Classes

Class	Line #	Total Statements	Complexity	TOTAL Coverage	Actions
EmblXmlSource	78	256	85	0.6808510468.1%	Show methods

Class EmblXmlSource

Class EmblXmlSource	Line # 78	Total Statements 256	Complexity 85	TOTAL Coverage 0.6808510468.1%
EmblXmlSource()   EmblXmlSource()	8888	1.01	1.01	1.0 1.0100%
getEmblSequenceRecords(String,String) : AlignmentI   getEmblSequenceRecords(String,String) : AlignmentI	103103	8.08	2.02	0.0 0.00%
getEmblSequenceRecords(String,String,File) : AlignmentI   getEmblSequenceRecords(String,String,File) : AlignmentI	137137	19.019	7.07	0.0 0.00%
getEmblEntries(InputStream) : List<EntryType>   getEmblEntries(InputStream) : List<EntryType>	193193	15.015	5.05	0.71428573 0.7142857371.4%
getSequence(String,EntryType,List<SequenceI>) : SequenceI   getSequence(String,EntryType,List<SequenceI>) : SequenceI	238238	33.033	8.08	0.76744187 0.7674418776.7%
parseCodingFeature(EntryType,Feature,String,SequenceI,List<SequenceI>,SequenceIdMatcher) : void   parseCodingFeature(EntryType,Feature,String,SequenceI,List<SequenceI>,SequenceIdMatcher) : void	321321	126.0126	39.039	0.7880435 0.788043578.8%
isDnaCoding() : boolean   isDnaCoding() : boolean	647647	1.01	1.01	0.0 0.00%
getCdsRanges(String,Feature) : int[]   getCdsRanges(String,Feature) : int[]	661661	8.08	3.03	0.6 0.660%
listToArray(List<int[]>) : int[]   listToArray(List<int[]>) : int[]	689689	6.06	1.01	1.0 1.0100%
makeCdsFeature(String,String,int,int,String,Map<String, String>) : SequenceFeature   makeCdsFeature(String,String,int,int,String,Map<String, String>) : SequenceFeature	718718	5.05	2.02	1.0 1.0100%
getAccessionSeparator() : String   getAccessionSeparator() : String	732732	1.01	1.01	0.0 0.00%
getAccessionValidator() : Regex   getAccessionValidator() : Regex	738738	1.01	1.01	0.0 0.00%
getDbVersion() : String   getDbVersion() : String	744744	1.01	1.01	0.0 0.00%
getTier() : int   getTier() : int	750750	1.01	1.01	0.0 0.00%
isValidReference(String) : boolean   isValidReference(String) : boolean	756756	3.03	3.03	0.0 0.00%
adjustForProteinLength(int,int[]) : int[]   adjustForProteinLength(int,int[]) : int[]	775775	27.027	9.09	0.85365856 0.8536585685.4%

 

Contributing tests

Source view

1		/*
2		* Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
3		* Copyright (C) $$Year-Rel$$ The Jalview Authors
4		*
5		* This file is part of Jalview.
6		*
7		* Jalview is free software: you can redistribute it and/or
8		* modify it under the terms of the GNU General Public License
9		* as published by the Free Software Foundation, either version 3
10		* of the License, or (at your option) any later version.
11		*
12		* Jalview is distributed in the hope that it will be useful, but
13		* WITHOUT ANY WARRANTY; without even the implied warranty
14		* of MERCHANTABILITY or FITNESS FOR A PARTICULAR
15		* PURPOSE. See the GNU General Public License for more details.
16		*
17		* You should have received a copy of the GNU General Public License
18		* along with Jalview. If not, see <http://www.gnu.org/licenses/>.
19		* The Jalview Authors are detailed in the 'AUTHORS' file.
