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

1 files changed, 26 insertions, 23 deletions

diff --git a/llvm/utils/update_test_checks.py b/llvm/utils/update_test_checks.py
index a7529af0109..5b4449702cc 100755
--- a/llvm/utils/update_test_checks.py
+++ b/llvm/utils/update_test_checks.py
@@ -68,7 +68,9 @@ OPT_FUNCTION_RE = re.compile(
     flags=(re.M | re.S))
 CHECK_PREFIX_RE = re.compile('--check-prefix=(\S+)')
 CHECK_RE = re.compile(r'^\s*;\s*([^:]+?)(?:-NEXT|-NOT|-DAG|-LABEL)?:')
-IR_VALUE_DEF_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+)%(.+?)([,\s\(\)]|\Z)')
 
 
 # Invoke the tool that is being tested.
@@ -156,33 +158,34 @@ def get_value_definition(var):
 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 = []
-  vars_seen = []
-  for line in lines:
+
+  for i, line in enumerate(lines):
     # An IR variable named '%.' matches the FileCheck regex string.
     line = line.replace('%.', '%dot')
-    m = IR_VALUE_DEF_RE.match(line)
-    if m:
-      vars_seen.append(m.group(1))
-      line = line.replace('%' + m.group(1), get_value_definition(m.group(1)))
-
-    lines_with_def.append(line)
-
-  # A single def isn't worth replacing?
-  #if len(vars_seen) < 2:
-  #  return lines
-
-  output_lines = []
-  vars_seen.sort(key=len, reverse=True)
-  for line in lines_with_def:
-    for var in vars_seen:
-      line = line.replace('%' + var, get_value_use(var))
-    output_lines.append(line)
-
-  return output_lines
+    # 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, tool_basename):