SF patch #872326: Generator expression implementation

(Code contributed by Jiwon Seo.)

The documentation portion of the patch is being re-worked and will be
checked-in soon.  Likewise, PEP 289 will be updated to reflect Guido's
rationale for the design decisions on binding behavior (as described in
in his patch comments and in discussions on python-dev).

The test file, test_genexps.py, is written in doctest format and is
meant to exercise all aspects of the the patch.  Further additions are
welcome from everyone.  Please stress test this new feature as much as
possible before the alpha release.

4 files changed, 259 insertions, 0 deletions

diff --git a/Lib/compiler/ast.py b/Lib/compiler/ast.py
index a10225b..064df50 100644
--- a/Lib/compiler/ast.py
+++ b/Lib/compiler/ast.py
@@ -1236,6 +1236,82 @@ class ListCompFor(Node):
     def __repr__(self):
         return "ListCompFor(%s, %s, %s)" % (repr(self.assign), repr(self.list), repr(self.ifs))
 
+class GenExpr(Node):
+    nodes["genexpr"] = "GenExpr"
+    def __init__(self, code):
+        self.code = code
+        self.argnames = ['[outmost-iterable]']
+        self.varargs = self.kwargs = None
+
+    def getChildren(self):
+        return self.code,
+
+    def getChildNodes(self):
+        return self.code,
+
+    def __repr__(self):
+        return "GenExpr(%s)" % (repr(self.code),)
+
+class GenExprInner(Node):
+    nodes["genexprinner"] = "GenExprInner"
+    def __init__(self, expr, quals):
+        self.expr = expr
+        self.quals = quals
+
+    def getChildren(self):
+        children = []
+        children.append(self.expr)
+        children.extend(flatten(self.quals))
+        return tuple(children)
+
+    def getChildNodes(self):
+        nodelist = []
+        nodelist.append(self.expr)
+        nodelist.extend(flatten_nodes(self.quals))
+        return tuple(nodelist)
+
+    def __repr__(self):
+        return "GenExprInner(%s, %s)" % (repr(self.expr), repr(self.quals))
+
+class GenExprFor(Node):
+    nodes["genexprfor"] = "GenExprFor"
+    def __init__(self, assign, iter, ifs):
+        self.assign = assign
+        self.iter = iter
+        self.ifs = ifs
+        self.is_outmost = False
+
+    def getChildren(self):
+        children = []
+        children.append(self.assign)
+        children.append(self.iter)
+        children.extend(flatten(self.ifs))
+        return tuple(children)
+
+    def getChildNodes(self):
+        nodelist = []
+        nodelist.append(self.assign)
+        nodelist.append(self.iter)
+        nodelist.extend(flatten_nodes(self.ifs))
+        return tuple(nodelist)
+
+    def __repr__(self):
+        return "GenExprFor(%s, %s, %s)" % (repr(self.assign), repr(self.iter), repr(self.ifs))
+
+class GenExprIf(Node):
+    nodes["genexprif"] = "GenExprIf"
+    def __init__(self, test):
+        self.test = test
+
+    def getChildren(self):
+        return self.test,
+
+    def getChildNodes(self):
+        return self.test,
+
+    def __repr__(self):
+        return "GenExprIf(%s)" % (repr(self.test),)
+
 klasses = globals()
 for k in nodes.keys():
     nodes[k] = klasses[nodes[k]]
diff --git a/Lib/compiler/pycodegen.py b/Lib/compiler/pycodegen.py
index 292e859..ef5a0d3 100644
--- a/Lib/compiler/pycodegen.py
+++ b/Lib/compiler/pycodegen.py
@@ -619,6 +619,79 @@ class CodeGenerator:
         self.newBlock()
         self.emit('POP_TOP')
 
