pll_utree_newick_export/pll_rtree_newick_export now accepts a callbac…

…k function for customizing the format of exported newick tree, added an example, minor memleak fix for deallocating the data element on tip nodes - issue #131

examples/lg4/lg4.c

@@ -124,7 +124,7 @@ int main(int argc, char * argv[])
   pll_utree_show_ascii(tree, PLL_UTREE_SHOW_LABEL |
                              PLL_UTREE_SHOW_BRANCH_LENGTH |
                              PLL_UTREE_SHOW_CLV_INDEX);
-  char * newick = pll_utree_export_newick(tree);
+  char * newick = pll_utree_export_newick(tree,NULL);
   printf("%s\n", newick);
   free(newick);
   */

examples/load-utree/load-utree.c

@@ -77,7 +77,7 @@ int main(int argc, char * argv[])
 
   /* export the tree to newick format with the selected inner node as the root
      of the unrooted binary tree */
-  char * newick = pll_utree_export_newick(root);
+  char * newick = pll_utree_export_newick(root,NULL);
 
   printf("%s\n", newick);
 

examples/newick-export/Makefile

@@ -0,0 +1,44 @@
+# Copyright (C) 2015 Tomas Flouri
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as
+# published by the Free Software Foundation, either version 3 of the
+# License, or (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+#
+# Contact: Tomas Flouri <Tomas.Flouri@h-its.org>,
+# Heidelberg Institute for Theoretical Studies,
+# Schloss-Wolfsbrunnenweg 35, D-69118 Heidelberg, Germany
+
+# Profiling
+#PROFILING=-g -pg
+PROFILING=-g
+
+# Compiler warnings
+WARN=-Wall -Wsign-compare
+
+CC = gcc
+CFLAGS = -Wall -g -O3 -D_GNU_SOURCE $(WARN)
+LINKFLAGS = -L. $(PROFILING)
+LIBS=-lpll -lm
+PROG=newick-export
+
+all: $(PROG)
+
+OBJS=newick-export.o
+
+$(PROG): $(OBJS)
+	$(CC) $(LINKFLAGS) -o $@ $+ $(LIBS) $(LDFLAGS)
+
+%.o: %.c
+	$(CC) $(CPPFLAGS) $(CFLAGS) -c -o $@ $<
+
+clean:
+	rm -f *~ $(OBJS) gmon.out $(PROG)

