List of usage examples for java.util LinkedList size
int size
To view the source code for java.util LinkedList size.
Click Source Link
From source file:com.act.lcms.v2.MZCollisionCounter.java
public static void main(String[] args) throws Exception { CLIUtil cliUtil = new CLIUtil(MassChargeCalculator.class, HELP_MESSAGE, OPTION_BUILDERS); CommandLine cl = cliUtil.parseCommandLine(args); File inputFile = new File(cl.getOptionValue(OPTION_INPUT_INCHI_LIST)); if (!inputFile.exists()) { cliUtil.failWithMessage("Input file at does not exist at %s", inputFile.getAbsolutePath()); }// w w w.j a v a2 s . co m List<MassChargeCalculator.MZSource> sources = new ArrayList<>(); try (BufferedReader reader = new BufferedReader(new FileReader(inputFile))) { String line; while ((line = reader.readLine()) != null) { line = line.trim(); sources.add(new MassChargeCalculator.MZSource(line)); if (sources.size() % 1000 == 0) { LOGGER.info("Loaded %d sources from input file", sources.size()); } } } Set<String> considerIons = Collections.emptySet(); if (cl.hasOption(OPTION_ONLY_CONSIDER_IONS)) { List<String> ions = Arrays.asList(cl.getOptionValues(OPTION_ONLY_CONSIDER_IONS)); LOGGER.info("Only considering ions for m/z calculation: %s", StringUtils.join(ions, ", ")); considerIons = new HashSet<>(ions); } TSVWriter<String, Long> tsvWriter = new TSVWriter<>(Arrays.asList("collisions", "count")); tsvWriter.open(new File(cl.getOptionValue(OPTION_OUTPUT_FILE))); try { LOGGER.info("Loaded %d sources in total from input file", sources.size()); MassChargeCalculator.MassChargeMap mzMap = MassChargeCalculator.makeMassChargeMap(sources, considerIons); if (!cl.hasOption(OPTION_COUNT_WINDOW_INTERSECTIONS)) { // Do an exact analysis of the m/z collisions if windowing is not specified. LOGGER.info("Computing precise collision histogram."); Iterable<Double> mzs = mzMap.ionMZIter(); Map<Integer, Long> collisionHistogram = histogram( StreamSupport.stream(mzs.spliterator(), false).map(mz -> { // See comment about Iterable below. try { return mzMap.ionMZToMZSources(mz).size(); } catch (NoSuchElementException e) { LOGGER.error("Caught no such element exception for mz %f: %s", mz, e.getMessage()); throw e; } })); List<Integer> sortedCollisions = new ArrayList<>(collisionHistogram.keySet()); Collections.sort(sortedCollisions); for (Integer collision : sortedCollisions) { tsvWriter.append(new HashMap<String, Long>() { { put("collisions", collision.longValue()); put("count", collisionHistogram.get(collision)); } }); } } else { /* After some deliberation (thanks Gil!), the windowed variant of this calculation counts the number of * structures whose 0.01 Da m/z windows (for some set of ions) overlap with each other. * * For example, let's assume we have five total input structures, and are only searching for one ion. Let's * also assume that three of those structures have m/z A and the remaining two have m/z B. The windows might * look like this in the m/z domain: * |----A----| * |----B----| * Because A represents three structures and overlaps with B, which represents two, we assign A a count of 5-- * this is the number of structures we believe could fall into the range of A given our current peak calling * approach. Similarly, B is assigned a count of 5, as the possibility for collision/confusion is symmetric. * * Note that this is an over-approximation of collisions, as we could more precisely only consider intersections * when the exact m/z of B falls within the window around A and vice versa. However, because we have observed * cases where the MS sensor doesn't report structures at exactly the m/z we predict, we employ this weaker * definition of intersection to give a slightly pessimistic view of what confusions might be