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.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,
54 * List of readable format file extensions by application in order
55 * corresponding to READABLE_FNAMES
57 public static final String[] READABLE_EXTENSIONS = new String[]
58 { "fa, fasta, mfa, fastq", "aln", "pfam", "msf", "pir", "blc", "amsa",
59 "sto,stk", "xml,rnaml", PhylipFile.FILE_EXT, JSONFile.FILE_EXT,
63 * List of readable formats by application in order corresponding to
66 public static final String[] READABLE_FNAMES = new String[]
67 { "Fasta", "Clustal", "PFAM", "MSF", "PIR", "BLC", "AMSA", "Stockholm",
68 "RNAML", PhylipFile.FILE_DESC, JSONFile.FILE_DESC, "Jalview", "HTML" };
71 * List of valid format strings for use by callers of the formatSequences
74 public static final String[] WRITEABLE_FORMATS = new String[]
75 { "BLC", "CLUSTAL", "FASTA", "MSF", "PileUp", "PIR", "PFAM", "AMSA",
76 "STH", PhylipFile.FILE_DESC, JSONFile.FILE_DESC };
79 * List of extensions corresponding to file format types in WRITABLE_FNAMES
80 * that are writable by the application.
82 public static final String[] WRITABLE_EXTENSIONS = new String[]
83 { "fa, fasta, mfa, fastq", "aln", "pfam", "msf", "pir", "blc", "amsa",
84 "sto,stk", PhylipFile.FILE_EXT, JSONFile.FILE_EXT, "jvp" };
87 * List of writable formats by the application. Order must correspond with the
88 * WRITABLE_EXTENSIONS list of formats.
90 public static final String[] WRITABLE_FNAMES = new String[]
91 { "Fasta", "Clustal", "PFAM", "MSF", "PIR", "BLC", "AMSA", "STH",
92 PhylipFile.FILE_DESC, JSONFile.FILE_DESC, "Jalview" };
94 public static String INVALID_CHARACTERS = "Contains invalid characters";
96 // TODO: make these messages dynamic
97 public static String SUPPORTED_FORMATS = "Formats currently supported are\n"
98 + prettyPrint(READABLE_FORMATS);
103 * @return grammatically correct(ish) list consisting of els elements.
105 public static String prettyPrint(String[] els)
107 StringBuffer list = new StringBuffer();
108 for (int i = 0, iSize = els.length - 1; i < iSize; i++)
113 list.append(" and " + els[els.length - 1] + ".");
114 return list.toString();
117 public static String FILE = "File";
119 public static String URL = "URL";
121 public static String PASTE = "Paste";
123 public static String CLASSLOADER = "ClassLoader";
126 * add jalview-derived non-secondary structure annotation from PDB structure
128 boolean annotFromStructure = false;
131 * add secondary structure from PDB data with built-in algorithms
133 boolean localSecondaryStruct = false;
136 * process PDB data with web services
138 boolean serviceSecondaryStruct = false;
140 AlignFile afile = null;
145 * character used to write newlines
147 protected String newline = System.getProperty("line.separator");
149 public void setNewlineString(String nl)
154 public String getNewlineString()
160 * check that this format is valid for reading
163 * a format string to be compared with READABLE_FORMATS
164 * @return true if format is readable
166 public static final boolean isValidFormat(String format)
168 return isValidFormat(format, false);
172 * validate format is valid for IO
175 * a format string to be compared with either READABLE_FORMATS or
178 * when true, format is checked for containment in WRITEABLE_FORMATS
179 * @return true if format is valid
181 public static final boolean isValidFormat(String format,
184 boolean valid = false;
185 String[] format_list = (forwriting) ? WRITEABLE_FORMATS
187 for (String element : format_list)
189 if (element.equalsIgnoreCase(format))
199 * Constructs the correct filetype parser for a characterised datasource
206 * File format of data provided by datasource
208 * @return DOCUMENT ME!
210 public Alignment readFile(String inFile, String type, String format)
211 throws java.io.IOException
213 // TODO: generalise mapping between format string and io. class instances
214 // using Constructor.invoke reflection
215 this.inFile = inFile;
218 if (format.equals("FASTA"))
220 afile = new FastaFile(inFile, type);
222 else if (format.equals("MSF"))
224 afile = new MSFfile(inFile, type);
226 else if (format.equals("PileUp"))
228 afile = new PileUpfile(inFile, type);
230 else if (format.equals("CLUSTAL"))
232 afile = new ClustalFile(inFile, type);
234 else if (format.equals("BLC"))
236 afile = new BLCFile(inFile, type);
238 else if (format.equals("PIR"))
240 afile = new PIRFile(inFile, type);
242 else if (format.equals("PFAM"))
244 afile = new PfamFile(inFile, type);
246 else if (format.equals("JnetFile"))
248 afile = new JPredFile(inFile, type);
249 ((JPredFile) afile).removeNonSequences();
251 else if (format.equals("PDB"))
253 afile = new MCview.PDBfile(annotFromStructure,
254 localSecondaryStruct, serviceSecondaryStruct, inFile, type);
255 // Uncomment to test Jmol data based PDB processing: JAL-1213
256 // afile = new jalview.ext.jmol.PDBFileWithJmol(inFile, type);
258 else if (format.equals("STH"))
260 afile = new StockholmFile(inFile, type);
262 else if (format.equals("SimpleBLAST"))
264 afile = new SimpleBlastFile(inFile, type);
266 else if (format.equals(PhylipFile.FILE_DESC))
268 afile = new PhylipFile(inFile, type);
270 else if (format.equals(JSONFile.FILE_DESC))
272 afile = new JSONFile(inFile, type);
274 else if (format.equals("RNAML"))
276 afile = new RnamlFile(inFile, type);
279 Alignment al = new Alignment(afile.getSeqsAsArray());
281 afile.addAnnotations(al);
282 afile.addSeqGroups(al);
285 } catch (Exception e)
288 System.err.println("Failed to read alignment using the '" + format
289 + "' reader.\n" + e);
291 if (e.getMessage() != null
292 && e.getMessage().startsWith(INVALID_CHARACTERS))
294 throw new java.io.IOException(e.getMessage());
297 // Finally test if the user has pasted just the sequence, no id
298 if (type.equalsIgnoreCase("Paste"))
302 // Possible sequence is just residues with no label
303 afile = new FastaFile(">UNKNOWN\n" + inFile, "Paste");
304 Alignment al = new Alignment(afile.getSeqsAsArray());
306 afile.addSeqGroups(al);
307 afile.addAnnotations(al);
310 } catch (Exception ex)
312 if (ex.toString().startsWith(INVALID_CHARACTERS))
314 throw new java.io.IOException(e.getMessage());
317 ex.printStackTrace();
321 // If we get to this stage, the format was not supported
322 throw new java.io.IOException(SUPPORTED_FORMATS);
327 * Constructs the correct filetype parser for an already open datasource
330 * an existing datasource
332 * File format of data that will be provided by datasource
334 * @return DOCUMENT ME!
336 public AlignmentI readFromFile(FileParse source, String format)
337 throws java.io.IOException
339 // TODO: generalise mapping between format string and io. class instances
340 // using Constructor.invoke reflection
341 // This is exactly the same as the readFile method except we substitute
342 // 'inFile, type' with 'source'
343 this.inFile = source.getInFile();
344 String type = source.type;
347 if (format.equals("FASTA"))
349 afile = new FastaFile(source);
351 else if (format.equals("MSF"))
353 afile = new MSFfile(source);
355 else if (format.equals("PileUp"))
357 afile = new PileUpfile(source);
359 else if (format.equals("CLUSTAL"))
361 afile = new ClustalFile(source);
363 else if (format.equals("BLC"))
365 afile = new BLCFile(source);
367 else if (format.equals("PIR"))
369 afile = new PIRFile(source);
371 else if (format.equals("PFAM"))
373 afile = new PfamFile(source);
375 else if (format.equals("JnetFile"))
377 afile = new JPredFile(source);
378 ((JPredFile) afile).removeNonSequences();
380 else if (format.equals("PDB"))
382 afile = new MCview.PDBfile(annotFromStructure,
383 localSecondaryStruct, serviceSecondaryStruct, source);
385 else if (format.equals("STH"))
387 afile = new StockholmFile(source);
389 else if (format.equals("RNAML"))
391 afile = new RnamlFile(source);
393 else if (format.equals("SimpleBLAST"))
395 afile = new SimpleBlastFile(source);
397 else if (format.equals(PhylipFile.FILE_DESC))
399 afile = new PhylipFile(source);
401 else if (format.equals(JSONFile.FILE_DESC))
403 afile = new JSONFile(source);
405 Alignment al = new Alignment(afile.getSeqsAsArray());
407 afile.addAnnotations(al);
408 afile.addSeqGroups(al);
411 } catch (Exception e)
414 System.err.println("Failed to read alignment using the '" + format
415 + "' reader.\n" + e);
417 if (e.getMessage() != null
418 && e.getMessage().startsWith(INVALID_CHARACTERS))
420 throw new java.io.IOException(e.getMessage());
423 // Finally test if the user has pasted just the sequence, no id
424 if (type.equalsIgnoreCase("Paste"))
428 // Possible sequence is just residues with no label
429 afile = new FastaFile(">UNKNOWN\n" + inFile, "Paste");
430 Alignment al = new Alignment(afile.getSeqsAsArray());
431 afile.addAnnotations(al);
434 } catch (Exception ex)
436 if (ex.toString().startsWith(INVALID_CHARACTERS))
438 throw new java.io.IOException(e.getMessage());
441 ex.printStackTrace();
445 // If we get to this stage, the format was not supported
446 throw new java.io.IOException(SUPPORTED_FORMATS);
452 * create an alignment flatfile from a Jalview alignment view
456 * @param selectedOnly
457 * @return flatfile in a string
459 public String formatSequences(String format, boolean jvsuffix,
460 AlignViewportI av, boolean selectedOnly)
463 AlignmentView selvew = av.getAlignmentView(selectedOnly, false);
464 AlignmentI aselview = selvew.getVisibleAlignment(av
466 List<AlignmentAnnotation> ala = (av
467 .getVisibleAlignmentAnnotation(selectedOnly));
470 for (AlignmentAnnotation aa : ala)
472 aselview.addAnnotation(aa);
476 return formatSequences(format, aselview, jvsuffix);
480 * Construct an output class for an alignment in a particular filetype TODO:
481 * allow caller to detect errors and warnings encountered when generating
485 * string name of alignment format
487 * the alignment to be written out
489 * passed to AlnFile class controls whether /START-END is added to
492 * @return alignment flat file contents
494 public String formatSequences(String format, AlignmentI alignment,
499 AlignFile afile = null;
500 if (format.equalsIgnoreCase("FASTA"))
502 afile = new FastaFile();
504 else if (format.equalsIgnoreCase("MSF"))
506 afile = new MSFfile();
508 else if (format.equalsIgnoreCase("PileUp"))
510 afile = new PileUpfile();
512 else if (format.equalsIgnoreCase("CLUSTAL"))
514 afile = new ClustalFile();
516 else if (format.equalsIgnoreCase("BLC"))
518 afile = new BLCFile();
520 else if (format.equalsIgnoreCase("PIR"))
522 afile = new PIRFile();
524 else if (format.equalsIgnoreCase("PFAM"))
526 afile = new PfamFile();
528 else if (format.equalsIgnoreCase("STH"))
530 afile = new StockholmFile(alignment);
532 else if (format.equalsIgnoreCase("AMSA"))
534 afile = new AMSAFile(alignment);
536 else if (format.equalsIgnoreCase(PhylipFile.FILE_DESC))
538 afile = new PhylipFile();
540 else if (format.equalsIgnoreCase(JSONFile.FILE_DESC))
542 afile = new JSONFile();
544 else if (format.equalsIgnoreCase("RNAML"))
546 afile = new RnamlFile();
551 throw new Exception(MessageManager.getString("error.implementation_error_unknown_file_format_string"));
553 afile.setNewlineString(newline);
554 afile.addJVSuffix(jvsuffix);
556 afile.setSeqs(alignment.getSequencesArray());
557 afile.addSeqGroups(alignment);
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);