2 * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
3 * Copyright (C) $$Year-Rel$$ 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.AlignExportSettingI;
24 import jalview.api.AlignmentViewPanel;
25 import jalview.datamodel.Alignment;
26 import jalview.datamodel.AlignmentAnnotation;
27 import jalview.datamodel.AlignmentI;
28 import jalview.datamodel.AlignmentView;
29 import jalview.util.MessageManager;
32 import java.io.IOException;
33 import java.io.InputStream;
34 import java.util.List;
37 * A low level class for alignment and feature IO with alignment formatting
38 * methods used by both applet and application for generating flat alignment
39 * files. It also holds the lists of magic format names that the applet and
40 * application will allow the user to read or write files with.
45 public class AppletFormatAdapter
47 private AlignmentViewPanel viewpanel;
49 public static String FILE = "File";
51 public static String URL = "URL";
53 public static String PASTE = "Paste";
55 public static String CLASSLOADER = "ClassLoader";
58 * add jalview-derived non-secondary structure annotation from PDB structure
60 boolean annotFromStructure = false;
63 * add secondary structure from PDB data with built-in algorithms
65 boolean localSecondaryStruct = false;
68 * process PDB data with web services
70 boolean serviceSecondaryStruct = false;
72 private AlignFile alignFile = null;
77 * character used to write newlines
79 protected String newline = System.getProperty("line.separator");
81 private AlignExportSettingI exportSettings;
84 * List of valid format strings used in the isValidFormat method
86 public static final String[] READABLE_FORMATS = new String[] { "BLC",
87 "CLUSTAL", "FASTA", "MSF", "PileUp", "PIR", "PFAM", "STH", "PDB",
88 "JnetFile", "RNAML", PhylipFile.FILE_DESC, JSONFile.FILE_DESC,
89 IdentifyFile.GFF3File, "HTML" };
92 * List of readable format file extensions by application in order
93 * corresponding to READABLE_FNAMES
95 public static final String[] READABLE_EXTENSIONS = new String[] {
96 "fa, fasta, mfa, fastq", "aln", "pfam", "msf", "pir", "blc", "amsa",
97 "sto,stk", "xml,rnaml", PhylipFile.FILE_EXT, JSONFile.FILE_EXT,
98 ".gff2,gff3", "jar,jvp", HtmlFile.FILE_EXT };
101 * List of readable formats by application in order corresponding to
102 * READABLE_EXTENSIONS
104 public static final String[] READABLE_FNAMES = new String[] { "Fasta",
105 "Clustal", "PFAM", "MSF", "PIR", "BLC", "AMSA", "Stockholm", "RNAML",
106 PhylipFile.FILE_DESC, JSONFile.FILE_DESC, IdentifyFile.GFF3File,
107 "Jalview", HtmlFile.FILE_DESC };
110 * List of valid format strings for use by callers of the formatSequences
113 public static final String[] WRITEABLE_FORMATS = new String[] { "BLC",
114 "CLUSTAL", "FASTA", "MSF", "PileUp", "PIR", "PFAM", "AMSA", "STH",
115 PhylipFile.FILE_DESC, JSONFile.FILE_DESC };
118 * List of extensions corresponding to file format types in WRITABLE_FNAMES
119 * that are writable by the application.
121 public static final String[] WRITABLE_EXTENSIONS = new String[] {
122 "fa, fasta, mfa, fastq", "aln", "pfam", "msf", "pir", "blc", "amsa",
123 "sto,stk", PhylipFile.FILE_EXT, JSONFile.FILE_EXT, "jvp" };
126 * List of writable formats by the application. Order must correspond with the
127 * WRITABLE_EXTENSIONS list of formats.
