[Python-checkins] r69480 - in python/trunk: Doc/library/collections.rst Lib/collections.py Lib/test/test_collections.py Misc/NEWS

[raymond.hettinger]

Author: raymond.hettinger
Date: Tue Feb 10 02:24:05 2009
New Revision: 69480

Log:
Issue 1818: collections.namedtuple() to support automatic renaming of invalid fieldnames.

Modified:
   python/trunk/Doc/library/collections.rst
   python/trunk/Lib/collections.py
   python/trunk/Lib/test/test_collections.py
   python/trunk/Misc/NEWS

Modified: python/trunk/Doc/library/collections.rst
==============================================================================
--- python/trunk/Doc/library/collections.rst	(original)
+++ python/trunk/Doc/library/collections.rst	Tue Feb 10 02:24:05 2009
@@ -617,7 +617,7 @@
 self-documenting code.  They can be used wherever regular tuples are used, and
 they add the ability to access fields by name instead of position index.
 
-.. function:: namedtuple(typename, field_names, [verbose])
+.. function:: namedtuple(typename, field_names, [verbose], [rename])
 
    Returns a new tuple subclass named *typename*.  The new subclass is used to
    create tuple-like objects that have fields accessible by attribute lookup as
@@ -635,6 +635,11 @@
    a :mod:`keyword` such as *class*, *for*, *return*, *global*, *pass*, *print*,
    or *raise*.
 
+   If *rename* is true, invalid fieldnames are automatically replaced
+   with positional names.  For example, ``['abc', 'def', 'ghi', 'abc']`` is
+   converted to ``['abc', '_2', 'ghi', '_4']``, eliminating the keyword
+   ``def`` and the duplicate fieldname ``abc``.
+
    If *verbose* is true, the class definition is printed just before being built.
 
    Named tuple instances do not have per-instance dictionaries, so they are
@@ -642,6 +647,9 @@
 
    .. versionadded:: 2.6
 
+   .. versionchanged:: 2.7
+      added support for *rename*.
+
 Example:
 
 .. doctest::

Modified: python/trunk/Lib/collections.py
==============================================================================
--- python/trunk/Lib/collections.py	(original)
+++ python/trunk/Lib/collections.py	Tue Feb 10 02:24:05 2009
@@ -16,7 +16,7 @@
 ### namedtuple
 ################################################################################
 
-def namedtuple(typename, field_names, verbose=False):
+def namedtuple(typename, field_names, verbose=False, rename=False):
     """Returns a new subclass of tuple with named fields.
 
     >>> Point = namedtuple('Point', 'x y')
@@ -45,6 +45,16 @@
     if isinstance(field_names, basestring):
         field_names = field_names.replace(',', ' ').split() # names separated by whitespace and/or commas
     field_names = tuple(map(str, field_names))
+    if rename:
+        names = list(field_names)
+        seen = set()
+        for i, name in enumerate(names):
+            if (not all(c.isalnum() or c=='_' for c in name) or _iskeyword(name)
+                or not name or name[0].isdigit() or name.startswith('_')
+                or name in seen):
+                names[i] = '_%d' % (i+1)
+            seen.add(name)
+        field_names = tuple(names)
     for name in (typename,) + field_names:
         if not all(c.isalnum() or c=='_' for c in name):
             raise ValueError('Type names and field names can only contain alphanumeric characters and underscores: %r' % name)
@@ -54,7 +64,7 @@
             raise ValueError('Type names and field names cannot start with a number: %r' % name)
     seen_names = set()
     for name in field_names:
-        if name.startswith('_'):
+        if name.startswith('_') and not rename:
             raise ValueError('Field names cannot start with an underscore: %r' % name)
         if name in seen_names:
             raise ValueError('Encountered duplicate field name: %r' % name)

Modified: python/trunk/Lib/test/test_collections.py
==============================================================================
--- python/trunk/Lib/test/test_collections.py	(original)
+++ python/trunk/Lib/test/test_collections.py	Tue Feb 10 02:24:05 2009
@@ -44,6 +44,17 @@
         self.assertRaises(TypeError, Point._make, [11])                     # catch too few args
         self.assertRaises(TypeError, Point._make, [11, 22, 33])             # catch too many args
 
+    def test_name_fixer(self):
+        for spec, renamed in [
+            [('efg', 'g%hi'),  ('efg', '_2')],                              # field with non-alpha char
+            [('abc', 'class'), ('abc', '_2')],                              # field has keyword
+            [('8efg', '9ghi'), ('_1', '_2')],                               # field starts with digit
+            [('abc', '_efg'), ('abc', '_2')],                               # field with leading underscore
+            [('abc', 'efg', 'efg', 'ghi'), ('abc', 'efg', '_3', 'ghi')],    # duplicate field
+            [('abc', '', 'x'), ('abc', '_2', 'x')],                         # fieldname is a space
+        ]:
+            self.assertEqual(namedtuple('NT', spec, rename=True)._fields, renamed)
+
     def test_instance(self):
         Point = namedtuple('Point', 'x y')
         p = Point(11, 22)

Modified: python/trunk/Misc/NEWS
==============================================================================
--- python/trunk/Misc/NEWS	(original)
+++ python/trunk/Misc/NEWS	Tue Feb 10 02:24:05 2009
@@ -155,6 +155,10 @@
 - Issue #5122: Synchronize tk load failure check to prevent a potential
   deadlock.
 
+- Issue #1818: collections.namedtuple() now supports a keyword argument
+  'rename' which lets invalid fieldnames be automatically converted to
+  positional names in the form, _1, _2, ...
+
 - Issue #4890: Handle empty text search pattern in Tkinter.Text.search.
 
 - Issue #5170: Fixed Unicode output bug in logging and added test case.