07 优化与重构 | 《Let’s Build A Simple Interpreter》笔记

本系列是《Let’s Build A Simple Interpreter》的阅读笔记。

为了提供更好的错误消息,指出代码中出现问题的位置,例如:SyntaxError: Unexpected token -> Token(TokenType.SEMI, ‘;’, position=23:13),需要向解释器添加一些功能,具体包括:

  • 添加错误代码和自定义异常:LexerError、ParserError 和 SemanticError
  • 向 Lexer 类添加新成员以帮助跟踪标记的位置:lineno 和 column
  • 修改 Advance 方法来更新词法分析器的 lineno 和 column 变量
  • 更新错误方法以引发 LexerError 异常,其中包含有关当前行和列的信息
  • 在 TokenType 枚举类中定义 token 类型
  • 添加代码以从 TokenType 枚举成员中自动创建保留关键字
  • 在 Token 类中添加新成员:lineno 和 column 以跟踪标记的行号和列号,相应在文本中重构 get_next_token 方法代码以使其更短,并拥有处理单字符标记的通用代码
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
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
"""SPI - Simple Pascal Interpreter. Part 15."""

import argparse
import sys
from enum import Enum

_SHOULD_LOG_SCOPE = False # see '--scope' command line option


class ErrorCode(Enum):
UNEXPECTED_TOKEN = 'Unexpected token'
ID_NOT_FOUND = 'Identifier not found'
DUPLICATE_ID = 'Duplicate id found'


class Error(Exception):
def __init__(self, error_code=None, token=None, message=None):
self.error_code = error_code
self.token = token
# add exception class name before the message
self.message = f'{self.__class__.__name__}: {message}'


class LexerError(Error):
pass


class ParserError(Error):
pass


class SemanticError(Error):
pass


###############################################################################
# #
# LEXER #
# #
###############################################################################


class TokenType(Enum):
# single-character token types
PLUS = '+'
MINUS = '-'
MUL = '*'
FLOAT_DIV = '/'
LPAREN = '('
RPAREN = ')'
SEMI = ';'
DOT = '.'
COLON = ':'
COMMA = ','
# block of reserved words
PROGRAM = 'PROGRAM' # marks the beginning of the block
INTEGER = 'INTEGER'
REAL = 'REAL'
INTEGER_DIV = 'DIV'
VAR = 'VAR'
PROCEDURE = 'PROCEDURE'
BEGIN = 'BEGIN'
END = 'END' # marks the end of the block
# misc
ID = 'ID'
INTEGER_CONST = 'INTEGER_CONST'
REAL_CONST = 'REAL_CONST'
ASSIGN = ':='
EOF = 'EOF'


class Token(object):
def __init__(self, type, value, lineno=None, column=None):
self.type = type
self.value = value
self.lineno = lineno
self.column = column

def __str__(self):
"""String representation of the class instance.

Example:
>>> Token(TokenType.INTEGER, 7, lineno=5, column=10)
Token(TokenType.INTEGER, 7, position=5:10)
"""
return 'Token({type}, {value}, position={lineno}:{column})'.format(
type=self.type,
value=repr(self.value),
lineno=self.lineno,
column=self.column,
)

def __repr__(self):
return self.__str__()


def _build_reserved_keywords():
"""Build a dictionary of reserved keywords.

The function relies on the fact that in the TokenType
enumeration the beginning of the block of reserved keywords is
marked with PROGRAM and the end of the block is marked with
the END keyword.

Result:
{'PROGRAM': <TokenType.PROGRAM: 'PROGRAM'>,
'INTEGER': <TokenType.INTEGER: 'INTEGER'>,
'REAL': <TokenType.REAL: 'REAL'>,
'DIV': <TokenType.INTEGER_DIV: 'DIV'>,
'VAR': <TokenType.VAR: 'VAR'>,
'PROCEDURE': <TokenType.PROCEDURE: 'PROCEDURE'>,
'BEGIN': <TokenType.BEGIN: 'BEGIN'>,
'END': <TokenType.END: 'END'>}
"""
# enumerations support iteration, in definition order
tt_list = list(TokenType)
start_index = tt_list.index(TokenType.PROGRAM)
end_index = tt_list.index(TokenType.END)
reserved_keywords = {
token_type.value: token_type
for token_type in tt_list[start_index:end_index + 1]
}
return reserved_keywords


