Factor out docstring dedenting from inspect.getdoc() into inspect.cleandoc()

to ease standalone use of the algorithm.

Doc/library/_ast.rst

-.. _ast:
-
-Abstract Syntax Trees
-=====================
-
-.. module:: _ast
-   :synopsis: Abstract Syntax Tree classes.
-
-.. sectionauthor:: Martin v. Löwis <martin@v.loewis.de>
-
-
-.. versionadded:: 2.5
-
-The ``_ast`` module helps Python applications to process trees of the Python
-abstract syntax grammar.  The abstract syntax itself might change with each
-Python release; this module helps to find out programmatically what the current
-grammar looks like.
-
-An abstract syntax tree can be generated by passing :data:`_ast.PyCF_ONLY_AST`
-as a flag to the :func:`compile` builtin function. The result will be a tree of
-objects whose classes all inherit from :class:`_ast.AST`.
-
-A modified abstract syntax tree can be compiled into a Python code object using
-the built-in :func:`compile` function.
-
-The actual classes are derived from the ``Parser/Python.asdl`` file, which is
-reproduced below. There is one class defined for each left-hand side symbol in
-the abstract grammar (for example, ``_ast.stmt`` or ``_ast.expr``). In addition,
-there is one class defined for each constructor on the right-hand side; these
-classes inherit from the classes for the left-hand side trees. For example,
-``_ast.BinOp`` inherits from ``_ast.expr``. For production rules with
-alternatives (aka "sums"), the left-hand side class is abstract: only instances
-of specific constructor nodes are ever created.
-
-Each concrete class has an attribute ``_fields`` which gives the names of all
-child nodes.
-
-Each instance of a concrete class has one attribute for each child node, of the
-type as defined in the grammar. For example, ``_ast.BinOp`` instances have an
-attribute ``left`` of type ``_ast.expr``.   Instances of ``_ast.expr`` and
-``_ast.stmt`` subclasses also have lineno and col_offset attributes.  The lineno
-is the line number of source text (1 indexed so the first line is line 1) and
-the col_offset is the utf8 byte offset of the first token that generated the
-node.  The utf8 offset is recorded because the parser uses utf8 internally.
-
-If these attributes are marked as optional in the grammar (using a question
-mark), the value might be ``None``. If the attributes can have zero-or-more
-values (marked with an asterisk), the values are represented as Python lists.
-All possible attributes must be present and have valid values when compiling an
-AST with :func:`compile`.
-
-The constructor of a class ``_ast.T`` parses their arguments as follows:
-
-* If there are positional arguments, there must be as many as there are items in
-  ``T._fields``; they will be assigned as attributes of these names.
-* If there are keyword arguments, they will set the attributes of the same names
-  to the given values.
-
-For example, to create and populate a ``UnaryOp`` node, you could use ::
-
-   node = _ast.UnaryOp()
-   node.op = _ast.USub()
-   node.operand = _ast.Num()
-   node.operand.n = 5
-   node.operand.lineno = 0
-   node.operand.col_offset = 0
-   node.lineno = 0
-   node.col_offset = 0
-
-or the more compact ::
-
-   node = _ast.UnaryOp(_ast.USub(), _ast.Num(5, lineno=0, col_offset=0),
-                       lineno=0, col_offset=0)
-
-
-
-Abstract Grammar
-----------------
-
-The module defines a string constant ``__version__`` which is the decimal
-subversion revision number of the file shown below.
-
-The abstract grammar is currently defined as follows:
-
-.. literalinclude:: ../../Parser/Python.asdl

Doc/library/inspect.rst

@@ -376,13 +376,9 @@ Note:
 Retrieving source code
 ----------------------
 
-
 .. function:: getdoc(object)
 
-   Get the documentation string for an object. All tabs are expanded to spaces.  To
-   clean up docstrings that are indented to line up with blocks of code, any
-   whitespace than can be uniformly removed from the second line onwards is
-   removed.
+   Get the documentation string for an object, cleaned up with :func:`cleandoc`.
 
 
 .. function:: getcomments(object)
@@ -429,6 +425,15 @@ Retrieving source code
    cannot be retrieved.
 
