update_analyze_test_checks.py

#!/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__ importprint_function

importargparse
importglob
importitertools
importos# Used to advertise this file's name ("autogenerated_note").
importstring
importsubprocess
importsys
importtempfile
importre

fromUpdateTestChecksimportcommon

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*\(')

defmain():
fromargparseimportRawTextHelpFormatter
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('tests', nargs='+')
args=parser.parse_args()

autogenerated_note= (ADVERT+'utils/'+os.path.basename(__file__))

opt_basename=os.path.basename(args.opt_binary)
if (opt_basename!="opt"):
print('ERROR: Unexpected opt name: '+opt_basename, file=sys.stderr)
sys.exit(1)

test_paths= [testforpatterninargs.testsfortestinglob.glob(pattern)]
fortestintest_paths:
ifargs.verbose:
print('Scanning for RUN lines in test file: %s'% (test,), file=sys.stderr)
withopen(test) asf:
input_lines= [l.rstrip() forlinf]

raw_lines= [m.group(1)
formin [common.RUN_LINE_RE.match(l) forlininput_lines] ifm]
run_lines= [raw_lines[0]] iflen(raw_lines) >0else []
forlinraw_lines[1:]:
ifrun_lines[-1].endswith("\\"):
run_lines[-1] =run_lines[-1].rstrip("\\") +" "+l
else:
run_lines.append(l)

ifargs.verbose:
print('Found %d RUN lines:'% (len(run_lines),), file=sys.stderr)
forlinrun_lines:
print(' RUN: '+l, file=sys.stderr)

prefix_list= []
forlinrun_lines:
 (tool_cmd, filecheck_cmd) =tuple([cmd.strip() forcmdinl.split('|', 1)])

ifnottool_cmd.startswith(opt_basename+' '):
print('WARNING: Skipping non-%s RUN line: %s'% (opt_basename, l), file=sys.stderr)
continue

ifnotfilecheck_cmd.startswith('FileCheck '):
print('WARNING: Skipping non-FileChecked RUN line: '+l, file=sys.stderr)
continue

tool_cmd_args=tool_cmd[len(opt_basename):].strip()
tool_cmd_args=tool_cmd_args.replace('< %s', '').replace('%s', '').strip()

check_prefixes= [itemformincommon.CHECK_PREFIX_RE.finditer(filecheck_cmd)
foriteminm.group(1).split(',')]
ifnotcheck_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= {}
forprefixes, _inprefix_list:
forprefixinprefixes:
func_dict.update({prefix: dict()})
forprefixes, opt_argsinprefix_list:
ifargs.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.
forraw_tool_outputinre.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([prefixforprefixes, _inprefix_listforprefixinprefixes])
ifargs.verbose:
print('Rewriting FileCheck prefixes: %s'% (prefix_set,), file=sys.stderr)
output_lines= []
output_lines.append(autogenerated_note)

forinput_lineininput_lines:
ifis_in_function_start:
ifinput_line=='':
continue
ifinput_line.lstrip().startswith(';'):
m=common.CHECK_RE.match(input_line)
ifnotmorm.group(1) notinprefix_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

ifis_in_function:
ifcommon.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
ifinput_line.strip() =='}':
is_in_function=False
continue

# Discard any previous script advertising.
ifinput_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)
ifnotm:
continue
func_name=m.group(1)
ifargs.functionisnotNoneandfunc_name!=args.function:
# When filtering on a specific function, skip all others.
continue
is_in_function=is_in_function_start=True

ifargs.verbose:
print('Writing %d lines to %s...'% (len(output_lines), test), file=sys.stderr)

withopen(test, 'wb') asf:
f.writelines(['{}\n'.format(l).encode('utf-8') forlinoutput_lines])


if__name__=='__main__':
main()