#include "Python.h"
#include "Python-ast.h"
#include "code.h"
#include "symtable.h"
#include "structmember.h"
/* error strings used for warnings */
#define GLOBAL_AFTER_ASSIGN \
"name '%U' is assigned to before global declaration"
#define NONLOCAL_AFTER_ASSIGN \
"name '%U' is assigned to before nonlocal declaration"
#define GLOBAL_AFTER_USE \
"name '%U' is used prior to global declaration"
#define NONLOCAL_AFTER_USE \
"name '%U' is used prior to nonlocal declaration"
#define GLOBAL_ANNOT \
"annotated name '%U' can't be global"
#define NONLOCAL_ANNOT \
"annotated name '%U' can't be nonlocal"
#define IMPORT_STAR_WARNING "import * only allowed at module level"
static PySTEntryObject *
ste_new(struct symtable *st, identifier name, _Py_block_ty block,
void *key, int lineno, int col_offset)
{
PySTEntryObject *ste = NULL;
PyObject *k = NULL;
k = PyLong_FromVoidPtr(key);
if (k == NULL)
goto fail;
ste = PyObject_New(PySTEntryObject, &PySTEntry_Type);
if (ste == NULL) {
Py_DECREF(k);
goto fail;
}
ste->ste_table = st;
ste->ste_id = k; /* ste owns reference to k */
Py_INCREF(name);
ste->ste_name = name;
ste->ste_symbols = NULL;
ste->ste_varnames = NULL;
ste->ste_children = NULL;
ste->ste_directives = NULL;
ste->ste_type = block;
ste->ste_nested = 0;
ste->ste_free = 0;
ste->ste_varargs = 0;
ste->ste_varkeywords = 0;
ste->ste_opt_lineno = 0;
ste->ste_opt_col_offset = 0;
ste->ste_tmpname = 0;
ste->ste_lineno = lineno;
ste->ste_col_offset = col_offset;
if (st->st_cur != NULL &&
(st->st_cur->ste_nested ||
st->st_cur->ste_type == FunctionBlock))
ste->ste_nested = 1;
ste->ste_child_free = 0;
ste->ste_generator = 0;
ste->ste_coroutine = 0;
ste->ste_returns_value = 0;
ste->ste_needs_class_closure = 0;
ste->ste_symbols = PyDict_New();
ste->ste_varnames = PyList_New(0);
ste->ste_children = PyList_New(0);
if (ste->ste_symbols == NULL
|| ste->ste_varnames == NULL
|| ste->ste_children == NULL)
goto fail;
if (PyDict_SetItem(st->st_blocks, ste->ste_id, (PyObject *)ste) < 0)
goto fail;
return ste;
fail:
Py_XDECREF(ste);
return NULL;
}
static PyObject *
ste_repr(PySTEntryObject *ste)
{
return PyUnicode_FromFormat("",
ste->ste_name,
PyLong_AS_LONG(ste->ste_id), ste->ste_lineno);
}
static void
ste_dealloc(PySTEntryObject *ste)
{
ste->ste_table = NULL;
Py_XDECREF(ste->ste_id);
Py_XDECREF(ste->ste_name);
Py_XDECREF(ste->ste_symbols);
Py_XDECREF(ste->ste_varnames);
Py_XDECREF(ste->ste_children);
Py_XDECREF(ste->ste_directives);
PyObject_Del(ste);
}
#define OFF(x) offsetof(PySTEntryObject, x)
static PyMemberDef ste_memberlist[] = {
{"id", T_OBJECT, OFF(ste_id), READONLY},
{"name", T_OBJECT, OFF(ste_name), READONLY},
{"symbols", T_OBJECT, OFF(ste_symbols), READONLY},
{"varnames", T_OBJECT, OFF(ste_varnames), READONLY},
{"children", T_OBJECT, OFF(ste_children), READONLY},
{"nested", T_INT, OFF(ste_nested), READONLY},
{"type", T_INT, OFF(ste_type), READONLY},
{"lineno", T_INT, OFF(ste_lineno), READONLY},
{NULL}
};
PyTypeObject PySTEntry_Type = {
PyVarObject_HEAD_INIT(&PyType_Type, 0)
"symtable entry",
sizeof(PySTEntryObject),
0,
(destructor)ste_dealloc, /* tp_dealloc */
0, /* tp_print */
0, /* tp_getattr */
0, /* tp_setattr */
0, /* tp_reserved */
(reprfunc)ste_repr, /* tp_repr */
