##// END OF EJS Templates
vfs: add walk...
vfs: add walk To eliminate "path prefix" (= "the root of vfs") part from "dirpath" yielded by "os.walk()" correctly, "path prefix" should have "os.sep" at the end of own string, but it isn't easy to ensure it, because: - examination by "path.endswith(os.sep)" isn't portable Some problematic encodings use 0x5c (= "os.sep" on Windows) as the tail byte of some multi-byte characters. - "os.path.join(path, '')" isn't portable With Python 2.7.9, this invocation doesn't add "os.sep" at the end of UNC path (see issue4557 for detail). Python 2.7.9 changed also behavior of "os.path.normpath()" (see *) and "os.path.splitdrive()" for UNC path. vfs root normpath splitdrive os.sep required =============== ============== =================== ============ z:\ z:\ z: + \ no z:\foo z:\foo z: + \foo yes z:\foo\ z:\foo z: + \foo yes [before Python 2.7.9] \\foo\bar \\foo\bar '' + \\foo\bar yes \\foo\bar\ \\foo\bar (*) '' + \\foo\bar yes \\foo\bar\baz \\foo\bar\baz '' + \\foo\bar\baz yes \\foo\bar\baz\ \\foo\bar\baz '' + \\foo\bar\baz yes [Python 2.7.9] \\foo\bar \\foo\bar \\foo\bar + '' yes \\foo\bar\ \\foo\bar\ (*) \\foo\bar + \ no \\foo\bar\baz \\foo\bar\baz \\foo\bar + \baz yes \\foo\bar\baz\ \\foo\bar\baz \\foo\bar + \baz yes If it is ensured that "normpath()"-ed vfs root is passed to "splitdrive()", adding "os.sep" is required only when "path" part of "splitdrive()" result isn't "os.sep" itself. This is just what "pathutil.nameasprefix()" examines. This patch applies "os.path.normpath()" on "self.join(None)" explicitly, because it isn't ensured that vfs root is already normalized: vfs itself is constructed with "realpath=False" (= avoid normalizing in "vfs.__init__()") in many code paths. This normalization should be much cheaper than subsequent file I/O for directory traversal.

File last commit:

r16848:19a915d4 default
r24725:ee751d47 default
Show More
base85.c
185 lines | 3.4 KiB | text/x-c | CLexer
/*
base85 codec
Copyright 2006 Brendan Cully <brendan@kublai.com>
This software may be used and distributed according to the terms of
the GNU General Public License, incorporated herein by reference.
Largely based on git's implementation
*/
#define PY_SSIZE_T_CLEAN
#include <Python.h>
#include "util.h"
static const char b85chars[] = "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ"
"abcdefghijklmnopqrstuvwxyz!#$%&()*+-;<=>?@^_`{|}~";
static char b85dec[256];
static void
b85prep(void)
{
int i;
memset(b85dec, 0, sizeof(b85dec));
for (i = 0; i < sizeof(b85chars); i++)
b85dec[(int)(b85chars[i])] = i + 1;
}
static PyObject *
b85encode(PyObject *self, PyObject *args)
{
const unsigned char *text;
PyObject *out;
char *dst;
Py_ssize_t len, olen, i;
unsigned int acc, val, ch;
int pad = 0;
if (!PyArg_ParseTuple(args, "s#|i", &text, &len, &pad))
return NULL;
if (pad)
olen = ((len + 3) / 4 * 5) - 3;
else {
olen = len % 4;
if (olen)
olen++;
olen += len / 4 * 5;
}
if (!(out = PyBytes_FromStringAndSize(NULL, olen + 3)))
return NULL;
dst = PyBytes_AsString(out);
while (len) {
acc = 0;
for (i = 24; i >= 0; i -= 8) {
ch = *text++;
acc |= ch << i;
if (--len == 0)
break;
}
for (i = 4; i >= 0; i--) {
val = acc % 85;
acc /= 85;
dst[i] = b85chars[val];
}
dst += 5;
}
if (!pad)
_PyBytes_Resize(&out, olen);
return out;
}
static PyObject *
b85decode(PyObject *self, PyObject *args)
{
PyObject *out;
const char *text;
char *dst;
Py_ssize_t len, i, j, olen, cap;
int c;
unsigned int acc;
if (!PyArg_ParseTuple(args, "s#", &text, &len))
return NULL;
olen = len / 5 * 4;
i = len % 5;
if (i)
olen += i - 1;
if (!(out = PyBytes_FromStringAndSize(NULL, olen)))
return NULL;
dst = PyBytes_AsString(out);
i = 0;
while (i < len)
{
acc = 0;
cap = len - i - 1;
if (cap > 4)
cap = 4;
for (j = 0; j < cap; i++, j++)
{
c = b85dec[(int)*text++] - 1;
if (c < 0)
return PyErr_Format(
PyExc_ValueError,
"bad base85 character at position %d",
(int)i);
acc = acc * 85 + c;
}
if (i++ < len)
{
c = b85dec[(int)*text++] - 1;
if (c < 0)
return PyErr_Format(
PyExc_ValueError,
"bad base85 character at position %d",
(int)i);
/* overflow detection: 0xffffffff == "|NsC0",
* "|NsC" == 0x03030303 */
if (acc > 0x03030303 || (acc *= 85) > 0xffffffff - c)
return PyErr_Format(
PyExc_ValueError,
"bad base85 sequence at position %d",
(int)i);
acc += c;
}
cap = olen < 4 ? olen : 4;
olen -= cap;
for (j = 0; j < 4 - cap; j++)
acc *= 85;
if (cap && cap < 4)
acc += 0xffffff >> (cap - 1) * 8;
for (j = 0; j < cap; j++)
{
acc = (acc << 8) | (acc >> 24);
*dst++ = acc;
}
}
return out;
}
static char base85_doc[] = "Base85 Data Encoding";
static PyMethodDef methods[] = {
{"b85encode", b85encode, METH_VARARGS,
"Encode text in base85.\n\n"
"If the second parameter is true, pad the result to a multiple of "
"five characters.\n"},
{"b85decode", b85decode, METH_VARARGS, "Decode base85 text.\n"},
{NULL, NULL}
};
#ifdef IS_PY3K
static struct PyModuleDef base85_module = {
PyModuleDef_HEAD_INIT,
"base85",
base85_doc,
-1,
methods
};
PyMODINIT_FUNC PyInit_base85(void)
{
b85prep();
return PyModule_Create(&base85_module);
}
#else
PyMODINIT_FUNC initbase85(void)
{
Py_InitModule3("base85", methods, base85_doc);
b85prep();
}
#endif