X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fio%2FAlignFile.java;h=5760fbe385781550f72b6bace208a6f9da3f2ab5;hb=37de9310bec3501cbc6381e0c3dcb282fcaad812;hp=cfd37b03379be1760443b1a7d1e75cee71f2230a;hpb=cabc3cd4652a56ce1f8b2b6ff35ad905e61127b1;p=jalview.git diff --git a/src/jalview/io/AlignFile.java b/src/jalview/io/AlignFile.java index cfd37b0..5760fbe 100755 --- a/src/jalview/io/AlignFile.java +++ b/src/jalview/io/AlignFile.java @@ -1,41 +1,39 @@ /* - * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8) - * Copyright (C) 2012 J Procter, AM Waterhouse, LM Lui, J Engelhardt, G Barton, M Clamp, S Searle + * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$) + * Copyright (C) $$Year-Rel$$ The Jalview Authors * * This file is part of Jalview. * * Jalview is free software: you can redistribute it and/or * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version. + * as published by the Free Software Foundation, either version 3 + * of the License, or (at your option) any later version. * * Jalview is distributed in the hope that it will be useful, but * WITHOUT ANY WARRANTY; without even the implied warranty * of MERCHANTABILITY or FITNESS FOR A PARTICULAR * PURPOSE. See the GNU General Public License for more details. * - * You should have received a copy of the GNU General Public License along with Jalview. If not, see . + * You should have received a copy of the GNU General Public License + * along with Jalview. If not, see . + * The Jalview Authors are detailed in the 'AUTHORS' file. */ package jalview.io; -import jalview.datamodel.Alignment; import jalview.datamodel.AlignmentAnnotation; +import jalview.datamodel.AlignmentI; import jalview.datamodel.Sequence; +import jalview.datamodel.SequenceGroup; import jalview.datamodel.SequenceI; +import jalview.util.MessageManager; import java.io.IOException; +import java.util.ArrayList; import java.util.Enumeration; import java.util.Hashtable; +import java.util.List; import java.util.Vector; -import javax.xml.parsers.ParserConfigurationException; - -import org.xml.sax.SAXException; - -import fr.orsay.lri.varna.exceptions.ExceptionFileFormatOrSyntax; -import fr.orsay.lri.varna.exceptions.ExceptionLoadingFailed; -import fr.orsay.lri.varna.exceptions.ExceptionPermissionDenied; -import fr.orsay.lri.varna.exceptions.ExceptionUnmatchedClosingParentheses; - /** * DOCUMENT ME! * @@ -49,14 +47,20 @@ public abstract class AlignFile extends FileParse int maxLength = 0; /** - * Sequences to be added to form a new alignment. + * Sequences to be added to form a new alignment. TODO: remove vector in this + * class */ protected Vector seqs; /** * annotation to be added to generated alignment object */ - protected Vector annotations; + protected Vector annotations; + + /** + * SequenceGroups to be added to the alignment object + */ + protected List seqGroups; /** * Properties to be added to generated alignment object @@ -69,39 +73,52 @@ public abstract class AlignFile extends FileParse boolean jvSuffix = true; + private boolean parseCalled; + /** * Creates a new AlignFile object. */ public AlignFile() { - // Shouldn't we init data structures (JBPNote: not sure - initData is for initialising the structures used for reading from a datasource, and the bare constructor hasn't got any datasource) - initData(); + // Shouldn't we init data structures (JBPNote: not sure - initData is for + // initialising the structures used for reading from a datasource, and the + // bare constructor hasn't got any datasource) + initData(); } /** * Constructor which parses the data from a file of some specified type. * - * @param inFile - * Filename to read from. + * @param dataObject + * Filename, URL or Pasted String to read from. + * @param type + * What type of file to read from (File, URL, Pasted String) + */ + public AlignFile(String dataObject, String type) throws IOException + { + this(true, dataObject, type); + } + + /** + * Constructor which (optionally delays) parsing of data from a file of some + * specified type. + * + * @param parseImmediately + * if false, need to call 'doParse()' to begin parsing data + * @param dataObject + * Filename, URL or Pasted String to read from. * @param type * What type of file to read from (File, URL) - * @throws SAXException - * @throws ParserConfigurationException - * @throws ExceptionFileFormatOrSyntax - * @throws ExceptionLoadingFailed - * @throws ExceptionPermissionDenied - * @throws InterruptedException - * @throws ExceptionUnmatchedClosingParentheses + * @throws IOException */ - public AlignFile(String inFile, String type) throws IOException, ExceptionFileFormatOrSyntax, ParserConfigurationException, SAXException, ExceptionPermissionDenied, ExceptionLoadingFailed, InterruptedException, ExceptionUnmatchedClosingParentheses + public AlignFile(boolean parseImmediately, String dataObject, String type) + throws IOException { - super(inFile, type); + super(dataObject, type); initData(); - parse(); - // sets the index of each sequence in the alignment - for (int i = 0, c = seqs.size(); i < c; i++) + if (parseImmediately) { - seqs.get(i).setIndex(i); + doParse(); } } @@ -111,18 +128,45 @@ public abstract class AlignFile extends FileParse * * @param source * @throws IOException - * @throws SAXException - * @throws ParserConfigurationException - * @throws ExceptionFileFormatOrSyntax - * @throws ExceptionLoadingFailed - * @throws ExceptionPermissionDenied - * @throws InterruptedException - * @throws ExceptionUnmatchedClosingParentheses */ - public