summaryrefslogtreecommitdiffstats
path: root/Parser
diff options
context:
space:
mode:
Diffstat (limited to 'Parser')
-rw-r--r--Parser/Python.asdl203
-rw-r--r--Parser/asdl.py35
-rwxr-xr-xParser/asdl_c.py110
-rw-r--r--Parser/intrcheck.c174
-rw-r--r--Parser/myreadline.c37
-rw-r--r--Parser/node.c2
-rw-r--r--Parser/parsetok.c64
-rw-r--r--Parser/parsetok_pgen.c2
-rw-r--r--Parser/pgenmain.c2
-rw-r--r--Parser/tokenizer.c100
-rw-r--r--Parser/tokenizer.h9
11 files changed, 341 insertions, 397 deletions
diff --git a/Parser/Python.asdl b/Parser/Python.asdl
index 9407b2f..c24d840 100644
--- a/Parser/Python.asdl
+++ b/Parser/Python.asdl
@@ -1,119 +1,120 @@
--- ASDL's four builtin types are identifier, int, string, object
+-- ASDL's five builtin types are identifier, int, string, bytes, object
-module Python version "$Revision$"
+module Python
{
- mod = Module(stmt* body)
- | Interactive(stmt* body)
- | Expression(expr body)
+ mod = Module(stmt* body)
+ | Interactive(stmt* body)
+ | Expression(expr body)
- -- not really an actual node but useful in Jython's typesystem.
- | Suite(stmt* body)
+ -- not really an actual node but useful in Jython's typesystem.
+ | Suite(stmt* body)
- stmt = FunctionDef(identifier name, arguments args,
+ stmt = FunctionDef(identifier name, arguments args,
stmt* body, expr* decorator_list, expr? returns)
- | ClassDef(identifier name,
- expr* bases,
- keyword* keywords,
- expr? starargs,
- expr? kwargs,
- stmt* body,
- expr* decorator_list)
- | Return(expr? value)
-
- | Delete(expr* targets)
- | Assign(expr* targets, expr value)
- | AugAssign(expr target, operator op, expr value)
-
- -- use 'orelse' because else is a keyword in target languages
- | For(expr target, expr iter, stmt* body, stmt* orelse)
- | While(expr test, stmt* body, stmt* orelse)
- | If(expr test, stmt* body, stmt* orelse)
- | With(expr context_expr, expr? optional_vars, stmt* body)
-
- | Raise(expr? exc, expr? cause)
- | TryExcept(stmt* body, excepthandler* handlers, stmt* orelse)
- | TryFinally(stmt* body, stmt* finalbody)
- | Assert(expr test, expr? msg)
-
- | Import(alias* names)
- | ImportFrom(identifier? module, alias* names, int? level)
-
- | Global(identifier* names)
- | Nonlocal(identifier* names)
- | Expr(expr value)
- | Pass | Break | Continue
-
- -- XXX Jython will be different
- -- col_offset is the byte offset in the utf8 string the parser uses
- attributes (int lineno, int col_offset)
-
- -- BoolOp() can use left & right?
- expr = BoolOp(boolop op, expr* values)
- | BinOp(expr left, operator op, expr right)
- | UnaryOp(unaryop op, expr operand)
- | Lambda(arguments args, expr body)
- | IfExp(expr test, expr body, expr orelse)
- | Dict(expr* keys, expr* values)
- | Set(expr* elts)
- | ListComp(expr elt, comprehension* generators)
- | SetComp(expr elt, comprehension* generators)
- | DictComp(expr key, expr value, comprehension* generators)
- | GeneratorExp(expr elt, comprehension* generators)
- -- the grammar constrains where yield expressions can occur
- | Yield(expr? value)
- -- need sequences for compare to distinguish between
- -- x < 4 < 3 and (x < 4) < 3
- | Compare(expr left, cmpop* ops, expr* comparators)
- | Call(expr func, expr* args, keyword* keywords,
- expr? starargs, expr? kwargs)
- | Num(object n) -- a number as a PyObject.
- | Str(string s) -- need to specify raw, unicode, etc?
- | Bytes(string s)
- | Ellipsis
- -- other literals? bools?
-
- -- the following expression can appear in assignment context
- | Attribute(expr value, identifier attr, expr_context ctx)
- | Subscript(expr value, slice slice, expr_context ctx)
- | Starred(expr value, expr_context ctx)
- | Name(identifier id, expr_context ctx)
- | List(expr* elts, expr_context ctx)
- | Tuple(expr* elts, expr_context ctx)
-
- -- col_offset is the byte offset in the utf8 string the parser uses
- attributes (int lineno, int col_offset)
-
- expr_context = Load | Store | Del | AugLoad | AugStore | Param
-
- slice = Slice(expr? lower, expr? upper, expr? step)
- | ExtSlice(slice* dims)
- | Index(expr value)
-
- boolop = And | Or
-
- operator = Add | Sub | Mult | Div | Mod | Pow | LShift
+ | ClassDef(identifier name,
+ expr* bases,
+ keyword* keywords,
+ expr? starargs,
+ expr? kwargs,
+ stmt* body,
+ expr* decorator_list)
+ | Return(expr? value)
+
+ | Delete(expr* targets)
+ | Assign(expr* targets, expr value)
+ | AugAssign(expr target, operator op, expr value)
+
+ -- use 'orelse' because else is a keyword in target languages
+ | For(expr target, expr iter, stmt* body, stmt* orelse)
+ | While(expr test, stmt* body, stmt* orelse)
+ | If(expr test, stmt* body, stmt* orelse)
+ | With(withitem* items, stmt* body)
+
+ | Raise(expr? exc, expr? cause)
+ | Try(stmt* body, excepthandler* handlers, stmt* orelse, stmt* finalbody)
+ | Assert(expr test, expr? msg)
+
+ | Import(alias* names)
+ | ImportFrom(identifier? module, alias* names, int? level)
+
+ | Global(identifier* names)
+ | Nonlocal(identifier* names)
+ | Expr(expr value)
+ | Pass | Break | Continue
+
+ -- XXX Jython will be different
+ -- col_offset is the byte offset in the utf8 string the parser uses
+ attributes (int lineno, int col_offset)
+
+ -- BoolOp() can use left & right?