RESERVED_KEYWORDS = _build_reserved_keywords()


class Lexer(object):
def __init__(self, text):
# client string input, e.g. "4 + 2 * 3 - 6 / 2"
self.text = text
# self.pos is an index into self.text
self.pos = 0
self.current_char = self.text[self.pos]
# token line number and column number
self.lineno = 1
self.column = 1

def error(self):
s = "Lexer error on '{lexeme}' line: {lineno} column: {column}".format(
lexeme=self.current_char,
lineno=self.lineno,
column=self.column,
)
raise LexerError(message=s)

def advance(self):
"""Advance the `pos` pointer and set the `current_char` variable."""
if self.current_char == '\n':
self.lineno += 1
self.column = 0

self.pos += 1
if self.pos > len(self.text) - 1:
self.current_char = None # Indicates end of input
else:
self.current_char = self.text[self.pos]
self.column += 1

def peek(self):
peek_pos = self.pos + 1
if peek_pos > len(self.text) - 1:
return None
else:
return self.text[peek_pos]

def skip_whitespace(self):
while self.current_char is not None and self.current_char.isspace():
self.advance()

def skip_comment(self):
while self.current_char != '}':
self.advance()
self.advance() # the closing curly brace

def number(self):
"""Return a (multidigit) integer or float consumed from the input."""

# Create a new token with current line and column number
token = Token(type=None, value=None, lineno=self.lineno, column=self.column)

result = ''
while self.current_char is not None and self.current_char.isdigit():
result += self.current_char
self.advance()

if self.current_char == '.':
result += self.current_char
self.advance()

while self.current_char is not None and self.current_char.isdigit():
result += self.current_char
self.advance()

token.type = TokenType.REAL_CONST
token.value = float(result)
else:
token.type = TokenType.INTEGER_CONST
token.value = int(result)

return token

def _id(self):
"""Handle identifiers and reserved keywords"""

# Create a new token with current line and column number
token = Token(type=None, value=None, lineno=self.lineno, column=self.column)

value = ''
while self.current_char is not None and self.current_char.isalnum():
value += self.current_char
self.advance()

token_type = RESERVED_KEYWORDS.get(value.upper())
if token_type is None:
token.type = TokenType.ID
token.value = value
else:
# reserved keyword
token.type = token_type
token.value = value.upper()

return token

def get_next_token(self):
"""Lexical analyzer (also known as scanner or tokenizer)

This method is responsible for breaking a sentence
apart into tokens. One token at a time.
"""
while self.current_char is not None:
if self.current_char.isspace():
self.skip_whitespace()
continue

if self.current_char == '{':
self.advance()
self.skip_comment()
continue

if self.current_char.isalpha():
return self._id()

if self.current_char.isdigit():
return self.number()

if self.current_char == ':' and self.peek() == '=':
token = Token(
type=TokenType.ASSIGN,
value=TokenType.ASSIGN.value, # ':='
lineno=self.lineno,
column=self.column,
)
self.advance()
self.advance()
return token

# single-character token
try:
# get enum member by value, e.g.
# TokenType(';') --> TokenType.SEMI
token_type = TokenType(self.current_char)
except ValueError:
# no enum member with value equal to self.current_char
self.error()
else:
# create a token with a single-character lexeme as its value
token = Token(
type=token_type,
value=token_type.value, # e.g. ';', '.', etc
lineno=self.lineno,
column=self.column,
)
self.advance()
return token

# EOF (end-of-file) token indicates that there is no more
# input left for lexical analysis
return Token(type=TokenType.EOF, value=None)


###############################################################################
# #
# PARSER #
# #
###############################################################################
class AST(object):
pass


class BinOp(AST):
def __init__(self, left, op, right):
self.left = left
self.token = self.op = op
self.right = right


class Num(AST):
def __init__(self, token):
self.token = token
self.value = token.value


class UnaryOp(AST):
def __init__(self, op, expr):
self.token = self.op = op
self.expr = expr


class Compound(AST):
"""Represents a 'BEGIN ... END' block"""
def __init__(self):
self.children = []


class Assign(AST):
def __init__(self, left, op, right):
self.left = left
self.token = self.op = op
self.right = right


class Var(AST):
"""The Var node is constructed out of ID token."""
def __init__(self, token):
self.token = token
self.value = token.value


class NoOp(AST):
pass


class Program(AST):
def __init__(self, name, block):
self.name = name
self.block = block


class Block(AST):
def __init__(self, declarations, compound_statement):
self.declarations = declarations
self.compound_statement = compound_statement


class VarDecl(AST):
def __init__(self, var_node, type_node):
self.var_node = var_node
self.type_node = type_node


