package compbio.cassandra;

import java.io.BufferedReader;
import java.io.FileNotFoundException;
import java.io.IOException;
import java.io.InputStream;
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 java.util.regex.Matcher;
import java.util.regex.Pattern;

import compbio.cassandra.JpredParser;
import compbio.data.sequence.FastaReader;
import compbio.data.sequence.FastaSequence;
import compbio.engine.JpredJob;
import compbio.engine.ProteoCachePropertyHelperManager;
import compbio.engine.archive.Archive;
import compbio.engine.archive.ArchivedJob;
import compbio.util.PropertyHelper;
import compbio.util.Util;

public class JpredParserHTTP implements JpredParser {
	private CassandraWriter cw = new CassandraWriter();
	private static Archive archive;
	private String dirprefix;
	private List<FastaSequence> alignment;
	private List<FastaSequence> predictions;
	private int countNoData;
	private static boolean archiving = false;
	private static final PropertyHelper ph = ProteoCachePropertyHelperManager.getPropertyHelper();
	static SimpleDateFormat timeformatter = new SimpleDateFormat("yyyy/MM/dd:H:m:s");

	public JpredParserHTTP() {
		dirprefix = "http://www.compbio.dundee.ac.uk/www-jpred/results";
	}

	public JpredParserHTTP(String sourceurl) {
		dirprefix = sourceurl;
	}

	public void setSource(String newsourceprefix) {
		dirprefix = newsourceprefix;
	}

	private boolean initBooleanValue(String key) {
		assert key != null;
		String status = ph.getProperty(key);
		if (Util.isEmpty(status)) {
			return false;
		}
		return new Boolean(status.trim()).booleanValue();
	}

	public void Parsing(String source, int nDays) throws IOException {
		Calendar cal = Calendar.getInstance();
		cal.add(Calendar.DATE, -nDays);
		archiving = initBooleanValue("archive.enable");
		if (archiving) {
			archive = new Archive();
		}
		for (int i = 0; i < nDays; ++i) {
			cal.add(Calendar.DATE, 1);
			String date = cal.get(Calendar.YEAR) + "/" + (cal.get(Calendar.MONTH) + 1) + "/" + cal.get(Calendar.DATE);
			ParsingOneDay(source, date);
		}
	}

	/*
	 * The method parses the Jpred output concise file in the FASTA format If
	 * there is a record with ID = QUERY or jobid, this a "one protein" job
	 * otherwise this is an alignment job
	 */
	private String parsePredictions(final InputStream stream, String jobid) throws FileNotFoundException {
		final FastaReader fr = new FastaReader(stream);
		String protein = "";
		while (fr.hasNext()) {
			final FastaSequence fs = fr.next();
			String seqid = fs.getId();
			String seq = fs.getSequence().replaceAll("\n", "");
			if (seqid.equals("jnetpred") || seqid.equals("Lupas_21") || seqid.equals("Lupas_14") || seqid.equals("Lupas_28")
					|| seqid.equals("JNETSOL25") || seqid.equals("JNETSOL5") || seqid.equals("JNETSOL0") || seqid.equals("JNETCONF")
					|| seqid.equals("JNETHMM") || seqid.equals("JNETPSSM") || seqid.equals("JNETCONF")) {
				predictions.add(fs);
			} else {
				alignment.add(fs);
				if (seqid.equals("QUERY") || seqid.equals(jobid))
					protein = seq;
			}
		}
		return protein;
	}

	private String parseSeqFile(final InputStream stream, String jobid) throws FileNotFoundException {
		final FastaReader fr = new FastaReader(stream);
		String protein = "";
		final FastaSequence fs = fr.next();
		protein = fs.getSequence().replaceAll("\n", "");
		if (fr.hasNext()) {
			// this is an aligment job...
			return "alignment";
		}
		return protein;
	}

	private String parseLogFile(final InputStream stream, JpredJob job) throws IOException {
		String out = "";
		BufferedReader buffer = new BufferedReader(new InputStreamReader(stream));
		String line;
		if (null != (out = buffer.readLine()) && (out.contains("version"))) {
			Matcher matcher = Pattern.compile("((\\d|\\.)+)").matcher(out);
			if (matcher.find())
				job.setProgramVersion(matcher.group(0));
		}
		while (null != (line = buffer.readLine())) {
			out += line;		
		}
		return out;
	}

	private int analyseJob(String[] jobinfo) throws IOException {
		alignment = new ArrayList<FastaSequence>();
		predictions = new ArrayList<FastaSequence>();
		boolean running = true;
		boolean ConcisefileExists = false;
		boolean LogfileExists = false;
		JpredJob job = new JpredJob(jobinfo[jobinfo.length - 1], jobinfo[0], jobinfo[1]);
		job.setIP(jobinfo[2]);
		job.setProgramName("Jpred");
		Date currDate = new Date();
		String maindir = dirprefix + "/" + job.getJobID() + "/";

