view mercurial/base85.c @ 25561:50a6c3c55db1 stable

parsers: do not cache RevlogError type (issue4451) Index lookups raise RevlogError when the lookup fails. The previous implementation was caching a reference to the RevlogError type in a static variable. This assumed that the "mercurial.error" module was only loaded once and there was only a single copy of it floating around in memory. Unfortunately, in some situations - including certain mod_wsgi configurations - this was not the case: the "mercurial.error" module could be reloaded. It was possible for a "RevlogError" reference from the first interpreter to be used by a second interpreter. While the underlying thing was a "mercurial.error.RevlogError," the object IDs were different, so the Python code in revlog.py was failing to catch the exception! This error has existed since the C index lookup code was implemented in changeset e8d37b78acfb, which was first released in Mercurial 2.2 in 2012. http://emptysqua.re/blog/python-c-extensions-and-mod-wsgi/#static-variables-are-shared contains more details. This patch removes the caching of the RevlogError type from the function. Since pretty much the entire function was refactored and the return value of the function wasn't used, I changed the function signature to not return anything. For reasons unknown to me, we were calling PyErr_SetObject() with the type of RevlogError and an instance of RevlogError. This was equivalent to the Python code "raise RevlogError(RevlogError)". This seemed wonky and completely unnecessary. The Python code only cares about the type of the exception, not its contents. So I got rid of this complexity. This is my first Python C extension patch. Please give extra scrutiny to it during review.
author Gregory Szorc <gregory.szorc@gmail.com>
date Fri, 12 Jun 2015 14:43:59 -0700
parents 19a915d43a68
children c1aefe57cf4e
line wrap: on
line source

/*
 base85 codec

 Copyright 2006 Brendan Cully <brendan@kublai.com>

 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