summaryrefslogtreecommitdiff
path: root/pysc-v/Frontend/lexer.py
blob: c4a9a7d2121838b6e3a0fdab930bfb545d05582c (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
# TODO Logging is interesting for debugging purposes, decide what to do with it
from logger import newlogger
logger = newlogger(__name__)
#import logging
#logger.setLevel(logging.WARN)


######

from enum import Enum
from reader import Reader

binChars = set("01")
octChars = set("01234567")
decChars = set("0123456789")
hexChars = set("0123456789ABCDEFabcdef")

class TokenType(Enum):
    """
    These are the possible tokens that the lexer knows, they are converted to
    their most accurate representation in python.
    """
    identifier  = 0 # Represented as strings
    label       = 1 # Represented as strings or integer if they are numeric
    instruction = 2 # Represented as strings
    directive   = 3 # Represented as strings
    integer     = 4 # Represented as int
    character   = 5 # Represented as strings of length 1
    string      = 6 # Represented as strings
    float       = 7 # Represented as ??
                    # (we need correct conversions to the binary value)
                    # TODO
    end         = 8
    argsep      = 9
    openparens  = 10
    closeparens = 11

class Lexer:
    def __init__(self, reader):
        self.reader     = reader
        self.tokenstart = 0

    def __iter__(self):
        return self

    def __next__(self):
        if self.reader.char is None:
            self.reader.advance()
        while True:
            try:
                # Instruction end
                if self.reader.char == "\n" or self.reader.char == ";":
                    self.reader.advance()
                    return (TokenType.end, None)

                # Argument separator
                elif self.reader.char == ",":
                    self.reader.advance()
                    return (TokenType.argsep, None)

                # String
                elif self.reader.char == '"':
                    return self.string()

                # Character
                elif self.reader.char == "'":
                    return self.character()

                # Comment
                elif self.reader.char == "#":
                    self.comment()

                # Parenthesis
                # Load a register as an address + an offset
                elif self.reader.char == '(':
                    self.reader.advance()
                    return (TokenType.openparens, None)
                elif self.reader.char == ')':
                    self.reader.advance()
                    return (TokenType.closeparens, None)

                # Starts with digit:
                # - Numbers (any kind)
                # - Numeric Labels
                # - Numeric Label references
                # - Load register as address: ld a1, 4(a0)
                #                                    ^^^^^
                #                                    offset + reg
                elif self.reader.char.isdigit() or self.reader.char == "-":
                    return self.number()

                # Identifiers
                elif self.reader.char.isalpha():
                    return self.identifier()

                elif self.reader.char == "":
                    break # FILE END

                else:
                    # TODO: Remove this, it's just for testing
                    self.reader.advance()
            except Exception as e:
                # Handle exceptions
                # raise StopIteration
                raise e
        raise StopIteration

    def string (self):
        logger.info("Found string")
        self.reader.advance()   # Ignore opening quotes

        string  = ""
        escaped = False         # Set if previous character was a backslash

        while self.reader.char != '"' or escaped:
            if self.reader.char == "":
                # TODO: Check how to do this
                raise ValueError("Error: string not closed, found EOF")
            if self.reader.char == "\n":
                # TODO: Consider the string as closed and continue but report
                # the error?
                raise ValueError("Error: string not closed, found newline")

            if escaped:
                string += self.escaped_char(self.reader.char)
                logger.debug("Escape sequence processed %s",
                        string[-1].__repr__())
                escaped = False
                continue
            if self.reader.char == "\\":
                escaped = True
                self.reader.advance()
                continue
            escaped = False
            string += self.reader.char
            self.reader.advance()
        logger.info("Lexed string %s", string.__repr__())
        self.reader.advance() # Discard closing "
        return (TokenType.string, string)

    def character (self):
        logger.info("Found character")
        self.reader.advance() # Ignore the opening quote
        character = self.reader.char
        if character == "":
            # TODO: Check how to do this
            raise ValueError("Error: found EOF")
        if not character.isprintable() :
            raise ValueError("Error: Non printable character")

        if character == "\\":
            self.reader.advance()
            character = self.escaped_char(self.reader.char)
            logger.debug("Escape sequence processed: %s", character.__repr__())

        # Make sure it's correctly closed
        self.reader.advance()
        if self.reader.char != "'":
            raise ValueError("Parse error: expected `'`, found " + self.reader.char)
        self.reader.advance() # Discard closing '

        logger.info("Lexed char %s", character.__repr__())
        return (TokenType.character, character)

    def comment(self):
        while self.reader != "\n":
            self.reader.advance()

    def escaped_char(self, ch):
        if ch == '"':
            return '"'
        elif ch == 'n':
            return '\n'
        elif ch == 't':
            return '\t'
        elif ch == '\\':
            return '\\'
        else:
            # TODO: implement more escape sequences
            return ""


    def number(self):
        """
        Process anything that starts with a number. Could be:
        - An actual number in hex, octal, binary or decimal
        - Numeric labels or numeric label references
        - floating point (not implemented yet)
        """
        numbstr = self.reader.char
        self.reader.advance()

        logger.info("Found number: %s", numbstr)

        # Hex, Bin, Oct and the 0
        if numbstr == "0":
            reprid = self.reader.peek()
            if   reprid == "x":
                self.reader.advance()
                return self.hex()
            elif reprid == "b":
                self.reader.advance()
                return self.bin()
            elif reprid.isdigit():
                return self.oct()
            else:
                return (TokenType.integer, 0)

        # TODO: floating point numbers

        # Decimal number
        # consume a decimal number
        while self.reader.char in decChars:
            numbstr += self.reader.char
            self.reader.advance()

        # Numeric label reference
        if self.reader.char in set("bf"):
            numbstr += self.reader.char
            self.reader.advance()
            return (TokenType.identifier, numbstr)
            # TODO: Return identifier or label?
            # It's a label-ref not a label!

        # Numeric label
        if self.reader.char in ":":
            self.reader.advance()
            return (TokenType.label, numbstr)

        return (TokenType.integer, int(numbstr))

    def hex(self):
        # TODO: Handle possible errors
        numbstr = ""
        while self.reader.char in hexChars:
            numbstr += self.reader.char
            self.reader.advance()
        return (TokenType.integer, int(numbstr, 16))

    def oct(self):
        # TODO: Handle possible errors
        numbstr = ""
        while self.reader.char in octChars:
            numbstr += self.reader.char
            self.reader.advance()
        return (TokenType.integer, int(numbstr, 8))

    def bin(self):
        # TODO: Handle possible errors
        numbstr = ""
        while self.reader.char in binChars:
            numbstr += self.reader.char
            self.reader.advance()
        return (TokenType.integer, int(numbstr, 2))


    def identifier(self):
        s = ""
        while self.reader.char.isalnum() or self.reader.char == "_":
            s += self.reader.char
            self.reader.advance()
        return  (TokenType.identifier, s)

if __name__ == "__main__":
    import sys
    with Reader(sys.argv[1]) as src:
        lexer = Lexer(src)
        for token in lexer:
            print(token)