X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fio%2FIdentifyFile.java;h=7ad8fcd6dc7833f4e696c1389c797a231defe046;hb=3d0101179759ef157b088ea135423cd909512d9f;hp=262989699218e83bed628d512570426b9d092afd;hpb=47168f025aefdaa044802bd5f8f510ffe43a4808;p=jalview.git
diff --git a/src/jalview/io/IdentifyFile.java b/src/jalview/io/IdentifyFile.java
index 2629896..7ad8fcd 100755
--- a/src/jalview/io/IdentifyFile.java
+++ b/src/jalview/io/IdentifyFile.java
@@ -1,30 +1,30 @@
/*
- * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8.2)
- * Copyright (C) 2014 The Jalview Authors
- *
+ * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
+ * Copyright (C) $$Year-Rel$$ 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 .
* The Jalview Authors are detailed in the 'AUTHORS' file.
*/
package jalview.io;
-import java.io.*;
+import java.io.IOException;
/**
* DOCUMENT ME!
- *
+ *
* @author $author$
* @version $Revision$
*/
@@ -32,26 +32,26 @@ public class IdentifyFile
{
/**
* 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
- * DOCUMENT ME!
- * @return ID String
+ * @param sourceType
+ * @return
+ * @throws FileFormatException
*/
- public String Identify(String file, String protocol)
+ public FileFormatI identify(String file, DataSourceType sourceType)
+ throws FileFormatException
{
String emessage = "UNIDENTIFIED FILE PARSING ERROR";
FileParse parser = null;
try
{
- parser = new FileParse(file, protocol);
+ parser = new FileParse(file, sourceType);
if (parser.isValid())
{
- return Identify(parser);
+ return identify(parser);
}
} catch (Exception e)
{
@@ -60,41 +60,58 @@ public class IdentifyFile
emessage = e.getMessage();
}
if (parser != null)
- return parser.errormessage;
- return emessage;
+ {
+ throw new FileFormatException(parser.errormessage);
+ }
+ throw new FileFormatException(emessage);
+ }
+
+ public FileFormatI identify(FileParse source) throws FileFormatException
+ {
+ return identify(source, true);
+ // preserves original behaviour prior to version 2.3
}
- public String Identify(FileParse source)
+ public FileFormatI identify(AlignmentFileReaderI file,
+ boolean closeSource) throws IOException
{
- return Identify(source, true); // preserves original behaviour prior to
- // version 2.3
+ FileParse fp = new FileParse(file.getInFile(),
+ file.getDataSourceType());
+ return identify(fp, closeSource);
}
/**
* Identify contents of source, closing it or resetting source to start
* afterwards.
- *
+ *
* @param source
* @param closeSource
- * @return filetype string
+ * @return (best guess at) file format
+ * @throws FileFormatException
*/
- public String Identify(FileParse source, boolean closeSource)
+ public FileFormatI identify(FileParse source, boolean closeSource)
+ throws FileFormatException
{
- String reply = "PFAM";
+ FileFormatI reply = FileFormat.Pfam;
String data;
- int length = 0;
+ int bytesRead = 0;
+ int trimmedLength = 0;
boolean lineswereskipped = false;
boolean isBinary = false; // true if length is non-zero and non-printable
// characters are encountered
+
try
{
if (!closeSource)
{
source.mark();
}
+ boolean aaIndexHeaderRead = false;
+
while ((data = source.nextLine()) != null)
{
- length += data.length();
+ bytesRead += data.length();
+ trimmedLength += data.trim().length();
if (!lineswereskipped)
{
for (int i = 0; !isBinary && i < data.length(); i++)
@@ -117,61 +134,56 @@ public class IdentifyFile
if (fileStr.lastIndexOf(".jar") > -1
|| fileStr.lastIndexOf(".zip") > -1)
{
- reply = "Jalview";
+ reply = FileFormat.Jalview;
}
}
if (!lineswereskipped && data.startsWith("PK"))
{
- reply = "Jalview"; // archive.
+ reply = FileFormat.Jalview; // archive.
break;
}
}
data = data.toUpperCase();
- if ((data.indexOf("# STOCKHOLM") > -1))
+ if (data.startsWith(ScoreMatrixFile.SCOREMATRIX))
{
- reply = "STH";
-
+ reply = FileFormat.ScoreMatrix;
break;
}
-
- if ((data.indexOf("<") > -1))
+ if (data.startsWith("H ") && !aaIndexHeaderRead)
{
- reply = "RNAML";
-
+ aaIndexHeaderRead = true;
+ }
+ if (data.startsWith("D ") && aaIndexHeaderRead)
+ {
+ reply = FileFormat.ScoreMatrix;
break;
}
-
- if ((data.length() < 1) || (data.indexOf("#") == 0))
+ if (data.startsWith("##GFF-VERSION"))
{
- lineswereskipped = true;
- continue;
+ // GFF - possibly embedded in a Jalview features file!
