( )⚙ D11684 dirstate: store mtimes with nanosecond precision in memory

This is an archive of the discontinued Mercurial Phabricator instance.

Differential D11684

dirstate: store mtimes with nanosecond precision in memory
ClosedPublic

Authored by SimonSapin on Oct 18 2021, 10:43 AM.

Details

Reviewers
Alphare
Group Reviewers
hg-reviewers
Commits
rHG269ff8978086: dirstate: store mtimes with nanosecond precision in memory
Summary

Keep integer seconds since the Unix epoch,
together with integer nanoseconds in the 0 <= n < 1e9 range.

For now, nanoseconds are still always zero.
This commit is about data structure changes.

Diff Detail

Repository
rHG Mercurial
Branch
default
Lint
No Linters Available
Unit
No Unit Test Coverage

Event Timeline

SimonSapin created this revision.Oct 18 2021, 10:43 AM
Alphare accepted this revision.Oct 19 2021, 8:44 AM
Alphare added a subscriber: Alphare.
Alphare added inline comments.
mercurial/dirstate.py
1395

Note that this comment still refers to "normal" and that lastnormaltime is still used. This could be worth following-up with a more up-to-date semantic.

This revision is now accepted and ready to land.Oct 19 2021, 8:44 AM
marmoute added a subscriber: marmoute.Oct 19 2021, 3:50 PM
marmoute added inline comments.
mercurial/dirstate.py
1395

This is currently still the same logic. We should eventually just drop the lastnormaltime and replace it with comparison with fsnow during the status operation. However, not today.

marmoute edited parent revisions, added: D11696: rust: remove now-unused DirstateEntry::clear_ambiguous_mtime method; removed: D11691: dirstate: rename a `very_likely_equal` method to `likely_equal`.Oct 19 2021, 6:03 PM
marmoute retitled this revision from dirstate: Store mtimes with nanosecond precision in memory to dirstate: store mtimes with nanosecond precision in memory.
marmoute added a child revision: D11700: dirstate-v2: add a new MTIME_SECOND_AMBIGUOUS flags.
marmoute updated this revision to Diff 30917.
marmoute updated this revision to Diff 30931.Oct 20 2021, 5:12 AM

