##// END OF EJS Templates
match: remove obsolete catching of OverflowError...
match: remove obsolete catching of OverflowError Since 0f6a1bdf89fb (match: handle large regexes, 2007-08-19), we catch an OverflowError from the regex engine and split up the regex if that happens. In 59a9dc9562e2 (ignore: split up huge patterns, 2008-02-11), that was extended to raise an OverflowError in our code even if the regex engine doesn't raise it. It's unclear if there was a range of regex sizes where the OverflowError would be raised from the regex engine but that were still below the limit we added in our code. Either way, both limitations were probably removed in Python 2.7.4 when the regex code width was extended from 16bit to 32bit (or Py_UCS4) integer (thanks to Yuya for finding that out). If at least the first limitation was removed, we no longer should be using OverflowError for flow control, so this patch changes that. Differential Revision: https://phab.mercurial-scm.org/D5309

File last commit:

r34215:aa877860 default
r40788:2f14d1bb 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)