summaryrefslogtreecommitdiff
path: root/BaseTools/Source/Python/Eot/CodeFragmentCollector.py
blob: 349f934304df704e25ad4f77219ce13dafbe6f35 (plain)
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
## @file
# preprocess source file
#
#  Copyright (c) 2007 ~ 2010, Intel Corporation
#
#  All rights reserved. This program and the accompanying materials
#  are licensed and made available under the terms and conditions of the BSD License
#  which accompanies this distribution.  The full text of the license may be found at
#  http://opensource.org/licenses/bsd-license.php
#
#  THE PROGRAM IS DISTRIBUTED UNDER THE BSD LICENSE ON AN "AS IS" BASIS,
#  WITHOUT WARRANTIES OR REPRESENTATIONS OF ANY KIND, EITHER EXPRESS OR IMPLIED.
#

##
# Import Modules
#
import re
import os
import sys

import antlr3
from CLexer import CLexer
from CParser import CParser

import FileProfile
from CodeFragment import PP_Directive
from ParserWarning import Warning


##define T_CHAR_SPACE                ' '
##define T_CHAR_NULL                 '\0'
##define T_CHAR_CR                   '\r'
##define T_CHAR_TAB                  '\t'
##define T_CHAR_LF                   '\n'
##define T_CHAR_SLASH                '/'
##define T_CHAR_BACKSLASH            '\\'
##define T_CHAR_DOUBLE_QUOTE         '\"'
##define T_CHAR_SINGLE_QUOTE         '\''
##define T_CHAR_STAR                 '*'
##define T_CHAR_HASH                 '#'

(T_CHAR_SPACE, T_CHAR_NULL, T_CHAR_CR, T_CHAR_TAB, T_CHAR_LF, T_CHAR_SLASH, \
T_CHAR_BACKSLASH, T_CHAR_DOUBLE_QUOTE, T_CHAR_SINGLE_QUOTE, T_CHAR_STAR, T_CHAR_HASH) = \
(' ', '\0', '\r', '\t', '\n', '/', '\\', '\"', '\'', '*', '#')

SEPERATOR_TUPLE = ('=', '|', ',', '{', '}')

(T_COMMENT_TWO_SLASH, T_COMMENT_SLASH_STAR) = (0, 1)

(T_PP_INCLUDE, T_PP_DEFINE, T_PP_OTHERS) = (0, 1, 2)

## The collector for source code fragments.
#
# PreprocessFile method should be called prior to ParseFile
#
# GetNext*** procedures mean these procedures will get next token first, then make judgement.
# Get*** procedures mean these procedures will make judgement on current token only.
#
class CodeFragmentCollector:
    ## The constructor
    #
    #   @param  self        The object pointer
    #   @param  FileName    The file that to be parsed
    #
    def __init__(self, FileName):
        self.Profile = FileProfile.FileProfile(FileName)
        self.Profile.FileLinesList.append(T_CHAR_LF)
        self.FileName = FileName
        self.CurrentLineNumber = 1
        self.CurrentOffsetWithinLine = 0

        self.__Token = ""
        self.__SkippedChars = ""

    ## __IsWhiteSpace() method
    #
    #   Whether char at current FileBufferPos is whitespace
    #
    #   @param  self        The object pointer
    #   @param  Char        The char to test
    #   @retval True        The char is a kind of white space
    #   @retval False       The char is NOT a kind of white space
    #
    def __IsWhiteSpace(self, Char):
        if Char in (T_CHAR_NULL, T_CHAR_CR, T_CHAR_SPACE, T_CHAR_TAB, T_CHAR_LF):
            return True
        else:
            return False

    ## __SkipWhiteSpace() method
    #
    #   Skip white spaces from current char, return number of chars skipped
    #
    #   @param  self        The object pointer
    #   @retval Count       The number of chars skipped
    #
    def __SkipWhiteSpace(self):
        Count = 0
        while not self.__EndOfFile():
            Count += 1
            if self.__CurrentChar() in (T_CHAR_NULL, T_CHAR_CR, T_CHAR_LF, T_CHAR_SPACE, T_CHAR_TAB):
                self.__SkippedChars += str(self.__CurrentChar())
                self.__GetOneChar()

            else:
                Count = Count - 1
                return Count

    ## __EndOfFile() method
    #
    #   Judge current buffer pos is at file end
    #
    #   @param  self        The object pointer
    #   @retval True        Current File buffer position is at file end
    #   @retval False       Current File buffer position is NOT at file end
    #
    def __EndOfFile(self):
        NumberOfLines = len(self.Profile.FileLinesList)
        SizeOfLastLine = len(self.Profile.FileLinesList[-1])
        if self.CurrentLineNumber == NumberOfLines and self.CurrentOffsetWithinLine >= SizeOfLastLine - 1:
            return True
        elif self.CurrentLineNumber > NumberOfLines:
            return True
        else:
            return False

