view mercurial/base85.c @ 5846:02884e56c217

New extension to support problematic MBCS on Windows. The aim of this extension is to clear the problem related to having 0x5c in 2nd byte of encoded bytes. So this extension is usefull for: * Japanese Windows user shift_jis encoding. * Chinese Windows user using big5 encoding. To use this extension, simply enable it without any customization. Note that some important python built-in functions and mercurial functions are altered for this extension to convert argument if need to handle MBCS.
author Shun-ichi GOTO <shunichi.goto@gmail.com>
date Wed, 09 Jan 2008 22:41:30 +0900
parents 4bad632913d8
children aecea6934fdd
line wrap: on
line source

/*
 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
*/

#include <Python.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;
	int 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 = PyString_FromStringAndSize(NULL, olen + 3)))
		return NULL;

	dst = PyString_AS_STRING(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)
                _PyString_Resize(&out, olen);

	return out;
}

static PyObject *
b85decode(PyObject *self, PyObject *args)
{
	PyObject *out;
	const char *text;
	char *dst;
	int len, i, j, olen, c, cap;
	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 = PyString_FromStringAndSize(NULL, olen)))
		return NULL;

	dst = PyString_AS_STRING(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", 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", 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", 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}
};

PyMODINIT_FUNC initbase85(void)
{
	Py_InitModule3("base85", methods, base85_doc);

	b85prep();
}