2 * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8.2)
3 * Copyright (C) 2014 The Jalview Authors
5 * This file is part of Jalview.
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.
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.
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.
23 import jalview.api.AlignViewportI;
24 import jalview.datamodel.Alignment;
25 import jalview.datamodel.AlignmentAnnotation;
26 import jalview.datamodel.AlignmentI;
27 import jalview.datamodel.AlignmentView;
28 import jalview.util.MessageManager;
31 import java.io.InputStream;
32 import java.util.List;
35 * A low level class for alignment and feature IO with alignment formatting
36 * methods used by both applet and application for generating flat alignment
37 * files. It also holds the lists of magic format names that the applet and
38 * application will allow the user to read or write files with.
43 public class AppletFormatAdapter
46 * List of valid format strings used in the isValidFormat method
48 public static final String[] READABLE_FORMATS = new String[]
49 { "BLC", "CLUSTAL", "FASTA", "MSF", "PileUp", "PIR", "PFAM", "STH",
50 "PDB", "JnetFile", "RNAML", PhylipFile.FILE_DESC, JSONFile.FILE_DESC, "HTML" }; // ,
55 * List of valid format strings for use by callers of the formatSequences
58 public static final String[] WRITEABLE_FORMATS = new String[]
59 { "BLC", "CLUSTAL", "FASTA", "MSF", "PileUp", "PIR", "PFAM", "AMSA",
60 "STH", PhylipFile.FILE_DESC, JSONFile.FILE_DESC };
63 * List of extensions corresponding to file format types in WRITABLE_FNAMES
64 * that are writable by the application.
66 public static final String[] WRITABLE_EXTENSIONS = new String[]
67 { "fa, fasta, mfa, fastq", "aln", "pfam", "msf", "pir", "blc", "amsa",
68 "sto,stk", PhylipFile.FILE_EXT, JSONFile.FILE_DESC, "jvp" };
71 * List of writable formats by the application. Order must correspond with the
72 * WRITABLE_EXTENSIONS list of formats.
74 public static final String[] WRITABLE_FNAMES = new String[]
75 { "Fasta", "Clustal", "PFAM", "MSF", "PIR", "BLC", "AMSA", "STH",
76 PhylipFile.FILE_DESC, JSONFile.FILE_DESC, "Jalview" };
79 * List of readable format file extensions by application in order
80 * corresponding to READABLE_FNAMES
82 public static final String[] READABLE_EXTENSIONS = new String[]
83 { "fa, fasta, mfa, fastq", "aln", "pfam", "msf", "pir", "blc", "amsa",
84 "jar,jvp", "sto,stk", "xml,rnaml", PhylipFile.FILE_EXT, JSONFile.FILE_EXT,
88 * List of readable formats by application in order corresponding to
91 public static final String[] READABLE_FNAMES = new String[]
92 { "Fasta", "Clustal", "PFAM", "MSF", "PIR", "BLC", "AMSA", "Jalview",
93 "Stockholm", "RNAML", PhylipFile.FILE_DESC, JSONFile.FILE_DESC,
99 public static String INVALID_CHARACTERS = "Contains invalid characters";
101 // TODO: make these messages dynamic
102 public static String SUPPORTED_FORMATS = "Formats currently supported are\n"
103 + prettyPrint(READABLE_FORMATS);
108 * @return grammatically correct(ish) list consisting of els elements.
110 public static String prettyPrint(String[] els)
112 StringBuffer list = new StringBuffer();
113 for (int i = 0, iSize = els.length - 1; i < iSize; i++)
118 list.append(" and " + els[els.length - 1] + ".");
119 return list.toString();
122 public static String FILE = "File";
124 public static String URL = "URL";
126 public static String PASTE = "Paste";
128 public static String CLASSLOADER = "ClassLoader";
131 * add jalview-derived non-secondary structure annotation from PDB structure
133 boolean annotFromStructure = false;
136 * add secondary structure from PDB data with built-in algorithms
138 boolean localSecondaryStruct = false;
141 * process PDB data with web services
143 boolean serviceSecondaryStruct = false;
145 AlignFile afile = null;
150 * character used to write newlines
152 protected String newline = System.getProperty("line.separator");
154 public void setNewlineString(String nl)
159 public String getNewlineString()
165 * check that this format is valid for reading
168 * a format string to be compared with READABLE_FORMATS
169 * @return true if format is readable
171 public static final boolean isValidFormat(String format)
173 return isValidFormat(format, false);
177 * validate format is valid for IO
180 * a format string to be compared with either READABLE_FORMATS or
183 * when true, format is checked for containment in WRITEABLE_FORMATS
184 * @return true if format is valid
186 public static final boolean isValidFormat(String format,
189 boolean valid = false;
190 String[] format_list = (forwriting) ? WRITEABLE_FORMATS
192 for (String element : format_list)
194 if (element.equalsIgnoreCase(format))
204 * Constructs the correct filetype parser for a characterised datasource
211 * File format of data provided by datasource
213 * @return DOCUMENT ME!