examples/newick-export/newick-export.c

@@ -0,0 +1,191 @@
+/*
+    Copyright (C) 2015 Tomas Flouri
+
+    This program is free software: you can redistribute it and/or modify
+    it under the terms of the GNU Affero General Public License as
+    published by the Free Software Foundation, either version 3 of the
+    License, or (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Affero General Public License for more details.
+
+    You should have received a copy of the GNU Affero General Public License
+    along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+    Contact: Tomas Flouri <Tomas.Flouri@h-its.org>,
+    Exelixis Lab, Heidelberg Instutute for Theoretical Studies
+    Schloss-Wolfsbrunnenweg 35, D-69118 Heidelberg, Germany
+*/
+
+#include "pll.h"
+#include <stdarg.h>
+#include <time.h>
+
+static void fatal(const char * format, ...) __attribute__ ((noreturn));
+
+static void fatal(const char * format, ...)
+{
+  va_list argptr;
+  va_start(argptr, format);
+  vfprintf(stderr, format, argptr);
+  va_end(argptr);
+  fprintf(stderr, "\n");
+  exit(EXIT_FAILURE);
+}
+
+typedef struct nodedata_s
+{
+  double support;
+  double rvalue;
+} nodedata_t;
+
+/* a callback function that prints the following information for the two types
+ * of nodes, tips and inners:
+
+
+   for tip nodes:
+     label, branch length and support value
+   
+   for inner nodes:
+     label, branch length, support value, and a random value 
+
+   Note that this is not a standard format that can be read by all tree viewers
+
+   Check the extended newick format for a more widespread notation:
+   http://dmi.uib.es/~gcardona/BioInfo/enewick.html
+
+*/
+static char * cb_serialize(const pll_unode_t * node)
+{
+  char * s = NULL;
+  nodedata_t * nd;
+
+
+  /* inner node */
+  if (node->next)
+  {
+    /* find which node of the round-about has the data element */
+    if (node->data)
+      nd = (nodedata_t *)(node->data);
+    else if (node->next->data)
+      nd = (nodedata_t *)(node->next->data);
+    else
+      nd = (nodedata_t *)(node->next->next->data);
+
+    asprintf(&s,
+             "%s[&support=%f,rvalue=%f]:%f",
+             node->label ? node->label : "",
+             nd->support,
+             nd->rvalue,
+             node->length);
+  }
+  else
+  {
+    nd = (nodedata_t *)(node->data);
+    asprintf(&s,
+             "%s[&support=%f]:%f",
+             node->label ? node->label : "",
+             nd->support,
+             node->length);
+  }
+
+  return s;
+}
+
+pll_utree_t * load_tree_unrooted(const char * filename)
+{
+  pll_utree_t * utree;
+  pll_rtree_t * rtree;
+
+  if (!(rtree = pll_rtree_parse_newick(filename)))
+  {
+    if (!(utree = pll_utree_parse_newick(filename)))
+    {
+      fprintf(stderr, "%s\n", pll_errmsg);
+      return NULL;
+    }
+  }
+  else
+  {
+    utree = pll_rtree_unroot(rtree);
+
+    pll_unode_t * root = utree->nodes[utree->tip_count+utree->inner_count-1];
+
+    /* optional step if using default PLL clv/pmatrix index assignments */
+    pll_utree_reset_template_indices(root, utree->tip_count);
+
+    pll_rtree_destroy(rtree,NULL);
+  }
+
+  return utree;
+}
+
+int main(int argc, char * argv[])
+{
+  unsigned int i;
+
+  if (argc != 2)
+    fatal("syntax: %s [newick]", argv[0]);
+
+  /* initialize pseudo-random number generator */
+  srandom(time(NULL));
+
+  /* load tree as unrooted */
+  pll_utree_t * utree = load_tree_unrooted(argv[1]);
+  if (!utree)
+    fatal("Tree must be a rooted or unrooted binary.");
+
+  /* set random support values for tip nodes */
+  for (i = 0; i < utree->tip_count; ++i)
+  {
+    pll_unode_t * node = utree->nodes[i];
+    nodedata_t * data;
+
+    node->data = malloc(sizeof(nodedata_t));
+
+    data = (nodedata_t *)(node->data);
+
+    data->support = random() / (double)RAND_MAX;
+  }
+
+  /* set random support values and a random value to each inner node, but
+     allocate the structure in only one of the three round-about nodes that make
+     up an inner node */
+  for (i = utree->tip_count; i < utree->tip_count + utree->inner_count; ++i)
+  {
+    pll_unode_t * node = utree->nodes[i];
+    nodedata_t * data;
+
+    node->data = malloc(sizeof(nodedata_t));
+
+    data = (nodedata_t *)(node->data);
+
+    data->support = random() / (double)RAND_MAX;
+    data->rvalue = data->support * random();
+  }
+
+  /* select a random inner node */
+  long int r = random() % utree->inner_count;
+  pll_unode_t * root = utree->nodes[utree->tip_count + r];
+
+  /* export the tree to newick format with the selected inner node as the root
+     of the unrooted binary tree.
+     
+     If we pass NULL as the callback function, then the tree is printed in newick
+     format with branch lengths only, i.e.
+  
+     char * newick = pll_utree_export_newick(root,NULL);
+  */
+
+  char * newick = pll_utree_export_newick(root,cb_serialize);
+
+  printf("%s\n", newick);
+
+  free(newick);
+
+  pll_utree_destroy(utree,free);
+
+  return 0;
+}

examples/newick-export/target.mk

@@ -0,0 +1,2 @@
+newick_exportdir = $(docdir)/examples/newick-export
+dist_newick_export_DATA = newick-export/newick-export.c newick-export/Makefile

examples/newick-fasta-rooted/newick-fasta-rooted.c

@@ -111,7 +111,7 @@ int main(int argc, char * argv[])
   pll_rtree_show_ascii(tree, PLL_UTREE_SHOW_LABEL |
                              PLL_UTREE_SHOW_BRANCH_LENGTH |
                              PLL_UTREE_SHOW_CLV_INDEX);
-  char * newick = pll_rtree_export_newick(tree);
+  char * newick = pll_rtree_export_newick(tree,NULL);
   printf("%s\n", newick);
   free(newick);
 

