##// END OF EJS Templates
copies: add config option for writing copy metadata to file and/or changset...
copies: add config option for writing copy metadata to file and/or changset This introduces a config option that lets you choose to write copy metadata to the changeset extras instead of to filelog. There's also an option to write it to both places. I imagine that may possibly be useful when transitioning an existing repo. The copy metadata is stored as two fields in extras: one for copies since p1 and one for copies since p2. I may need to add more information later in order to make copy tracing faster. Specifically, I'm thinking out recording which files were added or removed so that copies._chaincopies() doesn't have to look at the manifest for that. But that would just be an optimization and that can be added once we know if it's necessary. I have also considered saving space by using replacing the destination file path by an index into the "files" list, but that can also be changed later (but before the feature is ready to release). Differential Revision: https://phab.mercurial-scm.org/D6183

File last commit:

r34215:aa877860 default
r42317:0e41f40b default
Show More
charencode.py
85 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("\\u%04x" % x for x in range(32))
_jsonmap.extend(pycompat.bytechr(x) for x in range(32, 127))
_jsonmap.append('\\u007f')
_jsonmap[0x09] = '\\t'
_jsonmap[0x0a] = '\\n'
_jsonmap[0x22] = '\\"'
_jsonmap[0x5c] = '\\\\'
_jsonmap[0x08] = '\\b'
_jsonmap[0x0c] = '\\f'
_jsonmap[0x0d] = '\\r'
_paranoidjsonmap = _jsonmap[:]
_paranoidjsonmap[0x3c] = '\\u003c' # '<' (e.g. escape "</script>")
_paranoidjsonmap[0x3e] = '\\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 ''.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(r'H', u16b)
u16codes.pop(0) # drop BOM
return ''.join(jm[x] if x < 128 else '\\u%04x' % x for x in u16codes)