view mercurial/cext/base85.c @ 42377:0546ead39a7e stable

manifest: avoid corruption by dropping removed files with pure (issue5801)

Previously, removed files would simply be marked by overwriting the first byte
with NUL and dropping their entry in `self.position`.  But no effort was made to
ignore them when compacting the dictionary into text form.  This allowed them to
slip into the manifest revision, since the code seems to be trying to minimize
the string operations by copying as large a chunk as possible.  As part of this,
compact() walks the existing text based on entries in the `positions` list, and
consumed everything up to the next position entry.   This typically resulted in
a ValueError complaining about unsorted manifest entries.

Sometimes it seems that files do get dropped in large repos- it seems to
correspond to there being a new entry that would take the same slot.  A much
more trivial problem is that if the only changes were removals, `_compact()`
didn't even run because `__delitem__` doesn't add anything to `self.extradata`.
Now there's an explicit variable to flag this, both to allow `_compact()` to
run, and to avoid searching the manifest in cases where there are no removals.

In practice, this behavior was mostly obscured by the check in fastdelta() which
takes a different path that explicitly drops removed files if there are fewer
than 1000 changes.  However, timeless has a repo where after rebasing tens of
commits, a totally different path[1] is taken that bypasses the change count
check and hits this problem.

[1] https://www.mercurial-scm.org/repo/hg/file/2338bdea4474/mercurial/manifest.py#l1511

/*
 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, PY23("s#|i", "y#|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 = NULL;
	const char *text;
	char *dst;
	Py_ssize_t len, i, j, olen, cap;
	int c;
	unsigned int acc;

	if (!PyArg_ParseTuple(args, PY23("s#", "y#"), &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) {
				PyErr_Format(
				    PyExc_ValueError,
				    "bad base85 character at position %d",
				    (int)i);
				goto bail;
			}
			acc = acc * 85 + c;
		}
		if (i++ < len) {
			c = b85dec[(int)*text++] - 1;
			if (c < 0) {
				PyErr_Format(
				    PyExc_ValueError,
				    "bad base85 character at position %d",
				    (int)i);
				goto bail;
			}
			/* overflow detection: 0xffffffff == "|NsC0",
			 * "|NsC" == 0x03030303 */
			if (acc > 0x03030303 || (acc *= 85) > 0xffffffff - c) {
				PyErr_Format(
				    PyExc_ValueError,
				    "bad base85 sequence at position %d",
				    (int)i);
				goto bail;
			}
			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;
bail:
	Py_XDECREF(out);
	return NULL;
}

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