreebankService treebankService = locator.getTreebankService();
        FrenchTreebankXmlWriter xmlWriter = new FrenchTreebankXmlWriter();
        xmlWriter.setTreebankService(treebankService);

        if (ftbFileName.length() == 0) {
            xmlWriter.write(outDir);
        } else {
            TreebankFile ftbFile = treebankService.loadTreebankFile(ftbFileName);
            String fileName = ftbFileName.substring(ftbFileName.lastIndexOf('/') + 1);
            File xmlFile = new File(outDir, fileName);
            xmlFile.delete();
            xmlFile.createNewFile();

            Writer xmlFileWriter = new BufferedWriter(
                    new OutputStreamWriter(new FileOutputStream(xmlFile, false), "UTF8"));
            xmlWriter.write(xmlFileWriter, ftbFile);
            xmlFileWriter.flush();
            xmlFileWriter.close();
        }
    } else {
        throw new RuntimeException("Unknown command: " + command);
    }
    LOG.debug("========== END ============");
}

From source file:org.apache.cxf.cwiki.SiteExporter.java

public static void main(String[] args) throws Exception {
    Authenticator.setDefault(new Authenticator() {
        protected PasswordAuthentication getPasswordAuthentication() {
            return new PasswordAuthentication(userName, password.toCharArray());
        }//  ww  w  .  j av  a  2s  .c  o  m
    });
    ListIterator<String> it = Arrays.asList(args).listIterator();
    List<String> files = new ArrayList<String>();
    boolean forceAll = false;
    int maxThreads = -1;
    while (it.hasNext()) {
        String s = it.next();
        if ("-debug".equals(s)) {
            debug = true;
        } else if ("-user".equals(s)) {
            userName = it.next();
        } else if ("-password".equals(s)) {
            password = it.next();
        } else if ("-d".equals(s)) {
            rootOutputDir = new File(it.next());
        } else if ("-force".equals(s)) {
            forceAll = true;
        } else if ("-svn".equals(s)) {
            svn = true;
        } else if ("-commit".equals(s)) {
            commit = true;
        } else if ("-maxThreads".equals(s)) {
            maxThreads = Integer.parseInt(it.next());
        } else if (s != null && s.length() > 0) {
            files.add(s);
        }
    }

    List<SiteExporter> exporters = new ArrayList<SiteExporter>();
    for (String file : files) {
        exporters.add(new SiteExporter(file, forceAll));
    }
    List<SiteExporter> modified = new ArrayList<SiteExporter>();
    for (SiteExporter exporter : exporters) {
        if (exporter.initialize()) {
            modified.add(exporter);
        }
    }

    // render stuff only if needed
    if (!modified.isEmpty()) {
        setSiteExporters(exporters);

        if (maxThreads <= 0) {
            maxThreads = modified.size();
        }

        ExecutorService executor = Executors.newFixedThreadPool(maxThreads, new ThreadFactory() {
            public Thread newThread(Runnable r) {
                Thread t = new Thread(r);
                t.setDaemon(true);
                return t;
            }
        });
        List<Future<?>> futures = new ArrayList<Future<?>>(modified.size());
        for (SiteExporter exporter : modified) {
            futures.add(executor.submit(exporter));
        }
        for (Future<?> t : futures) {
            t.get();
        }
    }

    if (commit) {
        File file = FileUtils.createTempFile("svncommit", "txt");
        FileWriter writer = new FileWriter(file);
        writer.write(svnCommitMessage.toString());
        writer.close();
        callSvn(rootOutputDir, "commit", "-F", file.getAbsolutePath(), rootOutputDir.getAbsolutePath());
        svnCommitMessage.setLength(0);
    }
}

From source file:com.icesoft.faces.webapp.parser.TagToComponentMap.java

/**
 * Main method for when this class is run to build the serialized data from
 * a set of TLDS.// www  .ja va2 s. c  o  m
 *
 * @param args The runtime arguements.
 */
public static void main(String args[]) {

    /* arg[0] is "new" to create serialzed data or 'old' to read serialized data
       arg[1] is filename for serialized data;
       arg[2...] are tld's to process */

    FileInputStream tldFile = null;