+ expr = BoolOp(boolop op, expr* values)
+ | BinOp(expr left, operator op, expr right)
+ | UnaryOp(unaryop op, expr operand)
+ | Lambda(arguments args, expr body)
+ | IfExp(expr test, expr body, expr orelse)
+ | Dict(expr* keys, expr* values)
+ | Set(expr* elts)
+ | ListComp(expr elt, comprehension* generators)
+ | SetComp(expr elt, comprehension* generators)
+ | DictComp(expr key, expr value, comprehension* generators)
+ | GeneratorExp(expr elt, comprehension* generators)
+ -- the grammar constrains where yield expressions can occur
+ | Yield(expr? value)
+ | YieldFrom(expr value)
+ -- need sequences for compare to distinguish between
+ -- x < 4 < 3 and (x < 4) < 3
+ | Compare(expr left, cmpop* ops, expr* comparators)
+ | Call(expr func, expr* args, keyword* keywords,
+ expr? starargs, expr? kwargs)
+ | Num(object n) -- a number as a PyObject.
+ | Str(string s) -- need to specify raw, unicode, etc?
+ | Bytes(bytes s)
+ | Ellipsis
+ -- other literals? bools?
+
+ -- the following expression can appear in assignment context
+ | Attribute(expr value, identifier attr, expr_context ctx)
+ | Subscript(expr value, slice slice, expr_context ctx)
+ | Starred(expr value, expr_context ctx)
+ | Name(identifier id, expr_context ctx)
+ | List(expr* elts, expr_context ctx)
+ | Tuple(expr* elts, expr_context ctx)
+
+ -- col_offset is the byte offset in the utf8 string the parser uses
+ attributes (int lineno, int col_offset)
+
+ expr_context = Load | Store | Del | AugLoad | AugStore | Param
+
+ slice = Slice(expr? lower, expr? upper, expr? step)
+ | ExtSlice(slice* dims)
+ | Index(expr value)
+
+ boolop = And | Or
+
+ operator = Add | Sub | Mult | Div | Mod | Pow | LShift
| RShift | BitOr | BitXor | BitAnd | FloorDiv
- unaryop = Invert | Not | UAdd | USub
+ unaryop = Invert | Not | UAdd | USub
- cmpop = Eq | NotEq | Lt | LtE | Gt | GtE | Is | IsNot | In | NotIn
+ cmpop = Eq | NotEq | Lt | LtE | Gt | GtE | Is | IsNot | In | NotIn
- comprehension = (expr target, expr iter, expr* ifs)
+ comprehension = (expr target, expr iter, expr* ifs)
- -- not sure what to call the first argument for raise and except
- excepthandler = ExceptHandler(expr? type, identifier? name, stmt* body)
- attributes (int lineno, int col_offset)
+ excepthandler = ExceptHandler(expr? type, identifier? name, stmt* body)
+ attributes (int lineno, int col_offset)
- arguments = (arg* args, identifier? vararg, expr? varargannotation,
+ arguments = (arg* args, identifier? vararg, expr? varargannotation,
arg* kwonlyargs, identifier? kwarg,
expr? kwargannotation, expr* defaults,
expr* kw_defaults)
- arg = (identifier arg, expr? annotation)
+ arg = (identifier arg, expr? annotation)
- -- keyword arguments supplied to call
- keyword = (identifier arg, expr value)
+ -- keyword arguments supplied to call
+ keyword = (identifier arg, expr value)
- -- import name with optional 'as' alias.
- alias = (identifier name, identifier? asname)
+ -- import name with optional 'as' alias.
+ alias = (identifier name, identifier? asname)
+
+ withitem = (expr context_expr, expr? optional_vars)
}
diff --git a/Parser/asdl.py b/Parser/asdl.py
index 7b4e2dc..08aa05b 100644
--- a/Parser/asdl.py
+++ b/Parser/asdl.py
@@ -114,28 +114,20 @@ class ASDLParser(spark.GenericParser, object):
raise ASDLSyntaxError(tok.lineno, tok)
def p_module_0(self, info):
- " module ::= Id Id version { } "
- module, name, version, _0, _1 = info
+ " module ::= Id Id { } "
+ module, name, _0, _1 = info
if module.value != "module":
raise ASDLSyntaxError(module.lineno,
msg="expected 'module', found %s" % module)
- return Module(name, None, version)
+ return Module(name, None)
def p_module(self, info):
- " module ::= Id Id version { definitions } "
- module, name, version, _0, definitions, _1 = info
+ " module ::= Id Id { definitions } "
+ module, name, _0, definitions, _1 = info
if module.value != "module":
raise ASDLSyntaxError(module.lineno,
msg="expected 'module', found %s" % module)
- return Module(name, definitions, version)
-
- def p_version(self, info):
- "version ::= Id String"
- version, V = info
- if version.value != "version":
- raise ASDLSyntaxError(version.lineno,
- msg="expected 'version', found %" % version)
- return V
+ return Module(name, definitions)
def p_definition_0(self, definition):
" definitions ::= definition "
@@ -164,15 +156,11 @@ class ASDLParser(spark.GenericParser, object):
if id.value != "attributes":
raise ASDLSyntaxError(id.lineno,
msg="expected attributes, found %s" % id)
- if attributes:
- attributes.reverse()
return Sum(sum, attributes)
def p_product(self, info):
" product ::= ( fields ) "
_0, fields, _1 = info
- # XXX can't I just construct things in the right order?