20		*/
21		package jalview.ws.dbsources;
22
23		import java.util.Locale;
24
25		import java.io.File;
26		import java.io.FileInputStream;
27		import java.io.InputStream;
28		import java.text.ParseException;
29		import java.util.ArrayList;
30		import java.util.Arrays;
31		import java.util.Hashtable;
32		import java.util.List;
33		import java.util.Map;
34		import java.util.Map.Entry;
35
36		import javax.xml.bind.JAXBContext;
37		import javax.xml.bind.JAXBElement;
38		import javax.xml.bind.JAXBException;
39		import javax.xml.stream.FactoryConfigurationError;
40		import javax.xml.stream.XMLInputFactory;
41		import javax.xml.stream.XMLStreamException;
42		import javax.xml.stream.XMLStreamReader;
43
44
45		import jalview.analysis.SequenceIdMatcher;
46		import jalview.bin.Console;
47		import jalview.datamodel.Alignment;
48		import jalview.datamodel.AlignmentI;
49		import jalview.datamodel.DBRefEntry;
50		import jalview.datamodel.DBRefSource;
51		import jalview.datamodel.FeatureProperties;
52		import jalview.datamodel.Mapping;
53		import jalview.datamodel.Sequence;
54		import jalview.datamodel.SequenceFeature;
55		import jalview.datamodel.SequenceI;
56		import jalview.util.DBRefUtils;
57		import jalview.util.DnaUtils;
58		import jalview.util.MapList;
59		import jalview.util.MappingUtils;
60		import jalview.util.MessageManager;
61		import jalview.util.Platform;
62		import jalview.ws.ebi.EBIFetchClient;
63		import jalview.xml.binding.embl.EntryType;
64		import jalview.xml.binding.embl.EntryType.Feature;
65		import jalview.xml.binding.embl.EntryType.Feature.Qualifier;
66		import jalview.xml.binding.embl.ROOT;
67		import jalview.xml.binding.embl.XrefType;
68
69		import com.stevesoft.pat.Regex;
70
71		/**
72		* Provides XML binding and parsing of EMBL or EMBLCDS records retrieved from
73		* (e.g.) {@code https://www.ebi.ac.uk/ena/data/view/x53828&display=xml}.
74		*
75		* @deprecated endpoint withdrawn August 2020 (JAL-3692), use EmblFlatfileSource
76		*/
77		@Deprecated
		68.1% Uncovered Elements: 120 (376) Complexity: 85 Complexity Density: 0.33
78		public abstract class EmblXmlSource extends EbiFileRetrievedProxy
79		{
80		// TODO: delete class or update tyhis validator for 2.12 style Platform.regex
81		private static final Regex ACCESSION_REGEX = Platform.newRegex("^[A-Z]+[0-9]+");
82
83		/*
84		* JAL-1856 Embl returns this text for query not found
85		*/
86		private static final String EMBL_NOT_FOUND_REPLY = "ERROR 12 No entries found.";
87
		100% Uncovered Elements: 0 (1) Complexity: 1 Complexity Density: 1
88	1	public EmblXmlSource()...
89		{
90	1	super();
91		}
92
93		/**
94		* Retrieves and parses an emblxml file, and returns an alignment containing
95		* the parsed sequences, or null if none were found
96		*
97		* @param emprefx
98		* "EMBL" or "EMBLCDS" - anything else will not retrieve emblxml
99		* @param query
100		* @return
101		* @throws Exception
102		*/
		0% Uncovered Elements: 8 (8) Complexity: 2 Complexity Density: 0.25
103	0	protected AlignmentI getEmblSequenceRecords(String emprefx, String query)...
104		throws Exception
105		{
106	0	startQuery();
107	0	EBIFetchClient dbFetch = new EBIFetchClient();
108	0	File reply;
109	0	try
110		{
111	0	reply = dbFetch.fetchDataAsFile(
112		emprefx.toLowerCase(Locale.ROOT) + ":" + query.trim(), "display=xml",
113		"xml");
114		} catch (Exception e)
115		{
116	0	stopQuery();
117	0	throw new Exception(
118		String.format("EBI EMBL XML retrieval failed for %s:%s",
119		emprefx.toLowerCase(Locale.ROOT), query.trim()),
120		e);
121		}
122	0	return getEmblSequenceRecords(emprefx, query, reply);
123		}
124
125		/**
126		* parse an emblxml file stored locally
127		*
128		* @param emprefx
129		* either EMBL or EMBLCDS strings are allowed - anything else will
130		* not retrieve emblxml
131		* @param query
132		* @param file
133		* the EMBL XML file containing the results of a query
134		* @return
135		* @throws Exception
136		*/
		0% Uncovered Elements: 29 (29) Complexity: 7 Complexity Density: 0.37
137	0	protected AlignmentI getEmblSequenceRecords(String emprefx, String query,...