possible. */ // Compute windows for every m/z. We don't care about the original mz values since we just want the count. List<Double> mzs = mzMap.ionMZsSorted(); final Double windowHalfWidth; if (cl.hasOption(OPTION_WINDOW_HALFWIDTH)) { // Don't use get with default for this option, as we want the exact FP value of the default tolerance. windowHalfWidth = Double.valueOf(cl.getOptionValue(OPTION_WINDOW_HALFWIDTH)); } else { windowHalfWidth = DEFAULT_WINDOW_TOLERANCE; } /* Window = (lower bound, upper bound), counter of represented m/z's that collide with this window, and number * of representative structures (which will be used in counting collisions). */ LinkedList<CollisionWindow> allWindows = new LinkedList<CollisionWindow>() { { for (Double mz : mzs) { // CPU for memory trade-off: don't re-compute the window bounds over and over and over and over and over. try { add(new CollisionWindow(mz, windowHalfWidth, mzMap.ionMZToMZSources(mz).size())); } catch (NoSuchElementException e) { LOGGER.error("Caught no such element exception for mz %f: %s", mz, e.getMessage()); throw e; } } } }; // Sweep line time! The window ranges are the interesting points. We just accumulate overlap counts as we go. LinkedList<CollisionWindow> workingSet = new LinkedList<>(); List<CollisionWindow> finished = new LinkedList<>(); while (allWindows.size() > 0) { CollisionWindow thisWindow = allWindows.pop(); // Remove any windows from the working set that don't overlap with the next window. while (workingSet.size() > 0 && workingSet.peekFirst().getMaxMZ() < thisWindow.getMinMZ()) { finished.add(workingSet.pop()); } for (CollisionWindow w : workingSet) { /* Add the size of the new overlapping window's structure count to each of the windows in the working set, * which represents the number of possible confused structures that fall within the overlapping region. * We exclude the window itself as it should already have counted the colliding structures it represents. */ w.getAccumulator().add(thisWindow.getStructureCount()); /* Reciprocally, add the structure counts of all windows with which the current window overlaps to it. */ thisWindow.getAccumulator().add(w.getStructureCount()); } // Now that accumulation is complete, we can safely add the current window. workingSet.add(thisWindow); } // All the interesting events are done, so drop the remaining windows into the finished set. finished.addAll(workingSet); Map<Long, Long> collisionHistogram = histogram( finished.stream().map(w -> w.getAccumulator().longValue())); List<Long> sortedCollisions = new ArrayList<>(collisionHistogram.keySet()); Collections.sort(sortedCollisions); for (Long collision : sortedCollisions) { tsvWriter.append(new HashMap<String, Long>() { { put("collisions", collision); put("count", collisionHistogram.get(collision)); } }); } } } finally { if (tsvWriter != null) { tsvWriter.close(); } } }
From source file:AndroidUninstallStock.java
@SuppressWarnings("static-access") public static void main(String[] args) { try {//from w w w . ja v a 2 s . c o m String lang = Locale.getDefault().getLanguage(); GnuParser cmdparser = new GnuParser(); Options cmdopts = new Options(); for (String fld : Arrays.asList("shortOpts", "longOpts", "optionGroups")) { // hack for printOptions java.lang.reflect.Field fieldopt = cmdopts.getClass().getDeclaredField(fld); fieldopt.setAccessible(true); fieldopt.set(cmdopts, new LinkedHashMap<>()); } cmdopts.addOption("h", "help", false, "Help"); cmdopts.addOption("t", "test", false, "Show only report"); cmdopts.addOption(OptionBuilder.withLongOpt("adb").withArgName("file").hasArg() .withDescription("Path to ADB from Android SDK").create("a")); cmdopts.addOption(OptionBuilder.withLongOpt("dev").withArgName("device").hasArg() .withDescription("Select