    ## __EndOfLine() method
    #
    #   Judge current buffer pos is at line end
    #
    #   @param  self        The object pointer
    #   @retval True        Current File buffer position is at line end
    #   @retval False       Current File buffer position is NOT at line end
    #
    def __EndOfLine(self):
        SizeOfCurrentLine = len(self.Profile.FileLinesList[self.CurrentLineNumber - 1])
        if self.CurrentOffsetWithinLine >= SizeOfCurrentLine - 1:
            return True
        else:
            return False

    ## Rewind() method
    #
    #   Reset file data buffer to the initial state
    #
    #   @param  self        The object pointer
    #
    def Rewind(self):
        self.CurrentLineNumber = 1
        self.CurrentOffsetWithinLine = 0

    ## __UndoOneChar() method
    #
    #   Go back one char in the file buffer
    #
    #   @param  self        The object pointer
    #   @retval True        Successfully go back one char
    #   @retval False       Not able to go back one char as file beginning reached
    #
    def __UndoOneChar(self):

        if self.CurrentLineNumber == 1 and self.CurrentOffsetWithinLine == 0:
            return False
        elif self.CurrentOffsetWithinLine == 0:
            self.CurrentLineNumber -= 1
            self.CurrentOffsetWithinLine = len(self.__CurrentLine()) - 1
        else:
            self.CurrentOffsetWithinLine -= 1
        return True

    ## __GetOneChar() method
    #
    #   Move forward one char in the file buffer
    #
    #   @param  self        The object pointer
    #
    def __GetOneChar(self):
        if self.CurrentOffsetWithinLine == len(self.Profile.FileLinesList[self.CurrentLineNumber - 1]) - 1:
                self.CurrentLineNumber += 1
                self.CurrentOffsetWithinLine = 0
        else:
                self.CurrentOffsetWithinLine += 1

    ## __CurrentChar() method
    #
    #   Get the char pointed to by the file buffer pointer
    #
    #   @param  self        The object pointer
    #   @retval Char        Current char
    #
    def __CurrentChar(self):
        CurrentChar = self.Profile.FileLinesList[self.CurrentLineNumber - 1][self.CurrentOffsetWithinLine]

        return CurrentChar

    ## __NextChar() method
    #
    #   Get the one char pass the char pointed to by the file buffer pointer
    #
    #   @param  self        The object pointer
    #   @retval Char        Next char
    #
    def __NextChar(self):
        if self.CurrentOffsetWithinLine == len(self.Profile.FileLinesList[self.CurrentLineNumber - 1]) - 1:
            return self.Profile.FileLinesList[self.CurrentLineNumber][0]
        else:
            return self.Profile.FileLinesList[self.CurrentLineNumber - 1][self.CurrentOffsetWithinLine + 1]

    ## __SetCurrentCharValue() method
    #
    #   Modify the value of current char
    #
    #   @param  self        The object pointer
    #   @param  Value       The new value of current char
    #
    def __SetCurrentCharValue(self, Value):
        self.Profile.FileLinesList[self.CurrentLineNumber - 1][self.CurrentOffsetWithinLine] = Value

    ## __SetCharValue() method
    #
    #   Modify the value of current char
    #
    #   @param  self        The object pointer
    #   @param  Value       The new value of current char
    #
    def __SetCharValue(self, Line, Offset, Value):
        self.Profile.FileLinesList[Line - 1][Offset] = Value

    ## __CurrentLine() method
    #
    #   Get the list that contains current line contents
    #
    #   @param  self        The object pointer
    #   @retval List        current line contents
    #
    def __CurrentLine(self):
        return self.Profile.FileLinesList[self.CurrentLineNumber - 1]

