Mercurial > hg
view mercurial/base85.c @ 26755:bb0b955d050d
streamclone: support for producing and consuming stream clone bundles
Up to this point, stream clones only existed as a dynamically generated
data format produced and consumed during streaming clones. In order to
support this efficient cloning format with the clone bundles feature, we
need a more formal, on disk representation of the streaming clone data.
This patch introduces a new "bundle" type for streaming clones. Unlike
existing bundles, it does not contain changegroup data. It does,
however, share the same concepts like the 4 byte header which identifies
the type of data that follows and the 2 byte abbreviation for
compression types (of which only "UN" is currently supported).
The new bundle format is essentially the existing stream clone version 1
data format with some headers at the beginning.
Content negotiation at stream clone request time checked for repository
format/requirements compatibility before initiating a stream clone. We
can't do active content negotiation when using clone bundles. So, we put
this set of requirements inside the payload so consumers have a built-in
mechanism for checking compatibility before reading and applying lots of
data. Of course, we will also advertise this requirements set in clone
bundles. But that's for another patch.
We currently don't have a mechanism to produce and consume this new
bundle format. This will be implemented in upcoming patches.
It's worth noting that if a legacy client attempts to `hg unbundle` a
stream clone bundle (with the "HGS1" header), it will abort with:
"unknown bundle version S1," which seems appropriate.
author | Gregory Szorc <gregory.szorc@gmail.com> |
---|---|
date | Sat, 17 Oct 2015 11:14:52 -0700 |
parents | c1aefe57cf4e |
children | 4613a89bea42 |
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) { 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