0, /* tp_as_number */
0, /* tp_as_sequence */
0, /* tp_as_mapping */
0, /* tp_hash */
0, /* tp_call */
0, /* tp_str */
PyObject_GenericGetAttr, /* tp_getattro */
0, /* tp_setattro */
0, /* tp_as_buffer */
Py_TPFLAGS_DEFAULT, /* tp_flags */
0, /* tp_doc */
0, /* tp_traverse */
0, /* tp_clear */
0, /* tp_richcompare */
0, /* tp_weaklistoffset */
0, /* tp_iter */
0, /* tp_iternext */
0, /* tp_methods */
ste_memberlist, /* tp_members */
0, /* tp_getset */
0, /* tp_base */
0, /* tp_dict */
0, /* tp_descr_get */
0, /* tp_descr_set */
0, /* tp_dictoffset */
0, /* tp_init */
0, /* tp_alloc */
0, /* tp_new */
};
static int symtable_analyze(struct symtable *st);
static int symtable_enter_block(struct symtable *st, identifier name,
_Py_block_ty block, void *ast, int lineno,
int col_offset);
static int symtable_exit_block(struct symtable *st, void *ast);
static int symtable_visit_stmt(struct symtable *st, stmt_ty s);
static int symtable_visit_expr(struct symtable *st, expr_ty s);
static int symtable_visit_genexp(struct symtable *st, expr_ty s);
static int symtable_visit_listcomp(struct symtable *st, expr_ty s);
static int symtable_visit_setcomp(struct symtable *st, expr_ty s);
static int symtable_visit_dictcomp(struct symtable *st, expr_ty s);
static int symtable_visit_arguments(struct symtable *st, arguments_ty);
static int symtable_visit_excepthandler(struct symtable *st, excepthandler_ty);
static int symtable_visit_alias(struct symtable *st, alias_ty);
static int symtable_visit_comprehension(struct symtable *st, comprehension_ty);
static int symtable_visit_keyword(struct symtable *st, keyword_ty);
static int symtable_visit_slice(struct symtable *st, slice_ty);
static int symtable_visit_params(struct symtable *st, asdl_seq *args);
static int symtable_visit_argannotations(struct symtable *st, asdl_seq *args);
static int symtable_implicit_arg(struct symtable *st, int pos);
static int symtable_visit_annotations(struct symtable *st, stmt_ty s, arguments_ty, expr_ty);
static int symtable_visit_withitem(struct symtable *st, withitem_ty item);
static identifier top = NULL, lambda = NULL, genexpr = NULL,
listcomp = NULL, setcomp = NULL, dictcomp = NULL,
__class__ = NULL;
#define GET_IDENTIFIER(VAR) \
((VAR) ? (VAR) : ((VAR) = PyUnicode_InternFromString(# VAR)))
#define DUPLICATE_ARGUMENT \
"duplicate argument '%U' in function definition"
static struct symtable *
symtable_new(void)
{
struct symtable *st;
st = (struct symtable *)PyMem_Malloc(sizeof(struct symtable));
if (st == NULL) {
PyErr_NoMemory();
return NULL;
}
st->st_filename = NULL;
st->st_blocks = NULL;
if ((st->st_stack = PyList_New(0)) == NULL)
goto fail;
if ((st->st_blocks = PyDict_New()) == NULL)
goto fail;
st->st_cur = NULL;
st->st_private = NULL;
return st;
fail:
PySymtable_Free(st);
return NULL;
}
/* When compiling the use of C stack is probably going to be a lot
lighter than when executing Python code but still can overflow
and causing a Python crash if not checked (e.g. eval("()"*300000)).
Using the current recursion limit for the compiler seems too
restrictive (it caused at least one test to fail) so a factor is
used to allow deeper recursion when compiling an expression.