class Type(AST):
def __init__(self, token):
self.token = token
self.value = token.value


class Param(AST):
def __init__(self, var_node, type_node):
self.var_node = var_node
self.type_node = type_node


class ProcedureDecl(AST):
def __init__(self, proc_name, params, block_node):
self.proc_name = proc_name
self.params = params # a list of Param nodes
self.block_node = block_node


class Parser(object):
def __init__(self, lexer):
self.lexer = lexer
# set current token to the first token taken from the input
self.current_token = self.get_next_token()

def get_next_token(self):
return self.lexer.get_next_token()

def error(self, error_code, token):
raise ParserError(
error_code=error_code,
token=token,
message=f'{error_code.value} -> {token}',
)

def eat(self, token_type):
# compare the current token type with the passed token
# type and if they match then "eat" the current token
# and assign the next token to the self.current_token,
# otherwise raise an exception.
if self.current_token.type == token_type:
self.current_token = self.get_next_token()
else:
self.error(
error_code=ErrorCode.UNEXPECTED_TOKEN,
token=self.current_token,
)

def program(self):
"""program : PROGRAM variable SEMI block DOT"""
self.eat(TokenType.PROGRAM)
var_node = self.variable()
prog_name = var_node.value
self.eat(TokenType.SEMI)
block_node = self.block()
program_node = Program(prog_name, block_node)
self.eat(TokenType.DOT)
return program_node

def block(self):
"""block : declarations compound_statement"""
declaration_nodes = self.declarations()
compound_statement_node = self.compound_statement()
node = Block(declaration_nodes, compound_statement_node)
return node

def declarations(self):
"""
declarations : (VAR (variable_declaration SEMI)+)? procedure_declaration*
"""
declarations = []

if self.current_token.type == TokenType.VAR:
self.eat(TokenType.VAR)
while self.current_token.type == TokenType.ID:
var_decl = self.variable_declaration()
declarations.extend(var_decl)
self.eat(TokenType.SEMI)

while self.current_token.type == TokenType.PROCEDURE:
proc_decl = self.procedure_declaration()
declarations.append(proc_decl)

return declarations

def formal_parameters(self):
""" formal_parameters : ID (COMMA ID)* COLON type_spec """
param_nodes = []

param_tokens = [self.current_token]
self.eat(TokenType.ID)
while self.current_token.type == TokenType.COMMA:
self.eat(TokenType.COMMA)
param_tokens.append(self.current_token)
self.eat(TokenType.ID)

self.eat(TokenType.COLON)
type_node = self.type_spec()

for param_token in param_tokens:
param_node = Param(Var(param_token), type_node)
param_nodes.append(param_node)

return param_nodes

def formal_parameter_list(self):
""" formal_parameter_list : formal_parameters
| formal_parameters SEMI formal_parameter_list
"""
# procedure Foo();
if not self.current_token.type == TokenType.ID:
return []

param_nodes = self.formal_parameters()

while self.current_token.type == TokenType.SEMI:
self.eat(TokenType.SEMI)
param_nodes.extend(self.formal_parameters())

return param_nodes

def variable_declaration(self):
"""variable_declaration : ID (COMMA ID)* COLON type_spec"""
var_nodes = [Var(self.current_token)] # first ID
self.eat(TokenType.ID)

while self.current_token.type == TokenType.COMMA:
self.eat(TokenType.COMMA)
var_nodes.append(Var(self.current_token))
self.eat(TokenType.ID)

self.eat(TokenType.COLON)

type_node = self.type_spec()
var_declarations = [
VarDecl(var_node, type_node)
for var_node in var_nodes
]
return var_declarations

def procedure_declaration(self):
"""procedure_declaration :
PROCEDURE ID (LPAREN formal_parameter_list RPAREN)? SEMI block SEMI
"""
self.eat(TokenType.PROCEDURE)
proc_name = self.current_token.value
self.eat(TokenType.ID)
params = []

if self.current_token.type == TokenType.LPAREN:
self.eat(TokenType.LPAREN)
params = self.formal_parameter_list()
self.eat(TokenType.RPAREN)

self.eat(TokenType.SEMI)
block_node = self.block()
proc_decl = ProcedureDecl(proc_name, params, block_node)
self.eat(TokenType.SEMI)
return proc_decl

def type_spec(self):
"""type_spec : INTEGER
| REAL
"""
token = self.current_token
if self.current_token.type == TokenType.INTEGER:
self.eat(TokenType.INTEGER)
else:
self.eat(TokenType.REAL)
node = Type(token)
return node