- fields.reverse()
return Product(fields)
def p_sum_0(self, constructor):
@@ -196,8 +184,6 @@ class ASDLParser(spark.GenericParser, object):
def p_constructor_1(self, info):
" constructor ::= Id ( fields ) "
id, _0, fields, _1 = info
- # XXX can't I just construct things in the right order?
- fields.reverse()
return Constructor(id, fields)
def p_fields_0(self, field):
@@ -205,8 +191,8 @@ class ASDLParser(spark.GenericParser, object):
return [field[0]]
def p_fields_1(self, info):
- " fields ::= field , fields "
- field, _, fields = info
+ " fields ::= fields , field "
+ fields, _, field = info
return fields + [field]
def p_field_0(self, type_):
@@ -236,7 +222,7 @@ class ASDLParser(spark.GenericParser, object):
" field ::= Id ? "
return Field(type[0], opt=True)
-builtin_types = ("identifier", "string", "int", "bool", "object")
+builtin_types = ("identifier", "string", "bytes", "int", "object")
# below is a collection of classes to capture the AST of an AST :-)
# not sure if any of the methods are useful yet, but I'm adding them
@@ -246,10 +232,9 @@ class AST(object):
pass # a marker class
class Module(AST):
- def __init__(self, name, dfns, version):
+ def __init__(self, name, dfns):
self.name = name
self.dfns = dfns
- self.version = version
self.types = {} # maps type name to value (from dfns)
for type in dfns:
self.types[type.name.value] = type.value
diff --git a/Parser/asdl_c.py b/Parser/asdl_c.py
index 7f613db..a9e6626 100755
--- a/Parser/asdl_c.py
+++ b/Parser/asdl_c.py
@@ -84,8 +84,16 @@ class EmitVisitor(asdl.VisitorBase):
def __init__(self, file):
self.file = file
+ self.identifiers = set()
super(EmitVisitor, self).__init__()
+ def emit_identifier(self, name):
+ name = str(name)
+ if name in self.identifiers:
+ return
+ self.emit("_Py_IDENTIFIER(%s);" % name, 0)
+ self.identifiers.add(name)
+
def emit(self, s, depth, reflow=True):
# XXX reflow long lines?
if reflow:
@@ -485,12 +493,12 @@ class Obj2ModVisitor(PickleVisitor):
def visitField(self, field, name, sum=None, prod=None, depth=0):
ctype = get_c_type(field.type)
- self.emit("if (PyObject_HasAttrString(obj, \"%s\")) {" % field.name, depth)
+ self.emit("if (_PyObject_HasAttrId(obj, &PyId_%s)) {" % field.name, depth)
self.emit("int res;", depth+1)
if field.seq:
self.emit("Py_ssize_t len;", depth+1)
self.emit("Py_ssize_t i;", depth+1)
- self.emit("tmp = PyObject_GetAttrString(obj, \"%s\");" % field.name, depth+1)
+ self.emit("tmp = _PyObject_GetAttrId(obj, &PyId_%s);" % field.name, depth+1)
self.emit("if (tmp == NULL) goto failed;", depth+1)
if field.seq:
self.emit("if (!PyList_Check(tmp)) {", depth+1)
@@ -552,6 +560,8 @@ class PyTypesDeclareVisitor(PickleVisitor):
self.emit("static PyTypeObject *%s_type;" % name, 0)
self.emit("static PyObject* ast2obj_%s(void*);" % name, 0)
if prod.fields:
+ for f in prod.fields:
+ self.emit_identifier(f.name)
self.emit("static char *%s_fields[]={" % name,0)
for f in prod.fields:
self.emit('"%s",' % f.name, 1)
@@ -560,6 +570,8 @@ class PyTypesDeclareVisitor(PickleVisitor):
def visitSum(self, sum, name):
self.emit("static PyTypeObject *%s_type;" % name, 0)
if sum.attributes:
+ for a in sum.attributes:
+ self.emit_identifier(a.name)
self.emit("static char *%s_attributes[] = {" % name, 0)
for a in sum.attributes:
self.emit('"%s",' % a.name, 1)
@@ -579,6 +591,8 @@ class PyTypesDeclareVisitor(PickleVisitor):
def visitConstructor(self, cons, name):
self.emit("static PyTypeObject *%s_type;" % cons.name, 0)
if cons.fields:
+ for t in cons.fields:
+ self.emit_identifier(t.name)
self.emit("static char *%s_fields[]={" % cons.name, 0)
for t in cons.fields:
self.emit('"%s",' % t.name, 1)
@@ -588,13 +602,39 @@ class PyTypesVisitor(PickleVisitor):
def visitModule(self, mod):
self.emit("""
+typedef struct {
+ PyObject_HEAD
+ PyObject *dict;
+} AST_object;
+
+static void
+ast_dealloc(AST_object *self)
+{
+ Py_CLEAR(self->dict);
+ Py_TYPE(self)->tp_free(self);
+}
+
+static int
+ast_traverse(AST_object *self, visitproc visit, void *arg)
+{
+ Py_VISIT(self->dict);
+ return 0;
+}
+
+static void
+ast_clear(AST_object *self)
+{
+ Py_CLEAR(self->dict);
+}
+
static int
ast_type_init(PyObject *self, PyObject *args, PyObject *kw)
{
+ _Py_IDENTIFIER(_fields);
Py_ssize_t i, numfields = 0;
int res = -1;
PyObject *key, *value, *fields;
- fields = PyObject_GetAttrString((PyObject*)Py_TYPE(self), "_fields");
+ fields = _PyObject_GetAttrId((PyObject*)Py_TYPE(self), &PyId__fields);
if (!fields)
PyErr_Clear();
if (fields) {
@@ -644,7 +684,8 @@ static PyObject *
ast_type_reduce(PyObject *self, PyObject *unused)
{
PyObject *res;
- PyObject *dict = PyObject_GetAttrString(self, "__dict__");
+ _Py_IDENTIFIER(__dict__);
+ PyObject *dict = _PyObject_GetAttrId(self, &PyId___dict__);
if (dict == NULL) {
if (PyErr_ExceptionMatches(PyExc_AttributeError))
PyErr_Clear();
