File: dg-extract-results.py

package info (click to toggle)
gdb 8.3-1
  • links: PTS, VCS
  • area: main
  • in suites: bullseye, sid
  • size: 223,352 kB
  • sloc: ansic: 1,941,112; asm: 341,756; exp: 149,966; makefile: 56,735; sh: 24,156; cpp: 21,837; yacc: 12,932; perl: 5,331; xml: 5,239; ada: 5,191; python: 4,566; pascal: 3,134; lisp: 1,533; cs: 879; lex: 620; f90: 535; sed: 228; awk: 140; objc: 134; fortran: 43
file content (592 lines) | stat: -rw-r--r-- 23,886 bytes parent folder | download | duplicates (10)
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
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
#!/usr/bin/python
#
# Copyright (C) 2014 Free Software Foundation, Inc.
#
# This script is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 3, or (at your option)
# any later version.

import sys
import getopt
import re
import io
from datetime import datetime
from operator import attrgetter

# True if unrecognised lines should cause a fatal error.  Might want to turn
# this on by default later.
strict = False

# True if the order of .log segments should match the .sum file, false if
# they should keep the original order.
sort_logs = True

# A version of open() that is safe against whatever binary output
# might be added to the log.
def safe_open (filename):
    if sys.version_info >= (3, 0):
        return open (filename, 'r', errors = 'surrogateescape')
    return open (filename, 'r')

# Force stdout to handle escape sequences from a safe_open file.
if sys.version_info >= (3, 0):
    sys.stdout = io.TextIOWrapper (sys.stdout.buffer,
                                   errors = 'surrogateescape')

class Named:
    def __init__ (self, name):
        self.name = name

class ToolRun (Named):
    def __init__ (self, name):
        Named.__init__ (self, name)
        # The variations run for this tool, mapped by --target_board name.
        self.variations = dict()

    # Return the VariationRun for variation NAME.
    def get_variation (self, name):
        if name not in self.variations:
            self.variations[name] = VariationRun (name)
        return self.variations[name]

class VariationRun (Named):
    def __init__ (self, name):
        Named.__init__ (self, name)
        # A segment of text before the harness runs start, describing which
        # baseboard files were loaded for the target.
        self.header = None
        # The harnesses run for this variation, mapped by filename.
        self.harnesses = dict()
        # A list giving the number of times each type of result has
        # been seen.
        self.counts = []

    # Return the HarnessRun for harness NAME.
    def get_harness (self, name):
        if name not in self.harnesses:
            self.harnesses[name] = HarnessRun (name)
        return self.harnesses[name]

class HarnessRun (Named):
    def __init__ (self, name):
        Named.__init__ (self, name)
        # Segments of text that make up the harness run, mapped by a test-based
        # key that can be used to order them.
        self.segments = dict()
        # Segments of text that make up the harness run but which have
        # no recognized test results.  These are typically harnesses that
        # are completely skipped for the target.
        self.empty = []
        # A list of results.  Each entry is a pair in which the first element
        # is a unique sorting key and in which the second is the full
        # PASS/FAIL line.
        self.results = []

    # Add a segment of text to the harness run.  If the segment includes
    # test results, KEY is an example of one of them, and can be used to
    # combine the individual segments in order.  If the segment has no
    # test results (e.g. because the harness doesn't do anything for the
    # current configuration) then KEY is None instead.  In that case
    # just collect the segments in the order that we see them.
    def add_segment (self, key, segment):
        if key:
            assert key not in self.segments
            self.segments[key] = segment
        else:
            self.empty.append (segment)

class Segment:
    def __init__ (self, filename, start):
        self.filename = filename
        self.start = start
        self.lines = 0

