def write_trees_block(self, tree_list, stream):
block = []
newick_writer = newick.NewickWriter(
suppress_rooting=self.suppress_rooting,
suppress_edge_lengths=self.suppress_edge_lengths,
unquoted_underscores=self.unquoted_underscores,
preserve_spaces=self.preserve_spaces,
store_tree_weights=self.store_tree_weights,
suppress_annotations=self.suppress_annotations,
annotations_as_nhx=self.annotations_as_nhx,
suppress_item_comments=self.suppress_item_comments,
suppress_leaf_taxon_labels=self.suppress_leaf_taxon_labels,
suppress_leaf_node_labels=self.suppress_leaf_node_labels,
suppress_internal_taxon_labels=self.suppress_internal_taxon_labels,
suppress_internal_node_labels=self.suppress_internal_node_labels,
node_label_element_separator=self.node_label_element_separator,
node_label_compose_func=self.node_label_compose_func,
)
block.append('BEGIN TREES;')
if self._link_blocks():
title = self.compose_block_title(tree_list)
if title:
block.append(' %s;' % title)
if tree_list.taxon_set.labels:
block.append(' LINK TAXA = %s;' % textutils.escape_nexus_token(tree_list.taxon_set.label, preserve_spaces=self.preserve_spaces, quote_underscores=not self.unquoted_underscores))
for treeidx, tree in enumerate(tree_list):
if tree.label:
tree_name = tree.label
else:
tree_name = str(treeidx)
newick_str = newick_writer.compose_tree(tree)
block.append(' TREE %s = %s' % (textutils.escape_nexus_token(tree_name, preserve_spaces=self.preserve_spaces, quote_underscores=not self.unquoted_underscores),
newick_str))
block.append('END;\n\n')
stream.write('\n'.join(block))
def write_mesquite_association_block(self, out, domain_taxon_set_title=None, range_taxon_set_title=None):
"""
For debugging purposes ...
"""
out.write("BEGIN TaxaAssociation;\n")
if self.label:
title = self.label
else:
title = self.oid
out.write(" TITLE %s;\n" % textutils.escape_nexus_token(title))
if domain_taxon_set_title is None:
if self.domain_taxon_set.label:
domain_taxon_set_title = self.domain_taxon_set.label
else:
domain_taxon_set_title = self.domain_taxon_set.oid
if range_taxon_set_title is None:
if self.range_taxon_set.label:
range_taxon_set_title = self.range_taxon_set.label
else:
range_taxon_set_title = self.range_taxon_set.oid
out.write(" TAXA %s, %s;\n" % (
textutils.escape_nexus_token(range_taxon_set_title),
textutils.escape_nexus_token(domain_taxon_set_title)
))
out.write(" ASSOCIATES\n")
out.write(self.mesquite_association_rows() + "\n")
out.write(" ;\n")
out.write("END;\n")
def write_mesquite_association_block(self, out, domain_taxon_set_title=None, range_taxon_set_title=None):
"""
For debugging purposes ...
