Option parsing: support case-insensitive option matching.

Link.exe's command line options are case-insensitive. This patch
adds a new attribute to OptTable to let the option parser to compare
options, ignoring case.

Command lines are generally case-insensitive on Windows. CL.exe is an
exception. So this new attribute should be useful for other commands
running on Windows.

Differential Revision: http://llvm-reviews.chandlerc.com/D1485

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@189416 91177308-0d34-0410-b5e6-96231b3b80d8

include/llvm/Option/OptTable.h

@@ -51,6 +51,7 @@ private:
   /// \brief The static option information table.
   const Info *OptionInfos;
   unsigned NumOptionInfos;
+  bool IgnoreCase;
 
   unsigned TheInputOptionID;
   unsigned TheUnknownOptionID;
@@ -72,7 +73,8 @@ private:
   }
 
 protected:
-  OptTable(const Info *_OptionInfos, unsigned _NumOptionInfos);
+  OptTable(const Info *_OptionInfos, unsigned _NumOptionInfos,
+           bool _IgnoreCase = false);
 public:
   ~OptTable();
 

lib/Option/OptTable.cpp

@@ -19,47 +19,45 @@
 using namespace llvm;
 using namespace llvm::opt;
 
-// Ordering on Info. The ordering is *almost* lexicographic, with two
-// exceptions. First, '\0' comes at the end of the alphabet instead of
-// the beginning (thus options precede any other options which prefix
-// them). Second, for options with the same name, the less permissive
-// version should come first; a Flag option should precede a Joined
-// option, for example.
-
-static int StrCmpOptionName(const char *A, const char *B) {
-  char a = *A, b = *B;
-  while (a == b) {
-    if (a == '\0')
-      return 0;
-
-    a = *++A;
-    b = *++B;
-  }
-
-  if (a == '\0') // A is a prefix of B.
-    return 1;
-  if (b == '\0') // B is a prefix of A.
-    return -1;
-
-  // Otherwise lexicographic.
-  return (a < b) ? -1 : 1;
-}
-
 namespace llvm {
 namespace opt {
 
+// Ordering on Info. The ordering is *almost* case-insensitive lexicographic,
+// with an exceptions. '\0' comes at the end of the alphabet instead of the
+// beginning (thus options precede any other options which prefix them).
+static int StrCmpOptionNameIgnoreCase(const char *A, const char *B) {
+  size_t I = strlen(A);
+  size_t J = strlen(B);
+  // If A and B are the same length, compare them ignoring case.
+  if (I == J)
+    return strcasecmp(A, B);
+  // A is shorter than B. In this case A is less than B only when it's
+  // lexicographically less than B. strncasecmp() == 0 means A is a prefix of B,
+  // which in turn means A should appear *after* B.
+  if (I < J)
+    return strncasecmp(A, B, I) < 0 ? -1 : 1;
+  // Otherwise, vice versa.
+  return strncasecmp(A, B, J) <= 0 ? -1 : 1;
+}
+
+static int StrCmpOptionName(const char *A, const char *B) {
+  if (int N = StrCmpOptionNameIgnoreCase(A, B))
+    return N;
+  return strcmp(A, B);
+}
+
 static inline bool operator<(const OptTable::Info &A, const OptTable::Info &B) {
   if (&A == &B)
     return false;
 
   if (int N = StrCmpOptionName(A.Name, B.Name))
-    return N == -1;
+    return N < 0;
 
   for (const char * const *APre = A.Prefixes,
                   * const *BPre = B.Prefixes;
                           *APre != 0 && *BPre != 0; ++APre, ++BPre) {
     if (int N = StrCmpOptionName(*APre, *BPre))
-      return N == -1;
+      return N < 0;
   }
 
   // Names are the same, check that classes are in order; exactly one
@@ -71,19 +69,21 @@ static inline bool operator<(const OptTable::Info &A, const OptTable::Info &B) {
 
 // Support lower_bound between info and an option name.
 static inline bool operator<(const OptTable::Info &I, const char *Name) {
-  return StrCmpOptionName(I.Name, Name) == -1;
+  return StrCmpOptionNameIgnoreCase(I.Name, Name) < 0;
 }
 static inline bool operator<(const char *Name, const OptTable::Info &I) {
-  return StrCmpOptionName(Name, I.Name) == -1;
+  return StrCmpOptionNameIgnoreCase(Name, I.Name) < 0;
 }
 }
 }
 
 OptSpecifier::OptSpecifier(const Option *Opt) : ID(Opt->getID()) {}
 
-OptTable::OptTable(const Info *_OptionInfos, unsigned _NumOptionInfos)
+OptTable::OptTable(const Info *_OptionInfos, unsigned _NumOptionInfos,
+                   bool _IgnoreCase)
   : OptionInfos(_OptionInfos),
     NumOptionInfos(_NumOptionInfos),
+    IgnoreCase(_IgnoreCase),
     TheInputOptionID(0),
     TheUnknownOptionID(0),
     FirstSearchableIndex(0)
@@ -170,12 +170,26 @@ static bool isInput(const llvm::StringSet<> &Prefixes, StringRef Arg) {
   return true;
 }
 
