forked from OSchip/llvm-project
[utils] Refactor utils/update_{,llc_}test_checks.py to share more code
Summary:
This revision refactors 1. parser 2. CHECK line adder of utils/update_{,llc_}test_checks.py
so that thir functionality can be re-used by other utility scripts (e.g. D42712)
Reviewers: asb, craig.topper, RKSimon, echristo
Subscribers: llvm-commits, spatel
Differential Revision: https://reviews.llvm.org/D42805
llvm-svn: 324803
This commit is contained in:
Fangrui Song
parent
3da7205114
commit
4f0f426d1f
|
|
@ -1,10 +1,18 @@
|
|||
import re
|
||||
import string
|
||||
import sys
|
||||
|
||||
from . import common
|
||||
|
||||
if sys.version_info[0] > 2:
|
||||
class string:
|
||||
expandtabs = str.expandtabs
|
||||
else:
|
||||
import string
|
||||
|
||||
# RegEx: this is where the magic happens.
|
||||
|
||||
##### Assembly parser
|
||||
|
||||
ASM_FUNCTION_X86_RE = re.compile(
|
||||
r'^_?(?P<func>[^:]+):[ \t]*#+[ \t]*@(?P=func)\n[^:]*?'
|
||||
r'(?P<body>^##?[ \t]+[^:]+:.*?)\s*'
|
||||
|
|
@ -197,3 +205,29 @@ def build_function_body_dictionary_for_triple(args, raw_tool_output, triple, pre
|
|||
common.build_function_body_dictionary(
|
||||
function_re, scrubber, [args], raw_tool_output, prefixes,
|
||||
func_dict, args.verbose)
|
||||
|
||||
##### Generator of assembly CHECK lines
|
||||
|
||||
def add_asm_checks(output_lines, comment_marker, run_list, func_dict, func_name):
|
||||
printed_prefixes = []
|
||||
for p in run_list:
|
||||
checkprefixes = p[0]
|
||||
for checkprefix in checkprefixes:
|
||||
if checkprefix in printed_prefixes:
|
||||
break
|
||||
# TODO func_dict[checkprefix] may be None, '' or not exist.
|
||||
# Fix the call sites.
|
||||
if func_name not in func_dict[checkprefix] or not func_dict[checkprefix][func_name]:
|
||||
continue
|
||||
# Add some space between different check prefixes.
|
||||
if len(printed_prefixes) != 0:
|
||||
output_lines.append(comment_marker)
|
||||
printed_prefixes.append(checkprefix)
|
||||
output_lines.append('%s %s-LABEL: %s:' % (comment_marker, checkprefix, func_name))
|
||||
func_body = func_dict[checkprefix][func_name].splitlines()
|
||||
output_lines.append('%s %s: %s' % (comment_marker, checkprefix, func_body[0]))
|
||||
for func_line in func_body[1:]:
|
||||
output_lines.append('%s %s-NEXT: %s' % (comment_marker, checkprefix, func_line))
|
||||
# Add space between different check prefixes and the first line of code.
|
||||
# output_lines.append(';')
|
||||
break
|
||||
|
|
|
|||
|
|
@ -1,22 +1,16 @@
|
|||
from __future__ import print_function
|
||||
import re
|
||||
import string
|
||||
import subprocess
|
||||
import sys
|
||||
|
||||
RUN_LINE_RE = re.compile('^\s*;\s*RUN:\s*(.*)$')
|
||||
CHECK_PREFIX_RE = re.compile('--?check-prefix(?:es)?=(\S+)')
|
||||
CHECK_RE = re.compile(r'^\s*;\s*([^:]+?)(?:-NEXT|-NOT|-DAG|-LABEL)?:')
|
||||
if sys.version_info[0] > 2:
|
||||
class string:
|
||||
expandtabs = str.expandtabs
|
||||
else:
|
||||
import string
|
||||
|
||||
IR_FUNCTION_RE = re.compile('^\s*define\s+(?:internal\s+)?[^@]*@(\w+)\s*\(')
|
||||
TRIPLE_IR_RE = re.compile(r'^target\s+triple\s*=\s*"([^"]+)"$')
|
||||
TRIPLE_ARG_RE = re.compile(r'-mtriple=([^ ]+)')
|
||||
|
||||
SCRUB_LEADING_WHITESPACE_RE = re.compile(r'^(\s+)')
|
||||
SCRUB_WHITESPACE_RE = re.compile(r'(?!^(| \w))[ \t]+', flags=re.M)
|
||||
SCRUB_TRAILING_WHITESPACE_RE = re.compile(r'[ \t]+$', flags=re.M)
|
||||
SCRUB_KILL_COMMENT_RE = re.compile(r'^ *#+ +kill:.*\n')
|
||||
SCRUB_LOOP_COMMENT_RE = re.compile(
|
||||
r'# =>This Inner Loop Header:.*|# in Loop:.*', flags=re.M)
|
||||
##### Common utilities for update_*test_checks.py
|
||||
|
||||
def should_add_line_to_output(input_line, prefix_set):