class Prog:
    def __init__ (self):
        # The variations specified on the command line.
        self.variations = []
        # The variations seen in the input files.
        self.known_variations = set()
        # The tools specified on the command line.
        self.tools = []
        # Whether to create .sum rather than .log output.
        self.do_sum = True
        # Regexps used while parsing.
        self.test_run_re = re.compile (r'^Test Run By (\S+) on (.*)$')
        self.tool_re = re.compile (r'^\t\t=== (.*) tests ===$')
        self.result_re = re.compile (r'^(PASS|XPASS|FAIL|XFAIL|UNRESOLVED'
                                     r'|WARNING|ERROR|UNSUPPORTED|UNTESTED'
                                     r'|KFAIL):\s*(.+)')
        self.completed_re = re.compile (r'.* completed at (.*)')
        # Pieces of text to write at the head of the output.
        # start_line is a pair in which the first element is a datetime
        # and in which the second is the associated 'Test Run By' line.
        self.start_line = None
        self.native_line = ''
        self.target_line = ''
        self.host_line = ''
        self.acats_premable = ''
        # Pieces of text to write at the end of the output.
        # end_line is like start_line but for the 'runtest completed' line.
        self.acats_failures = []
        self.version_output = ''
        self.end_line = None
        # Known summary types.
        self.count_names = [
            '# of DejaGnu errors\t\t',
            '# of expected passes\t\t',
            '# of unexpected failures\t',
            '# of unexpected successes\t',
            '# of expected failures\t\t',
            '# of unknown successes\t\t',
            '# of known failures\t\t',
            '# of untested testcases\t\t',
            '# of unresolved testcases\t',
            '# of unsupported tests\t\t'
        ]
        self.runs = dict()

    def usage (self):
        name = sys.argv[0]
        sys.stderr.write ('Usage: ' + name
                          + ''' [-t tool] [-l variant-list] [-L] log-or-sum-file ...

    tool           The tool (e.g. g++, libffi) for which to create a
                   new test summary file.  If not specified then output
                   is created for all tools.
    variant-list   One or more test variant names.  If the list is
                   not specified then one is constructed from all
                   variants in the files for <tool>.
    sum-file       A test summary file with the format of those
                   created by runtest from DejaGnu.
    If -L is used, merge *.log files instead of *.sum.  In this
    mode the exact order of lines may not be preserved, just different
    Running *.exp chunks should be in correct order.
''')
        sys.exit (1)

    def fatal (self, what, string):
        if not what:
            what = sys.argv[0]
        sys.stderr.write (what + ': ' + string + '\n')
        sys.exit (1)

    # Parse the command-line arguments.
    def parse_cmdline (self):
        try:
            (options, self.files) = getopt.getopt (sys.argv[1:], 'l:t:L')
            if len (self.files) == 0:
                self.usage()
            for (option, value) in options:
                if option == '-l':
                    self.variations.append (value)
                elif option == '-t':
                    self.tools.append (value)
                else:
                    self.do_sum = False
        except getopt.GetoptError as e:
            self.fatal (None, e.msg)

    # Try to parse time string TIME, returning an arbitrary time on failure.
    # Getting this right is just a nice-to-have so failures should be silent.
    def parse_time (self, time):
        try:
            return datetime.strptime (time, '%c')
        except ValueError:
            return datetime.now()

    # Parse an integer and abort on failure.
    def parse_int (self, filename, value):
        try:
            return int (value)
        except ValueError:
            self.fatal (filename, 'expected an integer, got: ' + value)

    # Return a list that represents no test results.
    def zero_counts (self):
        return [0 for x in self.count_names]

    # Return the ToolRun for tool NAME.
    def get_tool (self, name):
        if name not in self.runs:
            self.runs[name] = ToolRun (name)
        return self.runs[name]

    # Add the result counts in list FROMC to TOC.
    def accumulate_counts (self, toc, fromc):
        for i in range (len (self.count_names)):
            toc[i] += fromc[i]