    TagToComponentMap map = new TagToComponentMap();

    if (args[0].equals("new")) {
        // Build new component map from tlds and serialize it;

        for (int i = 2; i < args.length; i++) {
            try {
                tldFile = new FileInputStream(args[i]);
                map.addTagAttrib((InputStream) tldFile);
            } catch (IOException e) {
                e.printStackTrace();
                return;
            }
        }

        try {
            FileOutputStream fos = new FileOutputStream(args[1]);
            ObjectOutputStream oos = new ObjectOutputStream(fos);
            oos.writeObject(map);
            oos.flush();
            oos.close();
        } catch (Exception e) {
            e.printStackTrace();
        }
    } else if (args[0].equals("old")) {
        // Build component from serialized data;
        try {
            FileInputStream fis = new FileInputStream(args[1]);
            ObjectInputStream ois = new ObjectInputStream(fis);
            map = (TagToComponentMap) ois.readObject();
        } catch (Exception e) {
            e.printStackTrace();
        }
    } else if (args[0].equals("facelets")) {
        // Build new component map from tld, and use that to
        //  generate a Facelets taglib.xml
        // args[0] is command
        // args[1] is output taglib.xml
        // args[2] is input tld

        try {
            FileWriter faceletsTaglibXmlWriter = new FileWriter(args[1]);
            String preamble = "<?xml version=\"1.0\"?>\n"
                    + "<facelet-taglib xmlns=\"http://java.sun.com/xml/ns/javaee\"\n"
                    + "xmlns:xsi=\"http://www.w3.org/2001/XMLSchema-instance\"\n"
                    + "xsi:schemaLocation=\"http://java.sun.com/xml/ns/javaee "
                    + "http://java.sun.com/xml/ns/javaee/web-facelettaglibrary_2_0.xsd\"\n"
                    + "version=\"2.0\">\n";

            String trailer = "</facelet-taglib>\n";
            faceletsTaglibXmlWriter.write(preamble);

            map.setFaceletsTaglibXmlWriter(faceletsTaglibXmlWriter);
            tldFile = new FileInputStream(args[2]);
            map.addTagAttrib((InputStream) tldFile);

            faceletsTaglibXmlWriter.write(trailer);
            faceletsTaglibXmlWriter.flush();
            faceletsTaglibXmlWriter.close();
        } catch (IOException e) {
            e.printStackTrace();
            return;
        }
    }
}

From source file:ch.kostceco.tools.kostsimy.KOSTSimy.java

/** Die Eingabe besteht aus 2 Parameter: [0] Original-Ordner [1] Replica-Ordner
 * //ww  w.  j  a  va 2s.c  o  m
 * @param args
 * @throws IOException */

public static void main(String[] args) throws IOException {
    ApplicationContext context = new ClassPathXmlApplicationContext("classpath:config/applicationContext.xml");

    // Zeitstempel Start
    java.util.Date nowStart = new java.util.Date();
    java.text.SimpleDateFormat sdfStart = new java.text.SimpleDateFormat("dd.MM.yyyy HH:mm:ss");
    String ausgabeStart = sdfStart.format(nowStart);

    KOSTSimy kostsimy = (KOSTSimy) context.getBean("kostsimy");
    File configFile = new File("configuration" + File.separator + "kostsimy.conf.xml");

    // Ueberprfung des Parameters (Log-Verzeichnis)
    String pathToLogfile = kostsimy.getConfigurationService().getPathToLogfile();

    File directoryOfLogfile = new File(pathToLogfile);

    if (!directoryOfLogfile.exists()) {
        directoryOfLogfile.mkdir();
    }

    // Im Logverzeichnis besteht kein Schreibrecht
    if (!directoryOfLogfile.canWrite()) {
        System.out.println(
                kostsimy.getTextResourceService().getText(ERROR_LOGDIRECTORY_NOTWRITABLE, directoryOfLogfile));
        System.exit(1);
    }

    if (!directoryOfLogfile.isDirectory()) {
        System.out.println(kostsimy.getTextResourceService().getText(ERROR_LOGDIRECTORY_NODIRECTORY));
        System.exit(1);
    }

    // Ist die Anzahl Parameter (2) korrekt?
    if (args.length > 3) {
        System.out.println(kostsimy.getTextResourceService().getText(ERROR_PARAMETER_USAGE));
        System.exit(1);
    }

    File origDir = new File(args[0]);
    File repDir = new File(args[1]);
    File logDatei = null;
    logDatei = origDir;

