2016-03-25 07:19:26 +08:00
|
|
|
#!/usr/bin/env python2.7
|
|
|
|
|
|
2016-04-06 02:00:47 +08:00
|
|
|
"""A script to generate FileCheck statements for regression tests.
|
2016-03-25 07:19:26 +08:00
|
|
|
|
|
|
|
|
This script is a utility to update LLVM opt or llc test cases with new
|
|
|
|
|
FileCheck patterns. It can either update all of the tests in the file or
|
|
|
|
|
a single test function.
|
2016-04-06 02:00:47 +08:00
|
|
|
|
|
|
|
|
Example usage:
|
|
|
|
|
$ update_test_checks.py --tool=../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 -instcombine -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!
|
2016-03-25 07:19:26 +08:00
|
|
|
"""
|
|
|
|
|
|
|
|
|
|
import argparse
|
|
|
|
|
import itertools
|
|
|
|
|
import os # Used to advertise this file's name ("autogenerated_note").
|
|
|
|
|
import string
|
|
|
|
|
import subprocess
|
|
|
|
|
import sys
|
|
|
|
|
import tempfile
|
|
|
|
|
import re
|
|
|
|
|
|
2016-04-06 03:50:21 +08:00
|
|
|
ADVERT = '; NOTE: Assertions have been autogenerated by '
|
2016-03-25 07:19:26 +08:00
|
|
|
|
|
|
|
|
# RegEx: this is where the magic happens.
|
|
|
|
|
|
2016-03-28 04:43:02 +08:00
|
|
|
SCRUB_LEADING_WHITESPACE_RE = re.compile(r'^(\s+)')
|
2016-03-25 07:19:26 +08:00
|
|
|
SCRUB_WHITESPACE_RE = re.compile(r'(?!^(| \w))[ \t]+', flags=re.M)
|
|
|
|
|
SCRUB_TRAILING_WHITESPACE_RE = re.compile(r'[ \t]+$', flags=re.M)
|
|
|
|
|
SCRUB_X86_SHUFFLES_RE = (
|
|
|
|
|
re.compile(
|
2016-07-03 21:08:29 +08:00
|
|
|
r'^(\s*\w+) [^#\n]+#+ ((?:[xyz]mm\d+|mem)( \{%k\d+\}( \{z\})?)? = .*)$',
|
2016-03-25 07:19:26 +08:00
|
|
|
flags=re.M))
|
|
|
|
|
SCRUB_X86_SP_RE = re.compile(r'\d+\(%(esp|rsp)\)')
|
|
|
|
|
SCRUB_X86_RIP_RE = re.compile(r'[.\w]+\(%rip\)')
|
2016-06-12 04:39:21 +08:00
|
|
|
SCRUB_X86_LCP_RE = re.compile(r'\.LCPI[0-9]+_[0-9]+')
|
2016-03-25 07:19:26 +08:00
|
|
|
SCRUB_KILL_COMMENT_RE = re.compile(r'^ *#+ +kill:.*\n')
|
|
|
|
|
SCRUB_IR_COMMENT_RE = re.compile(r'\s*;.*')
|
|
|
|
|
|
|
|
|
|
RUN_LINE_RE = re.compile('^\s*;\s*RUN:\s*(.*)$')
|
2016-03-26 01:00:12 +08:00
|
|
|
IR_FUNCTION_RE = re.compile('^\s*define\s+(?:internal\s+)?[^@]*@([\w-]+)\s*\(')
|
2016-03-25 07:19:26 +08:00
|
|
|
LLC_FUNCTION_RE = re.compile(
|
|
|
|
|
r'^_?(?P<func>[^:]+):[ \t]*#+[ \t]*@(?P=func)\n[^:]*?'
|
|
|
|
|
r'(?P<body>^##?[ \t]+[^:]+:.*?)\s*'
|
|
|
|
|
r'^\s*(?:[^:\n]+?:\s*\n\s*\.size|\.cfi_endproc|\.globl|\.comm|\.(?:sub)?section)',
|
|
|
|
|
flags=(re.M | re.S))
|
|
|
|
|
OPT_FUNCTION_RE = re.compile(
|
2016-03-26 01:00:12 +08:00
|
|
|
r'^\s*define\s+(?:internal\s+)?[^@]*@(?P<func>[\w-]+?)\s*\('
|
2017-01-10 03:24:19 +08:00
|
|
|
r'(\s+)?[^)]*[^{]*\{\n(?P<body>.*?)^\}$',
|
2016-03-25 07:19:26 +08:00
|
|
|
flags=(re.M | re.S))
|
2017-01-14 17:39:35 +08:00
|
|
|
CHECK_PREFIX_RE = re.compile('--?check-prefix(?:es)?=(\S+)')
|
2016-03-25 07:19:26 +08:00
|
|
|
CHECK_RE = re.compile(r'^\s*;\s*([^:]+?)(?:-NEXT|-NOT|-DAG|-LABEL)?:')
|
Update update_test_checks to work properly with phi nodes and other fun things.
