List of usage examples for java.util.regex Pattern compile
public static Pattern compile(String regex)
From source file:net.cloudkit.relaxation.HttpClientTest.java
public static void main(String[] args) throws Exception { InetAddress[] addresss = InetAddress.getAllByName("google.com"); for (InetAddress address : addresss) { System.out.println(address); }//w ww.java 2s. c o m CloseableHttpClient httpclient = HttpClients.createDefault(); String __VIEWSTATE = ""; String __EVENTVALIDATION = ""; HttpGet httpGet = new HttpGet("http://query.customs.gov.cn/MNFTQ/MRoadQuery.aspx?" + Math.random() * 1000); httpGet.setHeader("Accept", "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8"); httpGet.setHeader("Accept-Encoding", "gzip, deflate, sdch"); httpGet.setHeader("Accept-Language", "zh-CN,zh;q=0.8,en;q=0.6"); httpGet.setHeader("Cache-Control", "no-cache"); // httpGet.setHeader("Connection", "keep-alive"); httpGet.setHeader("Host", "query.customs.gov.cn"); httpGet.setHeader("Pragma", "no-cache"); httpGet.setHeader("Upgrade-Insecure-Requests", "1"); httpGet.setHeader("User-Agent", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36"); HttpClientContext context = HttpClientContext.create(); // CloseableHttpResponse response1 = httpclient.execute(httpGet, context); CloseableHttpResponse response1 = httpclient.execute(httpGet); // Header[] headers = response1.getHeaders(HttpHeaders.CONTENT_TYPE); // System.out.println("context cookies:" + context.getCookieStore().getCookies()); // String setCookie = response1.getFirstHeader("Set-Cookie").getValue(); // System.out.println("context cookies:" + setCookie); try { System.out.println(response1.getStatusLine()); HttpEntity entity1 = response1.getEntity(); // do something useful with the response body and ensure it is fully consumed String result = IOUtils.toString(entity1.getContent(), "GBK"); // System.out.println(result); Matcher m1 = Pattern.compile( "<input type=\\\"hidden\\\" name=\\\"__VIEWSTATE\\\" id=\\\"__VIEWSTATE\\\" value=\\\"(.*)\\\" />") .matcher(result); __VIEWSTATE = m1.find() ? m1.group(1) : ""; Matcher m2 = Pattern.compile( "<input type=\\\"hidden\\\" name=\\\"__EVENTVALIDATION\\\" id=\\\"__EVENTVALIDATION\\\" value=\\\"(.*)\\\" />") .matcher(result); __EVENTVALIDATION = m2.find() ? m2.group(1) : ""; System.out.println(__VIEWSTATE); System.out.println(__EVENTVALIDATION); /* File storeFile = new File("D:\\customs\\customs"+ i +".jpg"); FileOutputStream output = new FileOutputStream(storeFile); IOUtils.copy(input, output); output.close(); */ EntityUtils.consume(entity1); } finally { response1.close(); } HttpPost httpPost = new HttpPost( "http://query.customs.gov.cn/MNFTQ/MRoadQuery.aspx?" + Math.random() * 1000); httpPost.setHeader("Accept", "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8"); httpPost.setHeader("Accept-Encoding", "gzip, deflate"); httpPost.setHeader("Accept-Language", "zh-CN,zh;q=0.8,en;q=0.6"); httpPost.setHeader("Cache-Control", "no-cache"); // httpPost.setHeader("Connection", "keep-alive"); httpPost.setHeader("Content-Type", "application/x-www-form-urlencoded"); httpPost.setHeader("Cookie", "ASP.NET_SessionId=t1td453hcuy4oqiplekkqe55"); httpPost.setHeader("Host", "query.customs.gov.cn"); httpPost.setHeader("Origin", "http://query.customs.gov.cn"); httpPost.setHeader("Pragma", "no-cache"); httpPost.setHeader("Referer", "http://query.customs.gov.cn/MNFTQ/MRoadQuery.aspx"); httpPost.setHeader("Upgrade-Insecure-Requests", "1"); httpPost.setHeader("User-Agent", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36"); List<NameValuePair> nvps = new ArrayList<NameValuePair>(); nvps.add(new