    // Informationen zum Arbeitsverzeichnis holen
    String pathToWorkDir = kostsimy.getConfigurationService().getPathToWorkDir();
    /* Nicht vergessen in "src/main/resources/config/applicationContext-services.xml" beim
     * entsprechenden Modul die property anzugeben: <property name="configurationService"
     * ref="configurationService" /> */

    // Konfiguration des Loggings, ein File Logger wird zustzlich erstellt
    LogConfigurator logConfigurator = (LogConfigurator) context.getBean("logconfigurator");
    String logFileName = logConfigurator.configure(directoryOfLogfile.getAbsolutePath(), logDatei.getName());
    File logFile = new File(logFileName);
    // Ab hier kann ins log geschrieben werden...

    LOGGER.logError(kostsimy.getTextResourceService().getText(MESSAGE_XML_HEADER));
    LOGGER.logError(kostsimy.getTextResourceService().getText(MESSAGE_XML_START, ausgabeStart));
    LOGGER.logError(kostsimy.getTextResourceService().getText(MESSAGE_XML_END));
    LOGGER.logError(kostsimy.getTextResourceService().getText(MESSAGE_XML_INFO));
    System.out.println("KOST-Simy");
    System.out.println("");

    if (!origDir.exists()) {
        // Das Original-Verzeichnis existiert nicht
        LOGGER.logError(kostsimy.getTextResourceService().getText(ERROR_IOE,
                kostsimy.getTextResourceService().getText(ERROR_NOORIGDIR, origDir.getAbsolutePath())));
        System.out
                .println(kostsimy.getTextResourceService().getText(ERROR_NOORIGDIR, origDir.getAbsolutePath()));
        System.exit(1);
    }

    if (!repDir.exists()) {
        // Das Replica-Verzeichnis existiert nicht
        LOGGER.logError(kostsimy.getTextResourceService().getText(ERROR_IOE,
                kostsimy.getTextResourceService().getText(ERROR_NOREPDIR1, repDir.getAbsolutePath())));
        System.out
                .println(kostsimy.getTextResourceService().getText(ERROR_NOREPDIR1, repDir.getAbsolutePath()));
        System.exit(1);
    }

    File xslOrig = new File("resources" + File.separator + "kost-simy.xsl");
    File xslCopy = new File(directoryOfLogfile.getAbsolutePath() + File.separator + "kost-simy.xsl");
    if (!xslCopy.exists()) {
        Util.copyFile(xslOrig, xslCopy);
    }

    // Informationen zur prozentualen Stichprobe holen
    String randomTest = kostsimy.getConfigurationService().getRandomTest();
    /* Nicht vergessen in "src/main/resources/config/applicationContext-services.xml" beim
     * entsprechenden Modul die property anzugeben: <property name="configurationService"
     * ref="configurationService" /> */
    int iRandomTest = 100;
    try {
        iRandomTest = Integer.parseInt(randomTest);
    } catch (Exception ex) {
        // unzulaessige Eingabe --> 50 wird gesetzt
        iRandomTest = 50;
    }
    if (iRandomTest > 100 || iRandomTest < 1) {
        // unzulaessige Eingabe --> 50 wird gesetzt
        iRandomTest = 50;
    }

    File tmpDir = new File(pathToWorkDir);

    /* bestehendes Workverzeichnis Abbruch wenn nicht leer, da am Schluss das Workverzeichnis
     * gelscht wird und entsprechend bestehende Dateien gelscht werden knnen */
    if (tmpDir.exists()) {
        if (tmpDir.isDirectory()) {
            // Get list of file in the directory. When its length is not zero the folder is not empty.
            String[] files = tmpDir.list();
            if (files.length > 0) {
                LOGGER.logError(kostsimy.getTextResourceService().getText(ERROR_IOE,
                        kostsimy.getTextResourceService().getText(ERROR_WORKDIRECTORY_EXISTS, pathToWorkDir)));
                System.out.println(
                        kostsimy.getTextResourceService().getText(ERROR_WORKDIRECTORY_EXISTS, pathToWorkDir));
                System.exit(1);
            }
        }
    }

    // Im Pfad keine Sonderzeichen Programme knnen evtl abstrzen

    String patternStr = "[^!#\\$%\\(\\)\\+,\\-_\\.=@\\[\\]\\{\\}\\~:\\\\a-zA-Z0-9 ]";
    Pattern pattern = Pattern.compile(patternStr);