"""
out.write("BEGIN TaxaAssociation;\n")
if self.label:
title = self.label
else:
title = self.oid
out.write(" TITLE %s;\n" % textutils.escape_nexus_token(title))
if domain_taxon_set_title is None:
if self.domain_taxon_set.label:
domain_taxon_set_title = self.domain_taxon_set.label
else:
domain_taxon_set_title = self.domain_taxon_set.oid
if range_taxon_set_title is None:
if self.range_taxon_set.label:
range_taxon_set_title = self.range_taxon_set.label
else:
range_taxon_set_title = self.range_taxon_set.oid
out.write(" TAXA %s, %s;\n" % (
textutils.escape_nexus_token(range_taxon_set_title),
textutils.escape_nexus_token(domain_taxon_set_title)
))
out.write(" ASSOCIATES\n")
out.write(self.mesquite_association_rows() + "\n")
out.write(" ;\n")
out.write("END;\n")
def mesquite_association_rows(self):
rows = []
for rt in self.reverse:
x1 = textutils.escape_nexus_token(rt.label)
dt_labels = [dt.label for dt in self.reverse[rt]]
dt_labels.sort()
x2 = " ".join([textutils.escape_nexus_token(d) for d in dt_labels])
rows.append(" %s / %s" % (x1, x2))
return ",\n".join(rows)
def write_char_block(self, char_matrix, stream):
nexus = []
taxlabels = [textutils.escape_nexus_token(taxon.label, preserve_spaces=self.preserve_spaces, quote_underscores=not self.unquoted_underscores) for taxon in char_matrix.taxon_set]
max_label_len = max([len(label) for label in taxlabels])
nchar = max([len(seq) for seq in char_matrix.values()])
if self.simple:
nexus.append('BEGIN DATA;')
ntaxstr = "NTAX=%d" % len(taxlabels)
else:
nexus.append('BEGIN CHARACTERS;')
ntaxstr = ""
if self._link_blocks():
title = self.compose_block_title(char_matrix)
if title:
nexus.append(' %s;' % title)
if char_matrix.taxon_set.label:
nexus.append(' LINK TAXA = %s;' % textutils.escape_nexus_token(char_matrix.taxon_set.label, preserve_spaces=self.preserve_spaces, quote_underscores=not self.unquoted_underscores))
nexus.append(' DIMENSIONS %s NCHAR=%d;' % (ntaxstr, nchar))
nexus.append(' FORMAT %s;' % self.compose_format_terms(char_matrix))
nexus.append(' MATRIX')
state_string_map = {}
if isinstance(char_matrix, dataobject.ContinuousCharacterMatrix):
for taxon in char_matrix.taxon_set:
seq = " ".join([str(v) for v in char_matrix[taxon]])
nexus.append('%s %s' % (textutils.escape_nexus_token(taxon.label, preserve_spaces=self.preserve_spaces, quote_underscores=not self.unquoted_underscores).ljust(max_label_len), seq))
else:
for taxon in char_matrix.taxon_set:
seq_vec = char_matrix[taxon]
seq = StringIO()
for cell in seq_vec:
state = cell.value
assert state is not None, "Undefined state encountered in character sequence."
try:
seq.write(state_string_map[state])
except:
if state.symbol is not None:
state_string_map[state] = state.symbol
elif state.multistate == dataobject.StateAlphabetElement.AMBIGUOUS_STATE:
state_string_map[state] = "{%s}" % ("".join(state.fundamental_symbols))
elif state.multistate == dataobject.StateAlphabetElement.POLYMORPHIC_STATE:
state_string_map[state] = "(%s)" % ("".join(state.fundamental_symbols))
else:
raise Exception("Could not match character state to symbol: '%s'." % state)
seq.write(state_string_map[state])
nexus.append('%s %s' % (textutils.escape_nexus_token(taxon.label, preserve_spaces=self.preserve_spaces, quote_underscores=not self.unquoted_underscores).ljust(max_label_len), seq.getvalue()))
nexus.append(' ;')
nexus.append('END;\n\n')
if hasattr(char_matrix, "character_subsets"):
nexus.append('BEGIN SETS;')
for label, char_set in char_matrix.character_subsets.items():
label = textutils.escape_nexus_token(char_set.label,
preserve_spaces=self.preserve_spaces,
quote_underscores=not self.unquoted_underscores)
pos = " ".join(str(c+1) for c in char_set.character_indices)
nexus.append(' charset %s = %s;\n' % (label, pos))
nexus.append('END;\n\n')
stream.write('\n'.join(nexus))
def mesquite_association_rows(self):
rows = []
