compile.c

python s60 1.4.5版本的源代码

/* Portions Copyright (c) 2005 Nokia Corporation */
/* Compile an expression node to intermediate code */

/* XXX TO DO:
   XXX add __doc__ attribute == co_doc to code object attributes?
   XXX   (it's currently the first item of the co_const tuple)
   XXX Generate simple jump for break/return outside 'try...finally'
   XXX Allow 'continue' inside finally clause of try-finally
   XXX New opcode for loading the initial index for a for loop
   XXX other JAR tricks?
*/

#include "Python.h"

#include "node.h"
#include "token.h"
#include "graminit.h"
#include "compile.h"
#include "symtable.h"
#include "opcode.h"
#include "structmember.h"

#include <ctype.h>

/* Three symbols from graminit.h are also defined in Python.h, with
   Py_ prefixes to their names.  Python.h can't include graminit.h
   (which defines too many confusing symbols), but we can check here
   that they haven't changed (which is very unlikely, but possible). */
#if Py_single_input != single_input
  #error "single_input has changed -- update Py_single_input in Python.h"
#endif
#if Py_file_input != file_input
  #error "file_input has changed -- update Py_file_input in Python.h"
#endif
#if Py_eval_input != eval_input
  #error "eval_input has changed -- update Py_eval_input in Python.h"
#endif

#ifndef SYMBIAN
int Py_OptimizeFlag = 0;
#endif

#define OP_DELETE 0
#define OP_ASSIGN 1
#define OP_APPLY 2

#define VAR_LOAD 0
#define VAR_STORE 1
#define VAR_DELETE 2

#define DEL_CLOSURE_ERROR \
"can not delete variable '%.400s' referenced in nested scope"

#define DUPLICATE_ARGUMENT \
"duplicate argument '%s' in function definition"

#define ILLEGAL_DYNAMIC_SCOPE \
"%.100s: exec or 'import *' makes names ambiguous in nested scope"

#define GLOBAL_AFTER_ASSIGN \
"name '%.400s' is assigned to before global declaration"

#define GLOBAL_AFTER_USE \
"name '%.400s' is used prior to global declaration"

#define LOCAL_GLOBAL \
"name '%.400s' is a function parameter and declared global"

#define LATE_FUTURE \
"from __future__ imports must occur at the beginning of the file"

#define ASSIGN_DEBUG \
"can not assign to __debug__"

#define MANGLE_LEN 256

#define OFF(x) offsetof(PyCodeObject, x)

const static PyMemberDef code_memberlist[] = {
	{"co_argcount",	T_INT,		OFF(co_argcount),	READONLY},
	{"co_nlocals",	T_INT,		OFF(co_nlocals),	READONLY},
	{"co_stacksize",T_INT,		OFF(co_stacksize),	READONLY},
	{"co_flags",	T_INT,		OFF(co_flags),		READONLY},
	{"co_code",	T_OBJECT,	OFF(co_code),		READONLY},
	{"co_consts",	T_OBJECT,	OFF(co_consts),		READONLY},
	{"co_names",	T_OBJECT,	OFF(co_names),		READONLY},
	{"co_varnames",	T_OBJECT,	OFF(co_varnames),	READONLY},
	{"co_freevars",	T_OBJECT,	OFF(co_freevars),	READONLY},
	{"co_cellvars",	T_OBJECT,	OFF(co_cellvars),	READONLY},
	{"co_filename",	T_OBJECT,	OFF(co_filename),	READONLY},
	{"co_name",	T_OBJECT,	OFF(co_name),		READONLY},
	{"co_firstlineno", T_INT,	OFF(co_firstlineno),	READONLY},
	{"co_lnotab",	T_OBJECT,	OFF(co_lnotab),		READONLY},
	{NULL}	/* Sentinel */
};

static void
code_dealloc(PyCodeObject *co)
{
	Py_XDECREF(co->co_code);
	Py_XDECREF(co->co_consts);
	Py_XDECREF(co->co_names);
	Py_XDECREF(co->co_varnames);
	Py_XDECREF(co->co_freevars);
	Py_XDECREF(co->co_cellvars);
	Py_XDECREF(co->co_filename);
	Py_XDECREF(co->co_name);
	Py_XDECREF(co->co_lnotab);
	PyObject_DEL(co);
}

static PyObject *
code_repr(PyCodeObject *co)
{
	char buf[500];
	int lineno = -1;
	char *filename = "???";
	char *name = "???";