def compound_statement(self):
"""
compound_statement: BEGIN statement_list END
"""
self.eat(TokenType.BEGIN)
nodes = self.statement_list()
self.eat(TokenType.END)

root = Compound()
for node in nodes:
root.children.append(node)

return root

def statement_list(self):
"""
statement_list : statement
| statement SEMI statement_list
"""
node = self.statement()

results = [node]

while self.current_token.type == TokenType.SEMI:
self.eat(TokenType.SEMI)
results.append(self.statement())

return results

def statement(self):
"""
statement : compound_statement
| assignment_statement
| empty
"""
if self.current_token.type == TokenType.BEGIN:
node = self.compound_statement()
elif self.current_token.type == TokenType.ID:
node = self.assignment_statement()
else:
node = self.empty()
return node

def assignment_statement(self):
"""
assignment_statement : variable ASSIGN expr
"""
left = self.variable()
token = self.current_token
self.eat(TokenType.ASSIGN)
right = self.expr()
node = Assign(left, token, right)
return node

def variable(self):
"""
variable : ID
"""
node = Var(self.current_token)
self.eat(TokenType.ID)
return node

def empty(self):
"""An empty production"""
return NoOp()

def expr(self):
"""
expr : term ((PLUS | MINUS) term)*
"""
node = self.term()

while self.current_token.type in (TokenType.PLUS, TokenType.MINUS):
token = self.current_token
if token.type == TokenType.PLUS:
self.eat(TokenType.PLUS)
elif token.type == TokenType.MINUS:
self.eat(TokenType.MINUS)

node = BinOp(left=node, op=token, right=self.term())

return node

def term(self):
"""term : factor ((MUL | INTEGER_DIV | FLOAT_DIV) factor)*"""
node = self.factor()

while self.current_token.type in (
TokenType.MUL,
TokenType.INTEGER_DIV,
TokenType.FLOAT_DIV,
):
token = self.current_token
if token.type == TokenType.MUL:
self.eat(TokenType.MUL)
elif token.type == TokenType.INTEGER_DIV:
self.eat(TokenType.INTEGER_DIV)
elif token.type == TokenType.FLOAT_DIV:
self.eat(TokenType.FLOAT_DIV)

node = BinOp(left=node, op=token, right=self.factor())

return node

def factor(self):
"""factor : PLUS factor
| MINUS factor
| INTEGER_CONST
| REAL_CONST
| LPAREN expr RPAREN
| variable
"""
token = self.current_token
if token.type == TokenType.PLUS:
self.eat(TokenType.PLUS)
node = UnaryOp(token, self.factor())
return node
elif token.type == TokenType.MINUS:
self.eat(TokenType.MINUS)
node = UnaryOp(token, self.factor())
return node
elif token.type == TokenType.INTEGER_CONST:
self.eat(TokenType.INTEGER_CONST)
return Num(token)
elif token.type == TokenType.REAL_CONST:
self.eat(TokenType.REAL_CONST)
return Num(token)
elif token.type == TokenType.LPAREN:
self.eat(TokenType.LPAREN)
node = self.expr()
self.eat(TokenType.RPAREN)
return node
else:
node = self.variable()
return node

def parse(self):
"""
program : PROGRAM variable SEMI block DOT

block : declarations compound_statement

declarations : (VAR (variable_declaration SEMI)+)? procedure_declaration*

variable_declaration : ID (COMMA ID)* COLON type_spec

procedure_declaration :
PROCEDURE ID (LPAREN formal_parameter_list RPAREN)? SEMI block SEMI

formal_params_list : formal_parameters
| formal_parameters SEMI formal_parameter_list

formal_parameters : ID (COMMA ID)* COLON type_spec

type_spec : INTEGER | REAL

compound_statement : BEGIN statement_list END

statement_list : statement
| statement SEMI statement_list

statement : compound_statement
| assignment_statement
| empty

assignment_statement : variable ASSIGN expr

empty :

expr : term ((PLUS | MINUS) term)*

term : factor ((MUL | INTEGER_DIV | FLOAT_DIV) factor)*

factor : PLUS factor
| MINUS factor
| INTEGER_CONST
| REAL_CONST
| LPAREN expr RPAREN
| variable

variable: ID
"""
node = self.program()
if self.current_token.type != TokenType.EOF:
self.error(
error_code=ErrorCode.UNEXPECTED_TOKEN,
token=self.current_token,
)

return node


###############################################################################
# #
# AST visitors (walkers) #
# #
###############################################################################

class NodeVisitor(object):
def visit(self, node):
method_name = 'visit_' + type(node).__name__
visitor = getattr(self, method_name, self.generic_visit)
return visitor(node)

def generic_visit(self, node):
raise Exception('No visit_{} method'.format(type(node).__name__))


