[UpdateTestChecks] Share the code to parse RUN: lines between all scripts

Summary:
This commit also introduces a common.debug() function to avoid many
`if args.verbose:` statements. Depends on D70428.

Reviewers: xbolva00, MaskRay, jdoerfert

Reviewed By: MaskRay

Subscribers: llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D70432

Author: arichardson

llvm/utils/UpdateTestChecks/common.py

@@ -14,12 +14,17 @@ class string:
 ##### Common utilities for update_*test_checks.py
 
 
+_verbose = False
+
 def parse_commandline_args(parser):
   parser.add_argument('-v', '--verbose', action='store_true',
                       help='Show verbose output')
   parser.add_argument('-u', '--update-only', action='store_true',
                       help='Only update test if it was already autogened')
-  return parser.parse_args()
+  args = parser.parse_args()
+  global _verbose
+  _verbose = args.verbose
+  return args
 
 def should_add_line_to_output(input_line, prefix_set):
   # Skip any blank comment lines in the IR.
@@ -53,7 +58,7 @@ def invoke_tool(exe, cmd_args, ir):
 
 ##### LLVM IR parser
 
-RUN_LINE_RE = re.compile(r'^\s*[;#]\s*RUN:\s*(.*)$')
+RUN_LINE_RE = re.compile(r'^\s*(?://|[;#])\s*RUN:\s*(.*)$')
 CHECK_PREFIX_RE = re.compile(r'--?check-prefix(?:es)?[= ](\S+)')
 PREFIX_RE = re.compile('^[a-zA-Z0-9_-]+$')
 CHECK_RE = re.compile(r'^\s*[;#]\s*([^:]+?)(?:-NEXT|-NOT|-DAG|-LABEL|-SAME)?:')
@@ -91,6 +96,28 @@ def warn(msg, test_file=None):
     msg = '{}: {}'.format(msg, test_file)
   print('WARNING: {}'.format(msg), file=sys.stderr)
 
+def debug(*args, **kwargs):
+  # Python2 does not allow def debug(*args, file=sys.stderr, **kwargs):
+  if 'file' not in kwargs:
+    kwargs['file'] = sys.stderr
+  if _verbose:
+    print(*args, **kwargs)
+
+def find_run_lines(test, lines):
+  debug('Scanning for RUN lines in test file:', test)
+  raw_lines = [m.group(1)
+               for m in [RUN_LINE_RE.match(l) for l in 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)
+  debug('Found {} RUN lines in {}:'.format(len(run_lines), test))
+  for l in run_lines:
+    debug('  RUN: {}'.format(l))
+  return run_lines
+
 def scrub_body(body):
   # Scrub runs of whitespace out of the assembly, but leave the leading
   # whitespace in place.

llvm/utils/update_analyze_test_checks.py

@@ -69,8 +69,6 @@ def main():
 
   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]
 
@@ -84,20 +82,7 @@ def main():
         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)
-
+    run_lines = common.find_run_lines(test, input_lines)
     prefix_list = []
     for l in run_lines:
       if '|' not in l:
@@ -132,9 +117,8 @@ def main():
       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)
+      common.debug('Extracted opt cmd:', opt_basename, opt_args, file=sys.stderr)
+      common.debug('Extracted FileCheck prefixes:', str(prefixes), file=sys.stderr)
 
       raw_tool_outputs = common.invoke_tool(args.opt_binary, opt_args, test)
 
@@ -147,8 +131,7 @@ def main():
     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)
+    common.debug('Rewriting FileCheck prefixes:', str(prefix_set), file=sys.stderr)
     output_lines = []
     output_lines.append(autogenerated_note)
 
@@ -194,8 +177,7 @@ def main():
         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)
+    common.debug('Writing %d lines to %s...' % (len(output_lines), test))
 
     with open(test, 'wb') as f:
       f.writelines(['{}\n'.format(l).encode('utf-8') for l in output_lines])

llvm/utils/update_cc_test_checks.py

@@ -29,7 +29,6 @@
 ADVERT = '// NOTE: Assertions have been autogenerated by '
 
 CHECK_RE = re.compile(r'^\s*//\s*([^:]+?)(?:-NEXT|-NOT|-DAG|-LABEL)?:')
-RUN_LINE_RE = re.compile(r'^//\s*RUN:\s*(.*)$')
 
