List of usage examples for java.io BufferedReader close
public void close() throws IOException
From source file:com.adobe.aem.demo.Analytics.java
public static void main(String[] args) { String hostname = null;/* w ww . j av a 2s . com*/ String url = null; String eventfile = null; // Command line options for this tool Options options = new Options(); options.addOption("h", true, "Hostname"); options.addOption("u", true, "Url"); options.addOption("f", true, "Event data file"); CommandLineParser parser = new BasicParser(); try { CommandLine cmd = parser.parse(options, args); if (cmd.hasOption("u")) { url = cmd.getOptionValue("u"); } if (cmd.hasOption("f")) { eventfile = cmd.getOptionValue("f"); } if (cmd.hasOption("h")) { hostname = cmd.getOptionValue("h"); } if (eventfile == null || hostname == null || url == null) { System.out.println("Command line parameters: -h hostname -u url -f path_to_XML_file"); System.exit(-1); } } catch (ParseException ex) { logger.error(ex.getMessage()); } URLConnection urlConn = null; DataOutputStream printout = null; BufferedReader input = null; String u = "http://" + hostname + "/" + url; String tmp = null; try { URL myurl = new URL(u); urlConn = myurl.openConnection(); urlConn.setDoInput(true); urlConn.setDoOutput(true); urlConn.setUseCaches(false); urlConn.setRequestProperty("Content-Type", "application/x-www-form-urlencoded"); printout = new DataOutputStream(urlConn.getOutputStream()); String xml = readFile(eventfile, StandardCharsets.UTF_8); printout.writeBytes(xml); printout.flush(); printout.close(); input = new BufferedReader(new InputStreamReader(urlConn.getInputStream())); logger.debug(xml); while (null != ((tmp = input.readLine()))) { logger.debug(tmp); } printout.close(); input.close(); } catch (Exception ex) { logger.error(ex.getMessage()); } }
From source file:com.twentyn.patentSearch.DocumentSearch.java
public static void main(String[] args) throws Exception { System.out.println("Starting up..."); System.out.flush();//from www . ja v a2 s. c o m Options opts = new Options(); opts.addOption(Option.builder("x").longOpt("index").hasArg().required().desc("Path to index file to read") .build()); opts.addOption(Option.builder("h").longOpt("help").desc("Print this help message and exit").build()); opts.addOption(Option.builder("v").longOpt("verbose").desc("Print verbose log output").build()); opts.addOption(Option.builder("f").longOpt("field").hasArg().desc("The indexed field to search").build()); opts.addOption( Option.builder("q").longOpt("query").hasArg().desc("The query to use when searching").build()); opts.addOption(Option.builder("l").longOpt("list-file").hasArg() .desc("A file containing a list of queries to run in sequence").build()); opts.addOption( Option.builder("e").longOpt("enumerate").desc("Enumerate the documents in the index").build()); opts.addOption(Option.builder("d").longOpt("dump").hasArg() .desc("Dump terms in the document index for a specified field").build()); opts.addOption( Option.builder("o").longOpt("output").hasArg().desc("Write results JSON to this file.").build()); opts.addOption(Option.builder("n").longOpt("inchi-field").hasArg() .desc("The index of the InChI field if an input TSV is specified.").build()); opts.addOption(Option.builder("s").longOpt("synonym-field").hasArg() .desc("The index of the chemical synonym field if an input TSV is specified.").build()); HelpFormatter helpFormatter = new HelpFormatter(); CommandLineParser cmdLineParser = new DefaultParser(); CommandLine cmdLine = null; try { cmdLine = cmdLineParser.parse(opts, args); } catch (ParseException e) { System.out.println("Caught exception when parsing command line: " + e.getMessage()); helpFormatter.printHelp("DocumentIndexer", opts); System.exit(1); } if (cmdLine.hasOption("help")) { helpFormatter.printHelp("DocumentIndexer", opts); System.exit(0); } if (!(cmdLine.hasOption("enumerate") || cmdLine.hasOption("dump") || (cmdLine.hasOption("field") && (cmdLine.hasOption("query") || cmdLine.hasOption("list-file"))))) { System.out.println("Must specify one of 'enumerate', 'dump', or 'field' + {'query', 'list-file'}"); helpFormatter.printHelp("DocumentIndexer", opts); System.exit(1); } if (cmdLine.hasOption("verbose")) { // With help from http://stackoverflow.com/questions/23434252/programmatically-change-log-level-in-log4j2 LoggerContext ctx = (LoggerContext) LogManager.getContext(false); Configuration ctxConfig = ctx.getConfiguration(); LoggerConfig logConfig = ctxConfig.getLoggerConfig(LogManager.ROOT_LOGGER_NAME); logConfig.setLevel(Level.DEBUG); ctx.updateLoggers(); LOGGER.debug("Verbose logging enabled"); } ObjectMapper objectMapper = new ObjectMapper(); objectMapper.enable(SerializationFeature.INDENT_OUTPUT); objectMapper.setVisibility(PropertyAccessor.ALL, JsonAutoDetect.Visibility.ANY); LOGGER.info("Opening index at " + cmdLine.getOptionValue("index")); try (Directory indexDir = FSDirectory.open(new File(cmdLine.getOptionValue("index")).toPath()); IndexReader indexReader = DirectoryReader.open(indexDir);) { if (cmdLine.hasOption("enumerate")) { /* Enumerate all documents in the index. * With help from * http://stackoverflow.com/questions/2311845/is-it-possible-to-iterate-through-documents-stored-in-lucene-index */ for (int i = 0; i < indexReader.maxDoc(); i++) { Document doc = indexReader.document(i); LOGGER.info("Doc " + i + ":"); LOGGER.info(doc); } } else if (cmdLine.hasOption("dump")) { /* Dump indexed terms for a specific field. * With help from http://stackoverflow.com/questions/11148036/find-list-of-terms-indexed-by-lucene */ Terms terms = SlowCompositeReaderWrapper.wrap(indexReader).terms(cmdLine.getOptionValue("dump")); LOGGER.info("Has positions: " + terms.hasPositions()); LOGGER.info("Has offsets: " + terms.hasOffsets()); LOGGER.info("Has freqs: " + terms.hasFreqs()); LOGGER.info("Stats: " + terms.getStats()); LOGGER.info(terms); TermsEnum termsEnum = terms.iterator(); BytesRef br = null; while ((br = termsEnum.next()) != null) { LOGGER.info(" " + br.utf8ToString()); } } else { IndexSearcher searcher = new IndexSearcher(indexReader); String field = cmdLine.getOptionValue("field"); List<Pair<String, String>> queries = null; if (cmdLine.hasOption("query")) { queries = Collections.singletonList(Pair.of("", cmdLine.getOptionValue("query"))); } else if (cmdLine.hasOption("list-file")) { if (!(cmdLine.hasOption("inchi-field") && cmdLine.hasOption("synonym-field"))) { LOGGER.error("Must specify both inchi-field and synonym-field when using list-file."); System.exit(1); } Integer inchiField = Integer.parseInt(cmdLine.getOptionValue("inchi-field")); Integer synonymField = Integer.parseInt(cmdLine.getOptionValue("synonym-field")); queries = new LinkedList<>(); BufferedReader r = new BufferedReader(new FileReader(cmdLine.getOptionValue("list-file"))); String line; while ((line = r.readLine()) != null) { line = line.trim(); if (!line.isEmpty()) { // TODO: use a proper TSV reader; this is intentionally terrible as is. String[] fields = line.split("\t"); queries.add(Pair.of(fields[inchiField].replace("\"", ""), fields[synonymField])); } } r.close(); } if (queries == null || queries.size() == 0) { LOGGER.error("Found no queries to run."); return; } List<SearchResult> searchResults = new ArrayList<>(queries.size()); for (Pair<String, String> queryPair : queries) { String inchi = queryPair.getLeft(); String rawQueryString = queryPair.getRight(); /* The Lucene query parser interprets the kind of structural annotations we see in chemical entities * as query directives, which is not what we want at all. Phrase queries seem to work adequately * with the analyzer we're currently using. */ String queryString = rawQueryString.trim().toLowerCase(); String[] parts = queryString.split("\\s+"); PhraseQuery query = new PhraseQuery(); for (String p : parts) { query.add(new Term(field, p)); } LOGGER.info("Running query: " + query.toString()); BooleanQuery bq = new BooleanQuery(); bq.add(query, BooleanClause.Occur.MUST); bq.add(new TermQuery(new Term(field, "yeast")), BooleanClause.Occur.SHOULD); bq.add(new TermQuery(new