 
+.. function:: cleandoc(doc)
+
+   Clean up indentation from docstrings that are indented to line up with blocks
+   of code.  Any whitespace that can be uniformly removed from the second line
+   onwards is removed.  Also, all tabs are expanded to spaces.
+
+   .. versionadded:: 2.6
+
+
 .. _inspect-classes-functions:
 
 Classes and functions

Doc/library/language.rst

@@ -15,7 +15,7 @@ These modules include:
 .. toctree::
 
    parser.rst
-   _ast.rst
+   ast.rst
    symbol.rst
    token.rst
    keyword.rst

Lib/inspect.py

@@ -368,6 +368,13 @@ def getdoc(object):
         return None
     if not isinstance(doc, types.StringTypes):
         return None
+    return cleandoc(doc)
+
+def cleandoc(doc):
+    """Clean up indentation from docstrings.
+
+    Any whitespace that can be uniformly removed from the second line
+    onwards is removed."""
     try:
         lines = string.split(string.expandtabs(doc), '\n')
     except UnicodeError:

Lib/test/test_ast.py

 import sys, itertools, unittest
 from test import test_support
-import _ast
+import ast
 
 def to_tuple(t):
     if t is None or isinstance(t, (basestring, int, long, complex)):
@@ -123,9 +123,9 @@ eval_tests = [
 class AST_Tests(unittest.TestCase):
 
     def _assert_order(self, ast_node, parent_pos):
-        if not isinstance(ast_node, _ast.AST) or ast_node._fields is None:
+        if not isinstance(ast_node, ast.AST) or ast_node._fields is None:
             return
-        if isinstance(ast_node, (_ast.expr, _ast.stmt, _ast.excepthandler)):
+        if isinstance(ast_node, (ast.expr, ast.stmt, ast.excepthandler)):
             node_pos = (ast_node.lineno, ast_node.col_offset)
             self.assert_(node_pos >= parent_pos)
             parent_pos = (ast_node.lineno, ast_node.col_offset)
@@ -142,29 +142,29 @@ class AST_Tests(unittest.TestCase):
                                     (single_tests, single_results, "single"),
                                     (eval_tests, eval_results, "eval")):
             for i, o in itertools.izip(input, output):
-                ast_tree = compile(i, "?", kind, _ast.PyCF_ONLY_AST)
+                ast_tree = compile(i, "?", kind, ast.PyCF_ONLY_AST)
                 self.assertEquals(to_tuple(ast_tree), o)
                 self._assert_order(ast_tree, (0, 0))
 
     def test_nodeclasses(self):
-        x = _ast.BinOp(1, 2, 3, lineno=0)
+        x = ast.BinOp(1, 2, 3, lineno=0)
         self.assertEquals(x.left, 1)
         self.assertEquals(x.op, 2)
         self.assertEquals(x.right, 3)
         self.assertEquals(x.lineno, 0)
 
         # node raises exception when not given enough arguments
-        self.assertRaises(TypeError, _ast.BinOp, 1, 2)
+        self.assertRaises(TypeError, ast.BinOp, 1, 2)
 
         # can set attributes through kwargs too
-        x = _ast.BinOp(left=1, op=2, right=3, lineno=0)
+        x = ast.BinOp(left=1, op=2, right=3, lineno=0)
         self.assertEquals(x.left, 1)
         self.assertEquals(x.op, 2)
         self.assertEquals(x.right, 3)
         self.assertEquals(x.lineno, 0)
 
         # this used to fail because Sub._fields was None
-        x = _ast.Sub()
+        x = ast.Sub()
 
     def test_pickling(self):
         import pickle
@@ -181,8 +181,99 @@ class AST_Tests(unittest.TestCase):
                     ast2 = mod.loads(mod.dumps(ast, protocol))
                     self.assertEquals(to_tuple(ast2), to_tuple(ast))
 