+    def visitGenExpr(self, node):
+        gen = GenExprCodeGenerator(node, self.scopes, self.class_name,
+                                   self.get_module())
+        walk(node.code, gen)
+        gen.finish()
+        self.set_lineno(node)
+        frees = gen.scope.get_free_vars()
+        if frees:
+            for name in frees:
+                self.emit('LOAD_CLOSURE', name)
+            self.emit('LOAD_CONST', gen)
+            self.emit('MAKE_CLOSURE', 0)
+        else:
+            self.emit('LOAD_CONST', gen)
+            self.emit('MAKE_FUNCTION', 0)
+
+        # precomputation of outmost iterable
+        self.visit(node.code.quals[0].iter)
+        self.emit('GET_ITER')
+        self.emit('CALL_FUNCTION', 1)
+
+    def visitGenExprInner(self, node):
+        self.set_lineno(node)
+        # setup list
+
+        stack = []
+        for i, for_ in zip(range(len(node.quals)), node.quals):
+            start, anchor = self.visit(for_)
+            cont = None
+            for if_ in for_.ifs:
+                if cont is None:
+                    cont = self.newBlock()
+                self.visit(if_, cont)
+            stack.insert(0, (start, cont, anchor))
+
+        self.visit(node.expr)
+        self.emit('YIELD_VALUE')
+
+        for start, cont, anchor in stack:
+            if cont:
+                skip_one = self.newBlock()
+                self.emit('JUMP_FORWARD', skip_one)
+                self.startBlock(cont)
+                self.emit('POP_TOP')
+                self.nextBlock(skip_one)
+            self.emit('JUMP_ABSOLUTE', start)
+            self.startBlock(anchor)
+        self.emit('LOAD_CONST', None)
+
+    def visitGenExprFor(self, node):
+        start = self.newBlock()
+        anchor = self.newBlock()
+        
+        if node.is_outmost:
+            self.loadName('[outmost-iterable]')
+        else:
+            self.visit(node.iter)
+            self.emit('GET_ITER')
+
+        self.nextBlock(start)
+        self.set_lineno(node, force=True)
+        self.emit('FOR_ITER', anchor)
+        self.nextBlock()
+        self.visit(node.assign)
+        return start, anchor
+
+    def visitGenExprIf(self, node, branch):
+        self.set_lineno(node, force=True)
+        self.visit(node.test)
+        self.emit('JUMP_IF_FALSE', branch)
+        self.newBlock()
+        self.emit('POP_TOP')
+
     # exception related
 
     def visitAssert(self, node):
@@ -1199,6 +1272,7 @@ class AbstractFunctionCode:
             klass.lambdaCount = klass.lambdaCount + 1
         else:
             name = func.name
+
         args, hasTupleArg = generateArgList(func.argnames)
         self.graph = pyassem.PyFlowGraph(name, func.filename, args,
                                          optimized=1)
@@ -1263,6 +1337,21 @@ class FunctionCodeGenerator(NestedScopeMixin, AbstractFunctionCode,
         if self.scope.generator is not None:
             self.graph.setFlag(CO_GENERATOR)
 
+class GenExprCodeGenerator(NestedScopeMixin, AbstractFunctionCode,
+                           CodeGenerator):
+    super_init = CodeGenerator.__init__ # call be other init
+    scopes = None
+
+    __super_init = AbstractFunctionCode.__init__
+
+    def __init__(self, gexp, scopes, class_name, mod):
+        self.scopes = scopes
+        self.scope = scopes[gexp]
+        self.__super_init(gexp, scopes, 1, class_name, mod)
+        self.graph.setFreeVars(self.scope.get_free_vars())
+        self.graph.setCellVars(self.scope.get_cell_vars())
+        self.graph.setFlag(CO_GENERATOR)
+
 class AbstractClassCode:
 
     def __init__(self, klass, scopes, module):
diff --git a/Lib/compiler/symbols.py b/Lib/compiler/symbols.py
index fa668f1..6843e19 100644
--- a/Lib/compiler/symbols.py
+++ b/Lib/compiler/symbols.py
@@ -179,6 +179,21 @@ class ModuleScope(Scope):
 class FunctionScope(Scope):
     pass
 
+class GenExprScope(Scope):
+    __super_init = Scope.__init__
+
+    __counter = 1
+
+    def __init__(self, module, klass=None):
+        i = self.__counter
+        self.__counter += 1
+        self.__super_init("generator expression<%d>"%i, module, klass)
+        self.add_param('[outmost-iterable]')
+
+    def get_names(self):
+        keys = Scope.get_names()
+        return keys
+
 class LambdaScope(FunctionScope):
     __super_init = Scope.__init__
 
@@ -220,6 +235,32 @@ class SymbolVisitor:
         self.visit(node.code, scope)
         self.handle_free_vars(scope, parent)
 