Revision Contents
Changeset List

Diff 30876

mercurial/cext/parsers.c

dirstateItemObject *t; dirstateItemObject *t;
int wc_tracked; int wc_tracked;
int p1_tracked; int p1_tracked;
int p2_info; int p2_info;
int has_meaningful_data; int has_meaningful_data;
int has_meaningful_mtime; int has_meaningful_mtime;
int mode; int mode;
int size; int size;
int mtime; int mtime_s;
int mtime_ns;
PyObject *parentfiledata; PyObject *parentfiledata;
static char *keywords_name[] = { static char *keywords_name[] = {
"wc_tracked", "wc_tracked",
"p1_tracked", "p1_tracked",
"p2_info", "p2_info",
"has_meaningful_data", "has_meaningful_data",
"has_meaningful_mtime", "has_meaningful_mtime",
"parentfiledata", "parentfiledata",
if (p1_tracked) { if (p1_tracked) {
t->flags |= dirstate_flag_p1_tracked; t->flags |= dirstate_flag_p1_tracked;
} }
if (p2_info) { if (p2_info) {
t->flags |= dirstate_flag_p2_info; t->flags |= dirstate_flag_p2_info;
} }
if (parentfiledata != Py_None) { if (parentfiledata != Py_None) {
if (!PyTuple_CheckExact(parentfiledata)) { if (!PyArg_ParseTuple(parentfiledata, "ii(ii)", &mode, &size,
PyErr_SetString( &mtime_s, &mtime_ns)) {
PyExc_TypeError,
"parentfiledata should be a Tuple or None");
return NULL; return NULL;
} }
mode = (int)PyLong_AsLong(PyTuple_GetItem(parentfiledata, 0));
size = (int)PyLong_AsLong(PyTuple_GetItem(parentfiledata, 1));
mtime = (int)PyLong_AsLong(PyTuple_GetItem(parentfiledata, 2));
} else { } else {
has_meaningful_data = 0; has_meaningful_data = 0;
has_meaningful_mtime = 0; has_meaningful_mtime = 0;
} }
if (has_meaningful_data) { if (has_meaningful_data) {
t->flags |= dirstate_flag_has_meaningful_data; t->flags |= dirstate_flag_has_meaningful_data;
t->mode = mode; t->mode = mode;
t->size = size; t->size = size;
} else { } else {
t->mode = 0; t->mode = 0;
t->size = 0; t->size = 0;
} }
if (has_meaningful_mtime) { if (has_meaningful_mtime) {
t->flags |= dirstate_flag_has_file_mtime; t->flags |= dirstate_flag_has_file_mtime;
t->mtime = mtime; t->mtime_s = mtime_s;
t->mtime_ns = mtime_ns;
} else { } else {
t->mtime = 0; t->mtime_s = 0;
t->mtime_ns = 0;
} }
return (PyObject *)t; return (PyObject *)t;
} }
static void dirstate_item_dealloc(PyObject *o) static void dirstate_item_dealloc(PyObject *o)
{ {
PyObject_Del(o); PyObject_Del(o);
} }
if (dirstate_item_c_removed(self)) { if (dirstate_item_c_removed(self)) {
return 0; return 0;
} else if (!(self->flags & dirstate_flag_has_file_mtime) || } else if (!(self->flags & dirstate_flag_has_file_mtime) ||
!(self->flags & dirstate_flag_p1_tracked) || !(self->flags & dirstate_flag_p1_tracked) ||
!(self->flags & dirstate_flag_wc_tracked) || !(self->flags & dirstate_flag_wc_tracked) ||
(self->flags & dirstate_flag_p2_info)) { (self->flags & dirstate_flag_p2_info)) {
return ambiguous_time; return ambiguous_time;
} else { } else {
return self->mtime; return self->mtime_s;
} }
} }
static PyObject *dirstate_item_v2_data(dirstateItemObject *self) static PyObject *dirstate_item_v2_data(dirstateItemObject *self)
{ {
unsigned char flags = self->flags; unsigned char flags = self->flags;
int mode = dirstate_item_c_v1_mode(self); int mode = dirstate_item_c_v1_mode(self);
if ((mode & S_IXUSR) != 0) { if ((mode & S_IXUSR) != 0) {
flags |= dirstate_flag_mode_exec_perm; flags |= dirstate_flag_mode_exec_perm;
} else { } else {
flags &= ~dirstate_flag_mode_exec_perm; flags &= ~dirstate_flag_mode_exec_perm;
} }
if (S_ISLNK(mode)) { if (S_ISLNK(mode)) {
flags |= dirstate_flag_mode_is_symlink; flags |= dirstate_flag_mode_is_symlink;
} else { } else {
flags &= ~dirstate_flag_mode_is_symlink; flags &= ~dirstate_flag_mode_is_symlink;
} }
return Py_BuildValue("Bii", flags, self->size, self->mtime); return Py_BuildValue("Biii", flags, self->size, self->mtime_s,
self->mtime_ns);
}; };
static PyObject *dirstate_item_v1_state(dirstateItemObject *self) static PyObject *dirstate_item_v1_state(dirstateItemObject *self)
{ {
char state = dirstate_item_c_v1_state(self); char state = dirstate_item_c_v1_state(self);
return PyBytes_FromStringAndSize(&state, 1); return PyBytes_FromStringAndSize(&state, 1);
}; };
static PyObject *dirstate_item_v1_mode(dirstateItemObject *self) static PyObject *dirstate_item_v1_mode(dirstateItemObject *self)
{ {
return PyInt_FromLong(dirstate_item_c_v1_mode(self)); return PyInt_FromLong(dirstate_item_c_v1_mode(self));
}; };
static PyObject *dirstate_item_v1_size(dirstateItemObject *self) static PyObject *dirstate_item_v1_size(dirstateItemObject *self)
{ {
return PyInt_FromLong(dirstate_item_c_v1_size(self)); return PyInt_FromLong(dirstate_item_c_v1_size(self));
}; };
static PyObject *dirstate_item_v1_mtime(dirstateItemObject *self) static PyObject *dirstate_item_v1_mtime(dirstateItemObject *self)
{ {
return PyInt_FromLong(dirstate_item_c_v1_mtime(self)); return PyInt_FromLong(dirstate_item_c_v1_mtime(self));
}; };
static PyObject *dirstate_item_need_delay(dirstateItemObject *self, static PyObject *dirstate_item_need_delay(dirstateItemObject *self,
PyObject *value) PyObject *now)
{ {
long now; int now_s;
if (!pylong_to_long(value, &now)) { int now_ns;
if (!PyArg_ParseTuple(now, "ii", &now_s, &now_ns)) {
return NULL; return NULL;
} }
if (dirstate_item_c_v1_state(self) == 'n' && if (dirstate_item_c_v1_state(self) == 'n' && self->mtime_s == now_s &&
dirstate_item_c_v1_mtime(self) == now) { self->mtime_ns == now_ns) {
Py_RETURN_TRUE;
} else {
Py_RETURN_FALSE;
}
};
static PyObject *dirstate_item_mtime_likely_equal_to(dirstateItemObject *self,
PyObject *other)
{
int other_s;
int other_ns;
if (!PyArg_ParseTuple(other, "ii", &other_s, &other_ns)) {
return NULL;
}
if ((self->flags & dirstate_flag_has_file_mtime) &&
self->mtime_s == other_s && self->mtime_ns == other_ns) {
Py_RETURN_TRUE; Py_RETURN_TRUE;
} else { } else {
Py_RETURN_FALSE; Py_RETURN_FALSE;
} }
}; };
/* This will never change since it's bound to V1 /* This will never change since it's bound to V1
*/ */
static inline dirstateItemObject * static inline dirstateItemObject *
dirstate_item_from_v1_data(char state, int mode, int size, int mtime) dirstate_item_from_v1_data(char state, int mode, int size, int mtime)
{ {
dirstateItemObject *t = dirstateItemObject *t =
PyObject_New(dirstateItemObject, &dirstateItemType); PyObject_New(dirstateItemObject, &dirstateItemType);
if (!t) { if (!t) {
return NULL; return NULL;
} }
t->flags = 0; t->flags = 0;
t->mode = 0; t->mode = 0;
t->size = 0; t->size = 0;
t->mtime = 0; t->mtime_s = 0;
t->mtime_ns = 0;
if (state == 'm') { if (state == 'm') {
t->flags = (dirstate_flag_wc_tracked | t->flags = (dirstate_flag_wc_tracked |
dirstate_flag_p1_tracked | dirstate_flag_p2_info); dirstate_flag_p1_tracked | dirstate_flag_p2_info);
} else if (state == 'a') { } else if (state == 'a') {
t->flags = dirstate_flag_wc_tracked; t->flags = dirstate_flag_wc_tracked;
} else if (state == 'r') { } else if (state == 'r') {
if (size == dirstate_v1_nonnormal) { if (size == dirstate_v1_nonnormal) {
t->size = size; t->size = size;
} else { } else {
t->flags = (dirstate_flag_wc_tracked | t->flags = (dirstate_flag_wc_tracked |
dirstate_flag_p1_tracked | dirstate_flag_p1_tracked |
dirstate_flag_has_meaningful_data | dirstate_flag_has_meaningful_data |
dirstate_flag_has_file_mtime); dirstate_flag_has_file_mtime);
t->mode = mode; t->mode = mode;
t->size = size; t->size = size;
t->mtime = mtime; t->mtime_s = mtime;
} }
} else { } else {
PyErr_Format(PyExc_RuntimeError, PyErr_Format(PyExc_RuntimeError,
"unknown state: `%c` (%d, %d, %d)", state, mode, "unknown state: `%c` (%d, %d, %d)", state, mode,
size, mtime, NULL); size, mtime, NULL);
Py_DECREF(t); Py_DECREF(t);
return NULL; return NULL;
} }
static PyObject *dirstate_item_from_v2_meth(PyTypeObject *subtype, static PyObject *dirstate_item_from_v2_meth(PyTypeObject *subtype,
PyObject *args) PyObject *args)
{ {
dirstateItemObject *t = dirstateItemObject *t =
PyObject_New(dirstateItemObject, &dirstateItemType); PyObject_New(dirstateItemObject, &dirstateItemType);
if (!t) { if (!t) {
return NULL; return NULL;
} }
if (!PyArg_ParseTuple(args, "bii", &t->flags, &t->size, &t->mtime)) { if (!PyArg_ParseTuple(args, "biii", &t->flags, &t->size, &t->mtime_s,
&t->mtime_ns)) {
return NULL; return NULL;
} }
t->mode = 0; t->mode = 0;
if (t->flags & dirstate_flag_has_meaningful_data) { if (t->flags & dirstate_flag_has_meaningful_data) {
if (t->flags & dirstate_flag_mode_exec_perm) { if (t->flags & dirstate_flag_mode_exec_perm) {
t->mode = 0755; t->mode = 0755;
} else { } else {
t->mode = 0644; t->mode = 0644;
self->flags &= ~dirstate_flag_has_file_mtime; self->flags &= ~dirstate_flag_has_file_mtime;
Py_RETURN_NONE; Py_RETURN_NONE;
} }
/* See docstring of the python implementation for details */ /* See docstring of the python implementation for details */
static PyObject *dirstate_item_set_clean(dirstateItemObject *self, static PyObject *dirstate_item_set_clean(dirstateItemObject *self,
PyObject *args) PyObject *args)
{ {
int size, mode, mtime; int size, mode, mtime_s, mtime_ns;
if (!PyArg_ParseTuple(args, "iii", &mode, &size, &mtime)) { if (!PyArg_ParseTuple(args, "ii(ii)", &mode, &size, &mtime_s,
&mtime_ns)) {
return NULL; return NULL;
} }
self->flags = dirstate_flag_wc_tracked | dirstate_flag_p1_tracked | self->flags = dirstate_flag_wc_tracked | dirstate_flag_p1_tracked |
dirstate_flag_has_meaningful_data | dirstate_flag_has_meaningful_data |
dirstate_flag_has_file_mtime; dirstate_flag_has_file_mtime;
self->mode = mode; self->mode = mode;
self->size = size; self->size = size;
self->mtime = mtime; self->mtime_s = mtime_s;
self->mtime_ns = mtime_ns;
Py_RETURN_NONE; Py_RETURN_NONE;
} }
static PyObject *dirstate_item_set_tracked(dirstateItemObject *self) static PyObject *dirstate_item_set_tracked(dirstateItemObject *self)
{ {
self->flags |= dirstate_flag_wc_tracked; self->flags |= dirstate_flag_wc_tracked;
self->flags &= ~dirstate_flag_has_file_mtime; self->flags &= ~dirstate_flag_has_file_mtime;
Py_RETURN_NONE; Py_RETURN_NONE;
} }
static PyObject *dirstate_item_set_untracked(dirstateItemObject *self) static PyObject *dirstate_item_set_untracked(dirstateItemObject *self)
{ {
self->flags &= ~dirstate_flag_wc_tracked; self->flags &= ~dirstate_flag_wc_tracked;
self->mode = 0; self->mode = 0;
self->mtime = 0;
self->size = 0; self->size = 0;
self->mtime_s = 0;
self->mtime_ns = 0;
Py_RETURN_NONE; Py_RETURN_NONE;
} }
static PyObject *dirstate_item_drop_merge_data(dirstateItemObject *self) static PyObject *dirstate_item_drop_merge_data(dirstateItemObject *self)
{ {
if (self->flags & dirstate_flag_p2_info) { if (self->flags & dirstate_flag_p2_info) {
self->flags &= ~(dirstate_flag_p2_info | self->flags &= ~(dirstate_flag_p2_info |
dirstate_flag_has_meaningful_data | dirstate_flag_has_meaningful_data |
dirstate_flag_has_file_mtime); dirstate_flag_has_file_mtime);
self->mode = 0; self->mode = 0;
self->mtime = 0;
self->size = 0; self->size = 0;
self->mtime_s = 0;
self->mtime_ns = 0;
} }
Py_RETURN_NONE; Py_RETURN_NONE;
} }
static PyMethodDef dirstate_item_methods[] = { static PyMethodDef dirstate_item_methods[] = {
{"v2_data", (PyCFunction)dirstate_item_v2_data, METH_NOARGS, {"v2_data", (PyCFunction)dirstate_item_v2_data, METH_NOARGS,
"return data suitable for v2 serialization"}, "return data suitable for v2 serialization"},
{"v1_state", (PyCFunction)dirstate_item_v1_state, METH_NOARGS, {"v1_state", (PyCFunction)dirstate_item_v1_state, METH_NOARGS,
"return a \"state\" suitable for v1 serialization"}, "return a \"state\" suitable for v1 serialization"},
{"v1_mode", (PyCFunction)dirstate_item_v1_mode, METH_NOARGS, {"v1_mode", (PyCFunction)dirstate_item_v1_mode, METH_NOARGS,
"return a \"mode\" suitable for v1 serialization"}, "return a \"mode\" suitable for v1 serialization"},
{"v1_size", (PyCFunction)dirstate_item_v1_size, METH_NOARGS, {"v1_size", (PyCFunction)dirstate_item_v1_size, METH_NOARGS,
"return a \"size\" suitable for v1 serialization"}, "return a \"size\" suitable for v1 serialization"},
{"v1_mtime", (PyCFunction)dirstate_item_v1_mtime, METH_NOARGS, {"v1_mtime", (PyCFunction)dirstate_item_v1_mtime, METH_NOARGS,
"return a \"mtime\" suitable for v1 serialization"}, "return a \"mtime\" suitable for v1 serialization"},
{"need_delay", (PyCFunction)dirstate_item_need_delay, METH_O, {"need_delay", (PyCFunction)dirstate_item_need_delay, METH_O,
"True if the stored mtime would be ambiguous with the current time"}, "True if the stored mtime would be ambiguous with the current time"},
{"mtime_likely_equal_to", (PyCFunction)dirstate_item_mtime_likely_equal_to,
METH_O, "True if the stored mtime is likely equal to the given mtime"},
{"from_v1_data", (PyCFunction)dirstate_item_from_v1_meth, {"from_v1_data", (PyCFunction)dirstate_item_from_v1_meth,
METH_VARARGS | METH_CLASS, "build a new DirstateItem object from V1 data"}, METH_VARARGS | METH_CLASS, "build a new DirstateItem object from V1 data"},
{"from_v2_data", (PyCFunction)dirstate_item_from_v2_meth, {"from_v2_data", (PyCFunction)dirstate_item_from_v2_meth,
METH_VARARGS | METH_CLASS, "build a new DirstateItem object from V2 data"}, METH_VARARGS | METH_CLASS, "build a new DirstateItem object from V2 data"},
{"set_possibly_dirty", (PyCFunction)dirstate_item_set_possibly_dirty, {"set_possibly_dirty", (PyCFunction)dirstate_item_set_possibly_dirty,
METH_NOARGS, "mark a file as \"possibly dirty\""}, METH_NOARGS, "mark a file as \"possibly dirty\""},
{"set_clean", (PyCFunction)dirstate_item_set_clean, METH_VARARGS, {"set_clean", (PyCFunction)dirstate_item_set_clean, METH_VARARGS,
"mark a file as \"clean\""}, "mark a file as \"clean\""},
*/ */
static PyObject *pack_dirstate(PyObject *self, PyObject *args) static PyObject *pack_dirstate(PyObject *self, PyObject *args)
{ {
PyObject *packobj = NULL; PyObject *packobj = NULL;
PyObject *map, *copymap, *pl, *mtime_unset = NULL; PyObject *map, *copymap, *pl, *mtime_unset = NULL;
Py_ssize_t nbytes, pos, l; Py_ssize_t nbytes, pos, l;
PyObject *k, *v = NULL, *pn; PyObject *k, *v = NULL, *pn;
char *p, *s; char *p, *s;
int now; int now_s;
int now_ns;
if (!PyArg_ParseTuple(args, "O!O!O!i:pack_dirstate", &PyDict_Type, &map, if (!PyArg_ParseTuple(args, "O!O!O!(ii):pack_dirstate", &PyDict_Type,
&PyDict_Type, &copymap, &PyTuple_Type, &pl, &map, &PyDict_Type, &copymap, &PyTuple_Type, &pl,
&now)) { &now_s, &now_ns)) {
return NULL; return NULL;
} }
if (PyTuple_Size(pl) != 2) { if (PyTuple_Size(pl) != 2) {
PyErr_SetString(PyExc_TypeError, "expected 2-element tuple"); PyErr_SetString(PyExc_TypeError, "expected 2-element tuple");
return NULL; return NULL;
} }
goto bail; goto bail;
} }
tuple = (dirstateItemObject *)v; tuple = (dirstateItemObject *)v;
state = dirstate_item_c_v1_state(tuple); state = dirstate_item_c_v1_state(tuple);
mode = dirstate_item_c_v1_mode(tuple); mode = dirstate_item_c_v1_mode(tuple);
size = dirstate_item_c_v1_size(tuple); size = dirstate_item_c_v1_size(tuple);
mtime = dirstate_item_c_v1_mtime(tuple); mtime = dirstate_item_c_v1_mtime(tuple);
if (state == 'n' && mtime == now) { if (state == 'n' && tuple->mtime_s == now_s &&
tuple->mtime_ns == now_ns) {
/* See pure/parsers.py:pack_dirstate for why we do /* See pure/parsers.py:pack_dirstate for why we do
* this. */ * this. */
mtime = -1; mtime = -1;
mtime_unset = (PyObject *)dirstate_item_from_v1_data( mtime_unset = (PyObject *)dirstate_item_from_v1_data(
state, mode, size, mtime); state, mode, size, mtime);
if (!mtime_unset) { if (!mtime_unset) {
goto bail; goto bail;
} }

mercurial/cext/util.h

#endif #endif
/* clang-format off */ /* clang-format off */
typedef struct { typedef struct {
PyObject_HEAD PyObject_HEAD
unsigned char flags; unsigned char flags;
int mode; int mode;
int size; int size;
int mtime; int mtime_s;
int mtime_ns;
} dirstateItemObject; } dirstateItemObject;
/* clang-format on */ /* clang-format on */
static const unsigned char dirstate_flag_wc_tracked = 1; static const unsigned char dirstate_flag_wc_tracked = 1;
static const unsigned char dirstate_flag_p1_tracked = 1 << 1; static const unsigned char dirstate_flag_p1_tracked = 1 << 1;
static const unsigned char dirstate_flag_p2_info = 1 << 2; static const unsigned char dirstate_flag_p2_info = 1 << 2;
static const unsigned char dirstate_flag_has_meaningful_data = 1 << 3; static const unsigned char dirstate_flag_has_meaningful_data = 1 << 3;
static const unsigned char dirstate_flag_has_file_mtime = 1 << 4; static const unsigned char dirstate_flag_has_file_mtime = 1 << 4;

