-
Notifications
You must be signed in to change notification settings - Fork 12
/
parserLex.py
187 lines (159 loc) · 5.24 KB
/
parserLex.py
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
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
# This file is part of daf_butler.
#
# Developed for the LSST Data Management System.
# This product includes software developed by the LSST Project
# (https://www.lsst.org).
# See the COPYRIGHT file at the top-level directory of this distribution
# for details of code ownership.
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU 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 General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program. If not, see <https://www.gnu.org/licenses/>.
"""Module which defines PLY lexer for user expressions parsed by pre-flight.
"""
__all__ = ["ParserLex", "ParserLexError"]
# -------------------------------
# Imports of standard modules --
# -------------------------------
import re
# -----------------------------
# Imports for other modules --
# -----------------------------
from .ply import lex
# ----------------------------------
# Local non-exported definitions --
# ----------------------------------
_RE_RANGE = r"(?P<start>-?\d+)\s*\.\.\s*(?P<stop>-?\d+)(\s*:\s*(?P<stride>[1-9]\d*))?"
"""Regular expression to match range literal in the form NUM..NUM[:NUM],
this must match t_RANGE_LITERAL docstring.
"""
# ------------------------
# Exported definitions --
# ------------------------
class ParserLexError(Exception):
"""Exception raised for lex-phase errors.
Attributes
----------
expression : str
Full initial expression being parsed
remain : str
Remaining non-parsed part of the expression
pos : int
Current parsing position, offset from beginning of expression in
characters
lineno : int
Current line number in the expression
"""
def __init__(self, expression, remain, pos, lineno):
Exception.__init__(self, "Unexpected character at position {}".format(pos))
self.expression = expression
self.remain = remain
self.pos = pos
self.lineno = lineno
class ParserLex:
"""Class which defines PLY lexer.
"""
@classmethod
def make_lexer(cls, reflags=0, **kwargs):
"""Factory for lexers.
Returns
-------
`ply.lex.Lexer` instance.
"""
# make sure that flags that we need are there
kw = dict(reflags=reflags | re.IGNORECASE | re.VERBOSE)
kw.update(kwargs)
return lex.lex(object=cls(), **kw)
# literals = ""
# reserved words in a grammar.
# SQL has reserved words which we could potentially make reserved in our
# grammar too, for now try to pretend we don't care about SQL
reserved = dict(
# IS="IS",
IN="IN",
# NULL="NULL",
OR="OR",
AND="AND",
NOT="NOT",
# BETWEEN="BETWEEN",
# LIKE="LIKE",
# ESCAPE="ESCAPE",
# REGEXP="REGEXP"
)
# List of token names.
tokens = (
'NUMERIC_LITERAL',
'STRING_LITERAL',
'RANGE_LITERAL',
# 'TIME_LITERAL',
# 'DURATION_LITERAL',
'IDENTIFIER',
'LPAREN', 'RPAREN',
'EQ', 'NE', 'LT', 'LE', 'GT', 'GE',
'ADD', 'SUB', 'MUL', 'DIV', 'MOD',
'COMMA'
) + tuple(reserved.values())
# Regular expression rules for simple tokens
t_LPAREN = r'\('
t_RPAREN = r'\)'
t_EQ = '='
t_NE = '!='
t_LT = '<'
t_LE = '<='
t_GT = '>'
t_GE = '>='
t_ADD = r'\+'
t_SUB = '-'
t_MUL = r'\*'
t_DIV = '/'
t_MOD = '%'
t_COMMA = ','
# A string containing ignored characters (spaces and tabs)
t_ignore = ' \t'
# Define a rule so we can track line numbers
def t_newline(self, t):
r'\n+'
t.lexer.lineno += len(t.value)
# quoted string
def t_STRING_LITERAL(self, t):
r"'.*?'"
# strip quotes
t.value = t.value[1:-1]
return t
# range literal in format N..M[:S], spaces allowed, see _RE_RANGE
@lex.TOKEN(_RE_RANGE)
def t_RANGE_LITERAL(self, t):
match = re.match(_RE_RANGE, t.value)
start = int(match.group("start"))
stop = int(match.group("stop"))
stride = match.group("stride")
if stride is not None:
stride = int(stride)
t.value = (start, stop, stride)
return t
# numbers are used as strings by parser, do not convert
def t_NUMERIC_LITERAL(self, t):
r"""\d+(\.\d*)?(e[-+]?\d+)? # 1, 1., 1.1, 1e10, 1.1e-10, etc.
|
\.\d+(e[-+]?\d+)? # .1, .1e10, .1e+10
"""
return t
# identifiers can have dot, and we only support ASCII
def t_IDENTIFIER(self, t):
r"[a-zA-Z_][a-zA-Z0-9_]*(\.[a-zA-Z_][a-zA-Z0-9_]*)?"
# Check for reserved words
t.type = self.reserved.get(t.value.upper(), 'IDENTIFIER')
return t
def t_error(self, t):
"Error handling rule"
lexer = t.lexer
raise ParserLexError(lexer.lexdata, t.value, lexer.lexpos, lexer.lineno)