Merging the gen-branch into the main line, at Guido's direction. Yay!

Bugfix candidate in inspect.py:  it was referencing "self" outside of
a method.

Grammar/Grammar

@@ -43,10 +43,11 @@ augassign: '+=' | '-=' | '*=' | '/=' | '%=' | '&=' | '|=' | '^=' | '<<=' | '>>='
 print_stmt: 'print' ( [ test (',' test)* [','] ] | '>>' test [ (',' test)+ [','] ] )
 del_stmt: 'del' exprlist
 pass_stmt: 'pass'
-flow_stmt: break_stmt | continue_stmt | return_stmt | raise_stmt
+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' testlist
 raise_stmt: 'raise' [test [',' test [',' test]]]
 import_stmt: 'import' dotted_as_name (',' dotted_as_name)* | 'from' dotted_name 'import' ('*' | import_as_name (',' import_as_name)*)
 import_as_name: NAME [NAME NAME]

Include/compile.h

@@ -33,6 +33,7 @@ typedef struct {
 #define CO_VARARGS	0x0004
 #define CO_VARKEYWORDS	0x0008
 #define CO_NESTED       0x0010
+#define CO_GENERATOR    0x0020
 
 extern DL_IMPORT(PyTypeObject) PyCode_Type;
 

Include/frameobject.h

@@ -21,6 +21,8 @@ typedef struct _frame {
     PyObject *f_globals;	/* global symbol table (PyDictObject) */
     PyObject *f_locals;		/* local symbol table (PyDictObject) */
     PyObject **f_valuestack;	/* points after the last local */
+    PyObject **f_stackbottom;   /* points to the last item on the stack if
+                                  frame has yielded. */
     PyObject *f_trace;		/* Trace function */
     PyObject *f_exc_type, *f_exc_value, *f_exc_traceback;
     PyThreadState *f_tstate;

Include/graminit.h

@@ -18,47 +18,48 @@
 #define break_stmt 273
 #define continue_stmt 274
 #define return_stmt 275
-#define raise_stmt 276
-#define import_stmt 277
-#define import_as_name 278
-#define dotted_as_name 279
-#define dotted_name 280
-#define global_stmt 281
-#define exec_stmt 282
-#define assert_stmt 283
-#define compound_stmt 284
-#define if_stmt 285
-#define while_stmt 286
-#define for_stmt 287
-#define try_stmt 288
-#define except_clause 289
-#define suite 290
-#define test 291
-#define and_test 292
-#define not_test 293
-#define comparison 294
-#define comp_op 295
-#define expr 296
-#define xor_expr 297
-#define and_expr 298
-#define shift_expr 299
-#define arith_expr 300
-#define term 301
-#define factor 302
-#define power 303
-#define atom 304
-#define listmaker 305
-#define lambdef 306
-#define trailer 307
-#define subscriptlist 308
-#define subscript 309
-#define sliceop 310
-#define exprlist 311
-#define testlist 312
-#define dictmaker 313
-#define classdef 314
-#define arglist 315
-#define argument 316
-#define list_iter 317
-#define list_for 318
-#define list_if 319
+#define yield_stmt 276
+#define raise_stmt 277
+#define import_stmt 278
+#define import_as_name 279
+#define dotted_as_name 280
+#define dotted_name 281
+#define global_stmt 282
+#define exec_stmt 283
+#define assert_stmt 284
+#define compound_stmt 285
+#define if_stmt 286
+#define while_stmt 287
+#define for_stmt 288
+#define try_stmt 289
+#define except_clause 290
+#define suite 291
+#define test 292
+#define and_test 293
+#define not_test 294
+#define comparison 295
+#define comp_op 296
+#define expr 297
+#define xor_expr 298
+#define and_expr 299
+#define shift_expr 300
+#define arith_expr 301
+#define term 302
+#define factor 303
+#define power 304
+#define atom 305
+#define listmaker 306
+#define lambdef 307
+#define trailer 308
+#define subscriptlist 309
+#define subscript 310
+#define sliceop 311
+#define exprlist 312
+#define testlist 313
+#define dictmaker 314
+#define classdef 315
+#define arglist 316
+#define argument 317
+#define list_iter 318
+#define list_for 319
+#define list_if 320

Include/opcode.h

@@ -71,6 +71,7 @@ extern "C" {
 #define RETURN_VALUE	83
 #define IMPORT_STAR	84
 #define EXEC_STMT	85
+#define YIELD_VALUE	86
 