mercurial/dirstate.py

pathutil, pathutil,
policy, policy,
pycompat, pycompat,
scmutil, scmutil,
sparse, sparse,
util, util,
) )
from .dirstateutils import (
timestamp,
)
from .interfaces import ( from .interfaces import (
dirstate as intdirstate, dirstate as intdirstate,
util as interfaceutil, util as interfaceutil,
) )
parsers = policy.importmod('parsers') parsers = policy.importmod('parsers')
rustmod = policy.importrust('dirstate') rustmod = policy.importrust('dirstate')
def join(self, obj, fname): def join(self, obj, fname):
return obj._join(fname) return obj._join(fname)
def _getfsnow(vfs): def _getfsnow(vfs):
'''Get "now" timestamp on filesystem''' '''Get "now" timestamp on filesystem'''
tmpfd, tmpname = vfs.mkstemp() tmpfd, tmpname = vfs.mkstemp()
try: try:
return os.fstat(tmpfd)[stat.ST_MTIME] return timestamp.mtime_of(os.fstat(tmpfd))
finally: finally:
os.close(tmpfd) os.close(tmpfd)
vfs.unlink(tmpname) vfs.unlink(tmpname)
def requires_parents_change(func): def requires_parents_change(func):
def wrap(self, *args, **kwargs): def wrap(self, *args, **kwargs):
if not self.pendingparentchange(): if not self.pendingparentchange():
self._opener = opener self._opener = opener
self._validate = validate self._validate = validate
self._root = root self._root = root
self._sparsematchfn = sparsematchfn self._sparsematchfn = sparsematchfn
# ntpath.join(root, '') of Python 2.7.9 does not add sep if root is # ntpath.join(root, '') of Python 2.7.9 does not add sep if root is
# UNC path pointing to root share (issue4557) # UNC path pointing to root share (issue4557)
self._rootdir = pathutil.normasprefix(root) self._rootdir = pathutil.normasprefix(root)
self._dirty = False self._dirty = False
self._lastnormaltime = 0 self._lastnormaltime = timestamp.zero()
self._ui = ui self._ui = ui
self._filecache = {} self._filecache = {}
self._parentwriters = 0 self._parentwriters = 0
self._filename = b'dirstate' self._filename = b'dirstate'
self._pendingfilename = b'%s.pending' % self._filename self._pendingfilename = b'%s.pending' % self._filename
self._plchangecallbacks = {} self._plchangecallbacks = {}
self._origpl = None self._origpl = None
self._mapcls = dirstatemap.dirstatemap self._mapcls = dirstatemap.dirstatemap
This is different from localrepo.invalidatedirstate() because it always This is different from localrepo.invalidatedirstate() because it always
rereads the dirstate. Use localrepo.invalidatedirstate() if you want to rereads the dirstate. Use localrepo.invalidatedirstate() if you want to
check whether the dirstate has changed before rereading it.""" check whether the dirstate has changed before rereading it."""
for a in ("_map", "_branch", "_ignore"): for a in ("_map", "_branch", "_ignore"):
if a in self.__dict__: if a in self.__dict__:
delattr(self, a) delattr(self, a)
self._lastnormaltime = 0 self._lastnormaltime = timestamp.zero()
self._dirty = False self._dirty = False
self._parentwriters = 0 self._parentwriters = 0
self._origpl = None self._origpl = None
def copy(self, source, dest): def copy(self, source, dest):
"""Mark dest as a copy of source. Unmark dest if source is None.""" """Mark dest as a copy of source. Unmark dest if source is None."""
if source == dest: if source == dest:
return return
msg %= (pycompat.bytestr(d), pycompat.bytestr(filename)) msg %= (pycompat.bytestr(d), pycompat.bytestr(filename))
raise error.Abort(msg) raise error.Abort(msg)
def _get_filedata(self, filename): def _get_filedata(self, filename):
"""returns""" """returns"""
s = os.lstat(self._join(filename)) s = os.lstat(self._join(filename))
mode = s.st_mode mode = s.st_mode
size = s.st_size size = s.st_size
mtime = s[stat.ST_MTIME] mtime = timestamp.mtime_of(s)
return (mode, size, mtime) return (mode, size, mtime)
def _discoverpath(self, path, normed, ignoremissing, exists, storemap): def _discoverpath(self, path, normed, ignoremissing, exists, storemap):
if exists is None: if exists is None:
exists = os.path.lexists(os.path.join(self._root, path)) exists = os.path.lexists(os.path.join(self._root, path))
if not exists: if not exists:
# Maybe a path component exists # Maybe a path component exists
if not ignoremissing and b'/' in path: if not ignoremissing and b'/' in path:
pycompat.iteritems(self._plchangecallbacks) pycompat.iteritems(self._plchangecallbacks)
): ):
callback(self, self._origpl, self._pl) callback(self, self._origpl, self._pl)
self._origpl = None self._origpl = None
if now is None: if now is None:
# use the modification time of the newly created temporary file as the # use the modification time of the newly created temporary file as the
# filesystem's notion of 'now' # filesystem's notion of 'now'
now = util.fstat(st)[stat.ST_MTIME] & _rangemask now = timestamp.mtime_of(util.fstat(st))
# enough 'delaywrite' prevents 'pack_dirstate' from dropping # enough 'delaywrite' prevents 'pack_dirstate' from dropping
# timestamp of each entries in dirstate, because of 'now > mtime' # timestamp of each entries in dirstate, because of 'now > mtime'
delaywrite = self._ui.configint(b'debug', b'dirstate.delaywrite') delaywrite = self._ui.configint(b'debug', b'dirstate.delaywrite')
if delaywrite > 0: if delaywrite > 0:
# do we have any files to delay for? # do we have any files to delay for?
for f, e in pycompat.iteritems(self._map): for f, e in pycompat.iteritems(self._map):
if e.need_delay(now): if e.need_delay(now):
import time # to avoid useless import import time # to avoid useless import
# rather than sleep n seconds, sleep until the next # rather than sleep n seconds, sleep until the next
# multiple of n seconds # multiple of n seconds
clock = time.time() clock = time.time()
start = int(clock) - (int(clock) % delaywrite) start = int(clock) - (int(clock) % delaywrite)
end = start + delaywrite end = start + delaywrite
time.sleep(end - clock) time.sleep(end - clock)
now = end # trust our estimate that the end is near now # trust our estimate that the end is near now
now = timestamp.timestamp((end, 0))
break break
self._map.write(tr, st, now) self._map.write(tr, st, now)
self._lastnormaltime = 0 self._lastnormaltime = timestamp.zero()
self._dirty = False self._dirty = False
def _dirignore(self, f): def _dirignore(self, f):
if self._ignore(f): if self._ignore(f):
return True return True
for p in pathutil.finddirs(f): for p in pathutil.finddirs(f):
if self._ignore(p): if self._ignore(p):
return True return True
if not dcontains(fn): if not dcontains(fn):
if (listignored or mexact(fn)) and dirignore(fn): if (listignored or mexact(fn)) and dirignore(fn):
if listignored: if listignored:
iadd(fn) iadd(fn)
else: else:
uadd(fn) uadd(fn)
continue continue
# This is equivalent to 'state, mode, size, time = dmap[fn]' but not
# written like that for performance reasons. dmap[fn] is not a
# Python tuple in compiled builds. The CPython UNPACK_SEQUENCE
# opcode has fast paths when the value to be unpacked is a tuple or
# a list, but falls back to creating a full-fledged iterator in
# general. That is much slower than simply accessing and storing the
# tuple members one by one.
t = dget(fn) t = dget(fn)
mode = t.mode mode = t.mode
size = t.size size = t.size
time = t.mtime
if not st and t.tracked: if not st and t.tracked:
dadd(fn) dadd(fn)
elif t.p2_info: elif t.p2_info:
madd(fn) madd(fn)
elif t.added: elif t.added:
aadd(fn) aadd(fn)
elif t.removed: elif t.removed:
radd(fn) radd(fn)
elif t.tracked: elif t.tracked:
if ( if (
size >= 0 size >= 0
and ( and (
(size != st.st_size and size != st.st_size & _rangemask) (size != st.st_size and size != st.st_size & _rangemask)
or ((mode ^ st.st_mode) & 0o100 and checkexec) or ((mode ^ st.st_mode) & 0o100 and checkexec)
) )
or fn in copymap or fn in copymap
): ):
if stat.S_ISLNK(st.st_mode) and size != st.st_size: if stat.S_ISLNK(st.st_mode) and size != st.st_size:
# issue6456: Size returned may be longer due to # issue6456: Size returned may be longer due to
# encryption on EXT-4 fscrypt, undecided. # encryption on EXT-4 fscrypt, undecided.
ladd(fn) ladd(fn)
else: else:
madd(fn) madd(fn)
elif ( elif not t.mtime_likely_equal_to(timestamp.mtime_of(st)):
time != st[stat.ST_MTIME]
and time != st[stat.ST_MTIME] & _rangemask
):
ladd(fn) ladd(fn)
elif st[stat.ST_MTIME] == lastnormaltime: elif timestamp.mtime_of(st) == lastnormaltime:
AlphareUnsubmitted
Not Done

Note that this comment still refers to "normal" and that lastnormaltime is still used. This could be worth following-up with a more up-to-date semantic.

Alphare: Note that this comment still refers to "normal" and that `lastnormaltime` is still used. This…
marmouteUnsubmitted
Not Done

This is currently still the same logic. We should eventually just drop the lastnormaltime and replace it with comparison with fsnow during the status operation. However, not today.

marmoute: This is currently still the same logic. We should eventually just drop the `lastnormaltime` and…
# fn may have just been marked as normal and it may have # fn may have just been marked as normal and it may have
# changed in the same second without changing its size. # changed in the same second without changing its size.
# This can happen if we quickly do multiple commits. # This can happen if we quickly do multiple commits.
# Force lookup, so we don't miss such a racy file change. # Force lookup, so we don't miss such a racy file change.
ladd(fn) ladd(fn)
elif listclean: elif listclean:
cadd(fn) cadd(fn)
status = scmutil.status( status = scmutil.status(

mercurial/dirstatemap.py

"""record that the current state of the file on disk is unknown""" """record that the current state of the file on disk is unknown"""
entry = self[filename] entry = self[filename]
entry.set_possibly_dirty() entry.set_possibly_dirty()
self._refresh_entry(filename, entry) self._refresh_entry(filename, entry)
def set_clean(self, filename, mode, size, mtime): def set_clean(self, filename, mode, size, mtime):
"""mark a file as back to a clean state""" """mark a file as back to a clean state"""
entry = self[filename] entry = self[filename]
mtime = mtime & rangemask
size = size & rangemask size = size & rangemask
entry.set_clean(mode, size, mtime) entry.set_clean(mode, size, mtime)
self._refresh_entry(filename, entry) self._refresh_entry(filename, entry)
self.copymap.pop(filename, None) self.copymap.pop(filename, None)
def set_tracked(self, filename): def set_tracked(self, filename):
new = False new = False
entry = self.get(filename) entry = self.get(filename)

mercurial/dirstateutils/timestamp.py

  • This file was added.
# Copyright Mercurial Contributors
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
from __future__ import absolute_import
import stat
rangemask = 0x7FFFFFFF
class timestamp(tuple):
"""
A Unix timestamp with nanoseconds precision,
modulo 2**31 seconds.
A 2-tuple containing:
`truncated_seconds`: seconds since the Unix epoch,
truncated to its lower 31 bits
`subsecond_nanoseconds`: number of nanoseconds since `truncated_seconds`.
"""
def __new__(cls, value):
truncated_seconds, subsec_nanos = value
value = (truncated_seconds & rangemask, subsec_nanos)
return super(timestamp, cls).__new__(cls, value)
def zero():
"""
Returns the `timestamp` at the Unix epoch.
"""
return tuple.__new__(timestamp, (0, 0))
def mtime_of(stat_result):
"""
Takes an `os.stat_result`-like object and returns a `timestamp` object
for its modification time.
"""
# https://docs.python.org/2/library/os.html#os.stat_float_times
# "For compatibility with older Python versions,
# accessing stat_result as a tuple always returns integers."
secs = stat_result[stat.ST_MTIME]
# For now
subsec_nanos = 0
return timestamp((secs, subsec_nanos))

