Examples of htsjdk.tribble.readers.AsciiLineReader

htsjdk.tribble.readers.AsciiLineReader


        if (headerLines != null) {
            String lines = StringUtils.join(headerLines, "\n");
            byte[] bytes = lines.getBytes();
            InputStream is = new ByteArrayInputStream(bytes);
            LineIterator reader = new LineIteratorImpl(new AsciiLineReader(is));
            try {
                codec.readHeader(reader);
            } catch (IOException e) {
                log.error(e.getMessage(), e);
            }

View Full Code Here

    }




    public static AsciiLineReader openAsciiReader(ResourceLocator locator) throws IOException {
        InputStream stream = openInputStreamGZ(locator);
        return new AsciiLineReader(stream);


    }

View Full Code Here

        }
    }


    public static int estimateLineCount(String path) {


        AsciiLineReader reader = null;
        try {
            final int defaultLength = 100000;
            long fileLength = getContentLength(path);
            if (fileLength <= 0) {
                return defaultLength;
            }


            reader = openAsciiReader(new ResourceLocator(path));
            String nextLine;
            int lines = 0;
            // Skip the first 10 lines (headers, etc)
            int nSkip = 10;
            while (nSkip-- > 0 && reader.readLine() != null) {
            }
            long startPos = reader.getPosition();


            while ((nextLine = reader.readLine()) != null & lines < 100) {
                lines++;
            }


            if (lines == 0) {
                return defaultLength;
            }


            double bytesPerLine = (double) ((reader.getPosition() - startPos) / lines);
            int nLines = (int) (fileLength / bytesPerLine);
            return nLines;


        } catch (Exception e) {
            log.error("Error estimating line count", e);
            return 1000;
        } finally {
            try {
                reader.close();
            } catch (Exception e) {
                // Ignore errors closing reader
            }
        }

View Full Code Here


    /*
     */


    public static boolean parsableMAGE_TAB(ResourceLocator file) throws IOException {
        AsciiLineReader reader = null;
        try {
            reader = ParsingUtils.openAsciiReader(file);
            String nextLine = null;


            //skip first row
            reader.readLine();


            //check second row for MAGE_TAB identifiers
            if ((nextLine = reader.readLine()) != null && (nextLine.contains("Reporter REF") ||
                    nextLine.contains("Composite Element REF") || nextLine.contains("Term Source REF") ||
                    nextLine.contains("CompositeElement REF") || nextLine.contains("TermSource REF") ||
                    nextLine.contains("Coordinates REF"))) {
                return true;
            }
        } finally {
            if (reader != null) {
                reader.close();
            }
        }


        return false;
    }

View Full Code Here


        List<D> featuresList = new ArrayList<D>();
        String line;
        D feat;


        LineIterator lrw = new LineIteratorImpl(new AsciiLineReader(is));
        lineFeatureDecoder.readActualHeader(lrw);


        while (lrw.hasNext()) {
            line = lrw.next();
            try {

View Full Code Here


    /*
     */


    public static boolean parsableMAGE_TAB(ResourceLocator file) throws IOException {
        AsciiLineReader reader = null;
        try {
            reader = ParsingUtils.openAsciiReader(file);
            String nextLine = null;


            //skip first row
            reader.readLine();


            //check second row for MAGE_TAB identifiers
            if ((nextLine = reader.readLine()) != null && (nextLine.contains("Reporter REF") || nextLine.contains("Composite Element REF") || nextLine.contains("Term Source REF") || nextLine.contains("CompositeElement REF") || nextLine.contains("TermSource REF") || nextLine.contains("Coordinates REF"))) {
                int count = 0;
                // check if this mage_tab data matrix can be parsed by this class
                while ((nextLine = reader.readLine()) != null && count < 5) {
                    nextLine = nextLine.trim();
                    if (nextLine.startsWith("SNP_A") || nextLine.startsWith("CN_")) {
                        return true;
                    }


                    count++;
                }
                return false;
            }
        } finally {
            if (reader != null) {
                reader.close();
            }
        }


        return false;
    }

View Full Code Here


        float dataMin = 0;
        float dataMax = 0;


        InputStream is = null;
        AsciiLineReader reader = null;
        String nextLine = null;
        ChromosomeSummary chrSummary = null;
        List<ChromosomeSummary> chrSummaries = new ArrayList();
        String[] headings = null;
        WholeGenomeData wgData = null;
        int nRows = 0;


        int headerRows = 0;
        int count = 0;


        boolean logNormalized;
        try {


            int skipColumns = hasCalls ? 2 : 1;


