##// END OF EJS Templates
wireprotov2: add phases to "changesetdata" command...
wireprotov2: add phases to "changesetdata" command This commit teaches the "changesetdata" wire protocol command to emit the phase state for each changeset. This is a different approach from existing phase transfer in a few ways. Previously, if there are no new revisions (or we're not using bundle2), we perform a "listkeys" request to retrieve phase heads. And when revision data is being transferred with bundle2, phases data is encoded in a standalone bundle2 part. In both cases, phases data is logically decoupled from the changeset data and is encountered/applied after changeset revision data is received. The new wire protocol purposefully tries to more tightly associate changeset metadata (phases, bookmarks, obsolescence markers, etc) with the changeset revision and index data itself, rather than have it live as a separate entity that must be fetched and processed separately. I reckon that one reason we didn't do this before was it was difficult to add new data types/fields without breaking existing consumers. By using CBOR maps to transfer changeset data and putting clients in control of what fields are requested / present in those maps, we can easily add additional changeset data while maintaining backwards compatibility. I believe this to be a superior approach to the problem. That being said, for performance reasons, we may need to resort to alternative mechanisms for transferring data like phases. But for now, I think giving the wire protocol the ability to transfer changeset metadata next to the changeset itself is a powerful feature because it is a raw, changeset-centric data API. And if you build simple APIs for accessing the fundamental units of repository data, you enable client-side experimentation (partial clone, etc). If it turns out that we need specialized APIs or mechanisms for transferring data like phases, we can build in those APIs later. For now, I'd like to see how far we can get on simple APIs. It's worth noting that when phase data is being requested, the server will also emit changeset records for nodes in the bases specified by the "noderange" argument. This is to ensure that phase-only updates for nodes the client has are available to the client, even if no new changesets will be transferred. Differential Revision: https://phab.mercurial-scm.org/D4483

File last commit:

r36638:186c6df3 default
r39668:c1aacb0d default
Show More
mpatch.c
201 lines | 4.6 KiB | text/x-c | CLexer
/*
mpatch.c - efficient binary patching for Mercurial
This implements a patch algorithm that's O(m + nlog n) where m is the
size of the output and n is the number of patches.
Given a list of binary patches, it unpacks each into a hunk list,
then combines the hunk lists with a treewise recursion to form a
single hunk list. This hunk list is then applied to the original
text.
The text (or binary) fragments are copied directly from their source
Python objects into a preallocated output string to avoid the
allocation of intermediate Python objects. Working memory is about 2x
the total number of hunks.
Copyright 2005, 2006 Matt Mackall <mpm@selenic.com>
This software may be used and distributed according to the terms
of the GNU General Public License, incorporated herein by reference.
*/
#define PY_SSIZE_T_CLEAN
#include <Python.h>
#include <stdlib.h>
#include <string.h>
#include "bitmanipulation.h"
#include "compat.h"
#include "mpatch.h"
#include "util.h"
static char mpatch_doc[] = "Efficient binary patching.";
static PyObject *mpatch_Error;
static void setpyerr(int r)
{
switch (r) {
case MPATCH_ERR_NO_MEM:
PyErr_NoMemory();
break;
case MPATCH_ERR_CANNOT_BE_DECODED:
PyErr_SetString(mpatch_Error, "patch cannot be decoded");
break;
case MPATCH_ERR_INVALID_PATCH:
PyErr_SetString(mpatch_Error, "invalid patch");
break;
}
}
struct mpatch_flist *cpygetitem(void *bins, ssize_t pos)
{
const char *buffer;
struct mpatch_flist *res;
ssize_t blen;
int r;
PyObject *tmp = PyList_GetItem((PyObject *)bins, pos);
if (!tmp)
return NULL;
if (PyObject_AsCharBuffer(tmp, &buffer, (Py_ssize_t *)&blen))
return NULL;
if ((r = mpatch_decode(buffer, blen, &res)) < 0) {
if (!PyErr_Occurred())
setpyerr(r);
return NULL;
}
return res;
}
static PyObject *patches(PyObject *self, PyObject *args)
{
PyObject *text, *bins, *result;
struct mpatch_flist *patch;
const char *in;
int r = 0;
char *out;
Py_ssize_t len, outlen, inlen;
if (!PyArg_ParseTuple(args, "OO:mpatch", &text, &bins))
return NULL;
len = PyList_Size(bins);
if (!len) {
/* nothing to do */
Py_INCREF(text);
return text;
}
if (PyObject_AsCharBuffer(text, &in, &inlen))
return NULL;
patch = mpatch_fold(bins, cpygetitem, 0, len);
if (!patch) { /* error already set or memory error */
if (!PyErr_Occurred())
PyErr_NoMemory();
return NULL;
}
outlen = mpatch_calcsize(inlen, patch);
if (outlen < 0) {
r = (int)outlen;
result = NULL;
goto cleanup;
}
result = PyBytes_FromStringAndSize(NULL, outlen);
if (!result) {
result = NULL;
goto cleanup;
}
out = PyBytes_AsString(result);
/* clang-format off */
{
Py_BEGIN_ALLOW_THREADS
r = mpatch_apply(out, in, inlen, patch);
Py_END_ALLOW_THREADS
}
/* clang-format on */
if (r < 0) {
Py_DECREF(result);
result = NULL;
}
cleanup:
mpatch_lfree(patch);
if (!result && !PyErr_Occurred())
setpyerr(r);
return result;
}
/* calculate size of a patched file directly */
static PyObject *patchedsize(PyObject *self, PyObject *args)
{
long orig, start, end, len, outlen = 0, last = 0, pos = 0;
Py_ssize_t patchlen;
char *bin;
if (!PyArg_ParseTuple(args, PY23("ls#", "ly#"), &orig, &bin, &patchlen))
return NULL;
while (pos >= 0 && pos < patchlen) {
start = getbe32(bin + pos);
end = getbe32(bin + pos + 4);
len = getbe32(bin + pos + 8);
if (start > end)
break; /* sanity check */
pos += 12 + len;
outlen += start - last;
last = end;
outlen += len;
}
if (pos != patchlen) {
if (!PyErr_Occurred())
PyErr_SetString(mpatch_Error,
"patch cannot be decoded");
return NULL;
}
outlen += orig - last;
return Py_BuildValue("l", outlen);
}
static PyMethodDef methods[] = {
{"patches", patches, METH_VARARGS, "apply a series of patches\n"},
{"patchedsize", patchedsize, METH_VARARGS, "calculed patched size\n"},
{NULL, NULL},
};
static const int version = 1;
#ifdef IS_PY3K
static struct PyModuleDef mpatch_module = {
PyModuleDef_HEAD_INIT, "mpatch", mpatch_doc, -1, methods,
};
PyMODINIT_FUNC PyInit_mpatch(void)
{
PyObject *m;
m = PyModule_Create(&mpatch_module);
if (m == NULL)
return NULL;
mpatch_Error =
PyErr_NewException("mercurial.cext.mpatch.mpatchError", NULL, NULL);
Py_INCREF(mpatch_Error);
PyModule_AddObject(m, "mpatchError", mpatch_Error);
PyModule_AddIntConstant(m, "version", version);
return m;
}
#else
PyMODINIT_FUNC initmpatch(void)
{
PyObject *m;
m = Py_InitModule3("mpatch", methods, mpatch_doc);
mpatch_Error =
PyErr_NewException("mercurial.cext.mpatch.mpatchError", NULL, NULL);
PyModule_AddIntConstant(m, "version", version);
}
#endif