Merged revisions 61596-61597 via svnmerge from

svn+ssh://pythondev@svn.python.org/python/trunk

........
  r61596 | martin.v.loewis | 2008-03-18 23:43:46 -0500 (Di, 18 Mär 2008) | 2 lines

  Import lib2to3.
........
  r61597 | martin.v.loewis | 2008-03-18 23:58:04 -0500 (Di, 18 Mär 2008) | 3 lines

  Initialized merge tracking via "svnmerge" with revisions "1-61595" from
  svn+ssh://pythondev@svn.python.org/sandbox/trunk/2to3/lib2to3
........

Author: loewis

Lib/lib2to3/Grammar.txt

@@ -0,0 +1,153 @@
+# Grammar for Python
+
+# Note:  Changing the grammar specified in this file will most likely
+#        require corresponding changes in the parser module
+#        (../Modules/parsermodule.c).  If you can't make the changes to
+#        that module yourself, please co-ordinate the required changes
+#        with someone who can; ask around on python-dev for help.  Fred
+#        Drake <fdrake@acm.org> will probably be listening there.
+
+# NOTE WELL: You should also follow all the steps listed in PEP 306,
+# "How to Change Python's Grammar"
+
+# Commands for Kees Blom's railroad program
+#diagram:token NAME
+#diagram:token NUMBER
+#diagram:token STRING
+#diagram:token NEWLINE
+#diagram:token ENDMARKER
+#diagram:token INDENT
+#diagram:output\input python.bla
+#diagram:token DEDENT
+#diagram:output\textwidth 20.04cm\oddsidemargin  0.0cm\evensidemargin 0.0cm
+#diagram:rules
+
+# Start symbols for the grammar:
+#	file_input is a module or sequence of commands read from an input file;
+#	single_input is a single interactive statement;
+#	eval_input is the input for the eval() and input() functions.
+# NB: compound_stmt in single_input is followed by extra NEWLINE!
+file_input: (NEWLINE | stmt)* ENDMARKER
+single_input: NEWLINE | simple_stmt | compound_stmt NEWLINE
+eval_input: testlist NEWLINE* ENDMARKER
+
+decorator: '@' dotted_name [ '(' [arglist] ')' ] NEWLINE
+decorators: decorator+
+decorated: decorators (classdef | funcdef)
+funcdef: 'def' NAME parameters ['->' test] ':' suite
+parameters: '(' [typedargslist] ')'
+typedargslist: ((tfpdef ['=' test] ',')*
+                ('*' [tname] (',' tname ['=' test])* [',' '**' tname] | '**' tname)
+                | tfpdef ['=' test] (',' tfpdef ['=' test])* [','])
+tname: NAME [':' test]
+tfpdef: tname | '(' tfplist ')'
+tfplist: tfpdef (',' tfpdef)* [',']
+varargslist: ((vfpdef ['=' test] ',')*
+              ('*' [vname] (',' vname ['=' test])*  [',' '**' vname] | '**' vname)
+              | vfpdef ['=' test] (',' vfpdef ['=' test])* [','])
+vname: NAME
+vfpdef: vname | '(' vfplist ')'
+vfplist: vfpdef (',' vfpdef)* [',']
+
+stmt: simple_stmt | compound_stmt
+simple_stmt: small_stmt (';' small_stmt)* [';'] NEWLINE
+small_stmt: (expr_stmt | print_stmt  | del_stmt | pass_stmt | flow_stmt |
+             import_stmt | global_stmt | exec_stmt | assert_stmt)
+expr_stmt: testlist (augassign (yield_expr|testlist) |
+                     ('=' (yield_expr|testlist))*)
+augassign: ('+=' | '-=' | '*=' | '/=' | '%=' | '&=' | '|=' | '^=' |
+            '<<=' | '>>=' | '**=' | '//=')
+# For normal assignments, additional restrictions enforced by the interpreter
+print_stmt: 'print' ( [ test (',' test)* [','] ] |
+                      '>>' test [ (',' test)+ [','] ] )
+del_stmt: 'del' exprlist
+pass_stmt: 'pass'
+flow_stmt: break_stmt | continue_stmt | return_stmt | raise_stmt | yield_stmt
+break_stmt: 'break'
+continue_stmt: 'continue'
+return_stmt: 'return' [testlist]
+yield_stmt: yield_expr
+raise_stmt: 'raise' [test ['from' test | ',' test [',' test]]]
+import_stmt: import_name | import_from
+import_name: 'import' dotted_as_names
+import_from: ('from' ('.'* dotted_name | '.'+)
+              'import' ('*' | '(' import_as_names ')' | import_as_names))
+import_as_name: NAME ['as' NAME]
+dotted_as_name: dotted_name ['as' NAME]
+import_as_names: import_as_name (',' import_as_name)* [',']
+dotted_as_names: dotted_as_name (',' dotted_as_name)*
+dotted_name: NAME ('.' NAME)*
+global_stmt: ('global' | 'nonlocal') NAME (',' NAME)*
+exec_stmt: 'exec' expr ['in' test [',' test]]
+assert_stmt: 'assert' test [',' test]
+
+compound_stmt: if_stmt | while_stmt | for_stmt | try_stmt | with_stmt | funcdef | classdef | decorated
+if_stmt: 'if' test ':' suite ('elif' test ':' suite)* ['else' ':' suite]
+while_stmt: 'while' test ':' suite ['else' ':' suite]
+for_stmt: 'for' exprlist 'in' testlist ':' suite ['else' ':' suite]
+try_stmt: ('try' ':' suite
+           ((except_clause ':' suite)+
+	    ['else' ':' suite]
+	    ['finally' ':' suite] |
+	   'finally' ':' suite))
+with_stmt: 'with' test [ with_var ] ':' suite
+with_var: 'as' expr
+# NB compile.c makes sure that the default except clause is last
+except_clause: 'except' [test [(',' | 'as') test]]
+suite: simple_stmt | NEWLINE INDENT stmt+ DEDENT
+
+# Backward compatibility cruft to support:
+# [ x for x in lambda: True, lambda: False if x() ]
+# even while also allowing:
+# lambda x: 5 if x else 2
+# (But not a mix of the two)
+testlist_safe: old_test [(',' old_test)+ [',']]
+old_test: or_test | old_lambdef
+old_lambdef: 'lambda' [varargslist] ':' old_test
+
+test: or_test ['if' or_test 'else' test] | lambdef
+or_test: and_test ('or' and_test)*
+and_test: not_test ('and' not_test)*
+not_test: 'not' not_test | comparison
+comparison: expr (comp_op expr)*
+comp_op: '<'|'>'|'=='|'>='|'<='|'<>'|'!='|'in'|'not' 'in'|'is'|'is' 'not'
+expr: xor_expr ('|' xor_expr)*
+xor_expr: and_expr ('^' and_expr)*
+and_expr: shift_expr ('&' shift_expr)*
+shift_expr: arith_expr (('<<'|'>>') arith_expr)*
+arith_expr: term (('+'|'-') term)*
+term: factor (('*'|'/'|'%'|'//') factor)*
+factor: ('+'|'-'|'~') factor | power
+power: atom trailer* ['**' factor]
+atom: ('(' [yield_expr|testlist_gexp] ')' |
+       '[' [listmaker] ']' |
+       '{' [dictsetmaker] '}' |
+       '`' testlist1 '`' |
+       NAME | NUMBER | STRING+ | '.' '.' '.')
+listmaker: test ( comp_for | (',' test)* [','] )
+testlist_gexp: test ( comp_for | (',' test)* [','] )
+lambdef: 'lambda' [varargslist] ':' test
+trailer: '(' [arglist] ')' | '[' subscriptlist ']' | '.' NAME
+subscriptlist: subscript (',' subscript)* [',']
+subscript: test | [test] ':' [test] [sliceop]
+sliceop: ':' [test]
+exprlist: expr (',' expr)* [',']
+testlist: test (',' test)* [',']
+dictsetmaker: ( (test ':' test (comp_for | (',' test ':' test)* [','])) |
+                (test (comp_for | (',' test)* [','])) )
+
+classdef: 'class' NAME ['(' [arglist] ')'] ':' suite
+
+arglist: (argument ',')* (argument [',']| '*' test [',' '**' test] | '**' test)
+argument: test [comp_for] | test '=' test  # Really [keyword '='] test
+
+comp_iter: comp_for | comp_if
+comp_for: 'for' exprlist 'in' testlist_safe [comp_iter]
+comp_if: 'if' old_test [comp_iter]
+
+testlist1: test (',' test)*
+
+# not used in grammar, but may appear in "node" passed from Parser to Compiler
+encoding_decl: NAME
+
+yield_expr: 'yield' [testlist]

