[llvm] 2d068e5 - Fix Windows command line bug when last token in response file is ""

[Adrian McCarthy via llvm-commits]

Author: Adrian McCarthy
Date: 2020-05-27T14:49:30-07:00
New Revision: 2d068e534f1671459e1b135852c1b3c10502e929

URL: https://github.com/llvm/llvm-project/commit/2d068e534f1671459e1b135852c1b3c10502e929
DIFF: https://github.com/llvm/llvm-project/commit/2d068e534f1671459e1b135852c1b3c10502e929.diff

LOG: Fix Windows command line bug when last token in response file is ""

Patch by Neil Dhar <dhar at alumni.duke.edu>

Current state machine for parsing tokens from response files in Windows
does not correctly handle the case where the last token is "". The current
implementation handles the last token by only adding it if it is not empty,
however this does not cover the case where the last token is meant to be
the empty string. We can cover this case by checking whether the state
machine was last in the UNQUOTED state, which indicates that the last
character of the input was a non-whitespace character.

Differential Revision: https://reviews.llvm.org/D78346

Added: 
    

Modified: 
    llvm/lib/Support/CommandLine.cpp
    llvm/unittests/Support/CommandLineTest.cpp

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Support/CommandLine.cpp b/llvm/lib/Support/CommandLine.cpp
index aa7e79652af9..25612b7e8f23 100644
--- a/llvm/lib/Support/CommandLine.cpp
+++ b/llvm/lib/Support/CommandLine.cpp
@@ -1009,7 +1009,7 @@ tokenizeWindowsCommandLineImpl(StringRef Src, StringSaver &Saver,
     }
   }
 
-  if (!Token.empty())
+  if (State == UNQUOTED)
     AddToken(Saver.save(Token.str()));
 }
 

diff  --git a/llvm/unittests/Support/CommandLineTest.cpp b/llvm/unittests/Support/CommandLineTest.cpp
index a6b26b310b97..3e7ec8d5baf1 100644
--- a/llvm/unittests/Support/CommandLineTest.cpp
+++ b/llvm/unittests/Support/CommandLineTest.cpp
@@ -253,8 +253,8 @@ TEST(CommandLineTest, TokenizeGNUCommandLine) {
 }
 
 TEST(CommandLineTest, TokenizeWindowsCommandLine1) {
-  const char Input[] = "a\\b c\\\\d e\\\\\"f g\" h\\\"i j\\\\\\\"k \"lmn\" o pqr "
-                      "\"st \\\"u\" \\v";
+  const char Input[] =
+      R"(a\b c\\d e\\"f g" h\"i j\\\"k "lmn" o pqr "st \"u" \v)";
   const char *const Output[] = { "a\\b", "c\\\\d", "e\\f g", "h\"i", "j\\\"k",
                                  "lmn", "o", "pqr", "st \"u", "\\v" };
   testCommandLineTokenizer(cl::TokenizeWindowsCommandLine, Input, Output,
@@ -268,6 +268,17 @@ TEST(CommandLineTest, TokenizeWindowsCommandLine2) {
                            array_lengthof(Output));
 }
 
+TEST(CommandLineTest, TokenizeWindowsCommandLineQuotedLastArgument) {
+  const char Input1[] = R"(a b c d "")";
+  const char *const Output1[] = {"a", "b", "c", "d", ""};
+  testCommandLineTokenizer(cl::TokenizeWindowsCommandLine, Input1, Output1,
+                           array_lengthof(Output1));
+  const char Input2[] = R"(a b c d ")";
+  const char *const Output2[] = {"a", "b", "c", "d"};
+  testCommandLineTokenizer(cl::TokenizeWindowsCommandLine, Input2, Output2,
+                           array_lengthof(Output2));
+}
+
 TEST(CommandLineTest, TokenizeConfigFile1) {
   const char *Input = "\\";
   const char *const Output[] = { "\\" };