view mercurial/cext/base85.c @ 33289:abd7dedbaa36

sparse: vendor Facebook-developed extension

Facebook has developed an extension to enable "sparse" checkouts -
a working directory with a subset of files. This feature is a critical
component in enabling repositories to scale to infinite number of
files while retaining reasonable performance. It's worth noting
that sparse checkout is only one possible solution to this problem:
another is virtual filesystems that realize files on first access.
But given that virtual filesystems may not be accessible to all
users, sparse checkout is necessary as a fallback.

Per mailing list discussion at
https://www.mercurial-scm.org/pipermail/mercurial-devel/2017-March/095868.html
we want to add sparse checkout to the Mercurial distribution via
roughly the following mechanism:

1. Vendor extension as-is with minimal modifications (this patch)
2. Refactor extension so it is more clearly experimental and inline
   with Mercurial practices
3. Move code from extension into core where possible
4. Drop experimental labeling and/or move feature into core
   after sign-off from narrow clone feature owners

This commit essentially copies the sparse extension and tests
from revision 71e0a2aeca92a4078fe1b8c76e32c88ff1929737 of the
https://bitbucket.org/facebook/hg-experimental repository.

A list of modifications made as part of vendoring is as follows:

* "EXPERIMENTAL" added to module docstring
* Imports were changed to match Mercurial style conventions
* "testedwith" value was updated to core Mercurial special value and
  comment boilerplate was inserted
* A "clone_sparse" function was renamed to "clonesparse" to appease
  the style checker
* Paths to the sparse extension in tests reflect built-in location
* test-sparse-extensions.t was renamed to test-sparse-fsmonitor.t
  and references to "simplecache" were removed. The test always skips
  because it isn't trivial to run it given the way we currently run
  fsmonitor tests
* A double empty line was removed from test-sparse-profiles.t

There are aspects of the added code that are obviously not ideal.
The goal is to make a minimal number of modifications as part of
the vendoring to make it easier to track changes from the original
implementation. Refactoring will occur in subsequent patches.

/*
 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)
{
	unsigned 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}
};

static const int version = 1;

#ifdef IS_PY3K
static struct PyModuleDef base85_module = {
	PyModuleDef_HEAD_INIT,
	"base85",
	base85_doc,
	-1,
	methods
};

PyMODINIT_FUNC PyInit_base85(void)
{
	PyObject *m;
	b85prep();

	m = PyModule_Create(&base85_module);
	PyModule_AddIntConstant(m, "version", version);
	return m;
}
#else
PyMODINIT_FUNC initbase85(void)
{
	PyObject *m;
	m = Py_InitModule3("base85", methods, base85_doc);

	b85prep();
	PyModule_AddIntConstant(m, "version", version);
}
#endif