215 public Alignment readFile(String inFile, String type, String format)
216 throws java.io.IOException
218 // TODO: generalise mapping between format string and io. class instances
219 // using Constructor.invoke reflection
220 this.inFile = inFile;
223 if (format.equals("FASTA"))
225 afile = new FastaFile(inFile, type);
227 else if (format.equals("MSF"))
229 afile = new MSFfile(inFile, type);
231 else if (format.equals("PileUp"))
233 afile = new PileUpfile(inFile, type);
235 else if (format.equals("CLUSTAL"))
237 afile = new ClustalFile(inFile, type);
239 else if (format.equals("BLC"))
241 afile = new BLCFile(inFile, type);
243 else if (format.equals("PIR"))
245 afile = new PIRFile(inFile, type);
247 else if (format.equals("PFAM"))
249 afile = new PfamFile(inFile, type);
251 else if (format.equals("JnetFile"))
253 afile = new JPredFile(inFile, type);
254 ((JPredFile) afile).removeNonSequences();
256 else if (format.equals("PDB"))
258 afile = new MCview.PDBfile(annotFromStructure,
259 localSecondaryStruct, serviceSecondaryStruct, inFile, type);
260 // Uncomment to test Jmol data based PDB processing: JAL-1213
261 // afile = new jalview.ext.jmol.PDBFileWithJmol(inFile, type);
263 else if (format.equals("STH"))
265 afile = new StockholmFile(inFile, type);
267 else if (format.equals("SimpleBLAST"))
269 afile = new SimpleBlastFile(inFile, type);
271 else if (format.equals(PhylipFile.FILE_DESC))
273 afile = new PhylipFile(inFile, type);
275 else if (format.equals(JSONFile.FILE_DESC))
277 afile = new JSONFile(inFile, type);
279 else if (format.equals("RNAML"))
281 afile = new RnamlFile(inFile, type);
284 Alignment al = new Alignment(afile.getSeqsAsArray());
286 afile.addAnnotations(al);
289 } catch (Exception e)
292 System.err.println("Failed to read alignment using the '" + format
293 + "' reader.\n" + e);
295 if (e.getMessage() != null
296 && e.getMessage().startsWith(INVALID_CHARACTERS))
298 throw new java.io.IOException(e.getMessage());
301 // Finally test if the user has pasted just the sequence, no id
302 if (type.equalsIgnoreCase("Paste"))
306 // Possible sequence is just residues with no label
307 afile = new FastaFile(">UNKNOWN\n" + inFile, "Paste");
308 Alignment al = new Alignment(afile.getSeqsAsArray());
309 afile.addAnnotations(al);
312 } catch (Exception ex)
314 if (ex.toString().startsWith(INVALID_CHARACTERS))
316 throw new java.io.IOException(e.getMessage());
319 ex.printStackTrace();
323 // If we get to this stage, the format was not supported
324 throw new java.io.IOException(SUPPORTED_FORMATS);
329 * Constructs the correct filetype parser for an already open datasource
332 * an existing datasource
334 * File format of data that will be provided by datasource
336 * @return DOCUMENT ME!
