view mercurial/base85.c @ 5210:90d9ec0dc69d

merge: forcefully mark files that we get from the second parent as dirty After a hg merge, we want to include in the commit all the files that we got from the second parent, so that we have the correct file-level history. To make them visible to hg commit, we try to mark them as dirty. Unfortunately, right now we can't really mark them as dirty[1] - the best we can do is to mark them as needing a full comparison of their contents, but they will still be considered clean if they happen to be identical to the version in the first parent. This changeset extends the dirstate format in a compatible way, so that we can mark a file as dirty: Right now we use a negative file size to indicate we don't have valid stat data for this entry. In practice, this size is always -1. This patch uses -2 to indicate that the entry is dirty. Older versions of hg won't choke on this dirstate, but they may happily mark the file as clean after a full comparison, destroying all of our hard work. The patch adds a dirstate.normallookup method with the semantics of the current normaldirty, and changes normaldirty to forcefully mark the entry as dirty. This should fix issue522. [1] - well, we could put them in state 'm', but that state has a different meaning.
author Alexis S. L. Carvalho <alexis@cecm.usp.br>
date Thu, 23 Aug 2007 01:48:29 -0300
parents 4bad632913d8
children
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();
}