mercurial/dirstateutils/v2.py

copy_source_len, copy_source_len,
children_start, children_start,
children_count, children_count,
_descendants_with_entry_count, _descendants_with_entry_count,
_tracked_descendants_count, _tracked_descendants_count,
flags, flags,
size, size,
mtime_s, mtime_s,
_mtime_ns, mtime_ns,
) = NODE.unpack(node_bytes) ) = NODE.unpack(node_bytes)
# Parse child nodes of this node recursively # Parse child nodes of this node recursively
parse_nodes(map, copy_map, data, children_start, children_count) parse_nodes(map, copy_map, data, children_start, children_count)
item = parsers.DirstateItem.from_v2_data(flags, size, mtime_s) item = parsers.DirstateItem.from_v2_data(flags, size, mtime_s, mtime_ns)
if not item.any_tracked: if not item.any_tracked:
continue continue
path = slice_with_len(data, path_start, path_len) path = slice_with_len(data, path_start, path_len)
map[path] = item map[path] = item
if copy_source_start: if copy_source_start:
copy_map[path] = slice_with_len( copy_map[path] = slice_with_len(
data, copy_source_start, copy_source_len data, copy_source_start, copy_source_len
) )
basename_start = path.rfind(b'/') + 1 # 0 if rfind returns -1 basename_start = path.rfind(b'/') + 1 # 0 if rfind returns -1
if copy is not None: if copy is not None:
copy_source_start = paths_offset + len(path) copy_source_start = paths_offset + len(path)
copy_source_len = len(copy) copy_source_len = len(copy)
else: else:
copy_source_start = 0 copy_source_start = 0
copy_source_len = 0 copy_source_len = 0
if entry is not None: if entry is not None:
flags, size, mtime_s = entry.v2_data() flags, size, mtime_s, mtime_ns = entry.v2_data()
mtime_ns = 0
else: else:
# There are no mtime-cached directories in the Python implementation # There are no mtime-cached directories in the Python implementation
flags = 0 flags = 0
size = 0 size = 0
mtime_s = 0 mtime_s = 0
mtime_ns = 0 mtime_ns = 0
return NODE.pack( return NODE.pack(
path_start, path_start,
that order that order
## Special case for the root node ## Special case for the root node
The root node is not serialized in the format, but its information is The root node is not serialized in the format, but its information is
written to the docket. Again, see more details on the on-disk format in written to the docket. Again, see more details on the on-disk format in
`mercurial/helptext/internals/dirstate-v2`. `mercurial/helptext/internals/dirstate-v2`.
""" """
now = int(now)
data = bytearray() data = bytearray()
root_nodes_start = 0 root_nodes_start = 0
root_nodes_len = 0 root_nodes_len = 0
nodes_with_entry_count = 0 nodes_with_entry_count = 0
nodes_with_copy_source_count = 0 nodes_with_copy_source_count = 0
# Will always be 0 since this implementation always re-writes everything # Will always be 0 since this implementation always re-writes everything
# to disk # to disk
unreachable_bytes = 0 unreachable_bytes = 0

mercurial/merge.py

# merge.py - directory-level update/merge handling for Mercurial # merge.py - directory-level update/merge handling for Mercurial
# #
# Copyright 2006, 2007 Olivia Mackall <olivia@selenic.com> # Copyright 2006, 2007 Olivia Mackall <olivia@selenic.com>
# #
# This software may be used and distributed according to the terms of the # This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version. # GNU General Public License version 2 or any later version.
from __future__ import absolute_import from __future__ import absolute_import
import collections import collections
import errno import errno
import stat
import struct import struct
from .i18n import _ from .i18n import _
from .node import nullrev from .node import nullrev
from .thirdparty import attr from .thirdparty import attr
from .utils import stringutil from .utils import stringutil
from .dirstateutils import timestamp
from . import ( from . import (
copies, copies,
encoding, encoding,
error, error,
filemerge, filemerge,
match as matchmod, match as matchmod,
mergestate as mergestatemod, mergestate as mergestatemod,
obsutil, obsutil,
fctx(f).data(), fctx(f).data(),
flags, flags,
backgroundclose=True, backgroundclose=True,
atomictemp=atomictemp, atomictemp=atomictemp,
) )
if wantfiledata: if wantfiledata:
s = wfctx.lstat() s = wfctx.lstat()
mode = s.st_mode mode = s.st_mode
mtime = s[stat.ST_MTIME] mtime = timestamp.mtime_of(s)
filedata[f] = (mode, size, mtime) # for dirstate.normal # for dirstate.update_file's parentfiledata argument:
filedata[f] = (mode, size, mtime)
if i == 100: if i == 100:
yield False, (i, f) yield False, (i, f)
i = 0 i = 0
i += 1 i += 1
if i > 0: if i > 0:
yield False, (i, f) yield False, (i, f)
yield True, filedata yield True, filedata

mercurial/pure/parsers.py

yet. yet.
""" """
_wc_tracked = attr.ib() _wc_tracked = attr.ib()
_p1_tracked = attr.ib() _p1_tracked = attr.ib()
_p2_info = attr.ib() _p2_info = attr.ib()
_mode = attr.ib() _mode = attr.ib()
_size = attr.ib() _size = attr.ib()
_mtime = attr.ib() _mtime_s = attr.ib()
_mtime_ns = attr.ib()
def __init__( def __init__(
self, self,
wc_tracked=False, wc_tracked=False,
p1_tracked=False, p1_tracked=False,
p2_info=False, p2_info=False,
has_meaningful_data=True, has_meaningful_data=True,
has_meaningful_mtime=True, has_meaningful_mtime=True,
parentfiledata=None, parentfiledata=None,
): ):
self._wc_tracked = wc_tracked self._wc_tracked = wc_tracked
self._p1_tracked = p1_tracked self._p1_tracked = p1_tracked
self._p2_info = p2_info self._p2_info = p2_info
self._mode = None self._mode = None
self._size = None self._size = None
self._mtime = None self._mtime_s = None
self._mtime_ns = None
if parentfiledata is None: if parentfiledata is None:
has_meaningful_mtime = False has_meaningful_mtime = False
has_meaningful_data = False has_meaningful_data = False
if has_meaningful_data: if has_meaningful_data:
self._mode = parentfiledata[0] self._mode = parentfiledata[0]
self._size = parentfiledata[1] self._size = parentfiledata[1]
if has_meaningful_mtime: if has_meaningful_mtime:
self._mtime = parentfiledata[2] self._mtime_s, self._mtime_ns = parentfiledata[2]
@classmethod @classmethod
def from_v2_data(cls, flags, size, mtime): def from_v2_data(cls, flags, size, mtime_s, mtime_ns):
"""Build a new DirstateItem object from V2 data""" """Build a new DirstateItem object from V2 data"""
has_mode_size = bool(flags & DIRSTATE_V2_HAS_MODE_AND_SIZE) has_mode_size = bool(flags & DIRSTATE_V2_HAS_MODE_AND_SIZE)
mode = None mode = None
if has_mode_size: if has_mode_size:
assert stat.S_IXUSR == 0o100 assert stat.S_IXUSR == 0o100
if flags & DIRSTATE_V2_MODE_EXEC_PERM: if flags & DIRSTATE_V2_MODE_EXEC_PERM:
mode = 0o755 mode = 0o755
else: else:
mode = 0o644 mode = 0o644
if flags & DIRSTATE_V2_MODE_IS_SYMLINK: if flags & DIRSTATE_V2_MODE_IS_SYMLINK:
mode |= stat.S_IFLNK mode |= stat.S_IFLNK
else: else:
mode |= stat.S_IFREG mode |= stat.S_IFREG
return cls( return cls(
wc_tracked=bool(flags & DIRSTATE_V2_WDIR_TRACKED), wc_tracked=bool(flags & DIRSTATE_V2_WDIR_TRACKED),
p1_tracked=bool(flags & DIRSTATE_V2_P1_TRACKED), p1_tracked=bool(flags & DIRSTATE_V2_P1_TRACKED),
p2_info=bool(flags & DIRSTATE_V2_P2_INFO), p2_info=bool(flags & DIRSTATE_V2_P2_INFO),
has_meaningful_data=has_mode_size, has_meaningful_data=has_mode_size,
has_meaningful_mtime=bool(flags & DIRSTATE_V2_HAS_FILE_MTIME), has_meaningful_mtime=bool(flags & DIRSTATE_V2_HAS_FILE_MTIME),
parentfiledata=(mode, size, mtime), parentfiledata=(mode, size, (mtime_s, mtime_ns)),
) )
@classmethod @classmethod
def from_v1_data(cls, state, mode, size, mtime): def from_v1_data(cls, state, mode, size, mtime):
"""Build a new DirstateItem object from V1 data """Build a new DirstateItem object from V1 data
Since the dirstate-v1 format is frozen, the signature of this function Since the dirstate-v1 format is frozen, the signature of this function
is not expected to change, unlike the __init__ one. is not expected to change, unlike the __init__ one.
return cls(wc_tracked=True, p2_info=True) return cls(wc_tracked=True, p2_info=True)
elif size == NONNORMAL: elif size == NONNORMAL:
return cls(wc_tracked=True, p1_tracked=True) return cls(wc_tracked=True, p1_tracked=True)
elif mtime == AMBIGUOUS_TIME: elif mtime == AMBIGUOUS_TIME:
return cls( return cls(
wc_tracked=True, wc_tracked=True,
p1_tracked=True, p1_tracked=True,
has_meaningful_mtime=False, has_meaningful_mtime=False,
parentfiledata=(mode, size, 42), parentfiledata=(mode, size, (42, 0)),
) )
else: else:
return cls( return cls(
wc_tracked=True, wc_tracked=True,
p1_tracked=True, p1_tracked=True,
parentfiledata=(mode, size, mtime), parentfiledata=(mode, size, (mtime, 0)),
) )
else: else:
raise RuntimeError(b'unknown state: %s' % state) raise RuntimeError(b'unknown state: %s' % state)
def set_possibly_dirty(self): def set_possibly_dirty(self):
"""Mark a file as "possibly dirty" """Mark a file as "possibly dirty"
This means the next status call will have to actually check its content This means the next status call will have to actually check its content
to make sure it is correct. to make sure it is correct.
""" """
self._mtime = None self._mtime_s = None
self._mtime_ns = None
def set_clean(self, mode, size, mtime): def set_clean(self, mode, size, mtime):
"""mark a file as "clean" cancelling potential "possibly dirty call" """mark a file as "clean" cancelling potential "possibly dirty call"
Note: this function is a descendant of `dirstate.normal` and is Note: this function is a descendant of `dirstate.normal` and is
currently expected to be call on "normal" entry only. There are not currently expected to be call on "normal" entry only. There are not
reason for this to not change in the future as long as the ccode is reason for this to not change in the future as long as the ccode is
updated to preserve the proper state of the non-normal files. updated to preserve the proper state of the non-normal files.
""" """
self._wc_tracked = True self._wc_tracked = True
self._p1_tracked = True self._p1_tracked = True
self._mode = mode self._mode = mode
self._size = size self._size = size
self._mtime = mtime self._mtime_s, self._mtime_ns = mtime
def set_tracked(self): def set_tracked(self):
"""mark a file as tracked in the working copy """mark a file as tracked in the working copy
This will ultimately be called by command like `hg add`. This will ultimately be called by command like `hg add`.
""" """
self._wc_tracked = True self._wc_tracked = True
# `set_tracked` is replacing various `normallookup` call. So we mark # `set_tracked` is replacing various `normallookup` call. So we mark
# the files as needing lookup # the files as needing lookup
# #
# Consider dropping this in the future in favor of something less broad. # Consider dropping this in the future in favor of something less broad.
self._mtime = None self._mtime_s = None
self._mtime_ns = None
def set_untracked(self): def set_untracked(self):
"""mark a file as untracked in the working copy """mark a file as untracked in the working copy
This will ultimately be called by command like `hg remove`. This will ultimately be called by command like `hg remove`.
""" """
self._wc_tracked = False self._wc_tracked = False
self._mode = None self._mode = None
self._size = None self._size = None
self._mtime = None self._mtime_s = None
self._mtime_ns = None
def drop_merge_data(self): def drop_merge_data(self):
"""remove all "merge-only" from a DirstateItem """remove all "merge-only" from a DirstateItem
This is to be call by the dirstatemap code when the second parent is dropped This is to be call by the dirstatemap code when the second parent is dropped
""" """
if self._p2_info: if self._p2_info:
self._p2_info = False self._p2_info = False
self._mode = None self._mode = None
self._size = None self._size = None
self._mtime = None self._mtime_s = None
self._mtime_ns = None
@property @property
def mode(self): def mode(self):
return self.v1_mode() return self.v1_mode()
@property @property
def size(self): def size(self):
return self.v1_size() return self.v1_size()
@property @property
def mtime(self): def mtime(self):
return self.v1_mtime() return self.v1_mtime()
def mtime_likely_equal_to(self, other_mtime):
self_sec = self._mtime_s
if self_sec is None:
return False
self_ns = self._mtime_ns
other_sec, other_ns = other_mtime
return self_sec == other_sec and self_ns == other_ns
@property @property
def state(self): def state(self):
""" """
States are: States are:
n normal n normal
m needs merging m needs merging
r marked for removal r marked for removal
a marked for addition a marked for addition
if self._p2_info: if self._p2_info:
flags |= DIRSTATE_V2_P2_INFO flags |= DIRSTATE_V2_P2_INFO
if self._mode is not None and self._size is not None: if self._mode is not None and self._size is not None:
flags |= DIRSTATE_V2_HAS_MODE_AND_SIZE flags |= DIRSTATE_V2_HAS_MODE_AND_SIZE
if self.mode & stat.S_IXUSR: if self.mode & stat.S_IXUSR:
flags |= DIRSTATE_V2_MODE_EXEC_PERM flags |= DIRSTATE_V2_MODE_EXEC_PERM
if stat.S_ISLNK(self.mode): if stat.S_ISLNK(self.mode):
flags |= DIRSTATE_V2_MODE_IS_SYMLINK flags |= DIRSTATE_V2_MODE_IS_SYMLINK
if self._mtime is not None: if self._mtime_s is not None:
flags |= DIRSTATE_V2_HAS_FILE_MTIME flags |= DIRSTATE_V2_HAS_FILE_MTIME
return (flags, self._size or 0, self._mtime or 0) return (flags, self._size or 0, self._mtime_s or 0, self._mtime_ns or 0)
def v1_state(self): def v1_state(self):
"""return a "state" suitable for v1 serialization""" """return a "state" suitable for v1 serialization"""
if not self.any_tracked: if not self.any_tracked:
# the object has no state to record, this is -currently- # the object has no state to record, this is -currently-
# unsupported # unsupported
raise RuntimeError('untracked item') raise RuntimeError('untracked item')
elif self.removed: elif self.removed:
def v1_mtime(self): def v1_mtime(self):
"""return a "mtime" suitable for v1 serialization""" """return a "mtime" suitable for v1 serialization"""
if not self.any_tracked: if not self.any_tracked:
# the object has no state to record, this is -currently- # the object has no state to record, this is -currently-
# unsupported # unsupported
raise RuntimeError('untracked item') raise RuntimeError('untracked item')
elif self.removed: elif self.removed:
return 0 return 0
elif self._mtime is None: elif self._mtime_s is None:
return AMBIGUOUS_TIME return AMBIGUOUS_TIME
elif self._p2_info: elif self._p2_info:
return AMBIGUOUS_TIME return AMBIGUOUS_TIME
elif not self._p1_tracked: elif not self._p1_tracked:
return AMBIGUOUS_TIME return AMBIGUOUS_TIME
else: else:
return self._mtime return self._mtime_s
def need_delay(self, now): def need_delay(self, now):
"""True if the stored mtime would be ambiguous with the current time""" """True if the stored mtime would be ambiguous with the current time"""
return self.v1_state() == b'n' and self.v1_mtime() == now return self.v1_state() == b'n' and self.mtime_likely_equal_to(now)
def gettype(q): def gettype(q):
return int(q & 0xFFFF) return int(q & 0xFFFF)
class BaseIndexObject(object): class BaseIndexObject(object):
# Can I be passed to an algorithme implemented in Rust ? # Can I be passed to an algorithme implemented in Rust ?
if b'\0' in f: if b'\0' in f:
f, c = f.split(b'\0') f, c = f.split(b'\0')
copymap[f] = c copymap[f] = c
dmap[f] = DirstateItem.from_v1_data(*e[:4]) dmap[f] = DirstateItem.from_v1_data(*e[:4])
return parents return parents
def pack_dirstate(dmap, copymap, pl, now): def pack_dirstate(dmap, copymap, pl, now):
now = int(now)
cs = stringio() cs = stringio()
write = cs.write write = cs.write
write(b"".join(pl)) write(b"".join(pl))
for f, e in pycompat.iteritems(dmap): for f, e in pycompat.iteritems(dmap):
if e.need_delay(now): if e.need_delay(now):
# The file was last modified "simultaneously" with the current # The file was last modified "simultaneously" with the current
# write to dirstate (i.e. within the same second for file- # write to dirstate (i.e. within the same second for file-
# systems with a granularity of 1 sec). This commonly happens # systems with a granularity of 1 sec). This commonly happens

