formatting
[jalview.git] / src / jalview / io / AppletFormatAdapter.java
index b1952a9..f391a54 100755 (executable)
@@ -1,13 +1,13 @@
 /*
- * Jalview - A Sequence Alignment Editor and Viewer (Version 2.6)
- * Copyright (C) 2010 J Procter, AM Waterhouse, G Barton, M Clamp, S Searle
+ * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8)
+ * Copyright (C) 2012 J Procter, AM Waterhouse, LM Lui, J Engelhardt, G Barton, M Clamp, S Searle
  * 
  * This file is part of Jalview.
  * 
  * Jalview is free software: you can redistribute it and/or
  * modify it under the terms of the GNU General Public License 
  * as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version.
- * 
+ *  
  * Jalview is distributed in the hope that it will be useful, but 
  * WITHOUT ANY WARRANTY; without even the implied warranty 
  * of MERCHANTABILITY or FITNESS FOR A PARTICULAR 
@@ -45,21 +45,24 @@ public class AppletFormatAdapter
    * method
    */
   public static final String[] WRITEABLE_FORMATS = new String[]
-  { "BLC", "CLUSTAL", "FASTA", "MSF", "PileUp", "PIR", "PFAM", "AMSA" };
+  { "BLC", "CLUSTAL", "FASTA", "MSF", "PileUp", "PIR", "PFAM", "STH",
+      "AMSA" };
 
   /**
    * List of extensions corresponding to file format types in WRITABLE_FNAMES
    * that are writable by the application.
    */
   public static final String[] WRITABLE_EXTENSIONS = new String[]
-  { "fa, fasta, fastq", "aln", "pfam", "msf", "pir", "blc", "amsa", "jar" };
+  { "fa, fasta, fastq", "aln", "pfam", "msf", "pir", "blc", "amsa", "jar",
+      "sto,stk" };
 
   /**
    * List of writable formats by the application. Order must correspond with the
    * WRITABLE_EXTENSIONS list of formats.
    */
   public static final String[] WRITABLE_FNAMES = new String[]
-  { "Fasta", "Clustal", "PFAM", "MSF", "PIR", "BLC", "AMSA", "Jalview" };
+  { "Fasta", "Clustal", "PFAM", "MSF", "PIR", "BLC", "AMSA", "Jalview",
+      "STH" };
 
   /**
    * List of readable format file extensions by application in order
@@ -67,7 +70,7 @@ public class AppletFormatAdapter
    */
   public static final String[] READABLE_EXTENSIONS = new String[]
   { "fa, fasta, fastq", "aln", "pfam", "msf", "pir", "blc", "amsa", "jar",
-      "sto" }; // ,
+      "sto,stk" }; // ,
 
   // ".blast"
   // };
@@ -119,6 +122,21 @@ public class AppletFormatAdapter
   String inFile;
 
   /**
+   * character used to write newlines
+   */
+  protected String newline = System.getProperty("line.separator");
+
+  public void setNewlineString(String nl)
+  {
+    newline = nl;
+  }
+
+  public String getNewlineString()
+  {
+    return newline;
+  }
+
+  /**
    * check that this format is valid for reading
    * 
    * @param format
@@ -430,7 +448,7 @@ public class AppletFormatAdapter
       }
       else if (format.equalsIgnoreCase("STH"))
       {
-        afile = new StockholmFile();
+        afile = new StockholmFile(alignment);
       }
       else if (format.equalsIgnoreCase("AMSA"))
       {
@@ -441,7 +459,7 @@ public class AppletFormatAdapter
         throw new Exception(
                 "Implementation error: Unknown file format string");
       }
-
+      afile.setNewlineString(newline);
       afile.addJVSuffix(jvsuffix);
 
       afile.setSeqs(alignment.getSequencesArray());
@@ -463,6 +481,18 @@ public class AppletFormatAdapter
     return null;
   }
 
