treemanifests: remove _loadalllazy when doing copies
'before' here is https://phab.mercurial-scm.org/D4845 (not the committed/rebased
version)
diff --git:
repo | N | T | before (mean +- stdev) | after (mean +- stdev) | % of before
------+---+---+------------------------+-----------------------+------------
m-u | | | 1.329 s +- 0.011 s | 1.320 s +- 0.010 s | 99.3%
m-u | | x | 1.316 s +- 0.005 s | 1.334 s +- 0.018 s | 101.4%
m-u | x | | 1.330 s +- 0.021 s | 1.322 s +- 0.005 s | 99.4%
m-u | x | x | 87.2 ms +- 0.7 ms | 86.9 ms +- 1.5 ms | 99.7%
l-d-r | | | 203.3 ms +- 7.8 ms | 199.4 ms +- 1.8 ms | 98.1%
l-d-r | | x | 204.6 ms +- 2.8 ms | 201.7 ms +- 2.1 ms | 98.6%
l-d-r | x | | 90.5 ms +- 11.0 ms | 86.2 ms +- 1.0 ms | 95.2%
l-d-r | x | x | 66.3 ms +- 2.0 ms | 66.4 ms +- 0.9 ms | 100.2%
diff -c . --git:
repo | N | T | before (mean +- stdev) | after (mean +- stdev) | % of before
------+---+---+------------------------+-----------------------+------------
m-u | | | 239.4 ms +- 2.0 ms | 241.7 ms +- 4.6 ms | 101.0%
m-u | | x | 128.9 ms +- 1.9 ms | 130.9 ms +- 7.7 ms | 101.6%
m-u | x | | 241.1 ms +- 1.6 ms | 240.1 ms +- 1.4 ms | 99.6%
m-u | x | x | 133.4 ms +- 1.5 ms | 133.4 ms +- 1.2 ms | 100.0%
l-d-r | | | 84.3 ms +- 1.5 ms | 83.5 ms +- 1.0 ms | 99.1%
l-d-r | | x | 200.9 ms +- 6.3 ms | 203.0 ms +- 4.4 ms | 101.0%
l-d-r | x | | 108.1 ms +- 1.4 ms | 108.7 ms +- 2.1 ms | 100.6%
l-d-r | x | x | 190.2 ms +- 4.8 ms | 191.6 ms +- 2.0 ms | 100.7%
rebase -r . --keep -d .^^:
repo | N | T | before (mean +- stdev) | after (mean +- stdev) | % of before
------+---+---+------------------------+-----------------------+------------
m-u | | | 5.655 s +- 0.029 s | 5.640 s +- 0.036 s | 99.7%
m-u | | x | 5.813 s +- 0.038 s | 5.773 s +- 0.028 s | 99.3%
m-u | x | | 5.593 s +- 0.043 s | 5.589 s +- 0.028 s | 99.9%
m-u | x | x | 648.2 ms +- 19.2 ms | 637.3 ms +- 27.7 ms | 98.3%
l-d-r | | | 673.3 ms +- 8.0 ms | 673.2 ms +- 6.8 ms | 100.0%
l-d-r | | x | 6.583 s +- 0.030 s | 5.721 s +- 0.028 s | 86.9% <--
l-d-r | x | | 277.8 ms +- 6.7 ms | 276.0 ms +- 2.7 ms | 99.4%
l-d-r | x | x | 1.692 s +- 0.013 s | 720.9 ms +- 13.3 ms | 42.6% <--
status --change . --copies:
repo | N | T | before (mean +- stdev) | after (mean +- stdev) | % of before