device (\"adb devices\")").create("d")); cmdopts.addOption(null, "restore", false, "If packages have not yet removed and are disabled, " + "you can activate them again"); cmdopts.addOption(null, "google", false, "Delete packages are in the Google section"); cmdopts.addOption(null, "unapk", false, "Delete /system/app/ *.apk *.odex *.dex" + System.lineSeparator() + "(It is required to repeat command execution)"); cmdopts.addOption(null, "unlib", false, "Delete /system/lib/[libs in apk]"); //cmdopts.addOption(null, "unfrw", false, "Delete /system/framework/ (special list)"); cmdopts.addOption(null, "scanlibs", false, "(Dangerous!) Include all the libraries of selected packages." + " Use with --unlib"); cmdopts.addOptionGroup(new OptionGroup() { { addOption(OptionBuilder.withLongOpt("genfile").withArgName("file").hasArg().isRequired() .withDescription("Create file with list packages").create()); addOption(OptionBuilder.withLongOpt("lang").withArgName("ISO 639").hasArg().create()); } }); cmdopts.getOption("lang").setDescription( "See hl= in Google URL (default: " + lang + ") " + "for description from Google Play Market"); CommandLine cmd = cmdparser.parse(cmdopts, args); if (args.length == 0 || cmd.hasOption("help")) { PrintWriter console = new PrintWriter(System.out); HelpFormatter cmdhelp = new HelpFormatter(); cmdhelp.setOptionComparator(new Comparator<Option>() { @Override public int compare(Option o1, Option o2) { return 0; } }); console.println("WARNING: Before use make a backup with ClockworkMod Recovery!"); console.println(); console.println("AndroidUninstallStock [options] [AndroidListSoft.xml]"); cmdhelp.printOptions(console, 80, cmdopts, 3, 2); console.flush(); return; } String adb = cmd.getOptionValue("adb", "adb"); try { run(adb, "start-server"); } catch (IOException e) { System.out.println("Error: Not found ADB! Use -a or --adb"); return; } final boolean NotTest = !cmd.hasOption("test"); String deverror = getDeviceStatus(adb, cmd.getOptionValue("dev")); if (!deverror.isEmpty()) { System.out.println(deverror); return; } System.out.println("Getting list packages:"); LinkedHashMap<String, String> apklist = new LinkedHashMap<String, String>(); for (String ln : run(adb, "-s", lastdevice, "shell", "pm list packages -s -f")) { // "pm list packages" give list sorted by packages ;) String pckg = ln.substring("package:".length()); String pckgname = ln.substring(ln.lastIndexOf('=') + 1); pckg = pckg.substring(0, pckg.length() - pckgname.length() - 1); if (!pckgname.equals("android") && !pckgname.equals("com.android.vending")/*Google Play Market*/) { apklist.put(pckg, pckgname); } } for (String ln : run(adb, "-s", lastdevice, "shell", "ls /system/app/")) { String path = "/system/app/" + ln.replace(".odex", ".apk").replace(".dex", ".apk"); if (!apklist.containsKey(path)) { apklist.put(path, ""); } } apklist.remove("/system/app/mcRegistry"); for (Map.Entry<String, String> info : sortByValues(apklist).entrySet()) { System.out.println(info.getValue() + " = " + info.getKey()); } String genfile = cmd.getOptionValue("genfile"); if (genfile != null) { Path genpath = Paths.get(genfile); try (BufferedWriter gen = Files.newBufferedWriter(genpath, StandardCharsets.UTF_8, new StandardOpenOption[] { StandardOpenOption.CREATE, StandardOpenOption.TRUNCATE_EXISTING, StandardOpenOption.WRITE })) { if (cmd.getOptionValue("lang") != null) { lang = cmd.getOptionValue("lang"); } LinkedHashSet<String> listsystem = new LinkedHashSet<String>() { { add("com.android"); add("com.google.android"); //add("com.sec.android.app"); add("com.monotype.android"); add("eu.chainfire.supersu"); } }; // \r\n for Windows Notepad gen.write("<?xml version=\"1.0\" encoding=\"UTF-8\"?>\r\n"); gen.write("<!