Lib/lib2to3/PatternGrammar.txt

@@ -0,0 +1,28 @@
+# Copyright 2006 Google, Inc. All Rights Reserved.
+# Licensed to PSF under a Contributor Agreement.
+
+# A grammar to describe tree matching patterns.
+# Not shown here:
+# - 'TOKEN' stands for any token (leaf node)
+# - 'any' stands for any node (leaf or interior)
+# With 'any' we can still specify the sub-structure.
+
+# The start symbol is 'Matcher'.
+
+Matcher: Alternatives ENDMARKER
+
+Alternatives: Alternative ('|' Alternative)*
+
+Alternative: (Unit | NegatedUnit)+
+
+Unit: [NAME '='] ( STRING [Repeater]
+                 | NAME [Details] [Repeater]
+                 | '(' Alternatives ')' [Repeater]
+                 | '[' Alternatives ']'
+		 )
+
+NegatedUnit: 'not' (STRING | NAME [Details] | '(' Alternatives ')')
+
+Repeater: '*' | '+' | '{' NUMBER [',' NUMBER] '}'
+
+Details: '<' Alternatives '>'

Lib/lib2to3/__init__.py

@@ -0,0 +1 @@
+#empty

Lib/lib2to3/fixes/__init__.py

@@ -0,0 +1 @@
+# Dummy file to make this directory a package.