    # Parse the list of variations after 'Schedule of variations:'.
    # Return the number seen.
    def parse_variations (self, filename, file):
        num_variations = 0
        while True:
            line = file.readline()
            if line == '':
                self.fatal (filename, 'could not parse variation list')
            if line == '\n':
                break
            self.known_variations.add (line.strip())
            num_variations += 1
        return num_variations

    # Parse from the first line after 'Running target ...' to the end
    # of the run's summary.
    def parse_run (self, filename, file, tool, variation, num_variations):
        header = None
        harness = None
        segment = None
        final_using = 0

        # If this is the first run for this variation, add any text before
        # the first harness to the header.
        if not variation.header:
            segment = Segment (filename, file.tell())
            variation.header = segment

        # Parse the rest of the summary (the '# of ' lines).
        if len (variation.counts) == 0:
            variation.counts = self.zero_counts()

        # Parse up until the first line of the summary.
        if num_variations == 1:
            end = '\t\t=== ' + tool.name + ' Summary ===\n'
        else:
            end = ('\t\t=== ' + tool.name + ' Summary for '
                   + variation.name + ' ===\n')
        while True:
            line = file.readline()
            if line == '':
                self.fatal (filename, 'no recognised summary line')
            if line == end:
                break

            # Look for the start of a new harness.
            if line.startswith ('Running ') and line.endswith (' ...\n'):
                # Close off the current harness segment, if any.
                if harness:
                    segment.lines -= final_using
                    harness.add_segment (first_key, segment)
                name = line[len ('Running '):-len(' ...\n')]
                harness = variation.get_harness (name)
                segment = Segment (filename, file.tell())
                first_key = None
                final_using = 0
                continue

            # Record test results.  Associate the first test result with
            # the harness segment, so that if a run for a particular harness
            # has been split up, we can reassemble the individual segments
            # in a sensible order.
            #
            # dejagnu sometimes issues warnings about the testing environment
            # before running any tests.  Treat them as part of the header
            # rather than as a test result.
            match = self.result_re.match (line)
            if match and (harness or not line.startswith ('WARNING:')):
                if not harness:
                    self.fatal (filename, 'saw test result before harness name')
                name = match.group (2)
                # Ugly hack to get the right order for gfortran.
                if name.startswith ('gfortran.dg/g77/'):
                    name = 'h' + name
                key = (name, len (harness.results))
                harness.results.append ((key, line))
                if not first_key and sort_logs:
                    first_key = key
                if line.startswith ('ERROR: (DejaGnu)'):
                    for i in range (len (self.count_names)):
                        if 'DejaGnu errors' in self.count_names[i]:
                            variation.counts[i] += 1
                            break

            # 'Using ...' lines are only interesting in a header.  Splitting
            # the test up into parallel runs leads to more 'Using ...' lines
            # than there would be in a single log.
            if line.startswith ('Using '):
                final_using += 1
            else:
                final_using = 0

            # Add other text to the current segment, if any.
            if segment:
                segment.lines += 1

        # Close off the final harness segment, if any.
        if harness:
            segment.lines -= final_using
            harness.add_segment (first_key, segment)

        while True:
            before = file.tell()
            line = file.readline()
            if line == '':
                break
            if line == '\n':
                continue
            if not line.startswith ('# '):
                file.seek (before)
                break
            found = False
            for i in range (len (self.count_names)):
                if line.startswith (self.count_names[i]):
                    count = line[len (self.count_names[i]):-1].strip()
                    variation.counts[i] += self.parse_int (filename, count)
                    found = True
                    break
            if not found:
                self.fatal (filename, 'unknown test result: ' + line[:-1])

    # Parse an acats run, which uses a different format from dejagnu.
    # We have just skipped over '=== acats configuration ==='.
    def parse_acats_run (self, filename, file):
        # Parse the preamble, which describes the configuration and logs
        # the creation of support files.
        record = (self.acats_premable == '')
        if record:
            self.acats_premable = '\t\t=== acats configuration ===\n'
        while True:
            line = file.readline()
            if line == '':
                self.fatal (filename, 'could not parse acats preamble')
            if line == '\t\t=== acats tests ===\n':
                break
            if record:
                self.acats_premable += line