 SUBST = {
     '%clang': [],
@@ -38,9 +37,6 @@
 }
 
 def get_line2spell_and_mangled(args, clang_args):
-  def debug_mangled(*print_args, **kwargs):
-    if args.verbose:
-      print(*print_args, file=sys.stderr, **kwargs)
   ret = {}
   # Use clang's JSON AST dump to get the mangled name
   json_dump_args = [args.clang, *clang_args, '-fsyntax-only', '-o', '-']
@@ -49,7 +45,7 @@ def debug_mangled(*print_args, **kwargs):
     # -Xclang -ast-dump=json instead:
     json_dump_args.append('-Xclang')
   json_dump_args.append('-ast-dump=json')
-  debug_mangled('Running', ' '.join(json_dump_args))
+  common.debug('Running', ' '.join(json_dump_args))
   status = subprocess.run(json_dump_args, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
   if status.returncode != 0:
     sys.stderr.write('Failed to run ' + ' '.join(json_dump_args) + '\n')
@@ -67,20 +63,19 @@ def debug_mangled(*print_args, **kwargs):
     if node['kind'] != 'FunctionDecl':
       continue
     if node.get('isImplicit') is True and node.get('storageClass') == 'extern':
-      debug_mangled('Skipping builtin function:', node['name'], '@', node['loc'])
+      common.debug('Skipping builtin function:', node['name'], '@', node['loc'])
       continue
-    debug_mangled('Found function:', node['kind'], node['name'], '@', node['loc'])
+    common.debug('Found function:', node['kind'], node['name'], '@', node['loc'])
     line = node['loc'].get('line')
     # If there is no line it is probably a builtin function -> skip
     if line is None:
-      debug_mangled('Skipping function without line number:', node['name'], '@', node['loc'])
+      common.debug('Skipping function without line number:', node['name'], '@', node['loc'])
       continue
     spell = node['name']
     mangled = node.get('mangledName', spell)
     ret[int(line)-1] = (spell, mangled)
-  if args.verbose:
-    for line, func_name in sorted(ret.items()):
-      print('line {}: found function {}'.format(line+1, func_name), file=sys.stderr)
+  for line, func_name in sorted(ret.items()):
+    common.debug('line {}: found function {}'.format(line+1, func_name), file=sys.stderr)
   if not ret:
     common.warn('Did not find any functions using', ' '.join(json_dump_args))
   return ret
@@ -191,19 +186,7 @@ def main():
         continue
 
     # Extract RUN lines.
-    raw_lines = [m.group(1)
-                 for m in [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 {} RUN lines:'.format(len(run_lines)), file=sys.stderr)
-      for l in run_lines:
-        print('  RUN: ' + l, file=sys.stderr)
+    run_lines = common.find_run_lines(filename, input_lines)
 
     # Build a list of clang command lines and check prefixes from RUN lines.
     run_list = []
@@ -260,9 +243,8 @@ def main():
       for prefix in prefixes:
         func_dict.update({prefix: dict()})
     for prefixes, clang_args, extra_commands, triple_in_cmd in run_list:
-      if args.verbose:
-        print('Extracted clang cmd: clang {}'.format(clang_args), file=sys.stderr)
-        print('Extracted FileCheck prefixes: {}'.format(prefixes), file=sys.stderr)
+      common.debug('Extracted clang cmd: clang {}'.format(clang_args))
+      common.debug('Extracted FileCheck prefixes: {}'.format(prefixes))
 
       get_function_body(args, filename, clang_args, extra_commands, prefixes, triple_in_cmd, func_dict)
 

llvm/utils/update_llc_test_checks.py

@@ -43,8 +43,6 @@ def main():
 
   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]
 
@@ -65,20 +63,7 @@ def main():
         triple_in_ir = m.groups()[0]
         break
 
-    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)
-
+    run_lines = common.find_run_lines(test, input_lines)
     run_list = []
     for l in run_lines:
       if '|' not in l:
@@ -115,12 +100,6 @@ def main():
       llc_cmd_args = llc_cmd_args.replace('< %s', '').replace('%s', '').strip()
       if test.endswith('.mir'):
         llc_cmd_args += ' -x mir'
-        comment_sym = '#'
-        check_indent = '  '
-      else:
-        comment_sym = ';'
-        check_indent = ''
-
       check_prefixes = [item for m in common.CHECK_PREFIX_RE.finditer(filecheck_cmd)
                                for item in m.group(1).split(',')]
       if not check_prefixes:
@@ -130,6 +109,12 @@ def main():
       # now, we just ignore all but the last.
       run_list.append((check_prefixes, llc_cmd_args, triple_in_cmd, march_in_cmd))
 