###############################################################################
# #
# SYMBOLS, TABLES, SEMANTIC ANALYSIS #
# #
###############################################################################

class Symbol(object):
def __init__(self, name, type=None):
self.name = name
self.type = type


class VarSymbol(Symbol):
def __init__(self, name, type):
super().__init__(name, type)

def __str__(self):
return "<{class_name}(name='{name}', type='{type}')>".format(
class_name=self.__class__.__name__,
name=self.name,
type=self.type,
)

__repr__ = __str__


class BuiltinTypeSymbol(Symbol):
def __init__(self, name):
super().__init__(name)

def __str__(self):
return self.name

def __repr__(self):
return "<{class_name}(name='{name}')>".format(
class_name=self.__class__.__name__,
name=self.name,
)


class ProcedureSymbol(Symbol):
def __init__(self, name, params=None):
super().__init__(name)
# a list of formal parameters
self.params = params if params is not None else []

def __str__(self):
return '<{class_name}(name={name}, parameters={params})>'.format(
class_name=self.__class__.__name__,
name=self.name,
params=self.params,
)

__repr__ = __str__


class ScopedSymbolTable(object):
def __init__(self, scope_name, scope_level, enclosing_scope=None):
self._symbols = {}
self.scope_name = scope_name
self.scope_level = scope_level
self.enclosing_scope = enclosing_scope

def _init_builtins(self):
self.insert(BuiltinTypeSymbol('INTEGER'))
self.insert(BuiltinTypeSymbol('REAL'))

def __str__(self):
h1 = 'SCOPE (SCOPED SYMBOL TABLE)'
lines = ['\n', h1, '=' * len(h1)]
for header_name, header_value in (
('Scope name', self.scope_name),
('Scope level', self.scope_level),
('Enclosing scope',
self.enclosing_scope.scope_name if self.enclosing_scope else None
)
):
lines.append('%-15s: %s' % (header_name, header_value))
h2 = 'Scope (Scoped symbol table) contents'
lines.extend([h2, '-' * len(h2)])
lines.extend(
('%7s: %r' % (key, value))
for key, value in self._symbols.items()
)
lines.append('\n')
s = '\n'.join(lines)
return s

__repr__ = __str__

def log(self, msg):
if _SHOULD_LOG_SCOPE:
print(msg)

def insert(self, symbol):
self.log(f'Insert: {symbol.name}')
self._symbols[symbol.name] = symbol

def lookup(self, name, current_scope_only=False):
self.log(f'Lookup: {name}. (Scope name: {self.scope_name})')
# 'symbol' is either an instance of the Symbol class or None
symbol = self._symbols.get(name)

if symbol is not None:
return symbol

if current_scope_only:
return None

# recursively go up the chain and lookup the name
if self.enclosing_scope is not None:
return self.enclosing_scope.lookup(name)


class SemanticAnalyzer(NodeVisitor):
def __init__(self):
self.current_scope = None

def log(self, msg):
if _SHOULD_LOG_SCOPE:
print(msg)

def error(self, error_code, token):
raise SemanticError(
error_code=error_code,
token=token,
message=f'{error_code.value} -> {token}',
)

def visit_Block(self, node):
for declaration in node.declarations:
self.visit(declaration)
self.visit(node.compound_statement)

def visit_Program(self, node):
self.log('ENTER scope: global')
global_scope = ScopedSymbolTable(
scope_name='global',
scope_level=1,
enclosing_scope=self.current_scope, # None
)
global_scope._init_builtins()
self.current_scope = global_scope

# visit subtree
self.visit(node.block)

self.log(global_scope)

self.current_scope = self.current_scope.enclosing_scope
self.log('LEAVE scope: global')

def visit_Compound(self, node):
for child in node.children:
self.visit(child)

def visit_NoOp(self, node):
pass

def visit_BinOp(self, node):
self.visit(node.left)
self.visit(node.right)

def visit_ProcedureDecl(self, node):
proc_name = node.proc_name
proc_symbol = ProcedureSymbol(proc_name)
self.current_scope.insert(proc_symbol)

self.log(f'ENTER scope: {proc_name}')
# Scope for parameters and local variables
procedure_scope = ScopedSymbolTable(
scope_name=proc_name,
scope_level=self.current_scope.scope_level + 1,
enclosing_scope=self.current_scope
)
self.current_scope = procedure_scope

