commonnexus 1.8.0__tar.gz → 1.9.1__tar.gz

{commonnexus-1.8.0 → commonnexus-1.9.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: commonnexus
-Version: 1.8.0
+Version: 1.9.1
 Summary: A nexus (phylogenetics) file reader and writer (.nex, .trees)
 Home-page: https://github.com/dlce-eva/commonnexus
 Author: Robert Forkel
@@ -83,14 +83,15 @@ and writing NEXUS
 >>> print(Nexus.from_blocks(Data.from_data(nex.CHARACTERS.get_matrix())))
 #NEXUS
 BEGIN DATA;
-	DIMENSIONS NCHAR=10;
-	FORMAT DATATYPE=STANDARD MISSING=? GAP=- SYMBOLS="01";
-	MATRIX 
-    t1 1001010000
-    t2 0101000100
-    t3 0011101010
-    t4 0001100001
-    t5 0001100001;
+DIMENSIONS NCHAR=10;
+FORMAT DATATYPE=STANDARD MISSING=? GAP=- SYMBOLS="01";
+MATRIX 
+t1 1001010000
+t2 0101000100
+t3 0011101010
+t4 0001100001
+t5 0001100001
+;
 END;
 ```
 

{commonnexus-1.8.0 → commonnexus-1.9.1}/README.md

@@ -46,14 +46,15 @@ and writing NEXUS
 >>> print(Nexus.from_blocks(Data.from_data(nex.CHARACTERS.get_matrix())))
 #NEXUS
 BEGIN DATA;
-	DIMENSIONS NCHAR=10;
-	FORMAT DATATYPE=STANDARD MISSING=? GAP=- SYMBOLS="01";
-	MATRIX 
-    t1 1001010000
-    t2 0101000100
-    t3 0011101010
-    t4 0001100001
-    t5 0001100001;
+DIMENSIONS NCHAR=10;
+FORMAT DATATYPE=STANDARD MISSING=? GAP=- SYMBOLS="01";
+MATRIX 
+t1 1001010000
+t2 0101000100
+t3 0011101010
+t4 0001100001
+t5 0001100001
+;
 END;
 ```
 

{commonnexus-1.8.0 → commonnexus-1.9.1}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = commonnexus
-version = 1.8.0
+version = 1.9.1
 author = Robert Forkel
 author_email = robert_forkel@eva.mpg.de
 description = A nexus (phylogenetics) file reader and writer (.nex, .trees)

{commonnexus-1.8.0 → commonnexus-1.9.1}/src/commonnexus/__init__.py

@@ -1,4 +1,4 @@
 from .nexus import Nexus, Config  # noqa: F401
 from commonnexus.blocks import Block  # noqa: F401
 
-__version__ = '1.8.0'
+__version__ = '1.9.1'

{commonnexus-1.8.0 → commonnexus-1.9.1}/src/commonnexus/nexus.py

@@ -5,6 +5,7 @@ import collections
 import dataclasses
 
 from .tokenizer import TokenType, iter_tokens, get_name
+from .util import log_or_raise
 from commonnexus.command import Command
 from commonnexus.blocks import Block
 
@@ -45,7 +46,7 @@ class Config:
 
 class Nexus(list):
     """
-    A NEXUS object implemented as list of tokens with methods to access newick constituents.
+    A NEXUS object implemented as list of commands with methods to read and write blocks.
 