129 public static final String[] WRITABLE_FNAMES = new String[] { "Fasta",
130 "Clustal", "PFAM", "MSF", "PIR", "BLC", "AMSA", "STH",
131 PhylipFile.FILE_DESC, JSONFile.FILE_DESC, "Jalview" };
133 public static String INVALID_CHARACTERS = "Contains invalid characters";
135 // TODO: make these messages dynamic
136 public static String SUPPORTED_FORMATS = "Formats currently supported are\n"
137 + prettyPrint(READABLE_FORMATS);
139 public AppletFormatAdapter()
143 public AppletFormatAdapter(AlignmentViewPanel viewpanel)
145 this.viewpanel = viewpanel;
148 public AppletFormatAdapter(AlignmentViewPanel alignPanel,
149 AlignExportSettingI settings)
151 viewpanel = alignPanel;
152 exportSettings = settings;
158 * @return grammatically correct(ish) list consisting of els elements.
160 public static String prettyPrint(String[] els)
162 StringBuffer list = new StringBuffer();
163 for (int i = 0, iSize = els.length - 1; i < iSize; i++)
168 list.append(" and " + els[els.length - 1] + ".");
169 return list.toString();
172 public void setNewlineString(String nl)
177 public String getNewlineString()
183 * check that this format is valid for reading
186 * a format string to be compared with READABLE_FORMATS
187 * @return true if format is readable
189 public static final boolean isValidFormat(String format)
191 return isValidFormat(format, false);
195 * validate format is valid for IO
198 * a format string to be compared with either READABLE_FORMATS or
201 * when true, format is checked for containment in WRITEABLE_FORMATS
202 * @return true if format is valid
204 public static final boolean isValidFormat(String format,
211 boolean valid = false;
212 String[] format_list = (forwriting) ? WRITEABLE_FORMATS
214 for (String element : format_list)
216 if (element.equalsIgnoreCase(format))
226 * Constructs the correct filetype parser for a characterised datasource
233 * File format of data provided by datasource
235 * @return DOCUMENT ME!
237 public AlignmentI readFile(String inFile, String type, String format)
238 throws java.io.IOException
240 // TODO: generalise mapping between format string and io. class instances
241 // using Constructor.invoke reflection
242 this.inFile = inFile;
245 if (format.equals("FASTA"))
247 alignFile = new FastaFile(inFile, type);
249 else if (format.equals("MSF"))
251 alignFile = new MSFfile(inFile, type);
253 else if (format.equals("PileUp"))
255 alignFile = new PileUpfile(inFile, type);
257 else if (format.equals("CLUSTAL"))
259 alignFile = new ClustalFile(inFile, type);
261 else if (format.equals("BLC"))
263 alignFile = new BLCFile(inFile, type);
265 else if (format.equals("PIR"))
267 alignFile = new PIRFile(inFile, type);
269 else if (format.equals("PFAM"))
271 alignFile = new PfamFile(inFile, type);
273 else if (format.equals("JnetFile"))
275 alignFile = new JPredFile(inFile, type);
276 ((JPredFile) alignFile).removeNonSequences();
278 else if (format.equals("PDB"))
280 alignFile = new MCview.PDBfile(annotFromStructure,
281 localSecondaryStruct, serviceSecondaryStruct, inFile, type);
282 // Uncomment to test Jmol data based PDB processing: JAL-1213
283 // afile = new jalview.ext.jmol.PDBFileWithJmol(inFile, type);
285 else if (format.equals("STH"))
287 alignFile = new StockholmFile(inFile, type);
289 else if (format.equals("SimpleBLAST"))
291 alignFile = new SimpleBlastFile(inFile, type);
293 else if (format.equals(PhylipFile.FILE_DESC))
295 alignFile = new PhylipFile(inFile, type);
297 else if (format.equals(JSONFile.FILE_DESC))
299 alignFile = new JSONFile(inFile, type);
301 else if (format.equals(HtmlFile.FILE_DESC))
303 alignFile = new HtmlFile(inFile, type);
305 else if (format.equals("RNAML"))