138		File reply) throws Exception
139		{
140	0	List<EntryType> entries = null;
141	0	if (reply != null && reply.exists())
142		{
143	0	file = reply.getAbsolutePath();
144	0	if (reply.length() > EMBL_NOT_FOUND_REPLY.length())
145		{
146	0	InputStream is = new FileInputStream(reply);
147	0	entries = getEmblEntries(is);
148		}
149		}
150
151		/*
152		* invalid accession gets a reply with no <entry> elements, text content of
153		* EmbFile reads something like (e.g.) this ungrammatical phrase
154		* Entry: <acc> display type is either not supported or entry is not found.
155		*/
156	0	AlignmentI al = null;
157	0	List<SequenceI> seqs = new ArrayList<>();
158	0	List<SequenceI> peptides = new ArrayList<>();
159	0	if (entries != null)
160		{
161	0	for (EntryType entry : entries)
162		{
163	0	SequenceI seq = getSequence(emprefx, entry, peptides);
164	0	if (seq != null)
165		{
166	0	seqs.add(seq.deriveSequence());
167		// place DBReferences on dataset and refer
168		}
169		}
170	0	if (!seqs.isEmpty())
171		{
172	0	al = new Alignment(seqs.toArray(new SequenceI[seqs.size()]));
173		}
174		else
175		{
176	0	jalview.bin.Console.outPrintln(
177		"No record found for '" + emprefx + ":" + query + "'");
178		}
179		}
180
181	0	stopQuery();
182	0	return al;
183		}
184
185		/**
186		* Reads the XML reply from file and unmarshals it to Java objects. Answers a
187		* (possibly empty) list of <code>EntryType</code> objects.
188		*
189		* is
190		*
191		* @return
192		*/
		71.4% Uncovered Elements: 6 (21) Complexity: 5 Complexity Density: 0.33
193	2	List<EntryType> getEmblEntries(InputStream is)...
194		{
195	2	List<EntryType> entries = new ArrayList<>();
196	2	try
197		{
198	2	JAXBContext jc = JAXBContext.newInstance("jalview.xml.binding.embl");
199	2	XMLStreamReader streamReader = XMLInputFactory.newInstance()
200		.createXMLStreamReader(is);
201	2	javax.xml.bind.Unmarshaller um = jc.createUnmarshaller();
202	2	JAXBElement<ROOT> rootElement = um.unmarshal(streamReader,
203		ROOT.class);
204	2	ROOT root = rootElement.getValue();
205
206		/*
207		* document root contains either "entry" or "entrySet"
208		*/
209	2	if (root == null)
210		{
211	0	return entries;
212		}
213	2	if (root.getEntrySet() != null)
214		{
215	0	entries = root.getEntrySet().getEntry();
216		}
217	2	else if (root.getEntry() != null)
218		{
219	2	entries.add(root.getEntry());
220		}
221		} catch (JAXBException | XMLStreamException
222		| FactoryConfigurationError e)
223		{
224	0	e.printStackTrace();
225		}
226	2	return entries;
227		}
228
229		/**
230		* A helper method to parse XML data and construct a sequence, with any
231		* available database references and features
232		*
233		* @param emprefx
234		* @param entry
235		* @param peptides
236		* @return
237		*/
		76.7% Uncovered Elements: 10 (43) Complexity: 8 Complexity Density: 0.24
238	1	SequenceI getSequence(String sourceDb, EntryType entry,...
