view mercurial/cext/charencode.h @ 47120:7109a38830c9

dirstate-tree: Fold "tracked descendants" counter update in main walk

For the purpose of implementing `has_tracked_dir` (which means "has tracked
descendants) without an expensive sub-tree traversal, we maintaing a counter
of tracked descendants on each "directory" node of the tree-shaped dirstate.

Before this changeset, mutating or inserting a node at a given path would
involve:

* Walking the tree from root through ancestors to find the node or the spot
  where to insert it
* Looking at the previous node if any to decide what counter update is needed
* Performing any node mutation
* Walking the tree *again* to update counters in ancestor nodes

When profiling `hg status` on a large repo, this second walk takes times
while loading a the dirstate from disk.

It turns out we have enough information to decide before he first tree walk
what counter update is needed. This changeset merges the two walks, gaining
~10% of the total time for `hg update` (in the same hyperfine benchmark as
the previous changeset).

---

Profiling was done by compiling with this `.cargo/config`:

    [profile.release]
    debug = true

then running with:

    py-spy record -r 500 -n -o /tmp/hg.json --format speedscope -- \
    ./hg status -R $REPO --config experimental.dirstate-tree.in-memory=1

then visualizing the recorded JSON file in https://www.speedscope.app/

Differential Revision: https://phab.mercurial-scm.org/D10554

/*
 charencode.h - miscellaneous character encoding

 This software may be used and distributed according to the terms of
 the GNU General Public License, incorporated herein by reference.
*/

#ifndef _HG_CHARENCODE_H_
#define _HG_CHARENCODE_H_

#include <Python.h>
#include "compat.h"

/* This should be kept in sync with normcasespecs in encoding.py. */
enum normcase_spec {
	NORMCASE_LOWER = -1,
	NORMCASE_UPPER = 1,
	NORMCASE_OTHER = 0
};

PyObject *unhexlify(const char *str, Py_ssize_t len);
PyObject *isasciistr(PyObject *self, PyObject *args);
PyObject *asciilower(PyObject *self, PyObject *args);
PyObject *asciiupper(PyObject *self, PyObject *args);
PyObject *make_file_foldmap(PyObject *self, PyObject *args);
PyObject *jsonescapeu8fast(PyObject *self, PyObject *args);

/* clang-format off */
static const int8_t hextable[256] = {
	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
	 0,  1,  2,  3,  4,  5,  6,  7,  8,  9, -1, -1, -1, -1, -1, -1, /* 0-9 */
	-1, 10, 11, 12, 13, 14, 15, -1, -1, -1, -1, -1, -1, -1, -1, -1, /* A-F */
	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
	-1, 10, 11, 12, 13, 14, 15, -1, -1, -1, -1, -1, -1, -1, -1, -1, /* a-f */
	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1
};
/* clang-format on */

static inline int hexdigit(const char *p, Py_ssize_t off)
{
	int8_t val = hextable[(unsigned char)p[off]];

	if (val >= 0) {
		return val;
	}

	PyErr_SetString(PyExc_ValueError, "input contains non-hex character");
	return 0;
}

#endif /* _HG_CHARENCODE_H_ */