examples/newick-fasta-unrooted/newick-fasta-unrooted.c

@@ -129,7 +129,7 @@ int main(int argc, char * argv[])
   pll_utree_show_ascii(tree, PLL_UTREE_SHOW_LABEL |
                              PLL_UTREE_SHOW_BRANCH_LENGTH |
                              PLL_UTREE_SHOW_CLV_INDEX);
-  char * newick = pll_utree_export_newick(tree);
+  char * newick = pll_utree_export_newick(tree,NULL);
   printf("%s\n", newick);
   free(newick);
 

examples/newick-phylip-unrooted/newick-phylip-unrooted.c

@@ -136,7 +136,7 @@ int main(int argc, char * argv[])
   pll_utree_show_ascii(tree, PLL_UTREE_SHOW_LABEL |
                              PLL_UTREE_SHOW_BRANCH_LENGTH |
                              PLL_UTREE_SHOW_CLV_INDEX);
-  char * newick = pll_utree_export_newick(tree);
+  char * newick = pll_utree_export_newick(tree,NULL);
   printf("%s\n", newick);
   free(newick);
 

examples/parsimony/npr-pars.c

@@ -103,7 +103,7 @@ int main(int argc, char * argv[])
   pll_utree_show_ascii(tree, PLL_UTREE_SHOW_LABEL |
                              PLL_UTREE_SHOW_BRANCH_LENGTH |
                              PLL_UTREE_SHOW_CLV_INDEX);
-  char * newick = pll_utree_export_newick(tree);
+  char * newick = pll_utree_export_newick(tree,NULL);
   printf("%s\n", newick);
   free(newick);
 

examples/partial-traversal/partial.c

@@ -181,7 +181,7 @@ int main(int argc, char * argv[])
   pll_utree_show_ascii(tree, PLL_UTREE_SHOW_LABEL |
                              PLL_UTREE_SHOW_BRANCH_LENGTH |
                              PLL_UTREE_SHOW_CLV_INDEX);
-  char * newick = pll_utree_export_newick(tree);
+  char * newick = pll_utree_export_newick(tree,NULL);
   printf("%s\n", newick);
   free(newick);
 

examples/protein-list/protein-list.c

@@ -199,7 +199,7 @@ int main(int argc, char * argv[])
   pll_utree_show_ascii(tree, PLL_UTREE_SHOW_LABEL |
                              PLL_UTREE_SHOW_BRANCH_LENGTH |
                              PLL_UTREE_SHOW_CLV_INDEX);
-  char * newick = pll_utree_export_newick(tree);
+  char * newick = pll_utree_export_newick(tree,NULL);
   printf("%s\n", newick);
   free(newick);
 

examples/stepwise/stepwise.c

@@ -208,7 +208,7 @@ int main(int argc, char * argv[])
 
   /* export the tree to newick format with the selected inner node as the root
      of the unrooted binary tree */
-  char * newick = pll_utree_export_newick(root);
+  char * newick = pll_utree_export_newick(root,NULL);
   printf("%s\n", newick);
   free(newick);
 

src/parse_utree.y

@@ -108,6 +108,7 @@ PLL_EXPORT void pll_utree_destroy(pll_utree_t * tree,
   /* deallocate tip nodes */
   for (i = 0; i < tree->tip_count; ++i)
   {
+    dealloc_data(tree->nodes[i], cb_destroy);
     if (tree->nodes[i]->label)
       free(tree->nodes[i]->label);
     free(tree->nodes[i]);

src/pll.h

@@ -646,7 +646,8 @@ PLL_EXPORT pll_utree_t * pll_utree_wraptree(pll_unode_t * root,
 
 PLL_EXPORT void pll_utree_show_ascii(const pll_unode_t * tree, int options);
 
-PLL_EXPORT char * pll_utree_export_newick(const pll_unode_t * root);
+PLL_EXPORT char * pll_utree_export_newick(const pll_unode_t * root,
+                                   char * (*cb_serialize)(const pll_unode_t *));
 
 PLL_EXPORT int pll_utree_traverse(pll_unode_t * root,
                                   int traversal,
@@ -697,7 +698,8 @@ PLL_EXPORT void pll_msa_destroy(pll_msa_t * msa);
 
 PLL_EXPORT void pll_rtree_show_ascii(const pll_rnode_t * root, int options);
 
-PLL_EXPORT char * pll_rtree_export_newick(const pll_rnode_t * root);
+PLL_EXPORT char * pll_rtree_export_newick(const pll_rnode_t * root,
+                                   char * (*cb_serialize)(const pll_rnode_t *));
 
 PLL_EXPORT int pll_rtree_traverse(pll_rnode_t * root,
                                   int traversal,