338 public AlignmentI readFromFile(FileParse source, String format)
339 throws java.io.IOException
341 // TODO: generalise mapping between format string and io. class instances
342 // using Constructor.invoke reflection
343 // This is exactly the same as the readFile method except we substitute
344 // 'inFile, type' with 'source'
345 this.inFile = source.getInFile();
346 String type = source.type;
349 if (format.equals("FASTA"))
351 afile = new FastaFile(source);
353 else if (format.equals("MSF"))
355 afile = new MSFfile(source);
357 else if (format.equals("PileUp"))
359 afile = new PileUpfile(source);
361 else if (format.equals("CLUSTAL"))
363 afile = new ClustalFile(source);
365 else if (format.equals("BLC"))
367 afile = new BLCFile(source);
369 else if (format.equals("PIR"))
371 afile = new PIRFile(source);
373 else if (format.equals("PFAM"))
375 afile = new PfamFile(source);
377 else if (format.equals("JnetFile"))
379 afile = new JPredFile(source);
380 ((JPredFile) afile).removeNonSequences();
382 else if (format.equals("PDB"))
384 afile = new MCview.PDBfile(annotFromStructure,
385 localSecondaryStruct, serviceSecondaryStruct, source);
387 else if (format.equals("STH"))
389 afile = new StockholmFile(source);
391 else if (format.equals("RNAML"))
393 afile = new RnamlFile(source);
395 else if (format.equals("SimpleBLAST"))
397 afile = new SimpleBlastFile(source);
399 else if (format.equals(PhylipFile.FILE_DESC))
401 afile = new PhylipFile(source);
403 else if (format.equals(JSONFile.FILE_DESC))
405 afile = new JSONFile(source);
407 Alignment al = new Alignment(afile.getSeqsAsArray());
409 afile.addAnnotations(al);
412 } catch (Exception e)
415 System.err.println("Failed to read alignment using the '" + format
416 + "' reader.\n" + e);
418 if (e.getMessage() != null
419 && e.getMessage().startsWith(INVALID_CHARACTERS))
421 throw new java.io.IOException(e.getMessage());
424 // Finally test if the user has pasted just the sequence, no id
425 if (type.equalsIgnoreCase("Paste"))
429 // Possible sequence is just residues with no label
430 afile = new FastaFile(">UNKNOWN\n" + inFile, "Paste");
431 Alignment al = new Alignment(afile.getSeqsAsArray());
432 afile.addAnnotations(al);
435 } catch (Exception ex)
437 if (ex.toString().startsWith(INVALID_CHARACTERS))
439 throw new java.io.IOException(e.getMessage());
442 ex.printStackTrace();
446 // If we get to this stage, the format was not supported
447 throw new java.io.IOException(SUPPORTED_FORMATS);
453 * create an alignment flatfile from a Jalview alignment view
457 * @param selectedOnly
458 * @return flatfile in a string
460 public String formatSequences(String format, boolean jvsuffix,
461 AlignViewportI av, boolean selectedOnly)
464 AlignmentView selvew = av.getAlignmentView(selectedOnly, false);
465 AlignmentI aselview = selvew.getVisibleAlignment(av
467 List<AlignmentAnnotation> ala = (av
468 .getVisibleAlignmentAnnotation(selectedOnly));
471 for (AlignmentAnnotation aa : ala)
473 aselview.addAnnotation(aa);
477 return formatSequences(format, aselview, jvsuffix);
481 * Construct an output class for an alignment in a particular filetype TODO:
482 * allow caller to detect errors and warnings encountered when generating
486 * string name of alignment format
488 * the alignment to be written out
490 * passed to AlnFile class controls whether /START-END is added to
493 * @return alignment flat file contents
495 public String formatSequences(String format, AlignmentI alignment,
500 AlignFile afile = null;
501 if (format.equalsIgnoreCase("FASTA"))
503 afile = new FastaFile();
505 else if (format.equalsIgnoreCase("MSF"))
507 afile = new MSFfile();
509 else if (format.equalsIgnoreCase("PileUp"))
511 afile = new PileUpfile();
513 else if (format.equalsIgnoreCase("CLUSTAL"))
515 afile = new ClustalFile();
517 else if (format.equalsIgnoreCase("BLC"))
519 afile = new BLCFile();
521 else if (format.equalsIgnoreCase("PIR"))
523 afile = new PIRFile();
525 else if (format.equalsIgnoreCase("PFAM"))
527 afile = new PfamFile();
529 else if (format.equalsIgnoreCase("STH"))
531 afile = new StockholmFile(alignment);
533 else if (format.equalsIgnoreCase("AMSA"))
535 afile = new AMSAFile(alignment);
537 else if (format.equalsIgnoreCase(PhylipFile.FILE_DESC))
539 afile = new PhylipFile();
541 else if (format.equalsIgnoreCase(JSONFile.FILE_DESC))
543 afile = new JSONFile();
545 else if (format.equalsIgnoreCase("RNAML"))
