/*
- * Jalview - A Sequence Alignment Editor and Viewer
- * Copyright (C) 2007 AM Waterhouse, J Procter, G Barton, M Clamp, S Searle
+ * Jalview - A Sequence Alignment Editor and Viewer (Version 2.9.0b2)
+ * Copyright (C) 2015 The Jalview Authors
*
- * This program is free software; you can redistribute it and/or
+ * 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 2
+ * as published by the Free Software Foundation, either version 3
* of the License, or (at your option) any later version.
*
- * This program 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.
+ * 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 this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA
+ * 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.net.*;
+import java.io.IOException;
/**
* DOCUMENT ME!
*/
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.
+ * Identify a datasource's file content.
*
- * @param file DOCUMENT ME!
- * @param protocol DOCUMENT ME!
+ * @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
*/
public String Identify(String file, String protocol)
{
+ String emessage = "UNIDENTIFIED FILE PARSING ERROR";
FileParse parser = null;
- try {
+ try
+ {
parser = new FileParse(file, protocol);
- if (parser.isValid()) {
+ if (parser.isValid())
+ {
return Identify(parser);
}
- } catch (Exception e) {
+ } catch (Exception e)
+ {
System.err.println("Error whilst identifying");
e.printStackTrace(System.err);
+ emessage = e.getMessage();
}
- if (parser!=null)
+ if (parser != null)
+ {
return parser.errormessage;
- return "UNIDENTIFIED FILE PARSING ERROR";
+ }
+ return emessage;
}
- public String Identify(FileParse source) {
- return Identify(source, true); // preserves original behaviour prior to version 2.3
+
+ public String Identify(FileParse source)
+ {
+ return Identify(source, true); // preserves original behaviour prior to
+ // version 2.3
}
+
/**
- * Identify contents of source, closing it or resetting source to start afterwards.
+ * Identify contents of source, closing it or resetting source to start
+ * afterwards.
+ *
* @param source
* @param closeSource
* @return filetype string
*/
- public String Identify(FileParse source, boolean closeSource) {
+ public String Identify(FileParse source, boolean closeSource)
+ {
String reply = "PFAM";
String data;
- int length=0;
- boolean lineswereskipped=false;
- boolean isBinary = false; // true if length is non-zero and non-printable characters are encountered
- try {
- while ( (data = source.nextLine()) != null)
+ int length = 0;
+ boolean lineswereskipped = false;
+ boolean isBinary = false; // true if length is non-zero and non-printable
+ // characters are encountered
+ try
+ {
+ if (!closeSource)
{
- length+=data.length();
+ source.mark();
+ }
+ while ((data = source.nextLine()) != null)
+ {
+ length += data.trim().length();
if (!lineswereskipped)
{
- for (int i=0;!isBinary && i<data.length(); i++)
+ for (int i = 0; !isBinary && i < data.length(); i++)
{
char c = data.charAt(i);
- isBinary = (c<32 && c!='\t' && c!='\n' && c!='\r' && c!=5 && c!=27); // nominal binary character filter excluding CR, LF, tab,DEL and ^E for certain blast ids
+ isBinary = (c < 32 && c != '\t' && c != '\n' && c != '\r'
+ && c != 5 && c != 27); // nominal binary character filter
+ // excluding CR, LF, tab,DEL and ^E
+ // for certain blast ids
}
}
if (isBinary)
{
- // jar files are special - since they contain all sorts of random characters.
- if (source.inFile!=null)
+ // jar files are special - since they contain all sorts of random
+ // characters.
+ if (source.inFile != null)
{
- String fileStr=source.inFile.getName();
- // possibly a Jalview archive.
- if (fileStr.lastIndexOf(".jar")>-1 || fileStr.lastIndexOf(".zip")>-1)
- {
- reply = "Jalview";
- }
- }
- if (!lineswereskipped && data.startsWith("PK")) {
- reply="Jalview"; // archive.
+ String fileStr = source.inFile.getName();
+ // possibly a Jalview archive.
+ if (fileStr.lastIndexOf(".jar") > -1
+ || fileStr.lastIndexOf(".zip") > -1)
+ {
+ reply = "Jalview";
+ }
+ }
+ if (!lineswereskipped && data.startsWith("PK"))
+ {
+ reply = "Jalview"; // archive.
break;
}
}
data = data.toUpperCase();
- if ( (data.indexOf("# STOCKHOLM") > -1))
+ if (data.startsWith("##GFF-VERSION"))
+ {
+ reply = GFF3File;
+ break;
+ }
+ if (data.indexOf("# STOCKHOLM") > -1)
{
reply = "STH";
+ break;
+ }
+ // if (data.indexOf(">") > -1)
+ if (data.startsWith(">"))
+ {
+ // FASTA, PIR file or BLC file
+ boolean checkPIR = false, starterm = false;
+ if ((data.indexOf(">P1;") > -1) || (data.indexOf(">DL;") > -1))
+ {
+ // watch for PIR file attributes
+ checkPIR = true;
+ reply = "PIR";
+ }
+ // could also be BLC file, read next line to confirm
+ data = source.nextLine();
+ if (data.indexOf(">") > -1)
+ {
+ reply = "BLC";
+ }
+ else
+ {
+ // Is this a single line BLC file?
+ String data1 = source.nextLine();
+ String data2 = source.nextLine();
+ int c1;
+ if (checkPIR)
+ {
+ starterm = (data1 != null && data1.indexOf("*") > -1)
+ || (data2 != null && data2.indexOf("*") > -1);
+ }
+ if (data2 != null && (c1 = data.indexOf("*")) > -1)
+ {
+ if (c1 == 0 && c1 == data2.indexOf("*"))
+ {
+ reply = "BLC";
+ }
+ else
+ {
+ reply = "FASTA"; // possibly a bad choice - may be recognised as
+ // PIR
+ }
+ // otherwise can still possibly be a PIR file
+ }
+ else
+ {
+ reply = "FASTA";
+ // TODO : AMSA File is indicated if there is annotation in the
+ // FASTA file - but FASTA will automatically generate this at the
+ // mo.
+ if (!checkPIR)
+ {
+ break;
+ }
+ }
+ }
+ // final check for PIR content. require
+ // >P1;title\n<blah>\nterminated sequence to occur at least once.
+
+ // TODO the PIR/fasta ambiguity may be the use case that is needed to
+ // have
+ // a 'Parse as type XXX' parameter for the applet/application.
+ if (checkPIR)
+ {
+ String dta = null;
+ if (!starterm)
+ {
+ do
+ {
+ try
+ {
+ dta = source.nextLine();
+ } catch (IOException ex)
+ {
+ }
+ ;
+ if (dta != null && dta.indexOf("*") > -1)
+ {
+ starterm = true;
+ }
+ } while (dta != null && !starterm);
+ }
+ if (starterm)
+ {
+ reply = "PIR";
+ break;
+ }
+ else
+ {
+ reply = "FASTA"; // probably a bad choice!
+ }
+ }
+ // 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 == null)
+ {
+ break;
+ }
+ }
+ if (data.indexOf("{\"") > -1)
+ {
+ reply = JSONFile.FILE_DESC;
+ break;
+ }
if ((data.length() < 1) || (data.indexOf("#") == 0))
{
- lineswereskipped=true;
+ lineswereskipped = true;
continue;
}
break;
}
- if ( (data.indexOf("//") == 0) ||
- ( (data.indexOf("!!") > -1) &&
- (data.indexOf("!!") < data.indexOf(
- "_MULTIPLE_ALIGNMENT "))))
+ if ((data.indexOf("//") == 0)
+ || ((data.indexOf("!!") > -1) && (data.indexOf("!!") < data
+ .indexOf("_MULTIPLE_ALIGNMENT "))))
{
reply = "MSF";
break;
}
- else if ( (data.indexOf(">P1;") > -1) ||
- (data.indexOf(">DL;") > -1))
- {
- reply = "PIR";
- break;
- }
- else if (data.indexOf(">") > -1)
+ else if (data.indexOf("HEADER") == 0 || data.indexOf("ATOM") == 0)
{
- // could be BLC file, read next line to confirm
- data = source.nextLine();
-
- if (data.indexOf(">") > -1)
- {
- reply = "BLC";
- }
- else
- {
- //Is this a single line BLC file?
- source.nextLine();
- String data2 = source.nextLine();
- if (data2 != null
- && data.indexOf("*") > -1
- && data.indexOf("*") == data2.indexOf("*"))
- {
- reply = "BLC";
- }
- else
- {
- reply = "FASTA";
- }
- }
+ reply = "PDB";
break;
}
- else if (data.indexOf("HEADER") == 0 ||
- data.indexOf("ATOM") == 0)
+ else if (data.matches("\\s*\\d+\\s+\\d+\\s*"))
{
- reply = "PDB";
+ reply = PhylipFile.FILE_DESC;
break;
}
- else if (!lineswereskipped
- && data.charAt(0)!='*'
- && data.charAt(0)!=' '
- && data.indexOf(":") < data.indexOf(",")) // && data.indexOf(",")<data.indexOf(",", data.indexOf(",")))
+
+ /*
+ * // 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(",")<data.indexOf(",",
+ // data.indexOf(",")))
{
// file looks like a concise JNet file
reply = "JnetFile";
break;
}
-
- lineswereskipped=true; // this means there was some junk before any key file signature
+
+ lineswereskipped = true; // this means there was some junk before any
+ // key file signature
}
- if (closeSource) {
+ if (closeSource)
+ {
source.close();
- } else {
+ }
+ else
+ {
source.reset(); // so the file can be parsed from the beginning again.
}
- }
- catch (Exception ex)
+ } catch (Exception ex)
{
System.err.println("File Identification failed!\n" + ex);
return source.errormessage;
}
- if (length==0)
+ if (length == 0)
{
- System.err.println("File Identification failed! - Empty file was read.");
+ System.err
+ .println("File Identification failed! - Empty file was read.");
return "EMPTY DATA FILE";
}
return reply;
}
- public static void main(String[] args) {
- for (int i=0; args!=null && i<args.length; i++)
+
+ public static void main(String[] args)
+ {
+
+ for (int i = 0; args != null && i < args.length; i++)
{
IdentifyFile ider = new IdentifyFile();
String type = ider.Identify(args[i], AppletFormatAdapter.FILE);
- System.out.println("Type of "+args[i]+" is "+type);
+ System.out.println("Type of " + args[i] + " is " + type);
}
- if (args==null || args.length==0)
+ if (args == null || args.length == 0)
{
System.err.println("Usage: <Filename> [<Filename> ...]");
}
git://source.jalview.org / jalview.git / blobdiff