for rt in self.reverse:
x1 = textutils.escape_nexus_token(rt.label)
dt_labels = [dt.label for dt in self.reverse[rt]]
dt_labels.sort()
x2 = " ".join([textutils.escape_nexus_token(d) for d in dt_labels])
rows.append(" %s / %s" % (x1, x2))
return ",\n".join(rows)
def write_taxa_block(self, taxon_set, stream):
block = []
block.append("BEGIN TAXA;")
if not self.suppress_annotations:
block.append(nexustokenizer.format_annotation_as_comments(taxon_set, nhx=self.annotations_as_nhx))
if self._link_blocks():
title = self.compose_block_title(taxon_set)
if title:
block.append(" %s;" % title)
block.append(" DIMENSIONS NTAX=%d;" % len(taxon_set))
block.append(" TAXLABELS")
for taxon in taxon_set:
if self.suppress_annotations:
annotation_str = ""
else:
annotation_str = " " + nexustokenizer.format_annotation_as_comments(taxon, nhx=self.annotations_as_nhx)
block.append(
" %s%s"
% (
textutils.escape_nexus_token(
taxon.label,
preserve_spaces=self.preserve_spaces,
quote_underscores=not self.unquoted_underscores,
),
annotation_str,
)
)
block.append(" ;")
block.append("END;\n\n")
stream.write("\n".join(block))
def write_taxa_block(self, taxon_set, stream):
block = []
block.append('BEGIN TAXA;')
if not self.suppress_annotations:
block.append(
nexustokenizer.format_annotation_as_comments(
taxon_set, nhx=self.annotations_as_nhx))
if self._link_blocks():
title = self.compose_block_title(taxon_set)
if title:
block.append(' %s;' % title)
block.append(' DIMENSIONS NTAX=%d;' % len(taxon_set))
block.append(' TAXLABELS')
for taxon in taxon_set:
if self.suppress_annotations:
annotation_str = ""
else:
annotation_str = " " + nexustokenizer.format_annotation_as_comments(
taxon, nhx=self.annotations_as_nhx)
block.append(' %s%s' % (textutils.escape_nexus_token(
taxon.label,
preserve_spaces=self.preserve_spaces,
quote_underscores=not self.unquoted_underscores),
annotation_str))
block.append(' ;')
block.append('END;\n\n')
stream.write('\n'.join(block))
def write_trees_block(self, tree_list, stream):
block = []
newick_writer = newick.NewickWriter(
suppress_rooting=self.suppress_rooting,
suppress_edge_lengths=self.suppress_edge_lengths,
unquoted_underscores=self.unquoted_underscores,
preserve_spaces=self.preserve_spaces,
store_tree_weights=self.store_tree_weights,
suppress_annotations=self.suppress_annotations,
annotations_as_nhx=self.annotations_as_nhx,
suppress_item_comments=self.suppress_item_comments,
suppress_leaf_taxon_labels=self.suppress_leaf_taxon_labels,
suppress_leaf_node_labels=self.suppress_leaf_node_labels,
suppress_internal_taxon_labels=self.suppress_internal_taxon_labels,
suppress_internal_node_labels=self.suppress_internal_node_labels,
node_label_element_separator=self.node_label_element_separator,
node_label_compose_func=self.node_label_compose_func,
edge_label_compose_func=self.edge_label_compose_func,
)
block.append('BEGIN TREES;')
if not self.suppress_annotations:
block.append(
nexustokenizer.format_annotation_as_comments(
tree_list, nhx=self.annotations_as_nhx))
if self._link_blocks():
title = self.compose_block_title(tree_list)
if title:
block.append(' %s;' % title)
if tree_list.taxon_set.labels:
block.append(
' LINK TAXA = %s;' % textutils.escape_nexus_token(
tree_list.taxon_set.label,
preserve_spaces=self.preserve_spaces,
quote_underscores=not self.unquoted_underscores))
for treeidx, tree in enumerate(tree_list):
if tree.label:
tree_name = tree.label
else:
tree_name = str(treeidx)
newick_str = newick_writer.compose_tree(tree)
block.append(' TREE %s = %s' % (textutils.escape_nexus_token(
tree_name,
preserve_spaces=self.preserve_spaces,
quote_underscores=not self.unquoted_underscores), newick_str))
block.append('END;\n\n')
stream.write('\n'.join(block))
def choose_display_tag(self, node):
"""
Based on current settings, the attributes of a node, and
whether or not the node is a leaf, returns an appropriate tag.