# Insert parameters into the procedure scope
for param in node.params:
param_type = self.current_scope.lookup(param.type_node.value)
param_name = param.var_node.value
var_symbol = VarSymbol(param_name, param_type)
self.current_scope.insert(var_symbol)
proc_symbol.params.append(var_symbol)

self.visit(node.block_node)

self.log(procedure_scope)

self.current_scope = self.current_scope.enclosing_scope
self.log(f'LEAVE scope: {proc_name}')

def visit_VarDecl(self, node):
type_name = node.type_node.value
type_symbol = self.current_scope.lookup(type_name)

# We have all the information we need to create a variable symbol.
# Create the symbol and insert it into the symbol table.
var_name = node.var_node.value
var_symbol = VarSymbol(var_name, type_symbol)

# Signal an error if the table already has a symbol
# with the same name
if self.current_scope.lookup(var_name, current_scope_only=True):
self.error(
error_code=ErrorCode.DUPLICATE_ID,
token=node.var_node.token,
)

self.current_scope.insert(var_symbol)

def visit_Assign(self, node):
# right-hand side
self.visit(node.right)
# left-hand side
self.visit(node.left)

def visit_Var(self, node):
var_name = node.value
var_symbol = self.current_scope.lookup(var_name)
if var_symbol is None:
self.error(error_code=ErrorCode.ID_NOT_FOUND, token=node.token)

def visit_Num(self, node):
pass

def visit_UnaryOp(self, node):
pass


###############################################################################
# #
# INTERPRETER #
# #
###############################################################################

class Interpreter(NodeVisitor):
def __init__(self, tree):
self.tree = tree
self.GLOBAL_MEMORY = {}

def visit_Program(self, node):
self.visit(node.block)

def visit_Block(self, node):
for declaration in node.declarations:
self.visit(declaration)
self.visit(node.compound_statement)

def visit_VarDecl(self, node):
# Do nothing
pass

def visit_Type(self, node):
# Do nothing
pass

def visit_BinOp(self, node):
if node.op.type == TokenType.PLUS:
return self.visit(node.left) + self.visit(node.right)
elif node.op.type == TokenType.MINUS:
return self.visit(node.left) - self.visit(node.right)
elif node.op.type == TokenType.MUL:
return self.visit(node.left) * self.visit(node.right)
elif node.op.type == TokenType.INTEGER_DIV:
return self.visit(node.left) // self.visit(node.right)
elif node.op.type == TokenType.FLOAT_DIV:
return float(self.visit(node.left)) / float(self.visit(node.right))

def visit_Num(self, node):
return node.value

def visit_UnaryOp(self, node):
op = node.op.type
if op == TokenType.PLUS:
return +self.visit(node.expr)
elif op == TokenType.MINUS:
return -self.visit(node.expr)

def visit_Compound(self, node):
for child in node.children:
self.visit(child)

def visit_Assign(self, node):
var_name = node.left.value
var_value = self.visit(node.right)
self.GLOBAL_MEMORY[var_name] = var_value

def visit_Var(self, node):
var_name = node.value
var_value = self.GLOBAL_MEMORY.get(var_name)
return var_value

def visit_NoOp(self, node):
pass

def visit_ProcedureDecl(self, node):
pass

def interpret(self):
tree = self.tree
if tree is None:
return ''
return self.visit(tree)


def main():
parser = argparse.ArgumentParser(
description='SPI - Simple Pascal Interpreter'
)
parser.add_argument('inputfile', help='Pascal source file')
parser.add_argument(
'--scope',
help='Print scope information',
action='store_true',
)
args = parser.parse_args()
global _SHOULD_LOG_SCOPE
_SHOULD_LOG_SCOPE = args.scope

text = open(args.inputfile, 'r').read()

lexer = Lexer(text)
try:
parser = Parser(lexer)
tree = parser.parse()
except (LexerError, ParserError) as e:
print(e.message)
sys.exit(1)

semantic_analyzer = SemanticAnalyzer()
try:
semantic_analyzer.visit(tree)
except SemanticError as e:
print(e.message)
sys.exit(1)

interpreter = Interpreter(tree)
interpreter.interpret()


if __name__ == '__main__':
main()

07 优化与重构 | 《Let’s Build A Simple Interpreter》笔记

http://www.zh0ngtian.tech/posts/42fcef67.html

作者

zhongtian

发布于

2021-08-28

更新于

2023-12-16

许可协议

评论