@@ -664,12 +705,17 @@ static PyMethodDef ast_type_methods[] = {
{NULL}
};
+static PyGetSetDef ast_type_getsets[] = {
+ {"__dict__", PyObject_GenericGetDict, PyObject_GenericSetDict},
+ {NULL}
+};
+
static PyTypeObject AST_type = {
PyVarObject_HEAD_INIT(&PyType_Type, 0)
"_ast.AST",
- sizeof(PyObject),
+ sizeof(AST_object),
0,
- 0, /* tp_dealloc */
+ (destructor)ast_dealloc, /* tp_dealloc */
0, /* tp_print */
0, /* tp_getattr */
0, /* tp_setattr */
@@ -684,26 +730,26 @@ static PyTypeObject AST_type = {
PyObject_GenericGetAttr, /* tp_getattro */
PyObject_GenericSetAttr, /* tp_setattro */
0, /* tp_as_buffer */
- Py_TPFLAGS_DEFAULT | Py_TPFLAGS_BASETYPE, /* tp_flags */
+ Py_TPFLAGS_DEFAULT | Py_TPFLAGS_BASETYPE | Py_TPFLAGS_HAVE_GC, /* tp_flags */
0, /* tp_doc */
- 0, /* tp_traverse */
- 0, /* tp_clear */
+ (traverseproc)ast_traverse, /* tp_traverse */
+ (inquiry)ast_clear, /* tp_clear */
0, /* tp_richcompare */
0, /* tp_weaklistoffset */
0, /* tp_iter */
0, /* tp_iternext */
ast_type_methods, /* tp_methods */
0, /* tp_members */
- 0, /* tp_getset */
+ ast_type_getsets, /* tp_getset */
0, /* tp_base */
0, /* tp_dict */
0, /* tp_descr_get */
0, /* tp_descr_set */
- 0, /* tp_dictoffset */
+ offsetof(AST_object, dict),/* tp_dictoffset */
(initproc)ast_type_init, /* tp_init */
PyType_GenericAlloc, /* tp_alloc */
PyType_GenericNew, /* tp_new */
- PyObject_Del, /* tp_free */
+ PyObject_GC_Del, /* tp_free */
};
@@ -730,6 +776,7 @@ static PyTypeObject* make_type(char *type, PyTypeObject* base, char**fields, int
static int add_attributes(PyTypeObject* type, char**attrs, int num_fields)
{
int i, result;
+ _Py_IDENTIFIER(_attributes);
PyObject *s, *l = PyTuple_New(num_fields);
if (!l)
return 0;
@@ -741,7 +788,7 @@ static int add_attributes(PyTypeObject* type, char**attrs, int num_fields)
}
PyTuple_SET_ITEM(l, i, s);
}
- result = PyObject_SetAttrString((PyObject*)type, "_attributes", l) >= 0;
+ result = _PyObject_SetAttrId((PyObject*)type, &PyId__attributes, l) >= 0;
Py_DECREF(l);
return result;
}
@@ -750,7 +797,7 @@ static int add_attributes(PyTypeObject* type, char**attrs, int num_fields)
static PyObject* ast2obj_list(asdl_seq *seq, PyObject* (*func)(void*))
{
- int i, n = asdl_seq_LEN(seq);
+ Py_ssize_t i, n = asdl_seq_LEN(seq);
PyObject *result = PyList_New(n);
PyObject *value;
if (!result)
@@ -775,6 +822,7 @@ static PyObject* ast2obj_object(void *o)
}
#define ast2obj_identifier ast2obj_object
#define ast2obj_string ast2obj_object
+#define ast2obj_bytes ast2obj_object
static PyObject* ast2obj_int(long b)
{
@@ -812,6 +860,15 @@ static int obj2ast_string(PyObject* obj, PyObject** out, PyArena* arena)
return obj2ast_object(obj, out, arena);
}
+static int obj2ast_bytes(PyObject* obj, PyObject** out, PyArena* arena)
+{
+ if (!PyBytes_CheckExact(obj)) {
+ PyErr_SetString(PyExc_TypeError, "AST bytes must be of type bytes");
+ return 1;
+ }
+ return obj2ast_object(obj, out, arena);
+}
+
static int obj2ast_int(PyObject* obj, int* out, PyArena* arena)
{
int i;
@@ -910,10 +967,6 @@ class ASTModuleVisitor(PickleVisitor):
self.emit('if (PyDict_SetItemString(d, "AST", (PyObject*)&AST_type) < 0) return NULL;', 1)
self.emit('if (PyModule_AddIntConstant(m, "PyCF_ONLY_AST", PyCF_ONLY_AST) < 0)', 1)
self.emit("return NULL;", 2)
- # Value of version: "$Revision$"
- self.emit('if (PyModule_AddStringConstant(m, "__version__", "%s") < 0)'
- % mod.version, 1)
- self.emit("return NULL;", 2)
for dfn in mod.dfns:
self.visit(dfn)
self.emit("return m;", 1)
@@ -997,7 +1050,7 @@ class ObjVisitor(PickleVisitor):
for a in sum.attributes:
self.emit("value = ast2obj_%s(o->%s);" % (a.type, a.name), 1)
self.emit("if (!value) goto failed;", 1)
- self.emit('if (PyObject_SetAttrString(result, "%s", value) < 0)' % a.name, 1)
+ self.emit('if (_PyObject_SetAttrId(result, &PyId_%s, value) < 0)' % a.name, 1)
self.emit('goto failed;', 2)
self.emit('Py_DECREF(value);', 1)
self.func_end()
@@ -1043,7 +1096,7 @@ class ObjVisitor(PickleVisitor):
value = "o->v.%s.%s" % (name, field.name)
self.set(field, value, depth)
emit("if (!value) goto failed;", 0)
- emit('if (PyObject_SetAttrString(result, "%s", value) == -1)' % field.name, 0)
+ emit('if (_PyObject_SetAttrId(result, &PyId_%s, value) == -1)' % field.name, 0)
emit("goto failed;", 1)
emit("Py_DECREF(value);", 0)
@@ -1066,7 +1119,7 @@ class ObjVisitor(PickleVisitor):
# While the sequence elements are stored as void*,
# ast2obj_cmpop expects an enum
self.emit("{", depth)
- self.emit("int i, n = asdl_seq_LEN(%s);" % value, depth+1)
+ self.emit("Py_ssize_t i, n = asdl_seq_LEN(%s);" % value, depth+1)
self.emit("value = PyList_New(n);", depth+1)
self.emit("if (!value) goto failed;", depth+1)
self.emit("for(i = 0; i < n; i++)", depth+1)
@@ -1134,24 +1187,12 @@ class ChainOfVisitors:
common_msg = "/* File automatically generated by %s. */\n\n"
-c_file_msg = """
-/*
- __version__ %s.
