view mercurial/base85.c @ 25761:0d37b9b21467

hg: support for auto sharing stores when cloning

Many 3rd party consumers of Mercurial have created wrappers to
essentially perform clone+share as a single operation. This is
especially popular in automated processes like continuous integration
systems. The Jenkins CI software and Mozilla's Firefox release
automation infrastructure have both implemented custom code that
effectively perform clone+share. The common use case here is that
clients want to obtain N>1 checkouts while minimizing disk space and
network requirements. Furthermore, they often don't care that a clone
is an exact mirror of a remote: they are simply looking to obtain
checkouts of specific revisions.

When multiple third parties implement a similar feature, it's a good
sign that the feature is worth adding to the core product. This patch
adds support for an easy-to-use clone+share feature.

The internal "clone" function now accepts options to control auto
sharing during clone. When the auto share mode is active, a store will
be created/updated under the base directory specified and a new
repository pointing to the shared store will be created at the path
specified by the user.

The share extension has grown the ability to pass these options into
the clone command/function.

No command line options for this feature are added because we don't
feel the feature will be popular enough to warrant their existence.

There are two modes for auto share mode. In the default mode, the shared
repo is derived from the first changeset (rev 0) in the remote
repository. This enables related repositories existing at different URLs
to automatically use the same storage. In environments that operate
several repositories (separate repo for branch/head/bookmark or separate
repo per user), this has the potential to drastically reduce storage
and network requirements. In the other mode, the name is derived from the
remote's path/URL.

/*
 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
*/

#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