- Some changes to how the :attr:`.FromClause.c` collection behaves

when presented with duplicate columns.  The behavior of emitting a
warning and replacing the old column with the same name still
remains to some degree; the replacement in particular is to maintain
backwards compatibility.  However, the replaced column still remains
associated with the ``c`` collection now in a collection ``._all_columns``,
which is used by constructs such as aliases and unions, to deal with
the set of columns in ``c`` more towards what is actually in the
list of columns rather than the unique set of key names.  This helps
with situations where SELECT statements with same-named columns
are used in unions and such, so that the union can match the columns
up positionally and also there's some chance of :meth:`.FromClause.corresponding_column`
still being usable here (it can now return a column that is only
in selectable.c._all_columns and not otherwise named).
The new collection is underscored as we still need to decide where this
list might end up.   Theoretically it
would become the result of iter(selectable.c), however this would mean
that the length of the iteration would no longer match the length of
keys(), and that behavior needs to be checked out.
fixes #2974
- add a bunch more tests for ColumnCollection

2 files changed, 54 insertions, 32 deletions

diff --git a/lib/sqlalchemy/sql/base.py b/lib/sqlalchemy/sql/base.py
index 260cdab66..c2bdd8b1c 100644
--- a/lib/sqlalchemy/sql/base.py
+++ b/lib/sqlalchemy/sql/base.py
@@ -435,10 +435,10 @@ class ColumnCollection(util.OrderedProperties):
 
     """
 
-    def __init__(self, *cols):
+    def __init__(self):
         super(ColumnCollection, self).__init__()
-        self._data.update((c.key, c) for c in cols)
-        self.__dict__['_all_cols'] = util.column_set(self)
+        self.__dict__['_all_col_set'] = util.column_set()
+        self.__dict__['_all_columns'] = []
 
     def __str__(self):
         return repr([str(c) for c in self])
@@ -459,15 +459,26 @@ class ColumnCollection(util.OrderedProperties):
            Used by schema.Column to override columns during table reflection.
 
         """
+        remove_col = None
         if column.name in self and column.key != column.name:
             other = self[column.name]
             if other.name == other.key:
-                del self._data[other.name]
-                self._all_cols.remove(other)
+                remove_col = other
+                self._all_col_set.remove(other)
+                del self._data[other.key]
+
         if column.key in self._data:
-            self._all_cols.remove(self._data[column.key])
-        self._all_cols.add(column)
+            remove_col = self._data[column.key]
+            self._all_col_set.remove(remove_col)
+
+        self._all_col_set.add(column)
         self._data[column.key] = column
+        if remove_col is not None:
+            self._all_columns[:] = [column if c is remove_col
+                                            else c for c in self._all_columns]
+        else:
+            self._all_columns.append(column)
+
 
     def add(self, column):
         """Add a column to this collection.
@@ -497,37 +508,41 @@ class ColumnCollection(util.OrderedProperties):
                           '%r, which has the same key.  Consider '
                           'use_labels for select() statements.' % (key,
                           getattr(existing, 'table', None), value))
-            self._all_cols.remove(existing)
+
             # pop out memoized proxy_set as this
             # operation may very well be occurring
             # in a _make_proxy operation
             util.memoized_property.reset(value, "proxy_set")
-        self._all_cols.add(value)
+
+        self._all_col_set.add(value)
+        self._all_columns.append(value)
         self._data[key] = value
 
     def clear(self):
-        self._data.clear()
-        self._all_cols.clear()
+        raise NotImplementedError()
 
     def remove(self, column):
-        del self._data[column.key]
-        self._all_cols.remove(column)
+        raise NotImplementedError()
 
-    def update(self, value):
-        self._data.update(value)
-        self._all_cols.clear()
-        self._all_cols.update(self._data.values())
+    def update(self, iter):
+        cols = list(iter)
+        self._all_columns.extend(c for label, c in cols)
+        self._all_col_set.update(c for label, c in cols)
+        self._data.update((label, c) for label, c in cols)
 
     def extend(self, iter):
-        self.update((c.key, c) for c in iter)
+        cols = list(iter)
+        self._all_columns.extend(cols)
+        self._all_col_set.update(cols)
+        self._data.update((c.key, c) for c in cols)
 