        # Parse the test results themselves, using a dummy variation name.
        tool = self.get_tool ('acats')
        variation = tool.get_variation ('none')
        self.parse_run (filename, file, tool, variation, 1)

        # Parse the failure list.
        while True:
            before = file.tell()
            line = file.readline()
            if line.startswith ('*** FAILURES: '):
                self.acats_failures.append (line[len ('*** FAILURES: '):-1])
                continue
            file.seek (before)
            break

    # Parse the final summary at the end of a log in order to capture
    # the version output that follows it.
    def parse_final_summary (self, filename, file):
        record = (self.version_output == '')
        while True:
            line = file.readline()
            if line == '':
                break
            if line.startswith ('# of '):
                continue
            if record:
                self.version_output += line
            if line == '\n':
                break

    # Parse a .log or .sum file.
    def parse_file (self, filename, file):
        tool = None
        target = None
        num_variations = 1
        while True:
            line = file.readline()
            if line == '':
                return

            # Parse the list of variations, which comes before the test
            # runs themselves.
            if line.startswith ('Schedule of variations:'):
                num_variations = self.parse_variations (filename, file)
                continue

            # Parse a testsuite run for one tool/variation combination.
            if line.startswith ('Running target '):
                name = line[len ('Running target '):-1]
                if not tool:
                    self.fatal (filename, 'could not parse tool name')
                if name not in self.known_variations:
                    self.fatal (filename, 'unknown target: ' + name)
                self.parse_run (filename, file, tool,
                                tool.get_variation (name),
                                num_variations)
                # If there is only one variation then there is no separate
                # summary for it.  Record any following version output.
                if num_variations == 1:
                    self.parse_final_summary (filename, file)
                continue

            # Parse the start line.  In the case where several files are being
            # parsed, pick the one with the earliest time.
            match = self.test_run_re.match (line)
            if match:
                time = self.parse_time (match.group (2))
                if not self.start_line or self.start_line[0] > time:
                    self.start_line = (time, line)
                continue

            # Parse the form used for native testing.
            if line.startswith ('Native configuration is '):
                self.native_line = line
                continue

            # Parse the target triplet.
            if line.startswith ('Target is '):
                self.target_line = line
                continue

            # Parse the host triplet.
            if line.startswith ('Host   is '):
                self.host_line = line
                continue

            # Parse the acats premable.
            if line == '\t\t=== acats configuration ===\n':
                self.parse_acats_run (filename, file)
                continue

            # Parse the tool name.
            match = self.tool_re.match (line)
            if match:
                tool = self.get_tool (match.group (1))
                continue

            # Skip over the final summary (which we instead create from
            # individual runs) and parse the version output.
            if tool and line == '\t\t=== ' + tool.name + ' Summary ===\n':
                if file.readline() != '\n':
                    self.fatal (filename, 'expected blank line after summary')
                self.parse_final_summary (filename, file)
                continue

            # Parse the completion line.  In the case where several files
            # are being parsed, pick the one with the latest time.
            match = self.completed_re.match (line)
            if match:
                time = self.parse_time (match.group (1))
                if not self.end_line or self.end_line[0] < time:
                    self.end_line = (time, line)
                continue

            # Sanity check to make sure that important text doesn't get
            # dropped accidentally.
            if strict and line.strip() != '':
                self.fatal (filename, 'unrecognised line: ' + line[:-1])

    # Output a segment of text.
    def output_segment (self, segment):
        with safe_open (segment.filename) as file:
            file.seek (segment.start)
            for i in range (segment.lines):
                sys.stdout.write (file.readline())