    String name = tmpDir.getAbsolutePath();

    String[] pathElements = name.split("/");
    for (int i = 0; i < pathElements.length; i++) {
        String element = pathElements[i];

        Matcher matcher = pattern.matcher(element);

        boolean matchFound = matcher.find();
        if (matchFound) {
            LOGGER.logError(kostsimy.getTextResourceService().getText(ERROR_IOE,
                    kostsimy.getTextResourceService().getText(ERROR_SPECIAL_CHARACTER, name)));
            System.out.println(kostsimy.getTextResourceService().getText(ERROR_SPECIAL_CHARACTER, name));
            System.exit(1);
        }
    }

    // die Anwendung muss mindestens unter Java 6 laufen
    String javaRuntimeVersion = System.getProperty("java.vm.version");
    if (javaRuntimeVersion.compareTo("1.6.0") < 0) {
        LOGGER.logError(kostsimy.getTextResourceService().getText(ERROR_IOE,
                kostsimy.getTextResourceService().getText(ERROR_WRONG_JRE)));
        System.out.println(kostsimy.getTextResourceService().getText(ERROR_WRONG_JRE));
        System.exit(1);
    }

    // bestehendes Workverzeichnis wieder anlegen
    if (!tmpDir.exists()) {
        tmpDir.mkdir();
        File origDirTmp = new File(tmpDir.getAbsolutePath() + File.separator + "orig");
        File repDirTmp = new File(tmpDir.getAbsolutePath() + File.separator + "rep");
        origDirTmp.mkdir();
        repDirTmp.mkdir();
    }

    // Im workverzeichnis besteht kein Schreibrecht
    if (!tmpDir.canWrite()) {
        LOGGER.logError(kostsimy.getTextResourceService().getText(ERROR_IOE,
                kostsimy.getTextResourceService().getText(ERROR_WORKDIRECTORY_NOTWRITABLE, tmpDir)));
        System.out.println(kostsimy.getTextResourceService().getText(ERROR_WORKDIRECTORY_NOTWRITABLE, tmpDir));
        System.exit(1);
    }

    // Im Pfad keine Sonderzeichen --> Absturzgefahr
    name = origDir.getAbsolutePath();
    pathElements = name.split("/");
    for (int i = 0; i < pathElements.length; i++) {
        String element = pathElements[i];
        Matcher matcher = pattern.matcher(element);
        boolean matchFound = matcher.find();
        if (matchFound) {
            LOGGER.logError(kostsimy.getTextResourceService().getText(ERROR_IOE,
                    kostsimy.getTextResourceService().getText(ERROR_SPECIAL_CHARACTER, name)));
            System.out.println(kostsimy.getTextResourceService().getText(ERROR_SPECIAL_CHARACTER, name));
            System.exit(1);
        }
    }
    name = repDir.getAbsolutePath();
    pathElements = name.split("/");
    for (int i = 0; i < pathElements.length; i++) {
        String element = pathElements[i];
        Matcher matcher = pattern.matcher(element);
        boolean matchFound = matcher.find();
        if (matchFound) {
            LOGGER.logError(kostsimy.getTextResourceService().getText(ERROR_IOE,
                    kostsimy.getTextResourceService().getText(ERROR_SPECIAL_CHARACTER, name)));
            System.out.println(kostsimy.getTextResourceService().getText(ERROR_SPECIAL_CHARACTER, name));
            System.exit(1);
        }
    }

    LOGGER.logError(kostsimy.getTextResourceService().getText(MESSAGE_XML_IMAGE1));
    float count = 0;
    int countNio = 0;
    int countIo = 0;
    float countVal = 0;
    int countNotVal = 0;
    float percentage = (float) 0.0;

    if (!origDir.isDirectory()) {
        // TODO: Bildervergleich zweier Dateien --> erledigt --> nur Marker

        if (repDir.isDirectory()) {
            // Das Replica-ist ein Verzeichnis, aber Original eine Datei
            LOGGER.logError(kostsimy.getTextResourceService().getText(ERROR_IOE,
                    kostsimy.getTextResourceService().getText(ERROR_NOREPDIR2, repDir.getAbsolutePath())));
            System.out.println(
                    kostsimy.getTextResourceService().getText(ERROR_NOREPDIR2, repDir.getAbsolutePath()));
            System.exit(1);
        }
        boolean compFile = compFile(origDir, logFileName, directoryOfLogfile, repDir, tmpDir);

        float statIo = 0;
        int statNio = 0;
        float statUn = 0;
        if (compFile) {
            statIo = 100;
        } else {
            statNio = 100;
        }