+    if test.endswith('.mir'):
+      comment_sym = '#'
+      check_indent = '  '
+    else:
+      comment_sym = ';'
+      check_indent = ''
     autogenerated_note = (comment_sym + ADVERT + 'utils/' + script_name)
 
     func_dict = {}
@@ -138,9 +123,8 @@ def main():
       for prefix in prefixes:
         func_dict.update({prefix: dict()})
     for prefixes, llc_args, triple_in_cmd, march_in_cmd in run_list:
-      if args.verbose:
-        print('Extracted LLC cmd: ' + llc_tool + ' ' + llc_args, file=sys.stderr)
-        print('Extracted FileCheck prefixes: ' + str(prefixes), file=sys.stderr)
+      common.debug('Extracted LLC cmd:', llc_tool, llc_args)
+      common.debug('Extracted FileCheck prefixes:', str(prefixes))
 
       raw_tool_output = common.invoke_tool(args.llc_binary, llc_args, test)
       triple = triple_in_cmd or triple_in_ir
@@ -154,8 +138,7 @@ def main():
     is_in_function_start = False
     func_name = None
     prefix_set = set([prefix for p in run_list for prefix in p[0]])
-    if args.verbose:
-      print('Rewriting FileCheck prefixes: %s' % (prefix_set,), file=sys.stderr)
+    common.debug('Rewriting FileCheck prefixes:', str(prefix_set))
     output_lines = []
     output_lines.append(autogenerated_note)
 
@@ -199,8 +182,7 @@ def main():
         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)
+    common.debug('Writing %d lines to %s...' % (len(output_lines), test))
 
     with open(test, 'wb') as f:
       f.writelines(['{}\n'.format(l).encode('utf-8') for l in output_lines])

llvm/utils/update_mca_test_checks.py

@@ -83,26 +83,6 @@ def _parse_args():
   return args
 
 
-def _find_run_lines(input_lines, args):
-  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(r'\\'):
-      run_lines[-1] = run_lines[-1].rstrip('\\') + ' ' + l
-    else:
-      run_lines.append(l)
-
-  if args.verbose:
-    sys.stderr.write('Found {} RUN line{}:\n'.format(
-        len(run_lines), '' if len(run_lines) == 1 else 's'))
-    for line in run_lines:
-      sys.stderr.write('  RUN: {}\n'.format(line))
-
-  return run_lines
-
-
 def _get_run_infos(run_lines, args):
   run_infos = []
   for run_line in run_lines:
@@ -544,9 +524,7 @@ def _write_output(test_path, input_lines, prefix_list, block_infos,  # noqa
     return
   sys.stderr.write('      [{} lines total]\n'.format(len(output_lines)))
 
-  if args.verbose:
-    sys.stderr.write(
-        'Writing {} lines to {}...\n\n'.format(len(output_lines), test_path))
+  common.debug('Writing', len(output_lines), 'lines to', test_path, '..\n\n')
 
   with open(test_path, 'wb') as f:
     f.writelines(['{}\n'.format(l).encode('utf-8') for l in output_lines])
@@ -562,17 +540,13 @@ def main():
     # will be written once per source location per test.
     _configure_warnings(args)
 
-    if args.verbose:
-      sys.stderr.write(
-          'Scanning for RUN lines in test file: {}\n'.format(test_path))
-
     if not os.path.isfile(test_path):
       raise Error('could not find test file: {}'.format(test_path))
 
     with open(test_path) as f:
       input_lines = [l.rstrip() for l in f]
 
-    run_lines = _find_run_lines(input_lines, args)
+    run_lines = common.find_run_lines(test_path, input_lines)
     run_infos = _get_run_infos(run_lines, args)
     common_prefix, prefix_pad = _get_useful_prefix_info(run_infos)
     block_infos = _get_block_infos(run_infos, test_path, args, common_prefix)

llvm/utils/update_mir_test_checks.py

@@ -96,22 +96,6 @@ def find_triple_in_ir(lines, verbose=False):
     return None
 
 
-def find_run_lines(test, lines, verbose=False):
-    raw_lines = [m.group(1)
-                 for m in [common.RUN_LINE_RE.match(l) for l in 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 verbose:
-        log('Found {} RUN lines:'.format(len(run_lines)))
-        for l in run_lines:
-            log('  RUN: {}'.format(l))
-    return run_lines
-
-
 def build_run_list(test, run_lines, verbose=False):
     run_list = []
     all_prefixes = []
@@ -296,7 +280,6 @@ def should_add_line_to_output(input_line, prefix_set):
 
 
 def update_test_file(args, test):
-    log('Scanning for RUN lines in test file: {}'.format(test), args.verbose)
     with open(test) as fd:
         input_lines = [l.rstrip() for l in fd]
 
@@ -313,7 +296,7 @@ def update_test_file(args, test):
         return
 
     triple_in_ir = find_triple_in_ir(input_lines, args.verbose)
-    run_lines = find_run_lines(test, input_lines, args.verbose)
+    run_lines = common.find_run_lines(test, input_lines)
     run_list, common_prefixes = build_run_list(test, run_lines, args.verbose)
 
     simple_functions = find_functions_with_one_bb(input_lines, args.verbose)