BasicNameValuePair("__VIEWSTATE", __VIEWSTATE)); nvps.add(new BasicNameValuePair("__EVENTVALIDATION", __EVENTVALIDATION)); nvps.add(new BasicNameValuePair("ScrollTop", "")); nvps.add(new BasicNameValuePair("__essVariable", "")); nvps.add(new BasicNameValuePair("MRoadQueryCtrl1$txtManifestID", "5100312462240")); nvps.add(new BasicNameValuePair("MRoadQueryCtrl1$txtBillNo", "7PH650021105")); nvps.add(new BasicNameValuePair("MRoadQueryCtrl1$txtCode", "a778")); nvps.add(new BasicNameValuePair("MRoadQueryCtrl1$btQuery", " ")); nvps.add(new BasicNameValuePair("select", "")); nvps.add(new BasicNameValuePair("select1", "")); nvps.add(new BasicNameValuePair("select2", "")); nvps.add(new BasicNameValuePair("select3", "")); nvps.add(new BasicNameValuePair("select4", "")); nvps.add(new BasicNameValuePair("select5", "??")); nvps.add(new BasicNameValuePair("select6", "")); nvps.add(new BasicNameValuePair("select7", "")); nvps.add(new BasicNameValuePair("select8", "")); httpPost.setEntity(new UrlEncodedFormEntity(nvps, "GBK")); CloseableHttpResponse response2 = httpclient.execute(httpPost); try { System.out.println(response2.getStatusLine()); HttpEntity entity2 = response2.getEntity(); // do something useful with the response body // and ensure it is fully consumed // System.out.println(entity2.getContent()); System.out.println(IOUtils.toString(response2.getEntity().getContent(), "GBK")); EntityUtils.consume(entity2); } finally { response2.close(); } }
From source file:com.github.liyp.test.TestMain.java
@SuppressWarnings("unchecked") public static void main(String[] args) { // add a shutdown hook to stop the server Runtime.getRuntime().addShutdownHook(new Thread(new Runnable() { @Override//w w w .java 2 s . co m public void run() { System.out.println("########### shoutdown begin...."); try { Thread.sleep(10000); } catch (InterruptedException e) { e.printStackTrace(); } System.out.println("########### shoutdown end...."); } })); System.out.println(args.length); Iterator<String> iterator1 = IteratorUtils .arrayIterator(new String[] { "one", "two", "three", "11", "22", "AB" }); Iterator<String> iterator2 = IteratorUtils.arrayIterator(new String[] { "a", "b", "c", "33", "ab", "aB" }); Iterator<String> chainedIter = IteratorUtils.chainedIterator(iterator1, iterator2); System.out.println("=================="); Iterator<String> iter = IteratorUtils.filteredIterator(chainedIter, new Predicate() { @Override public boolean evaluate(Object arg0) { System.out.println("xx:" + arg0.toString()); String str = (String) arg0; return str.matches("([a-z]|[A-Z]){2}"); } }); while (iter.hasNext()) { System.out.println(iter.next()); } System.out.println("==================="); System.out.println("asas".matches("[a-z]{4}")); System.out.println("Y".equals(null)); System.out.println(String.format("%02d", 1000L)); System.out.println(ArrayUtils.toString(splitAndTrim(" 11, 21,12 ,", ","))); System.out.println(new ArrayList<String>().toString()); JSONObject json = new JSONObject("{\"keynull\":null}"); json.put("bool", false); json.put("keya", "as"); json.put("key2", 2212222222222222222L); System.out.println(json); System.out.println(json.get("keynull").equals(null)); String a = String.format("{\"id\":%d,\"method\":\"testCrossSync\"," + "\"circle\":%d},\"isEnd\":true", 1, 1); System.out.println(a.getBytes().length); System.out.println(new String[] { "a", "b" }); System.out.println(new JSONArray("[\"aa\",\"\"]")); String data = String.format("%9d %s", 1, RandomStringUtils.randomAlphanumeric(10)); System.out.println(data.getBytes().length); System.out.println(ArrayUtils.toString("1|2| 3| 333||| 3".split("\\|"))); JSONObject j1 = new JSONObject("{\"a\":\"11111\"}"); JSONObject j2 = new JSONObject(j1.toString()); j2.put("b", "22222"); System.out.println(j1 + " | " + j2); System.out.println("======================"); String regex = "\\d+(\\-\\d+){2} \\d+(:\\d+){2}"; Pattern pattern = Pattern.compile(regex); Matcher matcher = pattern.matcher("2015-12-28 15:46:14 _NC250_MD:motion de\n"); String eventDate = matcher.find() ? matcher.group() : ""; System.out.println(eventDate); }