	if (co->co_firstlineno != 0)
		lineno = co->co_firstlineno;
	if (co->co_filename && PyString_Check(co->co_filename))
		filename = PyString_AS_STRING(co->co_filename);
	if (co->co_name && PyString_Check(co->co_name))
		name = PyString_AS_STRING(co->co_name);
	PyOS_snprintf(buf, sizeof(buf),
		      "<code object %.100s at %p, file \"%.300s\", line %d>",
		      name, co, filename, lineno);
	return PyString_FromString(buf);
}

static int
code_compare(PyCodeObject *co, PyCodeObject *cp)
{
	int cmp;
	cmp = PyObject_Compare(co->co_name, cp->co_name);
	if (cmp) return cmp;
	cmp = co->co_argcount - cp->co_argcount;
	if (cmp) return (cmp<0)?-1:1;
	cmp = co->co_nlocals - cp->co_nlocals;
	if (cmp) return (cmp<0)?-1:1;
	cmp = co->co_flags - cp->co_flags;
	if (cmp) return (cmp<0)?-1:1;
	cmp = PyObject_Compare(co->co_code, cp->co_code);
	if (cmp) return cmp;
	cmp = PyObject_Compare(co->co_consts, cp->co_consts);
	if (cmp) return cmp;
	cmp = PyObject_Compare(co->co_names, cp->co_names);
	if (cmp) return cmp;
	cmp = PyObject_Compare(co->co_varnames, cp->co_varnames);
	if (cmp) return cmp;
	cmp = PyObject_Compare(co->co_freevars, cp->co_freevars);
	if (cmp) return cmp;
	cmp = PyObject_Compare(co->co_cellvars, cp->co_cellvars);
	return cmp;
}

static long
code_hash(PyCodeObject *co)
{
	long h, h0, h1, h2, h3, h4, h5, h6;
	h0 = PyObject_Hash(co->co_name);
	if (h0 == -1) return -1;
	h1 = PyObject_Hash(co->co_code);
	if (h1 == -1) return -1;
	h2 = PyObject_Hash(co->co_consts);
	if (h2 == -1) return -1;
	h3 = PyObject_Hash(co->co_names);
	if (h3 == -1) return -1;
	h4 = PyObject_Hash(co->co_varnames);
	if (h4 == -1) return -1;
	h5 = PyObject_Hash(co->co_freevars);
	if (h5 == -1) return -1;
	h6 = PyObject_Hash(co->co_cellvars);
	if (h6 == -1) return -1;
	h = h0 ^ h1 ^ h2 ^ h3 ^ h4 ^ h5 ^ h6 ^
		co->co_argcount ^ co->co_nlocals ^ co->co_flags;
	if (h == -1) h = -2;
	return h;
}

/* XXX code objects need to participate in GC? */

const PyTypeObject c_PyCode_Type = {
	PyObject_HEAD_INIT(NULL)
	0,
	"code",
	sizeof(PyCodeObject),
	0,
	(destructor)code_dealloc, 	/* tp_dealloc */
	0,				/* tp_print */
	0, 				/* tp_getattr */
	0,				/* tp_setattr */
	(cmpfunc)code_compare, 		/* tp_compare */
	(reprfunc)code_repr,		/* tp_repr */
	0,				/* tp_as_number */
	0,				/* tp_as_sequence */
	0,				/* tp_as_mapping */
	(hashfunc)code_hash, 		/* 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 */
	code_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 */
};

#define NAME_CHARS \
	"0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ_abcdefghijklmnopqrstuvwxyz"

/* all_name_chars(s): true iff all chars in s are valid NAME_CHARS */

static int
all_name_chars(unsigned char *s)
{
#ifndef SYMBIAN
 	static char ok_name_char[256];
#else
#define ok_name_char (PYTHON_GLOBALS->ok_name_char)
#endif
	static const unsigned char *const name_chars = (unsigned char *)NAME_CHARS;

	if (ok_name_char[*name_chars] == 0) {
		unsigned char *p;
		// XXX:CW32
		for (p = (unsigned char *)name_chars; *p; p++)
			ok_name_char[*p] = 1;
	}
	while (*s) {
		if (ok_name_char[*s++] == 0)
			return 0;
	}
	return 1;
}

static int
intern_strings(PyObject *tuple)
{
	int i;

	for (i = PyTuple_GET_SIZE(tuple); --i >= 0; ) {
		PyObject *v = PyTuple_GET_ITEM(tuple, i);
		if (v == NULL || !PyString_Check(v)) {
			Py_FatalError("non-string found in code slot");
			PyErr_BadInternalCall();
			return -1;
		}
		PyString_InternInPlace(&PyTuple_GET_ITEM(tuple, i));
	}
	return 0;
}

