-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathScanner.py
500 lines (451 loc) · 24.5 KB
/
Scanner.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
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
import sys
from collections import deque
class Scanner(object):
DEFAULT_BUFFER_SIZE = 100000 # default maximum number of tokens present in the token stream
CATEGORY_STR_SIZE = 9 # number of characters in the formatted category string of a token
def __init__(self, filepath, buffer_size=DEFAULT_BUFFER_SIZE, verbose=False):
self.__filepath = filepath # initialize all fields
self.__buffer_size = buffer_size
self.__token_buffer = deque()
self.__input_pos = 0
self.__input_stream = ""
self.__line_id = 1
self.__num_bytes = 0
self.__verbose = verbose
def print_tokens(self):
self.__verbose = True # set the verbose flag True
while True: # enter an infinite loop - check below for termination criteria
current_token = self.next_token() # extract the next token
if "EOF" in current_token: # if the end of file has not been reached
break # exit infinite loop
self.__verbose = False # reset the verbose flag to False
def next_token(self):
if not len(self.token_buffer): # if the token stream is empty
self.__populate_buffer() # extract and load more tokens
return self.token_buffer.popleft() # return the next token
def __populate_buffer(self):
file_reader = open(self.filepath) # obtain a file reader object
file_reader.seek(self.num_bytes) # move the file pointer appropriately
# as long as the maximum buffer size has not been reached
while len(self.token_buffer) <= self.buffer_size:
if self.input_pos >= len(self.input_stream): # if the current line has been entirely scanned
current_line = Scanner.__readline(file_reader) # read the next line in the file
if not len(current_line): # if the next line is empty
current_token = "< " + "EOF" + ", " + " (" + str(self.line_id) + ") >"
if self.verbose: # if verbose mode is on
print(Scanner.__construct_token_str(current_token)) # print the next token
# append the EOF token along with the line number to the token stream
self.token_buffer.append(current_token)
break # exit the while loop
self.__initialize(current_line) # otherwise re-initialize the scanner with the next line
current_token = self.__run() # extract the next token
if "EOF" in current_token: # handle this edge case for end of line
continue
# if verbose mode is on and the token is not invalid
if self.verbose and "INVALID" not in current_token:
print(Scanner.__construct_token_str(current_token)) # print the next token
# append the next token along with the line number to the token stream
self.token_buffer.append(current_token)
self.num_bytes = file_reader.tell() # record the number of bytes read so far
file_reader.close() # close the file reader object
def __run(self):
while True: # enter an infinite loop
if self.input_pos >= len(self.input_stream): # if the current line has been entirely scanned
# return the EOF token
return "< " + "EOF" + ", " + " (" + str(self.line_id) + ") >"
elif not 0 <= ord(self.input_stream[self.input_pos]) <= 127: # if the input character is not ASCII
sys.stderr.write(
" ".join(
list([
"Lexical error:",
str(self.line_id) + ":",
"\"" + self.input_stream[self.input_pos] + "\"",
"is not a valid ASCII character."
