##// END OF EJS Templates
py3: use pycompat.bytestr to convert _b85chars to bytes...
py3: use pycompat.bytestr to convert _b85chars to bytes The tranformer does append b'' to the value and make that a bytes but bytes in Python 3 returns the ascii value on getting characters using indexing. Characters of this string are queried using indexing multiple times in the file and to support that we use pycompat.bytestr which returns the bytechrs using indexing. Differential Revision: https://phab.mercurial-scm.org/D2072

File last commit:

r34215:aa877860 default
r35962:01b4d88c default
Show More
charencode.py
85 lines | 2.3 KiB | text/x-python | PythonLexer
Yuya Nishihara
encoding: drop circular import by proxying through '<policy>.charencode'...
r33756 # 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
Yuya Nishihara
encoding: extract stub for fast JSON escape...
r33925 import array
from .. import (
pycompat,
)
Yuya Nishihara
encoding: add function to test if a str consists of ASCII characters...
r33927 def isasciistr(s):
try:
s.decode('ascii')
return True
except UnicodeDecodeError:
return False
Yuya Nishihara
encoding: drop circular import by proxying through '<policy>.charencode'...
r33756 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()
Yuya Nishihara
encoding: extract stub for fast JSON escape...
r33925
_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
Yuya Nishihara
py3: use 'surrogatepass' error handler to process U+DCxx transparently...
r34215 if pycompat.ispy3:
_utf8strict = r'surrogatepass'
else:
_utf8strict = r'strict'
Yuya Nishihara
encoding: extract stub for fast JSON escape...
r33925 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
Yuya Nishihara
py3: use 'surrogatepass' error handler to process U+DCxx transparently...
r34215 u16b = u8chars.decode('utf-8', _utf8strict).encode('utf-16', _utf8strict)
u16codes = array.array(r'H', u16b)
Yuya Nishihara
encoding: extract stub for fast JSON escape...
r33925 u16codes.pop(0) # drop BOM
return ''.join(jm[x] if x < 128 else '\\u%04x' % x for x in u16codes)