Term(field, "ferment")), BooleanClause.Occur.SHOULD); bq.add(new TermQuery(new Term(field, "fermentation")), BooleanClause.Occur.SHOULD); bq.add(new TermQuery(new Term(field, "fermentive")), BooleanClause.Occur.SHOULD); bq.add(new TermQuery(new Term(field, "saccharomyces")), BooleanClause.Occur.SHOULD); LOGGER.info(" Full query: " + bq.toString()); TopDocs topDocs = searcher.search(bq, 100); ScoreDoc[] scoreDocs = topDocs.scoreDocs; if (scoreDocs.length == 0) { LOGGER.info("Search returned no results."); } List<ResultDocument> results = new ArrayList<>(scoreDocs.length); for (int i = 0; i < scoreDocs.length; i++) { ScoreDoc scoreDoc = scoreDocs[i]; Document doc = indexReader.document(scoreDoc.doc); LOGGER.info("Doc " + i + ": " + scoreDoc.doc + ", score " + scoreDoc.score + ": " + doc.get("id") + ", " + doc.get("title")); results.add(new ResultDocument(scoreDoc.doc, scoreDoc.score, doc.get("title"), doc.get("id"), null)); } LOGGER.info("----- Done with query " + query.toString()); // TODO: reduce memory usage when not writing results to an output file. searchResults.add(new SearchResult(inchi, rawQueryString, bq, results)); } if (cmdLine.hasOption("output")) { try (FileWriter writer = new FileWriter(cmdLine.getOptionValue("output"));) { writer.write(objectMapper.writeValueAsString(searchResults)); } } } } }
From source file:ASCII2NATIVE.java
public static void main(String[] args) { File f = new File("c:\\mydb.script"); File f2 = new File("c:\\mydb3.script"); if (f.exists() && f.isFile()) { // convert param-file BufferedReader br = null; StringBuffer sb = new StringBuffer(); String line;//from ww w. jav a 2 s. com try { br = new BufferedReader(new InputStreamReader(new FileInputStream(f), "JISAutoDetect")); while ((line = br.readLine()) != null) { System.out.println(ascii2Native(line)); sb.append(ascii2Native(line)).append(";\n");//.append(";\n\r") } BufferedWriter out = new BufferedWriter(new OutputStreamWriter(new FileOutputStream(f2), "utf-8")); out.append(sb.toString()); out.flush(); out.close(); } catch (FileNotFoundException e) { System.err.println("file not found - " + f); } catch (IOException e) { System.err.println("read error - " + f); } finally { try { if (br != null) br.close(); } catch (Exception e) { } } } else { // // convert param-data // System.out.print(ascii2native(args[i])); // if (i + 1 < args.length) // System.out.print(' '); } }
From source file:edu.nyu.vida.data_polygamy.relationship_computation.Relationship.java
/** * @param args/*from www. j a v a 2 s .com*/ * @throws ParseException */ @SuppressWarnings({ "deprecation" }) public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException { Options options = new Options(); Option forceOption = new Option("f", "force", false, "force the computation of the relationship " + "even if files already exist"); forceOption.setRequired(false); options.addOption(forceOption); Option scoreOption = new Option("sc", "score", true, "set threhsold for relationship score"); scoreOption.setRequired(false); scoreOption.setArgName("SCORE THRESHOLD"); options.addOption(scoreOption); Option strengthOption = new Option("st", "strength", true, "set threhsold for relationship strength"); strengthOption.setRequired(false); strengthOption.setArgName("STRENGTH THRESHOLD"); options.addOption(strengthOption); Option completeRandomizationOption = new Option("c", "complete-randomization", false, "use complete randomization when performing significance tests"); completeRandomizationOption.setRequired(false); options.addOption(completeRandomizationOption); Option idOption = new Option("id", "ids", false, "output id instead of names for datasets and attributes"); idOption.setRequired(false); options.addOption(idOption); Option g1Option = new Option("g1", "first-group", true, "set first group of datasets"); g1Option.setRequired(true); g1Option.setArgName("FIRST GROUP"); g1Option.setArgs(Option.UNLIMITED_VALUES); options.addOption(g1Option); Option g2Option = new Option("g2", "second-group", true, "set second group of datasets"); g2Option.setRequired(false); g2Option.setArgName("SECOND GROUP"); g2Option.setArgs(Option.UNLIMITED_VALUES); options.addOption(g2Option); Option machineOption = new Option("m", "machine", true, "machine identifier"); machineOption.setRequired(true); machineOption.setArgName("MACHINE"); machineOption.setArgs(1); options.addOption(machineOption); Option nodesOption = new Option("n", "nodes", true, "number of nodes"); nodesOption.setRequired(true); nodesOption.setArgName("NODES"); nodesOption.setArgs(1); options.addOption(nodesOption); Option s3Option = new Option("s3", "s3", false, "data on Amazon S3"); s3Option.setRequired(false); options.addOption(s3Option); Option awsAccessKeyIdOption = new Option("aws_id", "aws-id", true, "aws access key id; " + "this is required if the execution is on aws"); awsAccessKeyIdOption.setRequired(false); awsAccessKeyIdOption.setArgName("AWS-ACCESS-KEY-ID"); awsAccessKeyIdOption.setArgs(1); options.addOption(awsAccessKeyIdOption); Option awsSecretAccessKeyOption = new Option("aws_key", "aws-id", true, "aws secrect access key; " + "this is required if the execution is on aws"); awsSecretAccessKeyOption.setRequired(false); awsSecretAccessKeyOption.setArgName("AWS-SECRET-ACCESS-KEY"); awsSecretAccessKeyOption.setArgs(1); options.addOption(awsSecretAccessKeyOption); Option bucketOption = new Option("b", "s3-bucket", true, "bucket on s3; " + "this is required if the execution is on aws"); bucketOption.setRequired(false); bucketOption.setArgName("S3-BUCKET"); bucketOption.setArgs(1); options.addOption(bucketOption); Option helpOption = new Option("h", "help", false, "display this message"); helpOption.setRequired(false); options.addOption(helpOption); Option removeOption = new Option("r", "remove-not-significant", false, "remove relationships that are not" + "significant from the final output"); removeOption.setRequired(false); options.addOption(removeOption); HelpFormatter formatter = new HelpFormatter(); CommandLineParser parser = new PosixParser(); CommandLine cmd = null; try { cmd = parser.parse(options, args); } catch (ParseException e) { formatter.printHelp("hadoop jar data-polygamy.jar " + "edu.nyu.vida.data_polygamy.relationship_computation.Relationship", options, true); System.exit(0); } if (cmd.hasOption("h")) { formatter.printHelp("hadoop jar data-polygamy.jar " + "edu.nyu.vida.data_polygamy.relationship_computation.Relationship", options, true); System.exit(0); } boolean s3 = cmd.hasOption("s3"); String s3bucket = ""; String awsAccessKeyId = ""; String awsSecretAccessKey = ""; if (s3) { if ((!cmd.hasOption("aws_id")) || (!cmd.hasOption("aws_key")) || (!cmd.hasOption("b"))) { System.out.println( "Arguments 'aws_id', 'aws_key', and 'b'" + " are mandatory if execution is on AWS."); formatter.printHelp( "hadoop jar data-polygamy.jar " + "edu.nyu.vida.data_polygamy.relationship_computation.Relationship", options, true); System.exit(0); } s3bucket = cmd.getOptionValue("b"); awsAccessKeyId = cmd.getOptionValue("aws_id"); awsSecretAccessKey = cmd.getOptionValue("aws_key"); } boolean snappyCompression = false; boolean bzip2Compression = false; String machine = cmd.getOptionValue("m"); int nbNodes = Integer.parseInt(cmd.getOptionValue("n")); Configuration s3conf = new Configuration(); if (s3) { s3conf.set("fs.s3.awsAccessKeyId", awsAccessKeyId); s3conf.set("fs.s3.awsSecretAccessKey", awsSecretAccessKey); s3conf.set("bucket", s3bucket); } Path path = null; FileSystem fs = FileSystem.get(new Configuration()); ArrayList<String> shortDataset = new ArrayList<String>(); ArrayList<String> firstGroup = new ArrayList<String>(); ArrayList<String> secondGroup = new ArrayList<String>(); HashMap<String, String> datasetAgg = new HashMap<String, String>(); boolean removeNotSignificant = cmd.hasOption("r"); boolean removeExistingFiles = cmd.hasOption("f"); boolean completeRandomization = cmd.hasOption("c"); boolean hasScoreThreshold = cmd.hasOption("sc"); boolean hasStrengthThreshold = cmd.hasOption("st"); boolean outputIds = cmd.hasOption("id"); String scoreThreshold = hasScoreThreshold ? cmd.getOptionValue("sc") : ""; String strengthThreshold = hasStrengthThreshold ? cmd.getOptionValue("st") : ""; // all datasets ArrayList<String> all_datasets = new ArrayList<String>(); if (s3) { path = new Path(s3bucket + FrameworkUtils.datasetsIndexDir); fs = FileSystem.get(path.toUri(), s3conf); } else { path = new Path(fs.getHomeDirectory() + "/" + FrameworkUtils.datasetsIndexDir); } BufferedReader br = new BufferedReader(new InputStreamReader(fs.open(path))); String line = br.readLine(); while (line != null) { all_datasets.add(line.split("\t")[0]); line = br.readLine(); } br.close(); if (s3) fs.close(); String[] all_datasets_array = new String[all_datasets.size()]; all_datasets.toArray(all_datasets_array); String[] firstGroupCmd = cmd.getOptionValues("g1"); String[] secondGroupCmd = cmd.hasOption("g2") ? cmd.getOptionValues("g2") : all_datasets_array; addDatasets(firstGroupCmd, firstGroup, shortDataset, datasetAgg, path, fs, s3conf, s3, s3bucket); addDatasets(secondGroupCmd, secondGroup, shortDataset, datasetAgg, path, fs, s3conf, s3, s3bucket); if (shortDataset.size() == 0) { System.out.println("No datasets to process."); System.exit(0); } if (firstGroup.isEmpty()) { System.out.println("No indices from datasets in G1."); System.exit(0); } if (secondGroup.isEmpty()) { System.out.println("No indices from datasets in G2."); System.exit(0); } // getting dataset ids String datasetNames = ""; String datasetIds = ""; HashMap<String, String> datasetId = new HashMap<String, String>(); Iterator<String> it = shortDataset.iterator(); while (it.hasNext()) { datasetId.put(it.next(), null); } if (s3) { path = new Path(s3bucket + FrameworkUtils.datasetsIndexDir); fs = FileSystem.get(path.toUri(), s3conf); } else { path = new Path(fs.getHomeDirectory() + "/" + FrameworkUtils.datasetsIndexDir); } br = new BufferedReader(new InputStreamReader(fs.open(path))); line = br.readLine(); while (line != null) { String[] dt = line.split("\t"); all_datasets.add(dt[0]); if (datasetId.containsKey(dt[0])) { datasetId.put(dt[0], dt[1]); datasetNames += dt[0] + ","; datasetIds += dt[1] + ","; } line = br.readLine(); } br.close(); if (s3) fs.close(); datasetNames = datasetNames.substring(0, datasetNames.length() - 1); datasetIds = datasetIds.substring(0, datasetIds.length() - 1); it = shortDataset.iterator(); while (it.hasNext()) { String dataset = it.next(); if (datasetId.get(dataset) == null) { System.out.println("No dataset id for " + dataset); System.exit(0); } } String firstGroupStr = ""; String secondGroupStr = ""; for (String dataset : firstGroup) { firstGroupStr += datasetId.get(dataset) + ","; } for (String dataset : secondGroup) { secondGroupStr += datasetId.get(dataset) + ","; } firstGroupStr = firstGroupStr.substring(0, firstGroupStr.length() - 1); secondGroupStr = secondGroupStr.substring(0, secondGroupStr.length() - 1); String relationshipsDir = ""; if (outputIds) { relationshipsDir = FrameworkUtils.relationshipsIdsDir; } else { relationshipsDir = FrameworkUtils.relationshipsDir; } FrameworkUtils.createDir(s3bucket + relationshipsDir, s3conf, s3); String random = completeRandomization ? "complete" : "restricted"; String indexInputDirs = ""; String noRelationship = ""; HashSet<String> dirs = new HashSet<String>(); String dataset1; String dataset2; String datasetId1; String datasetId2; for (int i = 0; i < firstGroup.size(); i++) { for (int j = 0; j < secondGroup.size(); j++) { if (Integer.parseInt(datasetId.get(firstGroup.get(i))) < Integer .parseInt(datasetId.get(secondGroup.get(j)))) { dataset1 = firstGroup.get(i); dataset2 = secondGroup.get(j); } else { dataset1 = secondGroup.get(j); dataset2 = firstGroup.get(i); } datasetId1 = datasetId.get(dataset1); datasetId2 = datasetId.get(dataset2); if (dataset1.equals(dataset2)) continue; String correlationOutputFileName = s3bucket + relationshipsDir + "/" + dataset1 + "-" + dataset2 + "/"; if (removeExistingFiles) { FrameworkUtils.removeFile(correlationOutputFileName, s3conf, s3); } if (!FrameworkUtils.fileExists(correlationOutputFileName, s3conf, s3)) { dirs.add(s3bucket + FrameworkUtils.indexDir + "/" + dataset1); dirs.add(s3bucket + FrameworkUtils.indexDir + "/" + dataset2); } else { noRelationship += datasetId1 + "-" + datasetId2 + ","; } } } if (dirs.isEmpty()) { System.out.println("All the relationships were already computed."); System.out.println("Use -f in the beginning of the command line to force the computation."); System.exit(0); } for (String dir : dirs) { indexInputDirs += dir + ","; } Configuration conf = new Configuration(); Machine machineConf = new Machine(machine, nbNodes); String jobName = "relationship" + "-" + random; String relationshipOutputDir = s3bucket + relationshipsDir + "/tmp/"; FrameworkUtils.removeFile(relationshipOutputDir, s3conf, s3); for (int i = 0; i < shortDataset.size(); i++) { conf.set("dataset-" + datasetId.get(shortDataset.get(i)) + "-agg", datasetAgg.get(shortDataset.get(i))); } for (int i = 0; i < shortDataset.size(); i++) { conf.set("dataset-" + datasetId.get(shortDataset.get(i)) + "-agg-size", Integer.toString(datasetAgg.get(shortDataset.get(i)).split(",").length)); } conf.set("dataset-keys", datasetIds); conf.set("dataset-names", datasetNames); conf.set("first-group", firstGroupStr); conf.set("second-group", secondGroupStr); conf.set("complete-random", String.valueOf(completeRandomization)); conf.set("output-ids", String.valueOf(outputIds)); conf.set("complete-random-str", random); conf.set("main-dataset-id", datasetId.get(shortDataset.get(0))); conf.set("remove-not-significant", String.valueOf(removeNotSignificant)); if (noRelationship.length() > 0) { conf.set("no-relationship", noRelationship.substring(0, noRelationship.length() - 1)); } if (hasScoreThreshold) { conf.set("score-threshold", scoreThreshold); } if (hasStrengthThreshold) { conf.set("strength-threshold", strengthThreshold); } conf.set("mapreduce.tasktracker.map.tasks.maximum", String.valueOf(machineConf.getMaximumTasks())); conf.set("mapreduce.tasktracker.reduce.tasks.maximum", String.valueOf(machineConf.getMaximumTasks())); conf.set("mapreduce.jobtracker.maxtasks.perjob", "-1"); conf.set("mapreduce.reduce.shuffle.parallelcopies", "20"); conf.set("mapreduce.input.fileinputformat.split.minsize", "0"); conf.set("mapreduce.task.io.sort.mb", "200"); conf.set("mapreduce.task.io.sort.factor", "100"); conf.set("mapreduce.task.timeout", "2400000"); if (s3) { machineConf.setMachineConfiguration(conf); conf.set("fs.s3.awsAccessKeyId", awsAccessKeyId); conf.set("fs.s3.awsSecretAccessKey", awsSecretAccessKey); conf.set("bucket", s3bucket); } if (snappyCompression) { conf.set("mapreduce.map.output.compress", "true"); conf.set("mapreduce.map.output.compress.codec", "org.apache.hadoop.io.compress.SnappyCodec"); //conf.set("mapreduce.output.fileoutputformat.compress.codec", "org.apache.hadoop.io.compress.SnappyCodec"); } if (bzip2Compression) { conf.set("mapreduce.map.output.compress", "true"); conf.set("mapreduce.map.output.compress.codec", "org.apache.hadoop.io.compress.BZip2Codec"); //conf.set("mapreduce.output.fileoutputformat.compress.codec", "org.apache.hadoop.io.compress.BZip2Codec"); } Job job = new Job(conf); job.setJobName(jobName); job.setMapOutputKeyClass(PairAttributeWritable.class); job.setMapOutputValueClass(TopologyTimeSeriesWritable.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); job.setMapperClass(CorrelationMapper.class); job.setReducerClass(CorrelationReducer.class); job.setNumReduceTasks(machineConf.getNumberReduces()); job.setInputFormatClass(SequenceFileInputFormat.class); //job.setOutputFormatClass(TextOutputFormat.class); LazyOutputFormat.setOutputFormatClass(job, TextOutputFormat.class); FileInputFormat.setInputDirRecursive(job, true); FileInputFormat.setInputPaths(job, indexInputDirs.substring(0, indexInputDirs.length() - 1)); FileOutputFormat.setOutputPath(job, new Path(relationshipOutputDir)); job.setJarByClass(Relationship.class); long start = System.currentTimeMillis(); job.submit(); job.waitForCompletion(true); System.out.println(jobName + "\t" + (System.currentTimeMillis() - start)); // moving files to right place for (int i = 0; i < firstGroup.size(); i++) { for (int j = 0; j < secondGroup.size(); j++) { if (Integer.parseInt(datasetId.get(firstGroup.get(i))) < Integer .parseInt(datasetId.get(secondGroup.get(j)))) { dataset1 = firstGroup.get(i); dataset2 = secondGroup.get(j); } else { dataset1 = secondGroup.get(j); dataset2 = firstGroup.get(i); } if (dataset1.equals(dataset2)) continue; String from = s3bucket + relationshipsDir + "/tmp/" + dataset1 + "-" + dataset2 + "/"; String to = s3bucket + relationshipsDir + "/" + dataset1 + "-" + dataset2 + "/"; FrameworkUtils.renameFile(from, to, s3conf, s3); } } }