|
||||
# Skip any blank comment lines in the IR.
|
||||
|
|
@ -42,6 +36,38 @@ def invoke_tool(exe, cmd_args, ir):
|
|||
# Fix line endings to unix CR style.
|
||||
return stdout.replace('\r\n', '\n')
|
||||
|
||||
##### LLVM IR parser
|
||||
|
||||
RUN_LINE_RE = re.compile('^\s*;\s*RUN:\s*(.*)$')
|
||||
CHECK_PREFIX_RE = re.compile('--?check-prefix(?:es)?=(\S+)')
|
||||
CHECK_RE = re.compile(r'^\s*;\s*([^:]+?)(?:-NEXT|-NOT|-DAG|-LABEL)?:')
|
||||
|
||||
OPT_FUNCTION_RE = re.compile(
|
||||
r'^\s*define\s+(?:internal\s+)?[^@]*@(?P<func>[\w-]+?)\s*\('
|
||||
r'(\s+)?[^)]*[^{]*\{\n(?P<body>.*?)^\}$',
|
||||
flags=(re.M | re.S))
|
||||
|
||||
IR_FUNCTION_RE = re.compile('^\s*define\s+(?:internal\s+)?[^@]*@(\w+)\s*\(')
|
||||
TRIPLE_IR_RE = re.compile(r'^target\s+triple\s*=\s*"([^"]+)"$')
|
||||
TRIPLE_ARG_RE = re.compile(r'-mtriple=([^ ]+)')
|
||||
|
||||
SCRUB_LEADING_WHITESPACE_RE = re.compile(r'^(\s+)')
|
||||
SCRUB_WHITESPACE_RE = re.compile(r'(?!^(| \w))[ \t]+', flags=re.M)
|
||||
SCRUB_TRAILING_WHITESPACE_RE = re.compile(r'[ \t]+$', flags=re.M)
|
||||
SCRUB_KILL_COMMENT_RE = re.compile(r'^ *#+ +kill:.*\n')
|
||||
SCRUB_LOOP_COMMENT_RE = re.compile(
|
||||
r'# =>This Inner Loop Header:.*|# in Loop:.*', flags=re.M)
|
||||
|
||||
def scrub_body(body):
|
||||
# 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)
|
||||
return body
|
||||
|
||||
# Build up a dictionary of all the function bodies.
|
||||
def build_function_body_dictionary(function_re, scrubber, scrubber_args, raw_tool_output, prefixes, func_dict, verbose):
|
||||
for m in function_re.finditer(raw_tool_output):
|
||||
|
|
@ -66,3 +92,114 @@ def build_function_body_dictionary(function_re, scrubber, scrubber_args, raw_too
|
|||
continue
|
||||
|
||||
func_dict[prefix][func] = scrubbed_body
|
||||
|
||||
##### Generator of LLVM IR CHECK lines
|
||||
|
||||
SCRUB_IR_COMMENT_RE = re.compile(r'\s*;.*')
|
||||
|
||||
# Match things that look at identifiers, but only if they are followed by
|
||||
# spaces, commas, paren, or end of the string
|
||||
IR_VALUE_RE = re.compile(r'(\s+)%([\w\.]+?)([,\s\(\)]|\Z)')
|
||||
|
||||
# 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):
|
||||
# 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()
|
||||
lines_with_def = []
|
||||
|
||||
for i, line in enumerate(lines):
|
||||
# An IR variable named '%.' matches the FileCheck regex string.
|
||||
line = line.replace('%.', '%dot')
|
||||
# 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
|
||||
|
||||
|
||||
def add_ir_checks(output_lines, prefix_list, func_dict, func_name, opt_basename):
|
||||
# Label format is based on IR string.
|
||||
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.
|
||||
func_body = genericize_check_lines(func_body)
|
||||
|
||||
# This could be selectively enabled with an optional invocation argument.
|
||||
# Disabled for now: better to check everything. Be safe rather than sorry.
|
||||
|
||||
# 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).
|
||||
#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
|
||||
|
||||
is_blank_line = False
|
||||
|
||||
for func_line in func_body:
|
||||
if func_line.strip() == '':
|
||||
is_blank_line = True
|
||||
continue
|
||||
# Do not waste time checking IR comments.
|
||||
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
|
||||
|
|
|
|||
|
|
@ -19,30 +19,6 @@ from UpdateTestChecks import asm, common
|
|||
ADVERT = '; NOTE: Assertions have been autogenerated by '
|
||||
|
||||
|
||||
def add_checks(output_lines, run_list, func_dict, func_name):
|
||||
printed_prefixes = []
|
||||
for p in run_list:
|
||||
checkprefixes = p[0]
|
||||
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.
|
||||
if len(printed_prefixes) != 0:
|
||||
output_lines.append(';')
|
||||
printed_prefixes.append(checkprefix)
|
||||
output_lines.append('; %s-LABEL: %s:' % (checkprefix, func_name))
|
||||
func_body = func_dict[checkprefix][func_name].splitlines()
|
||||
output_lines.append('; %s: %s' % (checkprefix, func_body[0]))
|
||||
for func_line in func_body[1:]:
|
||||
output_lines.append('; %s-NEXT: %s' % (checkprefix, func_line))
|
||||
# Add space between different check prefixes and the first line of code.
|
||||
# output_lines.append(';')
|
||||
break
|
||||
return output_lines
|
||||
|
||||
|
||||
def main():
|
||||
parser = argparse.ArgumentParser(description=__doc__)
|
||||
parser.add_argument('-v', '--verbose', action='store_true',
|
||||
|
|
@ -156,7 +132,7 @@ def main():
|
|||
continue
|
||||
|
||||
# Print out the various check lines here.
|
||||
output_lines = add_checks(output_lines, run_list, func_dict, func_name)
|
||||
asm.add_asm_checks(output_lines, ';', run_list, func_dict, func_name)
|
||||
is_in_function_start = False
|
||||
|
||||
if is_in_function:
|
||||
|
|
|
|||
|
|
@ -44,133 +44,10 @@ ADVERT = '; NOTE: Assertions have been autogenerated by '
|
|||
|
||||
# RegEx: this is where the magic happens.
|
||||
|
||||
SCRUB_IR_COMMENT_RE = re.compile(r'\s*;.*')
|
||||
|
||||
IR_FUNCTION_RE = re.compile('^\s*define\s+(?:internal\s+)?[^@]*@([\w-]+)\s*\(')
|
||||
OPT_FUNCTION_RE = re.compile(
|
||||
r'^\s*define\s+(?:internal\s+)?[^@]*@(?P<func>[\w-]+?)\s*\('
|
||||
r'(\s+)?[^)]*[^{]*\{\n(?P<body>.*?)^\}$',
|
||||
flags=(re.M | re.S))
|
||||
# Match things that look at identifiers, but only if they are followed by
|
||||
# spaces, commas, paren, or end of the string
|
||||
IR_VALUE_RE = re.compile(r'(\s+)%([\w\.]+?)([,\s\(\)]|\Z)')
|
||||
|
||||
|
||||
|
||||
def scrub_body(body, opt_basename):
|
||||
# Scrub runs of whitespace out of the assembly, but leave the leading
|
||||
# whitespace in place.
|
||||
body = common.SCRUB_WHITESPACE_RE.sub(r' ', body)
|
||||
# Expand the tabs used for indentation.
|
||||
body = string.expandtabs(body, 2)
|
||||
# Strip trailing whitespace.
|
||||
body = common.SCRUB_TRAILING_WHITESPACE_RE.sub(r'', body)
|
||||
return 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):
|
||||
# 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()
|
||||
lines_with_def = []
|
||||
|
||||
for i, line in enumerate(lines):
|
||||
# An IR variable named '%.' matches the FileCheck regex string.
|
||||
line = line.replace('%.', '%dot')
|
||||
# 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
|
||||
|
||||
|
||||
def add_checks(output_lines, prefix_list, func_dict, func_name, opt_basename):
|
||||
# Label format is based on IR string.
|
||||
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.
|
||||
func_body = genericize_check_lines(func_body)
|
||||
|
||||
# This could be selectively enabled with an optional invocation argument.
|
||||
# Disabled for now: better to check everything. Be safe rather than sorry.
|
||||
|
||||
# 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).
|
||||
#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
|
||||
|
||||
is_blank_line = False
|
||||
|
||||
for func_line in func_body:
|
||||
if func_line.strip() == '':
|
||||
is_blank_line = True
|
||||
continue
|
||||
# Do not waste time checking IR comments.
|
||||
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 main():
|
||||
|
|
@ -247,8 +124,8 @@ def main():
|
|||
|
||||
raw_tool_output = common.invoke_tool(args.opt_binary, opt_args, test)
|
||||
common.build_function_body_dictionary(
|
||||
OPT_FUNCTION_RE, scrub_body, [opt_basename], raw_tool_output,
|
||||
prefixes, func_dict, args.verbose)
|
||||
common.OPT_FUNCTION_RE, common.scrub_body, [],
|
||||
raw_tool_output, prefixes, func_dict, args.verbose)
|
||||
|
||||
is_in_function = False
|
||||
is_in_function_start = False
|
||||
|
|
@ -269,7 +146,7 @@ def main():
|
|||
continue
|
||||
|
||||
# Print out the various check lines here.
|
||||
output_lines = add_checks(output_lines, prefix_list, func_dict, func_name, opt_basename)
|
||||
output_lines = common.add_ir_checks(output_lines, prefix_list, func_dict, func_name, opt_basename)
|
||||
is_in_function_start = False
|
||||
|
||||
if is_in_function:
|
||||
|
|
|
|||
Loading…
Reference in New Issue