-- & raplace with & or use <![CDATA[ ]]> -->\r\n"); gen.write("<AndroidUninstallStock>\r\n\r\n"); gen.write("<Normal>\r\n"); System.out.println(); System.out.println("\tNormal:"); writeInfo(gen, apklist, lang, listsystem, true); gen.write("\t<apk name=\"Exclude Google and etc\">\r\n"); for (String exc : listsystem) { gen.write("\t\t<exclude global=\"true\" in=\"package\" pattern=\"" + exc + "\" />\r\n"); } gen.write("\t</apk>\r\n"); gen.write("</Normal>\r\n\r\n"); gen.write("<Google>\r\n"); System.out.println(); System.out.println("\tGoogle:"); writeInfo(gen, apklist, lang, listsystem, false); gen.write("</Google>\r\n\r\n"); gen.write("</AndroidUninstallStock>\r\n"); System.out.println("File " + genpath.toAbsolutePath() + " created."); } return; } String[] FileName = cmd.getArgs(); if (!(FileName.length > 0 && Files.isReadable(Paths.get(FileName[0])))) { System.out.println("Error: File " + FileName[0] + " not found!"); return; } DocumentBuilderFactory xmlfactory = getXmlDocFactory(); // DocumentBuilder.setErrorHandler() for print errors Document xml = xmlfactory.newDocumentBuilder().parse(new File(FileName[0])); LinkedList<AusInfo> Normal = new LinkedList<AusInfo>(); LinkedList<AusInfo> Google = new LinkedList<AusInfo>(); NodeList ndaus = xml.getElementsByTagName("AndroidUninstallStock").item(0).getChildNodes(); for (int ndausx = 0, ndausc = ndaus.getLength(); ndausx < ndausc; ndausx++) { Node ndnow = ndaus.item(ndausx); NodeList nd = ndnow.getChildNodes(); String ndname = ndnow.getNodeName(); for (int ndx = 0, ndc = nd.getLength(); ndx < ndc; ndx++) { if (!nd.item(ndx).getNodeName().equalsIgnoreCase("apk")) { continue; } if (ndname.equalsIgnoreCase("Normal")) { Normal.add(getApkInfo(nd.item(ndx))); } else if (ndname.equalsIgnoreCase("Google")) { Google.add(getApkInfo(nd.item(ndx))); } } } // FIXME This part must be repeated until the "pm uninstall" will not issue "Failure" on all packages. // Now requires a restart. System.out.println(); System.out.println("Include and Exclude packages (Normal):"); LinkedHashMap<String, String> apkNormal = getApkFromPattern(apklist, Normal, false); System.out.println(); System.out.println("Global Exclude packages (Normal):"); apkNormal = getApkFromPattern(apkNormal, Normal, true); System.out.println(); System.out.println("Final list packages (Normal):"); for (Map.Entry<String, String> info : sortByValues(apkNormal).entrySet()) { System.out.println(info.getValue() + " = " + info.getKey()); } LinkedHashMap<String, String> apkGoogle = new LinkedHashMap<String, String>(); if (cmd.hasOption("google")) { System.out.println(); System.out.println("Include and Exclude packages (Google):"); apkGoogle = getApkFromPattern(apklist, Google, false); System.out.println(); System.out.println("Global Exclude packages (Google):"); apkGoogle = getApkFromPattern(apkGoogle, Google, true); System.out.println(); System.out.println("Final list packages (Google):"); for (Map.Entry<String, String> info : sortByValues(apkGoogle).entrySet()) { System.out.println(info.getValue() + " = " + info.getKey()); } } if (NotTest) { if (!hasRoot(adb)) { System.out.println("No Root"); System.out.println(); System.out.println("FINISH :)"); return; } } if (cmd.hasOption("restore")) { System.out.println(); System.out.println("Enable (Restore) packages (Normal):"); damage(adb, "pm enable ", NotTest, apkNormal, 2); if (cmd.hasOption("google")) { System.out.println(); System.out.println("Enable (Restore) packages (Google):"); damage(adb, "pm enable ", NotTest, apkGoogle, 2); } System.out.println(); System.out.println("FINISH :)"); return; } else { System.out.println(); System.out.println("Disable packages (Normal):"); damage(adb, "pm disable ", NotTest, apkNormal, 2); if (cmd.hasOption("google")) { System.out.println(); System.out.println("Disable packages (Google):"); damage(adb, "pm disable ", NotTest, apkGoogle, 2); } } if (!cmd.hasOption("unapk") && !cmd.hasOption("unlib")) { System.out.println(); System.out.println("FINISH :)"); return; } // Reboot now not needed /*if (NotTest) { reboot(adb, "-s", lastdevice, "reboot"); if (!hasRoot(adb)) { System.out.println("No Root"); System.out.println(); System.out.println("FINISH :)"); return; } }*/ if (cmd.hasOption("unlib")) { // "find" not found System.out.println(); System.out.println("Getting list libraries:"); LinkedList<String> liblist = new LinkedList<String>(); liblist.addAll(run(adb, "-s", lastdevice, "shell", "ls -l /system/lib/")); String dircur = "/system/lib/"; for (int x = 0; x < liblist.size(); x++) { if (liblist.get(x).startsWith("scan:")) { dircur = liblist.get(x).substring("scan:".length()); liblist.remove(x); x--; } else if (liblist.get(x).startsWith("d")) { String dir = liblist.get(x).substring(liblist.get(x).lastIndexOf(':') + 4) + "/"; liblist.remove(x); x--; liblist.add("scan:/system/lib/" + dir); liblist.addAll(run(adb, "-s", lastdevice, "shell", "ls -l /system/lib/" + dir)); continue; } liblist.set(x, dircur + liblist.get(x).substring(liblist.get(x).lastIndexOf(':') + 4)); System.out.println(liblist.get(x)); } final boolean scanlibs = cmd.hasOption("scanlibs"); LinkedHashMap<String, String> libNormal = getLibFromPatternInclude(adb, liblist, apkNormal, Normal, "Normal", scanlibs); libNormal = getLibFromPatternGlobalExclude(libNormal, Normal, "Normal"); System.out.println(); System.out.println("Final list libraries (Normal):"); for (Map.Entry<String, String> info : sortByValues(libNormal).entrySet()) { System.out.println(info.getKey() + " = " + info.getValue()); } LinkedHashMap<String, String> libGoogle = new LinkedHashMap<String, String>(); if (cmd.hasOption("google")) { libGoogle = getLibFromPatternInclude(adb, liblist, apkGoogle, Google, "Google", scanlibs); libGoogle = getLibFromPatternGlobalExclude(libGoogle, Google, "Google"); System.out.println(); System.out.println("Final list libraries (Google):"); for (Map.Entry<String, String> info : sortByValues(libGoogle).entrySet()) { System.out.println(info.getKey() + " = " + info.getValue()); } } LinkedHashMap<String, String> apkExclude = new LinkedHashMap<String, String>(apklist); for (String key : apkNormal.keySet()) { apkExclude.remove(key); } for (String key : apkGoogle.keySet()) { apkExclude.remove(key); } System.out.println(); System.out.println("Include libraries from Exclude packages:"); LinkedHashMap<String, String> libExclude = getLibFromPackage(adb, liblist, apkExclude); System.out.println(); System.out.println("Enclude libraries from Exclude packages (Normal):"); for (Map.Entry<String, String> info : sortByValues(libNormal).entrySet()) { if (libExclude.containsKey(info.getKey())) { System.out.println("exclude: " + info.getKey() + " = " + libExclude.get(info.getKey())); libNormal.remove(info.getKey()); } } System.out.println(); System.out.println("Enclude libraries from Exclude packages (Google):"); for (Map.Entry<String, String> info : sortByValues(libGoogle).entrySet()) { if (libExclude.containsKey(info.getKey())) { System.out.println("exclude: " + info.getKey() + " = " + libExclude.get(info.getKey())); libGoogle.remove(info.getKey()); } } System.out.println(); System.out.println("Delete libraries (Normal):"); damage(adb, "rm ", NotTest, libNormal, 1); if (cmd.hasOption("google")) { System.out.println(); System.out.println("Delete libraries (Google):"); damage(adb, "rm ", NotTest, libGoogle, 1); } } if (cmd.hasOption("unapk")) { System.out.println(); System.out.println("Cleaning data packages (Normal):"); damage(adb, "pm clear ", NotTest, apkNormal, 2); if (cmd.hasOption("google")) { System.out.println(); System.out.println("Cleaning data packages (Google):"); damage(adb, "pm clear ", NotTest, apkGoogle, 2); } System.out.println(); System.out.println("Uninstall packages (Normal):"); damage(adb, "pm uninstall ", NotTest, apkNormal, 2); if (cmd.hasOption("google")) { System.out.println(); System.out.println("Uninstall packages (Google):"); damage(adb, "pm uninstall ", NotTest, apkGoogle, 2); } } if (cmd.hasOption("unapk")) { System.out.println(); System.out.println("Delete packages (Normal):"); LinkedHashMap<String, String> dexNormal = new LinkedHashMap<String, String>(); for (Map.Entry<String, String> apk : apkNormal.entrySet()) { dexNormal.put(apk.getKey(), apk.getValue()); dexNormal.put(apk.getKey().replace(".apk", ".dex"), apk.getValue()); dexNormal.put(apk.getKey().replace(".apk", ".odex"), apk.getValue()); } damage(adb, "rm ", NotTest, dexNormal, 1); if (cmd.hasOption("google")) { System.out.println(); System.out.println("Delete packages (Google):"); LinkedHashMap<String, String> dexGoogle = new LinkedHashMap<String, String>(); for (Map.Entry<String, String> apk : apkGoogle.entrySet()) { dexGoogle.put(apk.getKey(), apk.getValue()); dexGoogle.put(apk.getKey().replace(".apk", ".dex"), apk.getValue()); dexGoogle.put(apk.getKey().replace(".apk", ".odex"), apk.getValue()); } damage(adb, "rm ", NotTest, dexGoogle, 1); } } if (NotTest) { run(adb, "-s", lastdevice, "reboot"); } System.out.println(); System.out.println("FINISH :)"); } catch (SAXException e) { System.out.println("Error parsing list: " + e); } catch (Throwable e) { e.printStackTrace(); } }
From source file:com.ikanow.aleph2.enrichment.utils.services.JsScriptEngineTestService.java
/** Entry point * @param args/*from w w w . j av a 2s .c o m*/ * @throws IOException */ public static void main(String[] args) throws IOException { if (args.length < 3) { System.out .println("ARGS: <script-file> <input-file> <output-prefix> [{[len: <LEN>], [group: <GROUP>]}]"); } // STEP 1: load script file final String user_script = Files.toString(new File(args[0]), Charsets.UTF_8); // STEP 2: get a stream for the JSON file final InputStream io_stream = new FileInputStream(new File(args[1])); // STEP 3: set up control if applicable Optional<JsonNode> json = Optional.of("").filter(__ -> args.length > 3).map(__ -> args[3]) .map(Lambdas.wrap_u(j -> _mapper.readTree(j))); // STEP 4: set up the various objects final DataBucketBean bucket = Mockito.mock(DataBucketBean.class); final JsScriptEngineService service_under_test = new JsScriptEngineService(); final LinkedList<ObjectNode> emitted = new LinkedList<>(); final LinkedList<JsonNode> grouped = new LinkedList<>(); final LinkedList<JsonNode> externally_emitted = new LinkedList<>(); final IEnrichmentModuleContext context = Mockito.mock(IEnrichmentModuleContext.class, new Answer<Void>() { @SuppressWarnings("unchecked") public Void answer(InvocationOnMock invocation) { try { Object[] args = invocation.getArguments(); if (invocation.getMethod().getName().equals("emitMutableObject")) { final Optional<JsonNode> grouping = (Optional<JsonNode>) args[3]; if (grouping.isPresent()) { grouped.add(grouping.get()); } emitted.add((ObjectNode) args[1]); } else if (invocation.getMethod().getName().equals("externalEmit")) { final DataBucketBean to = (DataBucketBean) args[0]; final Either<JsonNode, Map<String, Object>> out = (Either<JsonNode, Map<String, Object>>) args[1]; externally_emitted .add(((ObjectNode) out.left().value()).put("__a2_bucket", to.full_name())); } } catch (Exception e) { e.printStackTrace(); } return null; } }); final EnrichmentControlMetadataBean control = BeanTemplateUtils.build(EnrichmentControlMetadataBean.class) .with(EnrichmentControlMetadataBean::config, new LinkedHashMap<String, Object>( ImmutableMap.