From source file:SheetStructure.java
public static void main(String[] args) { HttpURLConnection connection = null; StringBuilder response = new StringBuilder(); //We are using Jackson JSON parser to serialize and deserialize the JSON. See http://wiki.fasterxml.com/JacksonHome //Feel free to use which ever library you prefer. ObjectMapper mapper = new ObjectMapper(); mapper.configure(DeserializationFeature.FAIL_ON_UNKNOWN_PROPERTIES, false); String accessToken = "";//Insert your access token here. try {/*from w w w . jav a2s . com*/ System.out.println("Starting HelloSmartsheet2: Betty's Bake Sale..."); //First Create a new sheet. String sheetName = "Betty's Bake Sale"; //We will be using POJOs to represent the REST request objects. We will convert these to and from JSON using Jackson JSON. //Their structure directly relates to the JSON that gets passed through the API. //Note that these POJOs are included as static inner classes to keep this to one file. Normally they would be broken out. Sheet newSheet = new Sheet(); newSheet.setName(sheetName); newSheet.setColumns(Arrays.asList(new Column("Baked Goods", "TEXT_NUMBER", null, true, null), new Column("Baker", "CONTACT_LIST", null, null, null), new Column("Price Per Item", "TEXT_NUMBER", null, null, null), new Column("Gluten Free?", "CHECKBOX", "FLAG", null, null), new Column("Status", "PICKLIST", null, null, Arrays.asList("Started", "Finished", "Delivered")))); connection = (HttpURLConnection) new URL(GET_SHEETS_URL).openConnection(); connection.addRequestProperty("Authorization", "Bearer " + accessToken); connection.addRequestProperty("Content-Type", "application/json"); connection.setDoOutput(true); mapper.writeValue(connection.getOutputStream(), newSheet); Result<Sheet> newSheetResult = mapper.readValue(connection.getInputStream(), new TypeReference<Result<Sheet>>() { }); newSheet = newSheetResult.getResult(); System.out.println("Sheet " + newSheet.getName() + " created, id: " + newSheet.getId()); //Now add a column: String columnName = "Delivery Date"; System.out.println("Adding column " + columnName + " to " + sheetName); Column newColumn = new Column(columnName, "DATE", 5); connection = (HttpURLConnection) new URL(SHEET_COLUMNS_URL.replace(ID, "" + newSheet.getId())) .openConnection(); connection.addRequestProperty("Authorization", "Bearer " + accessToken); connection.addRequestProperty("Content-Type", "application/json"); connection.setDoOutput(true); mapper.writeValue(connection.getOutputStream(), newColumn); Result<Column> newColumnResult = mapper.readValue(connection.getInputStream(), new TypeReference<Result<Column>>() { }); System.out.println( "Column " + newColumnResult.getResult().getTitle() + " added to " + newSheet.getName()); //Next, we will get the list of Columns from the API. We could figure this out based on what the server has returned in the result, but we'll just ask the API for it. System.out.println("Fetching " + newSheet.getName() + " sheet columns..."); connection = (HttpURLConnection) new URL(SHEET_COLUMNS_URL.replace(ID, "" + newSheet.getId())) .openConnection(); connection.addRequestProperty("Authorization", "Bearer " + accessToken); List<Column> allColumns = mapper.readValue(connection.getInputStream(), new TypeReference<List<Column>>() { }); System.out.println("Fetched."); //Now we will be adding rows System.out.println("Inserting rows into " + newSheet.getName()); List<Row> rows = new ArrayList<Row>(); rows.add(new Row(Arrays.asList(new Cell(allColumns.get(0).id, "Brownies"), new Cell(allColumns.get(1).id, "julieann@example.com"), new Cell(allColumns.get(2).id, "$1"), new Cell(allColumns.get(3).id, Boolean.TRUE), new Cell(allColumns.get(4).id, "Finished")))); rows.add(new Row(Arrays.asList(new Cell(allColumns.get(0).id, "Snickerdoodles"), new Cell(allColumns.get(1).id, "stevenelson@example.com"), new Cell(allColumns.get(2).id, "$1"), new Cell(allColumns.get(3).id, Boolean.FALSE), new Cell(allColumns.get(4).id, "Delivered"), new Cell(allColumns.get(5).id, "2013-09-04")))); rows.add(new Row(Arrays.asList(new Cell(allColumns.get(0).id, "Rice Krispy Treats"), new Cell(allColumns.get(1).id, "rickthames@example.com"), new Cell(allColumns.get(2).id, "$.50"), new Cell(allColumns.get(3).id, Boolean.TRUE), new Cell(allColumns.get(4).id, "Started")))); rows.add(new Row(Arrays.asList(new Cell(allColumns.get(0).id, "Muffins"), new Cell(allColumns.get(1).id, "sandrassmart@example.com"), new Cell(allColumns.get(2).id, "$1.50"), new Cell(allColumns.get(3).id, Boolean.FALSE), new Cell(allColumns.get(4).id, "Finished")))); rows.add(new Row(Arrays.asList(new Cell(allColumns.get(0).id, "Chocolate Chip Cookies"), new Cell(allColumns.get(1).id, "janedaniels@example.com"), new Cell(allColumns.get(2).id, "$1"), new Cell(allColumns.get(3).id, Boolean.FALSE), new Cell(allColumns.get(4).id, "Delivered"), new Cell(allColumns.get(5).id, "2013-09-05")))); rows.add(new Row(Arrays.asList(new Cell(allColumns.get(0).id, "Ginger Snaps"), new Cell(allColumns.get(1).id, "nedbarnes@example.com"), new Cell(allColumns.get(2).id, "$.50"), new Cell(allColumns.get(3).id, Boolean.TRUE), new Cell(allColumns.get(4).id, "Unknown", false)))); //Note that this one is strict=false. This is because "Unknown" was not one of the original options when the column was created. RowWrapper rowWrapper = new RowWrapper(); rowWrapper.setToBottom(true); rowWrapper.setRows(rows); connection = (HttpURLConnection) new URL(SHEET_ROWS_URL.replace(ID, "" + newSheet.getId())) .openConnection(); connection.addRequestProperty("Authorization", "Bearer " + accessToken); connection.addRequestProperty("Content-Type", "application/json"); connection.setDoOutput(true); mapper.writeValue(connection.getOutputStream(), rowWrapper); Result<List<Row>> newRowsResult = mapper.readValue(connection.getInputStream(), new TypeReference<Result<List<Row>>>() { }); System.out.println("Added " + newRowsResult.getResult().size() + " rows to " + newSheet.getName()); //Move a row to the top. System.out.println("Moving row 6 to the top."); RowWrapper moveToTop = new RowWrapper(); moveToTop.setToTop(true); connection = (HttpURLConnection) new URL( ROW_URL.replace(ID, "" + newRowsResult.getResult().get(5).getId())).openConnection(); connection.setRequestMethod("PUT"); connection.addRequestProperty("Authorization", "Bearer " + accessToken); connection.addRequestProperty("Content-Type", "application/json"); connection.setDoOutput(true); mapper.writeValue(connection.getOutputStream(), moveToTop); mapper.readValue(connection.getInputStream(), new TypeReference<Result<List<Row>>>() { }); System.out.println("Row 6 moved to top."); //Insert empty rows for spacing rows = new ArrayList<Row>(); rows.add(new Row(Arrays.asList(new Cell(allColumns.get(0).id, "")))); rows.add(new Row(Arrays.asList(new Cell(allColumns.get(0).id, "Delivered")))); rowWrapper = new RowWrapper(); rowWrapper.setToBottom(true); rowWrapper.setRows(rows); connection = (HttpURLConnection) new URL(SHEET_ROWS_URL.replace(ID, "" + newSheet.getId())) .openConnection(); connection.addRequestProperty("Authorization", "Bearer " + accessToken); connection.addRequestProperty("Content-Type", "application/json"); connection.setDoOutput(true); mapper.writeValue(connection.getOutputStream(), rowWrapper); Result<List<Row>> spacerRowsResult = mapper.readValue(connection.getInputStream(), new TypeReference<Result<List<Row>>>() { }); System.out.println("Added " + spacerRowsResult.getResult().size() + " rows to " + newSheet.getName()); //Move Delivered rows to be children of the last spacer row. System.out.println("Moving delivered rows to Delivered section..."); Long[] deliveredRowIds = new Long[] { newRowsResult.result.get(1).getId(), newRowsResult.result.get(4).getId() }; RowWrapper parentRowLocation = new RowWrapper(); parentRowLocation.setParentId(spacerRowsResult.getResult().get(1).getId()); for (Long deliveredId : deliveredRowIds) { System.out.println("Moving " + deliveredId + " to Delivered."); connection = (HttpURLConnection) new URL(ROW_URL.replace(ID, "" + deliveredId)).openConnection(); connection.setRequestMethod("PUT"); connection.addRequestProperty("Authorization", "Bearer " + accessToken); connection.addRequestProperty("Content-Type", "application/json"); connection.setDoOutput(true); mapper.writeValue(connection.getOutputStream(), parentRowLocation); mapper.readValue(connection.getInputStream(), new TypeReference<Result<List<Row>>>() { }); System.out.println("Row id " + deliveredId + " moved."); } System.out.println("Appending additional rows to items in progress..."); List<Row> siblingRows = new ArrayList<Row>(); siblingRows.add(new Row(Arrays.asList(new Cell(allColumns.get(0).id, "Scones"), new Cell(allColumns.get(1).id, "tomlively@example.com"), new Cell(allColumns.get(2).id, "$1.50"), new Cell(allColumns.get(3).id, Boolean.TRUE), new Cell(allColumns.get(4).id, "Finished")))); siblingRows.add(new Row(Arrays.asList(new Cell(allColumns.get(0).id, "Lemon Bars"), new Cell(allColumns.get(1).id, "rickthames@example.com"), new Cell(allColumns.get(2).id, "$1"), new Cell(allColumns.get(3).id, Boolean.FALSE), new Cell(allColumns.get(4).id, "Started")))); rowWrapper = new RowWrapper(); rowWrapper.setSiblingId(newRowsResult.getResult().get(3).getId()); rowWrapper.setRows(siblingRows); connection = (HttpURLConnection) new URL(SHEET_ROWS_URL.replace(ID, "" + newSheet.getId())) .openConnection(); connection.addRequestProperty("Authorization", "Bearer " + accessToken); connection.addRequestProperty("Content-Type", "application/json"); connection.setDoOutput(true); mapper.writeValue(connection.getOutputStream(), rowWrapper); Result<List<Row>> siblingRowsResult = mapper.readValue(connection.getInputStream(), new TypeReference<Result<List<Row>>>() { }); System.out.println("Added " + siblingRowsResult.getResult().size() + " rows to " + newSheet.getName()); System.out.println("Moving Status column to index 1..."); Column statusColumn = allColumns.get(4); Column moveColumn = new Column(); moveColumn.setIndex(1); moveColumn.setTitle(statusColumn.title); moveColumn.setSheetId(newSheet.getId()); moveColumn.setType(statusColumn.getType()); connection = (HttpURLConnection) new URL(COLUMN_URL.replace(ID, "" + statusColumn.getId())) .openConnection(); connection.addRequestProperty("Authorization", "Bearer " + accessToken); connection.addRequestProperty("Content-Type", "application/json"); connection.setDoOutput(true); connection.setRequestMethod("PUT"); mapper.writeValue(connection.getOutputStream(), moveColumn); Result<Column> movedColumnResult = mapper.readValue(connection.getInputStream(), new TypeReference<Result<Column>>() { }); System.out.println("Moved column " + movedColumnResult.getResult().getId()); System.out.println("Completed Hellosmartsheet2: Betty's Bake Sale."); } catch (IOException e) { InputStream is = ((HttpURLConnection) connection).getErrorStream(); if (is != null) { BufferedReader reader = new BufferedReader(new InputStreamReader(is)); String line; try { response = new StringBuilder(); while ((line = reader.readLine()) != null) { response.append(line); } reader.close(); Result<?> result = mapper.readValue(response.toString(), Result.class); System.err.println(result.message); } catch (IOException e1) { e1.printStackTrace(); } } e.printStackTrace(); } catch (Exception e) { System.out.println("Something broke: " + e.getMessage()); e.printStackTrace(); } }
From source file:MainClass.java
public static void main(String[] args) throws IOException { SSLServerSocketFactory ssf = (SSLServerSocketFactory) SSLServerSocketFactory.getDefault(); SSLServerSocket ss = (SSLServerSocket) ssf.createServerSocket(8080); ss.setNeedClientAuth(true);//w ww .ja v a 2s. c o m while (true) { try { Socket s = ss.accept(); OutputStream out = s.getOutputStream(); BufferedReader in = new BufferedReader(new InputStreamReader(s.getInputStream())); String line = null; while (((line = in.readLine()) != null) && (!("".equals(line)))) { System.out.println(line); } System.out.println(""); StringBuffer buffer = new StringBuffer(); buffer.append("<HTML>\n"); buffer.append("<HEAD><TITLE>HTTPS Server</TITLE></HEAD>\n"); buffer.append("<BODY>\n"); buffer.append("<H1>Success!</H1>\n"); buffer.append("</BODY>\n"); buffer.append("</HTML>\n"); String string = buffer.toString(); byte[] data = string.getBytes(); out.write("HTTP/1.0 200 OK\n".getBytes()); out.write(new String("Content-Length: " + data.length + "\n").getBytes()); out.write("Content-Type: text/html\n\n".getBytes()); out.write(data); out.flush(); out.close(); in.close(); s.close(); } catch (Exception e) { e.printStackTrace(); } } }
From source file:HTTPServer.java
public static void main(String[] args) throws Exception { ServerSocket sSocket = new ServerSocket(1777); while (true) { System.out.println("Waiting for a client..."); Socket newSocket = sSocket.accept(); System.out.println("accepted the socket"); OutputStream os = newSocket.getOutputStream(); BufferedReader br = new BufferedReader(new InputStreamReader(newSocket.getInputStream())); String inLine = null;/*from w w w.java2 s . c o m*/ while (((inLine = br.readLine()) != null) && (!(inLine.equals("")))) { System.out.println(inLine); } System.out.println(""); StringBuffer sb = new StringBuffer(); sb.append("<html>\n"); sb.append("<head>\n"); sb.append("<title>Java \n"); sb.append("</title>\n"); sb.append("</head>\n"); sb.append("<body>\n"); sb.append("<H1>HTTPServer Works!</H1>\n"); sb.append("</body>\n"); sb.append("</html>\n"); String string = sb.toString(); byte[] byteArray = string.getBytes(); os.write("HTTP/1.0 200 OK\n".getBytes()); os.write(new String("Content-Length: " + byteArray.length + "\n").getBytes()); os.write("Content-Type: text/html\n\n".getBytes()); os.write(byteArray); os.flush(); os.close(); br.close(); newSocket.close(); } }
From source file:edu.nyu.vida.data_polygamy.scalar_function_computation.Aggregation.java
/** * @param args/*from w w w .ja va2 s . co m*/ */ @SuppressWarnings({ "deprecation" }) public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException { Options options = new Options(); Option forceOption = new Option("f", "force", false, "force the computation of the aggregate functions " + "even if files already exist"); forceOption.setRequired(false); options.addOption(forceOption); Option gOption = new Option("g", "group", true, "set group of datasets for which the aggregate functions" + " will be computed, followed by their temporal and spatial attribute indices"); gOption.setRequired(true); gOption.setArgName("GROUP"); gOption.setArgs(Option.UNLIMITED_VALUES); options.addOption(gOption); Option machineOption = new Option("m", "machine", true, "machine identifier"); machineOption.setRequired(true); machineOption.setArgName("MACHINE"); machineOption.setArgs(1); options.addOption(machineOption); Option nodesOption = new Option("n", "nodes", true, "number of nodes"); nodesOption.setRequired(true); nodesOption.setArgName("NODES"); nodesOption.setArgs(1); options.addOption(nodesOption); Option s3Option = new Option("s3", "s3", false, "data on Amazon S3"); s3Option.setRequired(false); options.addOption(s3Option); Option awsAccessKeyIdOption = new Option("aws_id", "aws-id", true, "aws access key id; " + "this is required if the execution is on aws"); awsAccessKeyIdOption.setRequired(false); awsAccessKeyIdOption.setArgName("AWS-ACCESS-KEY-ID"); awsAccessKeyIdOption.setArgs(1); options.addOption(awsAccessKeyIdOption); Option awsSecretAccessKeyOption = new