[lit] Work around Windows MSys command line tokenization bug

[rnk]

Summary

This will allow us to revert LLD r284768, which added spaces to get MSys
echo to print what we want.

[ruiu]

Thank you for doing this. LGTM.

test/Other/lit-quoting.txt

2 ↗

(On Diff #75940)

{{^"$}}

llvm/trunk/test/Other/lit-quoting.txt

+RUN: echo "\"" | FileCheck %s
+CHECK: {{^"$}}

llvm/trunk/utils/lit/lit/TestRunner.py

def executeShCmd(cmd, shenv, results, timeout=0):
     finalExitCode = _executeShCmd(cmd, shenv, results, timeoutHelper)
     timeoutHelper.cancel()
     timeoutInfo = None
     if timeoutHelper.timeoutReached():
         timeoutInfo = 'Reached timeout of {} seconds'.format(timeout)
 
     return (finalExitCode, timeoutInfo)
 
+def quote_windows_command(seq):
+    """
+    Reimplement Python's private subprocess.list2cmdline for MSys compatibility
+
+    Based on CPython implementation here:
+      https://hg.python.org/cpython/file/849826a900d2/Lib/subprocess.py#l422
+
+    Some core util distributions (MSys) don't tokenize command line arguments
+    the same way that MSVC CRT does. Lit rolls its own quoting logic similar to
+    the stock CPython logic to paper over these quoting and tokenization rule
+    differences.
+
+    We use the same algorithm from MSDN as CPython
+    (http://msdn.microsoft.com/en-us/library/17w5ykft.aspx), but we treat more
+    characters as needing quoting, such as double quotes themselves.
+    """
+    result = []
+    needquote = False
+    for arg in seq:
+        bs_buf = []
+
+        # Add a space to separate this argument from the others
+        if result:
+            result.append(' ')
+
+        # This logic differs from upstream list2cmdline.
+        needquote = (" " in arg) or ("\t" in arg) or ("\"" in arg) or not arg
+        if needquote:
+            result.append('"')
+
+        for c in arg:
+            if c == '\\':
+                # Don't know if we need to double yet.
+                bs_buf.append(c)
+            elif c == '"':
+                # Double backslashes.
+                result.append('\\' * len(bs_buf)*2)
+                bs_buf = []
+                result.append('\\"')
+            else:
+                # Normal char
+                if bs_buf:
+                    result.extend(bs_buf)
+                    bs_buf = []
+                result.append(c)
+
+        # Add remaining backslashes, if any.
+        if bs_buf:
+            result.extend(bs_buf)
+
+        if needquote:
+            result.extend(bs_buf)
+            result.append('"')
+
+    return ''.join(result)
+
 def _executeShCmd(cmd, shenv, results, timeoutHelper):
     if timeoutHelper.timeoutReached():
         # Prevent further recursion if the timeout has been hit
         # as we should try avoid launching more processes.
         return None
 
     if isinstance(cmd, ShUtil.Seq):
         if cmd.op == ';':
for i,j in enumerate(cmd.commands):
         if kAvoidDevNull:
             for i,arg in enumerate(args):
                 if arg == "/dev/null":
                     f = tempfile.NamedTemporaryFile(delete=False)
                     f.close()
                     named_temp_files.append(f.name)
                     args[i] = f.name
 
+        # On Windows, do our own command line quoting for better compatibility
+        # with some core utility distributions.
+        if kIsWindows:
+            args = quote_windows_command(args)
+
         try:
             procs.append(subprocess.Popen(args, cwd=cmd_shenv.cwd,
                                           executable = executable,
                                           stdin = stdin,
                                           stdout = stdout,
                                           stderr = stderr,
                                           env = cmd_shenv.env,
                                           close_fds = kUseCloseFDs))