    ## __InsertComma() method
    #
    #   Insert ',' to replace PP
    #
    #   @param  self        The object pointer
    #   @retval List        current line contents
    #
    def __InsertComma(self, Line):


        if self.Profile.FileLinesList[Line - 1][0] != T_CHAR_HASH:
            BeforeHashPart = str(self.Profile.FileLinesList[Line - 1]).split(T_CHAR_HASH)[0]
            if BeforeHashPart.rstrip().endswith(T_CHAR_COMMA) or BeforeHashPart.rstrip().endswith(';'):
                return

        if Line - 2 >= 0 and str(self.Profile.FileLinesList[Line - 2]).rstrip().endswith(','):
            return

        if Line - 2 >= 0 and str(self.Profile.FileLinesList[Line - 2]).rstrip().endswith(';'):
            return

        if str(self.Profile.FileLinesList[Line]).lstrip().startswith(',') or str(self.Profile.FileLinesList[Line]).lstrip().startswith(';'):
            return

        self.Profile.FileLinesList[Line - 1].insert(self.CurrentOffsetWithinLine, ',')

    ## PreprocessFileWithClear() method
    #
    # Run a preprocess for the file to clean all comments
    #
    # @param  self        The object pointer
    #
    def PreprocessFileWithClear(self):

        self.Rewind()
        InComment = False
        DoubleSlashComment = False
        HashComment = False
        PPExtend = False
        PPDirectiveObj = None
        # HashComment in quoted string " " is ignored.
        InString = False
        InCharLiteral = False

        self.Profile.FileLinesList = [list(s) for s in self.Profile.FileLinesListFromFile]
        while not self.__EndOfFile():

            if not InComment and self.__CurrentChar() == T_CHAR_DOUBLE_QUOTE:
                InString = not InString

            if not InComment and self.__CurrentChar() == T_CHAR_SINGLE_QUOTE:
                InCharLiteral = not InCharLiteral
            # meet new line, then no longer in a comment for // and '#'
            if self.__CurrentChar() == T_CHAR_LF:
                if HashComment and PPDirectiveObj != None:
                    if PPDirectiveObj.Content.rstrip(T_CHAR_CR).endswith(T_CHAR_BACKSLASH):
                        PPDirectiveObj.Content += T_CHAR_LF
                        PPExtend = True
                    else:
                        PPExtend = False

                EndLinePos = (self.CurrentLineNumber, self.CurrentOffsetWithinLine)

                if InComment and DoubleSlashComment:
                    InComment = False
                    DoubleSlashComment = False

                if InComment and HashComment and not PPExtend:
                    InComment = False
                    HashComment = False
                    PPDirectiveObj.Content += T_CHAR_LF
                    PPDirectiveObj.EndPos = EndLinePos
                    FileProfile.PPDirectiveList.append(PPDirectiveObj)
                    PPDirectiveObj = None

                if InString or InCharLiteral:
                    CurrentLine = "".join(self.__CurrentLine())
                    if CurrentLine.rstrip(T_CHAR_LF).rstrip(T_CHAR_CR).endswith(T_CHAR_BACKSLASH):
                        SlashIndex = CurrentLine.rindex(T_CHAR_BACKSLASH)
                        self.__SetCharValue(self.CurrentLineNumber, SlashIndex, T_CHAR_SPACE)

                self.CurrentLineNumber += 1
                self.CurrentOffsetWithinLine = 0
            # check for */ comment end
            elif InComment and not DoubleSlashComment and not HashComment and self.__CurrentChar() == T_CHAR_STAR and self.__NextChar() == T_CHAR_SLASH:

                self.__SetCurrentCharValue(T_CHAR_SPACE)
                self.__GetOneChar()
                self.__SetCurrentCharValue(T_CHAR_SPACE)
                self.__GetOneChar()
                InComment = False
            # set comments to spaces
            elif InComment:
                if HashComment:
                    # // follows hash PP directive
                    if self.__CurrentChar() == T_CHAR_SLASH and self.__NextChar() == T_CHAR_SLASH:
                        InComment = False
                        HashComment = False
                        PPDirectiveObj.EndPos = (self.CurrentLineNumber, self.CurrentOffsetWithinLine - 1)
                        FileProfile.PPDirectiveList.append(PPDirectiveObj)
                        PPDirectiveObj = None
                        continue
                    else:
                        PPDirectiveObj.Content += self.__CurrentChar()

                self.__SetCurrentCharValue(T_CHAR_SPACE)
                self.__GetOneChar()
            # check for // comment
            elif self.__CurrentChar() == T_CHAR_SLASH and self.__NextChar() == T_CHAR_SLASH:
                InComment = True
                DoubleSlashComment = True