rust/hg-core/src/dirstate/entry.rs

use crate::dirstate_tree::on_disk::DirstateV2ParseError; use crate::dirstate_tree::on_disk::DirstateV2ParseError;
use crate::errors::HgError; use crate::errors::HgError;
use bitflags::bitflags; use bitflags::bitflags;
use std::convert::{TryFrom, TryInto}; use std::convert::{TryFrom, TryInto};
use std::fs; use std::fs;
use std::io; use std::io;
use std::time::{SystemTime, UNIX_EPOCH}; use std::time::{SystemTime, UNIX_EPOCH};
#[derive(Copy, Clone, Debug, Eq, PartialEq)] #[derive(Copy, Clone, Debug, Eq, PartialEq)]
pub enum EntryState { pub enum EntryState {
Normal, Normal,
Added, Added,
Removed, Removed,
Merged, Merged,
} }
/// The C implementation uses all signed types. This will be an issue /// `size` and `mtime.seconds` are truncated to 31 bits.
/// either when 4GB+ source files are commonplace or in 2038, whichever ///
/// comes first. /// TODO: double-check status algorithm correctness for files
#[derive(Debug, PartialEq, Copy, Clone)] /// larger than 2 GiB or modified after 2038.
#[derive(Debug, Copy, Clone)]
pub struct DirstateEntry { pub struct DirstateEntry {
pub(crate) flags: Flags, pub(crate) flags: Flags,
mode_size: Option<(u32, u32)>, mode_size: Option<(u32, u32)>,
mtime: Option<u32>, mtime: Option<TruncatedTimestamp>,
} }
bitflags! { bitflags! {
pub(crate) struct Flags: u8 { pub(crate) struct Flags: u8 {
const WDIR_TRACKED = 1 << 0; const WDIR_TRACKED = 1 << 0;
const P1_TRACKED = 1 << 1; const P1_TRACKED = 1 << 1;
const P2_INFO = 1 << 2; const P2_INFO = 1 << 2;
} }
} }
/// A Unix timestamp with nanoseconds precision /// A Unix timestamp with nanoseconds precision
#[derive(Copy, Clone)] #[derive(Debug, Copy, Clone)]
pub struct TruncatedTimestamp { pub struct TruncatedTimestamp {
truncated_seconds: u32, truncated_seconds: u32,
/// Always in the `0 .. 1_000_000_000` range. /// Always in the `0 .. 1_000_000_000` range.
nanoseconds: u32, nanoseconds: u32,
} }
impl TruncatedTimestamp { impl TruncatedTimestamp {
/// Constructs from a timestamp potentially outside of the supported range, /// Constructs from a timestamp potentially outside of the supported range,
pub const SIZE_NON_NORMAL: i32 = -1; pub const SIZE_NON_NORMAL: i32 = -1;
impl DirstateEntry { impl DirstateEntry {
pub fn from_v2_data( pub fn from_v2_data(
wdir_tracked: bool, wdir_tracked: bool,
p1_tracked: bool, p1_tracked: bool,
p2_info: bool, p2_info: bool,
mode_size: Option<(u32, u32)>, mode_size: Option<(u32, u32)>,
mtime: Option<u32>, mtime: Option<TruncatedTimestamp>,
) -> Self { ) -> Self {
if let Some((mode, size)) = mode_size { if let Some((mode, size)) = mode_size {
// TODO: return an error for out of range values? // TODO: return an error for out of range values?
assert!(mode & !RANGE_MASK_31BIT == 0); assert!(mode & !RANGE_MASK_31BIT == 0);
assert!(size & !RANGE_MASK_31BIT == 0); assert!(size & !RANGE_MASK_31BIT == 0);
} }
if let Some(mtime) = mtime {
assert!(mtime & !RANGE_MASK_31BIT == 0);
}
let mut flags = Flags::empty(); let mut flags = Flags::empty();
flags.set(Flags::WDIR_TRACKED, wdir_tracked); flags.set(Flags::WDIR_TRACKED, wdir_tracked);
flags.set(Flags::P1_TRACKED, p1_tracked); flags.set(Flags::P1_TRACKED, p1_tracked);
flags.set(Flags::P2_INFO, p2_info); flags.set(Flags::P2_INFO, p2_info);
Self { Self {
flags, flags,
mode_size, mode_size,
mtime, mtime,
mode_size: Some((mode, size)), mode_size: Some((mode, size)),
mtime: None, mtime: None,
} }
} else { } else {
// TODO:!return an error for negative values? // TODO:!return an error for negative values?
let mode = u32::try_from(mode).unwrap(); let mode = u32::try_from(mode).unwrap();
let size = u32::try_from(size).unwrap(); let size = u32::try_from(size).unwrap();
let mtime = u32::try_from(mtime).unwrap(); let mtime = u32::try_from(mtime).unwrap();
let mtime =
TruncatedTimestamp::from_already_truncated(mtime, 0)
.unwrap();
Self { Self {
flags: Flags::WDIR_TRACKED | Flags::P1_TRACKED, flags: Flags::WDIR_TRACKED | Flags::P1_TRACKED,
mode_size: Some((mode, size)), mode_size: Some((mode, size)),
mtime: Some(mtime), mtime: Some(mtime),
} }
} }
} }
EntryState::Added => Self { EntryState::Added => Self {
self.flags.intersects( self.flags.intersects(
Flags::WDIR_TRACKED | Flags::P1_TRACKED | Flags::P2_INFO, Flags::WDIR_TRACKED | Flags::P1_TRACKED | Flags::P2_INFO,
) )
} }
/// Returns `(wdir_tracked, p1_tracked, p2_info, mode_size, mtime)` /// Returns `(wdir_tracked, p1_tracked, p2_info, mode_size, mtime)`
pub(crate) fn v2_data( pub(crate) fn v2_data(
&self, &self,
) -> (bool, bool, bool, Option<(u32, u32)>, Option<u32>) { ) -> (
bool,
bool,
bool,
Option<(u32, u32)>,
Option<TruncatedTimestamp>,
) {
if !self.any_tracked() { if !self.any_tracked() {
// TODO: return an Option instead? // TODO: return an Option instead?
panic!("Accessing v1_state of an untracked DirstateEntry") panic!("Accessing v1_state of an untracked DirstateEntry")
} }
let wdir_tracked = self.flags.contains(Flags::WDIR_TRACKED); let wdir_tracked = self.flags.contains(Flags::WDIR_TRACKED);
let p1_tracked = self.flags.contains(Flags::P1_TRACKED); let p1_tracked = self.flags.contains(Flags::P1_TRACKED);
let p2_info = self.flags.contains(Flags::P2_INFO); let p2_info = self.flags.contains(Flags::P2_INFO);
let mode_size = self.mode_size; let mode_size = self.mode_size;
} }
if self.removed() { if self.removed() {
0 0
} else if self.flags.contains(Flags::P2_INFO) { } else if self.flags.contains(Flags::P2_INFO) {
MTIME_UNSET MTIME_UNSET
} else if !self.flags.contains(Flags::P1_TRACKED) { } else if !self.flags.contains(Flags::P1_TRACKED) {
MTIME_UNSET MTIME_UNSET
} else if let Some(mtime) = self.mtime { } else if let Some(mtime) = self.mtime {
i32::try_from(mtime).unwrap() i32::try_from(mtime.truncated_seconds()).unwrap()
} else { } else {
MTIME_UNSET MTIME_UNSET
} }
} }
// TODO: return `Option<EntryState>`? None when `!self.any_tracked` // TODO: return `Option<EntryState>`? None when `!self.any_tracked`
pub fn state(&self) -> EntryState { pub fn state(&self) -> EntryState {
self.v1_state() self.v1_state()
self.v1_size() self.v1_size()
} }
// TODO: return Option? // TODO: return Option?
pub fn mtime(&self) -> i32 { pub fn mtime(&self) -> i32 {
self.v1_mtime() self.v1_mtime()
} }
pub fn truncated_mtime(&self) -> Option<TruncatedTimestamp> {
self.mtime
}
pub fn drop_merge_data(&mut self) { pub fn drop_merge_data(&mut self) {
if self.flags.contains(Flags::P2_INFO) { if self.flags.contains(Flags::P2_INFO) {
self.flags.remove(Flags::P2_INFO); self.flags.remove(Flags::P2_INFO);
self.mode_size = None; self.mode_size = None;
self.mtime = None; self.mtime = None;
} }
} }
pub fn set_possibly_dirty(&mut self) { pub fn set_possibly_dirty(&mut self) {
self.mtime = None self.mtime = None
} }
pub fn set_clean(&mut self, mode: u32, size: u32, mtime: u32) { pub fn set_clean(
&mut self,
mode: u32,
size: u32,
mtime: TruncatedTimestamp,
) {
let size = size & RANGE_MASK_31BIT; let size = size & RANGE_MASK_31BIT;
let mtime = mtime & RANGE_MASK_31BIT;
self.flags.insert(Flags::WDIR_TRACKED | Flags::P1_TRACKED); self.flags.insert(Flags::WDIR_TRACKED | Flags::P1_TRACKED);
self.mode_size = Some((mode, size)); self.mode_size = Some((mode, size));
self.mtime = Some(mtime); self.mtime = Some(mtime);
} }
pub fn set_tracked(&mut self) { pub fn set_tracked(&mut self) {
self.flags.insert(Flags::WDIR_TRACKED); self.flags.insert(Flags::WDIR_TRACKED);
// `set_tracked` is replacing various `normallookup` call. So we mark // `set_tracked` is replacing various `normallookup` call. So we mark
} }
/// Returns a `(state, mode, size, mtime)` tuple as for /// Returns a `(state, mode, size, mtime)` tuple as for
/// `DirstateMapMethods::debug_iter`. /// `DirstateMapMethods::debug_iter`.
pub fn debug_tuple(&self) -> (u8, i32, i32, i32) { pub fn debug_tuple(&self) -> (u8, i32, i32, i32) {
(self.state().into(), self.mode(), self.size(), self.mtime()) (self.state().into(), self.mode(), self.size(), self.mtime())
} }
pub fn mtime_is_ambiguous(&self, now: i32) -> bool { pub fn mtime_is_ambiguous(&self, now: TruncatedTimestamp) -> bool {
self.state() == EntryState::Normal && self.mtime() == now if let Some(mtime) = self.mtime {
self.state() == EntryState::Normal && mtime.very_likely_equal(now)
} else {
false
}
} }
pub fn clear_ambiguous_mtime(&mut self, now: i32) -> bool { pub fn clear_ambiguous_mtime(&mut self, now: TruncatedTimestamp) -> bool {
let ambiguous = self.mtime_is_ambiguous(now); let ambiguous = self.mtime_is_ambiguous(now);
if ambiguous { if ambiguous {
// The file was last modified "simultaneously" with the current // The file was last modified "simultaneously" with the current
// write to dirstate (i.e. within the same second for file- // write to dirstate (i.e. within the same second for file-
// systems with a granularity of 1 sec). This commonly happens // systems with a granularity of 1 sec). This commonly happens
// for at least a couple of files on 'update'. // for at least a couple of files on 'update'.
// The user could change the file without changing its size // The user could change the file without changing its size
// within the same second. Invalidate the file's mtime in // within the same second. Invalidate the file's mtime in