------+---+---+------------------------+-----------------------+------------
m-u | | | 220.9 ms +- 1.6 ms | 219.9 ms +- 2.2 ms | 99.5%
m-u | | x | 109.2 ms +- 1.0 ms | 109.4 ms +- 0.8 ms | 100.2%
m-u | x | | 222.6 ms +- 1.7 ms | 221.4 ms +- 2.1 ms | 99.5%
m-u | x | x | 113.4 ms +- 0.5 ms | 113.1 ms +- 1.1 ms | 99.7%
l-d-r | | | 82.1 ms +- 1.7 ms | 82.1 ms +- 1.2 ms | 100.0%
l-d-r | | x | 199.8 ms +- 4.0 ms | 200.7 ms +- 3.6 ms | 100.5%
l-d-r | x | | 85.4 ms +- 1.5 ms | 85.2 ms +- 0.3 ms | 99.8%
l-d-r | x | x | 202.6 ms +- 4.4 ms | 208.0 ms +- 4.0 ms | 102.7%
status --copies:
repo | N | T | before (mean +- stdev) | after (mean +- stdev) | % of before
------+---+---+------------------------+-----------------------+------------
m-u | | | 1.941 s +- 0.014 s | 1.930 s +- 0.009 s | 99.4%
m-u | | x | 1.924 s +- 0.007 s | 1.950 s +- 0.010 s | 101.4%
m-u | x | | 1.959 s +- 0.085 s | 1.926 s +- 0.009 s | 98.3%
m-u | x | x | 96.2 ms +- 1.0 ms | 96.4 ms +- 0.7 ms | 100.2%
l-d-r | | | 604.4 ms +- 10.6 ms | 602.6 ms +- 7.1 ms | 99.7%
l-d-r | | x | 605.7 ms +- 4.1 ms | 607.4 ms +- 6.1 ms | 100.3%
l-d-r | x | | 182.4 ms +- 1.2 ms | 183.4 ms +- 1.2 ms | 100.5%
l-d-r | x | x | 150.8 ms +- 2.0 ms | 150.6 ms +- 1.0 ms | 99.9%
update $rev^; ~/src/hg/hg{hg}/hg update $rev:
repo | N | T | before (mean +- stdev) | after (mean +- stdev) | % of before
------+---+---+------------------------+-----------------------+------------
m-u | | | 3.185 s +- 0.027 s | 3.181 s +- 0.017 s | 99.9%
m-u | | x | 3.028 s +- 0.021 s | 2.954 s +- 0.010 s | 97.6%
m-u | x | | 3.168 s +- 0.010 s | 3.175 s +- 0.023 s | 100.2%
m-u | x | x | 317.5 ms +- 3.5 ms | 313.2 ms +- 2.9 ms | 98.6%
l-d-r | | | 456.2 ms +- 10.6 ms | 454.4 ms +- 5.8 ms | 99.6%
l-d-r | | x | 9.236 s +- 0.063 s | 757.9 ms +- 9.2 ms | 8.2% <--
l-d-r | x | | 257.6 ms +- 2.3 ms | 261.2 ms +- 1.7 ms | 101.4%
l-d-r | x | x | 1.614 s +- 0.013 s | 478.0 ms +- 14.3 ms | 29.6% <--
Differential Revision: https://phab.mercurial-scm.org/D4875
/*
charencode.c - miscellaneous character encoding
Copyright 2008 Matt Mackall <mpm@selenic.com> and others
This software may be used and distributed according to the terms of
the GNU General Public License, incorporated herein by reference.