Option("aws_key", "aws-id", true, "aws secrect access key; " + "this is required if the execution is on aws"); awsSecretAccessKeyOption.setRequired(false); awsSecretAccessKeyOption.setArgName("AWS-SECRET-ACCESS-KEY"); awsSecretAccessKeyOption.setArgs(1); options.addOption(awsSecretAccessKeyOption); Option bucketOption = new Option("b", "s3-bucket", true, "bucket on s3; " + "this is required if the execution is on aws"); bucketOption.setRequired(false); bucketOption.setArgName("S3-BUCKET"); bucketOption.setArgs(1); options.addOption(bucketOption); Option helpOption = new Option("h", "help", false, "display this message"); helpOption.setRequired(false); options.addOption(helpOption); HelpFormatter formatter = new HelpFormatter(); CommandLineParser parser = new PosixParser(); CommandLine cmd = null; try { cmd = parser.parse(options, args); } catch (ParseException e) { formatter.printHelp("hadoop jar data-polygamy.jar " + "edu.nyu.vida.data_polygamy.scalar_function_computation.Aggregation", options, true); System.exit(0); } if (cmd.hasOption("h")) { formatter.printHelp("hadoop jar data-polygamy.jar " + "edu.nyu.vida.data_polygamy.scalar_function_computation.Aggregation", options, true); System.exit(0); } boolean s3 = cmd.hasOption("s3"); String s3bucket = ""; String awsAccessKeyId = ""; String awsSecretAccessKey = ""; if (s3) { if ((!cmd.hasOption("aws_id")) || (!cmd.hasOption("aws_key")) || (!cmd.hasOption("b"))) { System.out.println( "Arguments 'aws_id', 'aws_key', and 'b'" + " are mandatory if execution is on AWS."); formatter.printHelp( "hadoop jar data-polygamy.jar " + "edu.nyu.vida.data_polygamy.scalar_function_computation.Aggregation", options, true); System.exit(0); } s3bucket = cmd.getOptionValue("b"); awsAccessKeyId = cmd.getOptionValue("aws_id"); awsSecretAccessKey = cmd.getOptionValue("aws_key"); } boolean snappyCompression = false; boolean bzip2Compression = false; String machine = cmd.getOptionValue("m"); int nbNodes = Integer.parseInt(cmd.getOptionValue("n")); Configuration s3conf = new Configuration(); if (s3) { s3conf.set("fs.s3.awsAccessKeyId", awsAccessKeyId); s3conf.set("fs.s3.awsSecretAccessKey", awsSecretAccessKey); s3conf.set("bucket", s3bucket); } String datasetNames = ""; String datasetIds = ""; String preProcessingDatasets = ""; ArrayList<String> shortDataset = new ArrayList<String>(); ArrayList<String> shortDatasetAggregation = new ArrayList<String>(); HashMap<String, String> datasetTempAtt = new HashMap<String, String>(); HashMap<String, String> datasetSpatialAtt = new HashMap<String, String>(); HashMap<String, String> preProcessingDataset = new HashMap<String, String>(); HashMap<String, String> datasetId = new HashMap<String, String>(); boolean removeExistingFiles = cmd.hasOption("f"); String[] datasetArgs = cmd.getOptionValues("g"); for (int i = 0; i < datasetArgs.length; i += 3) { String dataset = datasetArgs[i]; // getting pre-processing String tempPreProcessing = FrameworkUtils.searchPreProcessing(dataset, s3conf, s3); if (tempPreProcessing == null) { System.out.println("No pre-processing available for " + dataset); continue; } preProcessingDataset.put(dataset, tempPreProcessing); shortDataset.add(dataset); datasetTempAtt.put(dataset, ((datasetArgs[i + 1] == "null") ? null : datasetArgs[i + 1])); datasetSpatialAtt.put(dataset, ((datasetArgs[i + 2] == "null") ? null : datasetArgs[i + 2])); datasetId.put(dataset, null); } if (shortDataset.size() == 0) { System.out.println("No datasets to process."); System.exit(0); } // getting dataset id Path path = null; FileSystem fs = null; if (s3) { path = new Path(s3bucket + FrameworkUtils.datasetsIndexDir); fs = FileSystem.get(path.toUri(), s3conf); } else { fs = FileSystem.get(new Configuration()); path = new Path(fs.getHomeDirectory() + "/" + FrameworkUtils.datasetsIndexDir); } BufferedReader br = new BufferedReader(new InputStreamReader(fs.open(path))); String line = br.readLine(); while (line != null) { String[] dt = line.split("\t"); if (datasetId.containsKey(dt[0])) { datasetId.put(dt[0], dt[1]); datasetNames += dt[0] + ","; datasetIds += dt[1] + ","; } line = br.readLine(); } br.close(); if (s3) fs.close(); datasetNames = datasetNames.substring(0, datasetNames.length() - 1); datasetIds = datasetIds.substring(0, datasetIds.length() - 1); Iterator<String> it = shortDataset.iterator(); while (it.hasNext()) { String dataset = it.next(); if (datasetId.get(dataset) == null) { System.out.println("No dataset id for " + dataset); System.exit(0); } } FrameworkUtils.createDir(s3bucket + FrameworkUtils.aggregatesDir, s3conf, s3); // getting smallest resolution HashMap<String, String> tempResMap = new HashMap<String, String>(); HashMap<String, String> spatialResMap = new HashMap<String, String>(); HashMap<String, String> datasetTemporalStrMap = new HashMap<String, String>(); HashMap<String, String> datasetSpatialStrMap = new HashMap<String, String>(); HashSet<String> input = new HashSet<String>(); for (String dataset : shortDataset) { String[] datasetArray = preProcessingDataset.get(dataset).split("-"); String datasetTemporalStr = datasetArray[datasetArray.length - 2]; int datasetTemporal = utils.temporalResolution(datasetTemporalStr); String datasetSpatialStr = datasetArray[datasetArray.length - 1]; int datasetSpatial = utils.spatialResolution(datasetSpatialStr); // finding all possible resolutions String[] temporalResolutions = FrameworkUtils.getAggTempResolutions(datasetTemporal); String[] spatialResolutions = FrameworkUtils.getAggSpatialResolutions(datasetSpatial); String temporalResolution = ""; String spatialResolution = ""; String tempRes = ""; String spatialRes = ""; boolean dataAdded = false; for (int i = 0; i < temporalResolutions.length; i++) { for (int j = 0; j < spatialResolutions.length; j++) { temporalResolution = temporalResolutions[i]; spatialResolution = spatialResolutions[j]; String aggregatesOutputFileName = s3bucket + FrameworkUtils.aggregatesDir + "/" + dataset + "/"; if (removeExistingFiles) { FrameworkUtils.removeFile(aggregatesOutputFileName, s3conf, s3); } if (!FrameworkUtils.fileExists(aggregatesOutputFileName, s3conf, s3)) { dataAdded = true; tempRes += temporalResolution + "-"; spatialRes += spatialResolution + "-"; } } } if (dataAdded) { input.add(s3bucket + FrameworkUtils.preProcessingDir + "/" + preProcessingDataset.get(dataset)); shortDatasetAggregation.add(dataset); tempResMap.put(dataset, tempRes.substring(0, tempRes.length() - 1)); spatialResMap.put(dataset, spatialRes.substring(0, spatialRes.length() - 1)); datasetTemporalStrMap.put(dataset, datasetTemporalStr); datasetSpatialStrMap.put(dataset, datasetSpatialStr); } } if (input.isEmpty()) { System.out.println("All the input datasets have aggregates."); System.out.println("Use -f in the beginning of the command line to force the computation."); System.exit(0); } it = input.iterator(); while (it.hasNext()) { preProcessingDatasets += it.next() + ","; } Job aggJob = null; String aggregatesOutputDir = s3bucket + FrameworkUtils.aggregatesDir + "/tmp/"; String jobName = "aggregates"; FrameworkUtils.removeFile(aggregatesOutputDir, s3conf, s3); Configuration aggConf = new Configuration(); Machine machineConf = new Machine(machine, nbNodes); aggConf.set("dataset-name", datasetNames); aggConf.set("dataset-id", datasetIds); for (int i = 0; i < shortDatasetAggregation.size(); i++) { String dataset = shortDatasetAggregation.get(i); String id = datasetId.get(dataset); aggConf.set("dataset-" + id + "-temporal-resolutions", tempResMap.get(dataset)); aggConf.set("dataset-" + id + "-spatial-resolutions", spatialResMap.get(dataset)); aggConf.set("dataset-" + id + "-temporal-att", datasetTempAtt.get(dataset)); aggConf.set("dataset-" + id + "-spatial-att", datasetSpatialAtt.get(dataset)); aggConf.set("dataset-" + id + "-temporal", datasetTemporalStrMap.get(dataset)); aggConf.set("dataset-" + id + "-spatial", datasetSpatialStrMap.get(dataset)); if (s3) aggConf.set("dataset-" + id, s3bucket + FrameworkUtils.preProcessingDir + "/" + preProcessingDataset.get(dataset)); else aggConf.set("dataset-" + id, FileSystem.get(new