From: cmzmasek@gmail.com <cmzmasek@gmail.com@ca865154-3058-d1c3-3e42-d8f55a55bdbd>
Date: Mon, 30 Sep 2013 22:50:23 +0000 (+0000)
Subject: inprogress
X-Git-Url: http://source.jalview.org/gitweb/?a=commitdiff_plain;h=54f2b7c44d8829036bc85a2a21136451096c1204;p=jalview.git

inprogress
---

diff --git a/forester/resources/phyloxml_schema/1.10/phyloxml.xsd b/forester/resources/phyloxml_schema/1.10/phyloxml.xsd
index 525bc69..5512426 100644
--- a/forester/resources/phyloxml_schema/1.10/phyloxml.xsd
+++ b/forester/resources/phyloxml_schema/1.10/phyloxml.xsd
@@ -16,7 +16,7 @@
 <!--                                                             -->
 <!-- www.phyloxml.org                                            -->
 <!-- Version: 1.16                                               -->
-<!-- Last modified: 2013.09.29 by Christian M Zmasek             -->
+<!-- Last modified: 2013.09.30 by Christian  Zmasek              -->
 <!--                                                             -->
 <xs:schema xmlns:xs="http://www.w3.org/2001/XMLSchema" xmlns:phy="http://www.phyloxml.org"
    targetNamespace="http://www.phyloxml.org" elementFormDefault="qualified" attributeFormDefault="unqualified">
@@ -192,17 +192,18 @@
    <xs:complexType name="Sequence">
       <xs:annotation>
          <xs:documentation> Element Sequence is used to represent a molecular sequence (Protein, DNA, RNA) associated
-            with a node. 'symbol' is a short (maximal 30 characters) symbol of the sequence (e.g. 'ACTM') whereas
-            'name' is used for the full name (e.g. 'muscle Actin'). 'location' is used for the location of a sequence on
-            a genome/chromosome. The actual sequence can be stored with the 'mol_seq' element. Attribute 'type' is used
-            to indicate the type of sequence ('dna', 'rna', or 'protein'). One intended use for 'id_ref' is to link a
-            sequence to a taxonomy (via the taxonomy's 'id_source') in case of multiple sequences and taxonomies per
-            node. </xs:documentation>
+            with a node. 'symbol' is a short (maximal 20 characters) symbol of the sequence (e.g. 'ACTM') whereas
+            'name' is used for the full name (e.g. 'muscle Actin'). 'gene_name' can be used when protein and gene names differ.
+            'location' is used for the location of a sequence on a genome/chromosome. The actual sequence can be stored with the 
+            'mol_seq' element. Attribute 'type' is used to indicate the type of sequence ('dna', 'rna', or 'protein'). 
+            One intended use for 'id_ref' is to link a sequence to a taxonomy (via the taxonomy's 'id_source') in case 
+            of multiple sequences and taxonomies per node. </xs:documentation>
       </xs:annotation>
       <xs:sequence>
          <xs:element name="symbol" type="phy:SequenceSymbol" minOccurs="0"/>
          <xs:element name="accession" type="phy:Accession" minOccurs="0"/>
          <xs:element name="name" type="xs:token" minOccurs="0"/>
+         <xs:element name="gene_name" type="xs:token" minOccurs="0"/>
          <xs:element name="location" type="xs:token" minOccurs="0"/>
          <xs:element name="mol_seq" type="phy:MolSeq" minOccurs="0"/>
          <xs:element name="uri" type="phy:Uri" minOccurs="0" maxOccurs="unbounded"/>
@@ -217,7 +218,7 @@
    </xs:complexType>
    <xs:simpleType name="SequenceSymbol">
       <xs:restriction base="xs:token">
-         <xs:pattern value="\S{1,30}"/>
+         <xs:pattern value="\S{1,20}"/>
       </xs:restriction>
    </xs:simpleType>
    <xs:complexType name="MolSeq">
@@ -249,6 +250,7 @@
       <xs:simpleContent>
          <xs:extension base="xs:token">
             <xs:attribute name="source" type="xs:token" use="required"/>
+            <xs:attribute name="comment" type="xs:token"/>
          </xs:extension>
       </xs:simpleContent>
    </xs:complexType>