X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fio%2FIdentifyFile.java;h=a241e0e7fe6a92fda5c508defc7047fd102cd359;hb=17e77c3f2949a0729322b4a8d907f3f34b6a9914;hp=262989699218e83bed628d512570426b9d092afd;hpb=47168f025aefdaa044802bd5f8f510ffe43a4808;p=jalview.git

diff --git a/src/jalview/io/IdentifyFile.java b/src/jalview/io/IdentifyFile.java
index 2629896..a241e0e 100755
--- a/src/jalview/io/IdentifyFile.java
+++ b/src/jalview/io/IdentifyFile.java
@@ -1,41 +1,43 @@
 /*
- * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8.2)
- * Copyright (C) 2014 The Jalview Authors
- * 
+ * Jalview - A Sequence Alignment Editor and Viewer (Version 2.9)
+ * Copyright (C) 2015 The Jalview Authors
+ *
  * 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 
+ * 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 
+ *
+ * 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
  * PURPOSE.  See the GNU General Public License for more details.
- * 
+ *
  * You should have received a copy of the GNU General Public License
  * along with Jalview.  If not, see <http://www.gnu.org/licenses/>.
  * The Jalview Authors are detailed in the 'AUTHORS' file.
  */
 package jalview.io;
 
-import java.io.*;
+import java.io.IOException;
 
 /**
  * DOCUMENT ME!
- * 
+ *
  * @author $author$
  * @version $Revision$
  */
 public class IdentifyFile
 {
+  public static final String GFF3File = "GFF v2 or v3";
+
   /**
    * Identify a datasource's file content.
-   * 
+   *
    * @note Do not use this method for stream sources - create a FileParse object
    *       instead.
-   * 
+   *
    * @param file
    *          DOCUMENT ME!
    * @param protocol
@@ -60,7 +62,9 @@ public class IdentifyFile
       emessage = e.getMessage();
     }
     if (parser != null)
+    {
       return parser.errormessage;
+    }
     return emessage;
   }
 
@@ -73,7 +77,7 @@ public class IdentifyFile
   /**
    * Identify contents of source, closing it or resetting source to start
    * afterwards.
-   * 
+   *
    * @param source
    * @param closeSource
    * @return filetype string
@@ -94,7 +98,7 @@ public class IdentifyFile
       }
       while ((data = source.nextLine()) != null)
       {
-        length += data.length();
+        length += data.trim().length();
         if (!lineswereskipped)
         {
           for (int i = 0; !isBinary && i < data.length(); i++)
@@ -128,50 +132,18 @@ public class IdentifyFile
         }
         data = data.toUpperCase();
 
-        if ((data.indexOf("# STOCKHOLM") > -1))
-        {
-          reply = "STH";
-
-          break;
-        }
-        
-        if ((data.indexOf("<") > -1))
-        {
-          reply = "RNAML";
-          
-          break;
-        }
-
-        if ((data.length() < 1) || (data.indexOf("#") == 0))
-        {
-          lineswereskipped = true;
-          continue;
-        }
-
-        if (data.indexOf("PILEUP") > -1)
-        {
-          reply = "PileUp";
-
-          break;
-        }
-
-        if ((data.indexOf("//") == 0)
-                || ((data.indexOf("!!") > -1) && (data.indexOf("!!") < data
-                        .indexOf("_MULTIPLE_ALIGNMENT "))))
+        if (data.startsWith("##GFF-VERSION"))
         {
-          reply = "MSF";
-
+          reply = GFF3File;
           break;
         }
-        else if (data.indexOf("CLUSTAL") > -1)
+        if (data.indexOf("# STOCKHOLM") > -1)
         {
-          reply = "CLUSTAL";
-
+          reply = "STH";
           break;
         }
-        
-        
-        else if (data.indexOf(">") > -1)
+        // if (data.indexOf(">") > -1)
+        if (data.startsWith(">"))
         {
           // FASTA, PIR file or BLC file
           boolean checkPIR = false, starterm = false;
@@ -199,13 +171,16 @@ public class IdentifyFile
               starterm = (data1 != null && data1.indexOf("*") > -1)
                       || (data2 != null && data2.indexOf("*") > -1);
             }
-            if (data2 != null && (c1=data.indexOf("*")) > -1)
+            if (data2 != null && (c1 = data.indexOf("*")) > -1)
             {
-              if (c1==0 && c1 == data2.indexOf("*"))
+              if (c1 == 0 && c1 == data2.indexOf("*"))
               {
                 reply = "BLC";
-              } else {
-                reply = "FASTA"; // possibly a bad choice - may be recognised as PIR 
+              }
+              else
+              {
+                reply = "FASTA"; // possibly a bad choice - may be recognised as
+                // PIR
               }
               // otherwise can still possibly be a PIR file
             }
@@ -260,11 +235,77 @@ public class IdentifyFile
           // read as a FASTA (probably)
           break;
         }
+        if ((data.indexOf("<") > -1)) // possible Markup Language data i.e HTML,
+                                      // RNAML, XML
+        {
+          boolean identified = false;
+          do
+          {
+            if (data.matches("<(?i)html(\"[^\"]*\"|'[^']*'|[^'\">])*>"))
+            {
+              reply = HtmlFile.FILE_DESC;
+              identified = true;
+              break;
+            }
+
+            if (data.matches("<(?i)rnaml (\"[^\"]*\"|'[^']*'|[^'\">])*>"))
+            {
+              reply = "RNAML";
+              identified = true;
+              break;
+            }
+          } while ((data = source.nextLine()) != null);
+
+          if (identified)
+          {
+            break;
+          }
+        }
+
+        if (data.indexOf("{\"") > -1)
+        {
+          reply = JSONFile.FILE_DESC;
+          break;
+        }
+        if ((data.length() < 1) || (data.indexOf("#") == 0))
+        {
+          lineswereskipped = true;
+          continue;
+        }
+
+        if (data.indexOf("PILEUP") > -1)
+        {
+          reply = "PileUp";
+
+          break;
+        }
+
+        if ((data.indexOf("//") == 0)
+                || ((data.indexOf("!!") > -1) && (data.indexOf("!!") < data
+                        .indexOf("_MULTIPLE_ALIGNMENT "))))
+        {
+          reply = "MSF";
+
+          break;
+        }
+        else if (data.indexOf("CLUSTAL") > -1)
+        {
+          reply = "CLUSTAL";
+
+          break;
+        }
+
         else if (data.indexOf("HEADER") == 0 || data.indexOf("ATOM") == 0)
         {
           reply = "PDB";
           break;
         }
+        else if (data.matches("\\s*\\d+\\s+\\d+\\s*"))
+        {
+          reply = PhylipFile.FILE_DESC;
+          break;
+        }
+
         /*
          * // TODO comment out SimpleBLAST identification for Jalview 2.4.1 else
          * if (!lineswereskipped && data.indexOf("BLAST")<4) { reply =
@@ -310,6 +351,7 @@ public class IdentifyFile
 
   public static void main(String[] args)
   {
+
     for (int i = 0; args != null && i < args.length; i++)
     {
       IdentifyFile ider = new IdentifyFile();