/usr/lib/python3/dist-packages/funcparserlib/lexer.py is in python3-funcparserlib 0.3.6-7.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 | # -*- coding: utf-8 -*-
# Copyright (c) 2008/2013 Andrey Vlasovskikh
#
# Permission is hereby granted, free of charge, to any person obtaining
# a copy of this software and associated documentation files (the
# "Software"), to deal in the Software without restriction, including
# without limitation the rights to use, copy, modify, merge, publish,
# distribute, sublicense, and/or sell copies of the Software, and to
# permit persons to whom the Software is furnished to do so, subject to
# the following conditions:
#
# The above copyright notice and this permission notice shall be included
# in all copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
# IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
# CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
# TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
# SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
__all__ = ['make_tokenizer', 'Token', 'LexerError']
import re
class LexerError(Exception):
def __init__(self, place, msg):
self.place = place
self.msg = msg
def __str__(self):
s = 'cannot tokenize data'
line, pos = self.place
return '%s: %d,%d: "%s"' % (s, line, pos, self.msg)
class Token(object):
def __init__(self, type, value, start=None, end=None):
self.type = type
self.value = value
self.start = start
self.end = end
def __repr__(self):
return 'Token(%r, %r)' % (self.type, self.value)
def __eq__(self, other):
# FIXME: Case sensitivity is assumed here
return self.type == other.type and self.value == other.value
def _pos_str(self):
if self.start is None or self.end is None:
return ''
else:
sl, sp = self.start
el, ep = self.end
return '%d,%d-%d,%d:' % (sl, sp, el, ep)
def __str__(self):
s = "%s %s '%s'" % (self._pos_str(), self.type, self.value)
return s.strip()
@property
def name(self):
return self.value
def pformat(self):
return "%s %s '%s'" % (self._pos_str().ljust(20),
self.type.ljust(14),
self.value)
def make_tokenizer(specs):
"""[(str, (str, int?))] -> (str -> Iterable(Token))"""
def compile_spec(spec):
name, args = spec
return name, re.compile(*args)
compiled = [compile_spec(s) for s in specs]
def match_specs(specs, str, i, position):
line, pos = position
for type, regexp in specs:
m = regexp.match(str, i)
if m is not None:
value = m.group()
nls = value.count('\n')
n_line = line + nls
if nls == 0:
n_pos = pos + len(value)
else:
n_pos = len(value) - value.rfind('\n') - 1
return Token(type, value, (line, pos + 1), (n_line, n_pos))
else:
errline = str.splitlines()[line - 1]
raise LexerError((line, pos + 1), errline)
def f(str):
length = len(str)
line, pos = 1, 0
i = 0
while i < length:
t = match_specs(compiled, str, i, (line, pos))
yield t
line, pos = t.end
i += len(t.value)
return f
# This is an example of a token spec. See also [this article][1] for a
# discussion of searching for multiline comments using regexps (including `*?`).
#
# [1]: http://ostermiller.org/findcomment.html
_example_token_specs = [
('COMMENT', (r'\(\*(.|[\r\n])*?\*\)', re.MULTILINE)),
('COMMENT', (r'\{(.|[\r\n])*?\}', re.MULTILINE)),
('COMMENT', (r'//.*',)),
('NL', (r'[\r\n]+',)),
('SPACE', (r'[ \t\r\n]+',)),
('NAME', (r'[A-Za-z_][A-Za-z_0-9]*',)),
('REAL', (r'[0-9]+\.[0-9]*([Ee][+\-]?[0-9]+)*',)),
('INT', (r'[0-9]+',)),
('INT', (r'\$[0-9A-Fa-f]+',)),
('OP', (r'(\.\.)|(<>)|(<=)|(>=)|(:=)|[;,=\(\):\[\]\.+\-<>\*/@\^]',)),
('STRING', (r"'([^']|(''))*'",)),
('CHAR', (r'#[0-9]+',)),
('CHAR', (r'#\$[0-9A-Fa-f]+',)),
]
#tokenize = make_tokenizer(_example_token_specs)
|