##// END OF EJS Templates
dirstate: drop all logic around the "non-normal" sets...
dirstate: drop all logic around the "non-normal" sets The dirstate has a lot of code to compute a set of all "non-normal" and "from_other_parent" entries. This is all used in one, unique, location, when `setparent` is called and moved from a merge to a non merge. At that time, any "merge related" information has to be dropped. This is mostly useful for command like `graft` or `shelve` that move to a single-parent state -before- the commit. Otherwise the commit will already have removed all traces of the merge information in the dirstate (e.g. for a regular merges). The bookkeeping for these sets is quite invasive. And it seems simpler to just drop it and do the full computation in the single location where we actually use it (since we have to do the computation at least once anyway). This simplify the code a lot, and clarify why this kind of computation is needed. The possible drawback compared to the previous code are: - if the operation happens in a loop, we will end up doing it multiple time, - the C code to detect entry of interest have been dropped, for now. It will be re-introduced later, with a processing code directly in C for even faster operation. Differential Revision: https://phab.mercurial-scm.org/D11507

File last commit:

r47575:d4ba4d51 default
r48875:060cd909 default
Show More
charencode.py
90 lines | 2.3 KiB | text/x-python | PythonLexer
# charencode.py - miscellaneous character encoding
#
# Copyright 2005-2009 Olivia Mackall <olivia@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)