        LOGGER.logError(kostsimy.getTextResourceService().getText(MESSAGE_XML_IMAGE2));
        LOGGER.logError(
                kostsimy.getTextResourceService().getText(MESSAGE_XML_STATISTICS, statIo, statNio, statUn));

        LOGGER.logError(kostsimy.getTextResourceService().getText(MESSAGE_XML_LOGEND));
        // Zeitstempel End
        java.util.Date nowEnd = new java.util.Date();
        java.text.SimpleDateFormat sdfEnd = new java.text.SimpleDateFormat("dd.MM.yyyy HH:mm:ss");
        String ausgabeEnd = sdfEnd.format(nowEnd);
        ausgabeEnd = "<End>" + ausgabeEnd + "</End>";
        Util.valEnd(ausgabeEnd, logFile);
        Util.amp(logFile);

        // Die Konfiguration hereinkopieren
        try {
            DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
            factory.setValidating(false);

            factory.setExpandEntityReferences(false);

            Document docConfig = factory.newDocumentBuilder().parse(configFile);
            NodeList list = docConfig.getElementsByTagName("configuration");
            Element element = (Element) list.item(0);

            Document docLog = factory.newDocumentBuilder().parse(logFile);

            Node dup = docLog.importNode(element, true);

            docLog.getDocumentElement().appendChild(dup);
            FileWriter writer = new FileWriter(logFile);

            ByteArrayOutputStream baos = new ByteArrayOutputStream();
            ElementToStream(docLog.getDocumentElement(), baos);
            String stringDoc2 = new String(baos.toByteArray());
            writer.write(stringDoc2);
            writer.close();

            // Der Header wird dabei leider verschossen, wieder zurck ndern
            String newstring = kostsimy.getTextResourceService().getText(MESSAGE_XML_HEADER);
            String oldstring = "<?xml version=\"1.0\" encoding=\"UTF-8\"?><KOSTSimyLog>";
            Util.oldnewstring(oldstring, newstring, logFile);

        } catch (Exception e) {
            LOGGER.logError(
                    "<Error>" + kostsimy.getTextResourceService().getText(ERROR_XML_UNKNOWN, e.getMessage()));
            System.out.println("Exception: " + e.getMessage());
        }

        if (compFile) {
            // Lschen des Arbeitsverzeichnisses, falls eines angelegt wurde
            if (tmpDir.exists()) {
                Util.deleteDir(tmpDir);
            }
            // Validierte Datei valide
            System.exit(0);
        } else {
            // Lschen des Arbeitsverzeichnisses, falls eines angelegt wurde
            if (tmpDir.exists()) {
                Util.deleteDir(tmpDir);
            }
            // Fehler in Validierte Datei --> invalide
            System.exit(2);

        }
    } else {
        // TODO: Bildervergleich zweier Verzeichnisse --> in Arbeit --> nur Marker
        if (!repDir.isDirectory()) {
            // Das Replica-ist eine Datei, aber Original ein Ordner
            LOGGER.logError(kostsimy.getTextResourceService().getText(ERROR_IOE,
                    kostsimy.getTextResourceService().getText(ERROR_NOREPDIR3, repDir.getAbsolutePath())));
            System.out.println(
                    kostsimy.getTextResourceService().getText(ERROR_NOREPDIR3, repDir.getAbsolutePath()));
            System.exit(1);
        }