547 afile = new RnamlFile();
552 throw new Exception(MessageManager.getString("error.implementation_error_unknown_file_format_string"));
554 afile.setNewlineString(newline);
555 afile.addJVSuffix(jvsuffix);
557 afile.setSeqs(alignment.getSequencesArray());
559 // Add non auto calculated annotation to AlignFile
560 for (AlignmentAnnotation annot : alignment.getAlignmentAnnotation())
562 if (!annot.autoCalculated)
564 afile.annotations.add(annot);
569 String afileresp = afile.print();
570 if (afile.hasWarningMessage())
572 System.err.println("Warning raised when writing as " + format
573 + " : " + afile.getWarningMessage());
576 } catch (Exception e)
578 System.err.println("Failed to write alignment as a '" + format
586 public static String checkProtocol(String file)
588 String protocol = FILE;
589 String ft = file.toLowerCase().trim();
590 if (ft.indexOf("http:") == 0 || ft.indexOf("https:") == 0
591 || ft.indexOf("file:") == 0)
598 public static void main(String[] args)
601 while (i < args.length)
603 File f = new File(args[i]);
608 System.out.println("Reading file: " + f);
609 AppletFormatAdapter afa = new AppletFormatAdapter();
610 Runtime r = Runtime.getRuntime();
612 long memf = -r.totalMemory() + r.freeMemory();
613 long t1 = -System.currentTimeMillis();
614 Alignment al = afa.readFile(args[i], FILE,
615 new IdentifyFile().Identify(args[i], FILE));
616 t1 += System.currentTimeMillis();
618 memf += r.totalMemory() - r.freeMemory();
621 System.out.println("Alignment contains " + al.getHeight()
622 + " sequences and " + al.getWidth() + " columns.");
625 System.out.println(new AppletFormatAdapter().formatSequences(
627 } catch (Exception e)
630 .println("Couln't format the alignment for output as a FASTA file.");
631 e.printStackTrace(System.err);
636 System.out.println("Couldn't read alignment");
638 System.out.println("Read took " + (t1 / 1000.0) + " seconds.");
640 .println("Difference between free memory now and before is "
641 + (memf / (1024.0 * 1024.0) * 1.0) + " MB");
642 } catch (Exception e)
644 System.err.println("Exception when dealing with " + i
645 + "'th argument: " + args[i] + "\n" + e);
650 System.err.println("Ignoring argument '" + args[i] + "' (" + i
651 + "'th)- not a readable file.");
658 * try to discover how to access the given file as a valid datasource that
659 * will be identified as the given type.
663 * @return protocol that yields the data parsable as the given type
665 public static String resolveProtocol(String file, String format)
667 return resolveProtocol(file, format, false);
670 public static String resolveProtocol(String file, String format,
673 // TODO: test thoroughly!
674 String protocol = null;
677 System.out.println("resolving datasource started with:\n>>file\n"
678 + file + ">>endfile");
681 // This might throw a security exception in certain browsers
682 // Netscape Communicator for instance.
686 InputStream is = System.getSecurityManager().getClass()
687 .getResourceAsStream("/" + file);
695 System.err.println("Resource '" + file + "' was "
696 + (rtn ? "" : "not") + " located by classloader.");
701 protocol = AppletFormatAdapter.CLASSLOADER;
704 } catch (Exception ex)
707 .println("Exception checking resources: " + file + " " + ex);
710 if (file.indexOf("://") > -1)
712 protocol = AppletFormatAdapter.URL;
716 // skipping codebase prepend check.
717 protocol = AppletFormatAdapter.FILE;
724 System.out.println("Trying to get contents of resource as "
727 fp = new FileParse(file, protocol);
736 System.out.println("Successful.");
739 } catch (Exception e)
743 System.err.println("Exception when accessing content: " + e);
751 System.out.println("Accessing as paste.");
753 protocol = AppletFormatAdapter.PASTE;
757 fp = new FileParse(file, protocol);
762 } catch (Exception e)
764 System.err.println("Failed to access content as paste!");
773 if (format == null || format.length() == 0)
781 String idformat = new jalview.io.IdentifyFile().Identify(file,
783 if (idformat == null)
787 System.out.println("Format not identified. Inaccessible file.");
793 System.out.println("Format identified as " + idformat
794 + "and expected as " + format);
796 if (idformat.equals(format))
800 System.out.println("Protocol identified as " + protocol);
809 .println("File deemed not accessible via " + protocol);
814 } catch (Exception e)
818 System.err.println("File deemed not accessible via " + protocol);