Fix for bug 2788; allow internal node labels on taxonomies in Nexus f…

…iles.

Bio/Nexus/Trees.py

@@ -53,18 +53,18 @@ def __init__(self,tree=None,weight=1.0,rooted=False,name='',data=NodeData,values
         self.rooted=rooted
         self.name=name
         root=Nodes.Node(data())
-        self.add(root)
-        self.root=root.id
+        self.root = self.add(root)
         if tree:    # use the tree we have
             # if Tree is called from outside Nexus parser, we need to get rid of linebreaks, etc
             tree=tree.strip().replace('\n','').replace('\r','')
             # there's discrepancy whether newick allows semicolons et the end
             tree=tree.rstrip(';')
-            self._add_subtree(parent_id=root.id,tree=self._parse(tree)[0])
+            subtree_info, base_info = self._parse(tree)
+            root.data = self._add_nodedata(root.data, [[], base_info])
+            self._add_subtree(parent_id=root.id,tree=subtree_info)
 
     def _parse(self,tree):
         """Parses (a,b,c...)[[[xx]:]yy] into subcomponents and travels down recursively."""
-
         #Remove any leading/trailing white space - want any string starting
         #with " (..." should be recognised as a leaf, "(..."
         tree = tree.strip()
@@ -106,51 +106,48 @@ def _parse(self,tree):
 
     def _add_subtree(self,parent_id=None,tree=None):
         """Adds leaf or tree (in newick format) to a parent_id. (self,parent_id,tree)."""
-
         if parent_id is None:
             raise TreeError('Need node_id to connect to.')
         for st in tree:
+            nd=self.dataclass()
+            nd = self._add_nodedata(nd, st)
             if type(st[0])==list: # it's a subtree
-                nd=self.dataclass()
-                if isinstance(st[1][-1],str) and st[1][-1].startswith(NODECOMMENT_START): # last element of values is a text and starts with [&
-                    nd.comment=st[1].pop(-1)
-                if len(st[1])>=2: # if there's two values, support comes first. Is that always so?
-                    nd.support=st[1][0]
-                    if st[1][1] is not None:
-                        nd.branchlength=st[1][1]
-                elif len(st[1])==1: # otherwise it could be real branchlengths or support as branchlengths
-                    if not self.__values_are_support: # default
-                        if st[1][0] is not None:
-                            nd.branchlength=st[1][0]
-                    else:
-                        nd.support=st[1][0]
                 sn=Nodes.Node(nd)
                 self.add(sn,parent_id)
                 self._add_subtree(sn.id,st[0])
             else: # it's a leaf
-                nd=self.dataclass()
-                if isinstance(st[1][-1],str) and st[1][-1].startswith(NODECOMMENT_START):
-                    nd.comment=st[1].pop(-1)
                 nd.taxon=st[0]
-                if len(st)>1:
-                    if len(st[1])>=2: # if there's two values, support comes first. Is that always so?
-                        nd.support=st[1][0]
-                        if st[1][1] is not None:
-                            nd.branchlength=st[1][1]
-                    elif len(st[1])==1: # otherwise it could be real branchlengths or support as branchlengths
-                        if not self.__values_are_support: # default
-                            if st[1][0] is not None:
-                                nd.branchlength=st[1][0]
-                        else:
-                            nd.support=st[1][0]
                 leaf=Nodes.Node(nd)
                 self.add(leaf,parent_id)
+
+    def _add_nodedata(self, nd, st):
+        """Add data to the node parsed from the comments, taxon and support.
+        """
+        if isinstance(st[1][-1],str) and st[1][-1].startswith(NODECOMMENT_START):
+            nd.comment=st[1].pop(-1)
+        # if the first element is a string, it's the subtree node taxon
+        elif isinstance(st[1][0], str):
+            nd.taxon = st[1][0]
+            st[1] = st[1][1:]
+        if len(st)>1:
+            if len(st[1])>=2: # if there's two values, support comes first. Is that always so?
+                nd.support=st[1][0]
+                if st[1][1] is not None:
+                    nd.branchlength=st[1][1]
+            elif len(st[1])==1: # otherwise it could be real branchlengths or support as branchlengths
+                if not self.__values_are_support: # default
+                    if st[1][0] is not None:
+                        nd.branchlength=st[1][0]
+                else:
+                    nd.support=st[1][0]
+        return nd
 
     def _get_values(self, text):
         """Extracts values (support/branchlength) from xx[:yyy], xx."""
 
         if text=='':
             return None
+        nodecomment = None
         if NODECOMMENT_START in text: # if there's a [&....] comment, cut it out
             nc_start=text.find(NODECOMMENT_START)
             nc_end=text.find(NODECOMMENT_END)
@@ -159,10 +156,21 @@ def _get_values(self, text):
                                 % (NODECOMMENT_START, NODECOMMENT_END))
             nodecomment=text[nc_start:nc_end+1]
             text=text[:nc_start]+text[nc_end+1:]
-            values=[float(t) for t in text.split(':') if t.strip()]
+
+        # pase out supports and branchlengths, with internal node taxa info
+        values = []
+        taxonomy = None
+        for part in [t.strip() for t in text.split(":")]:
+            if part:
+                try:
+                    values.append(float(part))
+                except ValueError:
+                    assert taxonomy is None, "Two string taxonomies?"
+                    taxonomy = part
+        if taxonomy:
+            values.insert(0, taxonomy)
+        if nodecomment:
             values.append(nodecomment)
-        else:
-            values=[float(t) for t in text.split(':') if t.strip()]
         return values
 
     def _walk(self,node=None):