-
- This module must be committed separately after each AST grammar change;
- The __version__ number is set to the revision number of the commit
- containing the grammar change.
-*/
-
-"""
-
def main(srcfile):
argv0 = sys.argv[0]
components = argv0.split(os.sep)
argv0 = os.sep.join(components[-2:])
auto_gen_msg = common_msg % argv0
mod = asdl.parse(srcfile)
- mod.version = "82163"
if not asdl.check(mod):
sys.exit(1)
if INC_DIR:
@@ -1173,7 +1214,8 @@ def main(srcfile):
p = os.path.join(SRC_DIR, str(mod.name) + "-ast.c")
f = open(p, "w")
f.write(auto_gen_msg)
- f.write(c_file_msg % mod.version)
+ f.write('#include <stddef.h>\n')
+ f.write('\n')
f.write('#include "Python.h"\n')
f.write('#include "%s-ast.h"\n' % mod.name)
f.write('\n')
diff --git a/Parser/intrcheck.c b/Parser/intrcheck.c
deleted file mode 100644
index 4439864..0000000
--- a/Parser/intrcheck.c
+++ /dev/null
@@ -1,174 +0,0 @@
-
-/* Check for interrupts */
-
-#include "Python.h"
-#include "pythread.h"
-
-#ifdef QUICKWIN
-
-#include <io.h>
-
-void
-PyOS_InitInterrupts(void)
-{
-}
-
-void
-PyOS_FiniInterrupts(void)
-{
-}
-
-int
-PyOS_InterruptOccurred(void)
-{
- _wyield();
-}
-
-#define OK
-
-#endif /* QUICKWIN */
-
-#if defined(_M_IX86) && !defined(__QNX__)
-#include <io.h>
-#endif
-
-#if defined(MSDOS) && !defined(QUICKWIN)
-
-#ifdef __GNUC__
-
-/* This is for DJGPP's GO32 extender. I don't know how to trap
- * control-C (There's no API for ctrl-C, and I don't want to mess with
- * the interrupt vectors.) However, this DOES catch control-break.
- * --Amrit
- */
-
-#include <go32.h>
-
-void
-PyOS_InitInterrupts(void)
-{
- _go32_want_ctrl_break(1 /* TRUE */);
-}
-
-void
-PyOS_FiniInterrupts(void)
-{
-}
-
-int
-PyOS_InterruptOccurred(void)
-{
- return _go32_was_ctrl_break_hit();
-}
-
-#else /* !__GNUC__ */
-
-/* This might work for MS-DOS (untested though): */
-
-void
-PyOS_InitInterrupts(void)
-{
-}
-
-void
-PyOS_FiniInterrupts(void)
-{
-}
-
-int
-PyOS_InterruptOccurred(void)
-{
- int interrupted = 0;
- while (kbhit()) {
- if (getch() == '\003')
- interrupted = 1;
- }
- return interrupted;
-}
-
-#endif /* __GNUC__ */
-
-#define OK
-
-#endif /* MSDOS && !QUICKWIN */
-
-
-#ifndef OK
-
-/* Default version -- for real operating systems and for Standard C */
-
-#include <stdio.h>
-#include <string.h>
-#include <signal.h>
-
-static int interrupted;
-
-void
-PyErr_SetInterrupt(void)
-{
- interrupted = 1;
-}
-
-extern int PyErr_CheckSignals(void);
-
-static int
-checksignals_witharg(void * arg)
-{
- return PyErr_CheckSignals();
-}
-
-static void
-intcatcher(int sig)
-{
- extern void Py_Exit(int);
- static char message[] =
-"python: to interrupt a truly hanging Python program, interrupt once more.\n";
- switch (interrupted++) {
- case 0:
- break;
- case 1:
- write(2, message, strlen(message));
- break;
- case 2:
- interrupted = 0;
- Py_Exit(1);
- break;
- }
- PyOS_setsig(SIGINT, intcatcher);
- Py_AddPendingCall(checksignals_witharg, NULL);
-}
-
-static void (*old_siginthandler)(int) = SIG_DFL;
-
-void
-PyOS_InitInterrupts(void)
-{
- if ((old_siginthandler = PyOS_setsig(SIGINT, SIG_IGN)) != SIG_IGN)
- PyOS_setsig(SIGINT, intcatcher);
-}
-
-void
-PyOS_FiniInterrupts(void)
-{
- PyOS_setsig(SIGINT, old_siginthandler);
-}
-
-int
-PyOS_InterruptOccurred(void)
-{
- if (!interrupted)
- return 0;
- interrupted = 0;
- return 1;
-}
-
-#endif /* !OK */
-
-void
-PyOS_AfterFork(void)
-{
-#ifdef WITH_THREAD
- PyEval_ReInitThreads();
- PyThread_ReInitTLS();
-#endif
-}
diff --git a/Parser/myreadline.c b/Parser/myreadline.c
index 93edd7f..d864623 100644
--- a/Parser/myreadline.c
+++ b/Parser/myreadline.c
@@ -35,12 +35,11 @@ int (*PyOS_InputHook)(void) = NULL;
static int
my_fgets(char *buf, int len, FILE *fp)
{
- char *p;
- int err;
#ifdef MS_WINDOWS
- int i;
+ HANDLE hInterruptEvent;
#endif
-
+ char *p;
+ int err;
while (1) {
if (PyOS_InputHook != NULL)
(void)(PyOS_InputHook)();
@@ -57,20 +56,24 @@ my_fgets(char *buf, int len, FILE *fp)
/* Ctrl-C anywhere on the line or Ctrl-Z if the only character
on a line will set ERROR_OPERATION_ABORTED. Under normal
circumstances Ctrl-C will also have caused the SIGINT handler
- to fire. This signal fires in another thread and is not
- guaranteed to have occurred before this point in the code.