 #define POP_BLOCK	87
 #define END_FINALLY	88

Include/symtable.h

@@ -46,6 +46,7 @@ typedef struct _symtable_entry {
 	int ste_nested;          /* true if scope is nested */
 	int ste_child_free;      /* true if a child scope has free variables,
 				    including free refs to globals */
+	int ste_generator;       /* true if namespace is a generator */
 	int ste_opt_lineno;      /* lineno of last exec or import * */
 	struct symtable *ste_table;
 } PySymtableEntryObject;

Lib/dis.py

@@ -223,6 +223,7 @@ def_op('LOAD_LOCALS', 82)
 def_op('RETURN_VALUE', 83)
 def_op('IMPORT_STAR', 84)
 def_op('EXEC_STMT', 85)
+def_op('YIELD_STMT', 86)
 
 def_op('POP_BLOCK', 87)
 def_op('END_FINALLY', 88)

Lib/inspect.py

@@ -349,32 +349,28 @@ class ListReader:
             return self.lines[i]
         else: return ''
 
-class EndOfBlock(Exception): pass
-
-class BlockFinder:
-    """Provide a tokeneater() method to detect the end of a code block."""
-    def __init__(self):
-        self.indent = 0
-        self.started = 0
-        self.last = 0
-
-    def tokeneater(self, type, token, (srow, scol), (erow, ecol), line):
-        if not self.started:
-            if type == tokenize.NAME: self.started = 1
+def getblock(lines):
+    """Extract the block of code at the top of the given list of lines."""
+
+    indent = 0
+    started = 0
+    last = 0
+    tokens = tokenize.generate_tokens(ListReader(lines).readline)
+
+    for (type, token, (srow, scol), (erow, ecol), line) in tokens:
+        if not started:
+            if type == tokenize.NAME:
+                started = 1
         elif type == tokenize.NEWLINE:
-            self.last = srow
+            last = srow
         elif type == tokenize.INDENT:
-            self.indent = self.indent + 1
+            indent = indent + 1
         elif type == tokenize.DEDENT:
-            self.indent = self.indent - 1
-            if self.indent == 0: raise EndOfBlock, self.last
-
-def getblock(lines):
-    """Extract the block of code at the top of the given list of lines."""
-    try:
-        tokenize.tokenize(ListReader(lines).readline, BlockFinder().tokeneater)
-    except EndOfBlock, eob:
-        return lines[:eob.args[0]]
+            indent = indent - 1
+            if indent == 0:
+                return lines[:last]
+    else:
+        raise ValueError, "unable to find block"
 
 def getsourcelines(object):
     """Return a list of source lines and starting line number for an object.

Lib/tabnanny.py

@@ -77,9 +77,8 @@ def check(file):
     if verbose > 1:
         print "checking", `file`, "..."
 
-    reset_globals()
     try:
-        tokenize.tokenize(f.readline, tokeneater)
+        process_tokens(tokenize.generate_tokens(f.readline))
 
     except tokenize.TokenError, msg:
         errprint("%s: Token Error: %s" % (`file`, str(msg)))
@@ -244,28 +243,19 @@ def format_witnesses(w):
         prefix = prefix + "s"
     return prefix + " " + string.join(firsts, ', ')
 
-# The collection of globals, the reset_globals() function, and the
-# tokeneater() function, depend on which version of tokenize is
-# in use.
+# Need Guido's enhancement
+assert hasattr(tokenize, 'NL'), "tokenize module too old"
 
-if hasattr(tokenize, 'NL'):
-    # take advantage of Guido's patch!
-
-    indents = []
-    check_equal = 0
-
-    def reset_globals():
-        global indents, check_equal
-        check_equal = 0
-        indents = [Whitespace("")]
-
-    def tokeneater(type, token, start, end, line,
+def process_tokens(tokens,
                    INDENT=tokenize.INDENT,
                    DEDENT=tokenize.DEDENT,
                    NEWLINE=tokenize.NEWLINE,
-                   JUNK=(tokenize.COMMENT, tokenize.NL) ):
-        global indents, check_equal
+                   JUNK=(tokenize.COMMENT, tokenize.NL)):
 
+    indents = [Whitespace("")]
+    check_equal = 0
+
+    for (type, token, start, end, line) in tokens:
         if type == NEWLINE:
             # a program statement, or ENDMARKER, will eventually follow,
             # after some (possibly empty) run of tokens of the form
@@ -311,62 +301,6 @@ if hasattr(tokenize, 'NL'):
                 msg = "indent not equal e.g. " + format_witnesses(witness)
                 raise NannyNag(start[0], msg, line)
 
