1 package compbio.cassandra;
3 import java.io.BufferedReader;
4 import java.io.IOException;
5 import java.io.InputStreamReader;
6 import java.net.HttpURLConnection;
7 import java.net.MalformedURLException;
9 import java.net.URLConnection;
10 import java.text.ParseException;
11 import java.text.SimpleDateFormat;
12 import java.util.ArrayList;
13 import java.util.Calendar;
14 import java.util.Date;
15 import java.util.List;
17 import compbio.cassandra.JpredParser;
19 public class JpredParserHTTP implements JpredParser {
20 private CassandraCreate cc = new CassandraCreate();
21 private String dirprefix;
24 dirprefix = "http://www.compbio.dundee.ac.uk/www-jpred/results";
27 JpredParserHTTP(String sourceurl) {
28 dirprefix = sourceurl;
31 public void setSource(String newsourceprefix) {
32 dirprefix = newsourceprefix;
35 public void Parsing(String source, int nDays) {
36 Calendar cal = Calendar.getInstance();
37 cal.add(Calendar.DATE, -nDays);
38 for (int i = 0; i < nDays; ++i) {
39 cal.add(Calendar.DATE, 1);
40 int month = cal.get(Calendar.MONTH) + 1;
41 int year = cal.get(Calendar.YEAR);
42 int day = cal.get(Calendar.DATE);
43 String date = year + "/" + month + "/" + day;
44 ParsingForDate(source, date);
48 private void ParsingForDate(String input, String date) {
51 int countUnclearFASTAid = 0;
52 int countinsertions = 0;
53 int countinserted = 0;
54 int counAlignments = 0;
57 System.out.println("Inserting jobs for " + date);
59 URL url = new URL(input);
60 URLConnection conn = url.openConnection();
61 BufferedReader alljobs = new BufferedReader(new InputStreamReader(conn.getInputStream()));
64 while ((line = alljobs.readLine()) != null) {
65 if (line.matches(date + "(.*)jp_[^\\s]+")) {
66 String[] table = line.split("\\s+");
67 // Format of a record:
68 // starttime endtime ip email jobid (directory)
69 // 013/10/25:21:55:7 2013/10/25:21:59:13 201.239.98.172 unknown_email jp_J9HBCBT
70 String id = table[table.length - 1];
72 if (!cc.CheckID(id)) {
73 String datalink = dirprefix + "/" + id + "/" + id + ".concise.fasta";
74 URL urltable = new URL(datalink);
75 HttpURLConnection httpConnection = (HttpURLConnection) urltable.openConnection();
76 int responsecode = httpConnection.getResponseCode();
77 if (199 < responsecode && responsecode < 300) {
79 final FastaReader fr = new FastaReader(urltable.openStream());
80 final List<FastaSequence> seqs = new ArrayList<FastaSequence>();
81 String newprotein = "";
82 while (fr.hasNext()) {
83 final FastaSequence fs = fr.next();
84 if (fs.getId().equals("QUERY") || fs.getId().equals(id))
85 newprotein = fs.getSequence().replaceAll("\n", "");
89 if (newprotein.equals("")) {
90 countUnclearFASTAid++;
92 SimpleDateFormat formatter = new SimpleDateFormat("yyyy/MM/dd");
93 String dateInString1 = table[0].substring(0, table[0].indexOf(":"));
96 Date dat1 = formatter.parse(dateInString1);
97 dateWork1 = dat1.getTime();
98 } catch (ParseException e) {
101 cc.InsertData(dateWork1, table[0], table[1], table[2], id, "OK", "OK", newprotein, seqs);
103 // flush every 100 insertions
104 if (0 == countinsertions % 100) {
108 } catch (IOException e) {
118 if (line.matches(date + "(.*)Sequence0/(.*)")) {
126 System.out.println("Total number of jobs = " + totalcount);
127 System.out.println(" " + countinserted + " jobs inserted already");
128 System.out.println(" " + counAlignments + " jalview jobs");
129 System.out.println(" " + countStrange + " not analysed jobs");
130 System.out.println(" " + countNoData + " jobs without *.concise.fasta file");
131 System.out.println(" " + countUnclearFASTAid + " jobs with unclear FASTA protein id in *.concise.fasta");
132 System.out.println(" " + countinsertions + " new job insertions\n");
133 } catch (MalformedURLException e) {
135 } catch (IOException e) {