*/
#define PY_SSIZE_T_CLEAN
#include <Python.h>
#include <assert.h>
#include "charencode.h"
#include "compat.h"
#include "util.h"
#ifdef IS_PY3K
/* The mapping of Python types is meant to be temporary to get Python
* 3 to compile. We should remove this once Python 3 support is fully
* supported and proper types are used in the extensions themselves. */
#define PyInt_Type PyLong_Type
#define PyInt_AS_LONG PyLong_AS_LONG
#endif
/* clang-format off */
static const char lowertable[128] = {
'\x00', '\x01', '\x02', '\x03', '\x04', '\x05', '\x06', '\x07',
'\x08', '\x09', '\x0a', '\x0b', '\x0c', '\x0d', '\x0e', '\x0f',
'\x10', '\x11', '\x12', '\x13', '\x14', '\x15', '\x16', '\x17',
'\x18', '\x19', '\x1a', '\x1b', '\x1c', '\x1d', '\x1e', '\x1f',
'\x20', '\x21', '\x22', '\x23', '\x24', '\x25', '\x26', '\x27',
'\x28', '\x29', '\x2a', '\x2b', '\x2c', '\x2d', '\x2e', '\x2f',
'\x30', '\x31', '\x32', '\x33', '\x34', '\x35', '\x36', '\x37',
'\x38', '\x39', '\x3a', '\x3b', '\x3c', '\x3d', '\x3e', '\x3f',
'\x40',
'\x61', '\x62', '\x63', '\x64', '\x65', '\x66', '\x67', /* A-G */
'\x68', '\x69', '\x6a', '\x6b', '\x6c', '\x6d', '\x6e', '\x6f', /* H-O */
'\x70', '\x71', '\x72', '\x73', '\x74', '\x75', '\x76', '\x77', /* P-W */
'\x78', '\x79', '\x7a', /* X-Z */
'\x5b', '\x5c', '\x5d', '\x5e', '\x5f',
'\x60', '\x61', '\x62', '\x63', '\x64', '\x65', '\x66', '\x67',
'\x68', '\x69', '\x6a', '\x6b', '\x6c', '\x6d', '\x6e', '\x6f',
'\x70', '\x71', '\x72', '\x73', '\x74', '\x75', '\x76', '\x77',
'\x78', '\x79', '\x7a', '\x7b', '\x7c', '\x7d', '\x7e', '\x7f'
};
static const char uppertable[128] = {
'\x00', '\x01', '\x02', '\x03', '\x04', '\x05', '\x06', '\x07',
'\x08', '\x09', '\x0a', '\x0b', '\x0c', '\x0d', '\x0e', '\x0f',
'\x10', '\x11', '\x12', '\x13', '\x14', '\x15', '\x16', '\x17',
'\x18', '\x19', '\x1a', '\x1b', '\x1c', '\x1d', '\x1e', '\x1f',
'\x20', '\x21', '\x22', '\x23', '\x24', '\x25', '\x26', '\x27',
'\x28', '\x29', '\x2a', '\x2b', '\x2c', '\x2d', '\x2e', '\x2f',
'\x30', '\x31', '\x32', '\x33', '\x34', '\x35', '\x36', '\x37',
'\x38', '\x39', '\x3a', '\x3b', '\x3c', '\x3d', '\x3e', '\x3f',
'\x40', '\x41', '\x42', '\x43', '\x44', '\x45', '\x46', '\x47',
'\x48', '\x49', '\x4a', '\x4b', '\x4c', '\x4d', '\x4e', '\x4f',
'\x50', '\x51', '\x52', '\x53', '\x54', '\x55', '\x56', '\x57',
'\x58', '\x59', '\x5a', '\x5b', '\x5c', '\x5d', '\x5e', '\x5f',
'\x60',
'\x41', '\x42', '\x43', '\x44', '\x45', '\x46', '\x47', /* a-g */
'\x48', '\x49', '\x4a', '\x4b', '\x4c', '\x4d', '\x4e', '\x4f', /* h-o */
'\x50', '\x51', '\x52', '\x53', '\x54', '\x55', '\x56', '\x57', /* p-w */
'\x58', '\x59', '\x5a', /* x-z */
'\x7b', '\x7c', '\x7d', '\x7e', '\x7f'
};
/* 1: no escape, 2: \<c>, 6: \u<x> */
static const uint8_t jsonlentable[256] = {
6, 6, 6, 6, 6, 6, 6, 6, 2, 2, 2, 6, 2, 2, 6, 6, /* b, t, n, f, r */
6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,
1, 1, 2, 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, 2, 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, 6, /* DEL */
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,
};
static const uint8_t jsonparanoidlentable[128] = {
6, 6, 6, 6, 6, 6, 6, 6, 2, 2, 2, 6, 2, 2, 6, 6, /* b, t, n, f, r */
6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,
1, 1, 2, 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, 6, 1, 6, 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, 2, 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, 6, /* DEL */
};
static const char hexchartable[16] = {
'0', '1', '2', '3', '4', '5', '6', '7',
'8', '9', 'a', 'b', 'c', 'd', 'e', 'f',
};
/* clang-format on */
/*
* Turn a hex-encoded string into binary.
*/
PyObject *unhexlify(const char *str, Py_ssize_t len)
{
PyObject *ret;
char *d;
Py_ssize_t i;
ret = PyBytes_FromStringAndSize(NULL, len / 2);
if (!ret)
return NULL;
d = PyBytes_AsString(ret);
for (i = 0; i < len;) {
int hi = hexdigit(str, i++);
int lo = hexdigit(str, i++);
*d++ = (hi << 4) | lo;
}
return ret;
}
PyObject *isasciistr(PyObject *self, PyObject *args)
{
const char *buf;
Py_ssize_t i, len;
if (!PyArg_ParseTuple(args, PY23("s#:isasciistr", "y#:isasciistr"),
&buf, &len))
return NULL;
i = 0;
/* char array in PyStringObject should be at least 4-byte aligned */
if (((uintptr_t)buf & 3) == 0) {
const uint32_t *p = (const uint32_t *)buf;
for (; i < len / 4; i++) {
if (p[i] & 0x80808080U)
Py_RETURN_FALSE;
}
i *= 4;
}
for (; i < len; i++) {
if (buf[i] & 0x80)
Py_RETURN_FALSE;
}
Py_RETURN_TRUE;
}
static inline PyObject *
_asciitransform(PyObject *str_obj, const char table[128], PyObject *fallback_fn)
{
char *str, *newstr;
Py_ssize_t i, len;
PyObject *newobj = NULL;
PyObject *ret = NULL;
str = PyBytes_AS_STRING(str_obj);
len = PyBytes_GET_SIZE(str_obj);
newobj = PyBytes_FromStringAndSize(NULL, len);
if (!newobj)
goto quit;
newstr = PyBytes_AS_STRING(newobj);
for (i = 0; i < len; i++) {
char c = str[i];
if (c & 0x80) {
if (fallback_fn != NULL) {
ret = PyObject_CallFunctionObjArgs(
fallback_fn, str_obj, NULL);
} else {
PyObject *err = PyUnicodeDecodeError_Create(
"ascii", str, len, i, (i + 1),
"unexpected code byte");
PyErr_SetObject(PyExc_UnicodeDecodeError, err);
Py_XDECREF(err);
}
goto quit;
}
newstr[i] = table[(unsigned char)c];
}
ret = newobj;
Py_INCREF(ret);
quit:
Py_XDECREF(newobj);
return ret;
}
PyObject *asciilower(PyObject *self, PyObject *args)
{
PyObject *str_obj;
if (!PyArg_ParseTuple(args, "O!:asciilower", &PyBytes_Type, &str_obj))
return NULL;
return _asciitransform(str_obj, lowertable, NULL);
}
PyObject *asciiupper(PyObject *self, PyObject *args)
{
PyObject *str_obj;
if (!PyArg_ParseTuple(args, "O!:asciiupper", &PyBytes_Type, &str_obj))
return NULL;
return _asciitransform(str_obj, uppertable, NULL);
}
PyObject *make_file_foldmap(PyObject *self, PyObject *args)
{
PyObject *dmap, *spec_obj, *normcase_fallback;
PyObject *file_foldmap = NULL;
enum normcase_spec spec;
PyObject *k, *v;
dirstateTupleObject *tuple;
Py_ssize_t pos = 0;
const char *table;
if (!PyArg_ParseTuple(args, "O!O!O!:make_file_foldmap", &PyDict_Type,
&dmap, &PyInt_Type, &spec_obj, &PyFunction_Type,
&normcase_fallback))
goto quit;
spec = (int)PyInt_AS_LONG(spec_obj);
switch (spec) {
case NORMCASE_LOWER:
table = lowertable;
break;
case NORMCASE_UPPER:
table = uppertable;
break;
case NORMCASE_OTHER:
table = NULL;
break;
default:
PyErr_SetString(PyExc_TypeError, "invalid normcasespec");
goto quit;
}
/* Add some more entries to deal with additions outside this
function. */
file_foldmap = _dict_new_presized((PyDict_Size(dmap) / 10) * 11);
if (file_foldmap == NULL)
goto quit;
while (PyDict_Next(dmap, &pos, &k, &v)) {
if (!dirstate_tuple_check(v)) {
