update_cc_test_checks.py

#!/usr/bin/env python3
'''A utility to update LLVM IR CHECK lines in C/C++ FileCheck test files.

Example RUN lines in .c/.cc test files:

// RUN: %clang -emit-llvm -S %s -o - -O2 | FileCheck %s
// RUN: %clangxx -emit-llvm -S %s -o - -O2 | FileCheck -check-prefix=CHECK-A %s

Usage:

% utils/update_cc_test_checks.py --llvm-bin=release/bin test/a.cc
% utils/update_cc_test_checks.py --c-index-test=release/bin/c-index-test \
 --clang=release/bin/clang /tmp/c/a.cc
'''

importargparse
importcollections
importdistutils.spawn
importos
importshlex
importstring
importsubprocess
importsys
importre
importtempfile

fromUpdateTestChecksimportasm, common

ADVERT='// NOTE: Assertions have been autogenerated by '

CHECK_RE=re.compile(r'^\s*//\s*([^:]+?)(?:-NEXT|-NOT|-DAG|-LABEL)?:')
RUN_LINE_RE=re.compile('^//\s*RUN:\s*(.*)$')

SUBST= {
'%clang': [],
'%clang_cc1': ['-cc1'],
'%clangxx': ['--driver-mode=g++'],
}

defget_line2spell_and_mangled(args, clang_args):
ret= {}
withtempfile.NamedTemporaryFile() asf:
# TODO Make c-index-test print mangled names without circumventing through precompiled headers
status=subprocess.run([args.c_index_test, '-write-pch', f.name, *clang_args],
stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
ifstatus.returncode:
sys.stderr.write(status.stdout.decode())
sys.exit(2)
output=subprocess.check_output([args.c_index_test,
'-test-print-mangle', f.name])
ifsys.version_info[0] >2:
output=output.decode()

RE=re.compile(r'^FunctionDecl=(\w+):(\d+):\d+ \(Definition\) \[mangled=([^]]+)\]')
forlineinoutput.splitlines():
m=RE.match(line)
ifnotm: continue
spell, line, mangled=m.groups()
ifmangled=='_'+spell:
# HACK for MacOS (where the mangled name includes an _ for C but the IR won't):
mangled=spell
# Note -test-print-mangle does not print file names so if #include is used,
# the line number may come from an included file.
ret[int(line)-1] = (spell, mangled)
ifargs.verbose:
forline, func_nameinsorted(ret.items()):
print('line {}: found function {}'.format(line+1, func_name), file=sys.stderr)
returnret


defconfig():
parser=argparse.ArgumentParser(
description=__doc__,
formatter_class=argparse.RawTextHelpFormatter)
parser.add_argument('-v', '--verbose', action='store_true')
parser.add_argument('--llvm-bin', help='llvm $prefix/bin path')
parser.add_argument('--clang',
help='"clang" executable, defaults to $llvm_bin/clang')
parser.add_argument('--clang-args',
help='Space-separated extra args to clang, e.g. --clang-args=-v')
parser.add_argument('--c-index-test',
help='"c-index-test" executable, defaults to $llvm_bin/c-index-test')
parser.add_argument(
'--functions', nargs='+', help='A list of function name regexes. '
'If specified, update CHECK lines for functions matching at least one regex')
parser.add_argument(
'--x86_extra_scrub', action='store_true',
help='Use more regex for x86 matching to reduce diffs between various subtargets')
parser.add_argument('tests', nargs='+')
args=parser.parse_args()
args.clang_args=shlex.split(args.clang_argsor'')

ifargs.clangisNone:
ifargs.llvm_binisNone:
args.clang='clang'
else:
args.clang=os.path.join(args.llvm_bin, 'clang')
ifnotdistutils.spawn.find_executable(args.clang):
print('Please specify --llvm-bin or --clang', file=sys.stderr)
sys.exit(1)
ifargs.c_index_testisNone:
ifargs.llvm_binisNone:
args.c_index_test='c-index-test'
else:
args.c_index_test=os.path.join(args.llvm_bin, 'c-index-test')
ifnotdistutils.spawn.find_executable(args.c_index_test):
print('Please specify --llvm-bin or --c-index-test', file=sys.stderr)
sys.exit(1)

returnargs


defget_function_body(args, filename, clang_args, prefixes, triple_in_cmd, func_dict):
# TODO Clean up duplication of asm/common build_function_body_dictionary
# Invoke external tool and extract function bodies.
raw_tool_output=common.invoke_tool(args.clang, clang_args, filename)
if'-emit-llvm'inclang_args:
common.build_function_body_dictionary(
common.OPT_FUNCTION_RE, common.scrub_body, [],
raw_tool_output, prefixes, func_dict, args.verbose)
else:
print('The clang command line should include -emit-llvm as asm tests '
'are discouraged in Clang testsuite.', file=sys.stderr)
sys.exit(1)


defmain():
args=config()
autogenerated_note= (ADVERT+'utils/'+os.path.basename(__file__))

forfilenameinargs.tests:
withopen(filename) asf:
input_lines= [l.rstrip() forlinf]

# Extract RUN lines.
raw_lines= [m.group(1)
formin [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 {} RUN lines:'.format(len(run_lines)), file=sys.stderr)
forlinrun_lines:
print(' RUN: '+l, file=sys.stderr)

# Build a list of clang command lines and check prefixes from RUN lines.
run_list= []
line2spell_and_mangled_list=collections.defaultdict(list)
forlinrun_lines:
commands= [cmd.strip() forcmdinl.split('|', 1)]

triple_in_cmd=None
m=common.TRIPLE_ARG_RE.search(commands[0])
ifm:
triple_in_cmd=m.groups()[0]

# Apply %clang substitution rule, replace %s by `filename`, and append args.clang_args
clang_args=shlex.split(commands[0])
ifclang_args[0] notinSUBST:
print('WARNING: Skipping non-clang RUN line: '+l, file=sys.stderr)
continue
clang_args[0:1] =SUBST[clang_args[0]]
clang_args= [filenameifi=='%s'elseiforiinclang_args] +args.clang_args

# Extract -check-prefix in FileCheck args
filecheck_cmd=commands[-1]
ifnotfilecheck_cmd.startswith('FileCheck '):
print('WARNING: Skipping non-FileChecked RUN line: '+l, file=sys.stderr)
continue
check_prefixes= [itemformincommon.CHECK_PREFIX_RE.finditer(filecheck_cmd)
foriteminm.group(1).split(',')]
ifnotcheck_prefixes:
check_prefixes= ['CHECK']
run_list.append((check_prefixes, clang_args, triple_in_cmd))

# Strip CHECK lines which are in `prefix_set`, update test file.
prefix_set=set([prefixforpinrun_listforprefixinp[0]])
input_lines= []
withopen(filename, 'r+') asf:
forlineinf:
m=CHECK_RE.match(line)
ifnot (mandm.group(1) inprefix_set) andline!='//\n':
input_lines.append(line)
f.seek(0)
f.writelines(input_lines)
f.truncate()

# Execute clang, generate LLVM IR, and extract functions.
func_dict= {}
forpinrun_list:
prefixes=p[0]
forprefixinprefixes:
func_dict.update({prefix: dict()})
forprefixes, clang_args, triple_in_cmdinrun_list:
ifargs.verbose:
print('Extracted clang cmd: clang {}'.format(clang_args), file=sys.stderr)
print('Extracted FileCheck prefixes: {}'.format(prefixes), file=sys.stderr)

get_function_body(args, filename, clang_args, prefixes, triple_in_cmd, func_dict)

# Invoke c-index-test to get mapping from start lines to mangled names.
# Forward all clang args for now.
fork, vinget_line2spell_and_mangled(args, clang_args).items():
line2spell_and_mangled_list[k].append(v)

output_lines= [autogenerated_note]
foridx, lineinenumerate(input_lines):
# Discard any previous script advertising.
ifline.startswith(ADVERT):
continue
ifidxinline2spell_and_mangled_list:
added=set()
forspell, mangledinline2spell_and_mangled_list[idx]:
# One line may contain multiple function declarations.
# Skip if the mangled name has been added before.
# The line number may come from an included file,
# we simply require the spelling name to appear on the line
# to exclude functions from other files.
ifmangledinaddedorspellnotinline:
continue
ifargs.functionsisNoneorany(re.search(regex, spell) forregexinargs.functions):
ifadded:
output_lines.append('//')
added.add(mangled)
common.add_ir_checks(output_lines, '//', run_list, func_dict, mangled)
output_lines.append(line.rstrip('\n'))

# Update the test file.
withopen(filename, 'w') asf:
forlineinoutput_lines:
f.write(line+'\n')

return0


if__name__=='__main__':
sys.exit(main())