Using a scaling factor means this should automatically adjust when
the recursion limit is adjusted for small or large C stack allocations.
*/
#define COMPILER_STACK_FRAME_SCALE 3
struct symtable *
PySymtable_BuildObject(mod_ty mod, PyObject *filename, PyFutureFeatures *future)
{
struct symtable *st = symtable_new();
asdl_seq *seq;
int i;
PyThreadState *tstate;
int recursion_limit = Py_GetRecursionLimit();
if (st == NULL)
return NULL;
if (filename == NULL) {
PySymtable_Free(st);
return NULL;
}
Py_INCREF(filename);
st->st_filename = filename;
st->st_future = future;
/* Setup recursion depth check counters */
tstate = PyThreadState_GET();
if (!tstate) {
PySymtable_Free(st);
return NULL;
}
/* Be careful here to prevent overflow. */
st->recursion_depth = (tstate->recursion_depth < INT_MAX / COMPILER_STACK_FRAME_SCALE) ?
tstate->recursion_depth * COMPILER_STACK_FRAME_SCALE : tstate->recursion_depth;
st->recursion_limit = (recursion_limit < INT_MAX / COMPILER_STACK_FRAME_SCALE) ?
recursion_limit * COMPILER_STACK_FRAME_SCALE : recursion_limit;
/* Make the initial symbol information gathering pass */
if (!GET_IDENTIFIER(top) ||
!symtable_enter_block(st, top, ModuleBlock, (void *)mod, 0, 0)) {
PySymtable_Free(st);
return NULL;
}
st->st_top = st->st_cur;
switch (mod->kind) {
case Module_kind:
seq = mod->v.Module.body;
for (i = 0; i < asdl_seq_LEN(seq); i++)
if (!symtable_visit_stmt(st,
(stmt_ty)asdl_seq_GET(seq, i)))
goto error;
break;
case Expression_kind:
if (!symtable_visit_expr(st, mod->v.Expression.body))
goto error;
break;
case Interactive_kind:
seq = mod->v.Interactive.body;
for (i = 0; i < asdl_seq_LEN(seq); i++)
if (!symtable_visit_stmt(st,
(stmt_ty)asdl_seq_GET(seq, i)))
goto error;
break;
case Suite_kind:
PyErr_SetString(PyExc_RuntimeError,
"this compiler does not handle Suites");
goto error;
}
if (!symtable_exit_block(st, (void *)mod)) {
PySymtable_Free(st);
return NULL;
}
/* Make the second symbol analysis pass */
if (symtable_analyze(st))
return st;
PySymtable_Free(st);
return NULL;
error:
(void) symtable_exit_block(st, (void *)mod);
PySymtable_Free(st);
return NULL;
}
struct symtable *
PySymtable_Build(mod_ty mod, const char *filename_str, PyFutureFeatures *future)
{
PyObject *filename;
struct symtable *st;
filename = PyUnicode_DecodeFSDefault(filename_str);
if (filename == NULL)
return NULL;
st = PySymtable_BuildObject(mod, filename, future);
Py_DECREF(filename);
return st;
}
void
PySymtable_Free(struct symtable *st)
{
Py_XDECREF(st->st_filename);
Py_XDECREF(st->st_blocks);
Py_XDECREF(st->st_stack);
PyMem_Free((void *)st);
}
PySTEntryObject *
PySymtable_Lookup(struct symtable *st, void *key)
{
PyObject *k, *v;
k = PyLong_FromVoidPtr(key);
if (k == NULL)
return NULL;
v = PyDict_GetItem(st->st_blocks, k);
if (v) {
assert(PySTEntry_Check(v));
Py_INCREF(v);
}
else {
PyErr_SetString(PyExc_KeyError,
"unknown symbol table entry");
}
Py_DECREF(k);
return (PySTEntryObject *)v;
}
int
PyST_GetScope(PySTEntryObject *ste, PyObject *name)
{
PyObject *v = PyDict_GetItem(ste->ste_symbols, name);
if (!v)
return 0;
assert(PyLong_Check(v));
return (PyLong_AS_LONG(v) >> SCOPE_OFFSET) & SCOPE_MASK;
}
static int
error_at_directive(PySTEntryObject *ste, PyObject *name)
{
Py_ssize_t i;
PyObject *data;
assert(ste->ste_directives);
for (i = 0; i < PyList_GET_SIZE(ste->ste_directives); i++) {
data = PyList_GET_ITEM(ste->ste_directives, i);
assert(PyTuple_CheckExact(data));
assert(PyUnicode_CheckExact(PyTuple_GET_ITEM(data, 0)));
if (PyUnicode_Compare(PyTuple_GET_ITEM(data, 0), name) == 0) {
PyErr_SyntaxLocationObject(ste->ste_table->st_filename,
PyLong_AsLong(PyTuple_GET_ITEM(data, 1)),
PyLong_AsLong(PyTuple_GET_ITEM(data, 2)));
return 0;
}
}
PyErr_SetString(PyExc_RuntimeError,
"BUG: internal directive bookkeeping broken");
return 0;
}
/* Analyze raw symbol information to determine scope of each name.