    # Output a summary giving the number of times each type of result has
    # been seen.
    def output_summary (self, tool, counts):
        for i in range (len (self.count_names)):
            name = self.count_names[i]
            # dejagnu only prints result types that were seen at least once,
            # but acats always prints a number of unexpected failures.
            if (counts[i] > 0
                or (tool.name == 'acats'
                    and name.startswith ('# of unexpected failures'))):
                sys.stdout.write ('%s%d\n' % (name, counts[i]))

    # Output unified .log or .sum information for a particular variation,
    # with a summary at the end.
    def output_variation (self, tool, variation):
        self.output_segment (variation.header)
        for harness in sorted (variation.harnesses.values(),
                               key = attrgetter ('name')):
            sys.stdout.write ('Running ' + harness.name + ' ...\n')
            if self.do_sum:
                harness.results.sort()
                for (key, line) in harness.results:
                    sys.stdout.write (line)
            else:
                # Rearrange the log segments into test order (but without
                # rearranging text within those segments).
                for key in sorted (harness.segments.keys()):
                    self.output_segment (harness.segments[key])
                for segment in harness.empty:
                    self.output_segment (segment)
        if len (self.variations) > 1:
            sys.stdout.write ('\t\t=== ' + tool.name + ' Summary for '
                              + variation.name + ' ===\n\n')
            self.output_summary (tool, variation.counts)

    # Output unified .log or .sum information for a particular tool,
    # with a summary at the end.
    def output_tool (self, tool):
        counts = self.zero_counts()
        if tool.name == 'acats':
            # acats doesn't use variations, so just output everything.
            # It also has a different approach to whitespace.
            sys.stdout.write ('\t\t=== ' + tool.name + ' tests ===\n')
            for variation in tool.variations.values():
                self.output_variation (tool, variation)
                self.accumulate_counts (counts, variation.counts)
            sys.stdout.write ('\t\t=== ' + tool.name + ' Summary ===\n')
        else:
            # Output the results in the usual dejagnu runtest format.
            sys.stdout.write ('\n\t\t=== ' + tool.name + ' tests ===\n\n'
                              'Schedule of variations:\n')
            for name in self.variations:
                if name in tool.variations:
                    sys.stdout.write ('    ' + name + '\n')
            sys.stdout.write ('\n')
            for name in self.variations:
                if name in tool.variations:
                    variation = tool.variations[name]
                    sys.stdout.write ('Running target '
                                      + variation.name + '\n')
                    self.output_variation (tool, variation)
                    self.accumulate_counts (counts, variation.counts)
            sys.stdout.write ('\n\t\t=== ' + tool.name + ' Summary ===\n\n')
        self.output_summary (tool, counts)

    def main (self):
        self.parse_cmdline()
        try:
            # Parse the input files.
            for filename in self.files:
                with safe_open (filename) as file:
                    self.parse_file (filename, file)

            # Decide what to output.
            if len (self.variations) == 0:
                self.variations = sorted (self.known_variations)
            else:
                for name in self.variations:
                    if name not in self.known_variations:
                        self.fatal (None, 'no results for ' + name)
            if len (self.tools) == 0:
                self.tools = sorted (self.runs.keys())

            # Output the header.
            if self.start_line:
                sys.stdout.write (self.start_line[1])
            sys.stdout.write (self.native_line)
            sys.stdout.write (self.target_line)
            sys.stdout.write (self.host_line)
            sys.stdout.write (self.acats_premable)

            # Output the main body.
            for name in self.tools:
                if name not in self.runs:
                    self.fatal (None, 'no results for ' + name)
                self.output_tool (self.runs[name])

            # Output the footer.
            if len (self.acats_failures) > 0:
                sys.stdout.write ('*** FAILURES: '
                                  + ' '.join (self.acats_failures) + '\n')
            sys.stdout.write (self.version_output)
            if self.end_line:
                sys.stdout.write (self.end_line[1])
        except IOError as e:
            self.fatal (e.filename, e.strerror)

Prog().main()