-else:
-    # unpatched version of tokenize
-
-    nesting_level = 0
-    indents = []
-    check_equal = 0
-
-    def reset_globals():
-        global nesting_level, indents, check_equal
-        nesting_level = check_equal = 0
-        indents = [Whitespace("")]
-
-    def tokeneater(type, token, start, end, line,
-                   INDENT=tokenize.INDENT,
-                   DEDENT=tokenize.DEDENT,
-                   NEWLINE=tokenize.NEWLINE,
-                   COMMENT=tokenize.COMMENT,
-                   OP=tokenize.OP):
-        global nesting_level, indents, check_equal
-
-        if type == INDENT:
-            check_equal = 0
-            thisguy = Whitespace(token)
-            if not indents[-1].less(thisguy):
-                witness = indents[-1].not_less_witness(thisguy)
-                msg = "indent not greater e.g. " + format_witnesses(witness)
-                raise NannyNag(start[0], msg, line)
-            indents.append(thisguy)
-
-        elif type == DEDENT:
-            del indents[-1]
-
-        elif type == NEWLINE:
-            if nesting_level == 0:
-                check_equal = 1
-
-        elif type == COMMENT:
-            pass
-
-        elif check_equal:
-            check_equal = 0
-            thisguy = Whitespace(line)
-            if not indents[-1].equal(thisguy):
-                witness = indents[-1].not_equal_witness(thisguy)
-                msg = "indent not equal e.g. " + format_witnesses(witness)
-                raise NannyNag(start[0], msg, line)
-
-        if type == OP and token in ('{', '[', '('):
-            nesting_level = nesting_level + 1
-
-        elif type == OP and token in ('}', ']', ')'):
-            if nesting_level == 0:
-                raise NannyNag(start[0],
-                               "unbalanced bracket '" + token + "'",
-                               line)
-            nesting_level = nesting_level - 1
 
 if __name__ == '__main__':
     main()

Lib/tokenize.py

@@ -111,7 +111,12 @@ def tokenize(readline, tokeneater=printtoken):
     except StopTokenizing:
         pass
 
+# backwards compatible interface, probably not used
 def tokenize_loop(readline, tokeneater):
+    for token_info in generate_tokens(readline):
+        apply(tokeneater, token_info)
+
+def generate_tokens(readline):
     lnum = parenlev = continued = 0
     namechars, numchars = string.letters + '_', string.digits
     contstr, needcont = '', 0
@@ -129,12 +134,12 @@ def tokenize_loop(readline, tokeneater):
             endmatch = endprog.match(line)
             if endmatch:
                 pos = end = endmatch.end(0)
-                tokeneater(STRING, contstr + line[:end],
+                yield (STRING, contstr + line[:end],
                            strstart, (lnum, end), contline + line)
                 contstr, needcont = '', 0
                 contline = None
             elif needcont and line[-2:] != '\\\n' and line[-3:] != '\\\r\n':
-                tokeneater(ERRORTOKEN, contstr + line,
+                yield (ERRORTOKEN, contstr + line,
                            strstart, (lnum, len(line)), contline)
                 contstr = ''
                 contline = None
@@ -156,16 +161,16 @@ def tokenize_loop(readline, tokeneater):
             if pos == max: break
 
             if line[pos] in '#\r\n':           # skip comments or blank lines
-                tokeneater((NL, COMMENT)[line[pos] == '#'], line[pos:],
+                yield ((NL, COMMENT)[line[pos] == '#'], line[pos:],
                            (lnum, pos), (lnum, len(line)), line)
                 continue
 
             if column > indents[-1]:           # count indents or dedents
                 indents.append(column)
-                tokeneater(INDENT, line[:pos], (lnum, 0), (lnum, pos), line)
+                yield (INDENT, line[:pos], (lnum, 0), (lnum, pos), line)
             while column < indents[-1]:
                 indents = indents[:-1]
-                tokeneater(DEDENT, '', (lnum, pos), (lnum, pos), line)
+                yield (DEDENT, '', (lnum, pos), (lnum, pos), line)
 
         else:                                  # continued statement
             if not line:
@@ -181,12 +186,12 @@ def tokenize_loop(readline, tokeneater):
 
