| 1 | #!/usr/bin/env python2
|
| 2 | # Copyright 2019 Wilke Schwiedop. All rights reserved.
|
| 3 | # Copyright 2019 Andy Chu. All rights reserved.
|
| 4 | # Licensed under the Apache License, Version 2.0 (the "License");
|
| 5 | # you may not use this file except in compliance with the License.
|
| 6 | # You may obtain a copy of the License at
|
| 7 | #
|
| 8 | # http://www.apache.org/licenses/LICENSE-2.0
|
| 9 | """
|
| 10 | tokenizer.py: Tokenizer for find.
|
| 11 | """
|
| 12 |
|
| 13 | _ops = [
|
| 14 | ('!', 'BANG'),
|
| 15 | ('(', 'LPAR'),
|
| 16 | (')', 'RPAR'),
|
| 17 | ('-o', 'OR'),
|
| 18 | ('-a', 'AND'),
|
| 19 | (',', 'COMMA'),
|
| 20 | (';', 'SEMI'),
|
| 21 | ('+', 'PLUS'),
|
| 22 |
|
| 23 | ('-true', 'TRUE'),
|
| 24 | ('-false', 'FALSE'),
|
| 25 |
|
| 26 | ('-name', 'NAME'),
|
| 27 | ('-iname', 'INAME'),
|
| 28 |
|
| 29 | ('-lname', 'LNAME'),
|
| 30 | ('-ilname', 'ILNAME'),
|
| 31 |
|
| 32 | ('-path', 'PATH'),
|
| 33 | ('-ipath', 'IPATH'),
|
| 34 |
|
| 35 | ('-regex', 'REGEX'),
|
| 36 | ('-iregex', 'IREGEX'),
|
| 37 |
|
| 38 | ('-executable', 'EXECUTABLE'),
|
| 39 | ('-readable', 'READABLE'),
|
| 40 | ('-writable', 'WRITABLE'),
|
| 41 |
|
| 42 | ('-empty', 'EMPTY'),
|
| 43 |
|
| 44 | ('-size', 'SIZE'),
|
| 45 | ('-type', 'TYPE'),
|
| 46 | ('-xtype', 'XTYPE'),
|
| 47 | ('-perm', 'PERM'),
|
| 48 |
|
| 49 | ('-group', 'GROUP'),
|
| 50 | ('-user', 'USER'),
|
| 51 | ('-gid', 'GID'),
|
| 52 | ('-uid', 'UID'),
|
| 53 | ('-nogroup', 'NOGROUP'),
|
| 54 | ('-nouser', 'NOUSER'),
|
| 55 |
|
| 56 | ('-amin', 'AMIN'),
|
| 57 | ('-anewer', 'ANEWER'),
|
| 58 | ('-atime', 'ATIME'),
|
| 59 | ('-cmin', 'CMIN'),
|
| 60 | ('-cnewer', 'CNEWER'),
|
| 61 | ('-ctime', 'CTIME'),
|
| 62 | ('-mmin', 'MMIN'),
|
| 63 | # note -newer not -mnewer
|
| 64 | ('-newer', 'MNEWER'),
|
| 65 | ('-mtime', 'MTIME'),
|
| 66 | ('-newerXY', 'NEWERXY'),
|
| 67 |
|
| 68 | ('-delete', 'DELETE'),
|
| 69 | ('-prune', 'PRUNE'),
|
| 70 | ('-quit', 'QUIT'),
|
| 71 |
|
| 72 | ('-print', 'PRINT'),
|
| 73 | ('-print0', 'PRINT0'),
|
| 74 | ('-printf', 'PRINTF'),
|
| 75 | ('-ls', 'LS'),
|
| 76 | ('-fprint', 'FPRINT'),
|
| 77 | ('-fprint0', 'FPRINT0'),
|
| 78 | ('-fprintf', 'FPRINTF'),
|
| 79 | ('-fls', 'FLS'),
|
| 80 |
|
| 81 | ('-exec', 'EXEC'),
|
| 82 | ('-execdir', 'EXECDIR'),
|
| 83 | ('-ok', 'OK'),
|
| 84 | ('-okdir', 'OKDIR'),
|
| 85 | ]
|
| 86 |
|
| 87 | # start=100 is pgen voodoo, don't touch
|
| 88 | opmap = dict((op, i) for i, (op, name) in enumerate(_ops, start=100))
|
| 89 | tok_name = dict((i, name) for i, (op, name) in enumerate(_ops, start=100))
|
| 90 | tok_name[0] = 'ENDMARKER'
|
| 91 | tok_name[1] = 'STRING'
|
| 92 | #tok_name[len(tok_name)] = 'N_TOKENS'
|
| 93 | tok_name[256] = 'NT_OFFSET'
|
| 94 |
|
| 95 | import sys
|
| 96 | this_module = sys.modules[__name__]
|
| 97 | for i, name in tok_name.items():
|
| 98 | setattr(this_module, name, i)
|
| 99 |
|
| 100 | class TokenDef(object):
|
| 101 | def GetTerminalNum(self, label):
|
| 102 | """ e.g. NAME -> 1 """
|
| 103 | itoken = getattr(this_module, label, None)
|
| 104 | assert isinstance(itoken, int), label
|
| 105 | assert itoken in tok_name, label
|
| 106 | return itoken
|
| 107 |
|
| 108 | def GetOpNum(self, value):
|
| 109 | """ e.g '(' -> LPAR """
|
| 110 | return opmap[value]
|
| 111 |
|
| 112 | def GetKeywordNum(self, value):
|
| 113 | return None
|
| 114 |
|
| 115 |
|
| 116 | def tokenize(argv):
|
| 117 | start = end = (1, 0) # dummy location data
|
| 118 | line_text = ''
|
| 119 | for a in argv:
|
| 120 | #log('tok = %r', a)
|
| 121 | typ = opmap.get(a, STRING)
|
| 122 | # print (typ, a, start, end, line_text)
|
| 123 | yield (typ, a, start, end, line_text)
|
| 124 | yield (ENDMARKER, '', start, end, line_text)
|
| 125 |
|
| 126 | def is_terminal(type):
|
| 127 | # type (int) -> bool
|
| 128 | return type < NT_OFFSET
|
| 129 |
|
| 130 | def is_nonterminal(type):
|
| 131 | # type (int) -> bool
|
| 132 | return type >= NT_OFFSET
|
| 133 |
|
| 134 | def is_eof(type):
|
| 135 | # type (int) -> bool
|
| 136 | return type == ENDMARKER
|