Revert "[lit] Fix some convoluted logic around Unicode encoding, and de-duplicate across modules that used it."

This reverts r306625.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@306629 91177308-0d34-0410-b5e6-96231b3b80d8

2 files changed, 51 insertions, 62 deletions

diff --git a/utils/lit/lit/formats/googletest.py b/utils/lit/lit/formats/googletest.py
index 342c8153a3fc..29a92c4e960b 100644
--- a/utils/lit/lit/formats/googletest.py
+++ b/utils/lit/lit/formats/googletest.py
@@ -30,22 +30,19 @@ class GoogleTest(TestFormat):
           localConfig: TestingConfig instance"""
 
         try:
-            output = subprocess.check_output([path, '--gtest_list_tests'],
-                                             env=localConfig.environment)
-        except subprocess.CalledProcessError as exc:
-            litConfig.warning(
-                "unable to discover google-tests in %r: %s. Process output: %s"
-                % (path, sys.exc_info()[1], exc.output))
+            lines = lit.util.capture([path, '--gtest_list_tests'],
+                                     env=localConfig.environment)
+            if kIsWindows:
+              lines = lines.replace('\r', '')
+            lines = lines.split('\n')
+        except Exception as exc:
+            out = exc.output if isinstance(exc, subprocess.CalledProcessError) else ''
+            litConfig.warning("unable to discover google-tests in %r: %s. Process output: %s"
+                              % (path, sys.exc_info()[1], out))
             raise StopIteration
 
         nested_tests = []
-        for ln in output.splitlines(False):  # Don't keep newlines.
-            if 'Running main() from gtest_main.cc' in ln:
-                # Upstream googletest prints this to stdout prior to running
-                # tests. LLVM removed that print statement in r61540, but we
-                # handle it here in case upstream googletest is being used.
-                continue
-
+        for ln in lines:
             # The test name list includes trailing comments beginning with
             # a '#' on some lines, so skip those. We don't support test names
             # that use escaping to embed '#' into their name as the names come
@@ -55,6 +52,12 @@ class GoogleTest(TestFormat):
             if not ln.lstrip():
                 continue
 
+            if 'Running main() from gtest_main.cc' in ln:
+                # Upstream googletest prints this to stdout prior to running
+                # tests. LLVM removed that print statement in r61540, but we
+                # handle it here in case upstream googletest is being used.
+                continue
+
             index = 0
             while ln[index*2:index*2+2] == '  ':
                 index += 1
diff --git a/utils/lit/lit/util.py b/utils/lit/lit/util.py
index 917dca868a65..8991588a868d 100644
--- a/utils/lit/lit/util.py
+++ b/utils/lit/lit/util.py
@@ -8,52 +8,24 @@ import subprocess
 import sys
 import threading
 
-def to_bytes(s):
-    """Return the parameter as type 'bytes', possibly encoding it.
-
-    In Python2, the 'bytes' type is the same as 'str'. In Python3, they are
-    distinct.
-    """
-    if isinstance(s, bytes):
-        # In Python2, this branch is taken for both 'str' and 'bytes'.
-        # In Python3, this branch is taken only for 'bytes'.
-        return s
-    # In Python2, 's' is a 'unicode' object.
-    # In Python3, 's' is a 'str' object.
-    # Encode to UTF-8 to get 'bytes' data.
-    return s.encode('utf-8')
-
-def to_string(b):
-    """Return the parameter as type 'str', possibly encoding it.
-
-    In Python2, the 'str' type is the same as 'bytes'. In Python3, the
-    'str' type is (essentially) Python2's 'unicode' type, and 'bytes' is
-    distinct.
-    """
-    if isinstance(b, str):
-        # In Python2, this branch is taken for types 'str' and 'bytes'.
-        # In Python3, this branch is taken only for 'str'.
-        return b
-    if isinstance(b, bytes):
-        # In Python2, this branch is never taken ('bytes' is handled as 'str').
-        # In Python3, this is true only for 'bytes'.
-        return b.decode('utf-8')
-
-    # By this point, here's what we *don't* have:
-    #
-    #  - In Python2:
-    #    - 'str' or 'bytes' (1st branch above)
-    #  - In Python3:
-    #    - 'str' (1st branch above)
-    #    - 'bytes' (2nd branch above)
-    #
-    # The last type we might expect is the Python2 'unicode' type. There is no
-    # 'unicode' type in Python3 (all the Python3 cases were already handled). In
-    # order to get a 'str' object, we need to encode the 'unicode' object.
+def to_bytes(str):
+    # Encode to UTF-8 to get binary data.
+    if isinstance(str, bytes):
+        return str
+    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 b.encode('utf-8')
-    except AttributeError:
-        raise TypeError('not sure how to convert %s to %s' % (type(b), str))
+        return to_string(bytes.decode('utf-8'))
+    except AttributeError: # 'str' object has no attribute 'decode'.
+        return str(bytes)
+    except UnicodeError:
+        return str(bytes)
 
 def detectCPUs():
     """
@@ -67,8 +39,7 @@ def detectCPUs():
             if isinstance(ncpus, int) and ncpus > 0:
                 return ncpus
         else: # OSX:
-            return int(subprocess.check_output(['sysctl', '-n', 'hw.ncpu'],
-                                               stderr=subprocess.STDOUT))
+            return int(capture(['sysctl', '-n', 'hw.ncpu']))
     # Windows:
     if "NUMBER_OF_PROCESSORS" in os.environ:
         ncpus = int(os.environ["NUMBER_OF_PROCESSORS"])
@@ -96,6 +67,21 @@ def mkdir_p(path):
         if e.errno != errno.EEXIST:
             raise
 
+def capture(args, env=None):
+    """capture(command) - Run the given command (or argv list) in a shell and
+    return the standard output. Raises a CalledProcessError if the command
+    exits with a non-zero status."""
+    p = subprocess.Popen(args, stdout=subprocess.PIPE, stderr=subprocess.PIPE,
+                         env=env)
+    out, err = p.communicate()
+    out = convert_string(out)
+    err = convert_string(err)
+    if p.returncode != 0:
+        raise subprocess.CalledProcessError(cmd=args,
+                                            returncode=p.returncode,
+                                            output="{}\n{}".format(out, err))
+    return 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)."""
@@ -247,8 +233,8 @@ def executeCommand(command, cwd=None, env=None, input=None, timeout=0):
             timerObject.cancel()
 
     # Ensure the resulting output is always of string type.
-    out = to_string(out)
-    err = to_string(err)
+    out = convert_string(out)
+    err = convert_string(err)
 
     if hitTimeOut[0]:
         raise ExecuteCommandTimeoutException(