])
)
) # print an appropriate error
self.input_pos += 1 # advance the file pointer
continue
# if the current character is a whitespace
elif self.input_stream[self.input_pos] == " ":
self.input_pos += 1 # advance the file pointer
continue
# if the current character is a newline
elif self.input_stream[self.input_pos] == "\t":
self.input_pos += 1 # advance the file pointer
continue
# if the current character is a newline
elif self.input_stream[self.input_pos] == "\n":
self.input_pos += 1 # advance the file pointer
self.line_id += 1 # update line id counter
continue
# if the current line is a comment
elif self.input_stream[self.input_pos] == "/" and \
self.input_stream[self.input_pos + 1] == "/":
self.__ignore_comment() # skip the current line
continue
break
lexeme = ""
update_current_lexeme = self.__update_current_lexeme
if self.input_stream[self.input_pos] == "s":
lexeme = update_current_lexeme(lexeme)
if self.input_stream[self.input_pos] == "t":
lexeme = update_current_lexeme(lexeme)
if self.input_stream[self.input_pos] == "o":
lexeme = update_current_lexeme(lexeme)
if self.input_stream[self.input_pos] == "r":
lexeme = update_current_lexeme(lexeme)
if self.input_stream[self.input_pos] == "e": # "store" lexeme recognized
lexeme = update_current_lexeme(lexeme)
return "< " + "MEMOP" + ", " + lexeme + " (" + str(self.line_id) + ") >"
else:
lexeme = update_current_lexeme(lexeme)
token = "< " + "INVALID" + ", " + lexeme + " (" + str(self.line_id) + ") >"
self.__print_error(lexeme)
return token
else:
lexeme = update_current_lexeme(lexeme)
token = "< " + "INVALID" + ", " + lexeme + " (" + str(self.line_id) + ") >"
self.__print_error(lexeme)
return token
else:
lexeme = update_current_lexeme(lexeme)
token = "< " + "INVALID" + ", " + lexeme + " (" + str(self.line_id) + ") >"
self.__print_error(lexeme)
return token
elif self.input_stream[self.input_pos] == "u":
lexeme = update_current_lexeme(lexeme)
if self.input_stream[self.input_pos] == "b": # "sub" lexeme recognized
lexeme = update_current_lexeme(lexeme)
return "< " + "ARITHOP" + ", " + lexeme + " (" + str(self.line_id) + ") >"
else:
lexeme = update_current_lexeme(lexeme)
token = "< " + "INVALID" + ", " + lexeme + " (" + str(self.line_id) + ") >"
self.__print_error(lexeme)
return token
else:
lexeme = update_current_lexeme(lexeme)
token = "< " + "INVALID" + ", " + lexeme + " (" + str(self.line_id) + ") >"
self.__print_error(lexeme)
return token
elif self.input_stream[self.input_pos] == "l":
lexeme = update_current_lexeme(lexeme)
if self.input_stream[self.input_pos] == "o":
lexeme = update_current_lexeme(lexeme)
if self.input_stream[self.input_pos] == "a":
lexeme = update_current_lexeme(lexeme)
# "load" lexeme recognized
if self.input_stream[self.input_pos] == "d" and self.input_stream[self.input_pos + 1] != "I":
lexeme = update_current_lexeme(lexeme)
return "< " + "MEMOP" + ", " + lexeme + " (" + str(self.line_id) + ") >"
# "loadI" lexeme recognized
elif self.input_stream[self.input_pos] == "d" and self.input_stream[self.input_pos + 1] == "I":
lexeme = update_current_lexeme(lexeme)
lexeme = update_current_lexeme(lexeme)
return "< " + "LOADI" + ", " + lexeme + " (" + str(self.line_id) + ") >"
else:
lexeme = update_current_lexeme(lexeme)
token = "< " + "INVALID" + ", " + lexeme + " (" + str(self.line_id) + ") >"
self.__print_error(lexeme)
return token
else:
lexeme = update_current_lexeme(lexeme)
token = "< " + "INVALID" + ", " + lexeme + " (" + str(self.line_id) + ") >"
self.__print_error(lexeme)
return token
elif self.input_stream[self.input_pos] == "s":
lexeme = update_current_lexeme(lexeme)
if self.input_stream[self.input_pos] == "h":
lexeme = update_current_lexeme(lexeme)