     __hash__ = None
 
     @util.dependencies("sqlalchemy.sql.elements")
     def __eq__(self, elements, other):
         l = []
-        for c in other:
-            for local in self:
+        for c in getattr(other, "_all_columns", other):
+            for local in self._all_columns:
                 if c.shares_lineage(local):
                     l.append(c == local)
         return elements.and_(*l)
@@ -537,22 +552,28 @@ class ColumnCollection(util.OrderedProperties):
             raise exc.ArgumentError("__contains__ requires a string argument")
         return util.OrderedProperties.__contains__(self, other)
 
+    def __getstate__(self):
+        return {'_data': self.__dict__['_data'],
+                '_all_columns': self.__dict__['_all_columns']}
+
     def __setstate__(self, state):
         self.__dict__['_data'] = state['_data']
-        self.__dict__['_all_cols'] = util.column_set(self._data.values())
+        self.__dict__['_all_columns'] = state['_all_columns']
+        self.__dict__['_all_col_set'] = util.column_set(state['_all_columns'])
 
     def contains_column(self, col):
         # this has to be done via set() membership
-        return col in self._all_cols
+        return col in self._all_col_set
 
     def as_immutable(self):
-        return ImmutableColumnCollection(self._data, self._all_cols)
+        return ImmutableColumnCollection(self._data, self._all_col_set, self._all_columns)
 
 
 class ImmutableColumnCollection(util.ImmutableProperties, ColumnCollection):
-    def __init__(self, data, colset):
+    def __init__(self, data, colset, all_columns):
         util.ImmutableProperties.__init__(self, data)
-        self.__dict__['_all_cols'] = colset
+        self.__dict__['_all_col_set'] = colset
+        self.__dict__['_all_columns'] = all_columns
 
     extend = remove = util.ImmutableProperties._immutable
 
diff --git a/lib/sqlalchemy/sql/selectable.py b/lib/sqlalchemy/sql/selectable.py
index 59d6687b5..d59b45fae 100644
--- a/lib/sqlalchemy/sql/selectable.py
+++ b/lib/sqlalchemy/sql/selectable.py
@@ -342,7 +342,7 @@ class FromClause(Selectable):
             return column
         col, intersect = None, None
         target_set = column.proxy_set
-        cols = self.c
+        cols = self.c._all_columns
         for c in cols:
             expanded_proxy_set = set(_expand_cloned(c.proxy_set))
             i = target_set.intersection(expanded_proxy_set)
@@ -934,6 +934,7 @@ class Alias(FromClause):
                     or 'anon'))
         self.name = name
 
+
     @property
     def description(self):
         if util.py3k:
@@ -954,7 +955,7 @@ class Alias(FromClause):
         return self.element.is_derived_from(fromclause)
 
     def _populate_column_collection(self):
-        for col in self.element.columns:
+        for col in self.element.columns._all_columns:
             col._make_proxy(self)
 
     def _refresh_for_new_column(self, column):
@@ -1738,13 +1739,13 @@ class CompoundSelect(GenerativeSelect):
             s = _clause_element_as_expr(s)
 
             if not numcols:
-                numcols = len(s.c)
-            elif len(s.c) != numcols:
+                numcols = len(s.c._all_columns)
+            elif len(s.c._all_columns) != numcols:
                 raise exc.ArgumentError('All selectables passed to '
                         'CompoundSelect must have identical numbers of '
                         'columns; select #%d has %d columns, select '
-                        '#%d has %d' % (1, len(self.selects[0].c), n
-                        + 1, len(s.c)))
+                        '#%d has %d' % (1, len(self.selects[0].c._all_columns), n
+                        + 1, len(s.c._all_columns)))
 
             self.selects.append(s.self_group(self))
 
@@ -1876,7 +1877,7 @@ class CompoundSelect(GenerativeSelect):
         return False
 
     def _populate_column_collection(self):
-        for cols in zip(*[s.c for s in self.selects]):
+        for cols in zip(*[s.c._all_columns for s in self.selects]):
 
             # this is a slightly hacky thing - the union exports a
             # column that resembles just that of the *first* selectable.