        Map<String, File> fileMap = Util.getFileMap(origDir, false);
        Set<String> fileMapKeys = fileMap.keySet();
        boolean other = false;

        for (Iterator<String> iterator = fileMapKeys.iterator(); iterator.hasNext();) {
            String entryName = iterator.next();
            File newFile = fileMap.get(entryName);
            if (!newFile.isDirectory()) {
                origDir = newFile;
                count = count + 1;
                if ((origDir.getAbsolutePath().toLowerCase().endsWith(".pdf")
                        || origDir.getAbsolutePath().toLowerCase().endsWith(".pdfa")
                        || origDir.getAbsolutePath().toLowerCase().endsWith(".tif")
                        || origDir.getAbsolutePath().toLowerCase().endsWith(".tiff")
                        || origDir.getAbsolutePath().toLowerCase().endsWith(".jpeg")
                        || origDir.getAbsolutePath().toLowerCase().endsWith(".jpg")
                        || origDir.getAbsolutePath().toLowerCase().endsWith(".jpe")
                        || origDir.getAbsolutePath().toLowerCase().endsWith(".jp2")
                        || origDir.getAbsolutePath().toLowerCase().endsWith(".gif")
                        || origDir.getAbsolutePath().toLowerCase().endsWith(".png")
                        || origDir.getAbsolutePath().toLowerCase().endsWith(".bmp"))) {
                    percentage = 100 / count * countVal;
                    if (percentage < iRandomTest) {
                        // if ( 100 / count * (countVal + 1) <= iRandomTest ) {

                        countVal = countVal + 1;

                        String origWithOutExt = FilenameUtils.removeExtension(origDir.getName());

                        File repFile = new File(
                                repDir.getAbsolutePath() + File.separator + origWithOutExt + ".pdf");
                        if (!repFile.exists()) {
                            repFile = new File(
                                    repDir.getAbsolutePath() + File.separator + origWithOutExt + ".pdfa");
                            if (!repFile.exists()) {
                                repFile = new File(
                                        repDir.getAbsolutePath() + File.separator + origWithOutExt + ".tif");
                                if (!repFile.exists()) {
                                    repFile = new File(repDir.getAbsolutePath() + File.separator
                                            + origWithOutExt + ".tiff");
                                    if (!repFile.exists()) {
                                        repFile = new File(repDir.getAbsolutePath() + File.separator
                                                + origWithOutExt + ".jpeg");
                                        if (!repFile.exists()) {
                                            repFile = new File(repDir.getAbsolutePath() + File.separator
                                                    + origWithOutExt + ".jpg");
                                            if (!repFile.exists()) {
                                                repFile = new File(repDir.getAbsolutePath() + File.separator
                                                        + origWithOutExt + ".jpe");
                                                if (!repFile.exists()) {
                                                    repFile = new File(repDir.getAbsolutePath() + File.separator
                                                            + origWithOutExt + ".jp2");
                                                    if (!repFile.exists()) {
                                                        repFile = new File(repDir.getAbsolutePath()
                                                                + File.separator + origWithOutExt + ".gif");
                                                        if (!repFile.exists()) {
                                                            repFile = new File(repDir.getAbsolutePath()
                                                                    + File.separator + origWithOutExt + ".png");
                                                            if (!repFile.exists()) {
                                                                repFile = new File(repDir.getAbsolutePath()
                                                                        + File.separator + origWithOutExt
                                                                        + ".bmp");
                                                                if (!repFile.exists()) {
                                                                    other = true;
                                                                    LOGGER.logError(kostsimy
                                                                            .getTextResourceService()
                                                                            .getText(MESSAGE_XML_VALERGEBNIS));
                                                                    LOGGER.logError(kostsimy
                                                                            .getTextResourceService()
                                                                            .getText(MESSAGE_XML_COMPFILE,
                                                                                    origDir));
                                                                    LOGGER.logError(kostsimy
                                                                            .getTextResourceService().getText(
                                                                                    MESSAGE_XML_VALERGEBNIS_NOTVALIDATED));
                                                                    LOGGER.logError(
                                                                            kostsimy.getTextResourceService()
                                                                                    .getText(ERROR_NOREP,
                                                                                            origDir.getName()));
                                                                    LOGGER.logError(kostsimy
                                                                            .getTextResourceService().getText(
                                                                                    MESSAGE_XML_VALERGEBNIS_CLOSE));
                                                                }
                                                            }
                                                        }
                                                    }
                                                }
                                            }
                                        }
                                    }
                                }
                            }
                        }