From source file:musiccrawler.MusicCrawler.java
public static void main(String[] args) { String test = "\"Yeu"; String regex = "^\"|\"$"; Pattern p = Pattern.compile(regex); Matcher m = p.matcher(test);/*from w w w . j a va 2 s . c o m*/ System.out.println(test); if (m.find()) { System.out.println(test.replaceAll(regex, "")); } }
From source file:com.wittawat.wordseg.Main.java
public static void main(String[] args) throws Exception { Console con = System.console(); if (con == null) { System.out.println("The system must support console to run the program."); System.exit(1);/*from w w w . j a v a 2 s . co m*/ } // Load model System.out.println("Loading model ..."); Classifier model = Data.getDefaultModel(); System.out.println("Finished loading model."); System.out.println(getAgreement()); boolean isUseDict = true; // Dummy statement to eliminate all lazy loading System.out.println("\n" + new NukeTokenizer3( "?????", model, isUseDict).tokenize() + "\n"); System.out.println(getHelp()); final String SET_DICT_PAT_STR = "\\s*set\\s+dict\\s+(true|false)\\s*"; final Pattern SET_DICT_PAT = Pattern.compile(SET_DICT_PAT_STR); while (true) { System.out.print(">> "); String line = con.readLine(); if (line != null && !line.trim().equals("")) { line = line.trim(); try { if (line.equals("h") || line.equals("help")) { System.out.println(getHelp()); } else if (line.equals("about")) { System.out.println(getAbout()); } else if (line.equals("agreement")) { System.out.println(getAgreement()); } else if (SET_DICT_PAT.matcher(line).find()) { Matcher m = SET_DICT_PAT.matcher(line); m.find(); String v = m.group(1); isUseDict = v.equals("true"); System.out.println("Dictionary will " + (isUseDict ? "" : "not ") + "be used."); } else if (line.matches("q|quit|exit")) { System.out.println("Bye"); System.exit(0); } else if (line.contains(":tokfile:")) { String[] splits = line.split(":tokfile:"); String in = splits[0]; String out = splits[1]; String content = FileUtils.readFileToString(new File(in)); long start = new Date().getTime(); NukeTokenizer tokenizer = new NukeTokenizer3(content, model, isUseDict); String tokenized = tokenizer.tokenize(); long end = new Date().getTime(); System.out.println("Time to tokenize: " + (end - start) + " ms."); FileUtils.writeStringToFile(new File(out), tokenized); } else if (line.contains(":tokfile")) { String[] splits = line.split(":tokfile"); String in = splits[0]; String content = FileUtils.readFileToString(new File(in)); long start = new Date().getTime(); NukeTokenizer tokenizer = new NukeTokenizer3(content, model, isUseDict); String tokenized = tokenizer.tokenize(); long end = new Date().getTime(); System.out.println(tokenized); System.out.println("Time to tokenize: " + (end - start) + " ms."); } else if (line.contains(":tok:")) { String[] splits = line.split(":tok:"); String inText = splits[0]; String out = splits[1]; long start = new Date().getTime(); NukeTokenizer tokenizer = new NukeTokenizer3(inText, model, isUseDict); String tokenized = tokenizer.tokenize(); long end = new Date().getTime(); System.out.println("Time to tokenize: " + (end - start) + " ms."); FileUtils.writeStringToFile(new File(out), tokenized); } else if (line.contains(":tok")) { String[] splits = line.split(":tok"); String inText = splits[0]; long start = new Date().getTime(); NukeTokenizer tokenizer = new NukeTokenizer3(inText, model, isUseDict); String tokenized = tokenizer.tokenize(); long end = new Date().getTime(); System.out.println(tokenized); System.out.println("Time to tokenize: " + (end - start) + " ms."); } else { System.out.println("Unknown command"); } } catch (Exception e) { System.out.println("Error. See the exception."); e.printStackTrace(); } } } }
