X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fws%2Fdbsources%2FEmblXmlSource.java;h=ba46a6c3ad5f44c053bbef5386a7ac05445a697d;hb=d043ce47fc710d3eb2629ba926a8a7417bd67d8c;hp=a420d9f42ad29e7e584b9da210392683db2e684b;hpb=3b3c59cfa50e942d2fa5b367b7117cade9459ce7;p=jalview.git diff --git a/src/jalview/ws/dbsources/EmblXmlSource.java b/src/jalview/ws/dbsources/EmblXmlSource.java index a420d9f..ba46a6c 100644 --- a/src/jalview/ws/dbsources/EmblXmlSource.java +++ b/src/jalview/ws/dbsources/EmblXmlSource.java @@ -20,8 +20,30 @@ */ package jalview.ws.dbsources; +import java.util.Locale; + +import java.io.File; +import java.io.FileInputStream; +import java.io.InputStream; +import java.text.ParseException; +import java.util.ArrayList; +import java.util.Arrays; +import java.util.Hashtable; +import java.util.List; +import java.util.Map; +import java.util.Map.Entry; + +import javax.xml.bind.JAXBContext; +import javax.xml.bind.JAXBElement; +import javax.xml.bind.JAXBException; +import javax.xml.stream.FactoryConfigurationError; +import javax.xml.stream.XMLInputFactory; +import javax.xml.stream.XMLStreamException; +import javax.xml.stream.XMLStreamReader; + + import jalview.analysis.SequenceIdMatcher; -import jalview.bin.Cache; +import jalview.bin.Console; import jalview.datamodel.Alignment; import jalview.datamodel.AlignmentI; import jalview.datamodel.DBRefEntry; @@ -36,32 +58,28 @@ import jalview.util.DnaUtils; import jalview.util.MapList; import jalview.util.MappingUtils; import jalview.util.MessageManager; +import jalview.util.Platform; import jalview.ws.ebi.EBIFetchClient; import jalview.xml.binding.embl.EntryType; import jalview.xml.binding.embl.EntryType.Feature; import jalview.xml.binding.embl.EntryType.Feature.Qualifier; +import jalview.xml.binding.embl.ROOT; import jalview.xml.binding.embl.XrefType; -import java.io.File; -import java.io.FileInputStream; -import java.io.InputStream; -import java.text.ParseException; -import java.util.ArrayList; -import java.util.Arrays; -import java.util.Hashtable; -import java.util.List; -import java.util.Map; -import java.util.Map.Entry; - -import javax.xml.bind.JAXBContext; -import javax.xml.bind.JAXBException; -import javax.xml.stream.FactoryConfigurationError; -import javax.xml.stream.XMLInputFactory; -import javax.xml.stream.XMLStreamException; -import javax.xml.stream.XMLStreamReader; +import com.stevesoft.pat.Regex; +/** + * Provides XML binding and parsing of EMBL or EMBLCDS records retrieved from + * (e.g.) {@code https://www.ebi.ac.uk/ena/data/view/x53828&display=xml}. + * + * @deprecated endpoint withdrawn August 2020 (JAL-3692), use EmblFlatfileSource + */ +@Deprecated public abstract class EmblXmlSource extends EbiFileRetrievedProxy { + // TODO: delete class or update tyhis validator for 2.12 style Platform.regex + private static final Regex ACCESSION_REGEX = Platform.newRegex("^[A-Z]+[0-9]+"); + /* * JAL-1856 Embl returns this text for query not found */ @@ -91,14 +109,15 @@ public abstract class EmblXmlSource extends EbiFileRetrievedProxy try { reply = dbFetch.fetchDataAsFile( - emprefx.toLowerCase() + ":" + query.trim(), "display=xml", + emprefx.toLowerCase(Locale.ROOT) + ":" + query.trim(), "display=xml", "xml"); } catch (Exception e) { stopQuery(); - throw new Exception(MessageManager.formatMessage( - "exception.ebiembl_retrieval_failed_on", new String[] - { emprefx.toLowerCase(), query.trim() }), e); + throw new Exception( + String.format("EBI EMBL XML retrieval failed for %s:%s", + emprefx.toLowerCase(Locale.ROOT), query.trim()), + e); } return