                 if initial in numchars or \
                    (initial == '.' and token != '.'):      # ordinary number
-                    tokeneater(NUMBER, token, spos, epos, line)
+                    yield (NUMBER, token, spos, epos, line)
                 elif initial in '\r\n':
-                    tokeneater(parenlev > 0 and NL or NEWLINE,
+                    yield (parenlev > 0 and NL or NEWLINE,
                                token, spos, epos, line)
                 elif initial == '#':
-                    tokeneater(COMMENT, token, spos, epos, line)
+                    yield (COMMENT, token, spos, epos, line)
                 elif token in ("'''", '"""',               # triple-quoted
                                "r'''", 'r"""', "R'''", 'R"""',
                                "u'''", 'u"""', "U'''", 'U"""',
@@ -197,7 +202,7 @@ def tokenize_loop(readline, tokeneater):
                     if endmatch:                           # all on one line
                         pos = endmatch.end(0)
                         token = line[start:pos]
-                        tokeneater(STRING, token, spos, (lnum, pos), line)
+                        yield (STRING, token, spos, (lnum, pos), line)
                     else:
                         strstart = (lnum, start)           # multiple lines
                         contstr = line[start:]
@@ -216,23 +221,23 @@ def tokenize_loop(readline, tokeneater):
                         contline = line
                         break
                     else:                                  # ordinary string
-                        tokeneater(STRING, token, spos, epos, line)
+                        yield (STRING, token, spos, epos, line)
                 elif initial in namechars:                 # ordinary name
-                    tokeneater(NAME, token, spos, epos, line)
+                    yield (NAME, token, spos, epos, line)
                 elif initial == '\\':                      # continued stmt
                     continued = 1
                 else:
                     if initial in '([{': parenlev = parenlev + 1
                     elif initial in ')]}': parenlev = parenlev - 1
-                    tokeneater(OP, token, spos, epos, line)
+                    yield (OP, token, spos, epos, line)
             else:
-                tokeneater(ERRORTOKEN, line[pos],
+                yield (ERRORTOKEN, line[pos],
                            (lnum, pos), (lnum, pos+1), line)
                 pos = pos + 1
 
     for indent in indents[1:]:                 # pop remaining indent levels
-        tokeneater(DEDENT, '', (lnum, 0), (lnum, 0), '')
-    tokeneater(ENDMARKER, '', (lnum, 0), (lnum, 0), '')
+        yield (DEDENT, '', (lnum, 0), (lnum, 0), '')
+    yield (ENDMARKER, '', (lnum, 0), (lnum, 0), '')
 
 if __name__ == '__main__':                     # testing
     import sys

Objects/frameobject.c

@@ -67,6 +67,7 @@ frame_dealloc(PyFrameObject *f)
 {
 	int i, slots;
 	PyObject **fastlocals;
+	PyObject **p;
 
 	Py_TRASHCAN_SAFE_BEGIN(f)
 	/* Kill all local variables */
@@ -76,6 +77,10 @@ frame_dealloc(PyFrameObject *f)
 		Py_XDECREF(*fastlocals);
 	}
 
+	/* Free stack */
+	for (p = f->f_valuestack; p < f->f_stackbottom; p++) {
+		Py_XDECREF(*p);
+	}
 	Py_XDECREF(f->f_back);
 	Py_XDECREF(f->f_code);
 	Py_XDECREF(f->f_builtins);
@@ -221,6 +226,7 @@ PyFrame_New(PyThreadState *tstate, PyCodeObject *code, PyObject *globals,
 		f->f_localsplus[extras] = NULL;
 
 	f->f_valuestack = f->f_localsplus + (f->f_nlocals + ncells + nfrees);
+	f->f_stackbottom = f->f_valuestack;
 
 	return f;
 }

Python/compile.c

@@ -2634,13 +2634,37 @@ com_return_stmt(struct compiling *c, node *n)
 	if (!c->c_infunction) {
 		com_error(c, PyExc_SyntaxError, "'return' outside function");
 	}
-	if (NCH(n) < 2) {
-		com_addoparg(c, LOAD_CONST, com_addconst(c, Py_None));
+	if (c->c_flags & CO_GENERATOR) {
+		if (NCH(n) > 1) {
+			com_error(c, PyExc_SyntaxError,
+				  "'return' with argument inside generator");
+		}
+		com_addoparg(c, LOAD_CONST,
+				com_addconst(c, PyExc_StopIteration));
 		com_push(c, 1);
+		com_addoparg(c, RAISE_VARARGS, 1);
+	}
+	else {
+		if (NCH(n) < 2) {
+			com_addoparg(c, LOAD_CONST, com_addconst(c, Py_None));
+			com_push(c, 1);
+		}
+		else
+			com_node(c, CHILD(n, 1));
+		com_addbyte(c, RETURN_VALUE);
 	}
-	else
-		com_node(c, CHILD(n, 1));
-	com_addbyte(c, RETURN_VALUE);
+	com_pop(c, 1);
+}
+
+static void
+com_yield_stmt(struct compiling *c, node *n)
+{
+	REQ(n, yield_stmt); /* 'yield' testlist */
+	if (!c->c_infunction) {
+		com_error(c, PyExc_SyntaxError, "'yield' outside function");
+	}
+	com_node(c, CHILD(n, 1));
+	com_addbyte(c, YIELD_VALUE);
 	com_pop(c, 1);
 }
 