Lib/lib2to3/fixes/basefix.py

@@ -0,0 +1,165 @@
+# Copyright 2006 Google, Inc. All Rights Reserved.
+# Licensed to PSF under a Contributor Agreement.
+
+"""Base class for fixers (optional, but recommended)."""
+
+# Python imports
+import logging
+import itertools
+
+# Get a usable 'set' constructor
+try:
+    set
+except NameError:
+    from sets import Set as set
+
+# Local imports
+from ..patcomp import PatternCompiler
+from .. import pygram
+
+class BaseFix(object):
+
+    """Optional base class for fixers.
+
+    The subclass name must be FixFooBar where FooBar is the result of
+    removing underscores and capitalizing the words of the fix name.
+    For example, the class name for a fixer named 'has_key' should be
+    FixHasKey.
+    """
+
+    PATTERN = None  # Most subclasses should override with a string literal
+    pattern = None  # Compiled pattern, set by compile_pattern()
+    options = None  # Options object passed to initializer
+    filename = None # The filename (set by set_filename)
+    logger = None   # A logger (set by set_filename)
+    numbers = itertools.count(1) # For new_name()
+    used_names = set() # A set of all used NAMEs
+    order = "post" # Does the fixer prefer pre- or post-order traversal
+    explicit = False # Is this ignored by refactor.py -f all?
+
+    # Shortcut for access to Python grammar symbols
+    syms = pygram.python_symbols
+
+    def __init__(self, options, log):
+        """Initializer.  Subclass may override.
+
+        Args:
+            options: an optparse.Values instance which can be used
+                to inspect the command line options.
+            log: a list to append warnings and other messages to.
+        """
+        self.options = options
+        self.log = log
+        self.compile_pattern()
+
+    def compile_pattern(self):
+        """Compiles self.PATTERN into self.pattern.
+
+        Subclass may override if it doesn't want to use
+        self.{pattern,PATTERN} in .match().
+        """
+        if self.PATTERN is not None:
+            self.pattern = PatternCompiler().compile_pattern(self.PATTERN)
+
+    def set_filename(self, filename):
+        """Set the filename, and a logger derived from it.
+
+        The main refactoring tool should call this.
+        """
+        self.filename = filename
+        self.logger = logging.getLogger(filename)
+
+    def match(self, node):
+        """Returns match for a given parse tree node.
+
+        Should return a true or false object (not necessarily a bool).
+        It may return a non-empty dict of matching sub-nodes as
+        returned by a matching pattern.
+
+        Subclass may override.
+        """
+        results = {"node": node}
+        return self.pattern.match(node, results) and results
+
+    def transform(self, node, results):
+        """Returns the transformation for a given parse tree node.
+
+        Args:
+          node: the root of the parse tree that matched the fixer.
+          results: a dict mapping symbolic names to part of the match.
+          
+        Returns:
+          None, or a node that is a modified copy of the
+          argument node.  The node argument may also be modified in-place to
+          effect the same change.
+
+        Subclass *must* override.
+        """
+        raise NotImplementedError()
+
+    def parenthesize(self, node):
+        """Wrapper around pygram.parenthesize()."""
+        return pygram.parenthesize(node)
+
+    def new_name(self, template="xxx_todo_changeme"):
+        """Return a string suitable for use as an identifier
+
+        The new name is guaranteed not to conflict with other identifiers.
+        """
+        name = template
+        while name in self.used_names:
+            name = template + str(self.numbers.next())
+        self.used_names.add(name)
+        return name
+
+    def log_message(self, message):
+        if self.first_log:
+            self.first_log = False
+            self.log.append("### In file %s ###" % self.filename)
+        self.log.append(message)
+
+    def cannot_convert(self, node, reason=None):
+        """Warn the user that a given chunk of code is not valid Python 3,
+        but that it cannot be converted automatically.
+
+        First argument is the top-level node for the code in question.
+        Optional second argument is why it can't be converted.
+        """
+        lineno = node.get_lineno()
+        for_output = node.clone()
+        for_output.set_prefix("")
+        msg = "Line %d: could not convert: %s"
+        self.log_message(msg % (lineno, for_output))
+        if reason:
+            self.log_message(reason)
+
+    def warning(self, node, reason):
+        """Used for warning the user about possible uncertainty in the
+        translation.
+
+        First argument is the top-level node for the code in question.
+        Optional second argument is why it can't be converted.
+        """
+        lineno = node.get_lineno()
+        self.log_message("Line %d: %s" % (lineno, reason))
+
+    def start_tree(self, tree, filename):
+        """Some fixers need to maintain tree-wide state.
+        This method is called once, at the start of tree fix-up.
+        
+        tree - the root node of the tree to be processed.
+        filename - the name of the file the tree came from.
+        """
+        self.used_names = tree.used_names
+        self.set_filename(filename)
+        self.numbers = itertools.count(1)
+        self.first_log = True
+
+    def finish_tree(self, tree, filename):
+        """Some fixers need to maintain tree-wide state.
+        This method is called once, at the conclusion of tree fix-up.
+        
+        tree - the root node of the tree to be processed.
+        filename - the name of the file the tree came from.
+        """
+        pass