Summary:
Prior to this change, phi nodes were never considered defs, and so we ended up with undefined variables for any loop. Now, instead of trying to find just defs, we iterate over each actual IR value in the line, and replace them one by one with either a definition or a use.
We also don't try to match anything in the comment portions of the line.
I've tested it even on things like function pointer calls, etc, and against existing test cases uses update_test_checks
With this change, we are able to use update_tests on the cyclic cases in newgvn.
The only case i'm aware of that will misfire is if you have a string with which contains a valid token.
However, this is the same as it is now, with a slightly larger set of strings that may misfire.
Prior to this change, a test with the string " %a =" would be replaced.
Reviewers: spatel, chandlerc
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D28384
llvm-svn: 291357
2017-01-08 03:04:59 +08:00
|
|
|
# Match things that look at identifiers, but only if they are followed by
|
|
|
|
|
# spaces, commas, paren, or end of the string
|
2017-01-15 15:40:46 +08:00
|
|
|
IR_VALUE_RE = re.compile(r'(\s+)%([\w\.]+?)([,\s\(\)]|\Z)')
|
2016-03-25 07:19:26 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
# Invoke the tool that is being tested.
|
|
|
|
|
def invoke_tool(args, cmd_args, ir):
|
|
|
|
|
with open(ir) as ir_file:
|
|
|
|
|
stdout = subprocess.check_output(args.tool_binary + ' ' + cmd_args,
|
|
|
|
|
shell=True, stdin=ir_file)
|
|
|
|
|
# Fix line endings to unix CR style.
|
|
|
|
|
stdout = stdout.replace('\r\n', '\n')
|
|
|
|
|
return stdout
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# FIXME: Separate the x86-specific scrubbers, so this can be used for other targets.
|
|
|
|
|
def scrub_asm(asm):
|
|
|
|
|
# Detect shuffle asm comments and hide the operands in favor of the comments.
|
|
|
|
|
asm = SCRUB_X86_SHUFFLES_RE.sub(r'\1 {{.*#+}} \2', asm)
|
|
|
|
|
# Generically match the stack offset of a memory operand.
|
|
|
|
|
asm = SCRUB_X86_SP_RE.sub(r'{{[0-9]+}}(%\1)', asm)
|
|
|
|
|
# Generically match a RIP-relative memory operand.
|
|
|
|
|
asm = SCRUB_X86_RIP_RE.sub(r'{{.*}}(%rip)', asm)
|
2016-06-12 04:39:21 +08:00
|
|
|
# Generically match a LCP symbol.
|
|
|
|
|
asm = SCRUB_X86_LCP_RE.sub(r'{{\.LCPI.*}}', asm)
|
2016-03-25 07:19:26 +08:00
|
|
|
# Strip kill operands inserted into the asm.
|
|
|
|
|
asm = SCRUB_KILL_COMMENT_RE.sub('', asm)
|
|
|
|
|
return asm
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def scrub_body(body, tool_basename):
|
|
|
|
|
# Scrub runs of whitespace out of the assembly, but leave the leading
|
|
|
|
|
# whitespace in place.
|
|
|
|
|
body = SCRUB_WHITESPACE_RE.sub(r' ', body)
|
|
|
|
|
# Expand the tabs used for indentation.
|
|
|
|
|
body = string.expandtabs(body, 2)
|
|
|
|
|
# Strip trailing whitespace.
|
|
|
|
|
body = SCRUB_TRAILING_WHITESPACE_RE.sub(r'', body)
|
|
|
|
|
if tool_basename == "llc":
|
|
|
|
|
body = scrub_asm(body)
|
|
|
|
|
return body
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# Build up a dictionary of all the function bodies.
