/*
- * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8.2b1)
- * Copyright (C) 2014 The Jalview Authors
+ * Jalview - A Sequence Alignment Editor and Viewer (Version 2.9.0b1)
+ * Copyright (C) 2015 The Jalview Authors
*
* This file is part of Jalview.
*
*/
public class IdentifyFile
{
+ public static final String GFF3File = "GFF v2 or v3";
+
/**
* Identify a datasource's file content.
*
}
while ((data = source.nextLine()) != null)
{
- length += data.length();
+ length += data.trim().length();
if (!lineswereskipped)
{
for (int i = 0; !isBinary && i < data.length(); i++)
}
data = data.toUpperCase();
- if ((data.indexOf("# STOCKHOLM") > -1))
- {
- reply = "STH";
-
- break;
- }
- // if (data.matches("<(\"[^\"]*\"|'[^']*'|[^'\">])*>"))
- if (data.matches("<(?i)html(\"[^\"]*\"|'[^']*'|[^'\">])*>"))
- {
- reply = "HTML";
- break;
- }
-
- if (data.matches("<(?i)rnaml (\"[^\"]*\"|'[^']*'|[^'\">])*>"))
- {
- 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;
// 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;
+ 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;
}
-
/*
* // 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(",")))
+ // data.indexOf(",")<data.indexOf(",",
+ // data.indexOf(",")))
{
// file looks like a concise JNet file
reply = "JnetFile";
if (length == 0)
{
System.err
- .println("File Identification failed! - Empty file was read.");
+ .println("File Identification failed! - Empty file was read.");
return "EMPTY DATA FILE";
}
return reply;