rust/hg-core/src/dirstate/parsers.rs

packed.write_i32::<BigEndian>(mtime).unwrap(); packed.write_i32::<BigEndian>(mtime).unwrap();
packed.write_i32::<BigEndian>(length as i32).unwrap(); packed.write_i32::<BigEndian>(length as i32).unwrap();
packed.extend(filename.as_bytes()); packed.extend(filename.as_bytes());
if let Some(source) = copy_source { if let Some(source) = copy_source {
packed.push(b'\0'); packed.push(b'\0');
packed.extend(source.as_bytes()); packed.extend(source.as_bytes());
} }
} }
/// Seconds since the Unix epoch
pub struct Timestamp(pub i64);

rust/hg-core/src/dirstate/status.rs

// status.rs // status.rs
// //
// Copyright 2019 Raphaël Gomès <rgomes@octobus.net> // Copyright 2019 Raphaël Gomès <rgomes@octobus.net>
// //
// This software may be used and distributed according to the terms of the // This software may be used and distributed according to the terms of the
// GNU General Public License version 2 or any later version. // GNU General Public License version 2 or any later version.
//! Rust implementation of dirstate.status (dirstate.py). //! Rust implementation of dirstate.status (dirstate.py).
//! It is currently missing a lot of functionality compared to the Python one //! It is currently missing a lot of functionality compared to the Python one
//! and will only be triggered in narrow cases. //! and will only be triggered in narrow cases.
use crate::dirstate_tree::on_disk::DirstateV2ParseError; use crate::dirstate_tree::on_disk::DirstateV2ParseError;
use crate::{ use crate::{
dirstate::TruncatedTimestamp,
utils::hg_path::{HgPath, HgPathError}, utils::hg_path::{HgPath, HgPathError},
PatternError, PatternError,
}; };
use std::{borrow::Cow, fmt}; use std::{borrow::Cow, fmt};
/// Wrong type of file from a `BadMatch` /// Wrong type of file from a `BadMatch`
/// Note: a lot of those don't exist on all platforms. /// Note: a lot of those don't exist on all platforms.
/// the dirstate/explicit) paths, this comes up a lot. /// the dirstate/explicit) paths, this comes up a lot.
pub type HgPathCow<'a> = Cow<'a, HgPath>; pub type HgPathCow<'a> = Cow<'a, HgPath>;
#[derive(Debug, Copy, Clone)] #[derive(Debug, Copy, Clone)]
pub struct StatusOptions { pub struct StatusOptions {
/// Remember the most recent modification timeslot for status, to make /// Remember the most recent modification timeslot for status, to make
/// sure we won't miss future size-preserving file content modifications /// sure we won't miss future size-preserving file content modifications
/// that happen within the same timeslot. /// that happen within the same timeslot.
pub last_normal_time: i64, pub last_normal_time: TruncatedTimestamp,
/// Whether we are on a filesystem with UNIX-like exec flags /// Whether we are on a filesystem with UNIX-like exec flags
pub check_exec: bool, pub check_exec: bool,
pub list_clean: bool, pub list_clean: bool,
pub list_unknown: bool, pub list_unknown: bool,
pub list_ignored: bool, pub list_ignored: bool,
/// Whether to collect traversed dirs for applying a callback later. /// Whether to collect traversed dirs for applying a callback later.
/// Used by `hg purge` for example. /// Used by `hg purge` for example.
pub collect_traversed_dirs: bool, pub collect_traversed_dirs: bool,

rust/hg-core/src/dirstate_tree/dirstate_map.rs

use bytes_cast::BytesCast; use bytes_cast::BytesCast;
use micro_timer::timed; use micro_timer::timed;
use std::borrow::Cow; use std::borrow::Cow;
use std::convert::TryInto;
use std::path::PathBuf; use std::path::PathBuf;
use super::on_disk; use super::on_disk;
use super::on_disk::DirstateV2ParseError; use super::on_disk::DirstateV2ParseError;
use super::owning::OwningDirstateMap; use super::owning::OwningDirstateMap;
use super::path_with_basename::WithBasename; use super::path_with_basename::WithBasename;
use crate::dirstate::parsers::pack_entry; use crate::dirstate::parsers::pack_entry;
use crate::dirstate::parsers::packed_entry_size; use crate::dirstate::parsers::packed_entry_size;
use crate::dirstate::parsers::parse_dirstate_entries; use crate::dirstate::parsers::parse_dirstate_entries;
use crate::dirstate::parsers::Timestamp;
use crate::dirstate::CopyMapIter; use crate::dirstate::CopyMapIter;
use crate::dirstate::StateMapIter; use crate::dirstate::StateMapIter;
use crate::dirstate::TruncatedTimestamp; use crate::dirstate::TruncatedTimestamp;
use crate::dirstate::SIZE_FROM_OTHER_PARENT; use crate::dirstate::SIZE_FROM_OTHER_PARENT;
use crate::dirstate::SIZE_NON_NORMAL; use crate::dirstate::SIZE_NON_NORMAL;
use crate::matchers::Matcher; use crate::matchers::Matcher;
use crate::utils::hg_path::{HgPath, HgPathBuf}; use crate::utils::hg_path::{HgPath, HgPathBuf};
use crate::DirstateEntry; use crate::DirstateEntry;
Ok(false) Ok(false)
} }
} }
#[timed] #[timed]
pub fn pack_v1( pub fn pack_v1(
&mut self, &mut self,
parents: DirstateParents, parents: DirstateParents,
now: Timestamp, now: TruncatedTimestamp,
) -> Result<Vec<u8>, DirstateError> { ) -> Result<Vec<u8>, DirstateError> {
let map = self.get_map_mut(); let map = self.get_map_mut();
let now: i32 = now.0.try_into().expect("time overflow");
let mut ambiguous_mtimes = Vec::new(); let mut ambiguous_mtimes = Vec::new();
// Optizimation (to be measured?): pre-compute size to avoid `Vec` // Optizimation (to be measured?): pre-compute size to avoid `Vec`
// reallocations // reallocations
let mut size = parents.as_bytes().len(); let mut size = parents.as_bytes().len();
for node in map.iter_nodes() { for node in map.iter_nodes() {
let node = node?; let node = node?;
if let Some(entry) = node.entry()? { if let Some(entry) = node.entry()? {
size += packed_entry_size( size += packed_entry_size(
/// Returns new data and metadata together with whether that data should be /// Returns new data and metadata together with whether that data should be
/// appended to the existing data file whose content is at /// appended to the existing data file whose content is at
/// `map.on_disk` (true), instead of written to a new data file /// `map.on_disk` (true), instead of written to a new data file
/// (false). /// (false).
#[timed] #[timed]
pub fn pack_v2( pub fn pack_v2(
&mut self, &mut self,
now: Timestamp, now: TruncatedTimestamp,
can_append: bool, can_append: bool,
) -> Result<(Vec<u8>, Vec<u8>, bool), DirstateError> { ) -> Result<(Vec<u8>, Vec<u8>, bool), DirstateError> {
let map = self.get_map_mut(); let map = self.get_map_mut();
// TODO:!how do we want to handle this in 2038?
let now: i32 = now.0.try_into().expect("time overflow");
let mut paths = Vec::new(); let mut paths = Vec::new();
for node in map.iter_nodes() { for node in map.iter_nodes() {
let node = node?; let node = node?;
if let Some(entry) = node.entry()? { if let Some(entry) = node.entry()? {
if entry.mtime_is_ambiguous(now) { if entry.mtime_is_ambiguous(now) {
paths.push( paths.push(
node.full_path_borrowed(map.on_disk)? node.full_path_borrowed(map.on_disk)?
.detach_from_tree(), .detach_from_tree(),