@@ -3455,6 +3479,9 @@ com_node(struct compiling *c, node *n)
 	case return_stmt:
 		com_return_stmt(c, n);
 		break;
+	case yield_stmt:
+		com_yield_stmt(c, n);
+		break;
 	case raise_stmt:
 		com_raise_stmt(c, n);
 		break;
@@ -3674,10 +3701,19 @@ compile_funcdef(struct compiling *c, node *n)
 	c->c_infunction = 1;
 	com_node(c, CHILD(n, 4));
 	c->c_infunction = 0;
-	com_addoparg(c, LOAD_CONST, com_addconst(c, Py_None));
-	com_push(c, 1);
-	com_addbyte(c, RETURN_VALUE);
-	com_pop(c, 1);
+	if (c->c_flags & CO_GENERATOR) {
+		com_addoparg(c, LOAD_CONST,
+				com_addconst(c, PyExc_StopIteration));
+		com_push(c, 1);
+		com_addoparg(c, RAISE_VARARGS, 1);
+		com_pop(c, 1);
+	}
+	else {
+		com_addoparg(c, LOAD_CONST, com_addconst(c, Py_None));
+		com_push(c, 1);
+		com_addbyte(c, RETURN_VALUE);
+		com_pop(c, 1);
+	}
 }
 
 static void
@@ -4342,6 +4378,8 @@ symtable_update_flags(struct compiling *c, PySymtableEntryObject *ste,
 {
 	if (c->c_future && c->c_future->ff_nested_scopes)
 		c->c_flags |= CO_NESTED;
+	if (ste->ste_generator)
+		c->c_flags |= CO_GENERATOR;
 	if (ste->ste_type != TYPE_MODULE)
 		c->c_flags |= CO_NEWLOCALS;
 	if (ste->ste_type == TYPE_FUNCTION) {
@@ -4900,6 +4938,10 @@ symtable_node(struct symtable *st, node *n)
 	case del_stmt:
 		symtable_assign(st, CHILD(n, 1), 0);
 		break;
+	case yield_stmt:
+		st->st_cur->ste_generator = 1;
+		n = CHILD(n, 1);
+		goto loop;
 	case expr_stmt:
 		if (NCH(n) == 1)
 			n = CHILD(n, 0);

Python/marshal.c

@@ -17,6 +17,7 @@
 
 #define TYPE_NULL	'0'
 #define TYPE_NONE	'N'
+#define TYPE_STOPITER	'S'
 #define TYPE_ELLIPSIS   '.'
 #define TYPE_INT	'i'
 #define TYPE_INT64	'I'
@@ -120,6 +121,9 @@ w_object(PyObject *v, WFILE *p)
 	else if (v == Py_None) {
 		w_byte(TYPE_NONE, p);
 	}
+	else if (v == PyExc_StopIteration) {
+		w_byte(TYPE_STOPITER, p);
+	}
 	else if (v == Py_Ellipsis) {
 	        w_byte(TYPE_ELLIPSIS, p);
 	}
@@ -376,6 +380,10 @@ r_object(RFILE *p)
 		Py_INCREF(Py_None);
 		return Py_None;
 
+	case TYPE_STOPITER:
+		Py_INCREF(PyExc_StopIteration);
+		return PyExc_StopIteration;
+
 	case TYPE_ELLIPSIS:
 		Py_INCREF(Py_Ellipsis);
 		return Py_Ellipsis;

Python/symtable.c

@@ -69,6 +69,7 @@ PySymtableEntry_New(struct symtable *st, char *name, int type, int lineno)
 	else
 		ste->ste_nested = 0;
 	ste->ste_child_free = 0;
+	ste->ste_generator = 0;
 
 	if (PyDict_SetItem(st->st_symbols, ste->ste_id, (PyObject *)ste) < 0)
 	    goto fail;