     From the spec:
 
@@ -95,6 +96,7 @@ class Nexus(list):
         """
         self.cfg = config or Config(**kw)
         self.trailing_whitespace = []
+        self.leading = []
         self.block_implementations = {}
         for cls in Block.__subclasses__():
             self.block_implementations[cls.__name__.upper()] = cls
@@ -120,7 +122,10 @@ class Nexus(list):
                     if token.is_semicolon:
                         commands.append(Command(tuple(tokens)))
                         tokens = []
-            self.trailing_whitespace = tokens
+            if commands:
+                self.trailing_whitespace = tokens
+            else:
+                self.leading = tokens
             s = commands
         list.__init__(self, s)
 
@@ -211,6 +216,7 @@ class Nexus(list):
             END;
         """
         return NEXUS \
+            + ''.join(str(t) for t in self.leading) \
             + ''.join(''.join(str(t) for t in cmd) for cmd in self) \
             + ''.join(str(t) for t in self.trailing_whitespace)
 
@@ -224,8 +230,10 @@ class Nexus(list):
         p.write_text(text, encoding=self.cfg.encoding)
 
     def iter_comments(self):
+        yield from (t for t in self.leading if t.type == TokenType.COMMENT)
         for cmd in self:
             yield from (t for t in cmd if t.type == TokenType.COMMENT)
+        yield from (t for t in self.trailing_whitespace if t.type == TokenType.COMMENT)
 
     @property
     def comments(self) -> typing.List[str]:
@@ -262,6 +270,8 @@ class Nexus(list):
 
     def validate(self, log=None):
         valid = True
+        if any(t.type not in {TokenType.WHITESPACE, TokenType.COMMENT} for t in self.leading):
+            log_or_raise('Invalid token in preamble', log=log)
         for block in self.iter_blocks():
             #
             # FIXME: we can do a lot of validation here! If block.__commands__ is a list, there is
@@ -269,6 +279,9 @@ class Nexus(list):
             # If Payload.__multivalued__ == False, only one command instance is allowed, ...
             #
             valid = valid and block.validate(log=log)
+        if any(t.type not in {TokenType.WHITESPACE, TokenType.COMMENT}
+               for t in self.trailing_whitespace):
+            log_or_raise('Invalid token in text after the last command', log=log)
         return valid
 
     def get_numbers(self, object_name, items):

{commonnexus-1.8.0 → commonnexus-1.9.1}/src/commonnexus/tools/normalise.py

@@ -20,6 +20,8 @@ In addition, after normalisation, the following assumptions hold:
 import typing
 import collections
 
+import newick
+
 from commonnexus import Nexus
 from commonnexus.blocks.characters import Data
 from commonnexus.blocks import Taxa, Distances, Characters, Trees
@@ -28,15 +30,28 @@ from commonnexus.blocks import Taxa, Distances, Characters, Trees
 def normalise(nexus: Nexus,
               data_to_characters: bool = False,
               strip_comments: bool = False,
-              remove_taxa: typing.Optional[typing.Container[str]] = None) -> Nexus:
+              remove_taxa: typing.Optional[typing.Container[str]] = None,
+              rename_taxa: typing.Optional[
+                  typing.Union[typing.Callable[[str], str], typing.Dict[str, str]]] = None,
+              ) -> Nexus:
     """
+    Normalise a `Nexus` object as described above.
+
     :param nexus: A `Nexus` object to be normalised in-place.
     :param data_to_characters: Flag signaling whether DATA blocks should be converted to CHARACTER \
     blocks.
     :param strip_comments: Flag signaling whether to remove all non-command comments.
     :param remove_taxa: Container of taxon labels specifying taxa to remove from relevant blocks.
+    :param rename_taxa: Specification of taxa to rename; either a ``dict``, mapping old names to \
+    new names, or a callable, accepting the old name as sole argument and returning the new name.
     :return: The modified `Nexus` object.
 