getEmblSequenceRecords(emprefx, query, reply); } @@ -180,8 +199,9 @@ public abstract class EmblXmlSource extends EbiFileRetrievedProxy XMLStreamReader streamReader = XMLInputFactory.newInstance() .createXMLStreamReader(is); javax.xml.bind.Unmarshaller um = jc.createUnmarshaller(); - jalview.xml.binding.embl.ROOT root = (jalview.xml.binding.embl.ROOT) um - .unmarshal(streamReader); + JAXBElement rootElement = um.unmarshal(streamReader, + ROOT.class); + ROOT root = rootElement.getValue(); /* * document root contains either "entry" or "entrySet" @@ -561,6 +581,7 @@ public abstract class EmblXmlSource extends EbiFileRetrievedProxy proteinSeq = new Sequence(proteinSeqName, product.getSequenceAsString()); matcher.add(proteinSeq); + proteinSeq.setDescription(product.getDescription()); peptides.add(proteinSeq); } dnaToProteinMapping.setTo(proteinSeq); @@ -614,8 +635,7 @@ public abstract class EmblXmlSource extends EbiFileRetrievedProxy && dnaToProteinMapping.getTo() != null) { DBRefEntry dnaToEmblProteinRef = new DBRefEntry( - DBRefSource.EMBLCDSProduct, sequenceVersion, - proteinId); + DBRefSource.EMBLCDSProduct, sequenceVersion, proteinId); dnaToEmblProteinRef.setMap(dnaToProteinMapping); dnaToProteinMapping.setMappedFromId(proteinId); dna.addDBRef(dnaToEmblProteinRef); @@ -644,14 +664,14 @@ public abstract class EmblXmlSource extends EbiFileRetrievedProxy { return new int[] {}; } - + try { List ranges = DnaUtils.parseLocation(location); return listToArray(ranges); } catch (ParseException e) { - Cache.log.warn( + Console.warn( String.format("Not parsing inexact CDS location %s in ENA %s", location, accession)); return new int[] {}; @@ -708,10 +728,43 @@ public abstract class EmblXmlSource extends EbiFileRetrievedProxy return sf; } + @Override + public String getAccessionSeparator() + { + return null; + } + + @Override + public Regex getAccessionValidator() + { + return ACCESSION_REGEX; + } + + @Override + public String getDbVersion() + { + return "0"; + } + + @Override + public int getTier() + { + return 0; + } + + @Override + public boolean isValidReference(String accession) + { + if (accession == null || accession.length() < 2) + { + return false; + } + return getAccessionValidator().search(accession); + } + /** * Truncates (if necessary) the exon intervals to match 3 times the length of - * the protein; also accepts 3 bases longer (for stop codon not included in - * protein) + * the protein (including truncation for stop codon included in exon) * * @param proteinLength * @param exon @@ -726,17 +779,15 @@ public abstract class EmblXmlSource extends EbiFileRetrievedProxy } int expectedCdsLength = proteinLength * 3; int exonLength = MappingUtils.getLength(Arrays.asList(exon)); - + /* - * if exon length matches protein, or is shorter, or longer by the - * length of a stop codon (3 bases), then leave it unchanged + * if exon length matches protein, or is shorter, then leave it unchanged */ - if (expectedCdsLength >= exonLength - || expectedCdsLength == exonLength - 3) + if (expectedCdsLength >= exonLength) { return exon; } - + int origxon[]; int sxpos = -1; int endxon = 0; @@ -756,7 +807,7 @@ public abstract class EmblXmlSource extends EbiFileRetrievedProxy // .println("Truncating final exon interval on region by " // + (cdspos - cdslength)); } - + /* * shrink the final exon - reduce end position if forward * strand, increase it if reverse @@ -772,7 +823,7 @@ public abstract class EmblXmlSource extends EbiFileRetrievedProxy break; } } - + if (sxpos != -1) { // and trim the exon interval set if necessary