239		List<SequenceI> peptides)
240		{
241	1	String seqString = entry.getSequence();
242	1	if (seqString == null)
243		{
244	0	return null;
245		}
246	1	seqString = seqString.replace(" ", "").replace("\n", "").replace("\t",
247		"");
248	1	String accession = entry.getAccession();
249	1	SequenceI dna = new Sequence(sourceDb + "|" + accession, seqString);
250
251	1	dna.setDescription(entry.getDescription());
252	1	String sequenceVersion = String.valueOf(entry.getVersion().intValue());
253	1	DBRefEntry selfRref = new DBRefEntry(sourceDb, sequenceVersion,
254		accession);
255	1	dna.addDBRef(selfRref);
256	1	selfRref.setMap(
257		new Mapping(null, new int[]
258		{ 1, dna.getLength() }, new int[] { 1, dna.getLength() }, 1,
259		1));
260
261		/*
262		* add db references
263		*/
264	1	List<XrefType> xrefs = entry.getXref();
265	1	if (xrefs != null)
266		{
267	1	for (XrefType xref : xrefs)
268		{
269	2	String acc = xref.getId();
270	2	String source = DBRefUtils.getCanonicalName(xref.getDb());
271	2	String version = xref.getSecondaryId();
272	2	if (version == null || "".equals(version))
273		{
274	1	version = "0";
275		}
276	2	dna.addDBRef(new DBRefEntry(source, version, acc));
277		}
278		}
279
280	1	SequenceIdMatcher matcher = new SequenceIdMatcher(peptides);
281	1	try
282		{
283	1	List<Feature> features = entry.getFeature();
284	1	if (features != null)
285		{
286	1	for (Feature feature : features)
287		{
288	3	if (FeatureProperties.isCodingFeature(sourceDb,
289		feature.getName()))
290		{
291	3	parseCodingFeature(entry, feature, sourceDb, dna, peptides,
292		matcher);
293		}
294		}
295		}
296		} catch (Exception e)
297		{
298	0	jalview.bin.Console.errPrintln("EMBL Record Features parsing error!");
299	0	System.err
300		.println("Please report the following to help@jalview.org :");
301	0	jalview.bin.Console.errPrintln("EMBL Record " + accession);
302	0	jalview.bin.Console
303		.errPrintln("Resulted in exception: " + e.getMessage());
304	0	e.printStackTrace(System.err);
305		}
306
307	1	return dna;
308		}
309
310		/**
311		* Extracts coding region and product from a CDS feature and decorates it with
312		* annotations
313		*
314		* @param entry
315		* @param feature
316		* @param sourceDb
317		* @param dna
318		* @param peptides
319		* @param matcher
320		*/
		78.8% Uncovered Elements: 39 (184) Complexity: 39 Complexity Density: 0.31
321	3	void parseCodingFeature(EntryType entry, Feature feature, String sourceDb,...
322		SequenceI dna, List<SequenceI> peptides,
323		SequenceIdMatcher matcher)
324		{
325	3	final boolean isEmblCdna = sourceDb.equals(DBRefSource.EMBLCDS);
326	3	final String accession = entry.getAccession();
327	3	final String sequenceVersion = entry.getVersion().toString();
328
329	3	int[] exons = getCdsRanges(entry.getAccession(), feature);
330
331	3	String translation = null;
332	3	String proteinName = "";
333	3	String proteinId = null;
334	3	Map<String, String> vals = new Hashtable<>();
335
336		/*
337		* codon_start 1/2/3 in EMBL corresponds to phase 0/1/2 in CDS
338		* (phase is required for CDS features in GFF3 format)
339		*/
340	3	int codonStart = 1;
341
342		/*
343		* parse qualifiers, saving protein translation, protein id,
344		* codon start position, product (name), and 'other values'
345		*/
346	3	if (feature.getQualifier() != null)
347		{
348	3	for (Qualifier q : feature.getQualifier())
349		{
350	7	String qname = q.getName();
351	7	String value = q.getValue();
352	7	value = value == null ? ""
353		: value.trim().replace(" ", "").replace("\n", "")
354		.replace("\t", "");
355	7	if (qname.equals("translation"))
356		{
357	3	translation = value;
358		}
359	4	else if (qname.equals("protein_id"))
360		{
361	3	proteinId = value;
362		}
363	1	else if (qname.equals("codon_start"))
364		{
365	0	try
366		{
367	0	codonStart = Integer.parseInt(value.trim());