if self.input_stream[self.input_pos] == "i":
lexeme = update_current_lexeme(lexeme)
if self.input_stream[self.input_pos] == "f":
lexeme = update_current_lexeme(lexeme)
if self.input_stream[self.input_pos] == "t": # "lshift" lexeme recognized
lexeme = update_current_lexeme(lexeme)
return "< " + "ARITHOP" + ", " + lexeme + " (" + str(self.line_id) + ") >"
else:
lexeme = update_current_lexeme(lexeme)
token = "< " + "INVALID" + ", " + lexeme + " (" + str(self.line_id) + ") >"
self.__print_error(lexeme)
return token
else:
lexeme = update_current_lexeme(lexeme)
token = "< " + "INVALID" + ", " + lexeme + " (" + str(self.line_id) + ") >"
self.__print_error(lexeme)
return token
else:
lexeme = update_current_lexeme(lexeme)
token = "< " + "INVALID" + ", " + lexeme + " (" + str(self.line_id) + ") >"
self.__print_error(lexeme)
return token
else:
lexeme = update_current_lexeme(lexeme)
token = "< " + "INVALID" + ", " + lexeme + " (" + str(self.line_id) + ") >"
self.__print_error(lexeme)
return token
else:
lexeme = update_current_lexeme(lexeme)
token = "< " + "INVALID" + ", " + lexeme + " (" + str(self.line_id) + ") >"
self.__print_error(lexeme)
return token
elif self.input_stream[self.input_pos] == "r":
lexeme = update_current_lexeme(lexeme)
if self.input_stream[self.input_pos] == "s":
lexeme = update_current_lexeme(lexeme)
if self.input_stream[self.input_pos] == "h":
lexeme = update_current_lexeme(lexeme)
if self.input_stream[self.input_pos] == "i":
lexeme = update_current_lexeme(lexeme)
if self.input_stream[self.input_pos] == "f":
lexeme = update_current_lexeme(lexeme)
if self.input_stream[self.input_pos] == "t": # "rshift" lexeme recognized
lexeme = update_current_lexeme(lexeme)
return "< " + "ARITHOP" + ", " + lexeme + " (" + str(self.line_id) + ") >"
else:
lexeme = update_current_lexeme(lexeme)
token = "< " + "INVALID" + ", " + lexeme + " (" + str(self.line_id) + ") >"
self.__print_error(lexeme)
return token
else:
lexeme = update_current_lexeme(lexeme)
token = "< " + "INVALID" + ", " + lexeme + " (" + str(self.line_id) + ") >"
self.__print_error(lexeme)
return token
else:
lexeme = update_current_lexeme(lexeme)
token = "< " + "INVALID" + ", " + lexeme + " (" + str(self.line_id) + ") >"
self.__print_error(lexeme)
return token
else:
lexeme = update_current_lexeme(lexeme)
token = "< " + "INVALID" + ", " + lexeme + " (" + str(self.line_id) + ") >"
self.__print_error(lexeme)
return token
elif self.input_stream[self.input_pos] in "0123456789": # register lexeme recognized
lexeme = update_current_lexeme(lexeme)
while self.input_stream[self.input_pos] in "0123456789":
lexeme = update_current_lexeme(lexeme)
return "< " + "REG" + ", " + lexeme + " (" + str(self.line_id) + ") >"
else:
lexeme = update_current_lexeme(lexeme)
token = "< " + "INVALID" + ", " + lexeme + " (" + str(self.line_id) + ") >"
self.__print_error(lexeme)
return token
elif self.input_stream[self.input_pos] == "m":
lexeme = update_current_lexeme(lexeme)
if self.input_stream[self.input_pos] == "u":
lexeme = update_current_lexeme(lexeme)
if self.input_stream[self.input_pos] == "l":
lexeme = update_current_lexeme(lexeme)
if self.input_stream[self.input_pos] == "t": # "mult" lexeme recognized
lexeme = update_current_lexeme(lexeme)
return "< " + "ARITHOP" + ", " + lexeme + " (" + str(self.line_id) + ") >"
else:
lexeme = update_current_lexeme(lexeme)
token = "< " + "INVALID" + ", " + lexeme + " (" + str(self.line_id) + ") >"
self.__print_error(lexeme)
return token
else:
lexeme = update_current_lexeme(lexeme)
token = "< " + "INVALID" + ", " + lexeme + " (" + str(self.line_id) + ") >"
self.__print_error(lexeme)
return token
else:
lexeme = update_current_lexeme(lexeme)