+    .. warning::
+
+        ``remove_taxa`` and ``rename_taxa`` only operate on TAXA, CHARACTERS/DATA, DISTANCES and
+        TREES blocks. Thus, normalisation may result in an inconsistent NEXUS file, if the file
+        contains other blocks which reference taxa (e.g. NOTES).
+
     .. code-block:: python
 
         >>> from commonnexus import Nexus
@@ -94,6 +109,13 @@ def normalise(nexus: Nexus,
     """
     remove_taxa = remove_taxa or []
 
+    def rename_taxon(s):
+        if rename_taxa is None:
+            return s
+        if isinstance(rename_taxa, dict):
+            return rename_taxa.get(s, s)
+        return rename_taxa(s)
+
     if strip_comments:
         nexus = Nexus([cmd.without_comments() for cmd in nexus], config=nexus.cfg)
     nexus = Nexus([cmd.with_normalised_whitespace() for cmd in nexus], config=nexus.cfg)
@@ -102,7 +124,8 @@ def normalise(nexus: Nexus,
     if nexus.characters:
         matrix = nexus.characters.get_matrix()
         taxlabels = list(matrix.keys())
-        matrix = collections.OrderedDict((k, v) for k, v in matrix.items() if k not in remove_taxa)
+        matrix = collections.OrderedDict(
+            (rename_taxon(k), v) for k, v in matrix.items() if k not in remove_taxa)
         characters = nexus.DATA or nexus.CHARACTERS
         cls = Data if characters.name == 'DATA' and not data_to_characters else Characters
         nexus.replace_block(
@@ -116,20 +139,28 @@ def normalise(nexus: Nexus,
         else:
             taxlabels = list(matrix.keys())
         matrix = collections.OrderedDict(
-            (k, collections.OrderedDict((kk, vv) for kk, vv in v.items() if kk not in remove_taxa))
+            (rename_taxon(k), collections.OrderedDict(
+                (rename_taxon(kk), vv) for kk, vv in v.items() if kk not in remove_taxa))
             for k, v in matrix.items() if k not in remove_taxa)
         nexus.replace_block(nexus.DISTANCES, Distances.from_data(matrix))
 
     if nexus.TREES:
+        def rename(n):
+            if n.name:
+                new = rename_taxon(n.unquoted_name)
+                n.name = newick.Node(new, auto_quote=True).name
+
         trees = []
         for tree in nexus.TREES.trees:
             nwk = nexus.TREES.translate(tree) if nexus.TREES.TRANSLATE else tree.newick
             if remove_taxa:
                 nwk.prune_by_names(remove_taxa)
+            nwk.visit(rename)
             trees.append((tree.name, nwk, tree.rooted))
         nexus.replace_block(nexus.TREES, Trees.from_data(*trees))
 
     if taxlabels:
+        taxlabels = [rename_taxon(t) for t in taxlabels]
         taxa = Taxa.from_data([t for t in taxlabels if t not in remove_taxa])
         if nexus.TAXA:
             assert nexus.TAXA.DIMENSIONS.ntax == len(taxlabels)