307 alignFile = new RnamlFile(inFile, type);
309 else if (format.equals(IdentifyFile.GFF3File))
311 alignFile = new Gff3File(inFile, type);
313 return buildAlignmentFrom(alignFile);
314 } catch (Exception e)
317 System.err.println("Failed to read alignment using the '" + format
318 + "' reader.\n" + e);
320 if (e.getMessage() != null
321 && e.getMessage().startsWith(INVALID_CHARACTERS))
323 throw new java.io.IOException(e.getMessage());
326 // Finally test if the user has pasted just the sequence, no id
327 if (type.equalsIgnoreCase("Paste"))
331 // Possible sequence is just residues with no label
332 alignFile = new FastaFile(">UNKNOWN\n" + inFile, "Paste");
333 return buildAlignmentFrom(alignFile);
335 } catch (Exception ex)
337 if (ex.toString().startsWith(INVALID_CHARACTERS))
339 throw new java.io.IOException(e.getMessage());
342 ex.printStackTrace();
345 if (format.equalsIgnoreCase("HTML"))
347 throw new IOException(e.getMessage());
349 // If we get to this stage, the format was not supported
350 throw new java.io.IOException(SUPPORTED_FORMATS);
355 * Constructs the correct filetype parser for an already open datasource
358 * an existing datasource
360 * File format of data that will be provided by datasource
362 * @return DOCUMENT ME!
364 public AlignmentI readFromFile(FileParse source, String format)
365 throws java.io.IOException
367 // TODO: generalise mapping between format string and io. class instances
368 // using Constructor.invoke reflection
369 // This is exactly the same as the readFile method except we substitute
370 // 'inFile, type' with 'source'
371 this.inFile = source.getInFile();
372 String type = source.type;
375 if (format.equals("FASTA"))
377 alignFile = new FastaFile(source);
379 else if (format.equals("MSF"))
381 alignFile = new MSFfile(source);
383 else if (format.equals("PileUp"))
385 alignFile = new PileUpfile(source);
387 else if (format.equals("CLUSTAL"))
389 alignFile = new ClustalFile(source);
391 else if (format.equals("BLC"))
393 alignFile = new BLCFile(source);
395 else if (format.equals("PIR"))
397 alignFile = new PIRFile(source);
399 else if (format.equals("PFAM"))
401 alignFile = new PfamFile(source);
403 else if (format.equals("JnetFile"))
405 alignFile = new JPredFile(source);
406 ((JPredFile) alignFile).removeNonSequences();
408 else if (format.equals("PDB"))
410 alignFile = new MCview.PDBfile(annotFromStructure,
411 localSecondaryStruct, serviceSecondaryStruct, source);
413 else if (format.equals("STH"))
415 alignFile = new StockholmFile(source);
417 else if (format.equals("RNAML"))
419 alignFile = new RnamlFile(source);
421 else if (format.equals("SimpleBLAST"))
423 alignFile = new SimpleBlastFile(source);
425 else if (format.equals(PhylipFile.FILE_DESC))
427 alignFile = new PhylipFile(source);
429 else if (format.equals(IdentifyFile.GFF3File))
431 alignFile = new Gff3File(inFile, type);
433 else if (format.equals(JSONFile.FILE_DESC))
435 alignFile = new JSONFile(source);
437 else if (format.equals(HtmlFile.FILE_DESC))
439 alignFile = new HtmlFile(source);
442 return buildAlignmentFrom(alignFile);
444 } catch (Exception e)
447 System.err.println("Failed to read alignment using the '" + format
448 + "' reader.\n" + e);
450 if (e.getMessage() != null
451 && e.getMessage().startsWith(INVALID_CHARACTERS))
453 throw new java.io.IOException(e.getMessage());
456 // Finally test if the user has pasted just the sequence, no id
457 if (type.equalsIgnoreCase("Paste"))
461 // Possible sequence is just residues with no label
462 alignFile = new FastaFile(">UNKNOWN\n" + inFile, "Paste");
463 return buildAlignmentFrom(alignFile);
465 } catch (Exception ex)
467 if (ex.toString().startsWith(INVALID_CHARACTERS))
