2 * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
3 * Copyright (C) $$Year-Rel$$ The Jalview Authors
5 * This file is part of Jalview.
7 * Jalview is free software: you can redistribute it and/or
8 * modify it under the terms of the GNU General Public License
9 * as published by the Free Software Foundation, either version 3
10 * of the License, or (at your option) any later version.
12 * Jalview is distributed in the hope that it will be useful, but
13 * WITHOUT ANY WARRANTY; without even the implied warranty
14 * of MERCHANTABILITY or FITNESS FOR A PARTICULAR
15 * PURPOSE. See the GNU General Public License for more details.
17 * You should have received a copy of the GNU General Public License
18 * along with Jalview. If not, see <http://www.gnu.org/licenses/>.
19 * The Jalview Authors are detailed in the 'AUTHORS' file.
23 import java.io.IOException;
31 public class IdentifyFile
33 public static final String FeaturesFile = "GFF or Jalview features";
36 * Identify a datasource's file content.
38 * @note Do not use this method for stream sources - create a FileParse object
47 public String identify(String file, String protocol)
49 String emessage = "UNIDENTIFIED FILE PARSING ERROR";
50 FileParse parser = null;
53 parser = new FileParse(file, protocol);
56 return identify(parser);
60 System.err.println("Error whilst identifying");
61 e.printStackTrace(System.err);
62 emessage = e.getMessage();
66 return parser.errormessage;
71 public String identify(FileParse source)
73 return identify(source, true); // preserves original behaviour prior to
78 * Identify contents of source, closing it or resetting source to start
83 * @return filetype string
85 public String identify(FileParse source, boolean closeSource)
87 String reply = "PFAM";
90 int trimmedLength = 0;
91 boolean lineswereskipped = false;
92 boolean isBinary = false; // true if length is non-zero and non-printable
93 // characters are encountered
100 while ((data = source.nextLine()) != null)
102 bytesRead += data.length();
103 trimmedLength += data.trim().length();
104 if (!lineswereskipped)
106 for (int i = 0; !isBinary && i < data.length(); i++)
108 char c = data.charAt(i);
109 isBinary = (c < 32 && c != '\t' && c != '\n' && c != '\r'
110 && c != 5 && c != 27); // nominal binary character filter
111 // excluding CR, LF, tab,DEL and ^E
112 // for certain blast ids
117 // jar files are special - since they contain all sorts of random
119 if (source.inFile != null)
121 String fileStr = source.inFile.getName();
122 // possibly a Jalview archive.
123 if (fileStr.lastIndexOf(".jar") > -1
124 || fileStr.lastIndexOf(".zip") > -1)
129 if (!lineswereskipped && data.startsWith("PK"))
131 reply = "Jalview"; // archive.
135 data = data.toUpperCase();
137 if (data.startsWith("##GFF-VERSION"))
139 // GFF - possibly embedded in a Jalview features file!
140 reply = FeaturesFile;
143 if (looksLikeFeatureData(data))
145 reply = FeaturesFile;
148 if (data.indexOf("# STOCKHOLM") > -1)
153 // if (data.indexOf(">") > -1)
154 if (data.startsWith(">"))
156 // FASTA, PIR file or BLC file
157 boolean checkPIR = false, starterm = false;
158 if ((data.indexOf(">P1;") > -1) || (data.indexOf(">DL;") > -1))
160 // watch for PIR file attributes
164 // could also be BLC file, read next line to confirm
165 data = source.nextLine();
167 if (data.indexOf(">") > -1)
173 // Is this a single line BLC file?
174 String data1 = source.nextLine();
175 String data2 = source.nextLine();
179 starterm = (data1 != null && data1.indexOf("*") > -1)
180 || (data2 != null && data2.indexOf("*") > -1);
182 if (data2 != null && (c1 = data.indexOf("*")) > -1)
184 if (c1 == 0 && c1 == data2.indexOf("*"))
190 reply = "FASTA"; // possibly a bad choice - may be recognised as
193 // otherwise can still possibly be a PIR file
198 // TODO : AMSA File is indicated if there is annotation in the
199 // FASTA file - but FASTA will automatically generate this at the
207 // final check for PIR content. require
208 // >P1;title\n<blah>\nterminated sequence to occur at least once.
210 // TODO the PIR/fasta ambiguity may be the use case that is needed to
212 // a 'Parse as type XXX' parameter for the applet/application.
222 dta = source.nextLine();
223 } catch (IOException ex)
227 if (dta != null && dta.indexOf("*") > -1)
231 } while (dta != null && !starterm);
240 reply = "FASTA"; // probably a bad choice!
243 // read as a FASTA (probably)
246 if ((data.indexOf("<") > -1)) // possible Markup Language data i.e HTML,
249 // FIXME this is nuts - it consumes the rest of the file if no match
250 boolean identified = false;
253 if (data.matches("<(?i)html(\"[^\"]*\"|'[^']*'|[^'\">])*>"))
255 reply = HtmlFile.FILE_DESC;
260 if (data.matches("<(?i)rnaml (\"[^\"]*\"|'[^']*'|[^'\">])*>"))
266 } while ((data = source.nextLine()) != null);
278 if (data.indexOf("{\"") > -1)
280 reply = JSONFile.FILE_DESC;
283 if ((data.length() < 1) || (data.indexOf("#") == 0))
285 lineswereskipped = true;
289 if (data.indexOf("PILEUP") > -1)
296 if ((data.indexOf("//") == 0)
297 || ((data.indexOf("!!") > -1) && (data.indexOf("!!") < data
298 .indexOf("_MULTIPLE_ALIGNMENT "))))
304 else if (data.indexOf("CLUSTAL") > -1)
311 else if (data.indexOf("HEADER") == 0 || data.indexOf("ATOM") == 0)
316 else if (data.matches("\\s*\\d+\\s+\\d+\\s*"))
318 reply = PhylipFile.FILE_DESC;
323 if (!lineswereskipped && looksLikeJnetData(data))
330 lineswereskipped = true; // this means there was some junk before any
331 // key file signature
339 source.reset(bytesRead); // so the file can be parsed from the mark
341 } catch (Exception ex)
343 System.err.println("File Identification failed!\n" + ex);
344 return source.errormessage;
346 if (trimmedLength == 0)
349 .println("File Identification failed! - Empty file was read.");
350 return "EMPTY DATA FILE";
356 * Returns true if the data appears to be Jnet concise annotation format
361 protected boolean looksLikeJnetData(String data)
363 char firstChar = data.charAt(0);
364 int colonPos = data.indexOf(":");
365 int commaPos = data.indexOf(",");
366 boolean isJnet = firstChar != '*' && firstChar != ' ' && colonPos > -1
367 && commaPos > -1 && colonPos < commaPos;
368 // && data.indexOf(",")<data.indexOf(",", data.indexOf(","))) / ??
373 * Returns true if the data has at least 6 tab-delimited fields _and_
374 * fields 4 and 5 are integer (start/end)
378 protected boolean looksLikeFeatureData(String data)
384 String[] columns = data.split("\t");
385 if (columns.length < 6) {
388 for (int col = 3; col < 5; col++)
391 Integer.parseInt(columns[col]);
392 } catch (NumberFormatException e) {
399 public static void main(String[] args)
402 for (int i = 0; args != null && i < args.length; i++)
404 IdentifyFile ider = new IdentifyFile();
405 String type = ider.identify(args[i], AppletFormatAdapter.FILE);
406 System.out.println("Type of " + args[i] + " is " + type);
408 if (args == null || args.length == 0)
410 System.err.println("Usage: <Filename> [<Filename> ...]");