{commonnexus-1.8.0 → commonnexus-1.9.1}/src/commonnexus.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: commonnexus
-Version: 1.8.0
+Version: 1.9.1
 Summary: A nexus (phylogenetics) file reader and writer (.nex, .trees)
 Home-page: https://github.com/dlce-eva/commonnexus
 Author: Robert Forkel
@@ -83,14 +83,15 @@ and writing NEXUS
 >>> print(Nexus.from_blocks(Data.from_data(nex.CHARACTERS.get_matrix())))
 #NEXUS
 BEGIN DATA;
-	DIMENSIONS NCHAR=10;
-	FORMAT DATATYPE=STANDARD MISSING=? GAP=- SYMBOLS="01";
-	MATRIX 
-    t1 1001010000
-    t2 0101000100
-    t3 0011101010
-    t4 0001100001
-    t5 0001100001;
+DIMENSIONS NCHAR=10;
+FORMAT DATATYPE=STANDARD MISSING=? GAP=- SYMBOLS="01";
+MATRIX 
+t1 1001010000
+t2 0101000100
+t3 0011101010
+t4 0001100001
+t5 0001100001
+;
 END;
 ```
 

{commonnexus-1.8.0 → commonnexus-1.9.1}/tests/test_nexus.py

@@ -161,3 +161,18 @@ def test_Booleans_With_Values(fixture_dir):
 def test_Mesquite_multitaxa(fixture_dir):
     nex = Nexus.from_file(fixture_dir / 'multitaxa_mesquite.nex')
     assert [char.get_matrix() for char in nex.blocks['CHARACTERS']]
+
+
+def test_comments():
+    nex = Nexus('#NEXUS\n[comment]')
+    assert nex.comments == ['comment']
+    nex.append_block(Block.from_commands([], name='b', comment='block comment'))
+    assert nex.comments == ['comment', 'block comment']
+
+    with pytest.raises(ValueError):
+        nex = Nexus('#NEXUS\n[comment]]')
+        nex.validate()
+
+    with pytest.raises(ValueError):
+        nex = Nexus('#NEXUS\nBEGIN b; end;[comment]]')
+        nex.validate()

commonnexus-1.9.1/tests/test_tools_normalise.py

@@ -0,0 +1,185 @@
+from commonnexus import Nexus
+from commonnexus.tools.normalise import normalise
+
+
+def test_normalise(nexus):
+    nex = nexus(
+        CHARACTERS="DIMENSIONS NCHAR=3; MATRIX 't 1' 100 t2 010 t3 001;",
+        DISTANCES="FORMAT NODIAGONAL; MATRIX 't 1' t2  1.0 t3 2.0 3.0;",
+        TREES="TRANSLATE a 't 1', b t2, c t3; TREE 1 = (a,b\n,c);")
+    res = str(normalise(nex))
+    assert res == """#NEXUS
+BEGIN TAXA;
+DIMENSIONS NTAX=3;
+TAXLABELS 't 1' t2 t3;
+END;
+BEGIN CHARACTERS;
+DIMENSIONS NCHAR=3;
+FORMAT DATATYPE=STANDARD MISSING=? GAP=- SYMBOLS="01";
+MATRIX 
+'t 1' 100
+t2    010
+t3    001
+;
+END;
+BEGIN DISTANCES;
+DIMENSIONS NTAX=3;
+FORMAT TRIANGLE=BOTH MISSING=?;
+MATRIX 
+'t 1' 0 1.0 2.0
+t2    1.0 0 3.0
+t3    2.0 3.0 0
+;
+END;
+BEGIN TREES;
+TREE 1 = ('t 1',t2,t3);
+END;"""
+    res = normalise(Nexus(res))
+    assert res.characters.get_matrix()
+    assert res.DISTANCES.get_matrix()
+
+    res.remove_block(res.TAXA)
+    res.remove_block(res.CHARACTERS)
+    res = normalise(res)