"""
tag = None
if self.node_label_compose_func:
tag = self.node_label_compose_func(node)
else:
tag_parts = []
is_leaf = len(node.child_nodes()) == 0
if is_leaf:
if (
hasattr(node, "taxon")
and node.taxon
and node.taxon.label is not None
and not self.suppress_leaf_taxon_labels
):
tag_parts.append(str(node.taxon.label))
if (
hasattr(node, "label")
and node.label
and node.label is not None
and not self.suppress_leaf_node_labels
):
tag_parts.append(str(node.label))
if len(tag_parts) > 0:
tag = self.node_label_element_separator.join(tag_parts)
else:
return "_" # anonymous leaf
else:
if (
hasattr(node, "taxon")
and node.taxon
and node.taxon.label is not None
and not self.suppress_internal_taxon_labels
):
tag_parts.append(str(node.taxon.label))
if (
hasattr(node, "label")
and node.label
and node.label is not None
and not self.suppress_internal_node_labels
):
tag_parts.append(str(node.label))
if len(tag_parts) > 0:
tag = self.node_label_element_separator.join(tag_parts)
else:
return "" # nada
if tag:
tag = textutils.escape_nexus_token(
tag, preserve_spaces=self.preserve_spaces, quote_underscores=not self.unquoted_underscores
)
return tag
else:
return ""
def compose_block_title(self, block):
# if self.is_write_block_titles is False then no block titles;
# if only one taxon set, or attached taxon set mode, unless self.is_write_block_titles
# is explicitly True, then again, we do not write block titles
if not self._link_blocks():
return ""
if not block.label:
block.label = block.oid
if block.label:
return "TITLE %s" % textutils.escape_nexus_token(block.label, preserve_spaces=self.preserve_spaces, quote_underscores=not self.unquoted_underscores)
else:
return ""
def write_taxa_block(self, taxon_set, stream):
block = []
block.append('BEGIN TAXA;')
if self._link_blocks():
title = self.compose_block_title(taxon_set)
if title:
block.append(' %s;' % title)
block.append(' DIMENSIONS NTAX=%d;' % len(taxon_set))
block.append(' TAXLABELS')
for taxon in taxon_set:
block.append(' %s' % textutils.escape_nexus_token(taxon.label, preserve_spaces=self.preserve_spaces, quote_underscores=not self.unquoted_underscores))
block.append(' ;')
block.append('END;\n\n')
stream.write('\n'.join(block))
def choose_display_tag(self, node):
"""
Based on current settings, the attributes of a node, and
whether or not the node is a leaf, returns an appropriate tag.
"""
tag = None
if self.node_label_compose_func:
tag = self.node_label_compose_func(node)
else:
tag_parts = []
is_leaf = len(node.child_nodes()) == 0
if is_leaf:
if hasattr(node, 'taxon') \
and node.taxon \
and node.taxon.label is not None \
and not self.suppress_leaf_taxon_labels:
tag_parts.append(str(node.taxon.label))
if hasattr(node, 'label') \
and node.label \
and node.label is not None \
and not self.suppress_leaf_node_labels:
tag_parts.append(str(node.label))
if len(tag_parts) > 0:
tag = self.node_label_element_separator.join(tag_parts)
else:
return "_" # anonymous leaf
else:
if hasattr(node, 'taxon') \
and node.taxon \
and node.taxon.label is not None \
and not self.suppress_internal_taxon_labels:
tag_parts.append(str(node.taxon.label))
if hasattr(node, 'label') \
and node.label \
and node.label is not None \
and not self.suppress_internal_node_labels:
tag_parts.append(str(node.label))
if len(tag_parts) > 0:
tag = self.node_label_element_separator.join(tag_parts)
else:
return "" # nada
if tag:
tag = textutils.escape_nexus_token(
tag,
preserve_spaces=self.preserve_spaces,
quote_underscores=not self.unquoted_underscores)
return tag
else:
return ""
def compose_block_title(self, block):
# if self.is_write_block_titles is False then no block titles;
# if only one taxon set, or attached taxon set mode, unless self.is_write_block_titles
# is explicitly True, then again, we do not write block titles
if not self._link_blocks():
