Merge branch 'master' into pgrt-looking_for_integer

.travis.yml

@@ -6,6 +6,7 @@ os:
   - osx
 env:
   - PYVERSION="3.5"
+  - PYVERSION="3.8"
 before_install:
   - echo "$TRAVIS_OS_NAME"
   - if [[ "$TRAVIS_OS_NAME" == "linux" ]]; then wget https://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh -O miniconda.sh; fi

CHANGELOG.md

@@ -1,5 +1,9 @@
+* Version 4.3.15:
+	* some py3.8 changes and some java changes  from pgrt
+* Version 4.3.14:
+	* Added option `-R "Nmin Nmax"` to specify the range of full length sequences to UPP
 * Version 4.3.13:
-	* Added backtranslation functionality to UPP for amino acid sequences.
+    * Added backtranslation functionality to UPP for amino acid sequences.
 * Version 4.3.12:
 	* Added `-rt` to remove temp files	
 * Version 4.3.11:

sepp/__init__.py

@@ -23,7 +23,7 @@
 
 __all__ = ["alignment", "shortreadalignment", "taxonneighbourfinder",
            "tools", "problem"]
-version = "4.3.12"
+version = "4.3.15"
 _DEBUG = ("SEPP_DEBUG" in os.environ) and \
     (os.environ["SEPP_DEBUG"].lower() == "true")
 

sepp/exhaustive_upp.py

@@ -66,7 +66,7 @@ def generate_backbone(self):
         sequences.read_file_object(self.options.sequence_file)
         sequences.degap()
         fragments = MutableAlignment()
-        if (options().median_full_length is not None):
+        if (options().median_full_length is not None or options().full_length_range is not None):
             if (options().median_full_length == -1):
                 seq_lengths = sorted(
                     [len(seq) for seq in list(sequences.values())])
@@ -77,12 +77,17 @@ def generate_backbone(self):
                         seq_lengths[l2] + seq_lengths[l2 + 1]) / 2.0
                 else:
                     options().median_full_length = seq_lengths[l2]
-
-            (min_length, max_length) = (
-                int(options().median_full_length * (
-                    1 - options().backbone_threshold)),
-                int(options().median_full_length*(
-                    1 + options().backbone_threshold)))
+            if options().full_length_range is not None:
+                L = sorted(int(x) for x in options().full_length_range.split())
+                min_length = L[0]
+                max_length = L[1]
+            else:   
+                (min_length, max_length) = (
+                    int(options().median_full_length * (
+                        1 - options().backbone_threshold)),
+                    int(options().median_full_length*(
+                        1 + options().backbone_threshold)))
+            _LOG.info("Full length sequences are set to be from %d to %d character long" % (min_length,max_length))
             frag_names = [
                 name for name in sequences
                 if len(sequences[name]) > max_length or
@@ -383,6 +388,11 @@ def augment_parser():
         default=10,
         help="max alignment subset size of N "
              "[default: 10]")
+    decompGroup.add_argument(
+        "-R", "--full_length_range",type=str,
+        dest="full_length_range", metavar="\"Nmin Nmax\"",
+        default=None,
+        help="Only consider sequences with lengths within Nmin and Nmax")
     decompGroup.add_argument(
         "-M", "--median_full_length", type=int,
         dest="median_full_length", metavar="N",

sepp/metagenomics.py

@@ -229,7 +229,7 @@ def distribution(classification_files, output_dir):
                 assert frag_info['phylum']['unclassified'] != 1
                 for clade, cladeval in frag_info.items():
                     for clade_name, cnc in cladeval.items():
-                        if cnc not in distribution[clade]:
+                        if clade_name not in distribution[clade]:
                             distribution[clade][clade_name] = 0
                         distribution[clade][clade_name] += cnc
                 frag_info = {"species": {'unclassified': 1},

setup.py

@@ -30,7 +30,7 @@
 from distutils.spawn import find_executable
 
 use_setuptools(version="0.6.24")
-version = "4.3.13"
+version = "4.3.15"
 
 
 def get_tools_dir(where):

tools/merge/src/phylolab/taxonamic/JSONMerger.java

@@ -394,7 +394,9 @@ public int compare(JSONArray o1, JSONArray o2) {
             return (int) o;
           }
         });
-        sortedPlacements.addAll(placements);
+        for (Iterator<JSONArray> it=placements.iterator() ; it.hasNext() ;) {
+          sortedPlacements.add(it.next());
+        }
         double total = 0;
         ArrayList < JSONArray > list = new ArrayList < JSONArray > ();
         for (Iterator < JSONArray > itp = sortedPlacements.iterator(); threshold > total && itp.hasNext();) {          
@@ -565,7 +567,9 @@ public int compare(JSONObject o1, JSONObject o2) {
           return name1.compareTo(name2);
         }
       });
-      sortedPlacements.addAll(resultsPlacements);
+      for (int i=0 ; i<resultsPlacements.size() ; i++) {
+        sortedPlacements.add(resultsPlacements.getJSONObject(i));
+      }
       resultsPlacements = new JSONArray();
       resultsPlacements.addAll(sortedPlacements);
     }

tools/merge/src/phylolab/taxonamic/PPlacerJSONMerger.java

@@ -317,7 +317,9 @@ public int compare(JSONObject o1, JSONObject o2) {
 						return name1.compareTo(name2);
 					}
 				});
-			    sortedPlacements.addAll(resultsPlacements);
+                            for (int i=0 ; i<resultsPlacements.size() ; i++) {
+                              sortedPlacements.add(resultsPlacements.getJSONObject(i));
+                            }
 			    resultsPlacements = new JSONArray();
 			    resultsPlacements.addAll(sortedPlacements);
 			}