From source file:com.movielabs.availstool.AvailsTool.java
public static void main(String[] args) throws Exception { String fileName, outFile, sheetName; int sheetNum = -1; Logger log = LogManager.getLogger(AvailsTool.class.getName()); log.info("Initializing logger"); Options options = new Options(); options.addOption(Opts.v.name(), false, "verbose mode"); options.addOption(Opts.s.name(), true, "specify sheet"); options.addOption(Opts.f.name(), true, "specify file name"); options.addOption(Opts.o.name(), true, "specify output file name"); options.addOption(Opts.sstoxml.name(), false, "convert avails spreadsheet to XML"); options.addOption(Opts.xmltoss.name(), false, "convert avails XML to a spreadsheet"); options.addOption(Opts.dumpsheet.name(), false, "dump a single sheet from a spreadsheet"); options.addOption(Opts.dumpss.name(), false, "dump a spreadsheet file"); options.addOption(Opts.wx.name(), false, "treat warning as fatal error"); options.addOption(Opts.clean.name(), false, "clean up data entries"); CommandLineParser cli = new DefaultParser(); try {/* ww w. j a v a2 s . c o m*/ CommandLine cmd = cli.parse(options, args); boolean optToXML = cmd.hasOption(Opts.sstoxml.name()); boolean optToSS = cmd.hasOption(Opts.xmltoss.name()); boolean optDumpSS = cmd.hasOption(Opts.dumpss.name()); boolean optDumpSheet = cmd.hasOption(Opts.dumpsheet.name()); fileName = cmd.getOptionValue(Opts.f.name()); sheetName = cmd.getOptionValue(Opts.s.name()); boolean clean = cmd.hasOption(Opts.clean.name()); boolean wx = cmd.hasOption(Opts.wx.name()); boolean verbose = cmd.hasOption(Opts.v.name()); AvailSS ss; AvailsSheet as; String message; if (sheetName != null) { Pattern pat = Pattern.compile("^\\d+$"); Matcher m = pat.matcher(sheetName); if (m.matches()) sheetNum = Integer.parseInt(sheetName); } if (fileName == null) throw new ParseException("input file not specified"); if (!(optToXML | optToSS | optDumpSS | optDumpSheet)) throw new ParseException("missing operation"); if (optToXML) { if (optToSS | optDumpSS | optDumpSheet) throw new ParseException("more than one operation specified"); outFile = cmd.getOptionValue(Opts.o.name()); if (outFile == null) throw new ParseException("output file not specified"); ss = new AvailSS(fileName, log, wx, clean); if (sheetNum < 0) as = ss.addSheet(sheetName); else as = ss.addSheet(sheetNum); message = "toXML file: " + fileName + " sheet: " + sheetName; log.info(message); if (verbose) System.out.println(message); log.info("Options: -clean:" + clean + "; -wx:" + wx + "; output file: " + outFile); String timeStamp = new SimpleDateFormat("yyyy.MM.dd.HH.mm.ss").format(new java.util.Date()); String shortDesc = String.format("generated XML from %s:%s on %s", fileName, sheetName, timeStamp); as.makeXMLFile(outFile, shortDesc); } else if (optToSS) { if (optToXML | optDumpSS | optDumpSheet) throw new ParseException("more than one operation specified"); // TODO implement this outFile = cmd.getOptionValue(Opts.o.name()); if (outFile == null) throw new ParseException("output file not specified"); AvailXML x = new