##// END OF EJS Templates
cleanup: remove pointless r-prefixes on single-quoted strings...
cleanup: remove pointless r-prefixes on single-quoted strings This is the promised second step on single-quoted strings. These had existed because our source transformer didn't turn r'' into b'', so we had tagged some strings as r-strings to get "native" strings on both Pythons. Now that the transformer is gone, we can dispense with this nonsense. Methodology: I ran hg locate 'set:added() or modified() or clean()' | egrep '.*\.py$' | xargs egrep --color=never -n -- \[\^b\]\[\^a-z\]r\'\[\^\'\\\\\]\*\'\[\^\'\ in an emacs grep-mode buffer, and then used a keyboard macro to iterate over the results and remove the r prefix as needed. # skip-blame removing unneeded r prefixes left over from Python 3 migration. Differential Revision: https://phab.mercurial-scm.org/D7306

File last commit:

r43812:2fe6121c default
r43906:9f70512a 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)