            // BufferedReader reader = ParsingUtils.openBufferedReader(dataResourceLocator);
            is = ParsingUtils.openInputStreamGZ(dataResourceLocator);
            reader = new AsciiLineReader(is);


            // Infer datatype from extension.  This can be overriden in the
            // comment section
            if (isCopyNumberFileExt(dataResourceLocator.getPath())) {
                dataset.setTrackType(TrackType.COPY_NUMBER);
                dataset.getTrackProperties().setWindowingFunction(WindowFunction.mean);
            } else if (isLOHFileExt(dataResourceLocator.getPath())) {
                dataset.setTrackType(TrackType.LOH);
                dataset.getTrackProperties().setWindowingFunction(WindowFunction.mean);
            } else {
                dataset.getTrackProperties().setWindowingFunction(WindowFunction.mean);
            }


            // Parse comments and directives, if any
            nextLine = reader.readLine();
            while (nextLine.startsWith("#") || (nextLine.trim().length() == 0)) {
                headerRows++;


                if (nextLine.length() > 0) {
                    parseDirective(nextLine, dataset);
                }
                nextLine = reader.readLine();
            }


            if (chrColumn < 0) {
                setColumnDefaults();
            }




            // Parse column headings
            String[] data = nextLine.trim().split("\t");


            // Set last data column
            if (lastDataColumn < 0) {
                lastDataColumn = data.length - 1;
            }


            headings = getHeadings(data, skipColumns);


            dataset.setDataHeadings(headings);


            // Infer if the data is logNormalized by looking for negative data values.
            // Assume it is not until proven otherwise
            logNormalized = false;


            wgData = new WholeGenomeData(headings);


            int chrRowCount = 0;


            // Update
            int updateCount = 5000;
            long lastPosition = 0;
            while ((nextLine = reader.readLine()) != null) {


                if (igv != null && ++count % updateCount == 0) {
                    igv.setStatusBarMessage("Loaded: " + count + " / " + estLineCount + " (est)");
                }
                // Distance since last sample


                String[] tokens = Globals.tabPattern.split(nextLine, -1);
                int nTokens = tokens.length;
                if (nTokens > 0) {
                    String thisChr = genome.getChromosomeAlias(tokens[chrColumn]);
                    if (chrSummary == null || !thisChr.equals(chrSummary.getName())) {
                        // Update whole genome and previous chromosome summary, unless this is
                        // the first chromosome
                        if (chrSummary != null) {
                            updateWholeGenome(chrSummary.getName(), dataset, headings, wgData);
                            chrSummary.setNDataPoints(nRows);
                        }


                        // Shart the next chromosome
                        chrSummary = new ChromosomeSummary(thisChr, lastPosition);
                        chrSummaries.add(chrSummary);
                        nRows = 0;
                        wgData = new WholeGenomeData(headings);
                        chrRowCount = 0;


                    }
                    lastPosition = reader.getPosition();


                    int location = -1;
                    try {
                        location = ParsingUtils.parseInt(tokens[startColumn]) - startBase;

View Full Code Here

            // Get an estimate of the number of snps (rows).  THIS IS ONLY AN ESTIMATE
            int nRowsEst = chrSummary.getNDataPts();


            SeekableStream is = IGVSeekableStreamFactory.getInstance().getStreamFor(dataResourceLocator.getPath());
            is.seek(chrSummary.getStartPosition());
            AsciiLineReader reader = new AsciiLineReader(is);




            // Create containers to hold data
            IntArrayList startLocations = new IntArrayList(nRowsEst);
            IntArrayList endLocations = (hasEndLocations ? new IntArrayList(nRowsEst) : null);
            List<String> probes = new ArrayList(nRowsEst);


            Map<String, FloatArrayList> dataMap = new HashMap();
            for (String h : dataHeaders) {
                dataMap.put(h, new FloatArrayList(nRowsEst));
            }


            // Begin loop through rows
            String chromosome = chrSummary.getName();
            boolean chromosomeStarted = false;
            String nextLine = reader.readLine();


            while ((nextLine != null) && (nextLine.trim().length() > 0)) {


                if (!nextLine.startsWith("#")) {
                    try {
                        String[] tokens = Globals.tabPattern.split(nextLine, -1);