368		} catch (NumberFormatException e)
369		{
370	0	jalview.bin.Console.errPrintln("Invalid codon_start in XML for "
371		+ entry.getAccession() + ": " + e.getMessage());
372		}
373		}
374	1	else if (qname.equals("product"))
375		{
376		// sometimes name is returned e.g. for V00488
377	0	proteinName = value;
378		}
379		else
380		{
381		// throw anything else into the additional properties hash
382	1	if (!"".equals(value))
383		{
384	1	vals.put(qname, value);
385		}
386		}
387		}
388		}
389
390	3	DBRefEntry proteinToEmblProteinRef = null;
391	3	exons = MappingUtils.removeStartPositions(codonStart - 1, exons);
392
393	3	SequenceI product = null;
394	3	Mapping dnaToProteinMapping = null;
395	3	if (translation != null && proteinName != null && proteinId != null)
396		{
397	3	int translationLength = translation.length();
398
399		/*
400		* look for product in peptides list, if not found, add it
401		*/
402	3	product = matcher.findIdMatch(proteinId);
403	3	if (product == null)
404		{
405	3	product = new Sequence(proteinId, translation, 1,
406		translationLength);
407	3	product.setDescription(((proteinName.length() == 0)
408		? "Protein Product from " + sourceDb
409		: proteinName));
410	3	peptides.add(product);
411	3	matcher.add(product);
412		}
413
414		// we have everything - create the mapping and perhaps the protein
415		// sequence
416	3	if (exons == null || exons.length == 0)
417		{
418		/*
419		* workaround until we handle dna location for CDS sequence
420		* e.g. location="X53828.1:60..1058" correctly
421		*/
422	0	jalview.bin.Console.errPrintln(
423		"Implementation Notice: EMBLCDS records not properly supported yet - Making up the CDNA region of this sequence... may be incorrect ("
424		+ sourceDb + ":" + entry.getAccession() + ")");
425	0	int dnaLength = dna.getLength();
426	0	if (translationLength * 3 == (1 - codonStart + dnaLength))
427		{
428	0	jalview.bin.Console.errPrintln(
429		"Not allowing for additional stop codon at end of cDNA fragment... !");
430		// this might occur for CDS sequences where no features are marked
431	0	exons = new int[] { dna.getStart() + (codonStart - 1),
432		dna.getEnd() };
433	0	dnaToProteinMapping = new Mapping(product, exons,
434		new int[]
435		{ 1, translationLength }, 3, 1);
436		}
437	0	if ((translationLength + 1) * 3 == (1 - codonStart + dnaLength))
438		{
439	0	jalview.bin.Console.errPrintln(
440		"Allowing for additional stop codon at end of cDNA fragment... will probably cause an error in VAMSAs!");
441	0	exons = new int[] { dna.getStart() + (codonStart - 1),
442		dna.getEnd() - 3 };
443	0	dnaToProteinMapping = new Mapping(product, exons,
444		new int[]
445		{ 1, translationLength }, 3, 1);
446		}
447		}
448		else
449		{
450		// Trim the exon mapping if necessary - the given product may only be a
451		// fragment of a larger protein. (EMBL:AY043181 is an example)
452
453	3	if (isEmblCdna)
454		{
455		// TODO: Add a DbRef back to the parent EMBL sequence with the exon
456		// map
457		// if given a dataset reference, search dataset for parent EMBL
458		// sequence if it exists and set its map
459		// make a new feature annotating the coding contig
460		}
461		else
462		{
463		// final product length truncation check
464	3	int[] cdsRanges = adjustForProteinLength(translationLength,
465		exons);
466	3	dnaToProteinMapping = new Mapping(product, cdsRanges,
467		new int[]
468		{ 1, translationLength }, 3, 1);
469	3	if (product != null)
470		{
471		/*
472		* make xref with mapping from protein to EMBL dna
473		*/
474	3	DBRefEntry proteinToEmblRef = new DBRefEntry(DBRefSource.EMBL,
475		sequenceVersion, proteinId,
476		new Mapping(dnaToProteinMapping.getMap().getInverse()));
477	3	product.addDBRef(proteinToEmblRef);
478
479		/*
480		* make xref from protein to EMBLCDS; we assume here that the
481		* CDS sequence version is same as dna sequence (?!)
