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
|
# The MIT License (MIT)
#
# Copyright (c) 2007-2018 Einar Lielmanis, Liam Newman, and contributors.
#
# Permission is hereby granted, free of charge, to any person
# obtaining a copy of this software and associated documentation files
# (the "Software"), to deal in the Software without restriction,
# including without limitation the rights to use, copy, modify, merge,
# publish, distribute, sublicense, and/or sell copies of the Software,
# and to permit persons to whom the Software is furnished to do so,
# subject to the following conditions:
#
# The above copyright notice and this permission notice shall be
# included in all copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.
import re
from ..core.inputscanner import InputScanner
from ..core.token import Token
from ..core.tokenstream import TokenStream
from ..core.pattern import Pattern
from ..core.whitespacepattern import WhitespacePattern
__all__ = ["TOKEN", "Tokenizer", "TokenizerPatterns", "TokenTypes"]
class TokenTypes:
START = "TK_START"
RAW = "TK_RAW"
EOF = "TK_EOF"
def __init__(self):
pass
TOKEN = TokenTypes()
class TokenizerPatterns:
def __init__(self, input_scanner):
self.whitespace = WhitespacePattern(input_scanner)
class Tokenizer:
def __init__(self, input_string, options):
self._input = InputScanner(input_string)
self._options = options
self.__tokens = None
self._patterns = TokenizerPatterns(self._input)
def tokenize(self):
self._input.restart()
self.__tokens = TokenStream()
current = None
previous = Token(TOKEN.START, "")
open_token = None
open_stack = []
comments = TokenStream()
while previous.type != TOKEN.EOF:
current = self.__get_next_token_with_comments(previous, open_token)
if self._is_opening(current):
open_stack.append(open_token)
open_token = current
elif open_token is not None and self._is_closing(current, open_token):
current.opened = open_token
open_token.closed = current
open_token = open_stack.pop()
current.parent = open_token
self.__tokens.add(current)
previous = current
return self.__tokens
def __get_next_token_with_comments(self, previous, open_token):
current = self._get_next_token(previous, open_token)
if self._is_comment(current):
comments = TokenStream()
while self._is_comment(current):
comments.add(current)
current = self._get_next_token(previous, open_token)
if not comments.isEmpty():
current.comments_before = comments
comments = TokenStream()
current.parent = open_token
current.previous = previous
previous.next = current
return current
def _is_first_token(self):
return self.__tokens.isEmpty()
def _reset(self):
pass
def _get_next_token(self, previous_token, open_token):
self._readWhitespace()
resulting_string = self._input.read(re.compile(r".+"))
if resulting_string:
return self._create_token(TOKEN.RAW, resulting_string)
else:
return self._create_token(TOKEN.EOF, "")
def _is_comment(self, current_token):
return False
def _is_opening(self, current_token):
return False
def _is_closing(self, current_token, open_token):
return False
def _create_token(self, token_type, text):
token = Token(
token_type,
text,
self._patterns.whitespace.newline_count,
self._patterns.whitespace.whitespace_before_token,
)
return token
def _readWhitespace(self):
return self._patterns.whitespace.read()
|