-
- Therefore: check in a small loop to see if the trigger has
- fired, in which case assume this is a Ctrl-C event. If it
- hasn't fired within 10ms assume that this is a Ctrl-Z on its
- own or that the signal isn't going to fire for some other
- reason and drop through to check for EOF.
+ to fire which will have set the event object returned by
+ _PyOS_SigintEvent. This signal fires in another thread and
+ is not guaranteed to have occurred before this point in the
+ code.
+
+ Therefore: check whether the event is set with a small timeout.
+ If it is, assume this is a Ctrl-C and reset the event. If it
+ isn't set assume that this is a Ctrl-Z on its own and drop
+ through to check for EOF.
*/
if (GetLastError()==ERROR_OPERATION_ABORTED) {
- for (i = 0; i < 10; i++) {
- if (PyOS_InterruptOccurred())
- return 1;
- Sleep(1);
+ hInterruptEvent = _PyOS_SigintEvent();
+ switch (WaitForSingleObject(hInterruptEvent, 10)) {
+ case WAIT_OBJECT_0:
+ ResetEvent(hInterruptEvent);
+ return 1; /* Interrupt */
+ case WAIT_FAILED:
+ return -2; /* Error */
}
}
#endif /* MS_WINDOWS */
@@ -90,7 +93,7 @@ my_fgets(char *buf, int len, FILE *fp)
#endif
if (s < 0)
return 1;
- /* try again */
+ /* try again */
continue;
}
#endif
diff --git a/Parser/node.c b/Parser/node.c
index 0dea30f..1e4f0da 100644
--- a/Parser/node.c
+++ b/Parser/node.c
@@ -71,7 +71,7 @@ fancy_roundup(int n)
* capacity. The code is tricky to avoid that.
*/
#define XXXROUNDUP(n) ((n) <= 1 ? (n) : \
- (n) <= 128 ? (((n) + 3) & ~3) : \
+ (n) <= 128 ? _Py_SIZE_ROUND_UP((n), 4) : \
fancy_roundup(n))
diff --git a/Parser/parsetok.c b/Parser/parsetok.c
index bb9afc4..7beb735 100644
--- a/Parser/parsetok.c
+++ b/Parser/parsetok.c
@@ -13,7 +13,7 @@
/* Forward */
static node *parsetok(struct tok_state *, grammar *, int, perrdetail *, int *);
-static void initerr(perrdetail *err_ret, const char* filename);
+static int initerr(perrdetail *err_ret, const char* filename);
/* Parse input coming from a string. Return error code, print some errors. */
node *
@@ -48,7 +48,8 @@ PyParser_ParseStringFlagsFilenameEx(const char *s, const char *filename,
struct tok_state *tok;
int exec_input = start == file_input;
- initerr(err_ret, filename);
+ if (initerr(err_ret, filename) < 0)
+ return NULL;
if (*flags & PyPARSE_IGNORE_COOKIE)
tok = PyTokenizer_FromUTF8(s, exec_input);
@@ -59,7 +60,10 @@ PyParser_ParseStringFlagsFilenameEx(const char *s, const char *filename,
return NULL;
}
- tok->filename = filename ? filename : "<string>";
+#ifndef PGEN
+ Py_INCREF(err_ret->filename);
+ tok->filename = err_ret->filename;
+#endif
return parsetok(tok, g, start, err_ret, flags);
}
@@ -90,13 +94,17 @@ PyParser_ParseFileFlagsEx(FILE *fp, const char *filename,
{
struct tok_state *tok;
- initerr(err_ret, filename);
+ if (initerr(err_ret, filename) < 0)
+ return NULL;
if ((tok = PyTokenizer_FromFile(fp, (char *)enc, ps1, ps2)) == NULL) {
err_ret->error = E_NOMEM;
return NULL;
}
- tok->filename = filename;
+#ifndef PGEN
+ Py_INCREF(err_ret->filename);
+ tok->filename = err_ret->filename;
+#endif
return parsetok(tok, g, start, err_ret, flags);
}
@@ -216,6 +224,36 @@ parsetok(struct tok_state *tok, grammar *g, int start, perrdetail *err_ret,
if (err_ret->error == E_DONE) {
n = ps->p_tree;
ps->p_tree = NULL;
+
+#ifndef PGEN
+ /* Check that the source for a single input statement really
+ is a single statement by looking at what is left in the
+ buffer after parsing. Trailing whitespace and comments
+ are OK. */
+ if (start == single_input) {
+ char *cur = tok->cur;
+ char c = *tok->cur;
+
+ for (;;) {
+ while (c == ' ' || c == '\t' || c == '\n' || c == '\014')
+ c = *++cur;
+
+ if (!c)
+ break;
+
+ if (c != '#') {
+ err_ret->error = E_BADSINGLE;
+ PyNode_Free(n);
+ n = NULL;
+ break;
+ }
+
+ /* Suck up comment. */
+ while (c && c != '\n')
+ c = *++cur;
+ }
+ }
+#endif
}
else
n = NULL;
@@ -226,7 +264,7 @@ parsetok(struct tok_state *tok, grammar *g, int start, perrdetail *err_ret,
PyParser_Delete(ps);
if (n == NULL) {
- if (tok->lineno <= 1 && tok->done == E_EOF)
+ if (tok->done == E_EOF)
err_ret->error = E_EOF;
err_ret->lineno = tok->lineno;
if (tok->buf != NULL) {
@@ -269,14 +307,24 @@ done:
return n;
}
-static void