return ""
if not block.label:
block.label = block.oid
if block.label:
return "TITLE %s" % textutils.escape_nexus_token(
block.label,
preserve_spaces=self.preserve_spaces,
quote_underscores=not self.unquoted_underscores)
else:
return ""
def write_taxa_block(self, taxon_set, stream):
block = []
block.append('BEGIN TAXA;')
if self._link_blocks():
title = self.compose_block_title(taxon_set)
if title:
block.append(' %s;' % title)
block.append(' DIMENSIONS NTAX=%d;' % len(taxon_set))
block.append(' TAXLABELS')
for taxon in taxon_set:
block.append(' %s' % textutils.escape_nexus_token(
taxon.label,
preserve_spaces=self.preserve_spaces,
quote_underscores=not self.unquoted_underscores))
block.append(' ;')
block.append('END;\n\n')
stream.write('\n'.join(block))
def write_as_nexus(stream, patterns, label):
global LAST_COMMAND
stream.write("\n[!%s ]\n" % label)
p = patterns[0]
num_chars = len(patterns)
num_areas = len(p)
if num_areas < len(AREA_NAME_LIST):
warn(
'%d labels were found in the labels file, but only %d areas were read in the input NEXUS files'
% (len(AREA_NAME_LIST), num_areas))
elif num_areas > len(AREA_NAME_LIST):
warn(
'Only %d labels were found in the labels file, but %d areas were read in the input NEXUS files'
% (len(AREA_NAME_LIST), num_areas))
stream.write("""Begin Data;
Dimensions ntax = %d nchar = %d;
Format datatype=standard symbols="012" ;
Matrix \n""" % (num_areas, num_chars))
for area_ind in range(num_areas):
if AREA_NAME_LIST:
try:
name = AREA_NAME_LIST[area_ind]
except:
name = 'unlabelled area ' + str(1 + area_ind)
else:
name = "area%d" % area_ind
name = escape_nexus_token(name)
padding = ' ' * (col_width - len(name))
stream.write("%s%s" % (name, padding))
for p in patterns:
stream.write(" %s" % str(p[area_ind]))
stream.write("\n")
if num_areas > 11:
search = "HSearch"
else:
search = "BAndB"
stream.write(""";
End;
Begin Paup;
typeset * o = ord : 1-. ;
%s ;
SaveTrees from =1 to=100 file = %s.tre;
%s
End;
""" % (search, label, LAST_COMMAND))
stream.flush()
def write_as_nexus(stream, patterns, label):
global LAST_COMMAND
stream.write("\n[!%s ]\n" % label)
p = patterns[0]
num_chars = len(patterns)
num_areas = len(p)
if num_areas < len(AREA_NAME_LIST):
warn('%d labels were found in the labels file, but only %d areas were read in the input NEXUS files' % (
len(AREA_NAME_LIST),
num_areas))
elif num_areas > len(AREA_NAME_LIST):
warn('Only %d labels were found in the labels file, but %d areas were read in the input NEXUS files' % (
len(AREA_NAME_LIST),
num_areas))
stream.write("""Begin Data;
Dimensions ntax = %d nchar = %d;
Format datatype=standard symbols="012" ;
Matrix \n""" % (num_areas, num_chars))
for area_ind in range(num_areas):
if AREA_NAME_LIST:
try:
name = AREA_NAME_LIST[area_ind]
except:
name = 'unlabelled area ' + str(1 + area_ind)
else:
name = "area%d" % area_ind
name = escape_nexus_token(name)
padding = ' ' * (col_width - len(name))
stream.write("%s%s" % (name, padding))
for p in patterns:
stream.write(" %s" % str(p[area_ind]))
stream.write("\n")
if num_areas > 11:
search = "HSearch"
else:
search = "BAndB"
stream.write(""";
End;
Begin Paup;
typeset * o = ord : 1-. ;
%s ;
SaveTrees from =1 to=100 file = %s.tre;
%s
End;
""" % (search, label, LAST_COMMAND))
stream.flush()
def write_taxa_block(self, taxon_set, stream):
block = []
block.append("BEGIN TAXA;")
if self._link_blocks():
title = self.compose_block_title(taxon_set)
if title:
block.append(" %s;" % title)
block.append(" DIMENSIONS NTAX=%d;" % len(taxon_set))
block.append(" TAXLABELS")
for taxon in taxon_set:
block.append(
" %s"
% textutils.escape_nexus_token(