+
+class ASTHelpers_Test(unittest.TestCase):
+
+    def test_parse(self):
+        a = ast.parse('foo(1 + 1)')
+        b = compile('foo(1 + 1)', '<unknown>', 'exec', ast.PyCF_ONLY_AST)
+        self.assertEqual(ast.dump(a), ast.dump(b))
+
+    def test_dump(self):
+        node = ast.parse('spam(eggs, "and cheese")')
+        self.assertEqual(ast.dump(node),
+            "Module(body=[Expr(value=Call(func=Name(id='spam', ctx=Load()), "
+            "args=[Name(id='eggs', ctx=Load()), Str(s='and cheese')], "
+            "keywords=[], starargs=None, kwargs=None))])"
+        )
+        self.assertEqual(ast.dump(node, annotate_fields=False),
+            "Module([Expr(Call(Name('spam', Load()), [Name('eggs', Load()), "
+            "Str('and cheese')], [], None, None))])"
+        )
+        self.assertEqual(ast.dump(node, include_attributes=True),
+            "Module(body=[Expr(value=Call(func=Name(id='spam', ctx=Load(), "
+            "lineno=1, col_offset=0), args=[Name(id='eggs', ctx=Load(), "
+            "lineno=1, col_offset=5), Str(s='and cheese', lineno=1, "
+            "col_offset=11)], keywords=[], starargs=None, kwargs=None, "
+            "lineno=1, col_offset=0), lineno=1, col_offset=0)])"
+        )
+
+    def test_copy_location(self):
+        src = ast.parse('1 + 1', mode='eval')
+        src.body.right = ast.copy_location(ast.Num(2), src.body.right)
+        self.assertEqual(ast.dump(src, include_attributes=True),
+            'Expression(body=BinOp(left=Num(n=1, lineno=1, col_offset=0), '
+            'op=Add(), right=Num(n=2, lineno=1, col_offset=4), lineno=1, '
+            'col_offset=0))'
+        )
+
+    def test_fix_missing_locations(self):
+        src = ast.parse('write("spam")')
+        src.body.append(ast.Expr(ast.Call(ast.Name('spam', ast.Load()),
+                                          [ast.Str('eggs')], [], None, None)))
+        self.assertEqual(src, ast.fix_missing_locations(src))
+        self.assertEqual(ast.dump(src, include_attributes=True),
+            "Module(body=[Expr(value=Call(func=Name(id='write', ctx=Load(), "
+            "lineno=1, col_offset=0), args=[Str(s='spam', lineno=1, "
+            "col_offset=6)], keywords=[], starargs=None, kwargs=None, "
+            "lineno=1, col_offset=0), lineno=1, col_offset=0), "
+            "Expr(value=Call(func=Name(id='spam', ctx=Load(), lineno=1, "
+            "col_offset=0), args=[Str(s='eggs', lineno=1, col_offset=0)], "
+            "keywords=[], starargs=None, kwargs=None, lineno=1, "
+            "col_offset=0), lineno=1, col_offset=0)])"
+        )
+
+    def test_increment_lineno(self):
+        src = ast.parse('1 + 1', mode='eval')
+        self.assertEqual(ast.increment_lineno(src, n=3), src)
+        self.assertEqual(ast.dump(src, include_attributes=True),
+            'Expression(body=BinOp(left=Num(n=1, lineno=4, col_offset=0), '
+            'op=Add(), right=Num(n=1, lineno=4, col_offset=4), lineno=4, '
+            'col_offset=0))'
+        )
+
+    def test_iter_fields(self):
+        node = ast.parse('foo()', mode='eval')
+        d = dict(ast.iter_fields(node.body))
+        self.assertEqual(d.pop('func').id, 'foo')
+        self.assertEqual(d, {'keywords': [], 'kwargs': None,
+                             'args': [], 'starargs': None})
+
+    def test_iter_child_nodes(self):
+        node = ast.parse("spam(23, 42, eggs='leek')", mode='eval')
+        self.assertEqual(len(list(ast.iter_child_nodes(node.body))), 4)
+        iterator = ast.iter_child_nodes(node.body)
+        self.assertEqual(next(iterator).id, 'spam')
+        self.assertEqual(next(iterator).n, 23)
+        self.assertEqual(next(iterator).n, 42)
+        self.assertEqual(ast.dump(next(iterator)),
+            "keyword(arg='eggs', value=Str(s='leek'))"
+        )
+
+    def test_get_docstring(self):
+        node = ast.parse('def foo():\n  """line one\n  line two"""')
+        self.assertEqual(ast.get_docstring(node.body[0]),
+                         'line one\n  line two')
+
+    def test_literal_eval(self):
+        self.assertEqual(ast.literal_eval('[1, 2, 3]'), [1, 2, 3])
+        self.assertEqual(ast.literal_eval('{"foo": 42}'), {"foo": 42})
+        self.assertEqual(ast.literal_eval('(True, False, None)'), (True, False, None))
+        self.assertRaises(ValueError, ast.literal_eval, 'foo()')
+
+
 def test_main():
-    test_support.run_unittest(AST_Tests)
+    test_support.run_unittest(AST_Tests, ASTHelpers_Test)
 
 def main():
     if __name__ != '__main__':

Lib/test/test_inspect.py

@@ -185,6 +185,10 @@ class TestRetrievingSourceCode(GetSourceBase):
         self.assertEqual(inspect.getdoc(git.abuse),
                          'Another\n\ndocstring\n\ncontaining\n\ntabs')
 
+    def test_cleandoc(self):
+        self.assertEqual(inspect.cleandoc('An\n    indented\n    docstring.'),
+                         'An\nindented\ndocstring.')
+
     def test_getcomments(self):
         self.assertEqual(inspect.getcomments(mod), '# line 1\n')
         self.assertEqual(inspect.getcomments(mod.StupidGit), '# line 20\n')

Misc/NEWS

@@ -72,6 +72,9 @@ Extension Modules
 Library
 -------
 
+- Factored out the indentation cleaning from inspect.getdoc() into
+  inspect.cleandoc() to ease standalone use.
+
 - Issue #1798: Add ctypes calling convention that allows safe access
   to errno.