DL_EXPORT(PyCodeObject *)
PyCode_New(int argcount, int nlocals, int stacksize, int flags,
	   PyObject *code, PyObject *consts, PyObject *names,
	   PyObject *varnames, PyObject *freevars, PyObject *cellvars,
	   PyObject *filename, PyObject *name, int firstlineno,
	   PyObject *lnotab)
{
	PyCodeObject *co;
	int i;
	/* Check argument types */
	if (argcount < 0 || nlocals < 0 ||
	    code == NULL ||
	    consts == NULL || !PyTuple_Check(consts) ||
	    names == NULL || !PyTuple_Check(names) ||
	    varnames == NULL || !PyTuple_Check(varnames) ||
	    freevars == NULL || !PyTuple_Check(freevars) ||
	    cellvars == NULL || !PyTuple_Check(cellvars) ||
	    name == NULL || !PyString_Check(name) ||
	    filename == NULL || !PyString_Check(filename) ||
	    lnotab == NULL || !PyString_Check(lnotab) ||
	    !PyObject_CheckReadBuffer(code)) {
		PyErr_BadInternalCall();
		return NULL;
	}
	intern_strings(names);
	intern_strings(varnames);
	if (freevars == NULL)
		freevars = PyTuple_New(0);
	intern_strings(freevars);
	if (cellvars == NULL)
		cellvars = PyTuple_New(0);
	intern_strings(cellvars);
	/* Intern selected string constants */
	for (i = PyTuple_Size(consts); --i >= 0; ) {
		PyObject *v = PyTuple_GetItem(consts, i);
		if (!PyString_Check(v))
			continue;
		if (!all_name_chars((unsigned char *)PyString_AS_STRING(v)))
			continue;
		PyString_InternInPlace(&PyTuple_GET_ITEM(consts, i));
	}
	co = PyObject_NEW(PyCodeObject, &PyCode_Type);
	if (co != NULL) {
		co->co_argcount = argcount;
		co->co_nlocals = nlocals;
		co->co_stacksize = stacksize;
		co->co_flags = flags;
		Py_INCREF(code);
		co->co_code = code;
		Py_INCREF(consts);
		co->co_consts = consts;
		Py_INCREF(names);
		co->co_names = names;
		Py_INCREF(varnames);
		co->co_varnames = varnames;
		Py_INCREF(freevars);
		co->co_freevars = freevars;
		Py_INCREF(cellvars);
		co->co_cellvars = cellvars;
		Py_INCREF(filename);
		co->co_filename = filename;
		Py_INCREF(name);
		co->co_name = name;
		co->co_firstlineno = firstlineno;
		Py_INCREF(lnotab);
		co->co_lnotab = lnotab;
	}
	return co;
}


/* Data structure used internally */

/* The compiler uses two passes to generate bytecodes.  The first pass
   builds the symbol table.  The second pass generates the bytecode.

   The first pass uses a single symtable struct.  The second pass uses
   a compiling struct for each code block.  The compiling structs
   share a reference to the symtable.

   The two passes communicate via symtable_load_symbols() and via
   is_local() and is_global().  The former initializes several slots
   in the compiling struct: c_varnames, c_locals, c_nlocals,
   c_argcount, c_globals, and c_flags.
*/

/* All about c_lnotab.

c_lnotab is an array of unsigned bytes disguised as a Python string.  In -O
mode, SET_LINENO opcodes aren't generated, and bytecode offsets are mapped
to source code line #s (when needed for tracebacks) via c_lnotab instead.
The array is conceptually a list of
    (bytecode offset increment, line number increment)
pairs.  The details are important and delicate, best illustrated by example:

    byte code offset    source code line number
        0		    1
        6		    2
       50		    7
      350                 307
      361                 308

The first trick is that these numbers aren't stored, only the increments
from one row to the next (this doesn't really work, but it's a start):

    0, 1,  6, 1,  44, 5,  300, 300,  11, 1

The second trick is that an unsigned byte can't hold negative values, or
values larger than 255, so (a) there's a deep assumption that byte code
offsets and their corresponding line #s both increase monotonically, and (b)
if at least one column jumps by more than 255 from one row to the next, more
than one pair is written to the table. In case #b, there's no way to know
from looking at the table later how many were written.  That's the delicate
part.  A user of c_lnotab desiring to find the source line number
corresponding to a bytecode address A should do something like this

    lineno = addr = 0
    for addr_incr, line_incr in c_lnotab:
        addr += addr_incr
        if addr > A:
            return lineno
        lineno += line_incr