rust/hg-core/src/dirstate_tree/on_disk.rs

Flags::WDIR_TRACKED | Flags::P1_TRACKED | Flags::P2_INFO, Flags::WDIR_TRACKED | Flags::P1_TRACKED | Flags::P2_INFO,
) )
} }
pub(super) fn node_data( pub(super) fn node_data(
&self, &self,
) -> Result<dirstate_map::NodeData, DirstateV2ParseError> { ) -> Result<dirstate_map::NodeData, DirstateV2ParseError> {
if self.has_entry() { if self.has_entry() {
Ok(dirstate_map::NodeData::Entry(self.assume_entry())) Ok(dirstate_map::NodeData::Entry(self.assume_entry()?))
} else if let Some(mtime) = self.cached_directory_mtime()? { } else if let Some(mtime) = self.cached_directory_mtime()? {
Ok(dirstate_map::NodeData::CachedDirectory { mtime }) Ok(dirstate_map::NodeData::CachedDirectory { mtime })
} else { } else {
Ok(dirstate_map::NodeData::None) Ok(dirstate_map::NodeData::None)
} }
} }
pub(super) fn cached_directory_mtime( pub(super) fn cached_directory_mtime(
let permisions = if self.flags().contains(Flags::MODE_EXEC_PERM) { let permisions = if self.flags().contains(Flags::MODE_EXEC_PERM) {
0o755 0o755
} else { } else {
0o644 0o644
}; };
file_type | permisions file_type | permisions
} }
fn assume_entry(&self) -> DirstateEntry { fn assume_entry(&self) -> Result<DirstateEntry, DirstateV2ParseError> {
// TODO: convert through raw bits instead? // TODO: convert through raw bits instead?
let wdir_tracked = self.flags().contains(Flags::WDIR_TRACKED); let wdir_tracked = self.flags().contains(Flags::WDIR_TRACKED);
let p1_tracked = self.flags().contains(Flags::P1_TRACKED); let p1_tracked = self.flags().contains(Flags::P1_TRACKED);
let p2_info = self.flags().contains(Flags::P2_INFO); let p2_info = self.flags().contains(Flags::P2_INFO);
let mode_size = if self.flags().contains(Flags::HAS_MODE_AND_SIZE) { let mode_size = if self.flags().contains(Flags::HAS_MODE_AND_SIZE) {
Some((self.synthesize_unix_mode(), self.size.into())) Some((self.synthesize_unix_mode(), self.size.into()))
} else { } else {
None None
}; };
let mtime = if self.flags().contains(Flags::HAS_FILE_MTIME) { let mtime = if self.flags().contains(Flags::HAS_FILE_MTIME) {
Some(self.mtime.truncated_seconds.into()) Some(self.mtime.try_into()?)
} else { } else {
None None
}; };
DirstateEntry::from_v2_data( Ok(DirstateEntry::from_v2_data(
wdir_tracked, wdir_tracked,
p1_tracked, p1_tracked,
p2_info, p2_info,
mode_size, mode_size,
mtime, mtime,
) ))
} }
pub(super) fn entry( pub(super) fn entry(
&self, &self,
) -> Result<Option<DirstateEntry>, DirstateV2ParseError> { ) -> Result<Option<DirstateEntry>, DirstateV2ParseError> {
if self.has_entry() { if self.has_entry() {
Ok(Some(self.assume_entry())) Ok(Some(self.assume_entry()?))
} else { } else {
Ok(None) Ok(None)
} }
} }
pub(super) fn children<'on_disk>( pub(super) fn children<'on_disk>(
&self, &self,
on_disk: &'on_disk [u8], on_disk: &'on_disk [u8],
flags.set(Flags::MODE_IS_SYMLINK, is_symlink); flags.set(Flags::MODE_IS_SYMLINK, is_symlink);
flags.insert(Flags::HAS_MODE_AND_SIZE); flags.insert(Flags::HAS_MODE_AND_SIZE);
s.into() s.into()
} else { } else {
0.into() 0.into()
}; };
let mtime = if let Some(m) = mtime_opt { let mtime = if let Some(m) = mtime_opt {
flags.insert(Flags::HAS_FILE_MTIME); flags.insert(Flags::HAS_FILE_MTIME);
PackedTruncatedTimestamp { m.into()
truncated_seconds: m.into(),
nanoseconds: 0.into(),
}
} else { } else {
PackedTruncatedTimestamp::null() PackedTruncatedTimestamp::null()
}; };
(flags, size, mtime) (flags, size, mtime)
} }
} }
fn read_hg_path( fn read_hg_path(

rust/hg-core/src/dirstate_tree/status.rs

self.outcome self.outcome
.lock() .lock()
.unwrap() .unwrap()
.modified .modified
.push(hg_path.detach_from_tree()) .push(hg_path.detach_from_tree())
} else { } else {
let mtime = mtime_seconds(fs_metadata); let mtime = mtime_seconds(fs_metadata);
if truncate_i64(mtime) != entry.mtime() if truncate_i64(mtime) != entry.mtime()
|| mtime == self.options.last_normal_time || mtime
== self.options.last_normal_time.truncated_seconds() as i64
{ {
self.outcome self.outcome
.lock() .lock()
.unwrap() .unwrap()
.unsure .unsure
.push(hg_path.detach_from_tree()) .push(hg_path.detach_from_tree())
} else if self.options.list_clean { } else if self.options.list_clean {
self.outcome self.outcome

rust/hg-cpython/src/dirstate.rs

py_fn!( py_fn!(
py, py,
status_wrapper( status_wrapper(
dmap: DirstateMap, dmap: DirstateMap,
root_dir: PyObject, root_dir: PyObject,
matcher: PyObject, matcher: PyObject,
ignorefiles: PyList, ignorefiles: PyList,
check_exec: bool, check_exec: bool,
last_normal_time: i64, last_normal_time: (u32, u32),
list_clean: bool, list_clean: bool,
list_ignored: bool, list_ignored: bool,
list_unknown: bool, list_unknown: bool,
collect_traversed_dirs: bool collect_traversed_dirs: bool
) )
), ),
)?; )?;
let sys = PyModule::import(py, "sys")?; let sys = PyModule::import(py, "sys")?;
let sys_modules: PyDict = sys.get(py, "modules")?.extract(py)?; let sys_modules: PyDict = sys.get(py, "modules")?.extract(py)?;
sys_modules.set_item(py, dotted_name, &m)?; sys_modules.set_item(py, dotted_name, &m)?;
Ok(m) Ok(m)
} }

rust/hg-cpython/src/dirstate/dirstate_map.rs

use cpython::{ use cpython::{
exc, PyBool, PyBytes, PyClone, PyDict, PyErr, PyList, PyNone, PyObject, exc, PyBool, PyBytes, PyClone, PyDict, PyErr, PyList, PyNone, PyObject,
PyResult, Python, PythonObject, ToPyObject, UnsafePyLeaked, PyResult, Python, PythonObject, ToPyObject, UnsafePyLeaked,
}; };
use crate::{ use crate::{
dirstate::copymap::{CopyMap, CopyMapItemsIterator, CopyMapKeysIterator}, dirstate::copymap::{CopyMap, CopyMapItemsIterator, CopyMapKeysIterator},
dirstate::item::DirstateItem, dirstate::item::{timestamp, DirstateItem},
pybytes_deref::PyBytesDeref, pybytes_deref::PyBytesDeref,
}; };
use hg::{ use hg::{
dirstate::parsers::Timestamp,
dirstate::StateMapIter, dirstate::StateMapIter,
dirstate_tree::dirstate_map::DirstateMap as TreeDirstateMap, dirstate_tree::dirstate_map::DirstateMap as TreeDirstateMap,
dirstate_tree::on_disk::DirstateV2ParseError, dirstate_tree::on_disk::DirstateV2ParseError,
dirstate_tree::owning::OwningDirstateMap, dirstate_tree::owning::OwningDirstateMap,
revlog::Node, revlog::Node,
utils::files::normalize_case, utils::files::normalize_case,
utils::hg_path::{HgPath, HgPathBuf}, utils::hg_path::{HgPath, HgPathBuf},
DirstateEntry, DirstateError, DirstateParents, EntryState, DirstateEntry, DirstateError, DirstateParents, EntryState,
})? })?
.to_py_object(py)) .to_py_object(py))
} }
def write_v1( def write_v1(
&self, &self,
p1: PyObject, p1: PyObject,
p2: PyObject, p2: PyObject,
now: PyObject now: (u32, u32)
) -> PyResult<PyBytes> { ) -> PyResult<PyBytes> {
let now = Timestamp(now.extract(py)?); let now = timestamp(py, now)?;
let mut inner = self.inner(py).borrow_mut(); let mut inner = self.inner(py).borrow_mut();
let parents = DirstateParents { let parents = DirstateParents {
p1: extract_node_id(py, &p1)?, p1: extract_node_id(py, &p1)?,
p2: extract_node_id(py, &p2)?, p2: extract_node_id(py, &p2)?,
}; };
let result = inner.pack_v1(parents, now); let result = inner.pack_v1(parents, now);
match result { match result {
Ok(packed) => Ok(PyBytes::new(py, &packed)), Ok(packed) => Ok(PyBytes::new(py, &packed)),
Err(_) => Err(PyErr::new::<exc::OSError, _>( Err(_) => Err(PyErr::new::<exc::OSError, _>(
py, py,
"Dirstate error".to_string(), "Dirstate error".to_string(),
)), )),
} }
} }
/// Returns new data together with whether that data should be appended to /// Returns new data together with whether that data should be appended to
/// the existing data file whose content is at `self.on_disk` (True), /// the existing data file whose content is at `self.on_disk` (True),
/// instead of written to a new data file (False). /// instead of written to a new data file (False).
def write_v2( def write_v2(
&self, &self,
now: PyObject, now: (u32, u32),
can_append: bool, can_append: bool,
) -> PyResult<PyObject> { ) -> PyResult<PyObject> {
let now = Timestamp(now.extract(py)?); let now = timestamp(py, now)?;
let mut inner = self.inner(py).borrow_mut(); let mut inner = self.inner(py).borrow_mut();
let result = inner.pack_v2(now, can_append); let result = inner.pack_v2(now, can_append);
match result { match result {
Ok((packed, tree_metadata, append)) => { Ok((packed, tree_metadata, append)) => {
let packed = PyBytes::new(py, &packed); let packed = PyBytes::new(py, &packed);
let tree_metadata = PyBytes::new(py, &tree_metadata); let tree_metadata = PyBytes::new(py, &tree_metadata);
let tuple = (packed, tree_metadata, append); let tuple = (packed, tree_metadata, append);

