X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fio%2FIdentifyFile.java;h=f8d8415bf749474734b9a195015cfd728b9a8c38;hb=4815037f13748676b04b91dc761b73cf6f2d6ecd;hp=bf5f66551cafce3e1e5bc21ecbc9b245e3cbc5bc;hpb=539476a37ccaae7b2b665c9f9ccc817320582781;p=jalview.git diff --git a/src/jalview/io/IdentifyFile.java b/src/jalview/io/IdentifyFile.java index bf5f665..f8d8415 100755 --- a/src/jalview/io/IdentifyFile.java +++ b/src/jalview/io/IdentifyFile.java @@ -1,29 +1,30 @@ /* - * Jalview - A Sequence Alignment Editor and Viewer (Development Version 2.4.1) - * Copyright (C) 2009 AM Waterhouse, J Procter, G Barton, M Clamp, S Searle - * - * This program is free software; you can redistribute it and/or + * 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 - * 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 . + * The Jalview Authors are detailed in the 'AUTHORS' file. */ package jalview.io; -import java.io.*; -import java.net.*; +import java.io.IOException; /** * DOCUMENT ME! - * + * * @author $author$ * @version $Revision$ */ @@ -31,26 +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) { @@ -59,32 +60,44 @@ 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(AlignmentFileI 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 + // characters are encountered try { if (!closeSource) @@ -93,7 +106,8 @@ public class IdentifyFile } 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++) @@ -101,8 +115,8 @@ public class IdentifyFile 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 + // excluding CR, LF, tab,DEL and ^E + // for certain blast ids } } if (isBinary) @@ -116,120 +130,204 @@ 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("##GFF-VERSION")) { - reply = "STH"; - + // GFF - possibly embedded in a Jalview features file! + reply = FileFormat.Features; break; } - - if ((data.length() < 1) || (data.indexOf("#") == 0)) - { - lineswereskipped = true; - continue; - } - - 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; + boolean checkPIR = false, starterm = false; if ((data.indexOf(">P1;") > -1) || (data.indexOf(">DL;") > -1)) { // 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 { // Is this a single line BLC file? - source.nextLine(); + String data1 = source.nextLine(); String data2 = source.nextLine(); - if (data2 != null && data.indexOf("*") > -1) + int c1; + if (checkPIR) + { + starterm = (data1 != null && data1.indexOf("*") > -1) + || (data2 != null && data2.indexOf("*") > -1); + } + if (data2 != null && (c1 = data.indexOf("*")) > -1) { - if (data.indexOf("*") == data2.indexOf("*")) + if (c1 == 0 && c1 == data2.indexOf("*")) + { + reply = FileFormat.BLC; + } + else { - reply = "BLC"; + 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. + if (!checkPIR) + { + break; + } + } + } + // final check for PIR content. require + // >P1;title\n\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 = FileFormat.PIR; break; } + else + { + reply = FileFormat.Fasta; // probably a bad choice! + } } - // TODO final check for PIR content. require >P1;title\n\nterminated sequence to occur at least once. - // the PIR/fasta ambiguity may be the use case that is needed to have a 'Parse as type XXX' parameter for the applet/application. + // read as a FASTA (probably) break; } - else if (data.indexOf("HEADER") == 0 || data.indexOf("ATOM") == 0) + 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 = "PDB"; + reply = FileFormat.Json; break; } - // TODO comment out SimpleBLAST identification for Jalview 2.4.1 - else if (!lineswereskipped && data.indexOf("BLAST")<4) + 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 = "SimpleBLAST"; + reply = FileFormat.MSF; + break; - } - // end comments for Jalview 2.4.1 - else if (!lineswereskipped && data.charAt(0) != '*' - && data.charAt(0) != ' ' - && data.indexOf(":") < data.indexOf(",")) // && - // data.indexOf(",") -1) { - // file looks like a concise JNet file - reply = "JnetFile"; + reply = FileFormat.Clustal; + break; } + else if (data.indexOf("HEADER") == 0 || data.indexOf("ATOM") == 0) + { + reply = FileFormat.PDB; + break; + } + else if (data.matches("\\s*\\d+\\s+\\d+\\s*")) + { + reply = FileFormat.Phylip; + break; + } + else + { + if (!lineswereskipped && looksLikeJnetData(data)) + { + reply = FileFormat.Jnet; + break; + } + } + lineswereskipped = true; // this means there was some junk before any - // key file signature + // key file signature } if (closeSource) { @@ -237,28 +335,82 @@ public class IdentifyFile } else { - source.reset(); // so the file can be parsed from the beginning again. + source.reset(bytesRead); // so the file can be parsed from the mark } } catch (Exception ex) { System.err.println("File Identification failed!\n" + ex); - return source.errormessage; + throw new FileFormatException(source.errormessage); } - if (length == 0) + if (trimmedLength == 0) { System.err .println("File Identification failed! - Empty file was read."); - return "EMPTY DATA FILE"; + throw new FileFormatException("EMPTY DATA FILE"); } + System.out.println("File format identified as " + reply.toString()); return reply; } + /** + * Returns true if the data appears to be Jnet concise annotation format + * + * @param data + * @return + */ + protected boolean looksLikeJnetData(String data) + { + char firstChar = data.charAt(0); + int colonPos = data.indexOf(":"); + int commaPos = data.indexOf(","); + boolean isJnet = firstChar != '*' && firstChar != ' ' && colonPos > -1 + && commaPos > -1 && colonPos < commaPos; + // && data.indexOf(",")