##// END OF EJS Templates
nodemap: also use persistent nodemap for manifest...
nodemap: also use persistent nodemap for manifest The manifest as a different usage pattern than the changelog. First, while the lookup in changelog are not garanteed to match, the lookup in the manifest nodemap come from changelog and will exist in the manifest. In addition, looking up a manifest almost always result in unpacking a manifest an operation that rarely come cheap. Nevertheless, using a persistent nodemap provide a significant gain for some operations. For our measurementw, we use `hg cat --rev REV FILE` on the our reference mozilla-try. On this repository the persistent nodemap cache is about 29 MB in side for a total store side of 11,988 MB File with large history (file: b2g/config/gaia.json, revision: 195a1146daa0) no optimisation: 0.358s using mmap for index: 0.297s (-0.061s) persistent nodemap for changelog only: 0.275s (-0.024s) persistent nodemap for manifest too: 0.258s (-0.017s) File with small history (file: .hgignore, revision: 195a1146daa0) no optimisation: 0.377s using mmap for index: 0.296s (-0.061s) persistent nodemap for changelog only: 0.274s (-0.022s) persistent nodemap for manifest too: 0.257s (-0.017s) Same file but using a revision (8ba995b74e18) with a smaller manifest (3944829 bytes vs 10 bytes) no optimisation: 0.192s (-0.185s) using mmap for index: 0.131s (-0.061s) persistent nodemap for changelog only: 0.106s (-0.025s) persistent nodemap for manifest too: 0.087s (-0.019s) Differential Revision: https://phab.mercurial-scm.org/D8410

File last commit:

r43812:2fe6121c default
r45290:640d5b3b default
Show More
charencode.py
90 lines | 2.3 KiB | text/x-python | PythonLexer
# charencode.py - miscellaneous character encoding
#
# Copyright 2005-2009 Matt Mackall <mpm@selenic.com> and others
#
# 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 array
from .. import pycompat
def isasciistr(s):
try:
s.decode('ascii')
return True
except UnicodeDecodeError:
return False
def asciilower(s):
'''convert a string to lowercase if ASCII
Raises UnicodeDecodeError if non-ASCII characters are found.'''
s.decode('ascii')
return s.lower()
def asciiupper(s):
'''convert a string to uppercase if ASCII
Raises UnicodeDecodeError if non-ASCII characters are found.'''
s.decode('ascii')
return s.upper()
_jsonmap = []
_jsonmap.extend(b"\\u%04x" % x for x in range(32))
_jsonmap.extend(pycompat.bytechr(x) for x in range(32, 127))
_jsonmap.append(b'\\u007f')
_jsonmap[0x09] = b'\\t'
_jsonmap[0x0A] = b'\\n'
_jsonmap[0x22] = b'\\"'
_jsonmap[0x5C] = b'\\\\'
_jsonmap[0x08] = b'\\b'
_jsonmap[0x0C] = b'\\f'
_jsonmap[0x0D] = b'\\r'
_paranoidjsonmap = _jsonmap[:]
_paranoidjsonmap[0x3C] = b'\\u003c' # '<' (e.g. escape "</script>")
_paranoidjsonmap[0x3E] = b'\\u003e' # '>'
_jsonmap.extend(pycompat.bytechr(x) for x in range(128, 256))
def jsonescapeu8fast(u8chars, paranoid):
"""Convert a UTF-8 byte string to JSON-escaped form (fast path)
Raises ValueError if non-ASCII characters have to be escaped.
"""
if paranoid:
jm = _paranoidjsonmap
else:
jm = _jsonmap
try:
return b''.join(jm[x] for x in bytearray(u8chars))
except IndexError:
raise ValueError
if pycompat.ispy3:
_utf8strict = r'surrogatepass'
else:
_utf8strict = r'strict'
def jsonescapeu8fallback(u8chars, paranoid):
"""Convert a UTF-8 byte string to JSON-escaped form (slow path)
Escapes all non-ASCII characters no matter if paranoid is False.
"""
if paranoid:
jm = _paranoidjsonmap
else:
jm = _jsonmap
# non-BMP char is represented as UTF-16 surrogate pair
u16b = u8chars.decode('utf-8', _utf8strict).encode('utf-16', _utf8strict)
u16codes = array.array('H', u16b)
u16codes.pop(0) # drop BOM
return b''.join(jm[x] if x < 128 else b'\\u%04x' % x for x in u16codes)