be precise, tolist -> tolists, fts.d/todict behave now in the same way as seqs.d/todict, both return a dict {id: ft}

Author: trichter

sugar/core/fts.py

@@ -567,7 +567,7 @@ def tofmtstr(self, fmt, **kw):
         """
         return self.write(None, fmt)
 
-    def tolist(self, vals='type start stop strand'):
+    def tolists(self, vals='type start stop strand'):
         """
         Return a generator yielding a list for each feature
 
@@ -579,7 +579,7 @@ def tolist(self, vals='type start stop strand'):
 
         >>> from sugar import read_fts
         >>> fts = read_fts().select('cDNA_match')
-        >>> for record in fts.tolist('type start strand len'):
+        >>> for record in fts.tolists('type start strand len'):
         ...     print(*record)
         cDNA_match 101888622 - 4245
         cDNA_match 103140200 - 30745
@@ -623,7 +623,7 @@ def topandas(self, vals='type start stop strand', **kw):
         if isinstance(vals, str):
             vals = vals.split()
         kw.setdefault('columns', vals)
-        return pandas.DataFrame(self.tolist(vals=vals), **kw)
+        return pandas.DataFrame(self.tolists(vals=vals), **kw)
 
 
     def get(self, type):
@@ -660,17 +660,15 @@ def select(self, type):
 
     def todict(self):
         """
-        Return a dictionary with sequence ids as keys and FeatureLists as values
+        Return a dictionary with feature ids as keys and features as values
 
-        Similar as ``FeatureList.groupby('seqid')``.
-        The key for features without seqids is set to the empty string ``''``,
-        in the groupyby() method this key is set to ``None``.
+        .. note::
+            This method is different from the `FeatureList.groupby()` method.
+            Each value of the dict returned by ``todict()`` is a feature,
+            whereas each value of the dict returned by ``groupby()`` is a
+            FeatureList.
         """
-        d = {}
-        for ft in self:
-            seqid = ft.meta.get('seqid', '')
-            d.setdefault(seqid, self.__class__()).append(ft)
-        return d
+        return {ft.id: ft for ft in self}
 
     def groupby(self, keys=('seqid',)):
         """
@@ -693,9 +691,9 @@ def groupby(self, keys=('seqid',)):
     @property
     def d(self):
         """
-        Alias for ``FeatureList.groupby('seqid')``
+        Alias for ``FeatureList.todict()``
         """
-        return self.groupby('seqid')
+        return self.todict()
 
     @property
     def loc_range(self):

sugar/core/seq.py

@@ -735,7 +735,7 @@ def fts(self):
 
     @fts.setter
     def fts(self, value):
-        fts = FeatureList(value).todict()
+        fts = FeatureList(value).groupby('seqid')
         for seq in self:
             if seq.id in fts:
                 seq.fts = fts.pop(seq.id)
@@ -752,7 +752,7 @@ def add_fts(self, fts):
 
         :param fts: features to add
         """
-        fts = FeatureList(fts).todict()
+        fts = FeatureList(fts).groupby('seqid')
         for seq in self:
             if seq.id in fts:
                 seq.fts = seq.fts + fts.pop(seq.id)

sugar/tests/test_core_cane.py

@@ -64,7 +64,7 @@ def test_match():
 
 
 def test_orf():
-    seqs=read()
+    seqs = read()
     orfs = seqs[0].find_orfs()
     assert len(orfs) > 0
     longest_orf = orfs.sort(len)[-1]
@@ -75,7 +75,7 @@ def test_orf():
 
     orfs = seqs.find_orfs()
     for id_ in seqs.ids:
-        assert seqs.d[id_][orfs.d[id_].sort(len)[-1]] == seqs.d[id_]['cds']
+        assert seqs.d[id_][orfs.groupby('seqid')[id_].sort(len)[-1]] == seqs.d[id_]['cds']
 
 
 def test_filter_fts():
@@ -99,7 +99,6 @@ def test_filter_seqs():
     assert len(seqs2) < len(seqs)
 
 
-
 def test_groupby_fts_nested():
     fts = read_fts()
     d = fts.groupby(('type', len))

sugar/tests/test_core_fts.py

@@ -38,7 +38,7 @@ def test_fts_str():
 
 def test_fts_d():
     fts = read_fts()
-    assert len(fts.d[fts[0].meta.seqid]) > 0
+    assert fts.d[fts[-1].id] == fts[-1]
 
 
 def test_fts_rc():
@@ -124,9 +124,9 @@ def test_loc_hash():
     assert locs in {locs}
 
 
-def test_fts_tolist():
+def test_fts_tolists():
     fts = read_fts().select('CDS')
-    for type_, start, stop, strand in fts.tolist():
+    for type_, start, stop, strand in fts.tolists():
         assert type_ == 'CDS'
         assert start == 61943
         assert strand == '+'