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
188
189
190
191
192
193
194
195
|
#!/usr/bin/env python3
#
# Copyright © 2019 Keith Packard <keithp@keithp.com>
#
# 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, write to the Free Software Foundation, Inc.,
# 51 Franklin St, Fifth Floor, Boston, MA 02110-1301, USA.
#
grammar = {
"lines" : (("line", "lines"),
()
),
"line" : (("expr", "#PRINT", "NL"),
("NL",),
),
"expr" : (("term", "PLUS", "expr", "#ADD"),
("term", "MINUS", "expr", "#SUBTRACT"),
("term",)
),
"term" : (("fact", "term-p"),
),
"term-p" : (("TIMES", "fact", "#TIMES", "term-p"),
("DIVIDE", "fact", "#DIVIDE", "term-p"),
(),
),
"fact" : (("OP", "expr", "CP"),
("MINUS", "fact", "#NEGATE"),
("#PUSH", "NUMBER"),
)
}
def productions(non_terminal):
return grammar[non_terminal]
# flo
#
# factor left common expressions out of a grammar
#
def head(list):
return list[0]
def rest(list):
return list[1:]
def nthrest(list, n):
return list[n:]
def error(msg):
print(msg)
exit(1)
#
# remove the first element from each of a list
# of productions (unless the production is nil)
#
def clip_firsts(prods):
ret = ()
for prod in prods:
if prod:
ret += (head(prod),)
return ret
#
# return the first duplicated element from a list of elements
#
def find_common(firsts):
while firsts:
f = head(firsts)
firsts = rest(firsts)
if f in firsts:
return f
#
# return a list of productions which have the given
# element as their first member
#
def with_first(prods, first):
ret = ()
for prod in prods:
if first == head(prod):
ret = ret + (prod,)
return ret
#
# return a list of productions which *don't* have the given
# element as their first member
#
def without_first (prods, first):
ret = ()
for prod in prods:
if first != head(prod):
ret = ret + (prod,)
return ret
#
# strip the first 'count' elements off a list of productions
#
def remove_firsts (prods, count):
ret = ()
for prod in prods:
ret = ret + (nthrest(prod, count),)
return ret
#
# return True if each production in the list has the same first
# element
#
def all_common_first(prods):
while len(prods) >= 2:
if head(prods[0]) != head(prods[1]):
return False
prods = rest(prods)
return True
#
# return the maximal list of common first sub-lists
# from a set of productions
#
def max_common(prods):
ret = ()
while all_common_first(prods):
ret = ret + (head(prods[0]),)
prods = remove_firsts(prods, 1)
return ret
#
# factor out common left sub-lists from the list
# of productions
#
def eliminate_common(non_terminal):
prods = productions(non_terminal)
firsts = clip_firsts(prods)
common = find_common(firsts)
if common:
removed = with_first(prods, common)
remain = without_first(prods, common)
common_list = max_common(removed)
new_non_terminal = non_terminal
while True:
new_non_terminal = new_non_terminal + "-p"
if new_non_terminal not in grammar:
break
grammar[new_non_terminal] = remove_firsts(removed, len(common_list))
grammar[non_terminal] = ((common_list + (new_non_terminal,)),) + remain
#
# remove common left sub-expressions from each non-terminal
# in the grammar
#
def factor_left(non_terminals):
for non_terminal in non_terminals:
eliminate_common(non_terminal)
def get_non_terminals(grammar):
non_terminals = ()
for e in grammar:
non_terminals += (e,)
return non_terminals
def dump_grammar(grammar):
for nt,prods in grammar.items():
print("%s" % nt)
started = False
for prod in prods:
label = ":"
if started:
label = "|"
print("\t%s %s" % (label, prod))
started = True
print("\t;")
def flo():
factor_left(get_non_terminals(grammar))
flo()
dump_grammar(grammar)
|