Configuration()).getHomeDirectory() + "/" + FrameworkUtils.preProcessingDir + "/" + preProcessingDataset.get(dataset)); } aggConf.set("mapreduce.tasktracker.map.tasks.maximum", String.valueOf(machineConf.getMaximumTasks())); aggConf.set("mapreduce.tasktracker.reduce.tasks.maximum", String.valueOf(machineConf.getMaximumTasks())); aggConf.set("mapreduce.jobtracker.maxtasks.perjob", "-1"); aggConf.set("mapreduce.reduce.shuffle.parallelcopies", "20"); aggConf.set("mapreduce.input.fileinputformat.split.minsize", "0"); aggConf.set("mapreduce.task.io.sort.mb", "200"); aggConf.set("mapreduce.task.io.sort.factor", "100"); machineConf.setMachineConfiguration(aggConf); if (s3) { machineConf.setMachineConfiguration(aggConf); aggConf.set("fs.s3.awsAccessKeyId", awsAccessKeyId); aggConf.set("fs.s3.awsSecretAccessKey", awsSecretAccessKey); } if (snappyCompression) { aggConf.set("mapreduce.map.output.compress", "true"); aggConf.set("mapreduce.map.output.compress.codec", "org.apache.hadoop.io.compress.SnappyCodec"); //aggConf.set("mapreduce.output.fileoutputformat.compress.codec", "org.apache.hadoop.io.compress.SnappyCodec"); } if (bzip2Compression) { aggConf.set("mapreduce.map.output.compress", "true"); aggConf.set("mapreduce.map.output.compress.codec", "org.apache.hadoop.io.compress.BZip2Codec"); //aggConf.set("mapreduce.output.fileoutputformat.compress.codec", "org.apache.hadoop.io.compress.BZip2Codec"); } aggJob = new Job(aggConf); aggJob.setJobName(jobName); aggJob.setMapOutputKeyClass(SpatioTemporalWritable.class); aggJob.setMapOutputValueClass(AggregationArrayWritable.class); aggJob.setOutputKeyClass(SpatioTemporalWritable.class); aggJob.setOutputValueClass(FloatArrayWritable.class); //aggJob.setOutputKeyClass(Text.class); //aggJob.setOutputValueClass(Text.class); aggJob.setMapperClass(AggregationMapper.class); aggJob.setCombinerClass(AggregationCombiner.class); aggJob.setReducerClass(AggregationReducer.class); aggJob.setNumReduceTasks(machineConf.getNumberReduces()); aggJob.setInputFormatClass(SequenceFileInputFormat.class); //aggJob.setOutputFormatClass(SequenceFileOutputFormat.class); LazyOutputFormat.setOutputFormatClass(aggJob, SequenceFileOutputFormat.class); //LazyOutputFormat.setOutputFormatClass(aggJob, TextOutputFormat.class); SequenceFileOutputFormat.setCompressOutput(aggJob, true); SequenceFileOutputFormat.setOutputCompressionType(aggJob, CompressionType.BLOCK); FileInputFormat.setInputDirRecursive(aggJob, true); FileInputFormat.setInputPaths(aggJob, preProcessingDatasets.substring(0, preProcessingDatasets.length() - 1)); FileOutputFormat.setOutputPath(aggJob, new Path(aggregatesOutputDir)); aggJob.setJarByClass(Aggregation.class); long start = System.currentTimeMillis(); aggJob.submit(); aggJob.waitForCompletion(true); System.out.println(jobName + "\t" + (System.currentTimeMillis() - start)); // moving files to right place for (String dataset : shortDatasetAggregation) { String from = s3bucket + FrameworkUtils.aggregatesDir + "/tmp/" + dataset + "/"; String to = s3bucket + FrameworkUtils.aggregatesDir + "/" + dataset + "/"; FrameworkUtils.renameFile(from, to, s3conf, s3); } }
From source file:edu.nyu.vida.data_polygamy.standard_techniques.CorrelationTechniques.java
/** * @param args//from www. j av a2 s . c om * @throws ParseException */ @SuppressWarnings({ "deprecation" }) public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException { Options options = new Options(); Option forceOption = new Option("f", "force", false, "force the computation of the relationship " + "even if files already exist"); forceOption.setRequired(false); options.addOption(forceOption); Option g1Option = new Option("g1", "first-group", true, "set first group of datasets"); g1Option.setRequired(true); g1Option.setArgName("FIRST GROUP"); g1Option.setArgs(Option.UNLIMITED_VALUES); options.addOption(g1Option); Option g2Option = new Option("g2", "second-group", true, "set second group of datasets"); g2Option.setRequired(false); g2Option.setArgName("SECOND GROUP"); g2Option.setArgs(Option.UNLIMITED_VALUES); options.addOption(g2Option); Option machineOption = new Option("m", "machine", true, "machine identifier"); machineOption.setRequired(true); machineOption.setArgName("MACHINE"); machineOption.setArgs(1); options.addOption(machineOption); Option nodesOption = new Option("n", "nodes", true, "number of nodes"); nodesOption.setRequired(true); nodesOption.setArgName("NODES"); nodesOption.setArgs(1); options.addOption(nodesOption); Option s3Option = new Option("s3", "s3", false, "data on Amazon S3"); s3Option.setRequired(false); options.addOption(s3Option); Option awsAccessKeyIdOption = new Option("aws_id", "aws-id", true, "aws access key id; " + "this is required if the execution is on aws"); awsAccessKeyIdOption.setRequired(false); awsAccessKeyIdOption.setArgName("AWS-ACCESS-KEY-ID"); awsAccessKeyIdOption.setArgs(1); options.addOption(awsAccessKeyIdOption); Option awsSecretAccessKeyOption = new Option("aws_key", "aws-id", true, "aws secrect access key; " + "this is required if the execution is on aws"); awsSecretAccessKeyOption.setRequired(false); awsSecretAccessKeyOption.setArgName("AWS-SECRET-ACCESS-KEY"); awsSecretAccessKeyOption.setArgs(1); options.addOption(awsSecretAccessKeyOption); Option bucketOption = new Option("b", "s3-bucket", true, "bucket on s3; " + "this is required if the execution is on aws"); bucketOption.setRequired(false); bucketOption.setArgName("S3-BUCKET"); bucketOption.setArgs(1); options.addOption(bucketOption); Option helpOption = new Option("h", "help", false, "display this message"); helpOption.setRequired(false); options.addOption(helpOption); HelpFormatter formatter = new HelpFormatter(); CommandLineParser parser = new PosixParser(); CommandLine cmd = null; try { cmd = parser.parse(options, args); } catch (ParseException e) { formatter.printHelp( "hadoop jar data-polygamy.jar " + "edu.nyu.vida.data_polygamy.standard_techniques.CorrelationTechniques", options, true); System.exit(0); } if (cmd.hasOption("h")) { formatter.printHelp( "hadoop jar data-polygamy.jar " + "edu.nyu.vida.data_polygamy.standard_techniques.CorrelationTechniques", options, true); System.exit(0); } boolean s3 = cmd.hasOption("s3"); String s3bucket = ""; String awsAccessKeyId = ""; String awsSecretAccessKey = ""; if (s3) { if ((!cmd.hasOption("aws_id")) || (!cmd.hasOption("aws_key")) || (!cmd.hasOption("b"))) { System.out.println( "Arguments 'aws_id', 'aws_key', and 'b'" + " are mandatory if execution is on AWS."); formatter.printHelp( "hadoop jar data-polygamy.jar " + "edu.nyu.vida.data_polygamy.standard_techniques.CorrelationTechniques", options, true); System.exit(0); } s3bucket = cmd.getOptionValue("b"); awsAccessKeyId = cmd.getOptionValue("aws_id"); awsSecretAccessKey = cmd.getOptionValue("aws_key"); } boolean snappyCompression = false; boolean bzip2Compression = false; String machine = cmd.getOptionValue("m"); int nbNodes = Integer.parseInt(cmd.getOptionValue("n")); Configuration s3conf = new Configuration(); if (s3) { s3conf.set("fs.s3.awsAccessKeyId", awsAccessKeyId); s3conf.set("fs.s3.awsSecretAccessKey", awsSecretAccessKey); s3conf.set("bucket", s3bucket); } Path path = null; FileSystem fs = FileSystem.get(new Configuration()); ArrayList<String> shortDataset = new ArrayList<String>(); ArrayList<String> firstGroup = new ArrayList<String>(); ArrayList<String> secondGroup = new ArrayList<String>(); HashMap<String, String> datasetAgg = new HashMap<String, String>(); boolean removeExistingFiles = cmd.hasOption("f"); String[] firstGroupCmd = cmd.getOptionValues("g1"); String[] secondGroupCmd = cmd.hasOption("g2") ? cmd.getOptionValues("g2") : new String[0]; addDatasets(firstGroupCmd, firstGroup, shortDataset, datasetAgg, path, fs, s3conf, s3, s3bucket); addDatasets(secondGroupCmd, secondGroup, shortDataset, datasetAgg, path, fs, s3conf, s3, s3bucket); if (shortDataset.size() == 0) { System.out.println("No datasets to process."); System.exit(0); } if (firstGroup.isEmpty()) { System.out.println("First group of datasets (G1) is empty. " + "Doing G1 = G2."); firstGroup.addAll(secondGroup); } if (secondGroup.isEmpty()) { System.out.println("Second group of datasets (G2) is empty. " + "Doing G2 = G1."); secondGroup.addAll(firstGroup); } // getting dataset ids String datasetNames = ""; String datasetIds = ""; HashMap<String, String> datasetId = new HashMap<String, String>(); Iterator<String> it = shortDataset.iterator(); while (it.hasNext()) { datasetId.put(it.next(), null); } if (s3) { path = new Path(s3bucket + FrameworkUtils.datasetsIndexDir); fs = FileSystem.get(path.toUri(), s3conf); } else { path = new Path(fs.getHomeDirectory() + "/" + FrameworkUtils.datasetsIndexDir); } BufferedReader br = new BufferedReader(new InputStreamReader(fs.open(path))); String line = br.readLine(); while (line != null) { String[] dt = line.split("\t"); if (datasetId.containsKey(dt[0])) { datasetId.put(dt[0], dt[1]); datasetNames += dt[0] + ","; datasetIds += dt[1] + ","; } line = br.readLine(); } br.close(); if (s3) fs.close(); datasetNames = datasetNames.substring(0, datasetNames.length() - 1); datasetIds = datasetIds.substring(0, datasetIds.length() - 1); it = shortDataset.iterator(); while (it.hasNext()) { String dataset = it.next(); if (datasetId.get(dataset) == null) { System.out.println("No dataset id for " + dataset); System.exit(0); } } String firstGroupStr = ""; String secondGroupStr = ""; for (String dataset : firstGroup) { firstGroupStr += datasetId.get(dataset) + ","; } for (String dataset : secondGroup) { secondGroupStr += datasetId.get(dataset) + ","; } firstGroupStr = firstGroupStr.substring(0, firstGroupStr.length() - 1); secondGroupStr = secondGroupStr.substring(0, secondGroupStr.length() - 1); FrameworkUtils.createDir(s3bucket + FrameworkUtils.correlationTechniquesDir, s3conf, s3); String dataAttributesInputDirs = ""; String noRelationship = ""; HashSet<String> dirs = new HashSet<String>(); String dataset1; String dataset2; String datasetId1; String datasetId2; for (int i = 0; i < firstGroup.size(); i++) { for (int j = 0; j < secondGroup.size(); j++) { if (Integer.parseInt(datasetId.get(firstGroup.get(i))) < Integer .parseInt(datasetId.get(secondGroup.get(j)))) { dataset1 = firstGroup.get(i); dataset2 = secondGroup.get(j); } else { dataset1 = secondGroup.get(j); dataset2 = firstGroup.get(i); } datasetId1 = datasetId.get(dataset1); datasetId2 = datasetId.get(dataset2); if (dataset1.equals(dataset2)) continue; String correlationOutputFileName = s3bucket + FrameworkUtils.correlationTechniquesDir + "/" + dataset1 + "-" + dataset2 + "/"; if (removeExistingFiles) { FrameworkUtils.removeFile(correlationOutputFileName, s3conf, s3); } if (!FrameworkUtils.fileExists(correlationOutputFileName, s3conf, s3)) { dirs.add(s3bucket + FrameworkUtils.aggregatesDir + "/" + dataset1); dirs.add(s3bucket + FrameworkUtils.aggregatesDir + "/" + dataset2); } else { noRelationship += datasetId1 + "-" + datasetId2 + ","; } } } if (dirs.isEmpty()) { System.out.println("All the relationships were already computed."); System.out.println("Use -f in the beginning of the command line to force the computation."); System.exit(0); } for (String dir : dirs) { dataAttributesInputDirs += dir + ","; } Configuration conf = new Configuration(); Machine machineConf = new Machine(machine, nbNodes); String jobName = "correlation"; String correlationOutputDir = s3bucket + FrameworkUtils.correlationTechniquesDir + "/tmp/"; FrameworkUtils.removeFile(correlationOutputDir, s3conf, s3); for (int i = 0; i < shortDataset.size(); i++) { conf.set("dataset-" + datasetId.get(shortDataset.get(i)) + "-agg", datasetAgg.get(shortDataset.get(i))); } for (int i = 0; i < shortDataset.size(); i++) { conf.set("dataset-" + datasetId.get(shortDataset.get(i)) + "-agg-size", Integer.toString(datasetAgg.get(shortDataset.get(i)).split(",").length)); } conf.set("dataset-keys", datasetIds); conf.set("dataset-names", datasetNames); conf.set("first-group", firstGroupStr); conf.set("second-group", secondGroupStr); conf.set("main-dataset-id", datasetId.get(shortDataset.get(0))); if (noRelationship.length() > 0) { conf.set("no-relationship", noRelationship.substring(0, noRelationship.length() - 1)); } conf.set("mapreduce.tasktracker.map.tasks.maximum", String.valueOf(machineConf.getMaximumTasks())); conf.set("mapreduce.tasktracker.reduce.tasks.maximum", String.valueOf(machineConf.getMaximumTasks())); conf.set("mapreduce.jobtracker.maxtasks.perjob", "-1"); conf.set("mapreduce.reduce.shuffle.parallelcopies", "20"); conf.set("mapreduce.input.fileinputformat.split.minsize", "0"); conf.set("mapreduce.task.io.sort.mb", "200"); conf.set("mapreduce.task.io.sort.factor", "100"); conf.set("mapreduce.task.timeout", "2400000"); if (s3) { machineConf.setMachineConfiguration(conf); conf.set("fs.s3.awsAccessKeyId", awsAccessKeyId); conf.set("fs.s3.awsSecretAccessKey", awsSecretAccessKey); conf.set("bucket", s3bucket); } if (snappyCompression) { conf.set("mapreduce.map.output.compress", "true"); conf.set("mapreduce.map.output.compress.codec", "org.apache.hadoop.io.compress.SnappyCodec"); //conf.set("mapreduce.output.fileoutputformat.compress.codec", "org.apache.hadoop.io.compress.SnappyCodec"); } if (bzip2Compression) { conf.set("mapreduce.map.output.compress", "true"); conf.set("mapreduce.map.output.compress.codec", "org.apache.hadoop.io.compress.BZip2Codec"); //conf.set("mapreduce.output.fileoutputformat.compress.codec", "org.apache.hadoop.io.compress.BZip2Codec"); } Job job = new Job(conf); job.setJobName(jobName); job.setMapOutputKeyClass(PairAttributeWritable.class); job.setMapOutputValueClass(SpatioTemporalValueWritable.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); job.setMapperClass(CorrelationTechniquesMapper.class); job.setReducerClass(CorrelationTechniquesReducer.class); job.setNumReduceTasks(machineConf.getNumberReduces()); job.setInputFormatClass(SequenceFileInputFormat.class); LazyOutputFormat.setOutputFormatClass(job, TextOutputFormat.class); FileInputFormat.setInputDirRecursive(job, true); FileInputFormat.setInputPaths(job, dataAttributesInputDirs.substring(0, dataAttributesInputDirs.length() - 1)); FileOutputFormat.setOutputPath(job, new Path(correlationOutputDir)); job.setJarByClass(CorrelationTechniques.class); long start = System.currentTimeMillis(); job.submit(); job.waitForCompletion(true); System.out.println(jobName + "\t" + (System.currentTimeMillis() - start)); // moving files to right place for (int i = 0; i < firstGroup.size(); i++) { for (int j = 0; j < secondGroup.size(); j++) { if (Integer.parseInt(datasetId.get(firstGroup.get(i))) < Integer .parseInt(datasetId.get(secondGroup.get(j)))) { dataset1 = firstGroup.get(i); dataset2 = secondGroup.get(j); } else { dataset1 = secondGroup.get(j); dataset2 = firstGroup.get(i); } if (dataset1.equals(dataset2)) continue; String from = s3bucket + FrameworkUtils.correlationTechniquesDir + "/tmp/" + dataset1 + "-" + dataset2 + "/"; String to = s3bucket + FrameworkUtils.correlationTechniquesDir + "/" + dataset1 + "-" + dataset2 + "/"; FrameworkUtils.renameFile(from, to, s3conf, s3); } } }
From source file:Who.java
public static void main(String[] v) { Socket s = null;//from w w w .j a v a2 s.c o m PrintWriter out = null; BufferedReader in = null; try { // Connect to port 79 (the standard finger port) on the host. String hostname = "www.java2s.com"; s = new Socket(hostname, 79); // Set up the streams out = new PrintWriter(new OutputStreamWriter(s.getOutputStream())); in = new BufferedReader(new InputStreamReader(s.getInputStream())); // Send a blank line to the finger server, telling it that we want // a listing of everyone logged on instead of information about an // individual user. out.print("\n"); out.flush(); // Send it out // Now read the server's response // The server should send lines terminated with \n or \r. String line; while ((line = in.readLine()) != null) { System.out.println(line); } System.out.println("Who's Logged On: " + hostname); } catch (IOException e) { System.out.println("Who's Logged On: Error"); } // Close the streams! finally { try { in.close(); out.close(); s.close(); } catch (Exception e) { } } }