rust/hg-cpython/src/dirstate/item.rs

use cpython::exc; use cpython::exc;
use cpython::PyBytes; use cpython::PyBytes;
use cpython::PyErr; use cpython::PyErr;
use cpython::PyNone; use cpython::PyNone;
use cpython::PyObject; use cpython::PyObject;
use cpython::PyResult; use cpython::PyResult;
use cpython::Python; use cpython::Python;
use cpython::PythonObject; use cpython::PythonObject;
use hg::dirstate::DirstateEntry; use hg::dirstate::DirstateEntry;
use hg::dirstate::EntryState; use hg::dirstate::EntryState;
use hg::dirstate::TruncatedTimestamp;
use std::cell::Cell; use std::cell::Cell;
use std::convert::TryFrom; use std::convert::TryFrom;
py_class!(pub class DirstateItem |py| { py_class!(pub class DirstateItem |py| {
data entry: Cell<DirstateEntry>; data entry: Cell<DirstateEntry>;
def __new__( def __new__(
_cls, _cls,
wc_tracked: bool = false, wc_tracked: bool = false,
p1_tracked: bool = false, p1_tracked: bool = false,
p2_info: bool = false, p2_info: bool = false,
has_meaningful_data: bool = true, has_meaningful_data: bool = true,
has_meaningful_mtime: bool = true, has_meaningful_mtime: bool = true,
parentfiledata: Option<(u32, u32, u32)> = None, parentfiledata: Option<(u32, u32, (u32, u32))> = None,
) -> PyResult<DirstateItem> { ) -> PyResult<DirstateItem> {
let mut mode_size_opt = None; let mut mode_size_opt = None;
let mut mtime_opt = None; let mut mtime_opt = None;
if let Some((mode, size, mtime)) = parentfiledata { if let Some((mode, size, mtime)) = parentfiledata {
if has_meaningful_data { if has_meaningful_data {
mode_size_opt = Some((mode, size)) mode_size_opt = Some((mode, size))
} }
if has_meaningful_mtime { if has_meaningful_mtime {
mtime_opt = Some(mtime) mtime_opt = Some(timestamp(py, mtime)?)
} }
} }
let entry = DirstateEntry::from_v2_data( let entry = DirstateEntry::from_v2_data(
wc_tracked, p1_tracked, p2_info, mode_size_opt, mtime_opt, wc_tracked, p1_tracked, p2_info, mode_size_opt, mtime_opt,
); );
DirstateItem::create_instance(py, Cell::new(entry)) DirstateItem::create_instance(py, Cell::new(entry))
} }
Ok(size) Ok(size)
} }
def v1_mtime(&self) -> PyResult<i32> { def v1_mtime(&self) -> PyResult<i32> {
let (_state, _mode, _size, mtime) = self.entry(py).get().v1_data(); let (_state, _mode, _size, mtime) = self.entry(py).get().v1_data();
Ok(mtime) Ok(mtime)
} }
def need_delay(&self, now: i32) -> PyResult<bool> { def need_delay(&self, now: (u32, u32)) -> PyResult<bool> {
let now = timestamp(py, now)?;
Ok(self.entry(py).get().mtime_is_ambiguous(now)) Ok(self.entry(py).get().mtime_is_ambiguous(now))
} }
def mtime_likely_equal_to(&self, other: (u32, u32)) -> PyResult<bool> {
if let Some(mtime) = self.entry(py).get().truncated_mtime() {
Ok(mtime.very_likely_equal(timestamp(py, other)?))
} else {
Ok(false)
}
}
@classmethod @classmethod
def from_v1_data( def from_v1_data(
_cls, _cls,
state: PyBytes, state: PyBytes,
mode: i32, mode: i32,
size: i32, size: i32,
mtime: i32, mtime: i32,
) -> PyResult<Self> { ) -> PyResult<Self> {
self.update(py, |entry| entry.drop_merge_data()); self.update(py, |entry| entry.drop_merge_data());
Ok(PyNone) Ok(PyNone)
} }
def set_clean( def set_clean(
&self, &self,
mode: u32, mode: u32,
size: u32, size: u32,
mtime: u32, mtime: (u32, u32),
) -> PyResult<PyNone> { ) -> PyResult<PyNone> {
let mtime = timestamp(py, mtime)?;
self.update(py, |entry| entry.set_clean(mode, size, mtime)); self.update(py, |entry| entry.set_clean(mode, size, mtime));
Ok(PyNone) Ok(PyNone)
} }
def set_possibly_dirty(&self) -> PyResult<PyNone> { def set_possibly_dirty(&self) -> PyResult<PyNone> {
self.update(py, |entry| entry.set_possibly_dirty()); self.update(py, |entry| entry.set_possibly_dirty());
Ok(PyNone) Ok(PyNone)
} }
// TODO: Use https://doc.rust-lang.org/std/cell/struct.Cell.html#method.update instead when it’s stable // TODO: Use https://doc.rust-lang.org/std/cell/struct.Cell.html#method.update instead when it’s stable
pub fn update(&self, py: Python<'_>, f: impl FnOnce(&mut DirstateEntry)) { pub fn update(&self, py: Python<'_>, f: impl FnOnce(&mut DirstateEntry)) {
let mut entry = self.entry(py).get(); let mut entry = self.entry(py).get();
f(&mut entry); f(&mut entry);
self.entry(py).set(entry) self.entry(py).set(entry)
} }
} }
pub(crate) fn timestamp(
py: Python<'_>,
(s, ns): (u32, u32),
) -> PyResult<TruncatedTimestamp> {
TruncatedTimestamp::from_already_truncated(s, ns).map_err(|_| {
PyErr::new::<exc::ValueError, _>(
py,
"expected mtime truncated to 31 bits",
)
})
}

rust/hg-cpython/src/dirstate/status.rs

// status.rs // status.rs
// //
// Copyright 2019, Raphaël Gomès <rgomes@octobus.net> // Copyright 2019, Raphaël Gomès <rgomes@octobus.net>
// //
// This software may be used and distributed according to the terms of the // This software may be used and distributed according to the terms of the
// GNU General Public License version 2 or any later version. // GNU General Public License version 2 or any later version.
//! Bindings for the `hg::status` module provided by the //! Bindings for the `hg::status` module provided by the
//! `hg-core` crate. From Python, this will be seen as //! `hg-core` crate. From Python, this will be seen as
//! `rustext.dirstate.status`. //! `rustext.dirstate.status`.
use crate::dirstate::item::timestamp;
use crate::{dirstate::DirstateMap, exceptions::FallbackError}; use crate::{dirstate::DirstateMap, exceptions::FallbackError};
use cpython::exc::OSError; use cpython::exc::OSError;
use cpython::{ use cpython::{
exc::ValueError, ObjectProtocol, PyBytes, PyErr, PyList, PyObject, exc::ValueError, ObjectProtocol, PyBytes, PyErr, PyList, PyObject,
PyResult, PyTuple, Python, PythonObject, ToPyObject, PyResult, PyTuple, Python, PythonObject, ToPyObject,
}; };
use hg::{ use hg::{
matchers::{AlwaysMatcher, FileMatcher, IncludeMatcher}, matchers::{AlwaysMatcher, FileMatcher, IncludeMatcher},
pub fn status_wrapper( pub fn status_wrapper(
py: Python, py: Python,
dmap: DirstateMap, dmap: DirstateMap,
matcher: PyObject, matcher: PyObject,
root_dir: PyObject, root_dir: PyObject,
ignore_files: PyList, ignore_files: PyList,
check_exec: bool, check_exec: bool,
last_normal_time: i64, last_normal_time: (u32, u32),
list_clean: bool, list_clean: bool,
list_ignored: bool, list_ignored: bool,
list_unknown: bool, list_unknown: bool,
collect_traversed_dirs: bool, collect_traversed_dirs: bool,
) -> PyResult<PyTuple> { ) -> PyResult<PyTuple> {
let last_normal_time = timestamp(py, last_normal_time)?;
let bytes = root_dir.extract::<PyBytes>(py)?; let bytes = root_dir.extract::<PyBytes>(py)?;
let root_dir = get_path_from_bytes(bytes.data(py)); let root_dir = get_path_from_bytes(bytes.data(py));
let dmap: DirstateMap = dmap.to_py_object(py); let dmap: DirstateMap = dmap.to_py_object(py);
let mut dmap = dmap.get_inner_mut(py); let mut dmap = dmap.get_inner_mut(py);
let ignore_files: PyResult<Vec<_>> = ignore_files let ignore_files: PyResult<Vec<_>> = ignore_files
.iter(py) .iter(py)

rust/rhg/src/commands/status.rs

// status.rs // status.rs
// //
// Copyright 2020, Georges Racinet <georges.racinets@octobus.net> // Copyright 2020, Georges Racinet <georges.racinets@octobus.net>
// //
// This software may be used and distributed according to the terms of the // This software may be used and distributed according to the terms of the
// GNU General Public License version 2 or any later version. // GNU General Public License version 2 or any later version.
use crate::error::CommandError; use crate::error::CommandError;
use crate::ui::{Ui, UiError}; use crate::ui::{Ui, UiError};
use crate::utils::path_utils::relativize_paths; use crate::utils::path_utils::relativize_paths;
use clap::{Arg, SubCommand}; use clap::{Arg, SubCommand};
use hg; use hg;
use hg::config::Config; use hg::config::Config;
use hg::dirstate::TruncatedTimestamp;
use hg::errors::HgError; use hg::errors::HgError;
use hg::manifest::Manifest; use hg::manifest::Manifest;
use hg::matchers::AlwaysMatcher; use hg::matchers::AlwaysMatcher;
use hg::repo::Repo; use hg::repo::Repo;
use hg::utils::hg_path::{hg_path_to_os_string, HgPath}; use hg::utils::hg_path::{hg_path_to_os_string, HgPath};
use hg::{HgPathCow, StatusOptions}; use hg::{HgPathCow, StatusOptions};
use log::{info, warn}; use log::{info, warn};
use std::borrow::Cow; use std::borrow::Cow;
let repo = invocation.repo?; let repo = invocation.repo?;
let mut dmap = repo.dirstate_map_mut()?; let mut dmap = repo.dirstate_map_mut()?;
let options = StatusOptions { let options = StatusOptions {
// TODO should be provided by the dirstate parsing and // TODO should be provided by the dirstate parsing and
// hence be stored on dmap. Using a value that assumes we aren't // hence be stored on dmap. Using a value that assumes we aren't
// below the time resolution granularity of the FS and the // below the time resolution granularity of the FS and the
// dirstate. // dirstate.
last_normal_time: 0, last_normal_time: TruncatedTimestamp::new_truncate(0, 0),
// we're currently supporting file systems with exec flags only // we're currently supporting file systems with exec flags only
// anyway // anyway
check_exec: true, check_exec: true,
list_clean: display_states.clean, list_clean: display_states.clean,
list_unknown: display_states.unknown, list_unknown: display_states.unknown,
list_ignored: display_states.ignored, list_ignored: display_states.ignored,
collect_traversed_dirs: false, collect_traversed_dirs: false,
}; };

tests/fakedirstatewritetime.py

from mercurial import ( from mercurial import (
context, context,
dirstate, dirstate,
dirstatemap as dirstatemapmod, dirstatemap as dirstatemapmod,
extensions, extensions,
policy, policy,
registrar, registrar,
) )
from mercurial.dirstateutils import timestamp
from mercurial.utils import dateutil from mercurial.utils import dateutil
try: try:
from mercurial import rustext from mercurial import rustext
rustext.__name__ # force actual import (see hgdemandimport) rustext.__name__ # force actual import (see hgdemandimport)
except ImportError: except ImportError:
rustext = None rustext = None
parsers = policy.importmod('parsers') parsers = policy.importmod('parsers')
has_rust_dirstate = policy.importrust('dirstate') is not None has_rust_dirstate = policy.importrust('dirstate') is not None
def pack_dirstate(fakenow, orig, dmap, copymap, pl, now): def pack_dirstate(fakenow, orig, dmap, copymap, pl, now):
# execute what original parsers.pack_dirstate should do actually # execute what original parsers.pack_dirstate should do actually
# for consistency # for consistency
actualnow = int(now)
for f, e in dmap.items(): for f, e in dmap.items():
if e.need_delay(actualnow): if e.need_delay(now):
e.set_possibly_dirty() e.set_possibly_dirty()
return orig(dmap, copymap, pl, fakenow) return orig(dmap, copymap, pl, fakenow)
def fakewrite(ui, func): def fakewrite(ui, func):
# fake "now" of 'pack_dirstate' only if it is invoked while 'func' # fake "now" of 'pack_dirstate' only if it is invoked while 'func'
fakenow = ui.config(b'fakedirstatewritetime', b'fakenow') fakenow = ui.config(b'fakedirstatewritetime', b'fakenow')
if not fakenow: if not fakenow:
# Execute original one, if fakenow isn't configured. This is # Execute original one, if fakenow isn't configured. This is
# useful to prevent subrepos from executing replaced one, # useful to prevent subrepos from executing replaced one,
# because replacing 'parsers.pack_dirstate' is also effective # because replacing 'parsers.pack_dirstate' is also effective
# in subrepos. # in subrepos.
return func() return func()
# parsing 'fakenow' in YYYYmmddHHMM format makes comparison between # parsing 'fakenow' in YYYYmmddHHMM format makes comparison between
# 'fakenow' value and 'touch -t YYYYmmddHHMM' argument easy # 'fakenow' value and 'touch -t YYYYmmddHHMM' argument easy
fakenow = dateutil.parsedate(fakenow, [b'%Y%m%d%H%M'])[0] fakenow = dateutil.parsedate(fakenow, [b'%Y%m%d%H%M'])[0]
fakenow = timestamp.timestamp((fakenow, 0))
if has_rust_dirstate: if has_rust_dirstate:
# The Rust implementation does not use public parse/pack dirstate # The Rust implementation does not use public parse/pack dirstate
# to prevent conversion round-trips # to prevent conversion round-trips
orig_dirstatemap_write = dirstatemapmod.dirstatemap.write orig_dirstatemap_write = dirstatemapmod.dirstatemap.write
wrapper = lambda self, tr, st, now: orig_dirstatemap_write( wrapper = lambda self, tr, st, now: orig_dirstatemap_write(
self, tr, st, fakenow self, tr, st, fakenow
) )