469 throw new java.io.IOException(e.getMessage());
472 ex.printStackTrace();
476 // If we get to this stage, the format was not supported
477 throw new java.io.IOException(SUPPORTED_FORMATS);
482 * boilerplate method to handle data from an AlignFile and construct a new
483 * alignment or import to an existing alignment
486 * @return AlignmentI instance ready to pass to a UI constructor
488 private AlignmentI buildAlignmentFrom(AlignFile alignFile2)
490 // Standard boilerplate for creating alignment from parser
491 // alignFile.configureForView(viewpanel);
493 AlignmentI al = new Alignment(alignFile.getSeqsAsArray());
495 alignFile.addAnnotations(al);
497 alignFile.addGroups(al);
503 * create an alignment flatfile from a Jalview alignment view
508 * @param selectedOnly
509 * @return flatfile in a string
511 public String formatSequences(String format, boolean jvsuffix,
512 AlignmentViewPanel ap, boolean selectedOnly)
515 AlignmentView selvew = ap.getAlignViewport().getAlignmentView(
516 selectedOnly, false);
517 AlignmentI aselview = selvew.getVisibleAlignment(ap.getAlignViewport()
519 List<AlignmentAnnotation> ala = (ap.getAlignViewport()
520 .getVisibleAlignmentAnnotation(selectedOnly));
523 for (AlignmentAnnotation aa : ala)
525 aselview.addAnnotation(aa);
529 return formatSequences(format, aselview, jvsuffix);
533 * Construct an output class for an alignment in a particular filetype TODO:
534 * allow caller to detect errors and warnings encountered when generating
538 * string name of alignment format
540 * the alignment to be written out
542 * passed to AlnFile class controls whether /START-END is added to
545 * @return alignment flat file contents
547 public String formatSequences(String format, AlignmentI alignment,
552 AlignFile afile = null;
553 if (format.equalsIgnoreCase("FASTA"))
555 afile = new FastaFile();
557 else if (format.equalsIgnoreCase("MSF"))
559 afile = new MSFfile();
561 else if (format.equalsIgnoreCase("PileUp"))
563 afile = new PileUpfile();
565 else if (format.equalsIgnoreCase("CLUSTAL"))
567 afile = new ClustalFile();
569 else if (format.equalsIgnoreCase("BLC"))
571 afile = new BLCFile();
573 else if (format.equalsIgnoreCase("PIR"))
575 afile = new PIRFile();
577 else if (format.equalsIgnoreCase("PFAM"))
579 afile = new PfamFile();
581 else if (format.equalsIgnoreCase("STH"))
583 afile = new StockholmFile(alignment);
585 else if (format.equalsIgnoreCase("AMSA"))
587 afile = new AMSAFile(alignment);
589 else if (format.equalsIgnoreCase(PhylipFile.FILE_DESC))
591 afile = new PhylipFile();
593 else if (format.equalsIgnoreCase(JSONFile.FILE_DESC))
595 afile = new JSONFile();
597 else if (format.equalsIgnoreCase("RNAML"))
599 afile = new RnamlFile();
606 .getString("error.implementation_error_unknown_file_format_string"));
609 afile.setNewlineString(newline);
610 afile.addJVSuffix(jvsuffix);
611 afile.setExportSettings(exportSettings);
612 afile.configureForView(viewpanel);
614 // check whether we were given a specific alignment to export, rather than
615 // the one in the viewpanel
616 if (viewpanel == null || viewpanel.getAlignment() == null
617 || viewpanel.getAlignment() != alignment)
619 afile.setSeqs(alignment.getSequencesArray());
623 afile.setSeqs(viewpanel.getAlignment().getSequencesArray());
626 String afileresp = afile.print();
627 if (afile.hasWarningMessage())
629 System.err.println("Warning raised when writing as " + format
630 + " : " + afile.getWarningMessage());
633 } catch (Exception e)
635 System.err.println("Failed to write alignment as a '" + format
643 public static String checkProtocol(String file)
645 String protocol = FILE;
646 String ft = file.toLowerCase().trim();