+// Returns true if X starts with Y, ignoring case.
+static bool startsWithIgnoreCase(StringRef X, StringRef Y) {
+  if (X.size() < Y.size())
+    return false;
+  return X.substr(0, Y.size()).equals_lower(Y);
+}
+
 /// \returns Matched size. 0 means no match.
-static unsigned matchOption(const OptTable::Info *I, StringRef Str) {
+static unsigned matchOption(const OptTable::Info *I, StringRef Str,
+                            bool IgnoreCase) {
   for (const char * const *Pre = I->Prefixes; *Pre != 0; ++Pre) {
     StringRef Prefix(*Pre);
-    if (Str.startswith(Prefix) && Str.substr(Prefix.size()).startswith(I->Name))
-      return Prefix.size() + StringRef(I->Name).size();
+    if (Str.startswith(Prefix)) {
+      StringRef Rest = Str.substr(Prefix.size());
+      bool Matched = IgnoreCase
+          ? startsWithIgnoreCase(Rest, I->Name)
+          : Rest.startswith(I->Name);
+      if (Matched)
+        return Prefix.size() + StringRef(I->Name).size();
+    }
   }
   return 0;
 }
@@ -210,7 +224,7 @@ Arg *OptTable::ParseOneArg(const ArgList &Args, unsigned &Index,
     unsigned ArgSize = 0;
     // Scan for first option which is a proper prefix.
     for (; Start != End; ++Start)
-      if ((ArgSize = matchOption(Start, Str)))
+      if ((ArgSize = matchOption(Start, Str, IgnoreCase)))
         break;
     if (Start == End)
       break;

unittests/Option/OptionParsingTest.cpp

@@ -20,7 +20,7 @@ using namespace llvm::opt;
 enum ID {
   OPT_INVALID = 0, // This is not an option ID.
 #define OPTION(PREFIX, NAME, ID, KIND, GROUP, ALIAS, ALIASARGS, FLAGS, PARAM, \
-              HELPTEXT, METAVAR) OPT_##ID,
+               HELPTEXT, METAVAR) OPT_##ID,
 #include "Opts.inc"
   LastOption
 #undef OPTION
@@ -48,8 +48,8 @@ static const OptTable::Info InfoTable[] = {
 namespace {
 class TestOptTable : public OptTable {
 public:
-  TestOptTable()
-    : OptTable(InfoTable, array_lengthof(InfoTable)) {}
+  TestOptTable(bool IgnoreCase = false)
+    : OptTable(InfoTable, array_lengthof(InfoTable), IgnoreCase) {}
 };
 }
 
@@ -157,6 +157,26 @@ TEST(Option, AliasArgs) {
   EXPECT_EQ(AL->getAllArgValues(OPT_B)[1], "bar");
 }
 
+TEST(Option, IgnoreCase) {
+  TestOptTable T(true);
+  unsigned MAI, MAC;
+
+  const char *MyArgs[] = { "-a", "-joo" };
+  OwningPtr<InputArgList> AL(T.ParseArgs(MyArgs, array_endof(MyArgs), MAI, MAC));
+  EXPECT_TRUE(AL->hasArg(OPT_A));
+  EXPECT_TRUE(AL->hasArg(OPT_B));
+}
+
+TEST(Option, DoNotIgnoreCase) {
+  TestOptTable T;
+  unsigned MAI, MAC;
+
+  const char *MyArgs[] = { "-a", "-joo" };
+  OwningPtr<InputArgList> AL(T.ParseArgs(MyArgs, array_endof(MyArgs), MAI, MAC));
+  EXPECT_FALSE(AL->hasArg(OPT_A));
+  EXPECT_FALSE(AL->hasArg(OPT_B));
+}
+
 TEST(Option, SlurpEmpty) {
   TestOptTable T;
   unsigned MAI, MAC;

utils/TableGen/OptParserEmitter.cpp

@@ -13,27 +13,25 @@
 #include "llvm/ADT/Twine.h"
 #include "llvm/TableGen/Record.h"
 #include "llvm/TableGen/TableGenBackend.h"
+#include <cstring>
 #include <map>
+#include <strings.h>
 
 using namespace llvm;
 
+// Ordering on Info. The logic should match with the consumer-side function in
+// llvm/Option/OptTable.h.
 static int StrCmpOptionName(const char *A, const char *B) {
-  char a = *A, b = *B;
-  while (a == b) {
-    if (a == '\0')
-      return 0;
-
-    a = *++A;
-    b = *++B;
+  size_t I = strlen(A);
+  size_t J = strlen(B);
+  if (I == J) {
+    if (int N = strcasecmp(A, B))
+      return N;
+    return strcmp(A, B);
   }
-
-  if (a == '\0') // A is a prefix of B.
-    return 1;
-  if (b == '\0') // B is a prefix of A.
-    return -1;
-
-  // Otherwise lexicographic.
-  return (a < b) ? -1 : 1;
+  if (I < J)
+    return strncasecmp(A, B, I) < 0 ? -1 : 1;
+  return strncasecmp(A, B, J) <= 0 ? -1 : 1;
 }
 
 static int CompareOptionRecords(const void *Av, const void *Bv) {
@@ -50,7 +48,7 @@ static int CompareOptionRecords(const void *Av, const void *Bv) {
   if (!ASent)
     if (int Cmp = StrCmpOptionName(A->getValueAsString("Name").c_str(),
                                    B->getValueAsString("Name").c_str()))
-    return Cmp;
+      return Cmp;
 
   if (!ASent) {
     std::vector<std::string> APrefixes = A->getValueAsListOfStrings("Prefixes");