view mercurial/base85.c @ 23845:0a7fd54d4e60

revset: introduce "_parsealiasdecl" to parse alias declarations strictly

This patch introduces "_parsealiasdecl" to parse alias declarations
strictly. For example, "_parsealiasdecl" can detect problems below,
which current implementation can't.

  - un-closed parenthesis causes being treated as "alias symbol"

    because all of declarations not in "func(....)" style are
    recognized as "alias symbol".

    for example, "foo($1, $2" is treated as the alias symbol.

  - alias symbol/function names aren't examined whether they are valid
    as symbol or not

    for example, "foo bar" can be treated as the alias symbol, but of
    course such invalid symbol can't be referred in revset.

  - just splitting argument list by "," causes overlooking syntax
    problems in the declaration

    for example, all of invalid declarations below are overlooked:

    - foo("bar")     => taking one argument named as '"bar"'
    - foo("unclosed) => taking one argument named as '"unclosed'
    - foo(bar::baz)  => taking one argument named as 'bar::baz'
    - foo(bar($1))   => taking one argument named as 'bar($1)'

To decrease complication of patch, current implementation for alias
declarations is replaced by "_parsealiasdecl" in the subsequent
patch. This patch just introduces it.

This patch defines "_parsealiasdecl" not as a method of "revsetalias"
class but as a one of "revset" module, because of ease of testing by
doctest.

This patch factors some helper functions for "tree" out, because:

  - direct accessing like "if tree[0] == 'func' and len(tree) > 1"
    decreases readability

  - subsequent patch (and also existing code paths, in the future) can
    use them for readability

This patch also factors "_tokenizealias" out, because it can be used
also for parsing alias definitions strictly.

/*
 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