Tests/Nexus/int_node_labels.nex

@@ -0,0 +1,2 @@
+(((((Cephalotaxus:125.000000,(Taxus:100.000000,Torreya:100.000000)TT1:25.000000)Taxaceae:90.000000,((((((((Calocedrus:85.000000,Platycladus:85.000000)CP:5.000000,(Cupressus:85.000000,Juniperus:85.000000)CJ:5.000000)CJCP:5.000000,Chamaecyparis:95.000000)CCJCP:5.000000,(Thuja:7.870000,Thujopsis:7.870000)TT2:92.13)CJCPTT:30.000000,((Cryptomeria:120.000000,Taxodium:120.000000)CT:5.000000,Glyptostrobus:125.000000)CTG:5.000000)CupCallTax:5.830000,((Metasequoia:125.000000,Sequoia:125.000000)MS:5.000000,Sequoiadendron:130.000000)Sequoioid:5.830000)STCC:49.060001,Taiwania:184.889999)Taw+others:15.110000,Cunninghamia:200.000000)nonSci:15.000000)Tax+nonSci:10.000000,Sciadopitys:225.000000):25.000000,(((Abies:106.000000,Keteleeria:106.000000)AK:54.000000,(Pseudolarix:156.000000,Tsuga:156.000000)NTP:4.000000)NTPAK:24.000000,((Larix:87.000000,Pseudotsuga:87.000000)LP:81.000000,(Picea:155.000000,Pinus:155.000000)PPC:13.000000)Pinoideae:16.000000)Pinaceae:66.000000)Coniferales:25.000000,Gink
+go:275.000000)gymnosperm:75.000000;

Tests/test_Nexus.py

@@ -4,12 +4,14 @@
 import cStringIO
 import sys
 
-from Bio.Nexus import Nexus
+from Bio.Nexus import Nexus, Trees
 
 
 class NexusTest1(unittest.TestCase):
     def setUp(self):
-        self.handle = open("Nexus/test_Nexus_input.nex")
+        self.testfile_dir = "Nexus"
+        self.handle = open(os.path.join(self.testfile_dir, 
+            "test_Nexus_input.nex"))
 
     def tearDown(self):
         self.handle.close()
@@ -334,7 +336,48 @@ def test_TreeTest1(self):
 Root:  16
 """)
         self.assertEqual(t3.is_compatible(t2,threshold=0.3), [])
-
+
+    def test_internal_node_labels(self):
+        """Handle text labels on internal nodes.
+        """
+        ts1b = "(Cephalotaxus:125.000000,(Taxus:100.000000,Torreya:100.000000)"\
+               "TT1:25.000000)Taxaceae:90.000000;"
+        tree = Trees.Tree(ts1b)
+        assert self._get_flat_nodes(tree) == [('Taxaceae', 90.0, None, None),
+                ('Cephalotaxus', 125.0, None, None), ('TT1', 25.0, None, None),
+                ('Taxus', 100.0, None, None), ('Torreya', 100.0, None, None)]
+
+        ts1c = "(Cephalotaxus:125.000000,(Taxus:100.000000,Torreya:100.000000)"\
+                "25.000000)90.000000;"
+        tree = Trees.Tree(ts1c)
+        assert self._get_flat_nodes(tree) == [(None, 90.0, None, None),
+                ('Cephalotaxus', 125.0, None, None), (None, 25.0, None, None),
+                ('Taxus', 100.0, None, None), ('Torreya', 100.0, None, None)]
+
+        ts2 = "(((t9:0.385832, (t8:0.445135,t4:0.41401)C:0.024032)B:0.041436,"\
+          "t6:0.392496)A:0.0291131, t2:0.497673, ((t0:0.301171,"\
+          "t7:0.482152)E:0.0268148, ((t5:0.0984167,t3:0.488578)G:0.0349662,"\
+          "t1:0.130208)F:0.0318288)D:0.0273876);"
+        tree = Trees.Tree(ts2)
+
+        large_ex_handle = open(os.path.join(self.testfile_dir,
+            "int_node_labels.nex"))
+        tree = Trees.Tree(large_ex_handle.read())
+        large_ex_handle.close()
+
+    def _get_flat_nodes(self, tree):
+        cur_nodes = [tree.node(tree.root)]
+        nodedata = []
+        while len(cur_nodes) > 0:
+            new_nodes = []
+            for cur_node in cur_nodes:
+                nodedata.append((cur_node.data.taxon,
+                    cur_node.data.branchlength, cur_node.data.support,
+                    cur_node.data.comment))
+                new_nodes.extend([tree.node(nid) for nid in
+                    cur_node.get_succ()])
+            cur_nodes = new_nodes
+        return nodedata
 
 if __name__ == "__main__":
     runner = unittest.TextTestRunner(verbosity = 2)