482		*/
483	3	MapList proteinToCdsMapList = new MapList(
484		new int[]
485		{ 1, translationLength },
486		new int[]
487		{ 1 + (codonStart - 1),
488		(codonStart - 1) + 3 * translationLength },
489		1, 3);
490	3	DBRefEntry proteinToEmblCdsRef = new DBRefEntry(
491		DBRefSource.EMBLCDS, sequenceVersion, proteinId,
492		new Mapping(proteinToCdsMapList));
493	3	product.addDBRef(proteinToEmblCdsRef);
494
495		/*
496		* make 'direct' xref from protein to EMBLCDSPROTEIN
497		*/
498	3	proteinToEmblProteinRef = new DBRefEntry(proteinToEmblCdsRef);
499	3	proteinToEmblProteinRef.setSource(DBRefSource.EMBLCDSProduct);
500	3	proteinToEmblProteinRef.setMap(null);
501	3	product.addDBRef(proteinToEmblProteinRef);
502		}
503		}
504		}
505
506		/*
507		* add cds features to dna sequence
508		*/
509	3	String cds = feature.getName(); // "CDS"
510	7	for (int xint = 0; exons != null
511		&& xint < exons.length - 1; xint += 2)
512		{
513	4	int exonStart = exons[xint];
514	4	int exonEnd = exons[xint + 1];
515	4	int begin = Math.min(exonStart, exonEnd);
516	4	int end = Math.max(exonStart, exonEnd);
517	4	int exonNumber = xint / 2 + 1;
518	4	String desc = String.format("Exon %d for protein '%s' EMBLCDS:%s",
519		exonNumber, proteinName, proteinId);
520
521	4	SequenceFeature sf = makeCdsFeature(cds, desc, begin, end, sourceDb,
522		vals);
523
524	4	sf.setEnaLocation(feature.getLocation());
525	4	boolean forwardStrand = exonStart <= exonEnd;
526	4	sf.setStrand(forwardStrand ? "+" : "-");
527	4	sf.setPhase(String.valueOf(codonStart - 1));
528	4	sf.setValue(FeatureProperties.EXONPOS, exonNumber);
529	4	sf.setValue(FeatureProperties.EXONPRODUCT, proteinName);
530
531	4	dna.addSequenceFeature(sf);
532		}
533		}
534
535		/*
536		* add feature dbRefs to sequence, and mappings for Uniprot xrefs
537		*/
538	3	boolean hasUniprotDbref = false;
539	3	List<XrefType> xrefs = feature.getXref();
540	3	if (xrefs != null)
541		{
542	3	boolean mappingUsed = false;
543	3	for (XrefType xref : xrefs)
544		{
545		/*
546		* ensure UniProtKB/Swiss-Prot converted to UNIPROT
547		*/
548	3	String source = DBRefUtils.getCanonicalName(xref.getDb());
549	3	String version = xref.getSecondaryId();
550	3	if (version == null || "".equals(version))
551		{
552	2	version = "0";
553		}
554	3	DBRefEntry dbref = new DBRefEntry(source, version, xref.getId());
555	3	DBRefEntry proteinDbRef = new DBRefEntry(source, version,
556		dbref.getAccessionId());
557	3	if (source.equals(DBRefSource.UNIPROT))
558		{
559	3	String proteinSeqName = DBRefSource.UNIPROT + "|"
560		+ dbref.getAccessionId();
561	3	if (dnaToProteinMapping != null
562		&& dnaToProteinMapping.getTo() != null)
563		{
564	3	if (mappingUsed)
565		{
566		/*
567		* two or more Uniprot xrefs for the same CDS -
568		* each needs a distinct Mapping (as to a different sequence)
569		*/
570	1	dnaToProteinMapping = new Mapping(dnaToProteinMapping);
571		}
572	3	mappingUsed = true;
573
574		/*
575		* try to locate the protein mapped to (possibly by a
576		* previous CDS feature); if not found, construct it from
577		* the EMBL translation
578		*/
579	3	SequenceI proteinSeq = matcher.findIdMatch(proteinSeqName);
580	3	if (proteinSeq == null)
581		{
582	3	proteinSeq = new Sequence(proteinSeqName,
583		product.getSequenceAsString());
584	3	matcher.add(proteinSeq);
585	3	proteinSeq.setDescription(product.getDescription());
586	3	peptides.add(proteinSeq);
587		}
588	3	dnaToProteinMapping.setTo(proteinSeq);
589	3	dnaToProteinMapping.setMappedFromId(proteinId);
590	3	proteinSeq.addDBRef(proteinDbRef);
591	3	dbref.setMap(dnaToProteinMapping);
592		}
593	3	hasUniprotDbref = true;