AvailXML(fileName, log); x.makeSS(outFile); } else if (optDumpSS) { if (optToXML | optToSS | optDumpSheet) throw new ParseException("more than one operation specified"); message = "dumping file: " + fileName; log.info(message); if (verbose) System.out.println(message); AvailSS.dumpFile(fileName); } else { // dumpSheet if (sheetName == null) throw new ParseException("sheet name not specified"); message = "dumping file: " + fileName + " sheet: " + sheetName; log.info(message); if (verbose) System.out.println(message); ss = new AvailSS(fileName, log, wx, clean); if (sheetNum < 0) as = ss.addSheet(sheetName); else as = ss.addSheet(sheetNum); ss.dumpSheet(sheetName); } } catch (ParseException exp) { System.out.println("bad command line: " + exp.getMessage()); usage(); System.exit(-1); } }
From source file:de.mpg.escidoc.services.cone.util.CCCrawler.java
public static void main(String[] args) throws Exception { HttpClient httpClient = new HttpClient(); querier = QuerierFactory.newQuerier(false); // field_commercial for (YesNo fieldCommercial : YesNo.values()) { // field_derivatives for (YesNo fieldDerivatives : YesNo.values()) { // field_derivatives for (Jurisdiction fieldJurisdiction : Jurisdiction.values()) { String licenceUrl = ccUrl + "&field_commercial=" + fieldCommercial.toString() + "&field_derivatives=" + fieldDerivatives.toString() + "&field_jurisdiction=" + fieldJurisdiction.toString() + "&lang=de_DE"; System.out.println(licenceUrl); GetMethod method = new GetMethod(licenceUrl); ProxyHelper.executeMethod(httpClient, method); if (method.getStatusCode() == 200) { TreeFragment fragment = new TreeFragment(); String key1 = "urn:cone:commercial"; String key3 = "urn:cone:jurisdiction"; List<LocalizedTripleObject> list = new ArrayList<LocalizedTripleObject>(); list.add(new LocalizedString(fieldCommercial.toBoolean())); fragment.put(key1, list); List<LocalizedTripleObject> list2 = new ArrayList<LocalizedTripleObject>(); list2.add(new LocalizedString(fieldDerivatives.toBoolean())); fragment.put("urn:cone:derivatives", list2); List<LocalizedTripleObject> list3 = new ArrayList<LocalizedTripleObject>(); list3.add(new LocalizedString(fieldJurisdiction.toString())); fragment.put(key3, list3); String codeToCopy = extractCode(method); Pattern urlPattern = Pattern.compile("href=\"([^\"]+)\""); Matcher urlMatcher = urlPattern.matcher(codeToCopy); if (urlMatcher.find()) { String url = urlMatcher.group(1); fragment.setSubject(url); Pattern versionPattern = Pattern.compile("/(\\d+\\.\\d+)/[^/]+/$"); Matcher versionMatcher = versionPattern.matcher(url); if (versionMatcher.find()) { list = new ArrayList<LocalizedTripleObject>(); list.add(new LocalizedString(versionMatcher.group(1))); fragment.put("urn:cone:version", list); }// w w w. j a v a2 s. c o m Pattern imgPattern = Pattern.compile("src=\"([^\"]+)\""); Matcher imgMatcher = imgPattern.matcher(codeToCopy); if (imgMatcher.find()) { list = new ArrayList<LocalizedTripleObject>(); list.add(new LocalizedString(imgMatcher.group(1))); fragment.put("http://xmlns.com/foaf/0.1/depiction", list); } GetMethod method2 = new GetMethod(url); ProxyHelper.executeMethod(httpClient, method2); String page = method2.getResponseBodyAsString(); Pattern namePattern = Pattern.compile("<h2 property=\"dc:title\">([^<]+)</h2>"); Matcher nameMatcher = namePattern.matcher(page); if (nameMatcher.find()) { list = new ArrayList<LocalizedTripleObject>(); list.add(new LocalizedString(nameMatcher.group(1))); fragment.put("http://purl.org/dc/elements/1.1/title", list); } List<LocalizedTripleObject> languages = extractLanguages(page, url); fragment.put("urn:cone:translation", languages); querier.delete("cclicences", url); querier.create("cclicences", url, fragment); } } else { System.out.println("Not found: " + licenceUrl); } } } } querier.release(); }
From source file:com.twentyn.patentScorer.ScoreMerger.java
public static void main(String[] args) throws Exception { System.out.println("Starting up..."); System.out.flush();/*w w w.ja v a2 s.co m*/ Options opts = new Options(); opts.addOption(Option.builder("h").longOpt("help").desc("Print this help message and exit").build()); opts.addOption(Option.builder("r").longOpt("results").required().hasArg() .desc("A directory of search results to read").build()); opts.addOption(Option.builder("s").longOpt("scores").required().hasArg() .desc("A directory of patent classification scores to read").build()); opts.addOption(Option.builder("o").longOpt("output").required().hasArg() .desc("The output file where results will be written.").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); } File scoresDirectory = new File(cmdLine.getOptionValue("scores")); if (cmdLine.getOptionValue("scores") == null || !scoresDirectory.isDirectory()) { LOGGER.error("Not a directory of score files: " + cmdLine.getOptionValue("scores")); } File resultsDirectory = new File(cmdLine.getOptionValue("results")); if (cmdLine.getOptionValue("results") == null || !resultsDirectory.isDirectory()) { LOGGER.error("Not a directory of results files: " + cmdLine.getOptionValue("results")); } FileWriter outputWriter = new FileWriter(cmdLine.getOptionValue("output")); ObjectMapper objectMapper = new ObjectMapper(); objectMapper.enable(SerializationFeature.INDENT_OUTPUT); objectMapper.setVisibility(PropertyAccessor.ALL, JsonAutoDetect.Visibility.ANY); FilenameFilter jsonFilter = new FilenameFilter() { public final Pattern JSON_PATTERN = Pattern.compile("\\.json$"); public boolean accept(File dir, String name) { return JSON_PATTERN.matcher(name).find(); } }; Map<String, PatentScorer.ClassificationResult> scores = new HashMap<>(); LOGGER.info("Reading scores from directory at " + scoresDirectory.getAbsolutePath()); for (File scoreFile : scoresDirectory.listFiles(jsonFilter)) { BufferedReader reader = new BufferedReader(new FileReader(scoreFile)); int count = 0; String line; while ((line = reader.readLine()) != null) { PatentScorer.ClassificationResult res = objectMapper.readValue(line, PatentScorer.ClassificationResult.class); scores.put(res.docId, res); count++; } LOGGER.info("Read " + count + " scores from " + scoreFile.getAbsolutePath()); } Map<String, List<DocumentSearch.SearchResult>> synonymsToResults = new HashMap<>(); Map<String, List<DocumentSearch.SearchResult>> inchisToResults = new HashMap<>(); LOGGER.info("Reading results from directory at " + resultsDirectory); // With help from http://stackoverflow.com/questions/6846244/jackson-and-generic-type-reference. JavaType resultsType = objectMapper.getTypeFactory().constructCollectionType(List.class, DocumentSearch.SearchResult.class); List<File> resultsFiles = Arrays.asList(resultsDirectory.listFiles(jsonFilter)); Collections.sort(resultsFiles, new Comparator<File>() { @Override public int compare(File o1, File o2) { return o1.getName().compareTo(o2.getName()); } }); for (File resultsFile : resultsFiles) { BufferedReader reader = new BufferedReader(new FileReader(resultsFile)); CharBuffer buffer = CharBuffer.allocate(Long.valueOf(resultsFile.length()).intValue()); int bytesRead = reader.read(buffer); LOGGER.info("Read " + bytesRead + " bytes from " + resultsFile.getName() + " (length is " + resultsFile.length() + ")"); List<DocumentSearch.SearchResult> results = objectMapper.readValue(new CharArrayReader(buffer.array()), resultsType); LOGGER.info("Read " + results.size() + " results from " + resultsFile.getAbsolutePath()); int count = 0; for (DocumentSearch.SearchResult sres : results) { for (DocumentSearch.ResultDocument resDoc : sres.getResults()) { String docId = resDoc.getDocId(); PatentScorer.ClassificationResult classificationResult = scores.get(docId); if (classificationResult == null) { LOGGER.warn("No classification result found for " + docId); } else { resDoc.setClassifierScore(classificationResult.getScore()); } } if (!synonymsToResults.containsKey(sres.getSynonym())) { synonymsToResults.put(sres.getSynonym(), new ArrayList<DocumentSearch.SearchResult>()); } synonymsToResults.get(sres.getSynonym()).add(sres); count++; if (count % 1000 == 0) { LOGGER.info("Processed " + count + " search result documents"); } } } Comparator<DocumentSearch.ResultDocument> resultDocumentComparator = new Comparator<DocumentSearch.ResultDocument>() { @Override public int compare(DocumentSearch.ResultDocument o1, DocumentSearch.ResultDocument o2) { int cmp = o2.getClassifierScore().compareTo(o1.getClassifierScore()); if (cmp != 0) { return cmp; } cmp = o2.getScore().compareTo(o1.getScore()); return cmp; } }; for (Map.Entry<String, List<DocumentSearch.SearchResult>> entry : synonymsToResults.entrySet()) { DocumentSearch.SearchResult newSearchRes = null; // Merge all result documents into a single search result. for (DocumentSearch.SearchResult sr : entry.getValue()) { if (newSearchRes == null) { newSearchRes = sr; } else { newSearchRes.getResults().addAll(sr.getResults()); } } if (newSearchRes == null || newSearchRes.getResults() == null) { LOGGER.error("Search results for " + entry.getKey() + " are null."); continue; } Collections.sort(newSearchRes.getResults(), resultDocumentComparator); if (!inchisToResults.containsKey(newSearchRes.getInchi())) { inchisToResults.put(newSearchRes.getInchi(), new ArrayList<DocumentSearch.SearchResult>()); } inchisToResults.get(newSearchRes.getInchi()).add(newSearchRes); } List<String> sortedKeys = new ArrayList<String>(inchisToResults.keySet()); Collections.sort(sortedKeys); List<GroupedInchiResults> orderedResults = new ArrayList<>(sortedKeys.size()); Comparator<DocumentSearch.SearchResult> synonymSorter = new Comparator<DocumentSearch.SearchResult>() { @Override public int compare(DocumentSearch.SearchResult o1, DocumentSearch.SearchResult o2) { return o1.getSynonym().compareTo(o2.getSynonym()); } }; for (String inchi : sortedKeys) { List<DocumentSearch.SearchResult> res = inchisToResults.get(inchi); Collections.sort(res, synonymSorter); orderedResults.add(new GroupedInchiResults(inchi, res)); } objectMapper.writerWithView(Object.class).writeValue(outputWriter, orderedResults); outputWriter.close(); }
From source file:AIR.Common.Web.PatternUrlRewriter.java
public static void main(String[] args) { try {/*from w w w. j a v a 2 s.c om*/ Pattern p = Pattern.compile( "file:///D:/DataFiles/BB_Files/tds2_airws_org/TDSCore_2013-2014/Bank-([^/]*)/Items/Item-(?<bankid>[^/]*)-(?<itemid>[^/]*)/([^/]*)"); Matcher m = p.matcher( "file:///D:/DataFiles/BB_Files/tds2_airws_org/TDSCore_2013-2014/Bank-179/Items/Item-195-6821/Item_22489_v5_rubric.xml"); URL url = new URL(m.replaceFirst( "file:///C:/AIROSE Trainer Deployments/tmp/Datafiles/Item-${bankid}-${itemid}/Item_${itemid}_v5_rubric.xml")); System.err.println(url); } catch (Exception exp) { exp.printStackTrace(); } }
From source file:com.github.brosander.java.performance.sampler.analysis.PerformanceSampleAnalyzer.java