            # check for '#' comment
            elif self.__CurrentChar() == T_CHAR_HASH and not InString and not InCharLiteral:
                InComment = True
                HashComment = True
                PPDirectiveObj = PP_Directive('', (self.CurrentLineNumber, self.CurrentOffsetWithinLine), None)
            # check for /* comment start
            elif self.__CurrentChar() == T_CHAR_SLASH and self.__NextChar() == T_CHAR_STAR:

                self.__SetCurrentCharValue( T_CHAR_SPACE)
                self.__GetOneChar()
                self.__SetCurrentCharValue( T_CHAR_SPACE)
                self.__GetOneChar()
                InComment = True
            else:
                self.__GetOneChar()

        EndLinePos = (self.CurrentLineNumber, self.CurrentOffsetWithinLine)

        if InComment and HashComment and not PPExtend:
            PPDirectiveObj.EndPos = EndLinePos
            FileProfile.PPDirectiveList.append(PPDirectiveObj)
        self.Rewind()

    ## ParseFile() method
    #
    #   Parse the file profile buffer to extract fd, fv ... information
    #   Exception will be raised if syntax error found
    #
    #   @param  self        The object pointer
    #
    def ParseFile(self):
        self.PreprocessFileWithClear()
        # restore from ListOfList to ListOfString
        self.Profile.FileLinesList = ["".join(list) for list in self.Profile.FileLinesList]
        FileStringContents = ''
        for fileLine in self.Profile.FileLinesList:
            FileStringContents += fileLine
        cStream = antlr3.StringStream(FileStringContents)
        lexer = CLexer(cStream)
        tStream = antlr3.CommonTokenStream(lexer)
        parser = CParser(tStream)
        parser.translation_unit()

    ## CleanFileProfileBuffer() method
    #
    #   Reset all contents of the profile of a file
    #
    def CleanFileProfileBuffer(self):

        FileProfile.PPDirectiveList = []
        FileProfile.AssignmentExpressionList = []
        FileProfile.FunctionDefinitionList = []
        FileProfile.VariableDeclarationList = []
        FileProfile.EnumerationDefinitionList = []
        FileProfile.StructUnionDefinitionList = []
        FileProfile.TypedefDefinitionList = []
        FileProfile.FunctionCallingList = []

    ## PrintFragments() method
    #
    #   Print the contents of the profile of a file
    #
    def PrintFragments(self):

        print '################# ' + self.FileName + '#####################'

        print '/****************************************/'
        print '/*************** ASSIGNMENTS ***************/'
        print '/****************************************/'
        for asign in FileProfile.AssignmentExpressionList:
            print str(asign.StartPos) + asign.Name + asign.Operator + asign.Value

        print '/****************************************/'
        print '/********* PREPROCESS DIRECTIVES ********/'
        print '/****************************************/'
        for pp in FileProfile.PPDirectiveList:
            print str(pp.StartPos) + pp.Content

        print '/****************************************/'
        print '/********* VARIABLE DECLARATIONS ********/'
        print '/****************************************/'
        for var in FileProfile.VariableDeclarationList:
            print str(var.StartPos) + var.Modifier + ' '+ var.Declarator

        print '/****************************************/'
        print '/********* FUNCTION DEFINITIONS *********/'
        print '/****************************************/'
        for func in FileProfile.FunctionDefinitionList:
            print str(func.StartPos) + func.Modifier + ' '+ func.Declarator + ' ' + str(func.NamePos)

        print '/****************************************/'
        print '/************ ENUMERATIONS **************/'
        print '/****************************************/'
        for enum in FileProfile.EnumerationDefinitionList:
            print str(enum.StartPos) + enum.Content

        print '/****************************************/'
        print '/*********** STRUCTS/UNIONS *************/'
        print '/****************************************/'
        for su in FileProfile.StructUnionDefinitionList:
            print str(su.StartPos) + su.Content

        print '/****************************************/'
        print '/************** TYPEDEFS ****************/'
        print '/****************************************/'
        for typedef in FileProfile.TypedefDefinitionList:
            print str(typedef.StartPos) + typedef.ToType

##
#
# This acts like the main() function for the script, unless it is 'import'ed into another
# script.
#
if __name__ == "__main__":

    print "For Test."