view mercurial/base85.c @ 5195:33015dac5df5

convert: fix mercurial_sink.putcommit

Changeset 4ebc8693ce72 added some code to putcommit to avoid creating a
revision that touches no files, but this can break regular conversions
from some repositories:

- conceptually, since we're converting a repo, we should try to make
  the new hg repo as similar as possible to the original repo - we
  should create a new changeset, even if the original revision didn't
  touch any files (maybe the commit message had some important bit);

- even if a "regular" revision that doesn't touch any file may seem
  weird (and maybe even broken), it's completely legitimate for a merge
  revision to not touch any file, and, if we just skip it, the
  converted repo will end up with wrong history and possibly an extra
  head.

  As an example, say the crew and main hg repos are sync'ed.  Somebody
  sends an important patch to the mailing list.  Matt quickly applies
  and pushes it.  But at the same time somebody also applies it to crew
  and pushes it.  Suppose the commit message ended up being a bit
  different (say, there was a typo and somebody didn't fix it) or that
  the date ended up being different (because of different patch-applying
  scripts): the changeset hashes will be different, but the manifests
  will be the same.

  Since both changesets were pushed to public repos, it's hard to recall
  them.  If both are merged, the manifest from the resulting merge
  revision will have the exact same contents as its parents - i.e. the
  merge revision really doesn't touch any file at all.

To keep the file filtering stuff "working", the generic code was changed
to skip empty revisions if we're filtering the repo, fixing a bug in the
process (we want parents[0] instead of tip).

/*
 base85 codec

 Copyright 2006 Brendan Cully <[e-mail]>

 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();
}