+  public static String checkProtocol(String file)
+  {
+    String protocol = FILE;
+    String ft = file.toLowerCase().trim();
+    if (ft.indexOf("http:") == 0 || ft.indexOf("https:") == 0
+            || ft.indexOf("file:") == 0)
+    {
+      protocol = URL;
+    }
+    return protocol;
+  }
+
   public static void main(String[] args)
   {
     int i = 0;
@@ -475,44 +505,54 @@ public class AppletFormatAdapter
         {
           System.out.println("Reading file: " + f);
           AppletFormatAdapter afa = new AppletFormatAdapter();
-          Runtime r = Runtime.getRuntime();
-          System.gc();
-          long memf = -r.totalMemory() + r.freeMemory();
-          long t1 = -System.currentTimeMillis();
-          Alignment al = afa.readFile(args[i], FILE,
-                  new IdentifyFile().Identify(args[i], FILE));
-          t1 += System.currentTimeMillis();
-          System.gc();
-          memf += r.totalMemory() - r.freeMemory();
-          if (al != null)
+          String fName = f.getName();
+          String extension = fName.substring(fName.lastIndexOf(".") + 1,
+                  fName.length());
+          if (extension.equals("stk") || extension.equals("sto"))
           {
-            System.out.println("Alignment contains " + al.getHeight()
-                    + " sequences and " + al.getWidth() + " columns.");
-            try
-            {
-              System.out.println(new AppletFormatAdapter().formatSequences(
-                      "FASTA", al, true));
-            } catch (Exception e)
-            {
-              System.err
-                      .println("Couln't format the alignment for output as a FASTA file.");
-              e.printStackTrace(System.err);
-            }
+            afa.test(f);
           }
           else
           {
-            System.out.println("Couldn't read alignment");
+            Runtime r = Runtime.getRuntime();
+            System.gc();
+            long memf = -r.totalMemory() + r.freeMemory();
+            long t1 = -System.currentTimeMillis();
+            Alignment al = afa.readFile(args[i], FILE,
+                    new IdentifyFile().Identify(args[i], FILE));
+            t1 += System.currentTimeMillis();
+            System.gc();
+            memf += r.totalMemory() - r.freeMemory();
+            if (al != null)
+            {
+              System.out.println("Alignment contains " + al.getHeight()
+                      + " sequences and " + al.getWidth() + " columns.");
+              try
+              {
+                System.out.println(new AppletFormatAdapter()
+                        .formatSequences("FASTA", al, true));
+              } catch (Exception e)
+              {
+                System.err
+                        .println("Couln't format the alignment for output as a FASTA file.");
+                e.printStackTrace(System.err);
+              }
+            }
+            else
+            {
+              System.out.println("Couldn't read alignment");
+            }
+            System.out.println("Read took " + (t1 / 1000.0) + " seconds.");
+            System.out
+                    .println("Difference between free memory now and before is "
+                            + (memf / (1024.0 * 1024.0) * 1.0) + " MB");
           }
-          System.out.println("Read took " + (t1 / 1000.0) + " seconds.");
-          System.out
-                  .println("Difference between free memory now and before is "
-                          + (memf / (1024.0 * 1024.0) * 1.0) + " MB");
-
         } catch (Exception e)
         {
           System.err.println("Exception when dealing with " + i
                   + "'th argument: " + args[i] + "\n" + e);
         }
+
       }
       else
       {
@@ -523,6 +563,199 @@ public class AppletFormatAdapter
     }
   }
 
+  private void test(File f)
+  {
+    System.out.println("Reading file: " + f);
+    String ff = f.getPath();
+    try
+    {
+      Alignment al = readFile(ff, FILE,
+              new IdentifyFile().Identify(ff, FILE));
+      for (int i = 0; i < al.getSequencesArray().length; ++i)
+      {
+        al.getSequenceAt(i).setDatasetSequence(al.getSequenceAt(i));
+      }
+      AlignFile stFile = new StockholmFile(al);
+      stFile.setSeqs(al.getSequencesArray());
+
+      String stockholmoutput = stFile.print();
+      Alignment al_input = readFile(stockholmoutput,
+              AppletFormatAdapter.PASTE, "STH");
+      if (al != null && al_input != null)
+      {
+        System.out.println("Alignment contains: " + al.getHeight()
+                + " and " + al_input.getHeight() + " sequences; "
+                + al.getWidth() + " and " + al_input.getWidth()
+                + " columns.");
+        AlignmentAnnotation[] aa_new = al_input.getAlignmentAnnotation();
+        AlignmentAnnotation[] aa_original = al.getAlignmentAnnotation();
+
+        // check Alignment annotation
+        if (aa_new != null && aa_original != null)
+        {
+          System.out.println("Alignment contains: " + aa_new.length
+                  + "  and " + aa_original.length
+                  + " alignment annotation(s)");
+          for (int i = 0; i < aa_original.length; i++)
+          {
+            if (!equalss(aa_original[i], aa_new[i]))
+              System.out.println("Different alignment annotation");
+          }
+        }
+
+        // check sequences, annotation and features
+        SequenceI[] seq_original = new SequenceI[al.getSequencesArray().length];
+        seq_original = al.getSequencesArray();
+        SequenceI[] seq_new = new SequenceI[al_input.getSequencesArray().length];
+        seq_new = al_input.getSequencesArray();
+        SequenceFeature[] sequenceFeatures_original, sequenceFeatures_new;
+        AlignmentAnnotation annot_original, annot_new;
+        //
+        for (int i = 0; i < al.getSequencesArray().length; i++)
+        {
+          String name = seq_original[i].getName();
+          int start = seq_original[i].getStart();
+          int end = seq_original[i].getEnd();
+          System.out.println("Check sequence: " + name + "/" + start + "-"
+                  + end);
+
+          // search equal sequence
+          for (int in = 0; in < al_input.getSequencesArray().length; in++)
+          {
+            if (name.equals(seq_new[in].getName())
+                    && start == seq_new[in].getStart()
+                    && end == seq_new[in].getEnd())
+            {
+              String ss_original = seq_original[i].getSequenceAsString();
+              String ss_new = seq_new[in].getSequenceAsString();
+              if (!ss_original.equals(ss_new))
+              {
+                System.out.println("The sequences " + name + "/" + start
+                        + "-" + end + " are not equal");
+              }
+
+              // compare sequence features
+              if (seq_original[i].getSequenceFeatures() != null
+                      && seq_new[in].getSequenceFeatures() != null)
+              {
+                System.out.println("There are feature!!!");
+                sequenceFeatures_original = new SequenceFeature[seq_original[i]
+                        .getSequenceFeatures().length];
+                sequenceFeatures_original = seq_original[i]
+                        .getSequenceFeatures();
+                sequenceFeatures_new = new SequenceFeature[seq_new[in]
+                        .getSequenceFeatures().length];
+                sequenceFeatures_new = seq_new[in].getSequenceFeatures();
+
+                if (seq_original[i].getSequenceFeatures().length == seq_new[in]
+                        .getSequenceFeatures().length)
+                {
+                  for (int feat = 0; feat < seq_original[i]
+                          .getSequenceFeatures().length; feat++)
+                  {
+                    if (!sequenceFeatures_original[feat]
+                            .equals(sequenceFeatures_new[feat]))
+                    {
+                      System.out.println("Different features");
+                      break;
+                    }
+                  }
+                }
+                else
+                {
+                  System.out.println("different number of features");
+                }
+              }
+              else if (seq_original[i].getSequenceFeatures() == null
+                      && seq_new[in].getSequenceFeatures() == null)
+              {
+                System.out.println("No sequence features");
+              }
+              else if (seq_original[i].getSequenceFeatures() != null
+                      && seq_new[in].getSequenceFeatures() == null)
+              {
+                System.out
+                        .println("Coudn't compare sequence features new one");
+              }
+              // compare alignment annotation
+              if (al.getSequenceAt(i).getAnnotation() != null
+                      && al_input.getSequenceAt(in).getAnnotation() != null)
+              {
+                for (int j = 0; j < al.getSequenceAt(i).getAnnotation().length; j++)
+                {
+                  if (al.getSequenceAt(i).getAnnotation()[j] != null
+                          && al_input.getSequenceAt(in).getAnnotation()[j] != null)
+                  {
+                    annot_original = al.getSequenceAt(i).getAnnotation()[j];
+                    annot_new = al_input.getSequenceAt(in).getAnnotation()[j];
+                    if (!equalss(annot_original, annot_new))
+                      System.out.println("Different annotation");
+                  }
+                }
+              }
+              else if (al.getSequenceAt(i).getAnnotation() == null
+                      && al_input.getSequenceAt(in).getAnnotation() == null)
+              {
+                System.out.println("No annotations");
+              }
+              else if (al.getSequenceAt(i).getAnnotation() != null
+                      && al_input.getSequenceAt(in).getAnnotation() == null)
+              {
+                System.out.println("Coudn't compare annotations new one");
+              }
+              break;
+            }
+          }
+        }
+      }
+      else
+      {
+        System.out.println("Couldn't read alignment");
+      }
+    } catch (Exception e)
+    {
+      System.err.println("Couln't format the alignment for output file.");
+      e.printStackTrace(System.err);
+    }
+  }
+
+  /*
+   * compare annotations
+   */
+  private boolean equalss(AlignmentAnnotation annot_or,
+          AlignmentAnnotation annot_new)
+  {
+    if (annot_or.annotations.length != annot_new.annotations.length)
+    {
+      return false;
+    }
+    for (int i = 0; i < annot_or.annotations.length; i++)
+    {
+      if (annot_or.annotations[i] != null
+              && annot_new.annotations[i] != null)
+      {
+        if (!annot_or.annotations[i].displayCharacter
+                .equals(annot_new.annotations[i].displayCharacter)
+                && annot_or.annotations[i].secondaryStructure != annot_new.annotations[i].secondaryStructure
+                && !annot_or.annotations[i].description
+                        .equals(annot_new.annotations[i].description))
+        {
+          return false;
+        }
+      }
+      else if (annot_or.annotations[i] == null
+              && annot_new.annotations[i] == null)
+      {
+        continue;
+      }
+      else
+      {
+        return false;
+      }
+    }
+    return true;
+  }
+
   /**
    * try to discover how to access the given file as a valid datasource that
    * will be identified as the given type.