647 if (ft.indexOf("http:") == 0 || ft.indexOf("https:") == 0
648 || ft.indexOf("file:") == 0)
655 public static void main(String[] args)
658 while (i < args.length)
660 File f = new File(args[i]);
665 System.out.println("Reading file: " + f);
666 AppletFormatAdapter afa = new AppletFormatAdapter();
667 Runtime r = Runtime.getRuntime();
669 long memf = -r.totalMemory() + r.freeMemory();
670 long t1 = -System.currentTimeMillis();
671 AlignmentI al = afa.readFile(args[i], FILE,
672 new IdentifyFile().Identify(args[i], FILE));
673 t1 += System.currentTimeMillis();
675 memf += r.totalMemory() - r.freeMemory();
678 System.out.println("Alignment contains " + al.getHeight()
679 + " sequences and " + al.getWidth() + " columns.");
682 System.out.println(new AppletFormatAdapter().formatSequences(
684 } catch (Exception e)
687 .println("Couln't format the alignment for output as a FASTA file.");
688 e.printStackTrace(System.err);
693 System.out.println("Couldn't read alignment");
695 System.out.println("Read took " + (t1 / 1000.0) + " seconds.");
697 .println("Difference between free memory now and before is "
698 + (memf / (1024.0 * 1024.0) * 1.0) + " MB");
699 } catch (Exception e)
701 System.err.println("Exception when dealing with " + i
702 + "'th argument: " + args[i] + "\n" + e);
707 System.err.println("Ignoring argument '" + args[i] + "' (" + i
708 + "'th)- not a readable file.");
715 * try to discover how to access the given file as a valid datasource that
716 * will be identified as the given type.
720 * @return protocol that yields the data parsable as the given type
722 public static String resolveProtocol(String file, String format)
724 return resolveProtocol(file, format, false);
727 public static String resolveProtocol(String file, String format,
730 // TODO: test thoroughly!
731 String protocol = null;
734 System.out.println("resolving datasource started with:\n>>file\n"
735 + file + ">>endfile");
738 // This might throw a security exception in certain browsers
739 // Netscape Communicator for instance.
743 InputStream is = System.getSecurityManager().getClass()
744 .getResourceAsStream("/" + file);
752 System.err.println("Resource '" + file + "' was "
753 + (rtn ? "" : "not") + " located by classloader.");
758 protocol = AppletFormatAdapter.CLASSLOADER;
761 } catch (Exception ex)
764 .println("Exception checking resources: " + file + " " + ex);
767 if (file.indexOf("://") > -1)
769 protocol = AppletFormatAdapter.URL;
773 // skipping codebase prepend check.
774 protocol = AppletFormatAdapter.FILE;
781 System.out.println("Trying to get contents of resource as "
784 fp = new FileParse(file, protocol);
793 System.out.println("Successful.");
796 } catch (Exception e)
800 System.err.println("Exception when accessing content: " + e);
808 System.out.println("Accessing as paste.");
810 protocol = AppletFormatAdapter.PASTE;
814 fp = new FileParse(file, protocol);
819 } catch (Exception e)
821 System.err.println("Failed to access content as paste!");
830 if (format == null || format.length() == 0)
838 String idformat = new jalview.io.IdentifyFile().Identify(file,
840 if (idformat == null)
844 System.out.println("Format not identified. Inaccessible file.");
850 System.out.println("Format identified as " + idformat
851 + "and expected as " + format);
853 if (idformat.equals(format))
857 System.out.println("Protocol identified as " + protocol);
866 .println("File deemed not accessible via " + protocol);
871 } catch (Exception e)
875 System.err.println("File deemed not accessible via " + protocol);
885 public AlignFile getAlignFile()
890 public void setAlignFile(AlignFile alignFile)
892 this.alignFile = alignFile;