/usr/lib/python3/dist-packages/xdot/dot/scanner.py is in xdot 0.9-1.
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 | # Copyright 2008-2015 Jose Fonseca
#
# This program is free software: you can redistribute it and/or modify it
# under the terms of the GNU Lesser General Public License as published
# by the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU Lesser General Public License for more details.
#
# You should have received a copy of the GNU Lesser General Public License
# along with this program. If not, see <http://www.gnu.org/licenses/>.
#
import re
EOF = -1
SKIP = -2
ID = 0
STR_ID = 1
HTML_ID = 2
EDGE_OP = 3
LSQUARE = 4
RSQUARE = 5
LCURLY = 6
RCURLY = 7
COMMA = 8
COLON = 9
SEMI = 10
EQUAL = 11
PLUS = 12
STRICT = 13
GRAPH = 14
DIGRAPH = 15
NODE = 16
EDGE = 17
SUBGRAPH = 18
class Scanner:
"""Stateless scanner."""
# should be overriden by derived classes
tokens = []
symbols = {}
literals = {}
ignorecase = False
def __init__(self):
flags = re.DOTALL
if self.ignorecase:
flags |= re.IGNORECASE
self.tokens_re = re.compile(
b'|'.join([b'(' + regexp + b')'
for type, regexp, test_lit in self.tokens]),
flags
)
def next(self, buf, pos):
if pos >= len(buf):
return EOF, b'', pos
mo = self.tokens_re.match(buf, pos)
if mo:
text = mo.group()
type, regexp, test_lit = self.tokens[mo.lastindex - 1]
pos = mo.end()
if test_lit:
type = self.literals.get(text, type)
return type, text, pos
else:
c = buf[pos:pos+1]
return self.symbols.get(c, None), c, pos + 1
class DotScanner(Scanner):
# token regular expression table
tokens = [
# whitespace and comments
(SKIP,
br'[ \t\f\r\n\v]+|'
br'//[^\r\n]*|'
br'/\*.*?\*/|'
br'#[^\r\n]*',
False),
# Alphanumeric IDs
(ID, br'[a-zA-Z_\x80-\xff][a-zA-Z0-9_\x80-\xff]*', True),
# Numeric IDs
(ID, br'-?(?:\.[0-9]+|[0-9]+(?:\.[0-9]*)?)', False),
# String IDs
(STR_ID, br'"[^"\\]*(?:\\.[^"\\]*)*"', False),
# HTML IDs
(HTML_ID, br'<[^<>]*(?:<[^<>]*>[^<>]*)*>', False),
# Edge operators
(EDGE_OP, br'-[>-]', False),
]
# symbol table
symbols = {
b'[': LSQUARE,
b']': RSQUARE,
b'{': LCURLY,
b'}': RCURLY,
b',': COMMA,
b':': COLON,
b';': SEMI,
b'=': EQUAL,
b'+': PLUS,
}
# literal table
literals = {
b'strict': STRICT,
b'graph': GRAPH,
b'digraph': DIGRAPH,
b'node': NODE,
b'edge': EDGE,
b'subgraph': SUBGRAPH,
}
ignorecase = True
|