2 // FORESTER -- software libraries and applications
3 // for evolutionary biology research and applications.
5 // Copyright (C) 2008-2009 Christian M. Zmasek
6 // Copyright (C) 2008-2009 Burnham Institute for Medical Research
9 // This library is free software; you can redistribute it and/or
10 // modify it under the terms of the GNU Lesser General Public
11 // License as published by the Free Software Foundation; either
12 // version 2.1 of the License, or (at your option) any later version.
14 // This library is distributed in the hope that it will be useful,
15 // but WITHOUT ANY WARRANTY; without even the implied warranty of
16 // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
17 // Lesser General Public License for more details.
19 // You should have received a copy of the GNU Lesser General Public
20 // License along with this library; if not, write to the Free Software
21 // Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA
23 // Contact: phylosoft @ gmail . com
24 // WWW: https://sites.google.com/site/cmzmasek/home/software/forester
26 package org.forester.io.parsers.phyloxml;
28 import java.util.HashSet;
30 import java.util.regex.Pattern;
32 import org.forester.io.parsers.util.ParserUtils;
34 public final class PhyloXmlUtil {
36 public final static Pattern SEQUENCE_SYMBOL_PATTERN = Pattern.compile( "\\S{1,20}" );
37 public final static Pattern TAXOMONY_CODE_PATTERN = Pattern
38 .compile( ParserUtils.TAX_CODE );
39 public final static Pattern LIT_REF_DOI_PATTERN = Pattern
40 .compile( "[a-zA-Z0-9_\\.]+\\S+" );
41 public final static Set<String> SEQUENCE_TYPES = new HashSet<String>();
42 public static final int ROUNDING_DIGITS_FOR_PHYLOXML_DOUBLE_OUTPUT = 9;
43 public static final String VECTOR_PROPERTY_REF = "vector:index=";
44 public static final String VECTOR_PROPERTY_TYPE = "xsd:decimal";
45 public static final String UNIPROT_TAX_PROVIDER = "uniprot";
46 public static final String SEQ_TYPE_RNA = "rna";
47 public static final String SEQ_TYPE_DNA = "dna";
48 public static final String SEQ_TYPE_PROTEIN = "protein";
50 SEQUENCE_TYPES.add( SEQ_TYPE_RNA );
51 SEQUENCE_TYPES.add( SEQ_TYPE_PROTEIN );
52 SEQUENCE_TYPES.add( SEQ_TYPE_DNA );