594		}
595	3	if (product != null)
596		{
597		/*
598		* copy feature dbref to our protein product
599		*/
600	3	DBRefEntry pref = proteinDbRef;
601	3	pref.setMap(null); // reference is direct
602	3	product.addDBRef(pref);
603		// Add converse mapping reference
604	3	if (dnaToProteinMapping != null)
605		{
606	3	Mapping pmap = new Mapping(dna,
607		dnaToProteinMapping.getMap().getInverse());
608	3	pref = new DBRefEntry(sourceDb, sequenceVersion, accession);
609	3	pref.setMap(pmap);
610	3	if (dnaToProteinMapping.getTo() != null)
611		{
612	3	dnaToProteinMapping.getTo().addDBRef(pref);
613		}
614		}
615		}
616	3	dna.addDBRef(dbref);
617		}
618		}
619
620		/*
621		* if we have a product (translation) but no explicit Uniprot dbref
622		* (example: EMBL AAFI02000057 protein_id EAL65544.1)
623		* then construct mappings to an assumed EMBLCDSPROTEIN accession
624		*/
625	3	if (!hasUniprotDbref && product != null)
626		{
627	1	if (proteinToEmblProteinRef == null)
628		{
629		// assuming CDSPROTEIN sequence version = dna version (?!)
630	0	proteinToEmblProteinRef = new DBRefEntry(DBRefSource.EMBLCDSProduct,
631		sequenceVersion, proteinId);
632		}
633	1	product.addDBRef(proteinToEmblProteinRef);
634
635	1	if (dnaToProteinMapping != null
636		&& dnaToProteinMapping.getTo() != null)
637		{
638	1	DBRefEntry dnaToEmblProteinRef = new DBRefEntry(
639		DBRefSource.EMBLCDSProduct, sequenceVersion, proteinId);
640	1	dnaToEmblProteinRef.setMap(dnaToProteinMapping);
641	1	dnaToProteinMapping.setMappedFromId(proteinId);
642	1	dna.addDBRef(dnaToEmblProteinRef);
643		}
644		}
645		}
646
		0% Uncovered Elements: 1 (1) Complexity: 1 Complexity Density: 1
647	0	@Override...
648		public boolean isDnaCoding()
649		{
650	0	return true;
651		}
652
653		/**
654		* Returns the CDS positions as a single array of [start, end, start, end...]
655		* positions. If on the reverse strand, these will be in descending order.
656		*
657		* @param accession
658		* @param feature
659		* @return
660		*/
		60% Uncovered Elements: 4 (10) Complexity: 3 Complexity Density: 0.38
661	4	protected int[] getCdsRanges(String accession, Feature feature)...
662		{
663	4	String location = feature.getLocation();
664	4	if (location == null)
665		{
666	0	return new int[] {};
667		}
668
669	4	try
670		{
671	4	List<int[]> ranges = DnaUtils.parseLocation(location);
672	4	return listToArray(ranges);
673		} catch (ParseException e)
674		{
675	0	Console.warn(
676		String.format("Not parsing inexact CDS location %s in ENA %s",
677		location, accession));
678	0	return new int[] {};
679		}
680		}
681
682		/**
683		* Converts a list of [start, end] ranges to a single array of [start, end,
684		* start, end ...]
685		*
686		* @param ranges
687		* @return
688		*/
		100% Uncovered Elements: 0 (6) Complexity: 1 Complexity Density: 0.17
689	4	int[] listToArray(List<int[]> ranges)...
690		{
691	4	int[] result = new int[ranges.size() * 2];
692	4	int i = 0;
693	4	for (int[] range : ranges)
694		{
695	9	result[i++] = range[0];
696	9	result[i++] = range[1];
697		}
698	4	return result;
699		}
700
701		/**
702		* Helper method to construct a SequenceFeature for one cds range
703		*
704		* @param type
705		* feature type ("CDS")
706		* @param desc
707		* description
708		* @param begin
709		* start position
710		* @param end
711		* end position
712		* @param group
713		* feature group
714		* @param vals
715		* map of 'miscellaneous values' for feature
716		* @return
717		*/
		100% Uncovered Elements: 0 (7) Complexity: 2 Complexity Density: 0.4
718	4	protected SequenceFeature makeCdsFeature(String type, String desc,...
