view mercurial/base85.c @ 31793:69d8fcf20014

help: document bundle specifications

I softly formalized the concept of a "bundle specification" a while
ago when I was working on clone bundles and stream clone bundles and
wanted a more robust way to define what exactly is in a bundle file.

The concept has existed for a while. Since it is part of the clone
bundles feature and exposed to the user via the "-t" argument to
`hg bundle`, it is something we need to support for the long haul.

After the 4.1 release, I heard a few people comment that they didn't
realize you could generate zstd bundles with `hg bundle`. I'm
partially to blame for not documenting it in bundle's docstring.

Additionally, I added a hacky, experimental feature for controlling
the compression level of bundles in 76104a4899ad. As the commit
message says, I went with a quick and dirty solution out of time
constraints. Furthermore, I wanted to eventually store this
configuration in the "bundlespec" so it could be made more flexible.

Given:

a) bundlespecs are here to stay
b) we don't have great documentation over what they are, despite being
   a user-facing feature
c) the list of available compression engines and their behavior isn't
   exposed
d) we need an extensible place to modify behavior of compression
   engines

I want to move forward with formalizing bundlespecs as a user-facing
feature. This commit does that by introducing a "bundlespec" help
page. Leaning on the just-added compression engine documentation
and API, the topic also conveniently lists available compression
engines and details about them. This makes features like zstd
bundle compression more discoverable. e.g. you can now
`hg help -k zstd` and it lists the "bundlespec" topic.

/*
 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}
};

#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