public static void main(String[] args) { Options options = new Options(); options.addOption("i", FILE_OPT, true, "The file to analyze."); options.addOption("o", OUTPUT_FILE_OPT, true, "The output file (default json to stdout)."); options.addOption("p", RELEVANT_PATTERN_OPT, true, "Pattern(s) to include as roots in the output (default: " + DEFAULT_PATTERN + ")"); CommandLineParser parser = new DefaultParser(); try {/*from w w w. j av a2 s . co m*/ CommandLine commandLine = parser.parse(options, args); String file = commandLine.getOptionValue(FILE_OPT); if (StringUtils.isEmpty(file)) { printUsageAndExit("Must specify file", options, 1); } Pattern relevantPattern = Pattern .compile(commandLine.getOptionValue(RELEVANT_PATTERN_OPT, DEFAULT_PATTERN)); PerformanceSampleElement performanceSampleElement = relevantElements(relevantPattern, new ObjectMapper().readValue(new File(file), PerformanceSampleElement.class)); updateCounts(performanceSampleElement); String outputFile = commandLine.getOptionValue(OUTPUT_FILE_OPT); if (StringUtils.isEmpty(outputFile)) { new ObjectMapper().writerWithDefaultPrettyPrinter().writeValue(System.out, new OutputPerformanceSampleElement(performanceSampleElement)); } else { new ObjectMapper().writerWithDefaultPrettyPrinter().writeValue(new File(outputFile), new OutputPerformanceSampleElement(performanceSampleElement)); } } catch (Exception e) { e.printStackTrace(); printUsageAndExit(e.getMessage(), options, 2); } }
From source file:com.simple.sftpfetch.App.java
public static void main(String[] args) throws Exception { Security.addProvider(new org.bouncycastle.jce.provider.BouncyCastleProvider()); Options options = getOptions();//from w w w. j av a2 s .co m List<String> requiredProperties = asList("c"); CommandLineParser parser = new PosixParser(); try { CommandLine commandLine = parser.parse(options, args); if (commandLine.hasOption("h")) { printUsage(options); System.exit(0); } for (String opt : requiredProperties) { if (!commandLine.hasOption(opt)) { System.err.println("The option: " + opt + " is required."); printUsage(options); System.exit(1); } } Pattern pattern; if (commandLine.hasOption("p")) { pattern = Pattern.compile(commandLine.getOptionValue("p")); } else { pattern = MATCH_EVERYTHING; } String filename = commandLine.getOptionValue("c"); Properties properties = new Properties(); try { InputStream stream = new FileInputStream(new File(filename)); properties.load(stream); } catch (IOException ioe) { System.err.println("Unable to read properties from: " + filename); System.exit(2); } String routingKey = ""; if (commandLine.hasOption("r")) { routingKey = commandLine.getOptionValue("r"); } else if (properties.containsKey("rabbit.routingkey")) { routingKey = properties.getProperty("rabbit.routingkey"); } int daysToFetch; if (commandLine.hasOption("d")) { daysToFetch = Integer.valueOf(commandLine.getOptionValue("d")); } else { daysToFetch = Integer.valueOf(properties.getProperty(FETCH_DAYS)); } FileDecrypter decrypter = null; if (properties.containsKey("decryption.key.path")) { decrypter = new PGPFileDecrypter(new File(properties.getProperty("decryption.key.path"))); } else { decrypter = new NoopDecrypter(); } SftpClient sftpClient = new SftpClient(new JSch(), new SftpConnectionInfo(properties)); try { App app = new App(sftpClient, s3FromProperties(properties), new RabbitClient(new ConnectionFactory(), new RabbitConnectionInfo(properties)), decrypter, System.out); app.run(routingKey, daysToFetch, pattern, commandLine.hasOption("n"), commandLine.hasOption("o")); } finally { sftpClient.close(); } System.exit(0); } catch (UnrecognizedOptionException uoe) { System.err.println(uoe.getMessage()); printUsage(options); System.exit(10); } }