PyErr_SetString(PyExc_TypeError,
"expected a dirstate tuple");
goto quit;
}
tuple = (dirstateTupleObject *)v;
if (tuple->state != 'r') {
PyObject *normed;
if (table != NULL) {
normed = _asciitransform(k, table,
normcase_fallback);
} else {
normed = PyObject_CallFunctionObjArgs(
normcase_fallback, k, NULL);
}
if (normed == NULL)
goto quit;
if (PyDict_SetItem(file_foldmap, normed, k) == -1) {
Py_DECREF(normed);
goto quit;
}
Py_DECREF(normed);
}
}
return file_foldmap;
quit:
Py_XDECREF(file_foldmap);
return NULL;
}
/* calculate length of JSON-escaped string; returns -1 if unsupported */
static Py_ssize_t jsonescapelen(const char *buf, Py_ssize_t len, bool paranoid)
{
Py_ssize_t i, esclen = 0;
if (paranoid) {
/* don't want to process multi-byte escapes in C */
for (i = 0; i < len; i++) {
char c = buf[i];
if (c & 0x80) {
PyErr_SetString(PyExc_ValueError,
"cannot process non-ascii str");
return -1;
}
esclen += jsonparanoidlentable[(unsigned char)c];
if (esclen < 0) {
PyErr_SetString(PyExc_MemoryError,
"overflow in jsonescapelen");
return -1;
}
}
} else {
for (i = 0; i < len; i++) {
char c = buf[i];
esclen += jsonlentable[(unsigned char)c];
if (esclen < 0) {
PyErr_SetString(PyExc_MemoryError,
"overflow in jsonescapelen");
return -1;
}
}
}
return esclen;
}
/* map '\<c>' escape character */
static char jsonescapechar2(char c)
{
switch (c) {
case '\b':
return 'b';
case '\t':
return 't';
case '\n':
return 'n';
case '\f':
return 'f';
case '\r':
return 'r';
case '"':
return '"';
case '\\':
return '\\';
}
return '\0'; /* should not happen */
}
/* convert 'origbuf' to JSON-escaped form 'escbuf'; 'origbuf' should only
include characters mappable by json(paranoid)lentable */
static void encodejsonescape(char *escbuf, Py_ssize_t esclen,
const char *origbuf, Py_ssize_t origlen,
bool paranoid)
{
const uint8_t *lentable =
(paranoid) ? jsonparanoidlentable : jsonlentable;
Py_ssize_t i, j;
for (i = 0, j = 0; i < origlen; i++) {
char c = origbuf[i];
uint8_t l = lentable[(unsigned char)c];
assert(j + l <= esclen);
switch (l) {
case 1:
escbuf[j] = c;
break;
case 2:
escbuf[j] = '\\';
escbuf[j + 1] = jsonescapechar2(c);
break;
case 6:
memcpy(escbuf + j, "\\u00", 4);
escbuf[j + 4] = hexchartable[(unsigned char)c >> 4];
escbuf[j + 5] = hexchartable[(unsigned char)c & 0xf];
break;
}
j += l;
}
}
PyObject *jsonescapeu8fast(PyObject *self, PyObject *args)
{
PyObject *origstr, *escstr;
const char *origbuf;
Py_ssize_t origlen, esclen;
int paranoid;
if (!PyArg_ParseTuple(args, "O!i:jsonescapeu8fast", &PyBytes_Type,
&origstr, ¶noid))
return NULL;
origbuf = PyBytes_AS_STRING(origstr);
origlen = PyBytes_GET_SIZE(origstr);
esclen = jsonescapelen(origbuf, origlen, paranoid);
if (esclen < 0)
return NULL; /* unsupported char found or overflow */
if (origlen == esclen) {
Py_INCREF(origstr);
return origstr;
}
escstr = PyBytes_FromStringAndSize(NULL, esclen);
if (!escstr)
return NULL;
encodejsonescape(PyBytes_AS_STRING(escstr), esclen, origbuf, origlen,
paranoid);
return escstr;
}