+    def visitGenExpr(self, node, parent):
+        scope = GenExprScope(self.module, self.klass);
+        if parent.nested or isinstance(parent, FunctionScope) \
+                or isinstance(parent, GenExprScope):
+            scope.nested = 1
+
+        self.scopes[node] = scope
+        self.visit(node.code, scope)
+
+        self.handle_free_vars(scope, parent)
+
+    def visitGenExprInner(self, node, scope):
+        for genfor in node.quals:
+            self.visit(genfor, scope)
+
+        self.visit(node.expr, scope)
+
+    def visitGenExprFor(self, node, scope):
+        self.visit(node.assign, scope, 1)
+        self.visit(node.iter, scope)
+        for if_ in node.ifs:
+            self.visit(if_, scope)
+
+    def visitGenExprIf(self, node, scope):
+        self.visit(node.test, scope)
+        
     def visitLambda(self, node, parent, assign=0):
         # Lambda is an expression, so it could appear in an expression
         # context where assign is passed.  The transformer should catch
diff --git a/Lib/compiler/transformer.py b/Lib/compiler/transformer.py
index 9074fc7..6832cf1 100644
--- a/Lib/compiler/transformer.py
+++ b/Lib/compiler/transformer.py
@@ -534,6 +534,12 @@ class Transformer:
     testlist1 = testlist
     exprlist = testlist
 
+    def testlist_gexp(self, nodelist):
+        if len(nodelist) == 2 and nodelist[1][0] == symbol.gen_for:
+            test = self.com_node(nodelist[0])
+            return self.com_generator_expression(test, nodelist[1])
+        return self.testlist(nodelist)
+
     def test(self, nodelist):
         # and_test ('or' and_test)* | lambdef
         if len(nodelist) == 1 and nodelist[0][0] == symbol.lambdef:
@@ -1085,6 +1091,48 @@ class Transformer:
                 values.append(self.com_node(nodelist[i]))
             return List(values)
 
+    if hasattr(symbol, 'gen_for'):
+        def com_generator_expression(self, expr, node):
+            # gen_iter: gen_for | gen_if
+            # gen_for: 'for' exprlist 'in' test [gen_iter]
+            # gen_if: 'if' test [gen_iter]
+
+            lineno = node[1][2]
+            fors = []
+            while node:
+                t = node[1][1]
+                if t == 'for':
+                    assignNode = self.com_assign(node[2], OP_ASSIGN)
+                    genNode = self.com_node(node[4])
+                    newfor = GenExprFor(assignNode, genNode, [])
+                    newfor.lineno = node[1][2]
+                    fors.append(newfor)
+                    if (len(node)) == 5:
+                        node = None
+                    else:
+                        node = self.com_gen_iter(node[5])
+                elif t == 'if':
+                    test = self.com_node(node[2])
+                    newif = GenExprIf(test)
+                    newif.lineno = node[1][2]
+                    newfor.ifs.append(newif)
+                    if len(node) == 3:
+                        node = None
+                    else:
+                        node = self.com_gen_iter(node[3])
+                else:
+                    raise SyntaxError, \
+                            ("unexpected generator expression element: %s %d"
+                             % (node, lineno))
+            fors[0].is_outmost = True
+            n = GenExpr(GenExprInner(expr, fors))
+            n.lineno = lineno
+            return n
+
+        def com_gen_iter(self, node):
+            assert node[0] == symbol.gen_iter
+            return node[1]
+
     def com_dictmaker(self, nodelist):
         # dictmaker: test ':' test (',' test ':' value)* [',']
         items = []
@@ -1122,6 +1170,8 @@ class Transformer:
             if node[0] == token.STAR or node[0] == token.DOUBLESTAR:
                 break
             kw, result = self.com_argument(node, kw)
+            if len_nodelist != 2 and isinstance(result, GenExpr):
+                raise SyntaxError, 'generator expression needs parenthesis'
             args.append(result)
         else:
             # No broken by star arg, so skip the last one we processed.
@@ -1148,6 +1198,9 @@ class Transformer:
         return CallFunc(primaryNode, args, star_node, dstar_node)
 
     def com_argument(self, nodelist, kw):
+        if len(nodelist) == 3 and nodelist[2][0] == symbol.gen_for:
+            test = self.com_node(nodelist[1])
+            return 0, self.com_generator_expression(test, nodelist[2])
         if len(nodelist) == 2:
             if kw:
                 raise SyntaxError, "non-keyword arg after keyword arg"