+    assert res.TAXA
+
+
+def test_normalise_remove_taxon(nexus):
+    nex = nexus(
+        CHARACTERS="DIMENSIONS NCHAR=3; MATRIX 't 1' 100 t2 010 t3 001;",
+        DISTANCES="FORMAT NODIAGONAL; MATRIX 't 1' t2  1.0 t3 2.0 3.0;",
+        TREES="TRANSLATE a 't 1', b t2, c t3; TREE 1 = (a,b\n,c);")
+    res = str(normalise(nex, remove_taxa={'t2'}))
+    assert res == """#NEXUS
+BEGIN TAXA;
+DIMENSIONS NTAX=2;
+TAXLABELS 't 1' t3;
+END;
+BEGIN CHARACTERS;
+DIMENSIONS NCHAR=3;
+FORMAT DATATYPE=STANDARD MISSING=? GAP=- SYMBOLS="01";
+MATRIX 
+'t 1' 100
+t3    001
+;
+END;
+BEGIN DISTANCES;
+DIMENSIONS NTAX=2;
+FORMAT TRIANGLE=BOTH MISSING=?;
+MATRIX 
+'t 1' 0 2.0
+t3    2.0 0
+;
+END;
+BEGIN TREES;
+TREE 1 = ('t 1',t3);
+END;"""
+
+
+def test_normalise_rename_taxon1(nexus):
+    nex = nexus(
+        CHARACTERS="DIMENSIONS NCHAR=3; MATRIX 't 1' 100 t2 010 t3 001;",
+        DISTANCES="FORMAT NODIAGONAL; MATRIX 't 1' t2  1.0 t3 2.0 3.0;",
+        TREES="TRANSLATE a 't 1', b t2, c t3; TREE 1 = (a,b\n,c);")
+    res = str(normalise(nex, rename_taxa={'t 1': 't1'}))
+    assert res == """#NEXUS
+BEGIN TAXA;
+DIMENSIONS NTAX=3;
+TAXLABELS t1 t2 t3;
+END;
+BEGIN CHARACTERS;
+DIMENSIONS NCHAR=3;
+FORMAT DATATYPE=STANDARD MISSING=? GAP=- SYMBOLS="01";
+MATRIX 
+t1 100
+t2 010
+t3 001
+;
+END;
+BEGIN DISTANCES;
+DIMENSIONS NTAX=3;
+FORMAT TRIANGLE=BOTH MISSING=?;
+MATRIX 
+t1 0 1.0 2.0
+t2 1.0 0 3.0
+t3 2.0 3.0 0
+;
+END;
+BEGIN TREES;
+TREE 1 = (t1,t2,t3);
+END;"""
+
+
+def test_normalise_rename_taxon2(nexus):
+    nex = nexus(
+        CHARACTERS="DIMENSIONS NCHAR=3; MATRIX 't 1' 100 t2 010 t3 001;",
+        DISTANCES="FORMAT NODIAGONAL; MATRIX 't 1' t2  1.0 t3 2.0 3.0;",
+        TREES="TRANSLATE a 't 1', b t2, c t3; TREE 1 = (a,b\n,c);")
+    res = str(normalise(nex, rename_taxa=lambda t: t.replace(' ', '_')))
+    assert res == """#NEXUS
+BEGIN TAXA;
+DIMENSIONS NTAX=3;
+TAXLABELS t_1 t2 t3;
+END;
+BEGIN CHARACTERS;
+DIMENSIONS NCHAR=3;
+FORMAT DATATYPE=STANDARD MISSING=? GAP=- SYMBOLS="01";
+MATRIX 
+t_1 100
+t2  010
+t3  001
+;
+END;
+BEGIN DISTANCES;
+DIMENSIONS NTAX=3;
+FORMAT TRIANGLE=BOTH MISSING=?;
+MATRIX 
+t_1 0 1.0 2.0
+t2  1.0 0 3.0
+t3  2.0 3.0 0
+;
+END;
+BEGIN TREES;
+TREE 1 = (t_1,t2,t3);
+END;"""
+
+
+def test_normalise_rename_taxon3(nexus):
+    nex = nexus(
+        CHARACTERS="DIMENSIONS NCHAR=3; MATRIX 't 1' 100 t2 010 t3 001;",
+        DISTANCES="FORMAT NODIAGONAL; MATRIX 't 1' t2  1.0 t3 2.0 3.0;",
+        TREES="TRANSLATE a 't 1', b t2, c t3; TREE 1 = (a,b\n,c);")
+    res = str(normalise(nex, rename_taxa=lambda t: t.replace(' ', ':')))
+    assert res == """#NEXUS
+BEGIN TAXA;
