grammar.py (6660:a886774d5ae1) grammar.py (8452:3f2c329e9046)
1# Copyright (c) 2006-2009 Nathan Binkert <nate@binkert.org>
1# Copyright (c) 2006-2011 Nathan Binkert <nate@binkert.org>
2# All rights reserved.
3#
4# Redistribution and use in source and binary forms, with or without
5# modification, are permitted provided that the following conditions are
6# met: redistributions of source code must retain the above copyright
7# notice, this list of conditions and the following disclaimer;
8# redistributions in binary form must reproduce the above copyright
9# notice, this list of conditions and the following disclaimer in the

--- 9 unchanged lines hidden (view full) ---

19# OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
20# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
21# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
22# DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
23# THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
24# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
25# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
26
2# All rights reserved.
3#
4# Redistribution and use in source and binary forms, with or without
5# modification, are permitted provided that the following conditions are
6# met: redistributions of source code must retain the above copyright
7# notice, this list of conditions and the following disclaimer;
8# redistributions in binary form must reproduce the above copyright
9# notice, this list of conditions and the following disclaimer in the

--- 9 unchanged lines hidden (view full) ---

19# OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
20# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
21# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
22# DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
23# THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
24# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
25# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
26
27from ply import lex, yacc
27import os
28
28
29class TokenError(lex.LexError):
30 def __init__(self, msg, t):
31 super(TokenError, self).__init__(msg)
32 self.token = t
29import ply.lex
30import ply.yacc
33
31
34class ParseError(yacc.YaccError):
32class ParseError(Exception):
35 def __init__(self, message, token=None):
33 def __init__(self, message, token=None):
36 super(ParseError, self).__init__(message)
34 Exception.__init__(self, message)
37 self.token = token
38
35 self.token = token
36
39class Tokenizer(object):
40 def __init__(self, lexer, data):
41 if isinstance(data, basestring):
42 indata = [ data ]
43 elif isinstance(data, file):
44 indata = data.xreadlines()
45 else:
46 indata = data
37class Grammar(object):
38 def setupLexerFactory(self, **kwargs):
39 if 'module' in kwargs:
40 raise AttributeError, "module is an illegal attribute"
41 self.lex_kwargs = kwargs
47
42
48 def _input():
49 for i,line in enumerate(indata):
50 lexer.lineno = i + 1
51 lexer.input(line)
52 while True:
53 tok = lexer.token()
54 if not tok:
55 break
56 yield tok
57 self.input = _input()
58 self.lexer = lexer
43 def setupParserFactory(self, **kwargs):
44 if 'module' in kwargs:
45 raise AttributeError, "module is an illegal attribute"
59
46
60 def next(self):
61 return self.input.next()
47 if 'output' in kwargs:
48 dir,tab = os.path.split(output)
49 if not tab.endswith('.py'):
50 raise AttributeError, \
51 'The output file must end with .py'
52 kwargs['outputdir'] = dir
53 kwargs['tabmodule'] = tab[:-3]
62
54
63 def __iter__(self):
64 return self
55 self.yacc_kwargs = kwargs
65
56
66 def token(self):
67 try:
68 return self.next()
69 except StopIteration:
70 return None
71
72 def __getattr__(self, attr):
57 def __getattr__(self, attr):
73 return getattr(self.lexer, attr)
58 if attr == 'lexers':
59 self.lexers = []
60 return self.lexers
74
61
75class Grammar(object):
76 def __init__(self, output=None, debug=False):
77 self.yacc_args = {}
78 self.yacc_args['debug'] = debug
62 if attr == 'lex_kwargs':
63 self.setupLexerFactory()
64 return self.lex_kwargs
79
65
80 if output:
81 import os
66 if attr == 'yacc_kwargs':
67 self.setupParserFactory()
68 return self.yacc_kwargs
82
69
83 dir,tab = os.path.split(output)
84 if not tab.endswith('.py'):
85 raise AttributeError, 'The output file must end with .py'
86 self.yacc_args['outputdir'] = dir
87 self.yacc_args['tabmodule'] = tab[:-3]
70 if attr == 'lex':
71 self.lex = ply.lex.lex(module=self, **self.lex_kwargs)
72 return self.lex
88
73
89 def t_error(self, t):
90 raise lex.LexError("Illegal character %s @ %d:%d" % \
91 (`t.value[0]`, t.lineno, t.lexpos), `t.value[0]`)
74 if attr == 'yacc':
75 self.yacc = ply.yacc.yacc(module=self, **self.yacc_kwargs)
76 return self.yacc
92
77
93 def p_error(self, t):
94 if t:
95 msg = "Syntax error at %d:%d\n>>%s<<" % \
96 (t.lineno, t.lexpos + 1, t.value)
97 else:
98 msg = "Syntax error at end of input"
99 raise ParseError(msg, t)
78 if attr == 'current_lexer':
79 if not self.lexers:
80 return None
81 return self.lexers[-1][0]
100
82
101 def __getattr__(self, attr):
102 if attr == 'parser':
103 import ply.yacc
104 parser = ply.yacc.yacc(module=self, **self.yacc_args)
105 self.parser = parser
106 return parser
83 if attr == 'current_source':
84 if not self.lexers:
85 return '<none>'
86 return self.lexers[-1][1]
107
87
108 if attr == 'lexer':
109 import ply.lex
110 lexer = ply.lex.lex(module=self)
111 self.lexer = lexer
112 return lexer
88 if attr == 'current_line':
89 if not self.lexers:
90 return -1
91 return self.current_lexer.lineno
113
92
114 raise AttributeError, "'%s' object has no attribute '%s'" % \
115 (self.__class__.__name__, attr)
93 raise AttributeError, \
94 "'%s' object has no attribute '%s'" % (type(self), attr)
116
95
117 def parse(self, stmt, **kwargs):
118 self.lexer.lineno = 1
119 result = self.parser.parse(lexer=Tokenizer(self.lexer, stmt), **kwargs)
120 self.parser.restart()
96 def parse_string(self, data, source='<string>', debug=None, tracking=0):
97 if not isinstance(data, basestring):
98 raise AttributeError, \
99 "argument must be a string, was '%s'" % type(f)
121
100
101 import new
102 lexer = self.lex.clone()
103 lexer.input(data)
104 self.lexers.append((lexer, source))
105 dict = {
106 'productions' : self.yacc.productions,
107 'action' : self.yacc.action,
108 'goto' : self.yacc.goto,
109 'errorfunc' : self.yacc.errorfunc,
110 }
111 parser = new.instance(ply.yacc.LRParser, dict)
112 result = parser.parse(lexer=lexer, debug=debug, tracking=tracking)
113 self.lexers.pop()
122 return result
123
114 return result
115
116 def parse_file(self, f, **kwargs):
117 if isinstance(f, basestring):
118 source = f
119 f = file(f, 'r')
120 elif isinstance(f, file):
121 source = f.name
122 else:
123 raise AttributeError, \
124 "argument must be either a string or file, was '%s'" % type(f)
125
126 return self.parse_string(f.read(), source, **kwargs)
127
128 def p_error(self, t):
129 if t:
130 msg = "Syntax error at %s:%d:%d\n>>%s<<" % \
131 (self.current_source, t.lineno, t.lexpos + 1, t.value)
132 else:
133 msg = "Syntax error at end of %s" % (self.current_source, )
134 raise ParseError(msg, t)
135
136 def t_error(self, t):
137 msg = "Illegal character %s @ %d:%d" % \
138 (`t.value[0]`, t.lineno, t.lexpos)
139 raise ParseError(msg, t)