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
| #!/usr/bin/env python
"""A script to generate FileCheck statements for 'opt' analysis tests.
This script is a utility to update LLVM opt analysis test cases with new
FileCheck patterns. It can either update all of the tests in the file or
a single test function.
Example usage:
$ update_analyze_test_checks.py --opt=../bin/opt test/foo.ll
Workflow:
1. Make a compiler patch that requires updating some number of FileCheck lines
in regression test files.
2. Save the patch and revert it from your local work area.
3. Update the RUN-lines in the affected regression tests to look canonical.
Example: "; RUN: opt < %s -analyze -cost-model -S | FileCheck %s"
4. Refresh the FileCheck lines for either the entire file or select functions by
running this script.
5. Commit the fresh baseline of checks.
6. Apply your patch from step 1 and rebuild your local binaries.
7. Re-run this script on affected regression tests.
8. Check the diffs to ensure the script has done something reasonable.
9. Submit a patch including the regression test diffs for review.
A common pattern is to have the script insert complete checking of every
instruction. Then, edit it down to only check the relevant instructions.
The script is designed to make adding checks to a test case fast, it is *not*
designed to be authoratitive about what constitutes a good test!
"""
from __future__ import print_function
import argparse
import glob
import itertools
import os # Used to advertise this file's name ("autogenerated_note").
import string
import subprocess
import sys
import tempfile
import re
from UpdateTestChecks import common
ADVERT = '; NOTE: Assertions have been autogenerated by '
# RegEx: this is where the magic happens.
IR_FUNCTION_RE = re.compile('^\s*define\s+(?:internal\s+)?[^@]*@([\w-]+)\s*\(')
def main():
from argparse import RawTextHelpFormatter
parser = argparse.ArgumentParser(description=__doc__, formatter_class=RawTextHelpFormatter)
parser.add_argument('-v', '--verbose', action='store_true',
help='Show verbose output')
parser.add_argument('--opt-binary', default='opt',
help='The opt binary used to generate the test case')
parser.add_argument(
'--function', help='The function in the test file to update')
parser.add_argument('-u', '--update-only', action='store_true',
help='Only update test if it was already autogened')
parser.add_argument('tests', nargs='+')
args = parser.parse_args()
script_name = os.path.basename(__file__)
autogenerated_note = (ADVERT + 'utils/' + script_name)
opt_basename = os.path.basename(args.opt_binary)
if (opt_basename != "opt"):
common.error('Unexpected opt name: ' + opt_basename)
sys.exit(1)
test_paths = [test for pattern in args.tests for test in glob.glob(pattern)]
for test in test_paths:
if args.verbose:
print('Scanning for RUN lines in test file: %s' % (test,), file=sys.stderr)
with open(test) as f:
input_lines = [l.rstrip() for l in f]
first_line = input_lines[0] if input_lines else ""
if 'autogenerated' in first_line and script_name not in first_line:
common.warn("Skipping test which wasn't autogenerated by " + script_name + ": " + test)
continue
if args.update_only:
if not first_line or 'autogenerated' not in first_line:
common.warn("Skipping test which isn't autogenerated: " + test)
continue
raw_lines = [m.group(1)
for m in [common.RUN_LINE_RE.match(l) for l in input_lines] if m]
run_lines = [raw_lines[0]] if len(raw_lines) > 0 else []
for l in raw_lines[1:]:
if run_lines[-1].endswith("\\"):
run_lines[-1] = run_lines[-1].rstrip("\\") + " " + l
else:
run_lines.append(l)
if args.verbose:
print('Found %d RUN lines:' % (len(run_lines),), file=sys.stderr)
for l in run_lines:
print(' RUN: ' + l, file=sys.stderr)
prefix_list = []
for l in run_lines:
if '|' not in l:
common.warn('Skipping unparseable RUN line: ' + l)
continue
(tool_cmd, filecheck_cmd) = tuple([cmd.strip() for cmd in l.split('|', 1)])
common.verify_filecheck_prefixes(filecheck_cmd)
if not tool_cmd.startswith(opt_basename + ' '):
common.warn('WSkipping non-%s RUN line: %s' % (opt_basename, l))
continue
if not filecheck_cmd.startswith('FileCheck '):
common.warn('Skipping non-FileChecked RUN line: ' + l)
continue
tool_cmd_args = tool_cmd[len(opt_basename):].strip()
tool_cmd_args = tool_cmd_args.replace('< %s', '').replace('%s', '').strip()
check_prefixes = [item for m in common.CHECK_PREFIX_RE.finditer(filecheck_cmd)
for item in m.group(1).split(',')]
if not check_prefixes:
check_prefixes = ['CHECK']
# FIXME: We should use multiple check prefixes to common check lines. For
# now, we just ignore all but the last.
prefix_list.append((check_prefixes, tool_cmd_args))
func_dict = {}
for prefixes, _ in prefix_list:
for prefix in prefixes:
func_dict.update({prefix: dict()})
for prefixes, opt_args in prefix_list:
if args.verbose:
print('Extracted opt cmd: ' + opt_basename + ' ' + opt_args, file=sys.stderr)
print('Extracted FileCheck prefixes: ' + str(prefixes), file=sys.stderr)
raw_tool_outputs = common.invoke_tool(args.opt_binary, opt_args, test)
# Split analysis outputs by "Printing analysis " declarations.
for raw_tool_output in re.split(r'Printing analysis ', raw_tool_outputs):
common.build_function_body_dictionary(
common.ANALYZE_FUNCTION_RE, common.scrub_body, [],
raw_tool_output, prefixes, func_dict, args.verbose)
is_in_function = False
is_in_function_start = False
prefix_set = set([prefix for prefixes, _ in prefix_list for prefix in prefixes])
if args.verbose:
print('Rewriting FileCheck prefixes: %s' % (prefix_set,), file=sys.stderr)
output_lines = []
output_lines.append(autogenerated_note)
for input_line in input_lines:
if is_in_function_start:
if input_line == '':
continue
if input_line.lstrip().startswith(';'):
m = common.CHECK_RE.match(input_line)
if not m or m.group(1) not in prefix_set:
output_lines.append(input_line)
continue
# Print out the various check lines here.
common.add_analyze_checks(output_lines, ';', prefix_list, func_dict, func_name)
is_in_function_start = False
if is_in_function:
if common.should_add_line_to_output(input_line, prefix_set):
# This input line of the function body will go as-is into the output.
# Except make leading whitespace uniform: 2 spaces.
input_line = common.SCRUB_LEADING_WHITESPACE_RE.sub(r' ', input_line)
output_lines.append(input_line)
else:
continue
if input_line.strip() == '}':
is_in_function = False
continue
# Discard any previous script advertising.
if input_line.startswith(ADVERT):
continue
# If it's outside a function, it just gets copied to the output.
output_lines.append(input_line)
m = IR_FUNCTION_RE.match(input_line)
if not m:
continue
func_name = m.group(1)
if args.function is not None and func_name != args.function:
# When filtering on a specific function, skip all others.
continue
is_in_function = is_in_function_start = True
if args.verbose:
print('Writing %d lines to %s...' % (len(output_lines), test), file=sys.stderr)
with open(test, 'wb') as f:
f.writelines(['{}\n'.format(l).encode('utf-8') for l in output_lines])
if __name__ == '__main__':
main()
|