AlignFile(FileParse source) throws IOException, ExceptionFileFormatOrSyntax, ParserConfigurationException, SAXException, ExceptionPermissionDenied, ExceptionLoadingFailed, InterruptedException, ExceptionUnmatchedClosingParentheses + public AlignFile(FileParse source) throws IOException + { + this(true, source); + } + + /** + * Construct a new parser to read from the position where some other parsing + * process left + * + * @param parseImmediately + * if false, need to call 'doParse()' to begin parsing data + * @param source + */ + public AlignFile(boolean parseImmediately, FileParse source) + throws IOException { super(source); initData(); + if (parseImmediately) + { + doParse(); + } + } + + /** + * called if parsing was delayed till after parser was constructed + * + * @throws IOException + */ + public void doParse() throws IOException + { + if (parseCalled) + { + throw new IOException( + "Implementation error: Parser called twice for same data.\n" + + "Need to call initData() again before parsing can be reattempted."); + } + parseCalled = true; parse(); // sets the index of each sequence in the alignment for (int i = 0, c = seqs.size(); i < c; i++) @@ -139,6 +183,11 @@ public abstract class AlignFile extends FileParse return seqs; } + public List getSeqGroups() + { + return seqGroups; + } + /** * Return the Sequences in the seqs Vector as an array of Sequences */ @@ -148,7 +197,7 @@ public abstract class AlignFile extends FileParse for (int i = 0; i < seqs.size(); i++) { - s[i] = (SequenceI) seqs.elementAt(i); + s[i] = seqs.elementAt(i); } return s; @@ -160,7 +209,7 @@ public abstract class AlignFile extends FileParse * * @param al */ - public void addAnnotations(Alignment al) + public void addAnnotations(AlignmentI al) { addProperties(al); for (int i = 0; i < annotations.size(); i++) @@ -172,8 +221,7 @@ public abstract class AlignFile extends FileParse * Rna.GetBasePairsFromAlignmentAnnotation(annotations.elementAt(i)); * Rna.HelixMap(pairArray); */ - AlignmentAnnotation an = (AlignmentAnnotation) annotations - .elementAt(i); + AlignmentAnnotation an = annotations.elementAt(i); an.validateRangeAndDisplay(); al.addAnnotation(an); } @@ -181,13 +229,24 @@ public abstract class AlignFile extends FileParse } /** + * register sequence groups on the alignment for **output** + * + * @param al + */ + public void addSeqGroups(AlignmentI al) + { + this.seqGroups = al.getGroups(); + + } + + /** * Add any additional information extracted from the file to the alignment * properties. * * @note implicitly called by addAnnotations() * @param al */ - public void addProperties(Alignment al) + public void addProperties(AlignmentI al) { if (properties != null && properties.size() > 0) { @@ -215,7 +274,8 @@ public abstract class AlignFile extends FileParse if (key == null) { throw new Error( - "Implementation error: Cannot have null alignment property key."); + MessageManager + .getString("error.implementation_error_cannot_have_null_alignment")); } if (value == null) { @@ -242,8 +302,10 @@ public abstract class AlignFile extends FileParse */ protected void initData() { - seqs = new Vector(); - annotations = new Vector(); + seqs = new Vector(); + annotations = new Vector(); + seqGroups = new ArrayList(); + parseCalled = false; } /** @@ -254,7 +316,7 @@ public abstract class AlignFile extends FileParse */ protected void setSeqs(SequenceI[] s) { - seqs = new Vector(); + seqs = new Vector(); for (int i = 0; i < s.length; i++) { @@ -264,15 +326,8 @@ public abstract class AlignFile extends FileParse /** * This method must be implemented to parse the contents of the file. - * @throws ExceptionFileFormatOrSyntax - * @throws SAXException - * @throws ParserConfigurationException - * @throws ExceptionLoadingFailed - * @throws ExceptionPermissionDenied - * @throws InterruptedException - * @throws ExceptionUnmatchedClosingParentheses */ - public abstract void parse() throws IOException, ExceptionFileFormatOrSyntax, ParserConfigurationException, SAXException, ExceptionPermissionDenied, ExceptionLoadingFailed, InterruptedException, ExceptionUnmatchedClosingParentheses; + public abstract void parse() throws IOException; /** * Print out in alignment file format the Sequences in the seqs Vector. @@ -297,7 +352,15 @@ public abstract class AlignFile extends FileParse if (space > -1) { seq = new Sequence(id.substring(0, space), ""); - seq.setDescription(id.substring(space + 1)); + String desc = id.substring(space + 1); + seq.setDescription(desc); + + /* + * it is tempting to parse Ensembl style gene description e.g. + * chromosome:GRCh38:7:140696688:140721955:1 and set the + * start position of the sequence, but this causes much confusion + * for reverse strand feature locations + */ } else { @@ -321,25 +384,29 @@ public abstract class AlignFile extends FileParse /** * vector of String[] treeName, newickString pairs */ - Vector newickStrings = null; + Vector newickStrings = null; protected void addNewickTree(String treeName, String newickString) { if (newickStrings == null) { - newickStrings = new Vector(); + newickStrings = new Vector(); } - newickStrings.addElement(new String[] - { treeName, newickString }); + newickStrings.addElement(new String[] { treeName, newickString }); } protected int getTreeCount() { - if (newickStrings == null) + return newickStrings == null ? 0 : newickStrings.size(); + } + + public void addGroups(AlignmentI al) + { + + for (SequenceGroup sg : getSeqGroups()) { - return 0; + al.addGroup(sg); } - return newickStrings.size(); } }