--- /dev/null
+package compbio.cassandra;
+
+import java.io.BufferedReader;
+import java.io.File;
+import java.io.IOException;
+import java.io.InputStreamReader;
+import java.net.HttpURLConnection;
+import java.net.MalformedURLException;
+import java.io.FileInputStream;
+import java.text.ParseException;
+import java.text.SimpleDateFormat;
+import java.util.ArrayList;
+import java.util.Calendar;
+import java.util.Date;
+import java.util.List;
+
+public class JpredParserLocalFile {
+ private CassandraCreate cc = new CassandraCreate();
+ private String dirprefix;
+
+ public void setSource (String newsourceprefix) {
+ this.dirprefix = newsourceprefix;
+ }
+
+ JpredParserLocalFile() {
+ this.dirprefix = "/home/asherstnev/Projects/Java.projects/proteocache/data_stress_test/data.dat";
+ }
+
+ JpredParserLocalFile(String sourceurl) {
+ this.dirprefix = sourceurl;
+ }
+
+ 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;
+ ParsingForDate(source, date);
+ }
+ }
+
+ private void 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;
+
+ System.out.println("Inserting jobs for " + date);
+ try {
+ File file = new File(input);
+ BufferedReader alljobs = new BufferedReader(new InputStreamReader(new FileInputStream(file)));
+ String line;
+
+ while ((line = alljobs.readLine()) != null) {
+ if (line.matches(date + "(.*)jp_[^\\s]+")) {
+ String[] table = line.split("\\s+");
+ String id = table[table.length - 1];
+ totalcount++;
+ if (!cc.CheckID(id)) {
+ String confilename = dirprefix + "/" + id + "/" + id + ".concise";
+ File confile = new File(confilename);
+ if (confile.exists()) {
+ try {
+ final FastaReader fr = new FastaReader(confilename);
+ final List<FastaSequence> seqs = new ArrayList<FastaSequence>();
+ 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;
+ // flush every 100 insertions
+ if (0 == countinsertions % 100) {
+ cc.flushData();
+ }
+ }
+ } 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();
+ }
+ }
+}