719		int begin, int end, String group, Map<String, String> vals)
720		{
721	4	SequenceFeature sf = new SequenceFeature(type, desc, begin, end, group);
722	4	if (!vals.isEmpty())
723		{
724	1	for (Entry<String, String> val : vals.entrySet())
725		{
726	1	sf.setValue(val.getKey(), val.getValue());
727		}
728		}
729	4	return sf;
730		}
731
		0% Uncovered Elements: 1 (1) Complexity: 1 Complexity Density: 1
732	0	@Override...
733		public String getAccessionSeparator()
734		{
735	0	return null;
736		}
737
		0% Uncovered Elements: 1 (1) Complexity: 1 Complexity Density: 1
738	0	@Override...
739		public Regex getAccessionValidator()
740		{
741	0	return ACCESSION_REGEX;
742		}
743
		0% Uncovered Elements: 1 (1) Complexity: 1 Complexity Density: 1
744	0	@Override...
745		public String getDbVersion()
746		{
747	0	return "0";
748		}
749
		0% Uncovered Elements: 1 (1) Complexity: 1 Complexity Density: 1
750	0	@Override...
751		public int getTier()
752		{
753	0	return 0;
754		}
755
		0% Uncovered Elements: 5 (5) Complexity: 3 Complexity Density: 1
756	0	@Override...
757		public boolean isValidReference(String accession)
758		{
759	0	if (accession == null || accession.length() < 2)
760		{
761	0	return false;
762		}
763	0	return getAccessionValidator().search(accession);
764		}
765
766		/**
767		* Truncates (if necessary) the exon intervals to match 3 times the length of
768		* the protein (including truncation for stop codon included in exon)
769		*
770		* @param proteinLength
771		* @param exon
772		* an array of [start, end, start, end...] intervals
773		* @return the same array (if unchanged) or a truncated copy
774		*/
		85.4% Uncovered Elements: 6 (41) Complexity: 9 Complexity Density: 0.33
775	9	static int[] adjustForProteinLength(int proteinLength, int[] exon)...
776		{
777	9	if (proteinLength <= 0 || exon == null)
778		{
779	0	return exon;
780		}
781	9	int expectedCdsLength = proteinLength * 3;
782	9	int exonLength = MappingUtils.getLength(Arrays.asList(exon));
783
784		/*
785		* if exon length matches protein, or is shorter, then leave it unchanged
786		*/
787	9	if (expectedCdsLength >= exonLength)
788		{
789	5	return exon;
790		}
791
792	4	int origxon[];
793	4	int sxpos = -1;
794	4	int endxon = 0;
795	4	origxon = new int[exon.length];
796	4	System.arraycopy(exon, 0, origxon, 0, exon.length);
797	4	int cdspos = 0;
798	10	for (int x = 0; x < exon.length; x += 2)
799		{
800	10	cdspos += Math.abs(exon[x + 1] - exon[x]) + 1;
801	10	if (expectedCdsLength <= cdspos)
802		{
803		// advanced beyond last codon.
804	4	sxpos = x;
805	4	if (expectedCdsLength != cdspos)
806		{
807		// System.err
808		// .println("Truncating final exon interval on region by "
809		// + (cdspos - cdslength));
810		}
811
812		/*
813		* shrink the final exon - reduce end position if forward
814		* strand, increase it if reverse
815		*/
816	4	if (exon[x + 1] >= exon[x])
817		{
818	4	endxon = exon[x + 1] - cdspos + expectedCdsLength;
819		}
820		else
821		{
822	0	endxon = exon[x + 1] + cdspos - expectedCdsLength;
823		}
824	4	break;
825		}
826		}
827
828	4	if (sxpos != -1)
829		{
830		// and trim the exon interval set if necessary
831	4	int[] nxon = new int[sxpos + 2];
832	4	System.arraycopy(exon, 0, nxon, 0, sxpos + 2);
833	4	nxon[sxpos + 1] = endxon; // update the end boundary for the new exon
834		// set
835	4	exon = nxon;
836		}
837	4	return exon;
838		}
839
840		}