The next several functions are helpers for symtable_analyze(),
which determines whether a name is local, global, or free. In addition,
it determines which local variables are cell variables; they provide
bindings that are used for free variables in enclosed blocks.
There are also two kinds of global variables, implicit and explicit. An
explicit global is declared with the global statement. An implicit
global is a free variable for which the compiler has found no binding
in an enclosing function scope. The implicit global is either a global
or a builtin. Python's module and class blocks use the xxx_NAME opcodes
to handle these names to implement slightly odd semantics. In such a
block, the name is treated as global until it is assigned to; then it
is treated as a local.
The symbol table requires two passes to determine the scope of each name.
The first pass collects raw facts from the AST via the symtable_visit_*
functions: the name is a parameter here, the name is used but not defined
here, etc. The second pass analyzes these facts during a pass over the
PySTEntryObjects created during pass 1.
When a function is entered during the second pass, the parent passes
the set of all name bindings visible to its children. These bindings
are used to determine if non-local variables are free or implicit globals.
Names which are explicitly declared nonlocal must exist in this set of
visible names - if they do not, a syntax error is raised. After doing
the local analysis, it analyzes each of its child blocks using an
updated set of name bindings.
The children update the free variable set. If a local variable is added to
the free variable set by the child, the variable is marked as a cell. The
function object being defined must provide runtime storage for the variable
that may outlive the function's frame. Cell variables are removed from the
free set before the analyze function returns to its parent.
During analysis, the names are:
symbols: dict mapping from symbol names to flag values (including offset scope values)
scopes: dict mapping from symbol names to scope values (no offset)
local: set of all symbol names local to the current scope
bound: set of all symbol names local to a containing function scope
free: set of all symbol names referenced but not bound in child scopes
global: set of all symbol names explicitly declared as global
*/
#define SET_SCOPE(DICT, NAME, I) { \
PyObject *o = PyLong_FromLong(I); \
if (!o) \
return 0; \
if (PyDict_SetItem((DICT), (NAME), o) < 0) { \
Py_DECREF(o); \
return 0; \
} \
Py_DECREF(o); \
}
/* Decide on scope of name, given flags.
The namespace dictionaries may be modified to record information
about the new name. For example, a new global will add an entry to
global. A name that was global can be changed to local.