                        String thisChromosome = genome.getChromosomeAlias(tokens[chrColumn].trim());
                        if (thisChromosome.equals(chromosome)) {
                            chromosomeStarted = true;


                            // chromosomeData.setMarkerId(nRows, tokens[0]);


                            // The probe.  A new string is created to prevent holding on to the entire row through a substring reference
                            String probe = new String(tokens[probeColumn]);
                            probes.add(probe);


                            int start = ParsingUtils.parseInt(tokens[startColumn].trim()) - startBase;
                            if (hasEndLocations) {
                                endLocations.add(ParsingUtils.parseInt(tokens[endColumn].trim()));
                            }


                            startLocations.add(start);


                            if(tokens.length <= firstDataColumn + (dataHeaders.length - 1)*skipColumns){
                                String msg = "Line has too few data columns: " + nextLine;
                                log.error(msg);
                                throw new RuntimeException(msg);
                            }


                            for (int idx = 0; idx < dataHeaders.length; idx++) {
                                int i = firstDataColumn + idx * skipColumns;
                                float copyNo = i <= lastDataColumn ? readFloat(tokens[i]) : Float.NaN;
                                String heading = dataHeaders[idx];
                                dataMap.get(heading).add(copyNo);
                            }




                        } else if (chromosomeStarted) {
                            break;
                        }


                    } catch (NumberFormatException numberFormatException) {


                        // Skip line
                        log.info("Skipping line (NumberFormatException) " + nextLine);
                    }
                }


                nextLine = reader.readLine();
            }


            // Loop complete
            ChromosomeData cd = new ChromosomeData(chrSummary.getName());
            cd.setProbes(probes.toArray(new String[]{}));

View Full Code Here

        }
    }


    static List<String> getExpressionProbes() {
        String urlString = "http://www.broadinstitute.org/igv/resources/probes/affy/affy_human_mappings.txt.gz";
        AsciiLineReader bufReader = null;
        List<String> probes = new ArrayList(60000);
        try {
            InputStream is = null;


            if (HttpUtils.isRemoteURL(urlString)) {
                URL url = new URL(urlString);
                is = HttpUtils.getInstance().openConnectionStream(url);
            } else {
                is = new FileInputStream(urlString);
            }
            if (urlString.endsWith("gz")) {
                is = new GZIPInputStream(is);
            }
            bufReader = new AsciiLineReader(is);


            String nextLine = "";
            while ((nextLine = bufReader.readLine()) != null) {
                String[] tokens = nextLine.split("\t");
                probes.add(tokens[0]);
            }


            return probes;


        } catch (Exception e) {
            e.printStackTrace();
            return null;
        } finally {
            if (bufReader != null) {
                bufReader.close();
            }
        }


    }

View Full Code Here


        if (birdsuite) {
            dataset.setTrackType(TrackType.CNV);
        }


        AsciiLineReader reader = null;
        String nextLine = null;
        int lineNumber = 0;


        IParser<String[], Integer> parser = IParserFactory.getIndexParser(new String[0]);


        try {
            reader = ParsingUtils.openAsciiReader(locator);
            lineNumber = readHeader(reader);


            while ((nextLine = reader.readLine()) != null && (nextLine.trim().length() > 0)) {
                lineNumber++;
                String[] tokens = Globals.tabPattern.split(nextLine, -1);
                parseLine(parser, tokens);
            }


        } catch (IOException e) {
            if (nextLine != null && lineNumber != 0) {
                throw new ParserException(e.getMessage(), e, lineNumber, nextLine);
            } else {
                throw new RuntimeException(e);
            }
        } finally {
            if (reader != null) {
                reader.close();
            }
        }


        dataset.sortLists();
        return dataset;

View Full Code Here

0 1 2 3 4

TOP

Related Classes of htsjdk.tribble.readers.AsciiLineReader

org.broad.igv.cli_plugin.AsciiDecoder

org.broad.igv.data.expression.ExpressionFileParser

org.broad.igv.data.expression.ProbeToLocusMap

org.broad.igv.data.IGVDatasetParser

org.broad.igv.data.rnai.RNAIGCTDatasetParser

org.broad.igv.data.rnai.RNAIHairpinParser

org.broad.igv.data.seg.SegmentFileParser

org.broad.igv.data.WiggleParser

org.broad.igv.dev.db.SQLCodecSource

org.broad.igv.dev.SegmentedReader

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.