In order for this to work, when the addr field increments by more than 255,
the line # increment in each pair generated must be 0 until the remaining addr
increment is < 256.  So, in the example above, com_set_lineno should not (as
was actually done until 2.2) expand 300, 300 to 255, 255,  45, 45, but to
255, 0,  45, 255,  0, 45.
*/

struct compiling {
	PyObject *c_code;	/* string */
	PyObject *c_consts;	/* list of objects */
	PyObject *c_const_dict; /* inverse of c_consts */
	PyObject *c_names;	/* list of strings (names) */
	PyObject *c_name_dict;  /* inverse of c_names */
	PyObject *c_globals;	/* dictionary (value=None) */
	PyObject *c_locals;	/* dictionary (value=localID) */
	PyObject *c_varnames;	/* list (inverse of c_locals) */
	PyObject *c_freevars;	/* dictionary (value=None) */
	PyObject *c_cellvars;	/* list */
	int c_nlocals;		/* index of next local */
	int c_argcount;		/* number of top-level arguments */
	int c_flags;		/* same as co_flags */
	int c_nexti;		/* index into c_code */
	int c_errors;		/* counts errors occurred */
	int c_infunction;	/* set when compiling a function */
	int c_interactive;	/* generating code for interactive command */
	int c_loops;		/* counts nested loops */
	int c_begin;		/* begin of current loop, for 'continue' */
	int c_block[CO_MAXBLOCKS]; /* stack of block types */
	int c_nblocks;		/* current block stack level */
	char *c_filename;	/* filename of current node */
	char *c_name;		/* name of object (e.g. function) */
	int c_lineno;		/* Current line number */
	int c_stacklevel;	/* Current stack level */
	int c_maxstacklevel;	/* Maximum stack level */
	int c_firstlineno;
	PyObject *c_lnotab;	/* Table mapping address to line number */
	int c_last_addr, c_last_line, c_lnotab_next;
	char *c_private;	/* for private name mangling */
	int c_tmpname;		/* temporary local name counter */
	int c_nested;		/* Is block nested funcdef or lamdef? */
	int c_closure;		/* Is nested w/freevars? */
	struct symtable *c_symtable; /* pointer to module symbol table */
        PyFutureFeatures *c_future; /* pointer to module's __future__ */
};

static int
is_free(int v)
{
	if ((v & (USE | DEF_FREE))
	    && !(v & (DEF_LOCAL | DEF_PARAM | DEF_GLOBAL)))
		return 1;
	if (v & DEF_FREE_CLASS)
		return 1;
	return 0;
}

static void
com_error(struct compiling *c, PyObject *exc, char *msg)
{
	PyObject *t = NULL, *v = NULL, *w = NULL, *line = NULL;

	if (c == NULL) {
		/* Error occurred via symtable call to
		   is_constant_false */
		PyErr_SetString(exc, msg);
		return;
	}
	c->c_errors++;
	if (c->c_lineno < 1 || c->c_interactive) {
		/* Unknown line number or interactive input */
		PyErr_SetString(exc, msg);
		return;
	}
	v = PyString_FromString(msg);
	if (v == NULL)
		return; /* MemoryError, too bad */

	line = PyErr_ProgramText(c->c_filename, c->c_lineno);
	if (line == NULL) {
		Py_INCREF(Py_None);
		line = Py_None;
	}
	if (exc == PyExc_SyntaxError) {
		t = Py_BuildValue("(ziOO)", c->c_filename, c->c_lineno,
				  Py_None, line);
		if (t == NULL)
			goto exit;
		w = Py_BuildValue("(OO)", v, t);
		if (w == NULL)
			goto exit;
		PyErr_SetObject(exc, w);
	} else {
		/* Make sure additional exceptions are printed with
		   file and line, also. */
		PyErr_SetObject(exc, v);
		PyErr_SyntaxLocation(c->c_filename, c->c_lineno);
	}
 exit:
	Py_XDECREF(t);
	Py_XDECREF(v);
	Py_XDECREF(w);
	Py_XDECREF(line);
}

/* Interface to the block stack */

static void
block_push(struct compiling *c, int type)
{
	if (c->c_nblocks >= CO_MAXBLOCKS) {
		com_error(c, PyExc_SystemError,
			  "too many statically nested blocks");
	}
	else {
		c->c_block[c->c_nblocks++] = type;
	}
}

static void
block_pop(struct compiling *c, int type)
{
	if (c->c_nblocks > 0)
		c->c_nblocks--;
	if (c->c_block[c->c_nblocks] != type && c->c_errors == 0) {
		com_error(c, PyExc_SystemError, "bad block pop");
	}
}

/* Prototype forward declarations */

static int com_init(struct compiling *, char *);
static void com_free(struct compiling *);
static void com_push(struct compiling *, int);
static void com_pop(struct compiling *, int);
static void com_done(struct compiling *);
static void com_node(struct compiling *, node *);