<String, Object>builder().put("script", user_script).build())) .done().get(); service_under_test.onStageInitialize(context, bucket, control, Tuples._2T(ProcessingStage.batch, ProcessingStage.grouping), Optional.empty()); final BeJsonParser json_parser = new BeJsonParser(); // Run the file through final Stream<Tuple2<Long, IBatchRecord>> json_stream = StreamUtils .takeUntil(Stream.generate(() -> json_parser.getNextRecord(io_stream)), i -> null == i) .map(j -> Tuples._2T(0L, new BatchRecord(j))); service_under_test.onObjectBatch(json_stream, json.map(j -> j.get("len")).map(j -> (int) j.asLong(0L)), json.map(j -> j.get("group"))); System.out.println("RESULTS: "); System.out.println("emitted: " + emitted.size()); System.out.println("grouped: " + grouped.size()); System.out.println("externally emitted: " + externally_emitted.size()); Files.write(emitted.stream().map(j -> j.toString()).collect(Collectors.joining(";")), new File(args[2] + "emit.json"), Charsets.UTF_8); Files.write(grouped.stream().map(j -> j.toString()).collect(Collectors.joining(";")), new File(args[2] + "group.json"), Charsets.UTF_8); Files.write(externally_emitted.stream().map(j -> j.toString()).collect(Collectors.joining(";")), new File(args[2] + "external_emit.json"), Charsets.UTF_8); }
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.//from w ww .j ava2 s . com * * 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:Main.java
public static void add2Sequence(LinkedList<String> sequenceList, String url) { if (sequenceList.size() <= SEGMENTSIZE) { sequenceList.add(url);//from w w w . j a v a 2s . c om System.out.println("sequence no: " + sequenceList.size()); } else { } }
From source file:Main.java
public static Double[] toArray(LinkedList<Double> list) { Double[] result = new Double[list.size()]; for (int i = 0; i < result.length; i++) { result[i] = list.get(i);//from w w w . j a va 2s .c o m } return result; }
From source file:Main.java
public static Byte[] toBytes(LinkedList<Byte> listBytes) { Byte[] result = new Byte[listBytes.size()]; for (int i = 0; i < result.length; i++) { result[i] = listBytes.get(i);/*from w w w . j a va 2 s. c o m*/ } return result; }
From source file:Main.java
public static byte[] toSimpleBytes(LinkedList<Byte> listBytes) { byte[] result = new byte[listBytes.size()]; for (int i = 0; i < result.length; i++) { result[i] = listBytes.get(i);/*www . j av a 2 s . c o m*/ } return result; }
From source file:Main.java
public static LinkedList<byte[]> eatUpJavaHeap(LinkedList<byte[]> list, int eatUpSize, int atomSize) { try {//www .j ava 2 s. com while (list.size() * atomSize < eatUpSize) { list.add(new byte[atomSize]); } } catch (Throwable t) { t.printStackTrace(); } finally { } return list; }
From source file:com.dsclab.loader.app.Loader.java
public static Produce getProduce() { TableTask firstTableTask = tableTask.getFirst(); if (tableTask.size() != 0) { LinkedList<String> firstTaskSql = firstTableTask.getTaskSqlList(); while (firstTaskSql.size() == 0) { tableTask.removeFirst();/*from w w w . j a v a 2 s. c o m*/ if (tableTask.size() == 0) { return null; } firstTableTask = tableTask.getFirst(); firstTaskSql = firstTableTask.getTaskSqlList(); } //firstTableTask = tableTask.getFirst(); //firstTaskSql = firstTableTask.getTaskSqlList(); Table firstTableInfo = firstTableTask.getTableInfo(); System.out.println("Tablename:" + firstTableInfo.getTableName()); System.out.println("next table:" + tableTask.getFirst().getTableInfo().getTableName()); String taskSql = firstTaskSql.getFirst(); firstTaskSql.removeFirst(); System.out.println("TaskSql:" + taskSql); return new Produce(firstTableInfo, taskSql); } return null; }