token = "< " + "INVALID" + ", " + lexeme + " (" + str(self.line_id) + ") >"
self.__print_error(lexeme)
return token
elif self.input_stream[self.input_pos] == "a":
lexeme = update_current_lexeme(lexeme)
if self.input_stream[self.input_pos] == "d":
lexeme = update_current_lexeme(lexeme)
if self.input_stream[self.input_pos] == "d": # "add" lexeme recognized
lexeme = update_current_lexeme(lexeme)
return "< " + "ARITHOP" + ", " + lexeme + " (" + str(self.line_id) + ") >"
else:
lexeme = update_current_lexeme(lexeme)
token = "< " + "INVALID" + ", " + lexeme + " (" + str(self.line_id) + ") >"
self.__print_error(lexeme)
return token
else:
lexeme = update_current_lexeme(lexeme)
token = "< " + "INVALID" + ", " + lexeme + " (" + str(self.line_id) + ") >"
self.__print_error(lexeme)
return token
elif self.input_stream[self.input_pos] == "n":
lexeme = update_current_lexeme(lexeme)
if self.input_stream[self.input_pos] == "o":
lexeme = update_current_lexeme(lexeme)
if self.input_stream[self.input_pos] == "p": # "nop" lexeme recognized
lexeme = update_current_lexeme(lexeme)
return "< " + "NOP" + ", " + lexeme + " (" + str(self.line_id) + ") >"
else:
lexeme = update_current_lexeme(lexeme)
token = "< " + "INVALID" + ", " + lexeme + " (" + str(self.line_id) + ") >"
self.__print_error(lexeme)
return token
else:
lexeme = update_current_lexeme(lexeme)
token = "< " + "INVALID" + ", " + lexeme + " (" + str(self.line_id) + ") >"
self.__print_error(lexeme)
return token
elif self.input_stream[self.input_pos] == "o":
lexeme = update_current_lexeme(lexeme)
if self.input_stream[self.input_pos] == "u":
lexeme = update_current_lexeme(lexeme)
if self.input_stream[self.input_pos] == "t":
lexeme = update_current_lexeme(lexeme)
if self.input_stream[self.input_pos] == "p":
lexeme = update_current_lexeme(lexeme)
if self.input_stream[self.input_pos] == "u":
lexeme = update_current_lexeme(lexeme)
if self.input_stream[self.input_pos] == "t": # "output" lexeme recognized
lexeme = update_current_lexeme(lexeme)
return "< " + "OUTPUT" + ", " + lexeme + " (" + str(self.line_id) + ") >"
else:
lexeme = update_current_lexeme(lexeme)
token = "< " + "INVALID" + ", " + lexeme + " (" + str(self.line_id) + ") >"
self.__print_error(lexeme)
return token
else:
lexeme = update_current_lexeme(lexeme)
token = "< " + "INVALID" + ", " + lexeme + " (" + str(self.line_id) + ") >"
self.__print_error(lexeme)
return token
else:
lexeme = update_current_lexeme(lexeme)
token = "< " + "INVALID" + ", " + lexeme + " (" + str(self.line_id) + ") >"
self.__print_error(lexeme)
return token
else:
lexeme = update_current_lexeme(lexeme)
token = "< " + "INVALID" + ", " + lexeme + " (" + str(self.line_id) + ") >"
self.__print_error(lexeme)
return token
else:
lexeme = update_current_lexeme(lexeme)
token = "< " + "INVALID" + ", " + lexeme + " (" + str(self.line_id) + ") >"
self.__print_error(lexeme)
return token
elif self.input_stream[self.input_pos] in "0123456789": # constant lexeme recognized
lexeme = update_current_lexeme(lexeme)
while self.input_stream[self.input_pos] in "0123456789":
lexeme = update_current_lexeme(lexeme)
return "< " + "CONSTANT" + ", " + lexeme + " (" + str(self.line_id) + ") >"
elif self.input_stream[self.input_pos] == "=":
lexeme = update_current_lexeme(lexeme)
if self.input_stream[self.input_pos] == ">": # "=>" lexeme recognized
lexeme = update_current_lexeme(lexeme)
return "< " + "INTO" + ", " + lexeme + " (" + str(self.line_id) + ") >"
else:
lexeme = update_current_lexeme(lexeme)
token = "< " + "INVALID" + ", " + lexeme + " (" + str(self.line_id) + ") >"
self.__print_error(lexeme)
return token
elif self.input_stream[self.input_pos] == ",": # "," lexeme recognized
lexeme = update_current_lexeme(lexeme)