taxon.label, preserve_spaces=self.preserve_spaces, quote_underscores=not self.unquoted_underscores
)
)
block.append(" ;")
block.append("END;\n\n")
stream.write("\n".join(block))
def write_char_block(self, char_matrix, stream):
nexus = []
taxlabels = [
textutils.escape_nexus_token(
taxon.label,
preserve_spaces=self.preserve_spaces,
quote_underscores=not self.unquoted_underscores)
for taxon in char_matrix.taxon_set
]
max_label_len = max([len(label) for label in taxlabels])
nchar = max([len(seq) for seq in char_matrix.values()])
if self.simple:
nexus.append('BEGIN DATA;')
ntaxstr = "NTAX=%d" % len(taxlabels)
else:
nexus.append('BEGIN CHARACTERS;')
ntaxstr = ""
if self._link_blocks():
title = self.compose_block_title(char_matrix)
if title:
nexus.append(' %s;' % title)
if char_matrix.taxon_set.label:
nexus.append(
' LINK TAXA = %s;' % textutils.escape_nexus_token(
char_matrix.taxon_set.label,
preserve_spaces=self.preserve_spaces,
quote_underscores=not self.unquoted_underscores))
nexus.append(' DIMENSIONS %s NCHAR=%d;' % (ntaxstr, nchar))
nexus.append(' FORMAT %s;' % self.compose_format_terms(char_matrix))
nexus.append(' MATRIX')
state_string_map = {}
if isinstance(char_matrix, dataobject.ContinuousCharacterMatrix):
for taxon in char_matrix.taxon_set:
seq = " ".join([str(v) for v in char_matrix[taxon]])
nexus.append('%s %s' % (textutils.escape_nexus_token(
taxon.label,
preserve_spaces=self.preserve_spaces,
quote_underscores=not self.unquoted_underscores).ljust(
max_label_len), seq))
else:
for taxon in char_matrix.taxon_set:
try:
seq_vec = char_matrix[taxon]
except KeyError:
continue
seq = StringIO()
for cell in seq_vec:
state = cell.value
assert state is not None, "Undefined state encountered in character sequence."
try:
seq.write(state_string_map[state])
except:
if state.symbol is not None:
state_string_map[state] = state.symbol
elif state.multistate == dataobject.StateAlphabetElement.AMBIGUOUS_STATE:
state_string_map[state] = "{%s}" % ("".join(
state.fundamental_symbols))
elif state.multistate == dataobject.StateAlphabetElement.POLYMORPHIC_STATE:
state_string_map[state] = "(%s)" % ("".join(
state.fundamental_symbols))
else:
raise Exception(
"Could not match character state to symbol: '%s'."
% state)
seq.write(state_string_map[state])
nexus.append('%s %s' % (textutils.escape_nexus_token(
taxon.label,
preserve_spaces=self.preserve_spaces,
quote_underscores=not self.unquoted_underscores).ljust(
max_label_len), seq.getvalue()))
nexus.append(' ;')
nexus.append('END;\n\n')
if hasattr(char_matrix, "character_subsets"):
nexus.append('BEGIN SETS;')
for label, char_set in char_matrix.character_subsets.items():
label = textutils.escape_nexus_token(
char_set.label,
preserve_spaces=self.preserve_spaces,
quote_underscores=not self.unquoted_underscores)
pos = " ".join(str(c + 1) for c in char_set.character_indices)
nexus.append(' charset %s = %s;\n' % (label, pos))
nexus.append('END;\n\n')
stream.write('\n'.join(nexus))
if i in split:
stream.write('1')
else:
stream.write('0')
else:
stream.write('?'*len(split_list))
output.write("""#NEXUS
Begin Data;
Dimensions ntax = %d nchar = %d;
Format datatype=standard symbols="01" Missing = ?;
Matrix \n""" % (number_of_taxon + 1, branch_counter))
escaped_names = []
max_name_length = len('roottaxon')
for t in taxon_set:
name = t.label.split('@')[0]
escaped_names.append(escape_nexus_token(name))
max_name_length = max(max_name_length, len(escaped_names[-1]))
fmt = '%%-%ds %%s\n' %(max_name_length)
for i,stream in enumerate(code_list):
#esc_names,ottoid = escaped_names[i].split('@')
#output.write(fmt %(esc_names,stream.getvalue()))
output.write(fmt %(escaped_names[i],stream.getvalue()))
output.write(fmt %('roottaxon','0'*branch_counter))
output.write(""";
END;
""")