X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fio%2FIdentifyFile.java;h=d2c586a2fac2b401f057a630d2fafb6a9ea4dd6a;hb=4a3def9f59cefe629c9a33d87483283aee085928;hp=0556e76a20248be0a0ad19fc9e92eaeb4a255689;hpb=35ce4609cc8a776b1d85a1f2c2c70aaa106c1a3b;p=jalview.git diff --git a/src/jalview/io/IdentifyFile.java b/src/jalview/io/IdentifyFile.java index 0556e76..d2c586a 100755 --- a/src/jalview/io/IdentifyFile.java +++ b/src/jalview/io/IdentifyFile.java @@ -20,6 +20,9 @@ */ package jalview.io; +import java.util.Locale; + +import java.io.File; import java.io.IOException; /** @@ -30,6 +33,42 @@ import java.io.IOException; */ public class IdentifyFile { + + public FileFormatI identify(Object file, DataSourceType protocol) + throws FileFormatException + { + // BH 2018 + return (file instanceof File ? identify((File) file, protocol) + : identify((String) file, protocol)); + + } + + public FileFormatI identify(File file, DataSourceType sourceType) + throws FileFormatException + { + // BH 2018 + String emessage = "UNIDENTIFIED FILE PARSING ERROR"; + FileParse parser = null; + try + { + parser = new FileParse(file, sourceType); + if (parser.isValid()) + { + return identify(parser); + } + } catch (Exception e) + { + System.err.println("Error whilst identifying " + file); + e.printStackTrace(System.err); + emessage = e.getMessage(); + } + if (parser != null) + { + throw new FileFormatException(parser.errormessage); + } + throw new FileFormatException(emessage); + } + /** * Identify a datasource's file content. * @@ -55,7 +94,7 @@ public class IdentifyFile } } catch (Exception e) { - System.err.println("Error whilst identifying"); + System.err.println("Error whilst identifying " + file); e.printStackTrace(System.err); emessage = e.getMessage(); } @@ -72,10 +111,11 @@ public class IdentifyFile // preserves original behaviour prior to version 2.3 } - public FileFormatI identify(AlignmentFileReaderI file, boolean closeSource) - throws IOException + public FileFormatI identify(AlignmentFileReaderI file, + boolean closeSource) throws IOException { - FileParse fp = new FileParse(file.getInFile(), file.getDataSourceType()); + FileParse fp = new FileParse(file.getInFile(), + file.getDataSourceType()); return identify(fp, closeSource); } @@ -98,12 +138,15 @@ public class IdentifyFile 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) { bytesRead += data.length(); @@ -126,21 +169,48 @@ public class IdentifyFile if (source.inFile != null) { String fileStr = source.inFile.getName(); - // possibly a Jalview archive. - if (fileStr.lastIndexOf(".jar") > -1 - || fileStr.lastIndexOf(".zip") > -1) + if (fileStr.contains(".jar") || fileStr.contains(".zip") + || fileStr.contains(".jvp")) { + // possibly a Jalview archive (but check further) reply = FileFormat.Jalview; } } if (!lineswereskipped && data.startsWith("PK")) { - reply = FileFormat.Jalview; // archive. + reply = FileFormat.Jalview; // archive break; } } - data = data.toUpperCase(); + data = data.toUpperCase(Locale.ROOT); + if (data.startsWith(ScoreMatrixFile.SCOREMATRIX)) + { + reply = FileFormat.ScoreMatrix; + break; + } + if (data.startsWith("LOCUS")) + { + reply = FileFormat.GenBank; + break; + } + if (data.startsWith("ID ")) + { + if (data.substring(2).trim().split(";").length == 7) + { + reply = FileFormat.Embl; + break; + } + } + if (data.startsWith("H ") && !aaIndexHeaderRead) + { + aaIndexHeaderRead = true; + } + if (data.startsWith("D ") && aaIndexHeaderRead) + { + reply = FileFormat.ScoreMatrix; + break; + } if (data.startsWith("##GFF-VERSION")) { // GFF - possibly embedded in a Jalview features file! @@ -257,11 +327,16 @@ public class IdentifyFile // read as a FASTA (probably) break; } + if (data.indexOf("{\"") > -1) + { + reply = FileFormat.Json; + break; + } int lessThan = data.indexOf("<"); if ((lessThan > -1)) // possible Markup Language data i.e HTML, // RNAML, XML { - String upper = data.toUpperCase(); + String upper = data.toUpperCase(Locale.ROOT); if (upper.substring(lessThan).startsWith(" -1) - { - reply = FileFormat.Json; - break; - } if ((data.length() < 1) || (data.indexOf("#") == 0)) { lineswereskipped = true; @@ -292,9 +362,8 @@ public class IdentifyFile 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 = FileFormat.MSF; @@ -317,15 +386,33 @@ public class IdentifyFile reply = FileFormat.Phylip; break; } - else + else if (!lineswereskipped && looksLikeJnetData(data)) { - if (!lineswereskipped && looksLikeJnetData(data)) - { reply = FileFormat.Jnet; break; - } + } + else // phylogenetic file + { + String identifier = data.toLowerCase(); + String secondLine = source.nextLine().toLowerCase(); + if (identifier.startsWith(" [ ...]"); } } + }