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
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
|
from ply import lex
from ply import yacc
from makefilecom import expand
def scanmakefile(makefile):
makefile = "\n" + makefile #Add \n so you can guess vars
tokens = (
"END",
"COL",
"SEMICOL",
"EQ",
"PEQ",
"CEQ",
"QEQ",
"TEXT",
"COMMAND",
"PERCENT",
"ENDTAB",
"LIT",
"COMMA",
"SPACE",
)
states = (
("com", "exclusive"),
("ccode", "exclusive"), #command code
("var", "inclusive"),
)
# Match the first $(. Enter ccode state.
def t_ccode(t):
r'\$(\{|\()'
t.lexer.code_start = t.lexer.lexpos # Record the starting position
t.lexer.level = 1 # Initial level
t.lexer.push_state('ccode') # Enter 'ccode' state
# Rules for the ccode state
def t_ccode_newcom(t):
r'\$(\{|\()'
t.lexer.level +=1
def t_ccode_endcom(t):
r'(\}|\))'
t.lexer.level -=1
# If closing command, return the code fragment
if t.lexer.level == 0:
t.value = t.lexer.lexdata[t.lexer.code_start-1:t.lexer.lexpos]
t.type = "COMMAND"
t.lexer.pop_state()
return t
def t_ccode_text(t):
r"[^\$\(\{\)\}]"
def t_begin_com(t):
r"\#"
t.lexer.push_state("com")
def t_com_other(t):
r"[^(\n|\\)]+"
pass
def t_com_newline(t):
r".*\\\n"
t.lexer.lineno += 1
pass
def t_com_END(t):
r"\n"
t.lexer.pop_state()
t.lexer.lineno += 1
return t
def t_SEMICOL(t):
r";"
return t
def t_bsdexe(t): #Create a cleaner version
r".*\!=.*"
pass
def t_PERCENT(t):
r"\%"
return t
def t_var_TEXT(t):
r"[^ \n\t\$\\,]+"
return t
def t_var_SPACE(t):
r"[ \t]"
return t
def t_EQ(t):
r"=[ \t]*"
t.lexer.begin('var')
return t
def t_PEQ(t):
r"\+=[ \t]*"
t.lexer.begin('var')
return t
def t_CEQ(t):
r":=[ \t]*"
t.lexer.begin('var')
return t
def t_QEQ(t):
r"\?=[ \t]*"
t.lexer.begin('var')
return t
def t_contline(t):
r"\\\n"
t.lexer.lineno += 1
pass
def t_LIT(t):
r"\\."
t.value = t.value[1] #take the literal char
return t
def t_COL(t):
r":"
return t
def t_COMMA(t):
r","
return t
def t_spacetab(t):
r"[ \t]"
pass
def t_ENDTAB(t):
r"\n\t"
t.lexer.lineno += 1
return t
def t_TEXT(t):
r"[^ \n\t:\?\+=\\,]+"
return t
def t_END(t):
r"\n+"
t.lexer.lineno += t.value.count('\n')
t.lexer.begin('INITIAL')
return t
def t_ANY_error(t):
print("Illegal character '%s'" % t.value[0])
t.lexer.skip(1)
lexer = lex.lex()
lexer.input(makefile)
for tok in lexer:
print(tok)
#YACC begins here
#a dict with values of defined variables
variables = {}
ivars = [] #keep track of the immediate variables
targets = [] #buildtargets, [[target,deps,options],[target2,....
def p_peq(p): #immediate if peq was defined as immediate before else deferred
"""
end : end textstr PEQ textlst end
| end textstr PEQ end
"""
if len(p) == 6:
if not p[2] in variables:
variables[p[2]] = p[4]
elif not p[2] in ivars:
variables[p[2]] += p[4]
else:
textvalue = expand(p[4],variables) #expand any variables
variables[p[2]] = textvalue
def p_ceq(p): #immediate
"""
end : end textstr CEQ textlst end
| end textstr CEQ end
"""
if len(p) == 6:
print(p[4])
textvalue = expand(p[4],variables) #expand any variables
variables[p[2]] = textvalue
ivars.append(p[2])
else:
variables[p[2]] = []
ivars.append(p[2])
def p_qeq(p): #deferred
"""
end : end textstr QEQ textlst end
| end textstr QEQ end
"""
if not p[2] in variables and len(p) == 6:
variables[p[2]] = p[4]
else:
variables[p[2]] = []
def p_var(p): #deferred
"""
end : end textstr EQ textlst end
| end textstr EQ end
"""
if len(p) == 6:
variables[p[2]] = p[4]
else:
variables[p[2]] = []
def p_textlst(p):
"""
textlst : textlst spacestr command
| textlst spacestr textstr
| command
| textstr
"""
if len(p) == 4:
p[0] = p[1]+ [p[3]]
else:
p[0] = [p[1]]
def p_textstr(p):
"""
textstr : textstr LIT
| TEXT
| LIT
"""
if len(p) == 3:
p[0] = p[1] + p[2]
else:
p[0] = p[1]
def p_command(p):
"command : COMMAND"
p[0] = [p[1]] #commands are lists within the testlst
def p_end(p):
"""
end : end END
| spacestr END
| END
"""
def p_space(p):
"""
spacestr : spacestr SPACE
| SPACE
"""
if len(p) == 3:
p[0] = p[1] + p[2]
else:
p[0] = p[1]
def p_error(p):
print("syntax error at '%s'" % p.type,p.lexpos)
pass
yacc.yacc()
yacc.parse(makefile)
print(variables)
#for target in targets:
# print(target)
#print(variables)
#return targets
#immediate
#deferred
file="Makefile"
with open(file, encoding="utf-8", errors="replace") as inputfile:
scanmakefile(inputfile.read())
|