return "< " + "COMMA" + ", " + lexeme + " (" + str(self.line_id) + ") >"
else:
lexeme = update_current_lexeme(lexeme)
token = "< " + "INVALID" + ", " + lexeme + " (" + str(self.line_id) + ") >"
self.__print_error(lexeme)
return token
def __update_current_lexeme(self, lexeme):
self.input_pos += 1 # advance the file pointer
return lexeme + self.input_stream[self.input_pos - 1] # return the updated lexeme
def __initialize(self, input_stream):
self.input_pos = 0
self.input_stream = input_stream
def __ignore_comment(self):
while not self.input_stream[self.input_pos] == "\n" and \
self.input_pos < len(self.input_stream):
self.input_pos += 1 # skip the current character
@staticmethod
def __readline(file_reader):
next_line = ""
while True:
next_char = file_reader.read(1)
next_line += next_char
if next_char == "\n" or next_char == "":
break
return next_line
@staticmethod
def process_token(token):
processed_token = token.lstrip("< ").rstrip(" >") # strip off the outer substrings
# extract the line number
line_number = processed_token.split()[-1].lstrip("(").rstrip(")")
# if the token signifies the EOF, handle the special case
if "EOF" in processed_token:
return line_number, "EOF", str()
else: # otherwise
syntactic_category, lexeme = processed_token.split(", ", 1)
lexeme = lexeme.split()[0]
return line_number, syntactic_category, lexeme # return the post-processed constituents
@staticmethod
def __construct_token_str(token):
line_number, syntactic_category, lexeme = Scanner.process_token(token)
while len(syntactic_category) < Scanner.CATEGORY_STR_SIZE:
syntactic_category += " "
return line_number + ": < " + syntactic_category + ", \"" + lexeme + "\" >"
def __print_error(self, lexeme):
sys.stderr.write(
" ".join(
list([
"Lexical error:",
str(self.line_id) + ":",
"\"" + lexeme + "\"",
"is not a valid word.\n"
])
)
) # print the error message to stderr
self.line_id += 1 # skip to the next line
self.input_pos = len(self.input_stream)
@property
def filepath(self):
return self.__filepath # return the file path
@filepath.setter
def filepath(self, filepath):
self.__filepath = filepath # set the current file path to the input file path
@property
def buffer_size(self):
return self.__buffer_size # return the maximum size of the token buffer
@buffer_size.setter
def buffer_size(self, buffer_size):
self.__buffer_size = buffer_size # set the current buffer size to the input buffer size
@property
def token_buffer(self):
return self.__token_buffer # return the token stream
@token_buffer.setter
def token_buffer(self, token_buffer):
self.__token_buffer = deque(iterable=token_buffer)
@property
def input_pos(self):
return self.__input_pos # return the input position
@input_pos.setter
def input_pos(self, input_pos):
self.__input_pos = input_pos # set the current input position to the input input position
@property
def input_stream(self):
return self.__input_stream # return the input stream
@input_stream.setter
def input_stream(self, input_stream):
self.__input_stream = input_stream # set the current input stream to the input input stream
@property
def line_id(self):
return self.__line_id # return the number of lines scanned
@line_id.setter
def line_id(self, line_id):
self.__line_id = line_id # set the current number of lines to the input number of lines
@property
def num_bytes(self):
return self.__num_bytes # return the number of bytes
@num_bytes.setter
def num_bytes(self, num_bytes):
self.__num_bytes = num_bytes # set the current number of bytes to the input number of bytes
@property
def verbose(self):
return self.__verbose # return the verbose flag
@verbose.setter
def verbose(self, verbose):
self.__verbose = verbose # set the current verbose flag to the input verbose flag