+ reply = FileFormat.Features;
+ break;
}
-
- if (data.indexOf("PILEUP") > -1)
+ if (looksLikeFeatureData(data))
{
- reply = "PileUp";
-
+ reply = FileFormat.Features;
break;
}
-
- if ((data.indexOf("//") == 0)
- || ((data.indexOf("!!") > -1) && (data.indexOf("!!") < data
- .indexOf("_MULTIPLE_ALIGNMENT "))))
+ if (data.indexOf("# STOCKHOLM") > -1)
{
- reply = "MSF";
-
+ reply = FileFormat.Stockholm;
break;
}
- else if (data.indexOf("CLUSTAL") > -1)
+ if (data.indexOf("_ENTRY.ID") > -1
+ || data.indexOf("_AUDIT_AUTHOR.NAME") > -1
+ || data.indexOf("_ATOM_SITE.") > -1)
{
- reply = "CLUSTAL";
-
+ reply = FileFormat.MMCif;
break;
}
-
-
- else if (data.indexOf(">") > -1)
+ // if (data.indexOf(">") > -1)
+ if (data.startsWith(">"))
{
// FASTA, PIR file or BLC file
boolean checkPIR = false, starterm = false;
@@ -179,14 +191,14 @@ public class IdentifyFile
{
// watch for PIR file attributes
checkPIR = true;
- reply = "PIR";
+ reply = FileFormat.PIR;
}
// could also be BLC file, read next line to confirm
data = source.nextLine();
if (data.indexOf(">") > -1)
{
- reply = "BLC";
+ reply = FileFormat.BLC;
}
else
{
@@ -199,19 +211,23 @@ 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 = FileFormat.BLC;
+ }
+ else
{
- reply = "BLC";
- } else {
- reply = "FASTA"; // possibly a bad choice - may be recognised as PIR
+ reply = FileFormat.Fasta; // possibly a bad choice - may be
+ // recognised as
+ // PIR
}
// otherwise can still possibly be a PIR file
}
else
{
- reply = "FASTA";
+ reply = FileFormat.Fasta;
// TODO : AMSA File is indicated if there is annotation in the
// FASTA file - but FASTA will automatically generate this at the
// mo.
@@ -240,7 +256,6 @@ public class IdentifyFile
} catch (IOException ex)
{
}
- ;
if (dta != null && dta.indexOf("*") > -1)
{
starterm = true;
@@ -249,39 +264,84 @@ public class IdentifyFile
}
if (starterm)
{
- reply = "PIR";
+ reply = FileFormat.PIR;
break;
}
else
{
- reply = "FASTA"; // probably a bad choice!
+ reply = FileFormat.Fasta; // probably a bad choice!
}
}
// read as a FASTA (probably)
break;
}
+ int lessThan = data.indexOf("<");
+ if ((lessThan > -1)) // possible Markup Language data i.e HTML,
+ // RNAML, XML
+ {
+ String upper = data.toUpperCase();
+ if (upper.substring(lessThan).startsWith(" -1)
+ {
+ reply = FileFormat.Json;
+ break;
+ }
+ if ((data.length() < 1) || (data.indexOf("#") == 0))
+ {
+ lineswereskipped = true;
+ continue;
+ }
+
+ if (data.indexOf("PILEUP") > -1)
+ {
+ reply = FileFormat.Pileup;
+
+ break;
+ }
+
+ if ((data.indexOf("//") == 0) || ((data.indexOf("!!") > -1) && (data
+ .indexOf("!!") < data.indexOf("_MULTIPLE_ALIGNMENT "))))
+ {
+ reply = FileFormat.MSF;
+
+ break;
+ }
+ else if (data.indexOf("CLUSTAL") > -1)
+ {
+ reply = FileFormat.Clustal;
+
+ break;
+ }
+
else if (data.indexOf("HEADER") == 0 || data.indexOf("ATOM") == 0)
{
- reply = "PDB";
+ reply = FileFormat.PDB;
break;
}
- /*
- * // TODO comment out SimpleBLAST identification for Jalview 2.4.1 else
- * if (!lineswereskipped && data.indexOf("BLAST")<4) { reply =
- * "SimpleBLAST"; break;
- *
- * } // end comments for Jalview 2.4.1
- */
- else if (!lineswereskipped && data.charAt(0) != '*'
- && data.charAt(0) != ' '
- && data.indexOf(":") < data.indexOf(",")) // &&
- // data.indexOf(",") -1
+ && commaPos > -1 && colonPos < commaPos;
+ // && data.indexOf(",")