Reapply 122341 to fix PR8199 now that clang changes are in.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@122754 91177308-0d34-0410-b5e6-96231b3b80d8

docs/TestingGuide.html

@@ -376,6 +376,11 @@ clang/test directory. </p>
   shell. Consequently the syntax differs from normal shell script syntax in a 
   few ways.  You can specify as many RUN lines as needed.</p>
 
+  <p>lit performs substitution on each RUN line to replace LLVM tool
+  names with the full paths to the executable built for each tool (in
+  $(LLVM_OBJ_ROOT)/$(BuildMode)/bin).  This ensures that lit does not
+  invoke any stray LLVM tools in the user's path during testing.</p>
+
   <p>Each RUN line is executed on its own, distinct from other lines unless
   its last character is <tt>\</tt>. This continuation character causes the RUN
   line to be concatenated with the next one. In this way you can build up long

test/lit.cfg

@@ -4,6 +4,7 @@
 
 import os
 import sys
+import re
 
 # name: The name of this test suite.
 config.name = 'LLVM'
@@ -148,6 +149,44 @@ for sub in ['llvmgcc', 'llvmgxx', 'emitir', 'compile_cxx', 'compile_c',
     else:
         config.substitutions.append(('%' + sub, site_exp[sub]))
 
+# For each occurrence of an llvm tool name as its own word, replace it
+# with the full path to the build directory holding that tool.  This
+# ensures that we are testing the tools just built and not some random
+# tools that might happen to be in the user's PATH.  Thus this list
+# includes every tool placed in $(LLVM_OBJ_ROOT)/$(BuildMode)/bin
+# (llvm_tools_dir in lit parlance).
+                # Don't match 'bugpoint-'.
+for pattern in [r"\bbugpoint\b(?!-)",   r"\bclang\b",
+                r"\bedis\b",            r"\bgold\b",
+                r"\bllc\b",             r"\blli\b",
+                r"\bllvm-ar\b",         r"\bllvm-as\b",
+                r"\bllvm-bcanalyzer\b", r"\bllvm-config\b",
+                r"\bllvm-diff\b",       r"\bllvm-dis\b",
+                r"\bllvm-extract\b",    r"\bllvm-ld\b",
+                r"\bllvm-link\b",       r"\bllvm-mc\b",
+                r"\bllvm-nm\b",         r"\bllvm-prof\b",
+                r"\bllvm-ranlib\b",     r"\bllvm-shlib\b",
+                r"\bllvm-stub\b",       r"\bllvm2cpp\b",
+                # Don't match '-llvmc'.
+                r"(?<!-)\bllvmc\b",     r"\blto\b",
+                                        # Don't match '.opt', '-opt'
+                                        # or '^opt'.
+                r"\bmacho-dump\b",      r"(?<!\.|-|\^)\bopt\b",
+                r"\btblgen\b",          r"\bFileCheck\b",
+                r"\bFileUpdate\b",      r"\bc-index-test\b",
+                r"\bfpcmp\b",           r"\bllvm-PerfectShuffle\b",
+                # Handle these specially as they are strings searched
+                # for during testing.
+                r"\| \bcount\b",         r"\| \bnot\b"]:
+    # Extract the tool name from the pattern.  This relies on the tool
+    # name being surrounded by \b word match operators.  If the
+    # pattern starts with "| ", include it in the string to be
+    # substituted.
+    substitution = re.sub(r"^(\\)?((\| )?)\W+b([0-9A-Za-z-_]+)\\b\W*$",
+                          r"\2" + llvm_tools_dir + "/" + r"\4",
+                          pattern)
+    config.substitutions.append((pattern, substitution))
+
 excludes = []
 
 # Provide target_triple for use in XFAIL and XTARGET.

utils/lit/lit/TestRunner.py

@@ -8,6 +8,8 @@ import Util
 import platform
 import tempfile
 
+import re
+
 class InternalShellError(Exception):
     def __init__(self, command, message):
         self.command = command
@@ -444,11 +446,13 @@ def parseIntegratedTestScript(test, normalize_slashes=False):
             if ln[ln.index('END.'):].strip() == 'END.':
                 break
 
-    # Apply substitutions to the script.
+    # Apply substitutions to the script.  Allow full regular
+    # expression syntax.  Replace each matching occurrence of regular
+    # expression pattern a with substitution b in line ln.
     def processLine(ln):
         # Apply substitutions
         for a,b in substitutions:
-            ln = ln.replace(a,b)
+            ln = re.sub(a, b, ln)
 
         # Strip the trailing newline and any extra whitespace.
         return ln.strip()