*/
static int
analyze_name(PySTEntryObject *ste, PyObject *scopes, PyObject *name, long flags,
PyObject *bound, PyObject *local, PyObject *free,
PyObject *global)
{
if (flags & DEF_GLOBAL) {
if (flags & DEF_PARAM) {
PyErr_Format(PyExc_SyntaxError,
"name '%U' is parameter and global",
name);
return error_at_directive(ste, name);
}
if (flags & DEF_NONLOCAL) {
PyErr_Format(PyExc_SyntaxError,
"name '%U' is nonlocal and global",
name);
return error_at_directive(ste, name);
}
SET_SCOPE(scopes, name, GLOBAL_EXPLICIT);
if (PySet_Add(global, name) < 0)
return 0;
if (bound && (PySet_Discard(bound, name) < 0))
return 0;
return 1;
}
if (flags & DEF_NONLOCAL) {
if (flags & DEF_PARAM) {
PyErr_Format(PyExc_SyntaxError,
"name '%U' is parameter and nonlocal",
name);
return error_at_directive(ste, name);
}
if (!bound) {
PyErr_Format(PyExc_SyntaxError,
"nonlocal declaration not allowed at module level");
return error_at_directive(ste, name);
}
if (!PySet_Contains(bound, name)) {
PyErr_Format(PyExc_SyntaxError,
"no binding for nonlocal '%U' found",
name);
return error_at_directive(ste, name);
}
SET_SCOPE(scopes, name, FREE);
ste->ste_free = 1;
return PySet_Add(free, name) >= 0;
}
if (flags & DEF_BOUND) {
SET_SCOPE(scopes, name, LOCAL);
if (PySet_Add(local, name) < 0)
return 0;
if (PySet_Discard(global, name) < 0)
return 0;
return 1;
}
/* If an enclosing block has a binding for this name, it
is a free variable rather than a global variable.
Note that having a non-NULL bound implies that the block
is nested.
*/
if (bound && PySet_Contains(bound, name)) {
SET_SCOPE(scopes, name, FREE);
ste->ste_free = 1;
return PySet_Add(free, name) >= 0;
}
/* If a parent has a global statement, then call it global
explicit? It could also be global implicit.
*/
if (global && PySet_Contains(global, name)) {
SET_SCOPE(scopes, name, GLOBAL_IMPLICIT);
return 1;
}
if (ste->ste_nested)
ste->ste_free = 1;
SET_SCOPE(scopes, name, GLOBAL_IMPLICIT);
return 1;
}
#undef SET_SCOPE
/* If a name is defined in free and also in locals, then this block
provides the binding for the free variable. The name should be
marked CELL in this block and removed from the free list.
Note that the current block's free variables are included in free.
That's safe because no name can be free and local in the same scope.
*/
static int
analyze_cells(PyObject *scopes, PyObject *free)
{
PyObject *name, *v, *v_cell;
int success = 0;
Py_ssize_t pos = 0;
v_cell = PyLong_FromLong(CELL);
if (!v_cell)
return 0;
while (PyDict_Next(scopes, &pos, &name, &v)) {
long scope;
assert(PyLong_Check(v));
scope = PyLong_AS_LONG(v);
if (scope != LOCAL)
continue;
if (!PySet_Contains(free, name))
continue;
/* Replace LOCAL with CELL for this name, and remove
from free. It is safe to replace the value of name
in the dict, because it will not cause a resize.
*/
if (PyDict_SetItem(scopes, name, v_cell) < 0)
goto error;
if (PySet_Discard(free, name) < 0)
goto error;
}
success = 1;
error:
Py_DECREF(v_cell);
return success;
}
static int
drop_class_free(PySTEntryObject *ste, PyObject *free)
{
int res;
if (!GET_IDENTIFIER(__class__))
return 0;
res = PySet_Discard(free, __class__);
if (res < 0)
return 0;
if (res)
ste->ste_needs_class_closure = 1;
return 1;
}
/* Enter the final scope information into the ste_symbols dict.
*
* All arguments are dicts. Modifies symbols, others are read-only.
*/
static int
update_symbols(PyObject *symbols, PyObject *scopes,
PyObject *bound, PyObject *free, int classflag)
{
PyObject *name = NULL, *itr = NULL;
PyObject *v = NULL, *v_scope = NULL, *v_new = NULL, *v_free = NULL;
Py_ssize_t pos = 0;
/* Update scope information for all symbols in this scope */
while (PyDict_Next(symbols, &pos, &name, &v)) {
long scope, flags;
assert(PyLong_Check(v));
flags = PyLong_AS_LONG(v);
v_scope = PyDict_GetItem(scopes, name);
assert(v_scope && PyLong_Check(v_scope));
scope = PyLong_AS_LONG(v_scope);
flags |= (scope