[LIT] Decode string result in lit.util.capture

[EricWF]

Summary

I think this is probably a bug, but I'm putting this up for review just to be sure. I think that lit.util.capture should decode the resulting string in the same way lit.util.executeCommand does.

[• ddunbar]

LGTM

[EricWF]

Accepting.

llvm/trunk/utils/lit/lit/util.py

def to_bytes(str):
     # Encode to UTF-8 to get binary data.
     return str.encode('utf-8')
 
 def to_string(bytes):
     if isinstance(bytes, str):
         return bytes
     return to_bytes(bytes)
 
+def convert_string(bytes):
+    try:
+        return to_string(bytes.decode('utf-8'))
+    except UnicodeError:
+        return str(bytes)
+
 def detectCPUs():
     """
     Detects the number of CPUs on a system. Cribbed from pp.
     """
     # Linux, Unix and MacOS:
     if hasattr(os, "sysconf"):
         if "SC_NPROCESSORS_ONLN" in os.sysconf_names:
             # Linux & Unix:
except OSError:
             raise
 
 def capture(args, env=None):
     """capture(command) - Run the given command (or argv list) in a shell and
     return the standard output."""
     p = subprocess.Popen(args, stdout=subprocess.PIPE, stderr=subprocess.PIPE,
                          env=env)
     out,_ = p.communicate()
-    return out
+    return convert_string(out)
 
 def which(command, paths = None):
     """which(command, [paths]) - Look up the given command in the paths string
     (or the PATH environment variable, if unspecified)."""
 
     if paths is None:
         paths = os.environ.get('PATH','')
 
def executeCommand(command, cwd=None, env=None):
     out,err = p.communicate()
     exitCode = p.wait()
 
     # Detect Ctrl-C in subprocess.
     if exitCode == -signal.SIGINT:
         raise KeyboardInterrupt
 
     # Ensure the resulting output is always of string type.
-    try:
-        out = to_string(out.decode('utf-8'))
-    except:
-        out = str(out)
-    try:
-        err = to_string(err.decode('utf-8'))
-    except:
-        err = str(err)
+    out = convert_string(out)
+    err = convert_string(err)
 
     return out, err, exitCode
 
 def usePlatformSdkOnDarwin(config, lit_config):
     # On Darwin, support relocatable SDKs by providing Clang with a
     # default system root path.
     if 'darwin' in config.target_triple:
         try: