📄 marshal.c
字号:
/* Portions Copyright (c) 2005 Nokia Corporation */
/* Write Python objects to files and read them back.
This is intended for writing and reading compiled Python code only;
a true persistent storage facility would be much harder, since
it would have to take circular links and sharing into account. */
#include "Python.h"
#include "longintrepr.h"
#include "compile.h"
#include "marshal.h"
/* High water mark to determine when the marshalled object is dangerously deep
* and risks coring the interpreter. When the object stack gets this deep,
* raise an exception instead of continuing.
*/
#define MAX_MARSHAL_STACK_DEPTH 5000
#define TYPE_NULL '0'
#define TYPE_NONE 'N'
#define TYPE_STOPITER 'S'
#define TYPE_ELLIPSIS '.'
#define TYPE_INT 'i'
#define TYPE_INT64 'I'
#define TYPE_FLOAT 'f'
#define TYPE_COMPLEX 'x'
#define TYPE_LONG 'l'
#define TYPE_STRING 's'
#define TYPE_TUPLE '('
#define TYPE_LIST '['
#define TYPE_DICT '{'
#define TYPE_CODE 'c'
#define TYPE_UNICODE 'u'
#define TYPE_UNKNOWN '?'
typedef struct {
FILE *fp;
int error;
int depth;
/* If fp == NULL, the following are valid: */
PyObject *str;
char *ptr;
char *end;
} WFILE;
#define w_byte(c, p) if (((p)->fp)) putc((c), (p)->fp); \
else if ((p)->ptr != (p)->end) *(p)->ptr++ = (c); \
else w_more(c, p)
static void
w_more(int c, WFILE *p)
{
int size, newsize;
if (p->str == NULL)
return; /* An error already occurred */
size = PyString_Size(p->str);
newsize = size + 1024;
if (_PyString_Resize(&p->str, newsize) != 0) {
p->ptr = p->end = NULL;
}
else {
p->ptr = PyString_AS_STRING((PyStringObject *)p->str) + size;
p->end =
PyString_AS_STRING((PyStringObject *)p->str) + newsize;
*p->ptr++ = Py_SAFE_DOWNCAST(c, int, char);
}
}
static void
w_string(char *s, int n, WFILE *p)
{
if (p->fp != NULL) {
fwrite(s, 1, n, p->fp);
}
else {
while (--n >= 0) {
w_byte(*s, p);
s++;
}
}
}
static void
w_short(int x, WFILE *p)
{
w_byte((char)( x & 0xff), p);
w_byte((char)((x>> 8) & 0xff), p);
}
static void
w_long(long x, WFILE *p)
{
w_byte((char)( x & 0xff), p);
w_byte((char)((x>> 8) & 0xff), p);
w_byte((char)((x>>16) & 0xff), p);
w_byte((char)((x>>24) & 0xff), p);
}
#if SIZEOF_LONG > 4
static void
w_long64(long x, WFILE *p)
{
w_long(x, p);
w_long(x>>32, p);
}
#endif
static void
w_object(PyObject *v, WFILE *p)
{
int i, n;
p->depth++;
if (p->depth > MAX_MARSHAL_STACK_DEPTH) {
p->error = 2;
}
else if (v == NULL) {
w_byte(TYPE_NULL, 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);
}
else if (PyInt_Check(v)) {
long x = PyInt_AS_LONG((PyIntObject *)v);
#if SIZEOF_LONG > 4
long y = Py_ARITHMETIC_RIGHT_SHIFT(long, x, 31);
if (y && y != -1) {
w_byte(TYPE_INT64, p);
w_long64(x, p);
}
else
#endif
{
w_byte(TYPE_INT, p);
w_long(x, p);
}
}
else if (PyLong_Check(v)) {
PyLongObject *ob = (PyLongObject *)v;
w_byte(TYPE_LONG, p);
n = ob->ob_size;
w_long((long)n, p);
if (n < 0)
n = -n;
for (i = 0; i < n; i++)
w_short(ob->ob_digit[i], p);
}
else if (PyFloat_Check(v)) {
char buf[256]; /* Plenty to format any double */
PyFloat_AsReprString(buf, (PyFloatObject *)v);
n = strlen(buf);
w_byte(TYPE_FLOAT, p);
w_byte(n, p);
w_string(buf, n, p);
}
#ifndef WITHOUT_COMPLEX
else if (PyComplex_Check(v)) {
char buf[256]; /* Plenty to format any double */
PyFloatObject *temp;
w_byte(TYPE_COMPLEX, p);
temp = (PyFloatObject*)PyFloat_FromDouble(
PyComplex_RealAsDouble(v));
PyFloat_AsReprString(buf, temp);
Py_DECREF(temp);
n = strlen(buf);
w_byte(n, p);
w_string(buf, n, p);
temp = (PyFloatObject*)PyFloat_FromDouble(
PyComplex_ImagAsDouble(v));
PyFloat_AsReprString(buf, temp);
Py_DECREF(temp);
n = strlen(buf);
w_byte(n, p);
w_string(buf, n, p);
}
#endif
else if (PyString_Check(v)) {
w_byte(TYPE_STRING, p);
n = PyString_GET_SIZE(v);
w_long((long)n, p);
w_string(PyString_AS_STRING(v), n, p);
}
#ifdef Py_USING_UNICODE
else if (PyUnicode_Check(v)) {
PyObject *utf8;
utf8 = PyUnicode_AsUTF8String(v);
if (utf8 == NULL) {
p->depth--;
p->error = 1;
return;
}
w_byte(TYPE_UNICODE, p);
n = PyString_GET_SIZE(utf8);
w_long((long)n, p);
w_string(PyString_AS_STRING(utf8), n, p);
Py_DECREF(utf8);
}
#endif
else if (PyTuple_Check(v)) {
w_byte(TYPE_TUPLE, p);
n = PyTuple_Size(v);
w_long((long)n, p);
for (i = 0; i < n; i++) {
w_object(PyTuple_GET_ITEM(v, i), p);
}
}
else if (PyList_Check(v)) {
w_byte(TYPE_LIST, p);
n = PyList_GET_SIZE(v);
w_long((long)n, p);
for (i = 0; i < n; i++) {
w_object(PyList_GET_ITEM(v, i), p);
}
}
else if (PyDict_Check(v)) {
int pos;
PyObject *key, *value;
w_byte(TYPE_DICT, p);
/* This one is NULL object terminated! */
pos = 0;
while (PyDict_Next(v, &pos, &key, &value)) {
w_object(key, p);
w_object(value, p);
}
w_object((PyObject *)NULL, p);
}
else if (PyCode_Check(v)) {
PyCodeObject *co = (PyCodeObject *)v;
w_byte(TYPE_CODE, p);
w_short(co->co_argcount, p);
w_short(co->co_nlocals, p);
w_short(co->co_stacksize, p);
w_short(co->co_flags, p);
w_object(co->co_code, p);
w_object(co->co_consts, p);
w_object(co->co_names, p);
w_object(co->co_varnames, p);
w_object(co->co_freevars, p);
w_object(co->co_cellvars, p);
w_object(co->co_filename, p);
w_object(co->co_name, p);
w_short(co->co_firstlineno, p);
w_object(co->co_lnotab, p);
}
else if (PyObject_CheckReadBuffer(v)) {
/* Write unknown buffer-style objects as a string */
char *s;
// XXX:CW32
PyBufferProcs *pb = (PyBufferProcs *)v->ob_type->tp_as_buffer;
w_byte(TYPE_STRING, p);
n = (*pb->bf_getreadbuffer)(v, 0, (void **)&s);
w_long((long)n, p);
w_string(s, n, p);
}
else {
w_byte(TYPE_UNKNOWN, p);
p->error = 1;
}
p->depth--;
}
DL_EXPORT(void)
PyMarshal_WriteLongToFile(long x, FILE *fp)
{
WFILE wf;
wf.fp = fp;
wf.error = 0;
wf.depth = 0;
w_long(x, &wf);
}
DL_EXPORT(void)
PyMarshal_WriteObjectToFile(PyObject *x, FILE *fp)
{
WFILE wf;
wf.fp = fp;
wf.error = 0;
wf.depth = 0;
w_object(x, &wf);
}
typedef WFILE RFILE; /* Same struct with different invariants */
#define rs_byte(p) (((p)->ptr != (p)->end) ? (unsigned char)*(p)->ptr++ : EOF)
#define r_byte(p) ((p)->fp ? getc((p)->fp) : rs_byte(p))
static int
r_string(char *s, int n, RFILE *p)
{
if (p->fp != NULL)
return fread(s, 1, n, p->fp);
if (p->end - p->ptr < n)
n = p->end - p->ptr;
memcpy(s, p->ptr, n);
p->ptr += n;
return n;
}
static int
r_short(RFILE *p)
{
register short x;
x = r_byte(p);
x |= r_byte(p) << 8;
/* Sign-extension, in case short greater than 16 bits */
x |= -(x & 0x8000);
return x;
}
static long
r_long(RFILE *p)
{
register long x;
register FILE *fp = p->fp;
if (fp) {
x = getc(fp);
x |= (long)getc(fp) << 8;
x |= (long)getc(fp) << 16;
x |= (long)getc(fp) << 24;
}
else {
x = rs_byte(p);
x |= (long)rs_byte(p) << 8;
x |= (long)rs_byte(p) << 16;
x |= (long)rs_byte(p) << 24;
}
#if SIZEOF_LONG > 4
/* Sign extension for 64-bit machines */
x |= -(x & 0x80000000L);
#endif
return x;
}
/* r_long64 deals with the TYPE_INT64 code. On a machine with
sizeof(long) > 4, it returns a Python int object, else a Python long
object. Note that w_long64 writes out TYPE_INT if 32 bits is enough,
so there's no inefficiency here in returning a PyLong on 32-bit boxes
for everything written via TYPE_INT64 (i.e., if an int is written via
TYPE_INT64, it *needs* more than 32 bits).
*/
static PyObject *
r_long64(RFILE *p)
{
long lo4 = r_long(p);
long hi4 = r_long(p);
#if SIZEOF_LONG > 4
long x = (hi4 << 32) | (lo4 & 0xFFFFFFFFL);
return PyInt_FromLong(x);
#else
unsigned char buf[8];
int one = 1;
int is_little_endian = (int)*(char*)&one;
if (is_little_endian) {
memcpy(buf, &lo4, 4);
memcpy(buf+4, &hi4, 4);
}
else {
memcpy(buf, &hi4, 4);
memcpy(buf+4, &lo4, 4);
}
return _PyLong_FromByteArray(buf, 8, is_little_endian, 1);
#endif
}
static PyObject *
r_object(RFILE *p)
{
PyObject *v, *v2;
long i, n;
int type = r_byte(p);
switch (type) {
case EOF:
PyErr_SetString(PyExc_EOFError,
"EOF read where object expected");
return NULL;
case TYPE_NULL:
return NULL;
case TYPE_NONE:
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;
case TYPE_INT:
return PyInt_FromLong(r_long(p));
case TYPE_INT64:
return r_long64(p);
case TYPE_LONG:
{
int size;
PyLongObject *ob;
n = r_long(p);
size = n<0 ? -n : n;
ob = _PyLong_New(size);
if (ob == NULL)
return NULL;
ob->ob_size = n;
for (i = 0; i < size; i++)
ob->ob_digit[i] = r_short(p);
return (PyObject *)ob;
}
case TYPE_FLOAT:
{
char buf[256];
double dx;
n = r_byte(p);
if (r_string(buf, (int)n, p) != n) {
PyErr_SetString(PyExc_EOFError,
"EOF read where object expected");
return NULL;
}
buf[n] = '\0';
PyFPE_START_PROTECT("atof", return 0)
dx = atof(buf);
PyFPE_END_PROTECT(dx)
⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -