File: tokens.py

package info (click to toggle)
sip6 6.9.1-1
  • links: PTS, VCS
  • area: main
  • in suites: sid
  • size: 3,140 kB
  • sloc: ansic: 21,291; python: 18,914; makefile: 23
file content (381 lines) | stat: -rw-r--r-- 8,495 bytes parent folder | download | duplicates (2)
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
# SPDX-License-Identifier: BSD-2-Clause

# Copyright (c) 2024 Phil Thompson <[email protected]>


from ..specification import CodeBlock

from ply.lex import TOKEN


# The lexer states.
states = (
    ('code',            'exclusive'),
    ('ccomment',        'exclusive'),
    ('directive',       'inclusive'),
    ('needeol',         'inclusive'),
)


# The single character tokens.
literals = '(){}.,;:=!- */&|~<>[]%^'


# The non-code directives.
directives = {
    'AutoPyName', 'CompositeModule', 'DefaultDocstringFormat',
    'DefaultDocstringSignature', 'DefaultEncoding', 'DefaultMetatype',
    'DefaultSupertype', 'End', 'Exception', 'Feature', 'HideNamespace', 'If',
    'Import', 'Include', 'License', 'MappedType', 'Module', 'Platforms',
    'Property', 'Timeline',

    # Remove in SIP v7.
    'Plugin',
}


# The code directives.
code_directives = {
    'AccessCode', 'BIGetBufferCode', 'BIReleaseBufferCode',
    'ConvertFromTypeCode', 'ConvertToSubClassCode', 'ConvertToTypeCode',
    'Copying', 'Docstring', 'ExportedHeaderCode', 'ExportedTypeHintCode',
    'Extract', 'FinalisationCode', 'GCClearCode', 'GCTraverseCode', 'GetCode',
    'InitialisationCode', 'InstanceCode', 'MethodCode', 'ModuleCode',
    'ModuleHeaderCode', 'PickleCode', 'PostInitialisationCode',
    'PreInitialisationCode', 'PreMethodCode', 'RaiseCode', 'ReleaseCode',
    'SetCode', 'TypeCode', 'TypeHeaderCode', 'TypeHintCode', 'UnitCode',
    'UnitPostIncludeCode', 'VirtualCallCode', 'VirtualCatcherCode',
    'VirtualErrorHandler',

    # Remove in SIP v7.
    'BIGetCharBufferCode', 'BIGetReadBufferCode', 'BIGetSegCountCode',
    'BIGetWriteBufferCode',
}


# The plain keywords.
keywords = {
    'bool', 'char', 'class', 'const', 'double', 'enum', 'explicit', 'false',
    'final', 'float', 'int', 'long', 'namespace', 'noexcept', 'NULL',
    'operator', 'private', 'protected', 'public', 'Py_hash_t', 'Py_ssize_t',
    'Q_SIGNAL', 'Q_SIGNALS', 'Q_SLOT', 'Q_SLOTS', 'short', 'signals', 'signed',
    'SIP_PYBUFFER', 'SIP_PYCALLABLE', 'SIP_PYDICT', 'SIP_PYENUM', 'SIP_PYLIST',
    'SIP_PYOBJECT', 'SIP_PYSLICE', 'SIP_PYTUPLE', 'SIP_PYTYPE', 'size_t',
    'slots', 'static', 'struct', 'template', 'throw', 'true', 'typedef',
    'union', 'unsigned', 'virtual', 'void', 'wchar_t',

    # Remove in SIP v7.
    'SIP_SSIZE_T',
}


# The directive keywords.
directive_keywords = {
    'all_raise_py_exception', 'call_super_init', 'default_VirtualErrorHandler',
    'False', 'format', 'get', 'id', 'keyword_arguments', 'language',
    'licensee', 'name', 'optional', 'order', 'remove_leading', 'set',
    'signature', 'timestamp', 'True', 'type', 'py_ssize_t_clean',
    'use_argument_names', 'use_limited_api',
}


# The lexer tokens.
tokens = [
    'CODE_BLOCK', 'DOTTED_NAME', 'ELLIPSIS', 'EOF', 'EOL', 'FILE_PATH',
    'LOGICAL_OR', 'NAME', 'NUMBER', 'QUOTED_CHAR', 'REAL', 'SCOPE', 'STRING',
]

tokens.extend(directives)
tokens.extend(code_directives)
tokens.extend(keywords)
tokens.extend(directive_keywords)


# Handle EOF.
def t_eof(t):

    try:
        t.lexer.pm.pop_file()
    except IndexError:
        return None

    # Return an explicit EOF token.  This stops the parser looking too far into
    # the popped file.
    t.type = 'EOF'

    return t


# Handle errors.
def t_ANY_error(t):

    t.lexer.pm.lexer_error(t, "'{0}' is unexpected".format(t.value[0]))
    t.lexer.skip(1)


# Ignore whitespace except when reading code blocks.
t_ANY_ignore = ' \t\r'
t_code_ignore = ''


# Handle newlines outside of code blocks and comments.
def t_newline(t):
    r'\n'

    lexer = t.lexer
    pm = lexer.pm

    # Maintain the line number.
    lexer.lineno  = 1

    # Enter the 'code' state if we are at the end of a code directive name and
    # arguments.
    if pm.code_block is not None and pm.paren_depth == 0:
        pm.code_block.line_nr = lexer.lineno
        pm.set_lexer_state('code')


