X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fws%2Fdbsources%2FEmblXmlSource.java;fp=src%2Fjalview%2Fws%2Fdbsources%2FEmblXmlSource.java;h=ba46a6c3ad5f44c053bbef5386a7ac05445a697d;hb=d043ce47fc710d3eb2629ba926a8a7417bd67d8c;hp=7bb1977d73418df228eaa0f74454832f88d11d76;hpb=49db0dff1da16c3355b43a41498c1fc93ef47e91;p=jalview.git diff --git a/src/jalview/ws/dbsources/EmblXmlSource.java b/src/jalview/ws/dbsources/EmblXmlSource.java index 7bb1977..ba46a6c 100644 --- a/src/jalview/ws/dbsources/EmblXmlSource.java +++ b/src/jalview/ws/dbsources/EmblXmlSource.java @@ -41,8 +41,9 @@ 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; @@ -57,6 +58,7 @@ 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; @@ -64,17 +66,20 @@ import jalview.xml.binding.embl.EntryType.Feature.Qualifier; import jalview.xml.binding.embl.ROOT; import jalview.xml.binding.embl.XrefType; +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 * * @deprecated endpoint withdrawn August 2020 (JAL-3692), use EmblFlatfileSource */ - +@Deprecated public abstract class EmblXmlSource extends EbiFileRetrievedProxy { // TODO: delete class or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 = new Regex("^[A-Z]+[0-9]+"); + private static final Regex ACCESSION_REGEX = Platform.newRegex("^[A-Z]+[0-9]+"); + /* * JAL-1856 Embl returns this text for query not found */ @@ -659,13 +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[] {}; @@ -755,10 +761,10 @@ public abstract class EmblXmlSource extends EbiFileRetrievedProxy } 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 @@ -773,15 +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; @@ -801,6 +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 @@ -816,6 +823,7 @@ public abstract class EmblXmlSource extends EbiFileRetrievedProxy break; } } + if (sxpos != -1) { // and trim the exon interval set if necessary