|
|
|
|
|
def build_function_body_dictionary(raw_tool_output, prefixes, func_dict, verbose, tool_basename):
|
|
|
|
|
if tool_basename == "llc":
|
|
|
|
|
func_regex = LLC_FUNCTION_RE
|
|
|
|
|
else:
|
|
|
|
|
func_regex = OPT_FUNCTION_RE
|
|
|
|
|
for m in func_regex.finditer(raw_tool_output):
|
|
|
|
|
if not m:
|
|
|
|
|
continue
|
|
|
|
|
func = m.group('func')
|
|
|
|
|
scrubbed_body = scrub_body(m.group('body'), tool_basename)
|
|
|
|
|
if func.startswith('stress'):
|
|
|
|
|
# We only use the last line of the function body for stress tests.
|
|
|
|
|
scrubbed_body = '\n'.join(scrubbed_body.splitlines()[-1:])
|
|
|
|
|
if verbose:
|
|
|
|
|
print >>sys.stderr, 'Processing function: ' + func
|
|
|
|
|
for l in scrubbed_body.splitlines():
|
|
|
|
|
print >>sys.stderr, ' ' + l
|
|
|
|
|
for prefix in prefixes:
|
|
|
|
|
if func in func_dict[prefix] and func_dict[prefix][func] != scrubbed_body:
|
|
|
|
|
if prefix == prefixes[-1]:
|
|
|
|
|
print >>sys.stderr, ('WARNING: Found conflicting asm under the '
|
|
|
|
|
'same prefix: %r!' % (prefix,))
|
|
|
|
|
else:
|
|
|
|
|
func_dict[prefix][func] = None
|
|
|
|
|
continue
|
|
|
|
|
|
|
|
|
|
func_dict[prefix][func] = scrubbed_body
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# Create a FileCheck variable name based on an IR name.
|
|
|
|
|
def get_value_name(var):
|
|
|
|
|
if var.isdigit():
|
|
|
|
|
var = 'TMP' + var
|
|
|
|
|
var = var.replace('.', '_')
|
|
|
|
|
return var.upper()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# Create a FileCheck variable from regex.
|
|
|
|
|
def get_value_definition(var):
|
|
|
|
|
return '[[' + get_value_name(var) + ':%.*]]'
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# Use a FileCheck variable.
|
|
|
|
|
def get_value_use(var):
|
|
|
|
|
return '[[' + get_value_name(var) + ']]'
|
|
|
|
|
|
|
|
|
|
# Replace IR value defs and uses with FileCheck variables.
|
|
|
|
|
def genericize_check_lines(lines):
|
Update update_test_checks to work properly with phi nodes and other fun things.
Summary:
Prior to this change, phi nodes were never considered defs, and so we ended up with undefined variables for any loop. Now, instead of trying to find just defs, we iterate over each actual IR value in the line, and replace them one by one with either a definition or a use.
We also don't try to match anything in the comment portions of the line.
I've tested it even on things like function pointer calls, etc, and against existing test cases uses update_test_checks
With this change, we are able to use update_tests on the cyclic cases in newgvn.
The only case i'm aware of that will misfire is if you have a string with which contains a valid token.
However, this is the same as it is now, with a slightly larger set of strings that may misfire.
Prior to this change, a test with the string " %a =" would be replaced.
Reviewers: spatel, chandlerc
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D28384
llvm-svn: 291357
2017-01-08 03:04:59 +08:00
|
|
|
# This gets called for each match that occurs in
|
|
|
|
|
# a line. We transform variables we haven't seen
|
|
|
|
|
# into defs, and variables we have seen into uses.
|
|
|
|
|
def transform_line_vars(match):
|
|
|
|
|
var = match.group(2)
|
|
|
|
|
if var in vars_seen:
|
|
|
|
|
rv = get_value_use(var)
|
|
|
|
|
else:
|
|
|
|
|
vars_seen.add(var)
|
|
|
|
|
rv = get_value_definition(var)
|
|
|
|
|
# re.sub replaces the entire regex match
|
|
|
|
|
# with whatever you return, so we have
|
|
|
|
|
# to make sure to hand it back everything
|
|
|
|
|
# including the commas and spaces.
|
|
|
|
|
return match.group(1) + rv + match.group(3)
|
|
|
|
|
|
|
|
|
|
vars_seen = set()
|
2016-03-25 07:19:26 +08:00
|
|
|
lines_with_def = []
|
Update update_test_checks to work properly with phi nodes and other fun things.
Summary:
Prior to this change, phi nodes were never considered defs, and so we ended up with undefined variables for any loop. Now, instead of trying to find just defs, we iterate over each actual IR value in the line, and replace them one by one with either a definition or a use.
We also don't try to match anything in the comment portions of the line.
I've tested it even on things like function pointer calls, etc, and against existing test cases uses update_test_checks
With this change, we are able to use update_tests on the cyclic cases in newgvn.
The only case i'm aware of that will misfire is if you have a string with which contains a valid token.
However, this is the same as it is now, with a slightly larger set of strings that may misfire.
Prior to this change, a test with the string " %a =" would be replaced.
Reviewers: spatel, chandlerc
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D28384
llvm-svn: 291357
2017-01-08 03:04:59 +08:00
|
|
|
|
|
|
|
|
for i, line in enumerate(lines):
|
2016-03-28 04:44:35 +08:00
|
|
|
# An IR variable named '%.' matches the FileCheck regex string.
|
|
|
|
|
line = line.replace('%.', '%dot')
|
Update update_test_checks to work properly with phi nodes and other fun things.
Summary:
Prior to this change, phi nodes were never considered defs, and so we ended up with undefined variables for any loop. Now, instead of trying to find just defs, we iterate over each actual IR value in the line, and replace them one by one with either a definition or a use.
We also don't try to match anything in the comment portions of the line.
I've tested it even on things like function pointer calls, etc, and against existing test cases uses update_test_checks
With this change, we are able to use update_tests on the cyclic cases in newgvn.
The only case i'm aware of that will misfire is if you have a string with which contains a valid token.
However, this is the same as it is now, with a slightly larger set of strings that may misfire.
Prior to this change, a test with the string " %a =" would be replaced.
Reviewers: spatel, chandlerc
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D28384
llvm-svn: 291357
2017-01-08 03:04:59 +08:00
|
|
|
# Ignore any comments, since the check lines will too.
|
|
|
|
|
scrubbed_line = SCRUB_IR_COMMENT_RE.sub(r'', line)
|
|
|
|
|
lines[i] = IR_VALUE_RE.sub(transform_line_vars, scrubbed_line)
|
|
|
|
|
return lines
|
2016-03-25 07:19:26 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
def add_checks(output_lines, prefix_list, func_dict, func_name, tool_basename):
|
|
|
|
|
# Select a label format based on the whether we're checking asm or IR.
|
|
|
|
|
if tool_basename == "llc":
|
|
|
|
|
check_label_format = "; %s-LABEL: %s:"
|
|
|
|
|
else:
|
|
|
|
|
check_label_format = "; %s-LABEL: @%s("
|
|
|
|
|
|
|
|
|
|
printed_prefixes = []
|
|
|
|
|
for checkprefixes, _ in prefix_list:
|
|
|
|
|
for checkprefix in checkprefixes:
|
|
|
|
|
if checkprefix in printed_prefixes:
|
|
|
|
|
break
|
|
|
|
|
if not func_dict[checkprefix][func_name]:
|
|
|
|
|
continue
|
|
|
|
|
# Add some space between different check prefixes, but not after the last
|
|
|
|
|
# check line (before the test code).
|
|
|
|
|
#if len(printed_prefixes) != 0:
|
|
|
|
|
# output_lines.append(';')
|
|
|
|
|
printed_prefixes.append(checkprefix)
|
|
|
|
|
output_lines.append(check_label_format % (checkprefix, func_name))
|
|
|
|
|
func_body = func_dict[checkprefix][func_name].splitlines()
|
|
|
|
|
|
|
|
|
|
# For IR output, change all defs to FileCheck variables, so we're immune
|
|
|
|
|
# to variable naming fashions.
|
|
|
|
|
if tool_basename == "opt":
|
|
|
|
|
func_body = genericize_check_lines(func_body)
|
|
|
|
|
|
2016-04-06 00:49:07 +08:00
|
|
|
# This could be selectively enabled with an optional invocation argument.
|
|
|
|
|
# Disabled for now: better to check everything. Be safe rather than sorry.
|
|
|
|
|
|
2016-03-25 07:19:26 +08:00
|
|
|
# Handle the first line of the function body as a special case because
|
|
|
|
|
# it's often just noise (a useless asm comment or entry label).
|
2016-04-06 00:49:07 +08:00
|
|
|
#if func_body[0].startswith("#") or func_body[0].startswith("entry:"):
|
|
|
|
|
# is_blank_line = True
|
|
|
|
|
#else:
|
|
|
|
|
# output_lines.append('; %s: %s' % (checkprefix, func_body[0]))
|
|
|
|
|
# is_blank_line = False
|
|
|
|
|
|
|
|
|
|
# For llc tests, there may be asm directives between the label and the
|
|
|
|
|
# first checked line (most likely that first checked line is "# BB#0").
|
|
|
|
|
if tool_basename == "opt":
|
2016-03-25 07:19:26 +08:00
|
|
|
is_blank_line = False
|
2016-04-06 00:49:07 +08:00
|
|
|
else:
|
|
|
|
|
is_blank_line = True;
|
2016-03-25 07:19:26 +08:00
|
|
|
|
2016-04-06 00:49:07 +08:00
|
|
|
for func_line in func_body:
|
2016-03-25 07:19:26 +08:00
|
|
|
if func_line.strip() == '':
|
|
|
|
|
is_blank_line = True
|
|
|
|
|
continue
|
|
|
|
|
# Do not waste time checking IR comments.
|
|
|
|
|
if tool_basename == "opt":
|
|
|
|
|
func_line = SCRUB_IR_COMMENT_RE.sub(r'', func_line)
|
|
|
|
|
|
|
|
|
|
# Skip blank lines instead of checking them.
|
|
|
|
|
if is_blank_line == True:
|
|
|
|
|
output_lines.append('; %s: %s' % (checkprefix, func_line))
|
|
|
|
|
else:
|
|
|
|
|
output_lines.append('; %s-NEXT: %s' % (checkprefix, func_line))
|
|
|
|
|
is_blank_line = False
|
|
|
|
|
|
|
|
|
|
# Add space between different check prefixes and also before the first
|
|
|
|
|
# line of code in the test function.
|
|
|
|
|
output_lines.append(';')
|
|
|
|
|
break
|
|
|
|
|
return output_lines
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def should_add_line_to_output(input_line, prefix_set):
|
|
|
|
|
# Skip any blank comment lines in the IR.
|
|
|
|
|
if input_line.strip() == ';':
|
|
|
|
|
return False
|
|
|
|
|
# Skip any blank lines in the IR.
|
|
|
|
|
#if input_line.strip() == '':
|
|
|
|
|
# return False
|
|
|
|
|
# And skip any CHECK lines. We're building our own.
|
|
|
|
|
m = CHECK_RE.match(input_line)
|
|
|
|
|
if m and m.group(1) in prefix_set:
|
|
|
|
|
return False
|
|
|
|
|
|
|
|
|
|
return True
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def main():
|
2016-04-06 02:00:47 +08:00
|
|
|
from argparse import RawTextHelpFormatter
|
|
|
|
|
parser = argparse.ArgumentParser(description=__doc__, formatter_class=RawTextHelpFormatter)
|
2016-03-25 07:19:26 +08:00
|
|
|
parser.add_argument('-v', '--verbose', action='store_true',
|
|
|
|
|
help='Show verbose output')
|
|
|
|
|
parser.add_argument('--tool-binary', default='llc',
|
|
|
|
|
help='The tool 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()
|
|
|
|
|
|
2016-04-06 03:50:21 +08:00
|
|
|
autogenerated_note = (ADVERT + 'utils/' + os.path.basename(__file__))
|
2016-03-25 07:19:26 +08:00
|
|
|
|
|
|
|
|
tool_basename = os.path.basename(args.tool_binary)
|
|
|
|
|
if (tool_basename != "llc" and tool_basename != "opt"):
|
|
|
|
|
print >>sys.stderr, 'ERROR: Unexpected tool name: ' + tool_basename
|
|
|
|
|
sys.exit(1)
|
|
|
|
|
|
|
|
|
|
for test in args.tests:
|
|
|
|
|
if args.verbose:
|
|
|
|
|
print >>sys.stderr, 'Scanning for RUN lines in test file: %s' % (test,)
|
|
|
|
|
with open(test) as f:
|
|
|
|
|
input_lines = [l.rstrip() for l in f]
|
|
|
|
|
|
2016-12-30 03:32:34 +08:00
|
|
|
raw_lines = [m.group(1)
|
2016-03-25 07:19:26 +08:00
|
|
|
for m in [RUN_LINE_RE.match(l) for l in input_lines] if m]
|
2016-12-30 03:32:34 +08:00
|
|
|
run_lines = [raw_lines[0]] if len(raw_lines) > 0 else []
|
|
|
|
|
for l in raw_lines[1:]:
|
2016-12-30 04:05:51 +08:00
|
|
|
if run_lines[-1].endswith("\\"):
|
|
|
|
|
run_lines[-1] = run_lines[-1].rstrip("\\") + " " + l
|
|
|
|
|
else:
|
|
|
|
|
run_lines.append(l)
|
2016-12-30 03:32:34 +08:00
|
|
|
|
2016-03-25 07:19:26 +08:00
|
|
|
if args.verbose:
|
|
|
|
|
print >>sys.stderr, 'Found %d RUN lines:' % (len(run_lines),)
|
|
|
|
|
for l in run_lines:
|
|
|
|
|
print >>sys.stderr, ' RUN: ' + l
|
|
|
|
|
|
|
|
|
|
prefix_list = []
|
|
|
|
|
for l in run_lines:
|
|
|
|
|
(tool_cmd, filecheck_cmd) = tuple([cmd.strip() for cmd in l.split('|', 1)])
|
|
|
|
|
|
|
|
|
|
if not tool_cmd.startswith(tool_basename + ' '):
|
|
|
|
|
print >>sys.stderr, 'WARNING: Skipping non-%s RUN line: %s' % (tool_basename, l)
|
|
|
|
|
continue
|
|
|
|
|
|
|
|
|
|
if not filecheck_cmd.startswith('FileCheck '):
|
|
|
|
|
print >>sys.stderr, 'WARNING: Skipping non-FileChecked RUN line: ' + l
|
|
|
|
|
continue
|
|
|
|
|
|
|
|
|
|
tool_cmd_args = tool_cmd[len(tool_basename):].strip()
|
|
|
|
|
tool_cmd_args = tool_cmd_args.replace('< %s', '').replace('%s', '').strip()
|
|
|
|
|
|
2017-01-14 17:39:35 +08:00
|
|
|
check_prefixes = [item for m in CHECK_PREFIX_RE.finditer(filecheck_cmd)
|
|
|
|
|
for item in m.group(1).split(',')]
|
2016-03-25 07:19:26 +08:00
|
|
|
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, tool_args in prefix_list:
|
|
|
|
|
if args.verbose:
|
|
|
|
|
print >>sys.stderr, 'Extracted tool cmd: ' + tool_basename + ' ' + tool_args
|
|
|
|
|
print >>sys.stderr, 'Extracted FileCheck prefixes: ' + str(prefixes)
|
|
|
|
|
|
|
|
|
|
raw_tool_output = invoke_tool(args, tool_args, test)
|
|
|
|
|
build_function_body_dictionary(raw_tool_output, prefixes, func_dict, args.verbose, tool_basename)
|
|
|
|
|
|
|
|
|
|
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 >>sys.stderr, 'Rewriting FileCheck prefixes: %s' % (prefix_set,)
|
|
|
|
|
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 = 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.
|
|
|
|
|
output_lines = add_checks(output_lines, prefix_list, func_dict, name, tool_basename)
|
|
|
|
|
is_in_function_start = False
|
|
|
|
|
|
|
|
|
|
if is_in_function:
|
|
|
|
|
if should_add_line_to_output(input_line, prefix_set) == True:
|
|
|
|
|
# This input line of the function body will go as-is into the output.
|
2016-03-28 04:43:02 +08:00
|
|
|
# Except make leading whitespace uniform: 2 spaces.
|
|
|
|
|
input_line = SCRUB_LEADING_WHITESPACE_RE.sub(r' ', input_line)
|
2016-03-25 07:19:26 +08:00
|
|
|
output_lines.append(input_line)
|
|
|
|
|
else:
|
|
|
|
|
continue
|
|
|
|
|
if input_line.strip() == '}':
|
|
|
|
|
is_in_function = False
|
|
|
|
|
continue
|
|
|
|
|
|
2016-04-06 03:50:21 +08:00
|
|
|
# Discard any previous script advertising.
|
|
|
|
|
if input_line.startswith(ADVERT):
|
2016-03-25 07:19:26 +08:00
|
|
|
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
|
|
|
|
|
name = m.group(1)
|
|
|
|
|
if args.function is not None and 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>>sys.stderr, 'Writing %d lines to %s...' % (len(output_lines), test)
|
|
|
|
|
|
|
|
|
|
with open(test, 'wb') as f:
|
|
|
|
|
f.writelines([l + '\n' for l in output_lines])
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
if __name__ == '__main__':
|
|
|
|
|
main()
|
|
|
|
|
|