		try {
			Date finishTime = timeformatter.parse(jobinfo[1]);
			long delay = currDate.getTime() / 1000 - finishTime.getTime() / 1000;
			if (delay < 120) return 0;
		} catch (ParseException e) {
			e.printStackTrace();
		}

		try {
			URL dirurl = new URL(maindir);
			HttpURLConnection httpConnection_dirurl = (HttpURLConnection) dirurl.openConnection();
			if (httpConnection_dirurl.getResponseCode() < 199 || 300 <= httpConnection_dirurl.getResponseCode()) {
				return 0;
			}
			URL conciseurl = new URL(maindir + job.getJobID() + ".concise.fasta");
			URL logurl = new URL(maindir + "LOG");
			HttpURLConnection httpConnection_conciseurl = (HttpURLConnection) conciseurl.openConnection();
			HttpURLConnection httpConnection_logurl = (HttpURLConnection) logurl.openConnection();
			if (199 < httpConnection_conciseurl.getResponseCode() && httpConnection_conciseurl.getResponseCode() < 300) {
				ConcisefileExists = true;
				running = false;
				try {				
					job.setProtein(parsePredictions(conciseurl.openStream(), job.getJobID()));
				} catch (IOException e) {
					e.printStackTrace();
				}
			} else {
				// The job still can be running of failed...
				++countNoData;
			}
			if (199 < httpConnection_logurl.getResponseCode() && httpConnection_logurl.getResponseCode() < 300) {
				LogfileExists = true;
				job.setLog(parseLogFile(logurl.openStream(), job));
			} else {
				// The job has not been started at all...
				System.out.println ("WARNING! Job " + job.getJobID() + " has status FAIL/STOPPED");
				job.setExecutionStatus("FAIL");
				job.setFinalStatus("STOPPED");
				running = false;
			}
			if (job.getLog().matches("(.*)TIMEOUT\\syour\\sjob\\stimed\\sout(.*)")) {
				// blast job was too long (more than 3600 secs by default)...
				job.setExecutionStatus("FAIL");
				job.setFinalStatus("TIMEDOUT");
				running = false;
			} else if (job.getLog().matches("(.*)Jpred\\serror:\\sDied\\sat(.*)")) {
				// an internal Jpred error...
				job.setExecutionStatus("FAIL");
				job.setFinalStatus("JPREDERROR");
				running = false;
			} else if ((currDate.getTime() - job.getEndTime()) / 1000 > 3601 && LogfileExists && !ConcisefileExists) {
				// the job was stopped with unknown reason...
				job.setExecutionStatus("FAIL");
				job.setFinalStatus("STOPPED");
				running = false;
			}

			httpConnection_conciseurl.disconnect();
			httpConnection_logurl.disconnect();
		} catch (MalformedURLException e) {
			e.printStackTrace();
		}

		if (!running) {
			// logging the job
			job.setAlignment(alignment);
			job.setPredictions(predictions);
			if (job.getExecutionStatus().equals("FAIL")) {
				URL sequrl = new URL(maindir + job.getJobID() + ".seq");
				HttpURLConnection httpConnection_sequrl = (HttpURLConnection) sequrl.openConnection();
				if (199 < httpConnection_sequrl.getResponseCode() && httpConnection_sequrl.getResponseCode() < 300) {
					try {
						job.setProtein(parseSeqFile(sequrl.openStream(), job.getJobID()));
					} catch (IOException e) {
						e.printStackTrace();
					}
				}
			}
			cw.FormQueryTables(job);

			// archiving the job
			if (archiving) {
				ArchivedJob ajob = new ArchivedJob(job.getJobID());
				String arlink = archive.createJob(job.getJobID());
				if (job.getFinalStatus().equals("OK")) {
					ajob.setArchivePath(arlink);
					ajob.copyArchiveFromWeb(maindir + job.getJobID() + ".tar.gz");
					cw.ArchiveData(job, arlink);
				} else {
					cw.ArchiveData(job, "undefined");
				}
			}
			return 1;
		}

		return 0;
	}

	private void ParsingOneDay(String input, String date) {
		int totalcount = 0;
		int countinsertions = 0;
		int countinserted = 0;
		int countNotanalyzed = 0;
		countNoData = 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]+")) {
					totalcount++;
					String[] job = line.split("\\s+");
					String jobid = job[job.length - 1];
					if (cw.JobisNotInsterted(jobid)) {
						countinsertions += analyseJob(job);
					} else {
						++countinserted;
					}
				} else {
					++countNotanalyzed;
				}
			}
			alljobs.close();
			System.out.println("Total number of jobs = " + totalcount);
			System.out.println("   " + countinserted + " jobs inserted already");
			System.out.println("   " + countNotanalyzed + " not analysed jobs");
			System.out.println("   " + countNoData + " jobs without *.concise.fasta file (RUNNING or FAILED)");
			System.out.println("   " + countinsertions + " new job insertions\n");
		} catch (MalformedURLException e) {
			e.printStackTrace();
		} catch (IOException e) {
			e.printStackTrace();
		}
		;
	}
};