package compbio.cassandra; import java.io.BufferedReader; import java.io.IOException; import java.io.InputStreamReader; import java.net.HttpURLConnection; import java.net.MalformedURLException; import java.net.URL; import java.net.URLConnection; import java.text.ParseException; import java.text.SimpleDateFormat; import java.util.ArrayList; import java.util.Calendar; import java.util.Date; import java.util.List; import compbio.cassandra.JpredParser; public class JpredParserHTTP implements JpredParser { private CassandraCreate cc = new CassandraCreate(); private String dirprefix; JpredParserHTTP() { dirprefix = "http://www.compbio.dundee.ac.uk/www-jpred/results"; } JpredParserHTTP(String sourceurl) { dirprefix = sourceurl; } public void setSource(String newsourceprefix) { dirprefix = newsourceprefix; } public void Parsing(String source, int nDays) { Calendar cal = Calendar.getInstance(); cal.add(Calendar.DATE, -nDays); for (int i = 0; i < nDays; ++i) { cal.add(Calendar.DATE, 1); int month = cal.get(Calendar.MONTH) + 1; int year = cal.get(Calendar.YEAR); int day = cal.get(Calendar.DATE); String date = year + "/" + month + "/" + day; if (0 < ParsingForDate(source, date)) { cc.flushData(); } } } private int ParsingForDate(String input, String date) { int totalcount = 0; int countNoData = 0; int countUnclearFASTAid = 0; int countinsertions = 0; int countinserted = 0; int counAlignments = 0; int countStrange = 0; int njobs = 0; System.out.println("Inserting jobs for " + date); try { URL url = new URL(input); URLConnection conn = url.openConnection(); BufferedReader alljobs = new BufferedReader(new InputStreamReader(conn.getInputStream())); String line; while ((line = alljobs.readLine()) != null) { if (line.matches(date + "(.*)jp_[^\\s]+")) { String[] table = line.split("\\s+"); // Format of a record: // starttime endtime ip email jobid (directory) // 013/10/25:21:55:7 2013/10/25:21:59:13 201.239.98.172 unknown_email jp_J9HBCBT String id = table[table.length - 1]; totalcount++; if (!cc.CheckID(id)) { String datalink = dirprefix + "/" + id + "/" + id + ".concise.fasta"; URL urltable = new URL(datalink); HttpURLConnection httpConnection = (HttpURLConnection) urltable.openConnection(); int responsecode = httpConnection.getResponseCode(); if (199 < responsecode && responsecode < 300) { try { final FastaReader fr = new FastaReader(urltable.openStream()); final List seqs = new ArrayList(); String newprotein = ""; while (fr.hasNext()) { final FastaSequence fs = fr.next(); if (fs.getId().equals("QUERY") || fs.getId().equals(id)) newprotein = fs.getSequence().replaceAll("\n", ""); else seqs.add(fs); } if (newprotein.equals("")) { countUnclearFASTAid++; } else { SimpleDateFormat formatter = new SimpleDateFormat("yyyy/MM/dd"); String dateInString1 = table[0].substring(0, table[0].indexOf(":")); long dateWork1 = 0; try { Date dat1 = formatter.parse(dateInString1); dateWork1 = dat1.getTime(); } catch (ParseException e) { e.printStackTrace(); } cc.InsertData(dateWork1, table[0], table[1], table[2], id, "OK", "OK", newprotein, seqs); ++countinsertions; ++njobs; // flush every 50 insertions if (0 == countinsertions % 50) { cc.flushData(); njobs -= 50; } } } catch (IOException e) { e.printStackTrace(); } } else { countNoData++; } } else { ++countinserted; } } else { if (line.matches(date + "(.*)Sequence0/(.*)")) { ++counAlignments; } else { ++countStrange; } } } alljobs.close(); System.out.println("Total number of jobs = " + totalcount); System.out.println(" " + countinserted + " jobs inserted already"); System.out.println(" " + counAlignments + " jalview jobs"); System.out.println(" " + countStrange + " not analysed jobs"); System.out.println(" " + countNoData + " jobs without *.concise.fasta file"); System.out.println(" " + countUnclearFASTAid + " jobs with unclear FASTA protein id in *.concise.fasta"); System.out.println(" " + countinsertions + " new job insertions\n"); } catch (MalformedURLException e) { e.printStackTrace(); } catch (IOException e) { e.printStackTrace(); } return njobs; } }