# Maintain the parenthesis depth.
def t_LPAREN(t):
    r'\('

    t.lexer.pm.paren_depth  = 1
    t.type = '('

    return t


def t_RPAREN(t):
    r'\)'

    t.lexer.pm.paren_depth -= 1
    t.type = ')'

    return t


# Handle directives.
def t_DIRECTIVE(t):
    r'%[a-zA-Z][a-zA-Z]*'

    # The name of the directive is used as its type.
    name = t.value[t.value.index('%')   1:]

    if name in code_directives:
        t.lexer.pm.code_block = CodeBlock(t.lexer.pm.raw_sip_file)
        t.type = name
    elif name in directives:
        t.type = name

    return t


# Handle the %End of a code directive.
def t_code_END(t):
    r'%End'

    code_block = t.lexer.pm.code_block
    t.lexer.pm.code_block = None

    # Ignore any indentation preceding the # %End.
    code_block.text = code_block.text.rstrip(' \t')

    t.type = 'CODE_BLOCK'
    t.value = code_block
    t.lexer.begin('INITIAL')

    return t


# Handle a newline when an end-of-line needs to be reported to the parser.
def t_needeol_newline(t):
    r'\n'

    # Maintain the line number.
    t.lexer.lineno  = 1

    t.lexer.pm.set_lexer_state()
    t.type = 'EOL'

    return t


# Handle a newline in a code directive.
def t_code_newline(t):
    r'\n'

    # Maintain the line number.
    t.lexer.lineno  = 1

    t.lexer.pm.code_block.text  = t.value

    # Discard the token.
    return None


# Handle a character in a code directive.
def t_code_CH(t):
    r'.'

    t.lexer.pm.code_block.text  = t.value

    # Discard the token.
    return None


# Handle keywords, ellipsis, names, dotted name and file paths.
ambiguous = r'[._A-Za-z][._/A-Za-z\d\-]*[._A-Za-z\d]'

@TOKEN(ambiguous)
def t_AMBIGUOUS(t):

    t.type = t.lexer.pm.disambiguate_token(t.value, keywords)

    return t


# Handle directive keywords (ie. keywords that are only recognised in the
# context of a directive), ellipsis, names, dotted name and file paths.
@TOKEN(ambiguous)
def t_directive_AMBIGUOUS(t):

    t.type = t.lexer.pm.disambiguate_token(t.value, directive_keywords)

    return t


# Handle a C  -style comment.
def t_CPPCOMMENT(t):
    r'//.*'

    # Discard the token.
    return None


# Handle the start of a C-style comment.
def t_COMMENTSTART(t):
    r'/\*'

    t.lexer.push_state('ccomment')

    # Discard the token.
    return None


# Handle the end of a C-style comment.
def t_ccomment_COMMENTEND(t):
    r'\*/'

    t.lexer.pop_state()

    # Discard the token.
    return None


# Handle a newline in a C-style comment.
def t_ccomment_newline(t):
    r'\n'

    # Maintain the line number.
    t.lexer.lineno  = 1

    # Discard the token.
    return None


# Handle the content of a C-style comment.
def t_ccomment_CH(t):
    r'.'

    # Maintain the line number.
    if t.value == '\n':
        t.lexer.lineno  = 1

    # Discard the token.
    return None


# Handle an unsigned hexadecimal number.
def t_HEXNUMBER(t):
    r'0x[\da-fA-F] '

    t.type = 'NUMBER'
    t.value = int(t.value, base=16)

    return t


# Handle a number.
def t_NUMBER(t):
    r'-?(\d (\.\d*)?|\.\d )([eE][- ]?\d )?[fFlLuU]?'

    # Remove any suffix character.
    value = t.value
    if not value[-1].isdigit():
        value = value[:-1]

    try:
        t.type = 'NUMBER'
        t.value = int(value)
    except ValueError:
        t.type = 'REAL'
        t.value = float(value)

    return t


# Handle a double-quoted string.
def t_STRING(t):
    r'"(\\.|[^\\"])*"'

    # Strip the quotes and handle any standard escape characters.
    value = t.value.strip('"')
    value = value.replace(r'\n', '\n')
    value = value.replace(r'\r', '\r')
    value = value.replace(r'\t', '\t')
    value = value.replace(r'\\', '\\')

    t.type = 'STRING'
    t.value = value

    return t


# Handle a single-quoted hex encoded character.
def t_QHEXCH(t):
    r"'\\x[\da-fA-F] '"

    t.type = 'QUOTED_CHAR'
    t.value = chr(int(t.value.strip("'")[2:], base=16))

    return t


# Handle a single-quoted character.
def t_QCH(t):
    r"'[^'\n]*['\n]"

    # Make sure these is only one quoted character.  If not then report the
    # error and carry on with a fudged value.
    n_ch = len(t.value)

    if n_ch != 3:
        t.lexer.pm.lexer_error(t,
                "exactly one character expected between single quotes")

        if n_ch == 0:
            t.value = '?'

    t.type = 'QUOTED_CHAR'
    t.value = t.value[1]

    return t


# The remaining trivial token definitions.
t_LOGICAL_OR = r'\|\|'
t_SCOPE = r'::'

# We only deal with a single character as everything else is handled by
# AMBIGUOUS.
t_NAME = r'[_A-Za-z]'