+static int
initerr(perrdetail *err_ret, const char *filename)
{
err_ret->error = E_OK;
- err_ret->filename = filename;
err_ret->lineno = 0;
err_ret->offset = 0;
err_ret->text = NULL;
err_ret->token = -1;
err_ret->expected = -1;
+#ifndef PGEN
+ if (filename)
+ err_ret->filename = PyUnicode_DecodeFSDefault(filename);
+ else
+ err_ret->filename = PyUnicode_FromString("<string>");
+ if (err_ret->filename == NULL) {
+ err_ret->error = E_ERROR;
+ return -1;
+ }
+#endif
+ return 0;
}
diff --git a/Parser/parsetok_pgen.c b/Parser/parsetok_pgen.c
new file mode 100644
index 0000000..97b9288
--- /dev/null
+++ b/Parser/parsetok_pgen.c
@@ -0,0 +1,2 @@
+#define PGEN
+#include "parsetok.c"
diff --git a/Parser/pgenmain.c b/Parser/pgenmain.c
index 4b7b55a..52b8380 100644
--- a/Parser/pgenmain.c
+++ b/Parser/pgenmain.c
@@ -29,6 +29,8 @@ int Py_IgnoreEnvironmentFlag;
/* Forward */
grammar *getgrammar(char *filename);
+void Py_Exit(int) _Py_NO_RETURN;
+
void
Py_Exit(int sts)
{
diff --git a/Parser/tokenizer.c b/Parser/tokenizer.c
index 5ba12a4..93a4a5c 100644
--- a/Parser/tokenizer.c
+++ b/Parser/tokenizer.c
@@ -128,7 +128,6 @@ tok_new(void)
tok->prompt = tok->nextprompt = NULL;
tok->lineno = 0;
tok->level = 0;
- tok->filename = NULL;
tok->altwarning = 1;
tok->alterror = 1;
tok->alttabsize = 1;
@@ -140,6 +139,7 @@ tok_new(void)
tok->encoding = NULL;
tok->cont_line = 0;
#ifndef PGEN
+ tok->filename = NULL;
tok->decoding_readline = NULL;
tok->decoding_buffer = NULL;
#endif
@@ -462,6 +462,8 @@ static int
fp_setreadl(struct tok_state *tok, const char* enc)
{
PyObject *readline = NULL, *stream = NULL, *io = NULL;
+ _Py_IDENTIFIER(open);
+ _Py_IDENTIFIER(readline);
int fd;
io = PyImport_ImportModuleNoBlock("io");
@@ -474,13 +476,13 @@ fp_setreadl(struct tok_state *tok, const char* enc)
goto cleanup;
}
- stream = PyObject_CallMethod(io, "open", "isisOOO",
+ stream = _PyObject_CallMethodId(io, &PyId_open, "isisOOO",
fd, "r", -1, enc, Py_None, Py_None, Py_False);
if (stream == NULL)
goto cleanup;
Py_XDECREF(tok->decoding_readline);
- readline = PyObject_GetAttrString(stream, "readline");
+ readline = _PyObject_GetAttrId(stream, &PyId_readline);
tok->decoding_readline = readline;
/* The file has been reopened; parsing will restart from
@@ -545,7 +547,6 @@ decoding_fgets(char *s, int size, struct tok_state *tok)
{
char *line = NULL;
int badchar = 0;
- PyObject *filename;
for (;;) {
if (tok->decoding_state == STATE_NORMAL) {
/* We already have a codec associated with
@@ -586,19 +587,12 @@ decoding_fgets(char *s, int size, struct tok_state *tok)
if (badchar) {
/* Need to add 1 to the line number, since this line
has not been counted, yet. */
- if (tok->filename != NULL)
- filename = PyUnicode_DecodeFSDefault(tok->filename);
- else
- filename = PyUnicode_FromString("<file>");
- if (filename != NULL) {
- PyErr_Format(PyExc_SyntaxError,
- "Non-UTF-8 code starting with '\\x%.2x' "
- "in file %U on line %i, "
- "but no encoding declared; "
- "see http://python.org/dev/peps/pep-0263/ for details",
- badchar, filename, tok->lineno + 1);
- Py_DECREF(filename);
- }
+ PyErr_Format(PyExc_SyntaxError,
+ "Non-UTF-8 code starting with '\\x%.2x' "
+ "in file %U on line %i, "
+ "but no encoding declared; "
+ "see http://python.org/dev/peps/pep-0263/ for details",
+ badchar, tok->filename, tok->lineno + 1);
return error_ret(tok);
}
#endif
@@ -856,6 +850,7 @@ PyTokenizer_Free(struct tok_state *tok)
#ifndef PGEN
Py_XDECREF(tok->decoding_readline);
Py_XDECREF(tok->decoding_buffer);
+ Py_XDECREF(tok->filename);
#endif
if (tok->fp != NULL && tok->buf != NULL)
PyMem_FREE(tok->buf);
@@ -1250,8 +1245,13 @@ indenterror(struct tok_state *tok)
return 1;
}
if (tok->altwarning) {
- PySys_WriteStderr("%s: inconsistent use of tabs and spaces "
+#ifdef PGEN
+ PySys_WriteStderr("inconsistent use of tabs and spaces "
+ "in indentation\n");
+#else
+ PySys_FormatStderr("%U: inconsistent use of tabs and spaces "
"in indentation\n", tok->filename);
+#endif
tok->altwarning = 0;
}
return 0;
@@ -1260,14 +1260,16 @@ indenterror(struct tok_state *tok)
#ifdef PGEN
#define verify_identifier(tok) 1
#else
-/* Verify that the identifier follows PEP 3131. */
+/* Verify that the identifier follows PEP 3131.
