aboutsummaryrefslogtreecommitdiffstats
path: root/src/gallium/state_trackers/python/retrace/parser.py
blob: 5205f2d8dd588e82b964744a39e5f4fc7b6ae690 (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
#!/usr/bin/env python
##########################################################################
# 
# Copyright 2008 Tungsten Graphics, Inc., Cedar Park, Texas.
# All Rights Reserved.
# 
# 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, sub license, 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 (including the
# next paragraph) 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 NON-INFRINGEMENT.
# IN NO EVENT SHALL TUNGSTEN GRAPHICS AND/OR ITS SUPPLIERS 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 sys
import xml.parsers.expat
import binascii

from model import *


ELEMENT_START, ELEMENT_END, CHARACTER_DATA, EOF = range(4)


class XmlToken:

    def __init__(self, type, name_or_data, attrs = None, line = None, column = None):
        assert type in (ELEMENT_START, ELEMENT_END, CHARACTER_DATA, EOF)
        self.type = type
        self.name_or_data = name_or_data
        self.attrs = attrs
        self.line = line
        self.column = column

    def __str__(self):
        if self.type == ELEMENT_START:
            return '<' + self.name_or_data + ' ...>'
        if self.type == ELEMENT_END:
            return '</' + self.name_or_data + '>'
        if self.type == CHARACTER_DATA:
            return self.name_or_data
        if self.type == EOF:
            return 'end of file'
        assert 0


class XmlTokenizer:
    """Expat based XML tokenizer."""

    def __init__(self, fp, skip_ws = True):
        self.fp = fp
        self.tokens = []
        self.index = 0
        self.final = False
        self.skip_ws = skip_ws
        
        self.character_pos = 0, 0
        self.character_data = ''
        
        self.parser = xml.parsers.expat.ParserCreate()
        self.parser.StartElementHandler  = self.handle_element_start
        self.parser.EndElementHandler    = self.handle_element_end
        self.parser.CharacterDataHandler = self.handle_character_data
    
    def handle_element_start(self, name, attributes):
        self.finish_character_data()
        line, column = self.pos()
        token = XmlToken(ELEMENT_START, name, attributes, line, column)
        self.tokens.append(token)
    
    def handle_element_end(self, name):
        self.finish_character_data()
        line, column = self.pos()
        token = XmlToken(ELEMENT_END, name, None, line, column)
        self.tokens.append(token)

    def handle_character_data(self, data):
        if not self.character_data:
            self.character_pos = self.pos()
        self.character_data += data
    
    def finish_character_data(self):
        if self.character_data:
            if not self.skip_ws or not self.character_data.isspace(): 
                line, column = self.character_pos
                token = XmlToken(CHARACTER_DATA, self.character_data, None, line, column)
                self.tokens.append(token)
            self.character_data = ''
    
    def next(self):
        size = 16*1024
        while self.index >= len(self.tokens) and not self.final:
            self.tokens = []
            self.index = 0
            data = self.fp.read(size)
            self.final = len(data) < size
            data = data.rstrip('\0')
            try:
                self.parser.Parse(data, self.final)
            except xml.parsers.expat.ExpatError, e:
                #if e.code == xml.parsers.expat.errors.XML_ERROR_NO_ELEMENTS:
                if e.code == 3:
                    pass
                else:
                    raise e
        if self.index >= len(self.tokens):
            line, column = self.pos()
            token = XmlToken(EOF, None, None, line, column)
        else:
            token = self.tokens[self.index]
            self.index += 1
        return token

    def pos(self):
        return self.parser.CurrentLineNumber, self.parser.CurrentColumnNumber


class TokenMismatch(Exception):

    def __init__(self, expected, found):
        self.expected = expected
        self.found = found

    def __str__(self):
        return '%u:%u: %s expected, %s found' % (self.found.line, self.found.column, str(self.expected), str(self.found))



class XmlParser:
    """Base XML document parser."""

    def __init__(self, fp):
        self.tokenizer = XmlTokenizer(fp)
        self.consume()
    
    def consume(self):
        self.token = self.tokenizer.next()

    def match_element_start(self, name):
        return self.token.type == ELEMENT_START and self.token.name_or_data == name
    
    def match_element_end(self, name):
        return self.token.type == ELEMENT_END and self.token.name_or_data == name

    def element_start(self, name):
        while self.token.type == CHARACTER_DATA:
            self.consume()
        if self.token.type != ELEMENT_START:
            raise TokenMismatch(XmlToken(ELEMENT_START, name), self.token)
        if self.token.name_or_data != name:
            raise TokenMismatch(XmlToken(ELEMENT_START, name), self.token)
        attrs = self.token.attrs
        self.consume()
        return attrs
    
    def element_end(self, name):
        while self.token.type == CHARACTER_DATA:
            self.consume()
        if self.token.type != ELEMENT_END:
            raise TokenMismatch(XmlToken(ELEMENT_END, name), self.token)
        if self.token.name_or_data != name:
            raise TokenMismatch(XmlToken(ELEMENT_END, name), self.token)
        self.consume()

    def character_data(self, strip = True):
        data = ''
        while self.token.type == CHARACTER_DATA:
            data += self.token.name_or_data
            self.consume()
        if strip:
            data = data.strip()
        return data


class TraceParser(XmlParser):

    def parse(self):
        self.element_start('trace')
        while self.token.type not in (ELEMENT_END, EOF):
            call = self.parse_call()
            self.handle_call(call)
        if self.token.type != EOF:
            self.element_end('trace')

    def parse_call(self):
        attrs = self.element_start('call')
        klass = attrs['class']
        method = attrs['method']
        args = []
        ret = None
        while self.token.type == ELEMENT_START:
            if self.token.name_or_data == 'arg':
                arg = self.parse_arg()
                args.append(arg)
            elif self.token.name_or_data == 'ret':
                ret = self.parse_ret()
            elif self.token.name_or_data == 'call':
                # ignore nested function calls
                self.parse_call()
            else:
                raise TokenMismatch("<arg ...> or <ret ...>", self.token)
        self.element_end('call')
        
        return Call(klass, method, args, ret)

    def parse_arg(self):
        attrs = self.element_start('arg')
        name = attrs['name']
        value = self.parse_value()
        self.element_end('arg')

        return name, value

    def parse_ret(self):
        attrs = self.element_start('ret')
        value = self.parse_value()
        self.element_end('ret')

        return value

    def parse_value(self):
        expected_tokens = ('null', 'bool', 'int', 'uint', 'float', 'string', 'enum', 'array', 'struct', 'ptr', 'bytes')
        if self.token.type == ELEMENT_START:
            if self.token.name_or_data in expected_tokens:
                method = getattr(self, 'parse_' +  self.token.name_or_data)
                return method()
        raise TokenMismatch(" or " .join(expected_tokens), self.token)

    def parse_null(self):
        self.element_start('null')
        self.element_end('null')
        return Literal(None)
        
    def parse_bool(self):
        self.element_start('bool')
        value = int(self.character_data())
        self.element_end('bool')
        return Literal(value)
        
    def parse_int(self):
        self.element_start('int')
        value = int(self.character_data())
        self.element_end('int')
        return Literal(value)
        
    def parse_uint(self):
        self.element_start('uint')
        value = int(self.character_data())
        self.element_end('uint')
        return Literal(value)
        
    def parse_float(self):
        self.element_start('float')
        value = float(self.character_data())
        self.element_end('float')
        return Literal(value)
        
    def parse_enum(self):
        self.element_start('enum')
        name = self.character_data()
        self.element_end('enum')
        return NamedConstant(name)
        
    def parse_string(self):
        self.element_start('string')
        value = self.character_data()
        self.element_end('string')
        return Literal(value)
        
    def parse_bytes(self):
        self.element_start('bytes')
        value = binascii.a2b_hex(self.character_data())
        self.element_end('bytes')
        return Literal(value)
        
    def parse_array(self):
        self.element_start('array')
        elems = []
        while self.token.type != ELEMENT_END:
            elems.append(self.parse_elem())
        self.element_end('array')
        return Array(elems)

    def parse_elem(self):
        self.element_start('elem')
        value = self.parse_value()
        self.element_end('elem')
        return value

    def parse_struct(self):
        attrs = self.element_start('struct')
        name = attrs['name']
        members = []
        while self.token.type != ELEMENT_END:
            members.append(self.parse_member())
        self.element_end('struct')
        return Struct(name, members)

    def parse_member(self):
        attrs = self.element_start('member')
        name = attrs['name']
        value = self.parse_value()
        self.element_end('member')

        return name, value

    def parse_ptr(self):
        self.element_start('ptr')
        address = self.character_data()
        self.element_end('ptr')

        return Pointer(address)

    def handle_call(self, call):
        pass
    
    
class TraceDumper(TraceParser):
    
    def __init__(self, fp):
        TraceParser.__init__(self, fp)
        self.formatter = format.DefaultFormatter(sys.stdout)
        self.pretty_printer = PrettyPrinter(self.formatter)

    def handle_call(self, call):
        call.visit(self.pretty_printer)
        self.formatter.newline()
        

def main(ParserFactory):
    for arg in sys.argv[1:]:
        if arg.endswith('.gz'):
            import gzip
            stream = gzip.GzipFile(arg, 'rt')
        else:
            stream = open(arg, 'rt')
        parser = ParserFactory(stream)
        parser.parse()


if __name__ == '__main__':
    main(TraceDumper)