+DIMENSIONS NTAX=3;
+TAXLABELS 't:1' t2 t3;
+END;
+BEGIN CHARACTERS;
+DIMENSIONS NCHAR=3;
+FORMAT DATATYPE=STANDARD MISSING=? GAP=- SYMBOLS="01";
+MATRIX 
+'t:1' 100
+t2    010
+t3    001
+;
+END;
+BEGIN DISTANCES;
+DIMENSIONS NTAX=3;
+FORMAT TRIANGLE=BOTH MISSING=?;
+MATRIX 
+'t:1' 0 1.0 2.0
+t2    1.0 0 3.0
+t3    2.0 3.0 0
+;
+END;
+BEGIN TREES;
+TREE 1 = ('t:1',t2,t3);
+END;"""
+
+
+def test_normalise_stripcomments():
+    res = normalise(Nexus('#nexus beg[c]in bl[&c]ock; cmd; end[c];'), strip_comments=True)
+    assert '[c]' not in str(res)
+    assert '[&c]' in str(res)
+    assert res.BLOCK

commonnexus-1.8.0/tests/test_tools_normalise.py

@@ -1,83 +0,0 @@
-from commonnexus import Nexus
-from commonnexus.tools.normalise import normalise
-
-
-def test_normalise(nexus):
-    nex = nexus(
-        CHARACTERS="DIMENSIONS NCHAR=3; MATRIX 't 1' 100 t2 010 t3 001;",
-        DISTANCES="FORMAT NODIAGONAL; MATRIX 't 1' t2  1.0 t3 2.0 3.0;",
-        TREES="TRANSLATE a 't 1', b t2, c t3; TREE 1 = (a,b\n,c);")
-    res = str(normalise(nex))
-    assert res == """#NEXUS
-BEGIN TAXA;
-DIMENSIONS NTAX=3;
-TAXLABELS 't 1' t2 t3;
-END;
-BEGIN CHARACTERS;
-DIMENSIONS NCHAR=3;
-FORMAT DATATYPE=STANDARD MISSING=? GAP=- SYMBOLS="01";
-MATRIX 
-'t 1' 100
-t2    010
-t3    001
-;
-END;
-BEGIN DISTANCES;
-DIMENSIONS NTAX=3;
-FORMAT TRIANGLE=BOTH MISSING=?;
-MATRIX 
-'t 1' 0 1.0 2.0
-t2    1.0 0 3.0
-t3    2.0 3.0 0
-;
-END;
-BEGIN TREES;
-TREE 1 = ('t 1',t2,t3);
-END;"""
-    res = normalise(Nexus(res))
-    assert res.characters.get_matrix()
-    assert res.DISTANCES.get_matrix()
-
-    res.remove_block(res.TAXA)
-    res.remove_block(res.CHARACTERS)
-    res = normalise(res)
-    assert res.TAXA
-
-
-def test_normalise_remove_taxon(nexus):
-    nex = nexus(
-        CHARACTERS="DIMENSIONS NCHAR=3; MATRIX 't 1' 100 t2 010 t3 001;",
-        DISTANCES="FORMAT NODIAGONAL; MATRIX 't 1' t2  1.0 t3 2.0 3.0;",
-        TREES="TRANSLATE a 't 1', b t2, c t3; TREE 1 = (a,b\n,c);")
-    res = str(normalise(nex, remove_taxa={'t2'}))
-    assert res == """#NEXUS
-BEGIN TAXA;
-DIMENSIONS NTAX=2;
-TAXLABELS 't 1' t3;
-END;
-BEGIN CHARACTERS;
-DIMENSIONS NCHAR=3;
-FORMAT DATATYPE=STANDARD MISSING=? GAP=- SYMBOLS="01";
-MATRIX 
-'t 1' 100
-t3    001
-;
-END;
-BEGIN DISTANCES;
-DIMENSIONS NTAX=2;
-FORMAT TRIANGLE=BOTH MISSING=?;
-MATRIX 
-'t 1' 0 2.0
-t3    2.0 0
-;
-END;
-BEGIN TREES;
-TREE 1 = ('t 1',t3);
-END;"""
-
-
-def test_normalise_stripcomments():
-    res = normalise(Nexus('#nexus beg[c]in bl[&c]ock; cmd; end[c];'), strip_comments=True)
-    assert '[c]' not in str(res)
-    assert '[&c]' in str(res)
-    assert res.BLOCK