+ All identifier strings are guaranteed to be "ready" unicode objects.
+ */
static int
verify_identifier(struct tok_state *tok)
{
PyObject *s;
int result;
s = PyUnicode_DecodeUTF8(tok->start, tok->cur - tok->start, NULL);
- if (s == NULL) {
+ if (s == NULL || PyUnicode_READY(s) == -1) {
if (PyErr_ExceptionMatches(PyExc_UnicodeDecodeError)) {
PyErr_Clear();
tok->done = E_IDENTIFIER;
@@ -1410,13 +1412,20 @@ tok_get(register struct tok_state *tok, char **p_start, char **p_end)
/* Identifier (most frequent token!) */
nonascii = 0;
if (is_potential_identifier_start(c)) {
- /* Process b"", r"" and br"" */
- if (c == 'b' || c == 'B') {
- c = tok_nextc(tok);
- if (c == '"' || c == '\'')
- goto letter_quote;
- }
- if (c == 'r' || c == 'R') {
+ /* Process b"", r"", u"", br"" and rb"" */
+ int saw_b = 0, saw_r = 0, saw_u = 0;
+ while (1) {
+ if (!(saw_b || saw_u) && (c == 'b' || c == 'B'))
+ saw_b = 1;
+ /* Since this is a backwards compatibility support literal we don't
+ want to support it in arbitrary order like byte literals. */
+ else if (!(saw_b || saw_u || saw_r) && (c == 'u' || c == 'U'))
+ saw_u = 1;
+ /* ur"" and ru"" are not supported */
+ else if (!(saw_r || saw_u) && (c == 'r' || c == 'R'))
+ saw_r = 1;
+ else
+ break;
c = tok_nextc(tok);
if (c == '"' || c == '\'')
goto letter_quote;
@@ -1692,17 +1701,18 @@ PyTokenizer_Get(struct tok_state *tok, char **p_start, char **p_end)
return result;
}
-/* Get -*- encoding -*- from a Python file.
+/* Get the encoding of a Python file. Check for the coding cookie and check if
+ the file starts with a BOM.
- PyTokenizer_FindEncoding returns NULL when it can't find the encoding in
- the first or second line of the file (in which case the encoding
- should be assumed to be PyUnicode_GetDefaultEncoding()).
+ PyTokenizer_FindEncodingFilename() returns NULL when it can't find the
+ encoding in the first or second line of the file (in which case the encoding
+ should be assumed to be UTF-8).
+
+ The char* returned is malloc'ed via PyMem_MALLOC() and thus must be freed
+ by the caller. */
- The char * returned is malloc'ed via PyMem_MALLOC() and thus must be freed
- by the caller.
-*/
char *
-PyTokenizer_FindEncoding(int fd)
+PyTokenizer_FindEncodingFilename(int fd, PyObject *filename)
{
struct tok_state *tok;
FILE *fp;
@@ -1721,6 +1731,20 @@ PyTokenizer_FindEncoding(int fd)
fclose(fp);
return NULL;
}
+#ifndef PGEN
+ if (filename != NULL) {
+ Py_INCREF(filename);
+ tok->filename = filename;
+ }
+ else {
+ tok->filename = PyUnicode_FromString("<string>");
+ if (tok->filename == NULL) {
+ fclose(fp);
+ PyTokenizer_Free(tok);
+ return encoding;
+ }
+ }
+#endif
while (tok->lineno < 2 && tok->done == E_OK) {
PyTokenizer_Get(tok, &p_start, &p_end);
}
@@ -1734,6 +1758,12 @@ PyTokenizer_FindEncoding(int fd)
return encoding;
}
+char *
+PyTokenizer_FindEncoding(int fd)
+{
+ return PyTokenizer_FindEncodingFilename(fd, NULL);
+}
+
#ifdef Py_DEBUG
void
diff --git a/Parser/tokenizer.h b/Parser/tokenizer.h
index 2be3bf2..ed1f3aa 100644
--- a/Parser/tokenizer.h
+++ b/Parser/tokenizer.h
@@ -40,7 +40,13 @@ struct tok_state {
int level; /* () [] {} Parentheses nesting level */
/* Used to allow free continuations inside them */
/* Stuff for checking on different tab sizes */
- const char *filename; /* encoded to the filesystem encoding */
+#ifndef PGEN
+ /* pgen doesn't have access to Python codecs, it cannot decode the input
+ filename. The bytes filename might be kept, but it is only used by
+ indenterror() and it is not really needed: pgen only compiles one file
+ (Grammar/Grammar). */
+ PyObject *filename;
+#endif
int altwarning; /* Issue warning if alternate tabs don't match */
int alterror; /* Issue error if alternate tabs don't match */
int alttabsize; /* Alternate tab spacing */
@@ -69,7 +75,6 @@ extern void PyTokenizer_Free(struct tok_state *);
extern int PyTokenizer_Get(struct tok_state *, char **, char **);
extern char * PyTokenizer_RestoreEncoding(struct tok_state* tok,
int len, int *offset);
-extern char * PyTokenizer_FindEncoding(int);
#ifdef __cplusplus
}
generated by cgit v0.12 at 2024-12-12 12:36:46 (GMT)