                        if (!other) {
                            boolean compFile = compFile(origDir, logFileName, directoryOfLogfile, repFile,
                                    tmpDir);
                            if (compFile) {
                                // Vergleich bestanden
                                countIo = countIo + 1;
                            } else {
                                // Vergleich nicht bestanden
                                countNio = countNio + 1;
                            }
                        }
                    } else {
                        countNotVal = countNotVal + 1;
                        LOGGER.logError(kostsimy.getTextResourceService().getText(MESSAGE_XML_VALERGEBNIS));
                        LOGGER.logError(
                                kostsimy.getTextResourceService().getText(MESSAGE_XML_COMPFILE, origDir));
                        LOGGER.logError(kostsimy.getTextResourceService()
                                .getText(MESSAGE_XML_VALERGEBNIS_NOTVALIDATED));
                        LOGGER.logError(
                                kostsimy.getTextResourceService().getText(MESSAGE_XML_VALERGEBNIS_CLOSE));
                    }
                } else {
                    countNotVal = countNotVal + 1;
                    LOGGER.logError(kostsimy.getTextResourceService().getText(MESSAGE_XML_VALERGEBNIS));
                    LOGGER.logError(kostsimy.getTextResourceService().getText(MESSAGE_XML_COMPFILE, origDir));
                    LOGGER.logError(
                            kostsimy.getTextResourceService().getText(MESSAGE_XML_VALERGEBNIS_NOTVALIDATED));
                    LOGGER.logError(
                            kostsimy.getTextResourceService().getText(ERROR_INCORRECTFILEENDING, origDir));
                    LOGGER.logError(kostsimy.getTextResourceService().getText(MESSAGE_XML_VALERGEBNIS_CLOSE));
                }
            }
        }

        if (countNio == 0 && countIo == 0) {
            // keine Dateien verglichen
            LOGGER.logError(kostsimy.getTextResourceService().getText(ERROR_INCORRECTFILEENDINGS));
            System.out.println(kostsimy.getTextResourceService().getText(ERROR_INCORRECTFILEENDINGS));
        }

        float statIo = 100 / (float) count * (float) countIo;
        float statNio = 100 / (float) count * (float) countNio;
        float statUn = 100 - statIo - statNio;

        LOGGER.logError(kostsimy.getTextResourceService().getText(MESSAGE_XML_IMAGE2));
        LOGGER.logError(
                kostsimy.getTextResourceService().getText(MESSAGE_XML_STATISTICS, statIo, statNio, statUn));
        LOGGER.logError(kostsimy.getTextResourceService().getText(MESSAGE_XML_LOGEND));
        // Zeitstempel End
        java.util.Date nowEnd = new java.util.Date();
        java.text.SimpleDateFormat sdfEnd = new java.text.SimpleDateFormat("dd.MM.yyyy HH:mm:ss");
        String ausgabeEnd = sdfEnd.format(nowEnd);
        ausgabeEnd = "<End>" + ausgabeEnd + "</End>";
        Util.valEnd(ausgabeEnd, logFile);
        Util.amp(logFile);

        // Die Konfiguration hereinkopieren
        try {
            DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
            factory.setValidating(false);

            factory.setExpandEntityReferences(false);

            Document docConfig = factory.newDocumentBuilder().parse(configFile);
            NodeList list = docConfig.getElementsByTagName("configuration");
            Element element = (Element) list.item(0);

            Document docLog = factory.newDocumentBuilder().parse(logFile);

            Node dup = docLog.importNode(element, true);

            docLog.getDocumentElement().appendChild(dup);
            FileWriter writer = new FileWriter(logFile);

            ByteArrayOutputStream baos = new ByteArrayOutputStream();
            ElementToStream(docLog.getDocumentElement(), baos);
            String stringDoc2 = new String(baos.toByteArray());
            writer.write(stringDoc2);
            writer.close();

            // Der Header wird dabei leider verschossen, wieder zurck ndern
            String newstring = kostsimy.getTextResourceService().getText(MESSAGE_XML_HEADER);
            String oldstring = "<?xml version=\"1.0\" encoding=\"UTF-8\"?><KOSTSimyLog>";
            Util.oldnewstring(oldstring, newstring, logFile);

        } catch (Exception e) {
            LOGGER.logError(
                    "<Error>" + kostsimy.getTextResourceService().getText(ERROR_XML_UNKNOWN, e.getMessage()));
            System.out.println("Exception: " + e.getMessage());
        }

        if (countNio == 0 && countIo == 0) {
            // keine Dateien verglichen bestehendes Workverzeichnis ggf. lschen
            if (tmpDir.exists()) {
                Util.deleteDir(tmpDir);
            }
            System.exit(1);
        } else if (countNio == 0) {
            // bestehendes Workverzeichnis ggf. lschen
            if (tmpDir.exists()) {
                Util.deleteDir(tmpDir);
            }
            // alle Validierten Dateien valide
            System.exit(0);
        } else {
            // bestehendes Workverzeichnis ggf. lschen
            if (tmpDir.exists()) {
                Util.deleteDir(tmpDir);
            }
            // Fehler in Validierten Dateien --> invalide
            System.exit(2);
        }
        if (tmpDir.exists()) {
            Util.deleteDir(tmpDir);
            tmpDir.deleteOnExit();
        }
    }
}

From source file:com.nextdoor.bender.S3SnsNotifier.java

public static void main(String[] args) throws ParseException, InterruptedException, IOException {
    formatter = DateTimeFormat.forPattern("yyyy-MM-dd'T'HH:mm:ss.SSS'Z'").withZoneUTC();

    /*//from w ww .ja  v a2 s  .  co  m
     * Parse cli arguments
     */
    Options options = new Options();
    options.addOption(Option.builder().longOpt("bucket").hasArg().required()
            .desc("Name of S3 bucket to list s3 objects from").build());
    options.addOption(Option.builder().longOpt("key-file").hasArg().required()
            .desc("Local file of S3 keys to process").build());
    options.addOption(
            Option.builder().longOpt("sns-arn").hasArg().required().desc("SNS arn to publish to").build());
    options.addOption(Option.builder().longOpt("throttle-ms").hasArg()
            .desc("Amount of ms to wait between publishing to SNS").build());
    options.addOption(Option.builder().longOpt("processed-file").hasArg()
            .desc("Local file to use to store procssed S3 object names").build());
    options.addOption(Option.builder().longOpt("skip-processed").hasArg(false)
            .desc("Whether to skip S3 objects that have been processed").build());
    options.addOption(
            Option.builder().longOpt("dry-run").hasArg(false).desc("If set do not publish to SNS").build());

    CommandLineParser parser = new DefaultParser();
    CommandLine cmd = parser.parse(options, args);

    String bucket = cmd.getOptionValue("bucket");
    String keyFile = cmd.getOptionValue("key-file");
    String snsArn = cmd.getOptionValue("sns-arn");
    String processedFile = cmd.getOptionValue("processed-file", null);
    boolean skipProcessed = cmd.hasOption("skip-processed");
    dryRun = cmd.hasOption("dry-run");
    long throttle = Long.parseLong(cmd.getOptionValue("throttle-ms", "-1"));

    if (processedFile != null) {
        File file = new File(processedFile);

        if (!file.exists()) {
            logger.debug("creating local file to store processed s3 object names: " + processedFile);
            file.createNewFile();
        }
    }

    /*
     * Import S3 keys that have been processed
     */
    if (skipProcessed && processedFile != null) {
        try (BufferedReader br = new BufferedReader(new FileReader(processedFile))) {
            String line;
            while ((line = br.readLine()) != null) {
                alreadyPublished.add(line.trim());
            }
        }
    }

    /*
     * Setup writer for file containing processed S3 keys
     */
    FileWriter fw = null;
    BufferedWriter bw = null;
    if (processedFile != null) {
        fw = new FileWriter(processedFile, true);
        bw = new BufferedWriter(fw);
    }

    /*
     * Create clients
     */
    AmazonS3Client s3Client = new AmazonS3Client();
    AmazonSNSClient snsClient = new AmazonSNSClient();

    /*
     * Get S3 object list
     */
    try (BufferedReader br = new BufferedReader(new FileReader(keyFile))) {
        String line;
        while ((line = br.readLine()) != null) {
            String key = line.trim();

            if (alreadyPublished.contains(key)) {
                logger.info("skipping " + key);
            }

            ObjectMetadata om = s3Client.getObjectMetadata(bucket, key);

            S3EventNotification s3Notification = getS3Notification(key, bucket, om.getContentLength());

            String json = s3Notification.toJson();

            /*
             * Publish to SNS
             */
            if (publish(snsArn, json, snsClient, key) && processedFile != null) {
                bw.write(key + "\n");
                bw.flush();
            }

            if (throttle != -1) {
                Thread.sleep(throttle);
            }

        }
    }

    if (processedFile != null) {
        bw.close();
        fw.close();
    }
}